AMD EPYC vs. Intel Xeon open-source server benchmarks on Ubuntu Linux. Latest as of November 2018. Tests by Michael Larabel for a future article.
EPYC 7251 Processor: AMD EPYC 7251 8-Core @ 2.10GHz (8 Cores / 16 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe 126GB, Monitor: VE228, Network: Broadcom NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 128 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
EPYC 7351P Changed Processor to AMD EPYC 7351P 16-Core @ 2.40GHz (16 Cores / 32 Threads) .
EPYC 7401P Changed Processor to AMD EPYC 7401P 24-Core @ 2.00GHz (24 Cores / 48 Threads) .
EPYC 7551 Changed Processor to AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads) .
EPYC 7601 Changed Processor to AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads) .
2 x EPYC 7601 Processor: 2 x AMD EPYC 7601 32-Core @ 3.07GHz (64 Cores / 128 Threads) , Motherboard: Dell 02MJ3T (1.2.5 BIOS) , Chipset: AMD Family 17h, Memory: 516096MB , Disk: 280GB INTEL SSDPE21D280GA, Graphics: Matrox Matrox G200eW3 , Monitor: VE228, Network: Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
Xeon Silver 4108 Processor: Intel Xeon Silver 4108 @ 3.00GHz (8 Cores / 16 Threads) , Motherboard: TYAN S7100AG2NR (V3.03 BIOS) , Chipset: Intel Sky Lake-E DMI3 Registers , Memory: 23552MB , Disk: Samsung SSD 970 EVO 250GB , Graphics: ASPEED ASPEED Family , Audio: Realtek ALC892 , Monitor: VE228 , Network: Intel I350 Gigabit Connection
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 256 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersavePython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable
2 x Xeon Gold 6138 Processor: 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads) , Motherboard: TYAN S7106 (V1.01 BIOS) , Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 96256MB , Disk: 280GB INTEL SSDPE21D280GA , Graphics: llvmpipe 93GB , Monitor: VE228 , Network: Intel I210 Gigabit Connection
2 x 22-Core POWER9 176 Threads Processor: POWER9 altivec supported @ 3.80GHz (44 Cores / 176 Threads) , Motherboard: PowerNV T2P9D01 REV 1.01 , Memory: 65536MB , Disk: 280GB INTEL SSDPE21D280GA , Graphics: ASPEED ASPEED Family , Monitor: VE228 , Network: Broadcom NetXtreme BCM5719 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (ppc64le), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-mtune=power9-mcpu=power9 CFLAGS=-O3-mtune=power9-mcpu=power9Compiler Notes: --build=powerpc64le-linux-gnu --disable-libphobos --disable-multilib --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-secureplt --enable-shared --enable-targets=powerpcle-linux --enable-threads=posix --host=powerpc64le-linux-gnu --program-prefix=powerpc64le-linux-gnu- --target=powerpc64le-linux-gnu --with-cpu=power8 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-long-double-128 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: powernv-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7
MariaDB OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.3.8 Clients: 64 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 200 400 600 800 1000 SE +/- 0.51, N = 3 SE +/- 1.09, N = 3 SE +/- 0.36, N = 3 SE +/- 0.21, N = 3 SE +/- 18.74, N = 9 SE +/- 2.04, N = 9 SE +/- 2.26, N = 3 SE +/- 1.04, N = 3 421 606 555 607 442 107 989 91 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79 Blend File: Barbershop - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 400 800 1200 1600 2000 SE +/- 3.30, N = 3 SE +/- 0.61, N = 3 SE +/- 0.37, N = 3 SE +/- 1.57, N = 3 SE +/- 0.21, N = 3 SE +/- 0.96, N = 3 SE +/- 0.27, N = 3 SE +/- 0.41, N = 3 SE +/- 0.35, N = 3 1841 874 697 549 523 309 2039 407 473
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Extra - Threads: 16 - Solver Time EPYC 7551 EPYC 7601 2 x EPYC 7601 80 160 240 320 400 SE +/- 5.26, N = 9 SE +/- 4.09, N = 3 SE +/- 0.70, N = 3 391 257 184 1. Build Time Thu Nov 8 18:40:03 EST 2018;
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79 Blend File: Classroom - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 300 600 900 1200 1500 SE +/- 2.59, N = 3 SE +/- 1.06, N = 3 SE +/- 1.07, N = 3 SE +/- 0.60, N = 3 SE +/- 0.14, N = 3 SE +/- 0.21, N = 3 SE +/- 0.09, N = 3 SE +/- 0.28, N = 3 SE +/- 0.41, N = 3 1063 503 402 308 296 152 1329 236 331
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.7.0 vpxenc EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.21, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 11.05 11.14 11.12 11.57 12.25 12.22 10.79 13.91 1.78 -m64 -march=native -m64 -march=native -m64 -march=native -m64 -march=native -m64 -march=native -m64 -march=native -m64 -march=native -m64 -march=native 1. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE
Open Porous Media Git This is a test of a DUNE (Distributed and Unified Numerics Environment) module called OPM Benchmarks from the Open Porous Media project. Open Porous Media is a set of open-source tools concerning simulation of flow and transport of fluids in porous media. This test profile builds OPM and its dependencies from upstream Git. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Extra - Threads: 16 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 2 x Xeon Gold 6138 90 180 270 360 450 SE +/- 0.81, N = 3 SE +/- 2.97, N = 3 SE +/- 5.28, N = 9 SE +/- 4.11, N = 3 SE +/- 0.73, N = 3 SE +/- 0.40, N = 3 273 270 398 263 190 238 1. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018; 2. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018; 3. EPYC 7551: Build Time Thu Nov 8 18:40:03 EST 2018; 4. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 5. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 6. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79 Blend File: Pabellon Barcelona - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 200 400 600 800 1000 SE +/- 1.23, N = 3 SE +/- 0.08, N = 3 SE +/- 0.76, N = 3 SE +/- 0.61, N = 3 SE +/- 0.55, N = 3 SE +/- 0.27, N = 3 SE +/- 0.59, N = 3 SE +/- 0.40, N = 3 SE +/- 0.36, N = 3 891 415 334 259 248 134 1094 195 244
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 4K 8K 12K 16K 20K SE +/- 2.60, N = 3 SE +/- 17.33, N = 3 SE +/- 33.71, N = 3 SE +/- 82.85, N = 3 SE +/- 45.21, N = 3 SE +/- 25.94, N = 3 SE +/- 134.57, N = 3 SE +/- 238.01, N = 3 11704 12007 12395 12272 13033 12991 14107 16704 1. (CC) gcc options: -pthread -O3 -march=native -lm
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Barbershop - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 400 800 1200 1600 2000 1798 853 672 527 504 323 1892 374
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Extra - Threads: 16 - Solver Time EPYC 7351P EPYC 7401P 2 x Xeon Gold 6138 60 120 180 240 300 SE +/- 0.84, N = 3 SE +/- 2.97, N = 3 SE +/- 0.41, N = 3 266 264 232 1. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018; 2. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018; 3. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79 Blend File: Fishy Cat - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 150 300 450 600 750 SE +/- 0.32, N = 3 SE +/- 0.04, N = 3 SE +/- 0.35, N = 3 SE +/- 0.45, N = 3 SE +/- 0.18, N = 3 SE +/- 0.66, N = 3 SE +/- 0.60, N = 3 SE +/- 0.20, N = 3 SE +/- 0.55, N = 3 496.52 237.60 193.75 155.90 149.60 88.13 692.45 125.31 194.98
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Extra - Threads: 32 - Solver Time EPYC 7601 2 x EPYC 7601 60 120 180 240 300 SE +/- 3.23, N = 3 SE +/- 1.56, N = 3 259 158 1. Build Time Thu Nov 8 18:40:03 EST 2018;
OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Extra - Threads: 32 EPYC 7601 2 x EPYC 7601 2 x Xeon Gold 6138 60 120 180 240 300 SE +/- 3.24, N = 3 SE +/- 1.53, N = 3 SE +/- 2.26, N = 3 266 165 196 1. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 2. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 3. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;
OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Extra - Threads: 32 - Solver Time 2 x Xeon Gold 6138 40 80 120 160 200 SE +/- 2.02, N = 3 188.56 1. Build Time Wed Nov 14 07:09:02 EST 2018;
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1300 2600 3900 5200 6500 SE +/- 3.79, N = 3 SE +/- 16.65, N = 3 SE +/- 6.10, N = 3 SE +/- 29.24, N = 3 SE +/- 8.17, N = 3 SE +/- 1.04, N = 3 SE +/- 12.47, N = 3 SE +/- 62.63, N = 3 SE +/- 10.97, N = 3 4811 4885 4994 4991 5226 5367 5070 5688 6010 1. (CC) gcc options: -pthread -O3 -march=native -lm
Tinymembench OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 4K 8K 12K 16K 20K SE +/- 4.33, N = 3 SE +/- 1.78, N = 3 SE +/- 10.43, N = 3 SE +/- 5.65, N = 3 SE +/- 3.57, N = 3 SE +/- 7.22, N = 3 SE +/- 10.13, N = 3 SE +/- 34.89, N = 3 SE +/- 11.26, N = 3 9670 9811 9873 9919 9957 11162 19797 9323 17211 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O2 -O3 -lm
OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 3K 6K 9K 12K 15K SE +/- 6.56, N = 3 SE +/- 22.35, N = 3 SE +/- 4.14, N = 3 SE +/- 4.79, N = 3 SE +/- 2.17, N = 3 SE +/- 7.00, N = 3 SE +/- 5.48, N = 3 SE +/- 32.99, N = 3 SE +/- 19.82, N = 3 7215 7373 7404 7484 7483 8041 9104 6153 13063 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O2 -O3 -lm
RAR Compression This test measures the time needed to archive/compress two copies of the Linux 4.13 kernel source tree using RAR/WinRAR compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better RAR Compression 5.6.1 Linux Source Tree Archiving To RAR EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 40 80 120 160 200 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.24, N = 3 SE +/- 2.27, N = 3 SE +/- 0.29, N = 3 SE +/- 1.84, N = 12 SE +/- 1.04, N = 3 SE +/- 0.39, N = 3 190 152 152 149 145 108 148 118
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79 Blend File: BMW27 - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 100 200 300 400 500 SE +/- 1.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.33, N = 3 SE +/- 0.14, N = 3 SE +/- 0.24, N = 3 SE +/- 0.73, N = 3 SE +/- 0.38, N = 3 SE +/- 0.10, N = 3 347.99 170.96 139.27 110.17 106.24 60.54 439.39 84.06 110.30
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 2017-09-19 1024 Hash Memory, 26 Depth EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 30M 60M 90M 120M 150M SE +/- 41751.52, N = 3 SE +/- 309490.22, N = 3 SE +/- 543463.40, N = 3 SE +/- 689157.25, N = 3 SE +/- 351504.20, N = 3 SE +/- 1024911.36, N = 3 SE +/- 107251.48, N = 3 SE +/- 1344269.02, N = 4 17597927 37399010 49280378 63302402 66907463 119448261 15102990 81933755
Fhourstones This integer benchmark solves positions in the game of Connect-4, as played on a vertical 7x6 board. By default, it uses a 64Mb transposition table with the twobig replacement strategy. Positions are represented as 64-bit bitboards, and the hash function is computed using a single 64-bit modulo operation, giving 64-bit machines a slight edge. The alpha-beta searcher sorts moves dynamically based on the history heuristic. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Kpos / sec, More Is Better Fhourstones 3.1 Complex Connect-4 Solving EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 3K 6K 9K 12K 15K SE +/- 19.69, N = 3 SE +/- 147.31, N = 5 SE +/- 21.63, N = 3 SE +/- 15.44, N = 3 SE +/- 19.85, N = 3 SE +/- 12.05, N = 3 SE +/- 5.67, N = 3 SE +/- 11.81, N = 3 SE +/- 2.98, N = 3 9525 9708 10124 10293 10608 10350 10110 12811 12494 1. (CC) gcc options: -O3
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Pabellon Barcelona - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 200 400 600 800 1000 969 444 351 276 265 141 1157 204
