Debian 11 server benchmarks by Michael Larabel for a future article with Intel and AMD hardware.
Xeon 8380 2P: Debian 10.10 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Debian 10, Kernel: 4.19.0-17-amd64 (x86_64), Desktop: GNOME Shell 3.30.2, Display Server: X Server, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
EPYC 7763 2P: Debian 10.10 Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads)Motherboard: AMD DAYTONA_X (RYM1001D BIOS)Chipset: AMD Starship/MatisseMemory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
EPYC 7763 2P: Debian 11.0 OS: Debian 11, Kernel: 5.10.0-8-amd64 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)Python Notes: Python 3.9.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Xeon 8380 2P: Debian 11.0 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads)Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS)Chipset: Intel Device 0998Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Debian 11, Kernel: 5.10.0-8-amd64 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)Python Notes: Python 3.9.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Compiler File-System Screen Resolution Vulkan Xeon 8380 2P EPYC 7763 2P Xeon 8380 2P Debian 10.10 Debian 10.10 Debian 11.0 Debian 11.0 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 504GB 7682GB INTEL SSDPF2KX076TZ ASPEED VE228 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP Debian 10 4.19.0-17-amd64 (x86_64) GNOME Shell 3.30.2 X Server GCC 8.3.0 ext4 1920x1080 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads) AMD DAYTONA_X (RYM1001D BIOS) AMD Starship/Matisse 2 x Mellanox MT27710 Debian 11 5.10.0-8-amd64 (x86_64) GNOME Shell 3.38.4 GCC 10.2.1 20210110 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Intel Device 0998 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP X Server 1.20.11 1.0.2 1024x768 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler Details - Xeon 8380 2P: Debian 10.10: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - EPYC 7763 2P: Debian 10.10: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - EPYC 7763 2P: Debian 11.0: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Xeon 8380 2P: Debian 11.0: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Xeon 8380 2P: Debian 10.10: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 - EPYC 7763 2P: Debian 10.10: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119 - EPYC 7763 2P: Debian 11.0: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119 - Xeon 8380 2P: Debian 11.0: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270 Java Details - Xeon 8380 2P: Debian 10.10: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1) - EPYC 7763 2P: Debian 10.10: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1) - EPYC 7763 2P: Debian 11.0: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2) - Xeon 8380 2P: Debian 11.0: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2) Python Details - Xeon 8380 2P: Debian 10.10: Python 2.7.16 + Python 3.7.3 - EPYC 7763 2P: Debian 10.10: Python 2.7.16 + Python 3.7.3 - EPYC 7763 2P: Debian 11.0: Python 3.9.2 - Xeon 8380 2P: Debian 11.0: Python 3.9.2 Security Details - Xeon 8380 2P: Debian 10.10: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected - EPYC 7763 2P: Debian 10.10: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - EPYC 7763 2P: Debian 11.0: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected - Xeon 8380 2P: Debian 11.0: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
