2 x AMD EPYC 7763 64-Core testing with a AMD DAYTONA_X (RYM1001D BIOS) and ASPEED on Ubuntu 21.04 via the Phoronix Test Suite.
2 x Xeon Platinum 8380 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: 7682GB INTEL SSDPF2KX076TZ, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Desktop: GNOME Shell 3.38.4, Display Server: X Server, OpenGL: 4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits), Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Python 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
Xeon Platinum 8380 Changed Processor to Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads) .
Changed Memory to 252GB .
Xeon Platinum 8380 rest Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Security 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
Intel Xeon Platinum 8380 Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Python 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
8380 1P Processor: Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 252GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED , Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Desktop: GNOME Shell 3.38.4, Display Server: X Server, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
EPYC 7713 Processor: AMD EPYC 7713 64-Core @ 2.00GHz (64 Cores / 128 Threads) , Motherboard: AMD DAYTONA_X (RYM1001D BIOS) , Chipset: AMD Starship/Matisse , Memory: 252GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
EPYC 7713 2P Changed Processor to 2 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads) .
Changed Memory to 504GB .
EPYC 7343 2P xyz Changed Processor to 2 x AMD EPYC 7343 16-Core @ 3.20GHz (32 Cores / 64 Threads) .
EPYC 7443 2P Changed Processor to 2 x AMD EPYC 7443 24-Core @ 2.85GHz (48 Cores / 96 Threads) .
EPYC 7763 Changed Processor to AMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads) .
Changed Memory to 252GB .
EPYC 7763 2P Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads) , Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB , Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1024x768
WRF WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WRF 4.2.2 Input: conus 2.5km Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 4K 8K 12K 16K 20K 18393.74 18356.46 13209.48 13179.61 9822.73 8607.60 8314.77 1. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
Quantum ESPRESSO Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nanoscale. It is based on density-functional theory, plane waves, and pseudopotentials. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Quantum ESPRESSO 6.7 Input: AUSURF112 Xeon Platinum 8380 Intel Xeon Platinum 8380 2 x Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P EPYC 7713 EPYC 7763 400 800 1200 1600 2000 SE +/- 29.35, N = 9 SE +/- 12.08, N = 9 1783.19 1596.34 1169.15 1113.51 1106.65 1083.74 979.14 952.61 937.49 874.49 1. (F9X) gfortran options: -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
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 Xeon Platinum 8380 xyz EPYC 7343 2P Intel Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 2P EPYC 7763 EPYC 7763 2P 2 x Xeon Platinum 8380 700 1400 2100 2800 3500 3085.1 3039.2 3001.9 2993.9 2221.8 2168.0 2036.4 1937.2 1846.8 1. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.32.2 VGR Performance Metric EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 700K 1400K 2100K 2800K 3500K 414247 420308 423324 658980 752076 2411587 3117017 1. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -pthread -ldl -lm
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 2 x Xeon Platinum 8380 150 300 450 600 750 SE +/- 1.68, N = 3 SE +/- 1.68, N = 3 687.41 686.96 583.80 350.74 1. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -pthread -lmpi_cxx -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 EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 130 260 390 520 650 SE +/- 0.44, N = 3 SE +/- 1.61, N = 3 606.17 602.45 556.78 556.32 554.94 404.96 404.31 363.68 300.01 297.02 291.42 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
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 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7713 2P EPYC 7763 2P EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 200 400 600 800 1000 SE +/- 3.53, N = 3 401 402 509 586 593 618 638 639 641 820 MIN: 1 / MAX: 1555 MIN: 1 / MAX: 1549 MIN: 1 / MAX: 1768 MIN: 1 / MAX: 2142 MIN: 1 / MAX: 1707 MIN: 1 / MAX: 1787 MIN: 1 / MAX: 2354 MIN: 1 / MAX: 2861 MIN: 1 / MAX: 2858 MIN: 1 / MAX: 3230
MariaDB This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 512 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 2.75, N = 3 SE +/- 0.76, N = 3 303 359 365 369 377 484 575 664 866 870 -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -shared -lrt -shared -lrt -shared -lrt 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -lz -ldl
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 100, Lossless Compression Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7763 2P EPYC 7713 2P xyz EPYC 7343 2P EPYC 7443 2P 90 180 270 360 450 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 427.16 425.32 413.22 404.65 399.24 388.84 388.00 326.21 325.89 325.65 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
MariaDB This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 256 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 1.84, N = 3 SE +/- 1.12, N = 3 298 343 368 369 375 485 573 697 870 918 -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -llzma -lbz2 -lnuma -lpcre2-8 -lcrypt -lm -lssl -lcrypto -shared -lrt -shared -lrt -shared -lrt 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -lz -ldl
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU EPYC 7713 EPYC 7763 EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7763 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 4.70 5.09 6.12 6.21 6.26 7.11 7.30 8.17
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 EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 8 16 24 32 40 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 18.26 18.38 22.54 22.68 24.92 26.07 29.90 31.16 35.40 35.99 1. (CXX) g++ options: -O3 -pthread -lm
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: bertsquad-10 - Device: OpenMP CPU EPYC 7763 2P EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Xeon Platinum 8380 Intel Xeon Platinum 8380 130 260 390 520 650 SE +/- 8.14, N = 12 SE +/- 6.23, N = 5 305 372 504 509 516 586 605 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
Appleseed Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester EPYC 7763 2P EPYC 7343 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 70 140 210 280 350 331.27 302.43 177.78 148.97 147.80 107.46 106.17
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 EPYC 7713 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 170K 340K 510K 680K 850K SE +/- 5876.97, N = 15 SE +/- 10511.44, N = 3 492943.10 541996.24 758663.03 771533.42 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: super-resolution-10 - Device: OpenMP CPU EPYC 7763 2P EPYC 7343 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 1600 3200 4800 6400 8000 SE +/- 184.76, N = 12 SE +/- 15.90, N = 3 3237 4665 5516 5610 6055 6381 7609 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P EPYC 7763 EPYC 7713 xyz EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 3K 6K 9K 12K 15K SE +/- 5.70, N = 3 SE +/- 404.92, N = 3 7408.86 7452.07 7510.09 7672.39 7726.31 8606.25 9616.47 10078.60 11123.00 12928.80 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 1300 2600 3900 5200 6500 SE +/- 46.19, N = 3 SE +/- 4.90, N = 3 4997.05 5074.56 5108.79 5290.73 5305.67 5416.52 5663.14 5814.51 5815.83 6112.05 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
asmFish This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 60M 120M 180M 240M 300M SE +/- 767934.53, N = 3 SE +/- 1594885.41, N = 12 88559064 89220384 91756880 93143795 130301074 132776390 157634451 171121628 248962318 286644364
OpenFOAM OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 60M 8380 1P Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 EPYC 7763 xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 50 100 150 200 250 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 224.61 224.58 224.44 205.15 204.56 153.40 152.67 134.37 103.61 93.41 89.69 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 95, Compression Effort 7 EPYC 7713 EPYC 7763 EPYC 7713 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 2P 2 x Xeon Platinum 8380 EPYC 7443 2P EPYC 7343 2P xyz 50 100 150 200 250 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 234.27 230.72 226.49 224.44 223.97 223.30 218.16 192.60 192.59 191.82 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
Appleseed Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily EPYC 7763 2P EPYC 7343 2P Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 30 60 90 120 150 151.30 145.22 140.51 140.18 134.83 123.70 123.23