Hierarchical INTegration This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org QUIPs, More Is Better Hierarchical INTegration 1.0 Test: FLOAT EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 80M 160M 240M 320M 400M SE +/- 73811.70, N = 3 SE +/- 114111.35, N = 3 SE +/- 40280.23, N = 3 SE +/- 2471240.27, N = 3 SE +/- 652352.80, N = 3 SE +/- 126220.51, N = 3 SE +/- 871757.89, N = 3 SE +/- 767909.83, N = 3 237389150 237485331 245672557 243635582 261210613 262007933 297173399 366699191 1. (CC) gcc options: -O3 -march=native -lm
Minion Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Quasigroup EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 40 80 120 160 200 SE +/- 0.67, N = 3 SE +/- 0.76, N = 3 SE +/- 0.10, N = 3 SE +/- 1.32, N = 3 SE +/- 0.63, N = 3 SE +/- 0.95, N = 3 SE +/- 0.28, N = 3 SE +/- 0.28, N = 3 SE +/- 0.59, N = 3 164 164 158 158 149 147 149 120 175 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Single Thread - Mode: Read Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 4K 8K 12K 16K 20K SE +/- 29.83, N = 3 SE +/- 136.10, N = 3 SE +/- 35.53, N = 3 SE +/- 13.14, N = 3 SE +/- 155.22, N = 3 SE +/- 178.37, N = 3 SE +/- 107.48, N = 3 SE +/- 86.63, N = 3 SE +/- 160.04, N = 3 11515 12661 13668 14499 14805 15145 15076 17805 15502 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
GNU GMP GMPbench GMPbench is a test of the GMP 6.1.2 math library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GMPbench Score, More Is Better GNU GMP GMPbench 6.1.2 Total Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1000 2000 3000 4000 5000 3570 3573 3700 3704 3941 3940 3839 4710 3268 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Norne - Threads: 32 - Solver Time EPYC 7551 EPYC 7601 2 x EPYC 7601 20 40 60 80 100 SE +/- 1.16, N = 3 SE +/- 1.26, N = 5 SE +/- 0.97, N = 6 90.50 88.31 66.47 1. Build Time Thu Nov 8 18:40:03 EST 2018;
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 130K 260K 390K 520K 650K SE +/- 143.00, N = 3 SE +/- 971.65, N = 3 SE +/- 820.46, N = 3 SE +/- 1536.25, N = 3 SE +/- 3941.18, N = 3 SE +/- 3036.21, N = 3 SE +/- 270.54, N = 3 SE +/- 1512.41, N = 3 SE +/- 1721.99, N = 3 123039 249578 317536 407453 396841 518285 156504 584554 582611 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 2048 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 4K 8K 12K 16K 20K SE +/- 99.14, N = 3 SE +/- 183.27, N = 3 SE +/- 28.67, N = 3 SE +/- 118.60, N = 3 SE +/- 43.92, N = 3 SE +/- 126.72, N = 3 SE +/- 34.03, N = 3 SE +/- 268.19, N = 3 12315 14023 13850 12744 14761 13364 14462 18805 1. (CC) gcc options: -pthread -O3 -march=native -lm
CacheBench This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Write EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 6K 12K 18K 24K 30K SE +/- 23.89, N = 3 SE +/- 0.70, N = 3 SE +/- 17.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.29, N = 3 SE +/- 0.48, N = 3 SE +/- 5.33, N = 3 SE +/- 1.72, N = 3 SE +/- 0.59, N = 3 19802 19858 20532 20578 21909 21915 20901 25798 11869 1. (CC) gcc options: -lrt
OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read / Modify / Write EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 9K 18K 27K 36K 45K SE +/- 4.60, N = 3 SE +/- 7.32, N = 3 SE +/- 2.10, N = 3 SE +/- 6.55, N = 3 SE +/- 2.12, N = 3 SE +/- 0.93, N = 3 SE +/- 1.43, N = 3 SE +/- 0.99, N = 3 SE +/- 0.65, N = 3 38495 38501 39842 39908 42497 42505 34209 42218 21451 1. (CC) gcc options: -lrt
OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1000 2000 3000 4000 5000 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.54, N = 3 SE +/- 0.26, N = 3 2008 2008 2077 2081 2216 2216 2533 3125 4896 1. (CC) gcc options: -lrt
BYTE Unix Benchmark This is a test of BYTE. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 8M 16M 24M 32M 40M SE +/- 260711.56, N = 3 SE +/- 477072.38, N = 4 SE +/- 231609.59, N = 3 SE +/- 265797.72, N = 3 SE +/- 313116.33, N = 3 SE +/- 391137.33, N = 3 SE +/- 106664.99, N = 3 SE +/- 4427.74, N = 3 SE +/- 89617.34, N = 3 30484683 29882978 30669770 31422611 33474468 33652455 30656278 37843257 25038447 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2K 4K 6K 8K 10K SE +/- 48.28, N = 3 SE +/- 14.40, N = 3 SE +/- 6.27, N = 3 SE +/- 10.71, N = 3 SE +/- 26.41, N = 3 SE +/- 24.54, N = 3 SE +/- 1.48, N = 3 SE +/- 24.61, N = 3 7091 7098 7127 6509 7292 7824 8086 5125 1. (CC) gcc options: -O3 -march=native
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Classroom - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 200 400 600 800 1000 706.16 342.86 272.91 209.46 201.93 98.79 944.28 164.62
Open Porous Media Git This is a test of a DUNE (Distributed and Unified Numerics Environment) module called OPM Benchmarks from the Open Porous Media project. Open Porous Media is a set of open-source tools concerning simulation of flow and transport of fluids in porous media. This test profile builds OPM and its dependencies from upstream Git. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Norne - Threads: 32 EPYC 7551 EPYC 7601 2 x EPYC 7601 2 x Xeon Gold 6138 20 40 60 80 100 SE +/- 1.17, N = 3 SE +/- 1.26, N = 5 SE +/- 0.97, N = 6 SE +/- 1.19, N = 3 93.01 90.50 68.35 84.25 1. EPYC 7551: Build Time Thu Nov 8 18:40:03 EST 2018; 2. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 3. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 4. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Add EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 12K 24K 36K 48K 60K SE +/- 331.78, N = 12 SE +/- 583.28, N = 12 SE +/- 494.83, N = 12 SE +/- 499.65, N = 12 SE +/- 1266.42, N = 12 SE +/- 3639.91, N = 9 SE +/- 278.39, N = 3 SE +/- 604.72, N = 3 SE +/- 198.38, N = 3 22956 26176 26975 25584 30783 44730 49494 56998 49123 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm -rdynamic
Timed Linux Kernel Compilation This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.18 Time To Compile EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 30 60 90 120 150 SE +/- 1.58, N = 3 SE +/- 1.04, N = 3 SE +/- 0.79, N = 5 SE +/- 0.48, N = 10 SE +/- 0.49, N = 9 SE +/- 0.31, N = 12 SE +/- 1.50, N = 3 SE +/- 0.42, N = 12 SE +/- 0.74, N = 3 116.95 62.80 52.90 43.98 42.98 26.46 134.05 33.94 51.59
Stockfish This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20M 40M 60M 80M 100M SE +/- 85097.64, N = 3 SE +/- 96861.51, N = 3 SE +/- 474439.83, N = 3 SE +/- 451949.77, N = 3 SE +/- 186688.77, N = 3 SE +/- 302657.40, N = 3 SE +/- 44988.37, N = 3 SE +/- 599656.72, N = 3 SE +/- 653933.14, N = 3 16282402 33075412 43541579 56308691 57008073 100932062 12717282 69815559 83190230 -march=native -msse -msse3 -mpopcnt -march=native -msse -msse3 -mpopcnt -march=native -msse -msse3 -mpopcnt -march=native -msse -msse3 -mpopcnt -march=native -msse -msse3 -mpopcnt -march=native -msse -msse3 -mpopcnt -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -m64 -lpthread -O3 -fno-exceptions -std=c++11 -pedantic -flto
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 8192 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3K 6K 9K 12K 15K SE +/- 63.38, N = 3 SE +/- 3.69, N = 3 SE +/- 63.39, N = 3 SE +/- 160.57, N = 7 SE +/- 3.39, N = 3 SE +/- 2.15, N = 3 SE +/- 2.61, N = 3 SE +/- 2.43, N = 3 11660 12553 12509 12356 12634 12563 8468 4780 1. (CC) gcc options: -O3 -march=native
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 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 30K 60K 90K 120K 150K SE +/- 59.47, N = 3 SE +/- 443.11, N = 3 SE +/- 614.77, N = 3 SE +/- 633.86, N = 3 SE +/- 1083.97, N = 3 SE +/- 2850.88, N = 9 SE +/- 143.98, N = 3 SE +/- 2282.89, N = 3 SE +/- 2843.17, N = 3 30627 60038 77665 85123 91220 130239 28011 137914 158600 1. (CXX) g++ options: -pipe -lpthread
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 2.13b1 ATPase Simulation - 327,506 Atoms EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 0.856 1.712 2.568 3.424 4.28 SE +/- 0.00301, N = 3 SE +/- 0.00183, N = 3 SE +/- 0.00184, N = 3 SE +/- 0.00095, N = 3 SE +/- 0.00124, N = 3 SE +/- 0.00747, N = 12 SE +/- 0.00272, N = 3 SE +/- 0.00243, N = 3 3.08525 1.50755 1.21215 0.93337 0.90885 0.45828 3.80433 0.65118
Minion Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Solitaire EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20 40 60 80 100 SE +/- 0.47, N = 3 SE +/- 0.35, N = 3 SE +/- 0.49, N = 3 SE +/- 0.33, N = 3 SE +/- 0.54, N = 3 SE +/- 0.38, N = 3 SE +/- 0.02, N = 3 SE +/- 0.25, N = 3 SE +/- 0.29, N = 3 98.10 95.94 92.55 92.42 87.42 87.90 91.88 75.07 99.17 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Prepend EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 14K 28K 42K 56K 70K SE +/- 1281.01, N = 12 SE +/- 82.78, N = 3 SE +/- 1105.77, N = 12 SE +/- 2955.21, N = 12 SE +/- 1919.55, N = 12 SE +/- 663.14, N = 3 SE +/- 341.55, N = 3 SE +/- 99.58, N = 3 SE +/- 758.35, N = 12 26623 26435 28955 37074 50405 44855 55171 66549 53344 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm -rdynamic
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Norne - Threads: 32 - Solver Time 2 x Xeon Gold 6138 20 40 60 80 100 SE +/- 1.15, N = 3 82.03 1. Build Time Wed Nov 14 07:09:02 EST 2018;
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Fishy Cat - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 140 280 420 560 700 466.16 221.45 181.96 146.34 139.91 83.63 651.91 117.62
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 12K 24K 36K 48K 60K SE +/- 545.53, N = 12 SE +/- 47.62, N = 3 SE +/- 476.79, N = 12 SE +/- 86.23, N = 3 SE +/- 371.58, N = 7 SE +/- 784.66, N = 12 SE +/- 195.73, N = 3 SE +/- 294.71, N = 3 SE +/- 310.97, N = 3 23442 24973 26455 25250 29030 41189 49292 56738 49593 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm -rdynamic
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Norne - Threads: 16 - Solver Time EPYC 7351P EPYC 7401P 2 x Xeon Gold 6138 20 40 60 80 100 SE +/- 0.49, N = 3 SE +/- 0.40, N = 3 SE +/- 0.04, N = 3 80.78 74.14 73.56 1. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018; 2. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018; 3. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests to stress the system's CPU. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Noise-Gaussian EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 40 80 120 160 200 SE +/- 1.52, N = 12 SE +/- 0.67, N = 3 105 135 149 158 165 184 86 180 158 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -lwebp -lwebpmux -mtune=power9 -mcpu=power9 -lwebp -lwebpmux 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread
Timed PHP Compilation This test times how long it takes to build PHP 5 with the Zend engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.1.9 Time To Compile EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 20 40 60 80 100 SE +/- 0.41, N = 3 SE +/- 0.33, N = 3 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 SE +/- 0.22, N = 3 SE +/- 0.06, N = 3 SE +/- 0.28, N = 3 SE +/- 0.14, N = 3 99.04 81.56 77.52 77.05 73.19 70.36 102.63 60.29 1. (CC) gcc options: -O3 -march=native -pedantic -ldl -lz -lm
R Benchmark This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better R Benchmark EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 0.1459 0.2918 0.4377 0.5836 0.7295 SE +/- 0.0028, N = 3 SE +/- 0.0020, N = 3 SE +/- 0.0005, N = 3 SE +/- 0.0016, N = 3 SE +/- 0.0019, N = 3 SE +/- 0.0042, N = 3 SE +/- 0.0005, N = 3 SE +/- 0.0056, N = 3 SE +/- 0.0042, N = 3 0.2931 0.3908 0.4455 0.4892 0.4638 0.4728 0.2899 0.4308 0.6483 1. R scripting front-end version 3.5.1 (2018-07-02)