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: LuxCore Benchmark - Acceleration: CPU Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7713 2P EPYC 7763 EPYC 7763 2P 2 4 6 8 10 SE +/- 0.06, N = 15 SE +/- 0.14, N = 15 4.35 4.50 4.52 4.60 6.20 6.89 6.97 7.78 8.04 8.04 MIN: 1.8 / MAX: 5.01 MIN: 1.72 / MAX: 5.53 MIN: 1.65 / MAX: 5.32 MIN: 1.7 / MAX: 5.41 MIN: 2.3 / MAX: 7.29 MIN: 2.38 / MAX: 8.45 MIN: 2.62 / MAX: 8.15 MIN: 2.8 / MAX: 9.32 MIN: 3.14 / MAX: 9.36 MIN: 2.94 / MAX: 9.64
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 40 80 120 160 200 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 195.16 195.10 184.78 133.03 111.80 103.87 64.11
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 rest 20 40 60 80 100 SE +/- 0.06, N = 3 72.4 72.5 76.5 81.9 95.3 95.9 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 270 PRB SISO 256-QAM EPYC 7763 EPYC 7763 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7713 EPYC 7343 2P 30 60 90 120 150 SE +/- 0.12, N = 3 127.9 128.4 131.4 132.2 136.0 146.8 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
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 EPYC 7713 2P EPYC 7763 2P EPYC 7343 2P xyz EPYC 7713 EPYC 7763 EPYC 7443 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 700 1400 2100 2800 3500 SE +/- 2.97, N = 3 SE +/- 68.99, N = 15 3383.89 3332.83 2017.37 1992.82 1432.72 1337.31 1205.04 832.65 813.03 757.06 MIN: 3146.38 MIN: 3132.45 MIN: 1929.36 MIN: 1884.66 MIN: 1404.8 MIN: 1323.18 MIN: 1105.32 MIN: 780.27 MIN: 779.61 MIN: 648.2 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7763 2P 3M 6M 9M 12M 15M SE +/- 63537.44, N = 3 SE +/- 103809.83, N = 15 5452209 6553007 6676556 8822770 9170260 9564590 14481979 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: fcn-resnet101-11 - Device: OpenMP CPU EPYC 7343 2P EPYC 7763 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Xeon Platinum 8380 Intel Xeon Platinum 8380 50 100 150 200 250 SE +/- 1.69, N = 3 SE +/- 1.48, N = 3 61 85 115 119 197 204 206 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
YafaRay YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene 2 x Xeon Platinum 8380 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7763 EPYC 7763 2P EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 2.28, N = 15 SE +/- 1.05, N = 3 81.51 74.90 72.50 67.71 64.53 53.13 51.24 50.89 50.20 49.55 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: yolov4 - Device: OpenMP CPU EPYC 7763 2P EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Xeon Platinum 8380 Intel Xeon Platinum 8380 140 280 420 560 700 SE +/- 5.49, N = 3 SE +/- 2.17, N = 3 217 244 351 357 482 659 661 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -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: Pabellon Barcelona - Compute: CPU-Only Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 40 80 120 160 200 SE +/- 0.11, N = 3 SE +/- 0.02, N = 3 164.01 163.77 140.80 105.65 94.30 87.63 56.86
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.6 Model: shufflenet-v2-10 - Device: OpenMP CPU EPYC 7763 2P EPYC 7343 2P 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 EPYC 7763 2K 4K 6K 8K 10K SE +/- 2.92, N = 3 SE +/- 18.20, N = 3 4276 6458 8402 9037 9056 9776 10130 1. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
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 xyz EPYC 7343 2P Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 EPYC 7443 2P EPYC 7763 EPYC 7713 2P 2 x Xeon Platinum 8380 40 80 120 160 200 SE +/- 0.57, N = 3 SE +/- 0.89, N = 3 163.31 162.99 161.65 161.42 142.97 128.12 119.17 116.12 93.99 81.46 1. (CC) gcc options: -O2 -pthread
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 75, Compression Effort 7 EPYC 7713 EPYC 7763 EPYC 7763 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7443 2P xyz EPYC 7343 2P 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 125.04 124.03 121.38 121.36 120.69 119.70 117.57 102.12 102.04 101.79 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 30 60 90 120 150 SE +/- 0.25, N = 3 SE +/- 0.11, N = 3 142.20 141.61 126.11 91.79 81.12 71.11 41.55
Timed Node.js Compilation This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 30 60 90 120 150 SE +/- 0.25, N = 3 SE +/- 0.22, N = 3 143.46 142.51 127.55 127.48 111.45 102.07 100.73 90.57 77.71 72.27
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 4K EPYC 7763 2P EPYC 7343 2P Xeon Platinum 8380 rest Intel Xeon Platinum 8380 EPYC 7763 EPYC 7713 2 4 6 8 10 SE +/- 0.00, N = 3 5.48 5.66 5.67 5.67 5.98 6.15 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 13K 26K 39K 52K 65K SE +/- 71.21, N = 3 SE +/- 253.99, N = 12 58467.7 57591.0 51892.7 50709.6 46372.4 44203.8 41857.4 34155.0 33497.3 31369.9
Appleseed Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7763 2P 20 40 60 80 100 77.52 77.16 68.74 62.49 57.40 56.33 47.56
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 5 Mode: CPU Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 14K 28K 42K 56K 70K SE +/- 131.93, N = 3 SE +/- 308.74, N = 3 35107 35347 35627 46864 58824 66328
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate EPYC 7713 2P EPYC 7763 2P EPYC 7343 2P xyz EPYC 7443 2P EPYC 7763 EPYC 7713 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 5.94, N = 10 SE +/- 11.50, N = 3 563 571 605 674 682 686 690 753 841 867 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU xyz EPYC 7343 2P EPYC 7713 EPYC 7713 2P Intel Xeon Platinum 8380 EPYC 7763 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7763 2P 8 16 24 32 40 SE +/- 0.21, N = 3 SE +/- 0.33, N = 3 24.18 25.01 28.56 28.70 29.94 30.34 31.06 33.43 34.09
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Magi Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 1400 2800 4200 5600 7000 SE +/- 12.34, N = 15 SE +/- 39.37, N = 15 1346.63 1350.20 1652.75 2216.20 2496.14 2950.67 3057.65 3651.80 5450.89 6731.08 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Myriad-Groestl xyz EPYC 7343 2P EPYC 7443 2P EPYC 7763 Xeon Platinum 8380 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 EPYC 7713 2P EPYC 7763 2P 90K 180K 270K 360K 450K SE +/- 5943.89, N = 15 SE +/- 1515.66, N = 15 8306.91 8510.60 10010.00 40210.00 75707.00 84872.00 127280.00 180280.00 203240.00 426060.00 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Deepcoin EPYC 7343 2P xyz Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 20K 40K 60K 80K 100K SE +/- 1301.01, N = 15 SE +/- 2190.61, N = 15 30020 30120 33583 42720 49410 66780 66810 75061 104940 116180 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
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 EPYC 7713 2P 8380 1P EPYC 7763 2P Intel Xeon Platinum 8380 EPYC 7763 EPYC 7343 2P xyz 2 x Xeon Platinum 8380 EPYC 7713 Xeon Platinum 8380 EPYC 7443 2P 12 24 36 48 60 SE +/- 0.66, N = 3 SE +/- 0.81, N = 15 52.37 52.18 52.16 50.89 49.05 48.18 47.78 47.44 45.38 44.02 43.94 1. (CXX) g++ options: -O2 -lOpenCL
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7763 2P EPYC 7713 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 20K 40K 60K 80K 100K SE +/- 65.86, N = 3 SE +/- 433.14, N = 7 81701.5 80455.7 79233.1 75301.5 61526.1 57071.1 51914.6 51710.2 51314.0 47974.6
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: u8s8f32 - Engine: CPU EPYC 7763 2P EPYC 7713 2P xyz EPYC 7343 2P EPYC 7713 EPYC 7763 EPYC 7443 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 700 1400 2100 2800 3500 SE +/- 2.62, N = 3 SE +/- 0.92, N = 3 3445.50 3329.21 2051.05 2038.41 1421.50 1321.85 1170.48 821.59 810.36 675.12 MIN: 3192.29 MIN: 2854.93 MIN: 1948.41 MIN: 1925.93 MIN: 1392.12 MIN: 1309.31 MIN: 1105.02 MIN: 782.27 MIN: 779.4 MIN: 649.43 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: f32 - Engine: CPU EPYC 7763 2P EPYC 7713 2P xyz EPYC 7343 2P EPYC 7713 EPYC 7763 EPYC 7443 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 700 1400 2100 2800 3500 SE +/- 4.02, N = 3 SE +/- 2.14, N = 3 3355.77 3316.69 2037.27 1987.61 1426.74 1332.37 1172.40 823.73 812.26 675.16 MIN: 3132.45 MIN: 3107.51 MIN: 1959.13 MIN: 1916.12 MIN: 1390.97 MIN: 1314.96 MIN: 1101.74 MIN: 781.13 MIN: 778.91 MIN: 645.81 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 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 300 600 900 1200 1500 SE +/- 1.74, N = 3 SE +/- 2.16, N = 3 1457.60 1261.97 904.57 884.36 803.50 687.55 628.49 482.10 475.86 441.26 MIN: 1122.23 MIN: 1067.08 MIN: 795.56 MIN: 795.98 MIN: 706.72 MIN: 675.02 MIN: 610.75 MIN: 463.53 MIN: 461.87 MIN: 423.47 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 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7443 2P EPYC 7343 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 300 600 900 1200 1500 SE +/- 1.28, N = 3 SE +/- 1.03, N = 3 1518.83 1286.87 890.87 846.34 833.51 686.95 630.64 488.71 476.02 439.37 MIN: 1378.98 MIN: 1043.85 MIN: 789.94 MIN: 710.12 MIN: 771.64 MIN: 675.22 MIN: 615.71 MIN: 463.86 MIN: 462.14 MIN: 423.06 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: bf16bf16bf16 - Engine: CPU EPYC 7763 2P EPYC 7713 2P xyz EPYC 7443 2P EPYC 7343 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 300 600 900 1200 1500 SE +/- 0.97, N = 3 SE +/- 2.02, N = 3 1533.59 1322.33 891.27 870.63 853.32 688.72 627.44 485.53 476.21 439.64 MIN: 1351.18 MIN: 1114.39 MIN: 785.62 MIN: 716.01 MIN: 797.12 MIN: 676.89 MIN: 611.79 MIN: 463.97 MIN: 462.69 MIN: 422.12 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