Open Porous Media Git This is a test of a DUNE (Distributed and Unified Numerics Environment) module called OPM Benchmarks from the Open Porous Media project. Open Porous Media is a set of open-source tools concerning simulation of flow and transport of fluids in porous media. This test profile builds OPM and its dependencies from upstream Git. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Norne - Threads: 16 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 2 x Xeon Gold 6138 20 40 60 80 100 SE +/- 0.49, N = 3 SE +/- 0.40, N = 3 SE +/- 0.35, N = 3 SE +/- 0.79, N = 3 SE +/- 0.35, N = 3 SE +/- 0.05, N = 3 82.66 75.99 80.90 75.74 56.37 75.50 1. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018; 2. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018; 3. EPYC 7551: Build Time Thu Nov 8 18:40:03 EST 2018; 4. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 5. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018; 6. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;
IndigoBench This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Supercar EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 9 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 1.61 3.55 4.64 5.60 5.97 5.44 1.66 7.80
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Norne - Threads: 16 - Solver Time EPYC 7551 EPYC 7601 2 x EPYC 7601 20 40 60 80 100 SE +/- 0.36, N = 3 SE +/- 0.78, N = 3 SE +/- 0.35, N = 3 78.84 73.88 54.78 1. Build Time Thu Nov 8 18:40:03 EST 2018;
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 5M 10M 15M 20M 25M SE +/- 57635.42, N = 4 SE +/- 38957.95, N = 3 SE +/- 120495.49, N = 3 SE +/- 132910.28, N = 7 SE +/- 228446.84, N = 12 SE +/- 904286.44, N = 9 SE +/- 53788.68, N = 4 SE +/- 644813.65, N = 12 SE +/- 498192.34, N = 12 3412470 6568333 8529514 10765409 11160061 17118926 3229231 21250062 10422869 -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Replace EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 14K 28K 42K 56K 70K SE +/- 572.82, N = 12 SE +/- 46.91, N = 3 SE +/- 1847.72, N = 9 SE +/- 131.36, N = 3 SE +/- 3266.89, N = 12 SE +/- 678.19, N = 4 SE +/- 219.66, N = 3 SE +/- 505.28, N = 3 SE +/- 257.48, N = 3 25260 26700 29881 26399 41778 45576 54526 67473 52743 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm -rdynamic
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Append EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 14K 28K 42K 56K 70K SE +/- 1336.06, N = 9 SE +/- 147.85, N = 3 SE +/- 1229.56, N = 12 SE +/- 48.80, N = 3 SE +/- 92.84, N = 3 SE +/- 902.50, N = 3 SE +/- 96.81, N = 3 SE +/- 671.32, N = 12 SE +/- 190.56, N = 3 26038 26487 28893 26191 29843 45052 54686 67376 52605 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm -rdynamic
Open Porous Media Git OpenBenchmarking.org Seconds, Fewer Is Better Open Porous Media Git OPM Benchmark: Flow MPI Norne - Threads: 64 - Solver Time 2 x EPYC 7601 13 26 39 52 65 SE +/- 0.70, N = 3 56.55 1. Build Time Thu Nov 8 18:40:03 EST 2018;
AOBench AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 13 26 39 52 65 SE +/- 0.56, N = 12 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.69, N = 3 SE +/- 0.01, N = 3 49.65 49.16 47.45 47.33 44.47 44.51 43.18 35.70 59.87 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -lm -O3
IndigoBench This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Bedroom EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 0.8055 1.611 2.4165 3.222 4.0275 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 0.78 1.69 2.20 2.81 2.94 3.34 0.69 3.58
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20K 40K 60K 80K 100K SE +/- 5519.25, N = 12 SE +/- 1176.88, N = 12 SE +/- 428.81, N = 3 SE +/- 391.67, N = 3 SE +/- 1665.36, N = 12 SE +/- 2109.32, N = 12 SE +/- 575.65, N = 3 SE +/- 1607.29, N = 12 SE +/- 1052.87, N = 3 50039 45533 66800 55388 61957 53996 81317 96790 75241 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm -rdynamic
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2K 4K 6K 8K 10K SE +/- 37.42, N = 3 SE +/- 15.07, N = 3 SE +/- 10.13, N = 3 SE +/- 16.70, N = 3 SE +/- 11.95, N = 3 SE +/- 30.15, N = 3 SE +/- 2.08, N = 3 SE +/- 18.94, N = 3 6878 7007 7062 7001 7150 7650 8067 5113 1. (CC) gcc options: -O3 -march=native
Chaos Group V-RAY This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Chaos Group V-RAY 1.1.0 Mode: CPU EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 30 60 90 120 150 SE +/- 0.46, N = 3 SE +/- 0.26, N = 3 SE +/- 0.18, N = 3 SE +/- 0.20, N = 3 SE +/- 0.11, N = 3 SE +/- 0.20, N = 3 SE +/- 0.72, N = 3 SE +/- 0.12, N = 3 116.86 59.28 48.14 39.50 38.90 24.57 138.07 31.50
Minion Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Graceful EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 15 30 45 60 75 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 SE +/- 0.04, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 63.79 62.40 60.28 60.19 56.76 56.81 66.98 54.45 68.58 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 2048 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1300 2600 3900 5200 6500 SE +/- 36.27, N = 3 SE +/- 33.05, N = 3 SE +/- 28.93, N = 3 SE +/- 14.74, N = 3 SE +/- 19.00, N = 3 SE +/- 3.39, N = 3 SE +/- 19.86, N = 3 SE +/- 49.59, N = 3 SE +/- 11.43, N = 3 4850 5301 5215 5127 5781 5903 5238 5919 6088 1. (CC) gcc options: -pthread -O3 -march=native -lm
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests to stress the system's CPU. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Sharpen EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 0.58, N = 3 111 139 154 163 170 182 89 182 148 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -lwebp -lwebpmux -mtune=power9 -mcpu=power9 -lwebp -lwebpmux 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Enhanced EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 40 80 120 160 200 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 128 153 167 172 181 188 110 197 155 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -lwebp -lwebpmux -mtune=power9 -mcpu=power9 -lwebp -lwebpmux 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Swirl EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 50 100 150 200 250 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 155 169 179 182 191 194 142 208 165 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -lwebp -lwebpmux -mtune=power9 -mcpu=power9 -lwebp -lwebpmux 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Rotate EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 50 100 150 200 250 SE +/- 0.33, N = 3 171 171 176 178 187 188 176 208 198 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -lwebp -lwebpmux -mtune=power9 -mcpu=power9 -lwebp -lwebpmux 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: HWB Color Space EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 50 100 150 200 250 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.76, N = 3 182 187 193 197 206 208 176 226 184 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -lwebp -lwebpmux -mtune=power9 -mcpu=power9 -lwebp -lwebpmux 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread
Rust Mandelbrot This test profile is of the combined time for the serial and parallel Mandelbrot sets written in Rustlang via willi-kappler/mandel-rust. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rust Mandelbrot Time To Complete Serial/Parallel Mandelbrot EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 70.69 59.50 54.56 53.16 49.99 47.47 82.76 48.13 68.85 1. (CC) gcc options: -m64 -pie -nodefaultlibs
Apache Benchmark This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 5K 10K 15K 20K 25K SE +/- 42.54, N = 3 SE +/- 24.57, N = 3 SE +/- 116.37, N = 3 SE +/- 47.09, N = 3 SE +/- 313.51, N = 3 SE +/- 239.14, N = 3 SE +/- 26.94, N = 3 SE +/- 195.16, N = 3 SE +/- 191.16, N = 3 15364 16444 15923 15725 16363 15955 18608 22360 21403 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -shared -fPIC -pthread -O3
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 4096 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3K 6K 9K 12K 15K SE +/- 2.01, N = 3 SE +/- 213.76, N = 12 SE +/- 5.00, N = 3 SE +/- 8.05, N = 3 SE +/- 1.68, N = 3 SE +/- 7.46, N = 3 SE +/- 19.11, N = 3 SE +/- 2.97, N = 3 11730 11991 12613 11253 12647 12577 8470 4792 1. (CC) gcc options: -O3 -march=native
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: BMW27 - Compute: CPU-Only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 90 180 270 360 450 335.06 164.43 132.74 105.36 101.93 58.02 408.69 76.84
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 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 40 80 120 160 200 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.37, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 99.12 49.77 35.86 28.35 27.22 13.63 177.57 28.10 1. (CXX) g++ options: -fopenmp -O3 -march=native -O2
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Delete EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20K 40K 60K 80K 100K SE +/- 1332.03, N = 12 SE +/- 200.38, N = 3 SE +/- 574.84, N = 10 SE +/- 1876.44, N = 12 SE +/- 1632.16, N = 12 SE +/- 265.83, N = 3 SE +/- 422.79, N = 3 SE +/- 982.97, N = 3 SE +/- 347.42, N = 3 40913 42933 54399 61324 63499 63944 81660 97451 74707 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm -rdynamic
GNU MPC GNU MPC is a C library for the arithmetic of complex numbers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Global Score, More Is Better GNU MPC 1.1.0 Multi-Precision Benchmark EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 5.77, N = 3 SE +/- 12.02, N = 3 SE +/- 10.00, N = 3 SE +/- 10.00, N = 3 SE +/- 6.67, N = 3 SE +/- 3.33, N = 3 5590 5603 5780 5810 6140 6190 7073 8713 5460 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -lm -O3 -MT -MD -MP -MF
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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: LU.C EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 20K 40K 60K 80K 100K SE +/- 30.95, N = 3 SE +/- 592.65, N = 3 SE +/- 675.58, N = 3 SE +/- 75.17, N = 3 SE +/- 352.29, N = 3 SE +/- 702.85, N = 3 SE +/- 57.61, N = 3 SE +/- 423.98, N = 3 25279 44815 56107 36742 59969 114877 17836 76868 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 6K 12K 18K 24K 30K SE +/- 106.95, N = 3 SE +/- 130.34, N = 3 SE +/- 196.37, N = 3 SE +/- 109.45, N = 3 SE +/- 289.93, N = 3 SE +/- 343.02, N = 12 SE +/- 35.04, N = 12 SE +/- 347.42, N = 3 SE +/- 159.34, N = 3 5652 10992 13399 16608 17390 25458 3314 18976 28582 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
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 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.21, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 1.15, N = 9 SE +/- 0.03, N = 3 80.34 40.34 28.71 23.11 21.97 11.21 121.78 30.70 17.99 -march=native -march=native -march=native -march=native -march=native -march=native -march=native 1. (CC) gcc options: -lm -lpthread -O3
lzbench OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: XZ 0 - Process: Decompression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20 40 60 80 100 69 69 71 71 76 76 74 88 70 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: XZ 0 - Process: Compression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 8 16 24 32 40 SE +/- 0.33, N = 3 23 23 24 23 25 25 28 33 21 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
x265 This is a simple test of the x265 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 2.8 H.265 Video Encoding EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 8 16 24 32 40 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 7.16 10.63 11.30 11.08 11.70 13.50 20.11 34.89 1. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma
Gzip Compression This test measures the time needed to archive/compress two copies of the Linux 4.13 kernel source tree using Gzip compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Gzip Compression Linux Source Tree Archiving To .tar.gz EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 12 24 36 48 60 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 53.14 52.20 49.06 48.37 45.51 45.48 49.65 38.90 49.45
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 1.8.0-jumbo-1 Test: Traditional DES EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 60M 120M 180M 240M 300M SE +/- 30805.84, N = 3 SE +/- 104747.85, N = 3 SE +/- 359575.21, N = 3 SE +/- 250141.96, N = 3 SE +/- 1770832.28, N = 7 SE +/- 1261993.31, N = 3 SE +/- 31306.73, N = 3 SE +/- 277696.08, N = 3 43180000 83636667 107115000 137931000 136821857 258237667 27785667 154784333 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
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 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 400K 800K 1200K 1600K 2000K SE +/- 3209.41, N = 3 SE +/- 3875.74, N = 3 SE +/- 1972.15, N = 3 SE +/- 22818.33, N = 3 SE +/- 13270.20, N = 8 SE +/- 28692.91, N = 12 SE +/- 4847.40, N = 12 SE +/- 12714.82, N = 12 461295 930178 1114631 1178219 1139068 1726799 211148 969824 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
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 the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP Streamcluster EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 7 14 21 28 35 SE +/- 0.35, N = 7 SE +/- 0.17, N = 3 SE +/- 0.61, N = 9 SE +/- 1.66, N = 9 SE +/- 0.59, N = 12 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 SE +/- 0.25, N = 12 SE +/- 0.08, N = 3 26.73 15.09 17.25 21.48 18.31 20.64 21.12 13.29 28.57 1. (CXX) g++ options: -O2 -lOpenCL
Timed ImageMagick Compilation This test times how long it takes to build ImageMagick. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 13 26 39 52 65 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.34, N = 12 SE +/- 0.12, N = 3 SE +/- 0.31, N = 3 SE +/- 0.20, N = 3 SE +/- 0.10, N = 3 SE +/- 0.28, N = 3 49.91 33.47 30.88 29.77 28.02 23.27 57.23 22.83 24.65
Tesseract OCR Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.0.0-beta.3-249-g607e Time To OCR 7 Images EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 11 22 33 44 55 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.20, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 46.40 45.52 44.98 44.50 42.40 43.99 39.60 33.57 47.73
eSpeak Speech Engine This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better eSpeak Speech Engine 1.48.04 Text-To-Speech Synthesis EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 12 24 36 48 60 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.13, N = 3 SE +/- 0.20, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.23, N = 3 SE +/- 0.22, N = 3 SE +/- 0.05, N = 3 44.15 44.17 42.71 42.62 40.14 40.14 38.46 31.32 51.45 1. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions
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 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 71.23 36.69 28.96 23.01 22.61 12.82 109.43 19.02 20.33 -march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -march=native -lXpm -march=native -lSDL -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -mtune=power9 -mcpu=power9 -R/usr/lib -lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread 1. (CXX) g++ options: -pipe -O3 -ffast-math -pthread -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Composite EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 500 1000 1500 2000 2500 SE +/- 1.85, N = 4 SE +/- 21.22, N = 4 SE +/- 8.37, N = 4 SE +/- 5.49, N = 4 SE +/- 0.86, N = 4 SE +/- 1.60, N = 4 SE +/- 11.04, N = 4 SE +/- 5.38, N = 4 SE +/- 4.09, N = 4 1802 1780 1859 1863 1990 1991 1780 2177 1164
Sunflow Rendering System This test runs benchmarks of the Sunflow Rendering System. The Sunflow Rendering System is an open-source render engine for photo-realistic image synthesis with a ray-tracing core. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Sunflow Rendering System 0.07.2 Global Illumination + Image Synthesis EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 0.5445 1.089 1.6335 2.178 2.7225 SE +/- 0.05, N = 12 SE +/- 0.01, N = 3 SE +/- 0.02, N = 12 SE +/- 0.02, N = 12 SE +/- 0.01, N = 6 SE +/- 0.04, N = 9 SE +/- 0.03, N = 5 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 2.30 1.32 1.13 1.25 1.02 1.27 2.42 0.99 2.00
Compile Bench Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 500 1000 1500 2000 2500 SE +/- 0.99, N = 3 SE +/- 3.99, N = 3 SE +/- 1.71, N = 3 SE +/- 4.69, N = 3 SE +/- 2.35, N = 3 SE +/- 5.23, N = 3 SE +/- 55.98, N = 12 SE +/- 4.15, N = 3 SE +/- 7.21, N = 3 1401 1439 1471 1443 1551 1559 1217 1685 2343
Cryptsetup OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-whirlpool EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 200K 400K 600K 800K 1000K SE +/- 207.00, N = 3 SE +/- 945.21, N = 3 SE +/- 956.51, N = 3 SE +/- 1381.99, N = 3 SE +/- 1752.33, N = 3 SE +/- 284.00, N = 3 SE +/- 432.67, N = 3 570912 569262 587330 590420 628401 629397 668450 825217
OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup 2.0.4 PBKDF2-sha512 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 300K 600K 900K 1200K 1500K SE +/- 1997.34, N = 3 SE +/- 1216.16, N = 3 SE +/- 2932.33, N = 3 SE +/- 1774.58, N = 3 SE +/- 1482.13, N = 3 SE +/- 958.40, N = 3 SE +/- 4147.67, N = 3 SE +/- 13365.14, N = 3 849287 850659 878224 879193 939028 932898 1140200 1404599 817921
GNU Octave Benchmark This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 4.4.1 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 6 12 18 24 30 SE +/- 0.34, N = 3 SE +/- 0.21, N = 12 SE +/- 0.25, N = 12 SE +/- 0.13, N = 3 SE +/- 0.41, N = 3 SE +/- 0.27, N = 3 SE +/- 0.14, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 22.75 21.12 21.15 22.66 20.92 20.90 25.61 23.47 16.73
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 400 800 1200 1600 2000 SE +/- 0.67, N = 3 SE +/- 1.33, N = 3 SE +/- 4.26, N = 3 SE +/- 2.52, N = 3 SE +/- 0.88, N = 3 SE +/- 2.85, N = 3 SE +/- 4.81, N = 3 SE +/- 0.58, N = 3 SE +/- 4.37, N = 3 1668 1668 1615 1614 1514 1518 1405 1130 1815
lzbench OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Brotli 0 - Process: Decompression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 110 220 330 440 550 SE +/- 3.00, N = 3 SE +/- 0.33, N = 3 355 361 370 371 397 400 421 487 291 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Brotli 0 - Process: Compression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 80 160 240 320 400 SE +/- 1.33, N = 3 SE +/- 1.67, N = 3 306 306 319 319 339 342 300 359 320 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Cryptsetup OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup 2.0.4 PBKDF2-whirlpool 2 x 22-Core POWER9 176 Threads 90K 180K 270K 360K 450K SE +/- 243.33, N = 3 437393
lzbench OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Libdeflate 1 - Process: Decompression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 200 400 600 800 1000 SE +/- 4.00, N = 3 729 733 754 759 804 804 788 946 353 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Libdeflate 1 - Process: Compression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 40 80 120 160 200 SE +/- 0.58, N = 3 SE +/- 1.15, N = 3 SE +/- 1.20, N = 3 158 156 162 163 173 174 166 200 115 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Crafty This is a performance test of Crafty, an advanced open-source chess engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 1.6M 3.2M 4.8M 6.4M 8M SE +/- 2097.91, N = 3 SE +/- 8901.18, N = 3 SE +/- 5830.78, N = 3 SE +/- 3869.93, N = 3 SE +/- 19129.54, N = 3 SE +/- 8127.53, N = 3 SE +/- 5723.46, N = 3 SE +/- 11682.27, N = 3 5146918 5214390 5371574 5431520 5710603 5689725 6006573 7403335 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
lzbench OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Zstd 1 - Process: Decompression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 200 400 600 800 1000 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 1.00, N = 3 SE +/- 0.67, N = 3 751 750 776 782 826 828 770 917 797 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.org MB/s, More Is Better lzbench 2017-08-08 Test: Zstd 1 - Process: Compression EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 80 160 240 320 400 SE +/- 0.33, N = 3 292 292 303 305 325 326 298 359 281 1. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Node.js Octane Benchmark A Node.js version of the JavaScript Octane Benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better Node.js Octane Benchmark EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 8K 16K 24K 32K 40K SE +/- 32.66, N = 3 SE +/- 84.58, N = 3 SE +/- 104.41, N = 3 SE +/- 56.59, N = 3 SE +/- 40.22, N = 3 SE +/- 29.10, N = 3 SE +/- 36.71, N = 3 SE +/- 171.31, N = 3 SE +/- 111.34, N = 3 25686 26228 27391 27264 29242 29543 29739 36759 21850 1. Nodejs
v8.11.4
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 1024 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 5K 10K 15K 20K 25K SE +/- 205.54, N = 3 SE +/- 28.83, N = 3 SE +/- 165.68, N = 3 SE +/- 115.55, N = 3 SE +/- 52.59, N = 3 SE +/- 162.82, N = 3 SE +/- 265.38, N = 3 SE +/- 91.92, N = 3 14486 18894 19561 17944 20459 19018 17524 23220 1. (CC) gcc options: -pthread -O3 -march=native -lm
Y-Cruncher Y-Cruncher is a multi-threaded Pi benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.7.5.9481 Calculating 500M Pi Digits EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 13 26 39 52 65 SE +/- 0.23, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 53.42 29.18 23.04 21.56 19.33 15.61 56.50 12.66
Zstd Compression This test measures the time needed to compress a sample file (an Ubuntu file-system image) using Zstd compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 6 12 18 24 30 SE +/- 0.34, N = 7 SE +/- 0.24, N = 3 SE +/- 0.26, N = 12 SE +/- 0.24, N = 3 SE +/- 0.23, N = 3 SE +/- 0.31, N = 12 SE +/- 0.04, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 5 26.99 15.80 15.06 14.67 14.00 13.45 23.14 10.97 11.83 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -pthread -lz -llzma
Timed Apache Compilation This test times how long it takes to build the Apache HTTP Server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.7 Time To Compile EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 8 16 24 32 40 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 33.93 30.29 29.48 30.26 28.86 25.94 35.89 25.04 32.41
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: CPU Stress EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 3K 6K 9K 12K 15K SE +/- 0.84, N = 3 SE +/- 18.96, N = 3 SE +/- 78.60, N = 3 SE +/- 23.85, N = 3 SE +/- 94.71, N = 3 SE +/- 83.96, N = 3 SE +/- 0.76, N = 3 SE +/- 152.09, N = 3 SE +/- 22.81, N = 3 2050 4189 5797 7368 7700 15808 2208 13547 11656 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