PlaidML This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU xyz EPYC 7343 2P EPYC 7713 2P EPYC 7713 Intel Xeon Platinum 8380 EPYC 7763 EPYC 7763 2P Xeon Platinum 8380 2 x Xeon Platinum 8380 9 18 27 36 45 SE +/- 0.12, N = 3 SE +/- 0.31, N = 3 27.72 28.64 32.34 34.30 35.38 35.93 36.47 36.97 38.51
KTX-Software toktx This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 4 + Zstd Compression 19 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 20 40 60 80 100 SE +/- 0.27, N = 3 SE +/- 0.33, N = 3 102.13 102.03 91.20 91.17 67.85 66.59 60.83 54.92 41.58 35.46
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Blake-2 S EPYC 7343 2P xyz Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7443 2P EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7763 2P 900K 1800K 2700K 3600K 4500K SE +/- 117578.84, N = 12 SE +/- 58124.19, N = 12 2213910 2254660 2476303 2546270 3054050 3177080 3245100 3555670 3662348 4256830 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Skeincoin Xeon Platinum 8380 xyz EPYC 7343 2P Intel Xeon Platinum 8380 EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P 200K 400K 600K 800K 1000K SE +/- 23435.25, N = 12 SE +/- 19372.86, N = 12 407502 431810 435040 440310 531530 631030 643780 774163 982180 1106220 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: LBC, LBRY Credits EPYC 7343 2P xyz Intel Xeon Platinum 8380 EPYC 7443 2P EPYC 7763 EPYC 7713 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P 110K 220K 330K 440K 550K SE +/- 7613.62, N = 12 SE +/- 30611.01, N = 12 160220 161340 246000 247120 252310 253250 273780 402726 523470 526390 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
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 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 6M 12M 18M 24M 30M SE +/- 65507.38, N = 3 SE +/- 89609.36, N = 3 19731206 20813699 21114470 22695700 22830009 22881706 23355917 28998877 29092155 29143044 MIN: 960805 / MAX: 89356968 MIN: 964776 / MAX: 99594360 MIN: 902017 / MAX: 99609552 MIN: 883235 / MAX: 123906384 MIN: 842629 / MAX: 128294928 MIN: 890537 / MAX: 124630704 MIN: 848021 / MAX: 132591888 MIN: 1042294 / MAX: 173633256 MIN: 1047483 / MAX: 175929480 MIN: 1069452 / MAX: 176387184
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync EPYC 7343 2P EPYC 7713 EPYC 7713 2P EPYC 7763 2P EPYC 7763 Xeon Platinum 8380 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 100K 200K 300K 400K 500K SE +/- 985.63, N = 3 SE +/- 556.11, N = 3 152724 262453 265590 287088 379006 481504 482191 482217 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.10, N = 3 74.51 74.49 62.29 51.03 46.22 44.45 30.59
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 150M 300M 450M 600M 750M SE +/- 1359270.00, N = 3 SE +/- 1003430.17, N = 3 180764311 182180961 224736339 308507452 342349258 373831966 607030517 679371429 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Orange Juice - Acceleration: CPU xyz EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.14, N = 3 8.67 8.76 8.88 8.95 11.86 11.86 13.20 14.33 18.17 22.07 MIN: 7.68 / MAX: 9.24 MIN: 7.75 / MAX: 9.34 MIN: 7.54 / MAX: 10.04 MIN: 7.51 / MAX: 10.05 MIN: 10.29 / MAX: 13.3 MIN: 10.28 / MAX: 13.38 MIN: 11.71 / MAX: 15.71 MIN: 11.53 / MAX: 18.29 MIN: 15.71 / MAX: 24.37 MIN: 18.9 / MAX: 28.94
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Danish Mood - Acceleration: CPU xyz EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 4.21 4.25 4.34 4.42 5.78 6.28 6.97 7.36 7.57 8.47 MIN: 1.65 / MAX: 4.88 MIN: 1.71 / MAX: 4.9 MIN: 1.86 / MAX: 5.01 MIN: 1.74 / MAX: 5.11 MIN: 2.31 / MAX: 6.74 MIN: 2.49 / MAX: 7.32 MIN: 3.13 / MAX: 8.11 MIN: 3.08 / MAX: 8.56 MIN: 2.87 / MAX: 9.18 MIN: 3.97 / MAX: 10.18
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7713 2P EPYC 7763 2P EPYC 7763 1.1466 2.2932 3.4398 4.5864 5.733 SE +/- 0.007, N = 3 SE +/- 0.036, N = 3 1.848 1.859 1.985 1.993 2.075 4.734 4.755 4.844 4.974 5.096 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 200K 400K 600K 800K 1000K SE +/- 276.22, N = 3 SE +/- 1484.41, N = 3 1026060 1024320 885657 868189 766395 621532 585507 572750 413728 409402
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 300K 600K 900K 1200K 1500K SE +/- 1036.96, N = 3 SE +/- 2539.56, N = 3 1180890 1178463 1002310 965493 848232 668653 666967 635253 600810 519356
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: DLSC - Acceleration: CPU Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.08, N = 3 5.49 5.50 5.66 5.66 7.90 8.32 9.41 9.53 13.75 16.31 MIN: 5.31 / MAX: 6.18 MIN: 5.29 / MAX: 6.23 MIN: 5.51 / MAX: 6.22 MIN: 5.51 / MAX: 6.24 MIN: 7.67 / MAX: 8.99 MIN: 8.19 / MAX: 9.08 MIN: 8.72 / MAX: 12.17 MIN: 9.35 / MAX: 10.11 MIN: 13.42 / MAX: 15.46 MIN: 16.04 / MAX: 18.7
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 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7443 2P EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 30K 60K 90K 120K 150K SE +/- 82.87, N = 3 SE +/- 439.19, N = 3 152020.0 148809.0 126429.0 122773.0 90625.0 87000.9 81669.1 78070.1 74702.4 71891.6
7-Zip Compression This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 110K 220K 330K 440K 550K SE +/- 596.42, N = 3 SE +/- 3489.62, N = 3 200732 201596 203911 204915 278846 290307 334626 355140 453486 515282 1. (CXX) g++ options: -pipe -lpthread
TensorFlow Lite This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 12K 24K 36K 48K 60K SE +/- 122.59, N = 3 SE +/- 83.39, N = 3 57520.4 56410.0 53677.1 52703.7 47630.1 45773.4 40180.5 32738.9 30357.7 28959.5
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 xyz EPYC 7343 2P EPYC 7713 Intel Xeon Platinum 8380 EPYC 7443 2P Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7763 2P 2M 4M 6M 8M 10M SE +/- 15762.12, N = 3 SE +/- 14502.87, N = 3 3595000 3703000 5118000 5163000 5179000 5305667 5769000 9650000 10200000 10874000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen xyz EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 200 400 600 800 1000 SE +/- 1.45, N = 3 358 361 368 370 479 494 576 672 778 882 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7713 2P Intel Xeon Platinum 8380 EPYC 7763 EPYC 7763 2P Xeon Platinum 8380 2 x Xeon Platinum 8380 160 320 480 640 800 SE +/- 2.33, N = 3 SE +/- 2.03, N = 3 412 420 482 535 553 567 569 584 586 732 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Intel Xeon Platinum 8380 xyz EPYC 7343 2P Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 300 600 900 1200 1500 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 629 629 630 641 826 879 1023 1125 1328 1471 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space EPYC 7713 2P EPYC 7763 2P EPYC 7343 2P EPYC 7713 xyz EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 200 400 600 800 1000 SE +/- 2.33, N = 3 623 642 698 741 746 757 773 1042 1093 1159 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7763 2P 500 1000 1500 2000 2500 SE +/- 0.67, N = 3 SE +/- 4.10, N = 3 1406 1406 1425 1452 1742 1816 2120 2185 2191 2293 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Build2 This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 EPYC 7343 2P xyz EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P EPYC 7443 2P 15 30 45 60 75 SE +/- 0.25, N = 3 SE +/- 0.32, N = 3 67.39 67.16 60.45 58.81 58.57 58.21 57.64 54.29 54.12 53.81
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: Garlicoin EPYC 7343 2P xyz EPYC 7443 2P EPYC 7763 EPYC 7713 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 9K 18K 27K 36K 45K SE +/- 181.40, N = 4 SE +/- 585.01, N = 15 7522.57 7546.82 10710.00 14760.00 14820.00 15618.00 19310.00 27980.00 29100.00 41269.00 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Intel Xeon Platinum 8380 EPYC 7763 2P Xeon Platinum 8380 rest EPYC 7763 EPYC 7713 EPYC 7343 2P 30 60 90 120 150 SE +/- 0.60, N = 3 127.1 128.3 129.6 130.2 135.7 147.0 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P 90 180 270 360 450 SE +/- 0.12, N = 3 304.8 305.6 373.0 375.8 391.9 423.2 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.15.5 Algorithm: x25x Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 1000 2000 3000 4000 5000 SE +/- 14.01, N = 3 SE +/- 50.45, N = 15 1022.32 1036.39 1056.29 1069.35 1583.99 1621.67 1689.22 2725.03 4127.84 4539.44 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