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 1.3 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 2 x 22-Core POWER9 176 Threads 20K 40K 60K 80K 100K SE +/- 8.74, N = 3 SE +/- 15.90, N = 3 SE +/- 184.27, N = 3 SE +/- 30.75, N = 3 SE +/- 57.98, N = 3 SE +/- 40.45, N = 3 SE +/- 48.90, N = 3 11007 21958 30792 38667 40736 81871 48574 -masm=intel -march=native -masm=intel -march=native -masm=intel -march=native -masm=intel -march=native -masm=intel -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -fvisibility=hidden -lpthread -lcrypto -lz -ldl -lm -pthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Matrix Math EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 60K 120K 180K 240K 300K SE +/- 137.48, N = 3 SE +/- 313.84, N = 3 SE +/- 311.54, N = 3 SE +/- 196.62, N = 3 SE +/- 180.14, N = 3 SE +/- 512.47, N = 3 SE +/- 419.82, N = 3 SE +/- 1611.57, N = 3 SE +/- 191.50, N = 3 41846 84185 103356 132994 137445 293419 35402 217318 113069 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Crypto EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 3K 6K 9K 12K 15K SE +/- 0.69, N = 3 SE +/- 0.24, N = 3 SE +/- 46.58, N = 3 SE +/- 4.37, N = 3 SE +/- 37.19, N = 3 SE +/- 16.31, N = 3 SE +/- 0.72, N = 3 SE +/- 38.00, N = 3 SE +/- 65.89, N = 3 1609 3215 4494 5663 5918 11952 980 6203 8285 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Vector Math EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 30K 60K 90K 120K 150K SE +/- 3.26, N = 3 SE +/- 2.38, N = 3 SE +/- 78.64, N = 3 SE +/- 66.12, N = 3 SE +/- 102.55, N = 3 SE +/- 1218.29, N = 3 SE +/- 1.41, N = 3 SE +/- 1209.22, N = 3 SE +/- 36.72, N = 3 18477 36910 51190 64348 68691 136062 12411 76477 95173 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Stream This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 30K 60K 90K 120K 150K SE +/- 229.10, N = 5 SE +/- 9.78, N = 5 SE +/- 457.05, N = 5 SE +/- 933.91, N = 5 SE +/- 1329.22, N = 20 SE +/- 89.00, N = 5 SE +/- 1526.86, N = 20 83409 86857 84408 82083 158697 63795 130443 1. (CC) gcc options: -O3 -march=native -fopenmp
Swet Swet is a synthetic CPU/RAM benchmark, includes multi-processor test cases. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Swet 1.5.16 Average EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 130M 260M 390M 520M 650M SE +/- 4610229.20, N = 3 SE +/- 5491403.58, N = 3 SE +/- 1474249.14, N = 3 SE +/- 4965131.60, N = 3 SE +/- 2499215.04, N = 3 SE +/- 4256708.53, N = 3 SE +/- 4615543.22, N = 3 SE +/- 5231349.71, N = 3 SE +/- 771673.37, N = 3 485004712 479366975 505076073 506969513 528874816 491869221 526995827 614121047 293453929 1. (CC) gcc options: -lm -lpthread -lcurses -lrt
SciMark This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 500 1000 1500 2000 2500 SE +/- 1.51, N = 3 SE +/- 4.56, N = 3 SE +/- 2.09, N = 3 SE +/- 0.68, N = 3 SE +/- 4.34, N = 3 SE +/- 10.14, N = 3 SE +/- 2.52, N = 3 SE +/- 5.59, N = 3 SE +/- 0.73, N = 3 1347 1805 1859 1869 1940 1942 1913 2446 1255 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
Mencoder This test uses mplayer's mencoder utility and the libavcodec family for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Mencoder 1.3.0 AVI To LAVC EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 16 32 48 64 80 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 24.98 24.44 23.56 23.55 22.11 22.04 23.36 18.72 70.21 -fpie -pie -lfreetype -lfontconfig -fpie -pie -lfreetype -lfontconfig -fpie -pie -lfreetype -lfontconfig -fpie -pie -lfreetype -lfontconfig -fpie -pie -lfreetype -lfontconfig -fpie -pie -lfreetype -lfontconfig -fpie -pie -lfreetype -lfontconfig -fpie -pie -lasound -lfreetype -lfontconfig -lmad -lvorbisenc -lvorbis -logg -lasound -lmad -lvorbisenc -lvorbis -logg -std=gnu99 -O3 -mtune=power9 -mcpu=power9 -fno-tree-vectorize -maltivec -mabi=altivec -MMD -MP 1. (CC) gcc options: -lncurses -lrt -lpng -lz -ljpeg -lbz2 -lpthread -ldl -rdynamic -lm
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 1.8.0-jumbo-1 Test: Blowfish EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 15K 30K 45K 60K 75K SE +/- 46.49, N = 3 SE +/- 79.88, N = 3 SE +/- 663.77, N = 12 SE +/- 12.66, N = 3 SE +/- 87.49, N = 3 SE +/- 1082.68, N = 3 SE +/- 3.67, N = 3 SE +/- 312.53, N = 3 10107 19422 23048 26621 27591 71591 8005 48691 1. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
LuaJIT This test profile is a collection of Lua scripts/benchmarks run against a locally-built copy of LuaJIT upstream. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Composite EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 300 600 900 1200 1500 SE +/- 3.02, N = 3 SE +/- 0.97, N = 3 SE +/- 1.41, N = 3 SE +/- 1.42, N = 3 SE +/- 2.06, N = 3 SE +/- 3.64, N = 3 SE +/- 2.00, N = 3 SE +/- 0.60, N = 3 877 1026 1066 1071 1131 1124 1082 1356 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector
FLAC Audio Encoding This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 10 20 30 40 50 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 SE +/- 0.01, N = 5 13.66 13.64 13.18 13.14 12.37 12.34 11.49 9.28 44.21 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -logg -mtune=power9 -mcpu=power9 -logg 1. (CXX) g++ options: -O3 -fvisibility=hidden -lm
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 the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 16 32 48 64 80 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.03, N = 3 51.15 26.06 19.81 15.44 15.39 8.12 71.70 13.28 16.84 1. (CXX) g++ options: -O2 -lOpenCL
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.6 Test: auto-levels EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 23.76 23.21 23.07 24.07 22.97 22.39 26.05 23.70 42.54
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 130K 260K 390K 520K 650K SE +/- 800.35, N = 3 SE +/- 348.37, N = 3 SE +/- 476.01, N = 3 SE +/- 1386.84, N = 3 SE +/- 59.48, N = 3 SE +/- 895.53, N = 3 SE +/- 753.79, N = 3 SE +/- 1066.61, N = 3 SE +/- 1135.83, N = 3 362866 362169 372745 371645 399660 397929 479730 592004 332659
Go Benchmarks Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: build EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 6000M 12000M 18000M 24000M 30000M SE +/- 79725993.11, N = 3 SE +/- 71197974.92, N = 3 SE +/- 18848230.79, N = 3 SE +/- 18911874.89, N = 3 SE +/- 43011538.78, N = 3 SE +/- 38735390.67, N = 3 SE +/- 210856599.47, N = 3 SE +/- 69188517.89, N = 3 SE +/- 441335412.66, N = 4 23894546930 23606784874 23648119496 23875872285 22955552367 22058705682 23329557382 21160066842 28106987728
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SADD EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 400K 800K 1200K 1600K 2000K SE +/- 16974.58, N = 12 SE +/- 15101.94, N = 3 SE +/- 29072.20, N = 3 SE +/- 2539.67, N = 3 SE +/- 16774.42, N = 3 SE +/- 24288.76, N = 4 SE +/- 30871.66, N = 12 SE +/- 46193.94, N = 12 SE +/- 1492.96, N = 3 1384564 1474510 1531695 1594904 1656886 1652577 1654949 1968923 1301522 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Integer EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 7K 14K 21K 28K 35K 30603 33774 34064 31561 33834 25857 30552 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Integer EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 6K 12K 18K 24K 30K 26554 27313 26839 26613 29504 25545 29265 1. (CC) gcc options: -O3 -march=native
Rust Prime Benchmark Based on petehunt/rust-benchmark, this is a prime number benchmark that is multi-threaded and written in Rustlang. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rust Prime Benchmark Prime Number Test To 200,000,000 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 13 26 39 52 65 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 4 SE +/- 0.05, N = 12 57.82 29.07 22.65 17.02 15.63 8.14 23.03 4.48 3.54 1. (CC) gcc options: -m64 -pie -nodefaultlibs
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 7K 14K 21K 28K 35K 27297 28674 29101 24531 28859 31026 25497 26592 1. (CC) gcc options: -O3 -march=native
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.6 Test: rotate EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 21.94 20.49 20.18 20.12 19.14 17.80 22.89 20.71 29.31
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Floating Point EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 8K 16K 24K 32K 40K 32723 33278 32465 31974 31571 35322 25655 26862 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Floating Point EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 7K 14K 21K 28K 35K 27573 26811 28400 27347 28014 30580 25555 30702 1. (CC) gcc options: -O3 -march=native
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 7.1 1e12 Prime Number Generation EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 11 22 33 44 55 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 43.01 20.61 16.83 12.93 12.70 6.34 47.66 8.88 16.42 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -lpthread
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 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 0.49, N = 3 SE +/- 0.55, N = 3 SE +/- 32.65, N = 3 SE +/- 4.04, N = 3 SE +/- 19.16, N = 3 SE +/- 14.27, N = 3 SE +/- 1.20, N = 3 SE +/- 11.30, N = 3 SE +/- 40.66, N = 3 1242 2483 3503 4362 4554 9225 1286 7745 7377 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
GnuPG This test times how long it takes to encrypt a file using GnuPG. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GnuPG Linux 4.3 Package File Encryption EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 5 10 15 20 25 SE +/- 0.30, N = 4 SE +/- 0.34, N = 3 SE +/- 0.32, N = 3 SE +/- 0.27, N = 4 SE +/- 0.35, N = 3 SE +/- 0.27, N = 4 SE +/- 0.35, N = 3 SE +/- 0.25, N = 3 SE +/- 0.31, N = 3 18.99 19.45 18.74 18.39 17.36 17.23 17.82 14.42 18.58
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SET EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 400K 800K 1200K 1600K 2000K SE +/- 2556.44, N = 3 SE +/- 18027.86, N = 3 SE +/- 19395.95, N = 3 SE +/- 21411.56, N = 4 SE +/- 18354.77, N = 3 SE +/- 25872.16, N = 3 SE +/- 27918.55, N = 12 SE +/- 18319.51, N = 11 SE +/- 4793.10, N = 3 1123186 1308263 1318665 1310392 1367859 1396312 1391677 1784172 1086605 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Sudokut This is a test of Sudokut, which is a Sudoku puzzle solver written in Tcl. This test measures how long it takes to solve 100 Sudoku puzzles. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Sudokut 0.4 Total Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 20.30 20.59 19.92 19.91 18.78 18.07 13.83 11.11 19.44
dcraw This test times how long it takes to convert several high-resolution RAW NEF image files to PPM image format using dcraw. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better dcraw RAW To PPM Image Conversion EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 17.76 17.81 17.25 17.18 16.15 16.33 15.94 13.04 19.98 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -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. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: EP.C EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 400 800 1200 1600 2000 SE +/- 0.03, N = 3 SE +/- 1.08, N = 3 SE +/- 1.22, N = 3 SE +/- 0.51, N = 3 SE +/- 0.67, N = 3 SE +/- 0.70, N = 3 SE +/- 1.69, N = 3 SE +/- 10.17, N = 3 241 481 690 835 892 1777 259 1627 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2K 4K 6K 8K 10K SE +/- 5.39, N = 3 SE +/- 5.81, N = 3 SE +/- 3.27, N = 3 SE +/- 7.99, N = 3 SE +/- 4.06, N = 3 SE +/- 34.11, N = 3 SE +/- 1.29, N = 3 SE +/- 21.51, N = 3 6847 6977 6994 7144 7100 7600 8031 4923 1. (CC) gcc options: -O3 -march=native
x264 This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 30 60 90 120 150 SE +/- 0.23, N = 3 SE +/- 0.39, N = 3 SE +/- 0.53, N = 3 SE +/- 1.47, N = 12 SE +/- 0.50, N = 3 SE +/- 12.24, N = 9 SE +/- 0.23, N = 3 SE +/- 2.11, N = 3 SE +/- 2.16, N = 10 55.91 93.66 106.13 99.50 106.75 131.75 35.48 112.63 49.36 -lavformat -lavcodec -lavutil -lswscale -m64 -march=native -lavformat -lavcodec -lavutil -lswscale -m64 -march=native -lavformat -lavcodec -lavutil -lswscale -m64 -march=native -lavformat -lavcodec -lavutil -lswscale -m64 -march=native -lavformat -lavcodec -lavutil -lswscale -m64 -march=native -lavformat -lavcodec -lavutil -lswscale -m64 -march=native -m64 -march=native -lavformat -lavcodec -lavutil -lswscale -m64 -march=native -lavformat -lavcodec -lavutil -lswscale -mtune=power9 -mcpu=power9 -maltivec -mabi=altivec -mvsx 1. (CC) gcc options: -ldl -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: LPUSH EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 400K 800K 1200K 1600K 2000K SE +/- 19273.98, N = 3 SE +/- 21415.56, N = 12 SE +/- 19390.48, N = 3 SE +/- 13067.87, N = 3 SE +/- 14251.32, N = 3 SE +/- 3726.29, N = 3 SE +/- 11136.38, N = 3 SE +/- 13534.43, N = 3 SE +/- 2532.17, N = 3 986285 1064769 1107291 1119292 1197469 1215090 1381396 1724352 888114 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 1024 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1600 3200 4800 6400 8000 SE +/- 74.35, N = 3 SE +/- 7.61, N = 3 SE +/- 19.47, N = 3 SE +/- 18.94, N = 3 SE +/- 39.74, N = 3 SE +/- 19.93, N = 3 SE +/- 45.92, N = 3 SE +/- 4.37, N = 3 SE +/- 23.58, N = 3 5418 6001 6249 5803 6587 6623 5660 7572 6596 1. (CC) gcc options: -pthread -O3 -march=native -lm
GIMP GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.6 Test: resize EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.20, N = 3 14.48 13.48 13.23 13.48 12.86 12.34 16.49 15.38 17.95
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: GET EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 500K 1000K 1500K 2000K 2500K SE +/- 10123.48, N = 3 SE +/- 26137.53, N = 12 SE +/- 10607.60, N = 3 SE +/- 19052.51, N = 3 SE +/- 12124.99, N = 3 SE +/- 21300.51, N = 3 SE +/- 28285.41, N = 3 SE +/- 12798.88, N = 3 SE +/- 16810.41, N = 3 1546525 1716532 1731232 1869551 1838396 1902826 1941319 2475379 1622844 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
Bork File Encrypter Bork is a small, cross-platform file encryption utility. It is written in Java and designed to be included along with the files it encrypts for long-term storage. This test measures the amount of time it takes to encrypt a sample file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bork File Encrypter 1.4 File Encryption Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 13.49 13.44 13.02 12.87 12.23 12.21 9.90 7.65 22.15
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 12K 24K 36K 48K 60K SE +/- 153.98, N = 3 SE +/- 336.87, N = 3 SE +/- 134.20, N = 3 SE +/- 7.97, N = 3 SE +/- 42.58, N = 3 SE +/- 244.62, N = 3 SE +/- 1332.84, N = 12 SE +/- 328.49, N = 3 24551 24403 25075 25514 27233 26877 30270 55983 1. (CC) gcc options: -pthread -O3 -march=native -lm
FFmpeg This test uses FFmpeg for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 4.0.2 H.264 HD To NTSC DV EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 Xeon Silver 4108 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 11.24 10.68 10.70 10.83 10.51 18.34 -llzma 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lxcb-shape -lxcb-xfixes -pthread -lbz2 -O3 -march=native -std=c11 -fomit-frame-pointer -fPIC -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT
DaCapo Benchmark This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1600 3200 4800 6400 8000 SE +/- 47.64, N = 4 SE +/- 94.65, N = 4 SE +/- 94.68, N = 4 SE +/- 48.95, N = 4 SE +/- 83.82, N = 4 SE +/- 29.70, N = 4 SE +/- 8.54, N = 4 SE +/- 26.42, N = 4 7435 7075 6813 6942 6743 6437 5278 4378 6985
LAME MP3 Encoding LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 11.59 11.59 11.20 11.18 10.51 10.51 12.32 9.91 15.89 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lncurses -lm
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 1024 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3K 6K 9K 12K 15K SE +/- 37.55, N = 3 SE +/- 1.31, N = 3 SE +/- 2.86, N = 3 SE +/- 45.65, N = 3 SE +/- 1.14, N = 3 SE +/- 6.11, N = 3 SE +/- 1.29, N = 3 SE +/- 17.22, N = 3 11828 12607 12689 12867 12722 12757 8376 4792 1. (CC) gcc options: -O3 -march=native
Timed MAFFT Alignment This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.392 Multiple Sequence Alignment EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1.0913 2.1826 3.2739 4.3652 5.4565 SE +/- 0.13, N = 11 SE +/- 0.05, N = 12 SE +/- 0.06, N = 5 SE +/- 0.10, N = 9 SE +/- 0.03, N = 3 SE +/- 0.05, N = 12 SE +/- 0.04, N = 3 SE +/- 0.06, N = 12 SE +/- 0.26, N = 11 4.07 3.43 3.65 3.95 3.45 3.45 4.85 3.50 4.30 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
N-Queens This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 19.42 9.73 6.84 5.58 5.29 2.78 30.23 4.84 1. (CC) gcc options: -static -fopenmp -O3 -march=native
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 2048 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 13K 26K 39K 52K 65K SE +/- 59.33, N = 3 SE +/- 19.92, N = 3 SE +/- 199.16, N = 3 SE +/- 60.64, N = 3 SE +/- 58.67, N = 3 SE +/- 185.90, N = 3 SE +/- 1432.58, N = 12 SE +/- 279.19, N = 3 24724 24743 25430 25605 27240 27128 32149 60079 1. (CC) gcc options: -pthread -O3 -march=native -lm
Sysbench This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Events Per Second, More Is Better Sysbench 2018-07-28 Test: CPU EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 20K 40K 60K 80K 100K SE +/- 3.34, N = 3 SE +/- 5.28, N = 3 SE +/- 36.44, N = 3 SE +/- 114.17, N = 3 SE +/- 135.35, N = 3 SE +/- 80.32, N = 3 SE +/- 1.14, N = 3 SE +/- 350.34, N = 3 12101 24152 34901 42239 44722 88749 9642 60216 1. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=native -rdynamic -ldl -laio -lm
Timed HMMer Search This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 9.20 8.37 8.03 8.23 7.92 6.73 14.32 12.28 1. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 512 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 5K 10K 15K 20K 25K SE +/- 76.85, N = 3 SE +/- 38.39, N = 3 SE +/- 51.96, N = 3 SE +/- 21.39, N = 3 SE +/- 16.42, N = 3 SE +/- 12.50, N = 3 SE +/- 131.09, N = 3 SE +/- 60.05, N = 3 20754 21167 21880 21925 23368 23339 18553 23160 1. (CC) gcc options: -pthread -O3 -march=native -lm
Darktable Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.4.4 Test: Masskrug - Acceleration: CPU-only EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3 6 9 12 15 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 10.21 6.98 6.42 6.49 6.07 7.13 8.88 5.38
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2K 4K 6K 8K 10K SE +/- 6.49, N = 3 SE +/- 5.44, N = 3 SE +/- 6.17, N = 3 SE +/- 13.37, N = 3 SE +/- 4.86, N = 3 SE +/- 5.16, N = 3 SE +/- 19.50, N = 3 SE +/- 15.97, N = 3 6885 7040 7052 7145 7143 7599 7974 4905 1. (CC) gcc options: -O3 -march=native
Ogg Encoding This test times how long it takes to encode a sample WAV file to Ogg format using vorbis-tools, libvorbis, and libogg. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Ogg Encoding 1.3.3 WAV To Ogg EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 2 x Xeon Gold 6138 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 8.36 8.38 8.16 8.07 7.61 7.57 6.72 1. (CC) gcc options: -O2 -ffast-math -fsigned-char -O3 -march=native -logg
Smallpt Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 15.35 7.92 5.79 4.68 4.51 2.57 20.49 4.09 4.10 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -fopenmp -O3
Git This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2 4 6 8 10 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 7.93 7.86 7.63 7.50 7.15 7.10 7.45 6.20 8.67 1. git version 2.19.1
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 1024 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 13K 26K 39K 52K 65K SE +/- 118.17, N = 3 SE +/- 125.44, N = 3 SE +/- 35.80, N = 3 SE +/- 67.10, N = 3 SE +/- 55.97, N = 3 SE +/- 73.92, N = 3 SE +/- 1582.83, N = 9 SE +/- 168.06, N = 3 24302 24331 25372 25149 26946 26982 38678 60471 1. (CC) gcc options: -pthread -O3 -march=native -lm
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.72, N = 12 98.24 96.68 96.19 94.89 93.48 92.47 99.49 96.43 65.38 -march=native -lm -march=native -lm -march=native -lm -march=native -lm -march=native -lm -march=native -lm -march=native -march=native -lm -mtune=power9 -mcpu=power9 -lm 1. (CC) gcc options: -O3
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3K 6K 9K 12K 15K SE +/- 102.38, N = 12 SE +/- 114.53, N = 12 SE +/- 1.25, N = 3 SE +/- 74.27, N = 3 SE +/- 114.40, N = 3 SE +/- 110.80, N = 12 SE +/- 149.77, N = 12 SE +/- 6.17, N = 3 8635 8851 9463 9410 9982 9802 11830 14926 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 13.90, N = 3 SE +/- 23.73, N = 3 SE +/- 11.98, N = 3 SE +/- 7.47, N = 3 SE +/- 57.58, N = 3 SE +/- 38.36, N = 3 SE +/- 63.56, N = 3 SE +/- 97.54, N = 3 SE +/- 33.82, N = 3 7179 7151 7351 7451 7879 7878 7316 8743 7318 1. (CC) gcc options: -pthread -O3 -march=native -lm
libjpeg-turbo tjbench tjbench is a JPEG decompression/compression benchmark part of libjpeg-turbo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 1.5.3 Test: Decompression Throughput EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 40 80 120 160 200 SE +/- 1.11, N = 3 SE +/- 1.38, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 1.27, N = 3 SE +/- 0.14, N = 3 SE +/- 0.17, N = 3 SE +/- 0.02, N = 3 132 132 137 138 147 146 133 163 106 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
PolyBench-C PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: Correlation Computation EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 6.05 6.00 5.77 5.82 5.47 5.46 7.11 5.75 1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: Covariance Computation EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 6.04 6.01 5.76 5.80 5.48 5.44 7.10 5.75 1. (CC) gcc options: -O3 -march=native
Bullet Physics Engine This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Raytests EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1.1183 2.2366 3.3549 4.4732 5.5915 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.48 3.47 3.35 3.34 3.14 3.14 3.29 2.67 4.97 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 256 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 7K 14K 21K 28K 35K SE +/- 115.24, N = 3 SE +/- 40.93, N = 3 SE +/- 31.25, N = 3 SE +/- 60.62, N = 3 SE +/- 51.01, N = 3 SE +/- 30.28, N = 3 SE +/- 214.30, N = 3 SE +/- 535.19, N = 12 18622 18827 19490 19451 20641 20718 25409 34786 1. (CC) gcc options: -pthread -O3 -march=native -lm
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 21.03 20.49 19.99 19.55 18.88 19.55 17.98 16.05 32.71 -march=native -lm -march=native -lm -march=native -lm -march=native -lm -march=native -lm -march=native -lm -march=native -march=native -lm -mtune=power9 -mcpu=power9 -lm 1. (CC) gcc options: -O3
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: LU.A EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 30K 60K 90K 120K 150K SE +/- 124.40, N = 3 SE +/- 1902.85, N = 12 SE +/- 1428.44, N = 12 SE +/- 211.73, N = 3 SE +/- 38.80, N = 3 SE +/- 725.20, N = 3 SE +/- 20.75, N = 3 SE +/- 886.73, N = 3 23683 43353 60871 54846 70764 133328 19173 86125 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 512 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3K 6K 9K 12K 15K SE +/- 1.84, N = 3 SE +/- 0.99, N = 3 SE +/- 4.38, N = 3 SE +/- 2.69, N = 3 SE +/- 0.98, N = 3 SE +/- 1.99, N = 3 SE +/- 7.38, N = 3 SE +/- 1.11, N = 3 11891 12667 12723 12945 12749 12839 8453 4829 1. (CC) gcc options: -O3 -march=native
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 256 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 5K 10K 15K 20K 25K SE +/- 17.32, N = 3 SE +/- 80.86, N = 3 SE +/- 76.96, N = 3 SE +/- 121.76, N = 3 SE +/- 34.33, N = 3 SE +/- 337.65, N = 3 SE +/- 38.49, N = 3 20730 20739 21475 21574 22781 22920 19310 24425 1. (CC) gcc options: -pthread -O3 -march=native -lm