ebizzy This is a test of ebizzy, a program to generate workloads resembling web server workloads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz 2 x Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 700K 1400K 2100K 2800K 3500K SE +/- 17257.96, N = 15 SE +/- 19700.68, N = 15 1215587 1250548 1929281 2035986 2061987 2152796 2343849 2722832 2983612 3292270 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
Timed Godot Game Engine Compilation This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7713 2P EPYC 7763 2P EPYC 7713 EPYC 7763 EPYC 7443 2P 2 x Xeon Platinum 8380 13 26 39 52 65 SE +/- 0.18, N = 3 SE +/- 0.08, N = 3 56.79 56.58 55.54 55.05 54.60 52.22 51.51 48.85 48.55 48.07
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: vklBenchmarkStructuredVolume xyz EPYC 7343 2P EPYC 7443 2P Intel Xeon Platinum 8380 2 x Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 2P EPYC 7713 EPYC 7763 2P EPYC 7763 20M 40M 60M 80M 100M SE +/- 177762.64, N = 3 SE +/- 47834.23, N = 3 90357350 91207878 94729627 103982528 104922070 105023963 105283002 112140810 112216063 112590670 MIN: 1086860 / MAX: 822732120 MIN: 1087105 / MAX: 936742536 MIN: 1095792 / MAX: 889815816 MIN: 1363161 / MAX: 855550476 MIN: 1391949 / MAX: 891929412 MIN: 1379843 / MAX: 899785764 MIN: 995486 / MAX: 1002199248 MIN: 1010309 / MAX: 1234899288 MIN: 969158 / MAX: 1170792936 MIN: 948977 / MAX: 1160124336
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P 30 60 90 120 150 SE +/- 2.67, N = 3 104.2 110.1 121.1 122.7 127.8 139.0 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P 80 160 240 320 400 SE +/- 0.25, N = 3 278.4 279.9 340.2 342.5 357.3 385.4 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 8380 1P xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 16 32 48 64 80 SE +/- 0.66, N = 3 SE +/- 0.24, N = 3 71.99 71.88 71.28 60.29 60.15 45.68 43.76 41.55 39.07 26.09 23.52 1. (CXX) g++ options: -O2 -lOpenCL
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 0 - Input: Bosphorus 1080p EPYC 7763 2P Xeon Platinum 8380 rest Intel Xeon Platinum 8380 EPYC 7763 EPYC 7343 2P EPYC 7713 3 6 9 12 15 SE +/- 0.01, N = 3 11.60 11.80 11.80 12.65 12.99 13.17 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P 2 x Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 12K 24K 36K 48K 60K SE +/- 6.99, N = 3 SE +/- 67.30, N = 3 14658.2 14707.2 20728.4 26504.2 27726.9 28019.1 31200.3 50981.4 56689.3 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Kripke Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 EPYC 7343 2P EPYC 7763 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 60M 120M 180M 240M 300M SE +/- 953041.14, N = 3 SE +/- 1334158.46, N = 15 117265000 139185600 175168000 175890300 178965233 272389100 286104000 1. (CXX) g++ options: -O3 -fopenmp
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 4K EPYC 7763 2P EPYC 7343 2P EPYC 7763 EPYC 7713 Xeon Platinum 8380 rest Intel Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.07, N = 3 11.29 11.97 13.66 13.84 13.97 13.99 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 12 24 36 48 60 SE +/- 0.09, N = 3 SE +/- 0.23, N = 3 51.05 50.74 46.02 35.53 32.19 28.24 21.05
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 20.96 20.91 20.30 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
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 xyz EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 EPYC 7443 2P EPYC 7763 EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7763 2P 3 6 9 12 15 SE +/- 0.010, N = 3 SE +/- 0.005, N = 3 3.029 3.992 5.011 5.017 5.103 5.173 5.640 8.545 9.063 10.146 1. (CXX) g++ options: -O3 -pthread
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 700K 1400K 2100K 2800K 3500K SE +/- 1975.05, N = 3 SE +/- 1412.48, N = 3 1190387.62 1206142.70 1447390.74 1448947.25 1976325.27 1986960.57 2112124.09 2365407.62 3054345.88 3263224.98 1. (CC) gcc options: -O2 -lrt" -lrt
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7343 2P xyz EPYC 7763 EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 10K 20K 30K 40K 50K SE +/- 49.28, N = 3 SE +/- 93.94, N = 3 10495.8 10580.9 20662.0 22096.5 23854.1 24408.9 24696.1 28113.8 42840.1 48256.7 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7343 2P xyz EPYC 7763 EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 10K 20K 30K 40K 50K SE +/- 37.57, N = 3 SE +/- 73.04, N = 3 9174.67 9239.59 18222.50 20580.00 20991.70 20991.70 22571.70 25393.10 40368.60 45143.30 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Timed Wasmer Compilation This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile EPYC 7763 2P EPYC 7713 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P 10 20 30 40 50 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 42.24 42.05 41.66 40.51 37.69 37.68 37.54 37.27 36.78 36.00 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Samples / Second, More Is Better srsRAN 21.04 Test: OFDM_Test EPYC 7763 2P EPYC 7763 EPYC 7713 Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7343 2P 30M 60M 90M 120M 150M SE +/- 305505.05, N = 3 111500000 113400000 119400000 120300000 120400000 125900000 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 1.2242 2.4484 3.6726 4.8968 6.121 SE +/- 0.01029, N = 3 SE +/- 0.00173, N = 3 5.44095 5.37652 3.25912 MIN: 5.25 MIN: 5.25 MIN: 3.09 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: f32 - Engine: CPU EPYC 7713 2P EPYC 7763 2P EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 xyz EPYC 7343 2P Xeon Platinum 8380 Intel Xeon Platinum 8380 6 12 18 24 30 SE +/- 0.01372, N = 3 SE +/- 0.21071, N = 12 26.76670 25.69790 8.07087 7.62671 7.20659 6.96910 5.88417 5.85031 4.51612 3.63762 MIN: 20.7 MIN: 19.39 MIN: 6.19 MIN: 5.86 MIN: 5.67 MIN: 6.54 MIN: 4.74 MIN: 4.66 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P EPYC 7763 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 0.324 0.648 0.972 1.296 1.62 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.57 0.57 0.70 0.77 0.82 0.85 0.85 1.11 1.25 1.44
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7713 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 10K 20K 30K 40K 50K SE +/- 73.93, N = 3 SE +/- 97.10, N = 3 21723.1 21752.4 23489.6 23539.9 31580.6 35892.5 41535.1 42337.0 42770.8 48042.3 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
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: u8s8f32 - Engine: CPU EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 0.4273 0.8546 1.2819 1.7092 2.1365 SE +/- 0.010254, N = 9 SE +/- 0.006531, N = 15 1.899320 1.617540 1.525700 1.267000 1.225780 1.152590 0.961258 0.947461 0.918737 0.872017 MIN: 1.2 MIN: 1.31 MIN: 1.29 MIN: 0.86 MIN: 1 MIN: 0.94 MIN: 0.76 MIN: 0.75 MIN: 0.77 MIN: 0.77 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.5 Scene: Rainbow Colors and Prism - Acceleration: CPU EPYC 7343 2P Intel Xeon Platinum 8380 xyz 2 x Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P EPYC 7713 EPYC 7763 EPYC 7443 2P 5 10 15 20 25 SE +/- 0.63, N = 15 SE +/- 0.27, N = 15 12.28 13.35 13.51 14.11 14.39 16.43 16.82 17.16 19.00 19.71 MIN: 11.34 / MAX: 12.53 MIN: 12.25 / MAX: 13.95 MIN: 13.44 / MAX: 13.59 MIN: 10.63 / MAX: 19.45 MIN: 12.31 / MAX: 19.48 MIN: 15.11 / MAX: 16.69 MIN: 16.75 / MAX: 16.9 MIN: 15.7 / MAX: 17.4 MIN: 17.35 / MAX: 19.31 MIN: 17.96 / MAX: 20
OpenFOAM OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 8 Input: Motorbike 30M EPYC 7343 2P xyz Xeon Platinum 8380 8380 1P Intel Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 10 20 30 40 50 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 43.38 36.94 23.49 23.42 23.39 20.99 19.77 17.45 16.45 15.26 14.30 1. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.92 1.84 2.76 3.68 4.6 SE +/- 0.02087, N = 4 SE +/- 0.00418, N = 4 4.08878 4.03139 2.99485 MIN: 3.19 MIN: 3.2 MIN: 2.85 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 40K 80K 120K 160K 200K SE +/- 132.64, N = 3 SE +/- 139.20, N = 3 60339 60553 65894 68981 96966 98002 109440 118869 183183 188774 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Aircrack-ng Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.5.2 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 90K 180K 270K 360K 450K SE +/- 128.50, N = 3 SE +/- 353.02, N = 3 105477.35 105738.89 136235.31 136488.77 186439.73 191730.77 208121.13 211019.99 369821.88 414484.41 1. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -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 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 EPYC 7713 2P EPYC 7763 xyz EPYC 7343 2P EPYC 7443 2P 7 14 21 28 35 SE +/- 0.18, N = 3 SE +/- 0.31, N = 3 30.55 30.53 29.69 29.26 29.19 29.08 28.42 27.99 27.88 25.95 1. (CXX) g++ options: -O3 -fPIC -lm