Optcarrot Optcarrot is an NES emulator benchmark for the Ruby language. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better Optcarrot Optimized Benchmark EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 30 60 90 120 150 SE +/- 0.17, N = 4 SE +/- 0.09, N = 4 SE +/- 0.11, N = 4 SE +/- 0.14, N = 4 SE +/- 0.67, N = 4 SE +/- 0.14, N = 4 SE +/- 0.63, N = 4 SE +/- 0.20, N = 4 SE +/- 0.03, N = 4 54.99 55.71 56.79 57.35 60.74 59.82 92.91 114.67 49.07 1. EPYC 7251: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 2. EPYC 7351P: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 3. EPYC 7401P: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 4. EPYC 7551: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 5. EPYC 7601: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 6. 2 x EPYC 7601: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 7. Xeon Silver 4108: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 8. 2 x Xeon Gold 6138: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu] 9. 2 x 22-Core POWER9 176 Threads: ruby 2.5.1p57 (2018-03-29 revision 63029) [powerpc64le-linux-gnu]
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 512 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 11K 22K 33K 44K 55K SE +/- 124.63, N = 3 SE +/- 44.88, N = 3 SE +/- 205.23, N = 3 SE +/- 95.84, N = 3 SE +/- 106.81, N = 3 SE +/- 30.27, N = 3 SE +/- 441.60, N = 7 SE +/- 25.41, N = 3 22612 22565 23368 23496 25143 24876 35404 49508 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 512 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1700 3400 5100 6800 8500 SE +/- 20.19, N = 3 SE +/- 8.00, N = 3 SE +/- 7.39, N = 3 SE +/- 5.90, N = 3 SE +/- 29.10, N = 3 SE +/- 8.96, N = 3 SE +/- 14.48, N = 3 SE +/- 79.27, N = 3 SE +/- 11.10, N = 3 6315 6858 7055 7120 7545 7501 6440 7761 7066 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 2048 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 5.51, N = 3 SE +/- 45.42, N = 3 SE +/- 2.04, N = 3 SE +/- 20.79, N = 3 SE +/- 41.75, N = 3 SE +/- 35.10, N = 3 SE +/- 100.55, N = 3 SE +/- 71.15, N = 3 SE +/- 38.68, N = 3 7276 7210 7474 7522 7984 7967 7342 9016 7350 1. (CC) gcc options: -pthread -O3 -march=native -lm
Tachyon This is a test of the threaded Tachyon, a parallel ray-tracing system. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.98.9 Total Time EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 4 SE +/- 0.02, N = 12 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 7.69 3.94 2.86 2.37 2.37 1.48 9.78 2.49 1. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 64 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 4K 8K 12K 16K 20K SE +/- 54.37, N = 3 SE +/- 20.27, N = 3 SE +/- 103.85, N = 3 SE +/- 99.65, N = 3 SE +/- 44.76, N = 3 SE +/- 57.51, N = 3 SE +/- 527.45, N = 12 SE +/- 202.32, N = 3 12062 12165 12707 12717 13420 13458 12611 16593 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 32 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 8K 16K 24K 32K 40K SE +/- 4.73, N = 3 SE +/- 8.14, N = 3 SE +/- 5.78, N = 3 SE +/- 12.60, N = 3 SE +/- 22.84, N = 3 SE +/- 12.35, N = 3 SE +/- 92.02, N = 3 SE +/- 682.47, N = 12 23284 23287 24075 24125 25666 25704 30575 37123 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 256 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 85.65, N = 7 SE +/- 14.67, N = 3 SE +/- 48.04, N = 3 SE +/- 13.08, N = 3 SE +/- 3.90, N = 3 SE +/- 32.99, N = 3 SE +/- 6.86, N = 3 SE +/- 20.18, N = 3 SE +/- 13.47, N = 3 6825 6969 7144 7214 7707 7688 6578 7973 7242 1. (CC) gcc options: -pthread -O3 -march=native -lm
Parboil The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 12 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 4.95 2.82 2.36 1.96 1.85 1.90 7.80 1.87 2.69 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
PolyBench-C PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: 3 Matrix Multiplications EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 1.0035 2.007 3.0105 4.014 5.0175 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 4.32 3.88 3.87 3.72 3.66 3.64 4.46 3.26 1. (CC) gcc options: -O3 -march=native
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 1024 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 6.43, N = 3 SE +/- 2.11, N = 3 SE +/- 19.94, N = 3 SE +/- 6.48, N = 3 SE +/- 4.44, N = 3 SE +/- 7.34, N = 3 SE +/- 71.02, N = 3 SE +/- 47.78, N = 3 SE +/- 22.02, N = 3 7703 7707 7966 7999 8512 8507 7568 9321 7571 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 3K 6K 9K 12K 15K SE +/- 9.41, N = 3 SE +/- 13.43, N = 3 SE +/- 6.86, N = 3 SE +/- 2.68, N = 3 SE +/- 12.03, N = 3 SE +/- 12.06, N = 3 SE +/- 144.76, N = 5 SE +/- 24.61, N = 3 SE +/- 123.10, N = 12 9648 9591 9971 9997 10626 10640 10140 12779 8803 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 128 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 5K 10K 15K 20K 25K SE +/- 80.88, N = 3 SE +/- 25.40, N = 3 SE +/- 12.39, N = 3 SE +/- 45.95, N = 3 SE +/- 13.92, N = 3 SE +/- 33.78, N = 3 SE +/- 245.69, N = 3 SE +/- 418.34, N = 3 14579 14638 15166 15175 16184 16160 16347 21540 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 64 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 17.75, N = 3 SE +/- 8.42, N = 3 SE +/- 6.97, N = 3 SE +/- 24.19, N = 3 SE +/- 16.83, N = 3 SE +/- 135.30, N = 3 SE +/- 26.89, N = 3 SE +/- 75.64, N = 3 SE +/- 14.92, N = 3 7049 7071 7289 7283 7781 7652 8277 10137 7072 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 128 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 6K 12K 18K 24K 30K SE +/- 51.87, N = 3 SE +/- 122.86, N = 3 SE +/- 64.58, N = 3 SE +/- 21.31, N = 3 SE +/- 82.15, N = 3 SE +/- 38.53, N = 3 SE +/- 59.42, N = 3 SE +/- 228.34, N = 3 22690 22609 23452 20663 25024 25097 22949 28501 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 64 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 7K 14K 21K 28K 35K SE +/- 32.97, N = 3 SE +/- 5.24, N = 3 SE +/- 54.06, N = 3 SE +/- 70.97, N = 3 SE +/- 40.48, N = 3 SE +/- 21.30, N = 3 SE +/- 312.71, N = 3 SE +/- 322.58, N = 3 23052 23048 23857 23888 25417 25509 25878 32447 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 64 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 3K 6K 9K 12K 15K SE +/- 3.94, N = 3 SE +/- 5.93, N = 3 SE +/- 12.00, N = 3 SE +/- 1.39, N = 3 SE +/- 8.58, N = 3 SE +/- 106.80, N = 3 SE +/- 91.03, N = 3 SE +/- 2.65, N = 3 SE +/- 6.67, N = 3 7157 7151 7411 7411 7894 7790 9507 11866 6825 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 512 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 28.29, N = 3 SE +/- 28.83, N = 3 SE +/- 7.78, N = 3 SE +/- 35.70, N = 3 SE +/- 29.16, N = 3 SE +/- 7.17, N = 3 SE +/- 38.44, N = 3 SE +/- 67.87, N = 3 SE +/- 43.59, N = 3 7458 7462 7762 7724 8230 8290 7833 9441 7735 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 128 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 30.56, N = 3 SE +/- 17.41, N = 3 SE +/- 4.97, N = 3 SE +/- 24.98, N = 3 SE +/- 4.01, N = 3 SE +/- 18.87, N = 3 SE +/- 62.88, N = 3 SE +/- 4.79, N = 3 SE +/- 0.62, N = 3 7089 7053 7256 7255 7775 7776 7377 9006 7276 1. (CC) gcc options: -pthread -O3 -march=native -lm
TSCP This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 300K 600K 900K 1200K 1500K SE +/- 1315.49, N = 5 SE +/- 433.33, N = 5 SE +/- 1594.13, N = 5 SE +/- 2113.08, N = 5 SE +/- 674.17, N = 5 SE +/- 2138.20, N = 5 SE +/- 1453.67, N = 5 SE +/- 625.35, N = 5 773139 772047 800096 803842 853127 854735 960221 1186000 1. (CC) gcc options: -O3 -march=native
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 128 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 7.85, N = 3 SE +/- 29.20, N = 3 SE +/- 36.41, N = 3 SE +/- 78.20, N = 3 SE +/- 12.89, N = 3 SE +/- 29.00, N = 3 SE +/- 50.56, N = 3 SE +/- 102.73, N = 3 SE +/- 11.93, N = 3 6823 6772 6950 7107 7505 7548 7879 9827 7203 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 256 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2K 4K 6K 8K 10K SE +/- 33.97, N = 3 SE +/- 54.99, N = 3 SE +/- 48.89, N = 3 SE +/- 24.61, N = 3 SE +/- 31.92, N = 3 SE +/- 35.12, N = 3 SE +/- 51.13, N = 3 SE +/- 67.52, N = 3 SE +/- 29.31, N = 3 7389 7346 7597 7664 8091 8187 7589 9489 8251 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 32 EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 3K 6K 9K 12K 15K SE +/- 6.78, N = 3 SE +/- 0.00, N = 3 SE +/- 11.05, N = 3 SE +/- 10.33, N = 3 SE +/- 11.35, N = 3 SE +/- 4.41, N = 3 SE +/- 140.16, N = 3 SE +/- 138.99, N = 3 SE +/- 30.24, N = 3 9225 7211 9537 9560 10169 10163 10179 12627 7478 1. (CC) gcc options: -pthread -O3 -march=native -lm
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sin EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 143 164 132 132 136 136 117 105
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: cos EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 40 80 120 160 200 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 144 164 132 132 137 137 117 106
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2K 4K 6K 8K 10K SE +/- 2.48, N = 3 SE +/- 2.83, N = 3 SE +/- 3.11, N = 3 SE +/- 5.34, N = 3 SE +/- 6.21, N = 3 SE +/- 6.53, N = 3 SE +/- 2.79, N = 3 SE +/- 4.45, N = 3 6068 6164 6195 6278 6258 6875 7989 4950 1. (CC) gcc options: -O3 -march=native
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: tanh EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 9 18 27 36 45 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.81, N = 12 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 36.20 41.41 33.33 33.34 35.19 34.50 30.96 27.87
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 1.3095 2.619 3.9285 5.238 6.5475 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.09 5.82 4.69 4.69 4.83 4.83 4.22 3.80
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 1.3073 2.6146 3.9219 5.2292 6.5365 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.08 5.81 4.68 4.68 4.82 4.82 3.63 3.27
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 1.3073 2.6146 3.9219 5.2292 6.5365 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.08 5.81 4.68 4.68 4.82 4.82 3.63 3.26
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.95 5.65 4.55 4.55 4.70 4.70 9.98 8.98
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 128 MiB EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 3K 6K 9K 12K 15K SE +/- 2.19, N = 3 SE +/- 4.63, N = 3 SE +/- 4.25, N = 3 SE +/- 1.60, N = 3 SE +/- 8.53, N = 3 SE +/- 1.74, N = 3 SE +/- 13.65, N = 3 SE +/- 1.77, N = 3 11908 12660 12729 12985 12807 12943 8522 4980 1. (CC) gcc options: -O3 -march=native
Java SciMark This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 300 600 900 1200 1500 SE +/- 0.10, N = 4 SE +/- 0.18, N = 4 SE +/- 0.12, N = 4 SE +/- 0.27, N = 4 SE +/- 0.62, N = 4 SE +/- 0.40, N = 4 SE +/- 4.20, N = 4 SE +/- 5.90, N = 4 SE +/- 0.16, N = 4 1219 1220 1262 1264 1346 1346 1154 1415 797
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Dense LU Matrix Factorization EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1100 2200 3300 4400 5500 SE +/- 11.21, N = 4 SE +/- 13.67, N = 4 SE +/- 33.70, N = 4 SE +/- 31.76, N = 4 SE +/- 10.41, N = 4 SE +/- 8.68, N = 4 SE +/- 46.87, N = 4 SE +/- 31.04, N = 4 SE +/- 12.22, N = 4 3488 3496 3579 3595 3857 3861 4245 5128 2342
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Sparse Matrix Multiply EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 500 1000 1500 2000 2500 SE +/- 0.74, N = 4 SE +/- 0.65, N = 4 SE +/- 0.35, N = 4 SE +/- 0.56, N = 4 SE +/- 0.63, N = 4 SE +/- 0.54, N = 4 SE +/- 2.59, N = 4 SE +/- 2.01, N = 4 SE +/- 0.60, N = 4 1901 1899 1967 1970 2097 2098 1663 2055 1028