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D EPYC 7343 2P xyz EPYC 7713 Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 2K 4K 6K 8K 10K SE +/- 12.97, N = 3 SE +/- 95.83, N = 5 3258.13 3260.32 4457.54 4588.57 4592.89 4593.84 4754.63 5008.84 8890.34 9689.54 9906.97 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P Xeon Platinum 8380 rest Intel Xeon Platinum 8380 16 32 48 64 80 SE +/- 0.21, N = 3 55.4 55.5 58.1 63.2 71.4 71.7 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8380 rest Intel Xeon Platinum 8380 EPYC 7763 EPYC 7763 2P EPYC 7713 EPYC 7343 2P 30 60 90 120 150 SE +/- 0.52, N = 3 98.3 99.1 116.5 117.1 123.3 130.1 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.4 Preset: Exhaustive Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 32.68 32.49 30.00 29.99 22.43 22.33 20.10 16.64 12.49 10.57 1. (CXX) g++ options: -O3 -flto -pthread
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P 50 100 150 200 250 SE +/- 0.49, N = 3 203.4 207.5 217.4 219.4 231.1 245.4 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P 90 180 270 360 450 SE +/- 1.16, N = 3 295.9 306.8 371.5 374.6 392.5 419.4 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Intel Xeon Platinum 8380 Xeon Platinum 8380 8380 1P EPYC 7713 EPYC 7763 xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P 20K 40K 60K 80K 100K SE +/- 75.47, N = 3 SE +/- 74.38, N = 4 37582.44 37645.41 37872.10 51913.52 52076.01 67834.56 69238.03 71298.76 92499.87 112813.92 113445.30 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.2244 0.4488 0.6732 0.8976 1.122 SE +/- 0.001560, N = 4 SE +/- 0.001365, N = 4 0.997116 0.960174 0.604378 MIN: 0.92 MIN: 0.91 MIN: 0.56 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 Obj xyz EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7713 2P EPYC 7763 2P EPYC 7763 2 x Xeon Platinum 8380 16 32 48 64 80 SE +/- 0.12, N = 3 SE +/- 0.27, N = 3 34.64 34.71 39.80 39.99 42.68 56.02 57.10 59.86 60.93 72.45 MIN: 34.38 / MAX: 35.22 MIN: 34.47 / MAX: 35.56 MIN: 38.22 / MAX: 44.71 MIN: 38.39 / MAX: 44.94 MIN: 42.1 / MAX: 45.52 MIN: 55 / MAX: 58.09 MIN: 53.94 / MAX: 59.96 MIN: 56.57 / MAX: 64.49 MIN: 59.68 / MAX: 63.26 MIN: 62.12 / MAX: 82.66
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P 50 100 150 200 250 SE +/- 0.03, N = 3 174.2 174.3 186.0 189.0 197.1 212.6 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 21.04 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7343 2P 80 160 240 320 400 SE +/- 0.45, N = 3 268.2 273.2 341.6 343.1 355.6 388.4 -mavx512f -mavx512cd -mavx512bw -mavx512dq -mavx512f -mavx512cd -mavx512bw -mavx512dq 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 2 x Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.04039, N = 5 SE +/- 0.05061, N = 8 9.15446 9.04144 5.73331 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj EPYC 7343 2P xyz EPYC 7443 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 EPYC 7713 2P EPYC 7763 EPYC 7763 2P 2 x Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.40, N = 3 31.56 31.60 40.44 50.02 50.10 50.19 57.70 57.74 58.45 89.62 MIN: 31.36 / MAX: 31.94 MIN: 31.37 / MAX: 32.52 MIN: 39.84 / MAX: 42.58 MIN: 46.7 / MAX: 53.93 MIN: 46.69 / MAX: 54.05 MIN: 49.37 / MAX: 52.05 MIN: 54.01 / MAX: 61.75 MIN: 56.71 / MAX: 59.43 MIN: 54.87 / MAX: 64.29 MIN: 70.4 / MAX: 98.44
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 EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 70M 140M 210M 280M 350M SE +/- 570049.11, N = 3 SE +/- 1599896.72, N = 3 91112345 91338853 94073662 94879448 134632597 145906191 176135880 180945380 270723204 321187870 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
Algebraic Multi-Grid Benchmark AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 EPYC 7443 2P EPYC 7343 2P xyz EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 400M 800M 1200M 1600M 2000M SE +/- 408650.35, N = 3 SE +/- 1152755.01, N = 3 1007308000 1011973000 1082117000 1083897000 1084411667 1656214000 1660998000 1682638000 1905866000 1925810000 2082103333 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi
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 EPYC 7343 2P xyz Xeon Platinum 8380 Intel Xeon Platinum 8380 8380 1P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 0.1345 0.269 0.4035 0.538 0.6725 SE +/- 0.00101, N = 3 SE +/- 0.00027, N = 3 0.59757 0.59454 0.51889 0.51829 0.51702 0.45265 0.44068 0.38261 0.27064 0.27020 0.22104
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.4595 0.919 1.3785 1.838 2.2975 SE +/- 0.00210, N = 5 SE +/- 0.00217, N = 5 2.04221 2.02106 1.81271 MIN: 1.72 MIN: 1.69 MIN: 1.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7763 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 14 28 42 56 70 SE +/- 0.05, N = 3 SE +/- 0.11, N = 4 21.37 21.80 22.03 22.12 23.10 55.67 56.59 57.42 57.96 61.72 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
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: BT.C xyz EPYC 7343 2P Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 60K 120K 180K 240K 300K SE +/- 204.16, N = 3 SE +/- 236.31, N = 4 108305.07 108369.25 116983.50 117289.05 117333.47 129191.01 135693.32 138431.97 198052.38 238582.42 256807.60 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9 video format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.10.0 Speed: Speed 5 - Input: Bosphorus 1080p EPYC 7763 EPYC 7763 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7713 EPYC 7343 2P 7 14 21 28 35 SE +/- 0.02, N = 3 25.16 25.17 25.30 25.46 26.43 28.30 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=gnu++11
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: bf16bf16bf16 - Engine: CPU Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.9117 1.8234 2.7351 3.6468 4.5585 SE +/- 0.00912, N = 7 SE +/- 0.00172, N = 7 4.05180 4.02680 2.08924 MIN: 3.98 MIN: 3.98 MIN: 2.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 EPYC 7763 2P EPYC 7713 2P EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 Xeon Platinum 8380 Intel Xeon Platinum 8380 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 23.41 24.47 25.43 25.59 26.34 26.39 28.65 29.81 31.23 31.26 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
TTSIOD 3D Renderer A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping EPYC 7763 2P EPYC 7713 2P xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 2 x Xeon Platinum 8380 Xeon Platinum 8380 300 600 900 1200 1500 SE +/- 13.05, N = 3 SE +/- 3.16, N = 3 529.05 598.91 617.09 667.42 718.13 1200.48 1237.93 1317.18 1354.59 1356.01 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
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: u8s8f32 - Engine: CPU EPYC 7763 2P EPYC 7713 2P xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 0.1995 0.399 0.5985 0.798 0.9975 SE +/- 0.001200, N = 3 SE +/- 0.000930, N = 3 0.886478 0.840544 0.815109 0.787616 0.667261 0.632602 0.586786 0.363977 0.344966 0.343258 MIN: 0.76 MIN: 0.78 MIN: 0.69 MIN: 0.7 MIN: 0.61 MIN: 0.59 MIN: 0.56 MIN: 0.32 MIN: 0.3 MIN: 0.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Exhaustive EPYC 7343 2P Xeon Platinum 8380 rest Intel Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7763 2P 5 10 15 20 25 SE +/- 0.0241, N = 3 20.9268 19.5959 19.5906 14.6599 12.9989 6.5794 1. (CXX) g++ options: -O3 -flto -pthread
Tachyon This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 6 12 18 24 30 SE +/- 0.0744, N = 3 SE +/- 0.0495, N = 4 26.8736 26.8592 24.8002 24.4027 18.0213 17.5416 15.9955 13.6825 10.2908 8.8141 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 1300M 2600M 3900M 5200M 6500M SE +/- 2451530.13, N = 3 SE +/- 284800.12, N = 3 1579300000 1582500000 2067100000 2075100000 2736900000 2876400000 3036600000 3086533333 5241800000 5898900000 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 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 1200M 2400M 3600M 4800M 6000M SE +/- 3090487.20, N = 3 SE +/- 4603018.33, N = 3 1565266667 1565800000 2043100000 2045300000 2735000000 2855000000 3033500000 3279266667 5160800000 5816700000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 6K 12K 18K 24K 30K SE +/- 55.43, N = 3 SE +/- 75.18, N = 3 8708.9 8726.8 8767.3 8768.9 12524.0 12617.3 14245.0 17835.8 24950.9 28443.0 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
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: 64 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7713 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 700M 1400M 2100M 2800M 3500M SE +/- 1039764.93, N = 3 SE +/- 4053941.84, N = 3 1654066667 1662300000 2028700000 2029700000 2597700000 2704000000 2823900000 2927600000 3047333333 3122100000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
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 Xeon Platinum 8380 8380 1P Intel Xeon Platinum 8380 EPYC 7713 EPYC 7763 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.02, N = 4 24.04 24.00 23.97 22.37 22.10 18.28 18.06 15.03 11.15 11.10 11.06 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 12 24 36 48 60 SE +/- 0.06, N = 3 SE +/- 0.32, N = 3 23.57 23.70 28.28 28.67 34.86 37.48 37.49 40.17 50.72 53.68 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Timed Mesa Compilation This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7443 2P EPYC 7763 2P 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 22.12 21.79 19.43 19.27 19.14 18.71 18.29 17.02 16.93 16.85
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 0.6705 1.341 2.0115 2.682 3.3525 SE +/- 0.00, N = 3 SE +/- 0.00, N = 5 1.13 1.14 1.43 1.54 1.66 1.77 1.78 2.25 2.52 2.98
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 0.6728 1.3456 2.0184 2.6912 3.364 SE +/- 0.00, N = 3 SE +/- 0.00, N = 5 1.13 1.14 1.43 1.54 1.66 1.79 1.79 2.23 2.56 2.99
Basis Universal Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 3 Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7443 2P EPYC 7763 EPYC 7713 2P EPYC 7763 2P 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.04, N = 4 22.96 22.87 19.16 19.07 15.78 15.51 15.11 14.97 11.67 11.45 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Second, More Is Better ASKAP 1.0 Test: Hogbom Clean OpenMP EPYC 7713 2P EPYC 7763 2P EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 300 600 900 1200 1500 SE +/- 11.55, N = 4 SE +/- 14.64, N = 4 307.69 327.87 337.84 340.14 350.88 497.51 515.46 1238.71 1250.00 1266.33 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster xyz EPYC 7343 2P 2 x Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P EPYC 7443 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 8380 1P EPYC 7713 EPYC 7763 2 4 6 8 10 SE +/- 0.063, N = 15 SE +/- 0.063, N = 15 8.332 7.917 7.652 7.009 7.008 6.870 6.797 6.762 6.697 5.684 5.602 1. (CXX) g++ options: -O2 -lOpenCL
LULESH LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 EPYC 7713 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 xyz EPYC 7443 2P EPYC 7343 2P EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7763 2P 8K 16K 24K 32K 40K SE +/- 16.09, N = 5 SE +/- 62.90, N = 4 14625.72 18688.07 18779.65 18986.86 23445.30 23594.29 23765.14 33312.13 35311.85 36504.82 1. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7713 xyz 2 x Xeon Platinum 8380 EPYC 7343 2P EPYC 7763 EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 12 24 36 48 60 SE +/- 0.02, N = 3 SE +/- 0.19, N = 4 27.42 27.57 37.23 38.57 38.71 38.94 40.28 45.10 51.61 53.22 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Pennant Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig 8380 1P Xeon Platinum 8380 Intel Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P EPYC 7763 EPYC 7713 2P EPYC 7763 2P 6 12 18 24 30 SE +/- 0.015026, N = 3 SE +/- 0.010712, N = 4 23.843380 23.843000 23.787280 14.413790 14.053590 14.023940 11.039630 10.598630 9.849013 5.856924 5.250010 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -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: IP Shapes 1D - Data Type: f32 - Engine: CPU EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P EPYC 7443 2P Intel Xeon Platinum 8380 EPYC 7713 Xeon Platinum 8380 EPYC 7763 2 x Xeon Platinum 8380 0.4444 0.8888 1.3332 1.7776 2.222 SE +/- 0.000855, N = 4 SE +/- 0.003790, N = 4 1.974910 1.797060 1.510840 1.410220 1.314690 1.295130 1.216750 1.212030 1.117940 0.914865 MIN: 1.77 MIN: 1.6 MIN: 1.12 MIN: 1.14 MIN: 1.13 MIN: 1.16 MIN: 1.15 MIN: 1.16 MIN: 1.06 MIN: 0.85 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
CloverLeaf CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm.in input file (Problem 5). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics EPYC 7443 2P xyz EPYC 7343 2P 8380 1P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 5 10 15 20 25 SE +/- 0.01, N = 4 SE +/- 0.04, N = 5 21.69 20.84 19.30 16.14 16.10 15.92 15.13 14.43 12.08 11.39 10.08 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
miniFE MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P 2 x Xeon Platinum 8380 EPYC 7443 2P 6K 12K 18K 24K 30K SE +/- 13.81, N = 4 SE +/- 90.91, N = 4 21813.7 21869.2 23015.8 23081.4 23125.0 25426.5 25829.6 27799.2 28313.3 28391.4 28937.9 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 EPYC 7713 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 60K 120K 180K 240K 300K SE +/- 47.08, N = 3 SE +/- 58.73, N = 4 97768.80 98026.96 98453.55 134934.77 140264.40 140772.34 140955.13 144533.40 188790.14 266766.31 287620.18 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 EPYC 7763 EPYC 7713 xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 1000 2000 3000 4000 5000 SE +/- 6.51, N = 3 SE +/- 20.88, N = 4 2321.21 2326.91 2333.56 2541.43 2543.37 2666.75 2777.35 2882.84 3086.24 4162.54 4672.62 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 5 10 15 20 25 SE +/- 0.167, N = 3 SE +/- 0.011, N = 5 21.645 21.298 17.501 17.474 12.754 12.307 11.219 11.008 6.654 5.834 1. (CC) gcc options: -lm -lpthread -O3
m-queens A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 5 10 15 20 25 SE +/- 0.039, N = 3 SE +/- 0.027, N = 5 22.128 22.113 17.466 17.426 13.207 12.056 11.955 11.301 6.838 6.175 1. (CXX) g++ options: -fopenmp -O2 -march=native
toyBrot Fractal Generator ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: TBB Intel Xeon Platinum 8380 8380 1P Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 3K 6K 9K 12K 15K SE +/- 115.12, N = 8 SE +/- 55.68, N = 9 14660 14012 13486 11335 10684 8199 7582 6924 6791 3889 3602 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
ACES DGEMM This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 9 18 27 36 45 SE +/- 0.03, N = 4 SE +/- 0.08, N = 6 10.65 10.70 14.69 14.70 15.24 20.90 23.03 28.15 31.76 37.53 1. (CC) gcc options: -O3 -march=native -fopenmp
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 4 8 12 16 20 SE +/- 0.041, N = 3 SE +/- 0.039, N = 5 15.515 15.436 13.966 13.833 10.564 10.341 9.695 9.257 7.739 7.290 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Embree 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 xyz EPYC 7343 2P Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 20 40 60 80 100 SE +/- 0.09, N = 4 SE +/- 0.26, N = 5 34.39 34.46 44.17 44.17 47.41 48.07 57.65 75.50 82.25 100.82 MIN: 33.96 / MAX: 35.03 MIN: 34.05 / MAX: 35.3 MIN: 42.27 / MAX: 48.76 MIN: 42.4 / MAX: 48.84 MIN: 46.62 / MAX: 50.24 MIN: 47.12 / MAX: 49.71 MIN: 56.62 / MAX: 59.26 MIN: 65.3 / MAX: 94.46 MIN: 77.67 / MAX: 97.65 MIN: 93.3 / MAX: 111.79
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.10, N = 5 36.07 36.53 37.22 37.34 52.18 53.82 62.58 64.77 89.22 109.80 MIN: 34.8 / MAX: 40.77 MIN: 35.31 / MAX: 40.33 MIN: 36.77 / MAX: 38.02 MIN: 36.88 / MAX: 38.1 MIN: 51.24 / MAX: 53.72 MIN: 50.91 / MAX: 58.13 MIN: 61.62 / MAX: 65.13 MIN: 59.87 / MAX: 79.46 MIN: 83.22 / MAX: 102.41 MIN: 99.24 / MAX: 121.11
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon EPYC 7343 2P xyz Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 EPYC 7763 2P EPYC 7713 2P 2 x Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.50, N = 4 SE +/- 0.22, N = 5 38.04 38.18 42.61 44.06 47.82 62.97 69.23 69.26 73.27 83.57 MIN: 37.8 / MAX: 38.45 MIN: 37.89 / MAX: 39.12 MIN: 39.84 / MAX: 49.36 MIN: 41.96 / MAX: 49.48 MIN: 47.18 / MAX: 49.45 MIN: 61.94 / MAX: 65.45 MIN: 67.83 / MAX: 71.15 MIN: 65.36 / MAX: 72.56 MIN: 69.46 / MAX: 75.56 MIN: 69.17 / MAX: 92.21
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Degridding EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P EPYC 7713 EPYC 7763 Xeon Platinum 8380 Intel Xeon Platinum 8380 2 x Xeon Platinum 8380 5K 10K 15K 20K 25K SE +/- 195.78, N = 5 SE +/- 396.15, N = 8 3370.33 3413.54 3698.00 5788.17 6051.27 8068.36 8068.36 16445.20 19018.30 24810.20 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve OpenMP - Gridding xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 4K 8K 12K 16K 20K SE +/- 155.70, N = 5 SE +/- 158.49, N = 8 3207.90 3647.34 4096.25 4930.67 5120.31 9861.33 9861.33 13312.80 14169.20 18859.80 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 20 40 60 80 100 SE +/- 0.10, N = 5 SE +/- 0.34, N = 6 35.38 35.53 45.33 56.33 58.29 58.60 65.04 68.62 71.37 107.90 MIN: 35.15 / MAX: 35.91 MIN: 35.31 / MAX: 36.08 MIN: 44.76 / MAX: 46.72 MIN: 55.27 / MAX: 58.68 MIN: 53.64 / MAX: 61.72 MIN: 53.96 / MAX: 61.75 MIN: 63.76 / MAX: 66.74 MIN: 66.01 / MAX: 72.78 MIN: 66.56 / MAX: 74.57 MIN: 96.18 / MAX: 112.26
Basis Universal Basis Universal is a GPU texture codec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 2 Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 4 8 12 16 20 SE +/- 0.024, N = 4 SE +/- 0.018, N = 4 15.021 14.930 12.364 12.189 11.415 10.970 10.679 10.487 9.135 9.018 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