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Fast Fourier Transform EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 300 600 900 1200 1500 SE +/- 4.80, N = 4 SE +/- 109.56, N = 4 SE +/- 7.82, N = 4 SE +/- 9.27, N = 4 SE +/- 9.53, N = 4 SE +/- 1.67, N = 4 SE +/- 3.47, N = 4 SE +/- 10.59, N = 4 SE +/- 8.55, N = 4 1286 1170 1333 1330 1423 1413 1102 1379 896
OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Monte Carlo EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 300 600 900 1200 1500 SE +/- 0.00, N = 4 SE +/- 0.12, N = 4 SE +/- 2.34, N = 4 SE +/- 0.00, N = 4 SE +/- 0.14, N = 4 SE +/- 2.92, N = 4 SE +/- 0.36, N = 4 SE +/- 0.11, N = 4 SE +/- 0.17, N = 4 1114 1114 1155 1155 1230 1235 737 911 756
Bullet Physics Engine This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Convex Trimesh EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 0.4545 0.909 1.3635 1.818 2.2725 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.49 1.48 1.44 1.43 1.34 1.34 1.45 1.17 2.02 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Prim Trimesh EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 0.3488 0.6976 1.0464 1.3952 1.744 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.27 1.26 1.21 1.21 1.14 1.14 1.22 0.99 1.55 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 136 Ragdolls EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 0.9405 1.881 2.8215 3.762 4.7025 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.80 3.44 3.32 3.31 3.11 3.12 3.30 2.69 4.18 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Convex EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 6.20 5.92 5.70 5.69 5.35 5.35 5.70 4.63 8.82 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Stack EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 7.05 6.42 6.17 6.16 5.84 5.81 5.79 4.69 7.72 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 3000 Fall EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 6.20 5.55 5.36 5.33 5.05 5.06 5.26 4.23 6.32 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
SciMark This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 400 800 1200 1600 2000 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.29, N = 3 SE +/- 0.28, N = 3 SE +/- 0.17, N = 3 SE +/- 1.86, N = 3 SE +/- 0.34, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 1526 1530 1582 1586 1688 1686 1511 1867 1248 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 1300 2600 3900 5200 6500 SE +/- 4.16, N = 3 SE +/- 10.24, N = 3 SE +/- 12.85, N = 3 SE +/- 4.87, N = 3 SE +/- 0.36, N = 3 SE +/- 72.81, N = 3 SE +/- 11.60, N = 3 SE +/- 24.65, N = 3 SE +/- 2.48, N = 3 2293 4486 4642 4640 4796 4844 4755 5856 3440 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 600 1200 1800 2400 3000 SE +/- 9.64, N = 3 SE +/- 13.38, N = 3 SE +/- 3.30, N = 3 SE +/- 4.24, N = 3 SE +/- 22.23, N = 3 SE +/- 28.59, N = 3 SE +/- 3.73, N = 3 SE +/- 2.94, N = 3 SE +/- 0.21, N = 3 2203 2302 2342 2385 2441 2398 2224 3009 1120 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 150 300 450 600 750 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.43, N = 3 SE +/- 2.13, N = 3 SE +/- 1.45, N = 3 206 203 208 210 219 227 411 685 305 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 200 400 600 800 1000 SE +/- 0.05, N = 3 SE +/- 0.17, N = 3 SE +/- 0.16, N = 3 SE +/- 0.08, N = 3 SE +/- 0.47, N = 3 SE +/- 0.06, N = 3 SE +/- 0.30, N = 3 SE +/- 0.22, N = 3 SE +/- 0.05, N = 3 504 504 521 523 556 556 661 816 162 -march=native -march=native -march=native -march=native -march=native -march=native -march=native -march=native -mtune=power9 -mcpu=power9 1. (CC) gcc options: -O3 -lm
LuaJIT This test profile is a collection of Lua scripts/benchmarks run against a locally-built copy of LuaJIT upstream. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Jacobi Successive Over-Relaxation EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 300 600 900 1200 1500 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.21, N = 3 SE +/- 0.16, N = 3 SE +/- 0.24, N = 3 SE +/- 0.24, N = 3 SE +/- 0.26, N = 3 1284 1289 1334 1336 1422 1423 1125 1388 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector
OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Dense LU Matrix Factorization EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 700 1400 2100 2800 3500 SE +/- 8.94, N = 3 SE +/- 4.68, N = 3 SE +/- 7.32, N = 3 SE +/- 6.54, N = 3 SE +/- 14.00, N = 3 SE +/- 13.01, N = 3 SE +/- 9.44, N = 3 SE +/- 3.91, N = 3 1713 2434 2543 2564 2695 2672 2622 3202 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector
OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Sparse Matrix Multiply EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 300 600 900 1200 1500 SE +/- 6.24, N = 3 SE +/- 1.77, N = 3 SE +/- 0.20, N = 3 SE +/- 2.97, N = 3 SE +/- 4.48, N = 3 SE +/- 6.85, N = 3 SE +/- 0.54, N = 3 SE +/- 0.87, N = 3 829 838 868 868 918 899 958 1189 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector
OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Fast Fourier Transform EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 120 240 360 480 600 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.23, N = 3 SE +/- 0.62, N = 3 SE +/- 0.35, N = 3 SE +/- 0.13, N = 3 SE +/- 0.57, N = 3 SE +/- 0.29, N = 3 217 224 229 231 238 248 332 537 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector
OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.0.5 Test: Monte Carlo EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 100 200 300 400 500 SE +/- 0.13, N = 3 SE +/- 0.60, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 SE +/- 0.29, N = 3 343 345 356 357 380 380 375 462 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector
Stream This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 40K 80K 120K 160K 200K SE +/- 165.28, N = 5 SE +/- 20.37, N = 5 SE +/- 417.61, N = 5 SE +/- 1153.78, N = 5 SE +/- 1994.93, N = 5 SE +/- 55.56, N = 5 SE +/- 1051.54, N = 5 94328 99688 96936 93632 174091 49169 114790 1. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 40K 80K 120K 160K 200K SE +/- 453.73, N = 5 SE +/- 9.67, N = 5 SE +/- 590.87, N = 5 SE +/- 1186.43, N = 5 SE +/- 2485.73, N = 5 SE +/- 53.43, N = 5 SE +/- 2206.28, N = 5 94020 100146 97224 93875 176076 49018 111538 1. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 30K 60K 90K 120K 150K SE +/- 10.28, N = 5 SE +/- 11.68, N = 5 SE +/- 133.33, N = 5 SE +/- 1054.13, N = 5 SE +/- 1900.60, N = 5 SE +/- 46.94, N = 5 SE +/- 384.23, N = 5 83749 86788 85076 82672 154691 44560 109172 1. (CC) gcc options: -O3 -march=native -fopenmp
Compile Bench Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree EPYC 7251 EPYC 7351P EPYC 7401P EPYC 7551 EPYC 7601 2 x EPYC 7601 Xeon Silver 4108 2 x Xeon Gold 6138 2 x 22-Core POWER9 176 Threads 500 1000 1500 2000 2500 SE +/- 9.33, N = 3 SE +/- 4.64, N = 3 SE +/- 5.75, N = 3 SE +/- 5.86, N = 3 SE +/- 0.00, N = 3 SE +/- 31.91, N = 3 SE +/- 25.29, N = 3 SE +/- 13.50, N = 3 SE +/- 8.76, N = 3 2136 2169 2207 2158 2334 2379 2149 2535 1583
EPYC 7251 Processor: AMD EPYC 7251 8-Core @ 2.10GHz (8 Cores / 16 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe 126GB, Monitor: VE228, Network: Broadcom NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 128 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
Testing initiated at 13 November 2018 05:25 by user phoronix.
EPYC 7351P Processor: AMD EPYC 7351P 16-Core @ 2.40GHz (16 Cores / 32 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe 126GB, Monitor: VE228, Network: Broadcom NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 128 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
Testing initiated at 12 November 2018 06:13 by user phoronix.
EPYC 7401P Processor: AMD EPYC 7401P 24-Core @ 2.00GHz (24 Cores / 48 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe 126GB, Monitor: VE228, Network: Broadcom NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 128 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
Testing initiated at 11 November 2018 07:36 by user phoronix.
EPYC 7551 Processor: AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe 126GB, Monitor: VE228, Network: Broadcom NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 128 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
Testing initiated at 8 November 2018 20:56 by user phoronix.
EPYC 7601 Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe 126GB, Monitor: VE228, Network: Broadcom NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 128 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
Testing initiated at 10 November 2018 11:47 by user phoronix.
2 x EPYC 7601 Processor: 2 x AMD EPYC 7601 32-Core @ 3.07GHz (64 Cores / 128 Threads), Motherboard: Dell 02MJ3T (1.2.5 BIOS), Chipset: AMD Family 17h, Memory: 516096MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: Matrox Matrox G200eW3, Monitor: VE228, Network: Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 128 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwPython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp
Testing initiated at 9 November 2018 14:26 by user phoronix.
Xeon Silver 4108 Processor: Intel Xeon Silver 4108 @ 3.00GHz (8 Cores / 16 Threads), Motherboard: TYAN S7100AG2NR (V3.03 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 23552MB, Disk: Samsung SSD 970 EVO 250GB, Graphics: ASPEED ASPEED Family, Audio: Realtek ALC892, Monitor: VE228, Network: Intel I350 Gigabit Connection
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 256 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersavePython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable
Testing initiated at 14 November 2018 20:47 by user phoronix.
2 x Xeon Gold 6138 Processor: 2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads), Motherboard: TYAN S7106 (V1.01 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 96256MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: llvmpipe 93GB, Monitor: VE228, Network: Intel I210 Gigabit Connection
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (x86_64), Desktop: GNOME Shell 3.30.1, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 3.3 Mesa 18.2.2 (LLVM 7.0 256 bits), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: intel_pstate powersavePython Notes: Python 2.7.15+ + Python 3.6.7Security Notes: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable
Testing initiated at 14 November 2018 07:39 by user phoronix.
2 x 22-Core POWER9 176 Threads Processor: POWER9 altivec supported @ 3.80GHz (44 Cores / 176 Threads), Motherboard: PowerNV T2P9D01 REV 1.01, Memory: 65536MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: ASPEED ASPEED Family, Monitor: VE228, Network: Broadcom NetXtreme BCM5719 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.19.1-041901-generic (ppc64le), Compiler: GCC 8.2.0, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-mtune=power9-mcpu=power9 CFLAGS=-O3-mtune=power9-mcpu=power9Compiler Notes: --build=powerpc64le-linux-gnu --disable-libphobos --disable-multilib --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-secureplt --enable-shared --enable-targets=powerpcle-linux --enable-threads=posix --host=powerpc64le-linux-gnu --program-prefix=powerpc64le-linux-gnu- --target=powerpc64le-linux-gnu --with-cpu=power8 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-long-double-128 -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: powernv-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.7
Testing initiated at 15 November 2018 17:39 by user phoronix.