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 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.1177 0.2354 0.3531 0.4708 0.5885 SE +/- 0.000427, N = 4 SE +/- 0.000574, N = 4 0.522926 0.474391 0.431797 0.425751 0.401736 0.392781 0.364021 0.344166 0.329636 0.249611 MIN: 0.44 MIN: 0.42 MIN: 0.37 MIN: 0.36 MIN: 0.35 MIN: 0.37 MIN: 0.35 MIN: 0.29 MIN: 0.29 MIN: 0.23 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: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P EPYC 7763 EPYC 7713 2P EPYC 7763 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.2305 0.461 0.6915 0.922 1.1525 SE +/- 0.000310, N = 4 SE +/- 0.001610, N = 4 1.024620 1.018940 0.813627 0.799036 0.755328 0.739821 0.697542 0.239514 0.234327 0.228632 MIN: 0.92 MIN: 0.91 MIN: 0.77 MIN: 0.72 MIN: 0.72 MIN: 0.65 MIN: 0.62 MIN: 0.21 MIN: 0.21 MIN: 0.2 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
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 Xeon Platinum 8380 Intel Xeon Platinum 8380 2 x Xeon Platinum 8380 0.6328 1.2656 1.8984 2.5312 3.164 SE +/- 0.00595, N = 10 SE +/- 0.01197, N = 10 2.81248 2.79965 2.56596 1. (CXX) g++ options: -std=c++0x -march=core2 -msse2 -msse3 -mssse3 -mno-sse4.1 -mno-sse4.2 -mno-sse4a -mno-avx -mno-fma -mno-bmi2 -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7713 2P EPYC 7763 2P xyz EPYC 7343 2P EPYC 7763 EPYC 7443 2P 14 28 42 56 70 SE +/- 0.08, N = 4 SE +/- 0.33, N = 4 42.56 42.65 47.84 53.52 54.88 57.86 58.18 59.30 63.38 64.38 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -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_3d - Data Type: bf16bf16bf16 - Engine: CPU Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 1.3298 2.6596 3.9894 5.3192 6.649 SE +/- 0.00133, N = 9 SE +/- 0.00332, N = 9 5.91004 5.87433 3.56396 MIN: 5.76 MIN: 5.71 MIN: 3.49 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Chimera 1080p 10-bit xyz EPYC 7343 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 200 400 600 800 1000 SE +/- 0.41, N = 3 SE +/- 1.95, N = 3 741.77 745.05 774.74 775.38 861.39 912.13 944.91 976.44 1006.91 1149.71 MIN: 587.41 / MAX: 957.29 MIN: 593.18 / MAX: 955.66 MIN: 590.4 / MAX: 1067.33 MIN: 588.21 / MAX: 1071.6 MIN: 524.86 / MAX: 1144.29 MIN: 669.24 / MAX: 1136.98 MIN: 633.59 / MAX: 1225.85 MIN: 667.9 / MAX: 1265.98 MIN: 413.09 / MAX: 1202.67 MIN: 492.42 / MAX: 1400.99 1. (CC) gcc options: -pthread -lm
KTX-Software toktx This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 + Zstd Compression 19 EPYC 7343 2P xyz EPYC 7763 EPYC 7713 Xeon Platinum 8380 EPYC 7763 2P Intel Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 2P 2 x Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.026, N = 5 SE +/- 0.024, N = 5 11.260 11.183 10.642 10.589 10.387 10.335 10.291 10.177 10.174 9.111
toyBrot Fractal Generator ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Tasks Intel Xeon Platinum 8380 Xeon Platinum 8380 8380 1P xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 3K 6K 9K 12K 15K SE +/- 31.23, N = 4 SE +/- 27.45, N = 6 13739 13726 13714 11049 10930 8075 7949 7883 7220 4416 3888 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
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 EPYC 7763 2P EPYC 7713 2P EPYC 7443 2P EPYC 7763 EPYC 7713 EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 1.0362 2.0724 3.1086 4.1448 5.181 SE +/- 0.00142, N = 5 SE +/- 0.00190, N = 5 4.60517 4.47136 3.69608 3.51895 3.49877 2.95336 2.95187 1.44450 1.42703 1.36768 MIN: 3.91 MIN: 3.87 MIN: 3.11 MIN: 3.35 MIN: 3.34 MIN: 2.38 MIN: 2.4 MIN: 1.4 MIN: 1.4 MIN: 1.33 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
toyBrot Fractal Generator ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: OpenMP Intel Xeon Platinum 8380 Xeon Platinum 8380 8380 1P xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 3K 6K 9K 12K 15K SE +/- 13.75, N = 4 SE +/- 8.35, N = 6 14058 14057 14041 11073 10987 8211 7871 7320 7281 4949 4383 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
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: u8s8f32 - Engine: CPU EPYC 7763 2P EPYC 7713 2P EPYC 7713 EPYC 7763 EPYC 7443 2P EPYC 7343 2P xyz 2 x Xeon Platinum 8380 Intel Xeon Platinum 8380 Xeon Platinum 8380 0.2383 0.4766 0.7149 0.9532 1.1915 SE +/- 0.001219, N = 5 SE +/- 0.000558, N = 5 1.059290 0.991264 0.677189 0.640182 0.578318 0.510912 0.504712 0.438511 0.435640 0.427987 MIN: 0.88 MIN: 0.9 MIN: 0.62 MIN: 0.6 MIN: 0.53 MIN: 0.46 MIN: 0.46 MIN: 0.4 MIN: 0.41 MIN: 0.41 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
toyBrot Fractal Generator ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better toyBrot Fractal Generator 2020-11-18 Implementation: C++ Threads 8380 1P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz EPYC 7713 EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7763 EPYC 7713 2P EPYC 7763 2P 3K 6K 9K 12K 15K SE +/- 27.98, N = 4 SE +/- 17.11, N = 6 13488 13486 13439 10858 10856 7713 7662 6992 6827 4175 3657 1. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
Pennant Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig 8380 1P Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 3 6 9 12 15 SE +/- 0.018568, N = 4 SE +/- 0.011962, N = 7 11.367730 11.328990 11.321090 8.417617 8.358178 6.643267 6.116076 6.072207 4.707610 3.685405 3.401556 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Intel Xeon Platinum 8380 Xeon Platinum 8380 8380 1P EPYC 7713 EPYC 7763 xyz EPYC 7343 2P EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 30K 60K 90K 120K 150K SE +/- 41.49, N = 6 SE +/- 106.40, N = 7 57129.81 57275.08 57286.34 60594.05 62443.86 75528.30 76625.42 81688.12 100812.54 108518.14 121334.72 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
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 CFD Solver xyz EPYC 7343 2P EPYC 7443 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 8380 1P EPYC 7713 2P Xeon Platinum 8380 EPYC 7763 2P 2 x Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.007, N = 7 SE +/- 0.024, N = 8 12.660 11.775 8.162 6.719 6.495 6.395 6.318 6.250 6.211 5.967 4.709 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: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 EPYC 7713 2P EPYC 7763 2P 0.3314 0.6628 0.9942 1.3256 1.657 SE +/- 0.000410, N = 7 SE +/- 0.003046, N = 7 1.473100 1.459520 1.397170 1.208930 1.203100 0.945964 0.894939 0.857172 0.623759 0.579442 MIN: 1.43 MIN: 1.43 MIN: 1.24 MIN: 0.96 MIN: 0.96 MIN: 0.86 MIN: 0.77 MIN: 0.8 MIN: 0.55 MIN: 0.52 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: u8s8f32 - Engine: CPU EPYC 7443 2P xyz EPYC 7343 2P EPYC 7713 EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 2P 2 x Xeon Platinum 8380 EPYC 7713 2P 0.6351 1.2702 1.9053 2.5404 3.1755 SE +/- 0.000981, N = 7 SE +/- 0.002416, N = 7 2.822600 2.745390 2.553760 1.642970 1.602440 1.500090 1.482560 1.425080 0.915086 0.785042 MIN: 2.47 MIN: 2.26 MIN: 2.22 MIN: 1.57 MIN: 1.54 MIN: 1.41 MIN: 1.32 MIN: 0.47 MIN: 0.85 MIN: 0.48 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better WebP2 Image Encode 20210126 Encode Settings: Quality 100, Compression Effort 5 EPYC 7713 2P EPYC 7713 EPYC 7763 2P EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7443 2P xyz EPYC 7343 2P 2 4 6 8 10 SE +/- 0.002, N = 6 SE +/- 0.007, N = 6 7.141 6.996 6.978 6.848 6.320 6.303 6.251 5.835 5.753 5.748 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -rdynamic -lpthread -ljpeg -lwebp -lwebpdemux
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Xeon Platinum 8380 Intel Xeon Platinum 8380 8380 1P EPYC 7713 EPYC 7763 xyz EPYC 7443 2P EPYC 7343 2P 2 x Xeon Platinum 8380 EPYC 7763 2P EPYC 7713 2P 10K 20K 30K 40K 50K SE +/- 41.74, N = 6 SE +/- 84.43, N = 8 22890.25 22960.66 23077.99 23938.94 24486.03 26122.63 26447.65 29672.43 40188.84 47461.28 47537.25 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B 8380 1P Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 EPYC 7343 2P xyz EPYC 7763 EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 30K 60K 90K 120K 150K SE +/- 122.82, N = 6 SE +/- 276.83, N = 9 49716.46 50133.58 50295.80 88404.43 88850.99 91436.93 93581.86 94225.90 123538.14 142089.18 143309.96 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction EPYC 7343 2P EPYC 7763 Intel Xeon Platinum 8380 Xeon Platinum 8380 8380 1P EPYC 7713 xyz EPYC 7443 2P EPYC 7713 2P EPYC 7763 2P 2 x Xeon Platinum 8380 1.2421 2.4842 3.7263 4.9684 6.2105 SE +/- 0.00960015, N = 7 SE +/- 0.00858289, N = 9 5.52046394 5.40164614 5.34965897 5.26849863 5.25334501 5.16119099 4.90903282 3.95002103 2.73742104 2.65836406 2.57966831 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz
KTX-Software toktx This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7343 2P xyz 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 EPYC 7443 2P EPYC 7763 2P EPYC 7713 2P 2 4 6 8 10 SE +/- 0.006, N = 7 SE +/- 0.005, N = 8 6.037 6.013 5.120 5.117 4.658 4.494 4.413 4.334 3.915 3.890
Primesieve Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.4 1e12 Prime Number Generation Xeon Platinum 8380 Intel Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7443 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 2 4 6 8 10 SE +/- 0.020, N = 6 SE +/- 0.010, N = 9 7.166 7.099 6.288 6.286 4.954 4.556 4.400 3.693 2.727 2.418 1. (CXX) g++ options: -O3 -lpthread
rays1bench This is a test of rays1bench, a simple path-tracer / ray-tracing that supports SSE and AVX instructions, multi-threading, and other features. This test profile is measuring the performance of the "large scene" in rays1bench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org mrays/s, More Is Better rays1bench 2020-01-09 Large Scene Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 EPYC 7763 EPYC 7443 2P 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 120 240 360 480 600 SE +/- 0.17, N = 7 SE +/- 0.57, N = 8 183.45 184.56 235.63 235.82 270.56 292.90 315.06 346.31 501.47 548.62
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.9.0 Video Input: Summer Nature 4K Xeon Platinum 8380 EPYC 7343 2P xyz Intel Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7763 2P EPYC 7763 EPYC 7713 2P 120 240 360 480 600 SE +/- 0.60, N = 3 SE +/- 0.65, N = 3 404.27 404.32 404.88 405.76 470.15 525.08 532.57 559.16 561.10 567.75 MIN: 275.43 / MAX: 456.48 MIN: 286.8 / MAX: 449.32 MIN: 298.45 / MAX: 452.23 MIN: 281.5 / MAX: 454.16 MIN: 273.44 / MAX: 506.85 MIN: 254.89 / MAX: 569.99 MIN: 189.3 / MAX: 586.86 MIN: 133.86 / MAX: 655.76 MIN: 279.06 / MAX: 604.48 MIN: 128.52 / MAX: 672.61 1. (CC) gcc options: -pthread -lm
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_3d - Data Type: u8s8f32 - Engine: CPU EPYC 7343 2P xyz EPYC 7443 2P EPYC 7713 EPYC 7713 2P EPYC 7763 EPYC 7763 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.2394 0.4788 0.7182 0.9576 1.197 SE +/- 0.002283, N = 15 SE +/- 0.000612, N = 9 1.063800 1.054860 0.832834 0.773162 0.769713 0.710643 0.655887 0.323917 0.310362 0.190628 MIN: 0.96 MIN: 0.95 MIN: 0.67 MIN: 0.71 MIN: 0.66 MIN: 0.67 MIN: 0.56 MIN: 0.29 MIN: 0.29 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: VMAF Optimized - Input: Bosphorus 1080p Intel Xeon Platinum 8380 EPYC 7713 EPYC 7763 2P xyz EPYC 7343 2P EPYC 7713 2P EPYC 7443 2P 2 x Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 110 220 330 440 550 SE +/- 5.22, N = 15 SE +/- 4.09, N = 15 349.52 386.43 391.50 437.34 440.76 450.19 460.84 475.45 485.12 506.63 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Thorough Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7343 2P EPYC 7763 EPYC 7713 EPYC 7763 2P 2 4 6 8 10 SE +/- 0.0247, N = 3 7.4554 7.4107 6.4762 6.1705 6.1015 5.5001 1. (CXX) g++ options: -O3 -flto -pthread
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 Intel Xeon Platinum 8380 Xeon Platinum 8380 xyz EPYC 7343 2P EPYC 7713 2P 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7763 2P EPYC 7443 2P EPYC 7763 80 160 240 320 400 SE +/- 0.54, N = 10 SE +/- 2.91, N = 15 289.72 290.36 307.69 309.44 309.60 313.93 318.64 335.76 347.62 348.63 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 8380 1P EPYC 7763 EPYC 7443 2P xyz EPYC 7343 2P EPYC 7763 2P EPYC 7713 2P 2 x Xeon Platinum 8380 30K 60K 90K 120K 150K SE +/- 182.12, N = 9 SE +/- 268.68, N = 11 56287.53 56347.39 57300.93 58038.46 58366.16 83229.61 85228.18 86520.29 99876.13 102996.76 118831.52 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C xyz EPYC 7343 2P EPYC 7443 2P 8380 1P Xeon Platinum 8380 Intel Xeon Platinum 8380 EPYC 7713 EPYC 7763 2 x Xeon Platinum 8380 EPYC 7713 2P EPYC 7763 2P 2K 4K 6K 8K 10K SE +/- 32.20, N = 11 SE +/- 69.57, N = 15 3253.26 3261.39 4058.34 4269.94 4334.33 4493.03 4696.97 4862.97 7939.02 8360.16 9332.11 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
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_3d - Data Type: f32 - Engine: CPU EPYC 7763 2P EPYC 7343 2P EPYC 7763 xyz EPYC 7713 2P EPYC 7713 EPYC 7443 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 0.7436 1.4872 2.2308 2.9744 3.718 SE +/- 0.000612, N = 9 SE +/- 0.000669, N = 9 3.305080 3.074760 2.879530 2.843710 2.268330 2.056450 1.883210 1.464100 1.371550 0.839556 MIN: 2.39 MIN: 2.52 MIN: 2.11 MIN: 2.51 MIN: 2.11 MIN: 1.9 MIN: 1.52 MIN: 1.31 MIN: 1.31 MIN: 0.8 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: Visual Quality Optimized - Input: Bosphorus 1080p EPYC 7713 2P EPYC 7343 2P xyz EPYC 7713 Intel Xeon Platinum 8380 EPYC 7763 2P EPYC 7763 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7443 2P 80 160 240 320 400 SE +/- 2.16, N = 10 SE +/- 2.30, N = 9 336.40 350.43 351.29 354.38 363.45 365.50 368.98 370.64 371.88 378.03 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
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 EPYC 7343 2P xyz Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7443 2P EPYC 7713 EPYC 7713 2P EPYC 7763 2 x Xeon Platinum 8380 EPYC 7763 2P 8 16 24 32 40 SE +/- 0.23, N = 15 SE +/- 0.33, N = 15 16.38 17.05 20.34 20.84 21.66 21.97 28.76 30.88 31.56 33.49 1. (CXX) g++ options: -O3 -pthread -lm
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p xyz EPYC 7763 2P EPYC 7343 2P EPYC 7713 2P EPYC 7713 2 x Xeon Platinum 8380 EPYC 7443 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 EPYC 7763 110 220 330 440 550 SE +/- 1.83, N = 10 SE +/- 0.89, N = 11 420.77 442.30 446.75 449.86 469.37 469.70 474.62 484.52 485.54 488.27 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.0 Preset: Medium Intel Xeon Platinum 8380 Xeon Platinum 8380 rest EPYC 7763 EPYC 7763 2P EPYC 7713 EPYC 7343 2P 1.1028 2.2056 3.3084 4.4112 5.514 SE +/- 0.0185, N = 3 4.9012 4.8512 4.2197 4.1349 4.0674 3.9015 1. (CXX) g++ options: -O3 -flto -pthread
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p EPYC 7343 2P xyz EPYC 7713 2P Intel Xeon Platinum 8380 Xeon Platinum 8380 2 x Xeon Platinum 8380 EPYC 7713 EPYC 7443 2P EPYC 7763 2P EPYC 7763 140 280 420 560 700 SE +/- 1.28, N = 12 SE +/- 3.29, N = 11 552.49 561.27 574.71 583.09 583.64 584.72 588.24 595.83 600.00 629.59 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
2 x Xeon Platinum 8380 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: 7682GB INTEL SSDPF2KX076TZ, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Desktop: GNOME Shell 3.38.4, Display Server: X Server, OpenGL: 4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits), Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Python 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 1 June 2021 16:32 by user phoronix.
Xeon Platinum 8380 Processor: Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 252GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Desktop: GNOME Shell 3.38.4, Display Server: X Server, OpenGL: 4.5 Mesa 21.0.1 (LLVM 11.0.1 256 bits), Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Python 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 2 June 2021 14:06 by user phoronix.
Xeon Platinum 8380 rest Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Security 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 3 June 2021 17:21 by user phoronix.
Intel Xeon Platinum 8380 Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Python 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 3 June 2021 18:45 by user phoronix.
8380 1P Processor: Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 252GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, 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 -vProcessor Notes: Scaling Governor: intel_pstate performance - CPU Microcode: 0xd000270Python 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 4 June 2021 06:32 by user phoronix.
EPYC 7713 Processor: AMD EPYC 7713 64-Core @ 2.00GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 252GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 5 June 2021 12:26 by user phoronix.
EPYC 7713 2P Processor: 2 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 7 June 2021 11:22 by user phoronix.
EPYC 7343 2P Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 9 June 2021 18:17 by user phoronix.
xyz Processor: 2 x AMD EPYC 7343 16-Core @ 3.20GHz (32 Cores / 64 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 June 2021 04:37 by user phoronix.
EPYC 7443 2P Processor: 2 x AMD EPYC 7443 24-Core @ 2.85GHz (48 Cores / 96 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 12 June 2021 12:24 by user phoronix.
EPYC 7763 Processor: AMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 252GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 13 June 2021 13:29 by user phoronix.
EPYC 7763 2P Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Network: 2 x Mellanox MT27710
OS: Ubuntu 21.04, Kernel: 5.13.0-051300rc4-generic (x86_64) 20210530, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.3.0, File-System: ext4, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001119Python Notes: Python 3.9.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 14 June 2021 07:49 by user phoronix.