rocksdb: Read Rand Write Rand rocksdb: Update Rand stress-ng: System V Message Passing renaissance: In-Memory Database Shootout pgbench: 100 - 100 - Read Only - Average Latency pgbench: 100 - 100 - Read Only stress-ng: Crypto svt-hevc: 10 - Bosphorus 1080p rocksdb: Rand Fill svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p rocksdb: Rand Read svt-vp9: VMAF Optimized - Bosphorus 1080p rodinia: OpenMP LavaMD rocksdb: Seq Fill stress-ng: Malloc svt-av1: Preset 8 - Bosphorus 4K stress-ng: Glibc C String Functions svt-hevc: 7 - Bosphorus 1080p svt-vp9: Visual Quality Optimized - Bosphorus 1080p pyperformance: django_template asmfish: 1024 Hash Memory, 26 Depth svt-hevc: 1 - Bosphorus 1080p renaissance: Savina Reactors.IO stockfish: Total Time svt-av1: Preset 4 - Bosphorus 4K pyperformance: regex_compile build-apache: Time To Compile build-ffmpeg: Time To Compile pyperformance: pickle_pure_python pyperformance: chaos pyperformance: 2to3 build-nodejs: Time To Compile viennacl: CPU BLAS - dGEMV-T build-llvm: Ninja pyperformance: json_loads build-linux-kernel: Time To Compile npb: BT.C renaissance: Apache Spark PageRank viennacl: CPU BLAS - sDOT cassandra: Writes npb: CG.C phpbench: PHP Benchmark Suite build-llvm: Unix Makefiles numpy: namd: ATPase Simulation - 327,506 Atoms renaissance: Akka Unbalanced Cobwebbed Tree rodinia: OpenMP HotSpot3D gromacs: MPI CPU - water_GMX50_bare pyperformance: raytrace tnn: CPU - SqueezeNet v2 pybench: Total For Average Test Times lammps: Rhodopsin Protein pyperformance: crypto_pyaes pyperformance: pathlib pyperformance: nbody pyperformance: go rocksdb: Read While Writing ctx-clock: Context Switch Time redis: SET redis: LPUSH redis: SADD redis: LPOP pgbench: 100 - 250 - Read Write - Average Latency pgbench: 100 - 250 - Read Write pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 100 - Read Write viennacl: CPU BLAS - sAXPY yafaray: Total Time For Sample Scene renaissance: Genetic Algorithm Using Jenetics + Futures renaissance: Scala Dotty rodinia: OpenMP Streamcluster npb: FT.C npb: EP.D Xeon 8380 2P EPYC 7763 2P Xeon 8380 2P Debian 10.10 Debian 10.10 Debian 11.0 Debian 11.0 924973 98999 6811966.15 18344.4 0.200 500723 12801.98 262.59 105709 212.26 315786554 214.28 44.973 106954 1431913434.68 32.925 7441922.78 169.31 178.29 84 178415877 29.07 21135.0 181927486 2.666 263 32.786 21.576 663 161 508 91.863 634 115.958 35.2 23.466 196078.72 5161.7 518 162273 40281.43 696512 176.808 349.31 0.27214 32337.8 104.973 9.002 488 72.872 996 25.593 152 30.0 168 281 9456177 197 1621978.77 1294255.02 1704483.96 2175922.05 8.819 28364 4.804 20823 627 110.682 6758.7 1300.9 8.061 86158.53 3586.88 2736354 227942 10330862.26 8362.2 0.092 1089858 27404.94 505.94 204348 392.19 605696264 391.63 26.933 198990 2869325583.07 57.443 12069712.93 297.04 316.11 56.1 293138816 46.18 12875.0 293175558 3.808 184 21.907 17.513 448 123 342 66.731 783 88.738 25.2 17.572 259687.67 4363.1 402 209032 46540.98 583370 162.052 413.56 0.22714 36698.7 94.001 9.959 508 68.777 1040 28.051 108 19.1 130 260 15341112 122 1572054.70 1415875.02 1621685.12 2139255.95 5.725 44469 2.355 42490 743 137.381 2928.0 922.6 8.063 111226.41 4988.33 2296152 188028 15918301.22 9020.6 0.090 1109390 28094.72 572.17 181629 438.74 647540344 438.77 22.025 190362 2837926434.87 65.214 14357589.21 325.76 337.18 48.4 297587716 46.57 13591.6 297021258 4.089 168 22.319 14.229 440 108 353 71.573 930 96.642 24.9 19.334 257121.36 4550.5 470 193729 49354.99 607606 179.781 426.63 0.22688 36821.1 92.590 10.147 475 68.257 982 32.773 106 17.7 125 258 16290934 147 1743277.50 1532789.82 2004012.64 2204683.33 4.141 60608 1.765 57604 1061 54.250 3351.3 899.7 7.729 123519.45 9945.18 842654 89854 8987819.52 18748.4 0.090 1106588 13490.32 267.46 93862 207.43 367360276 216.76 37.777 98770 1439057052.08 32.554 7917452.97 171.38 183.67 58.4 175018835 27.96 21000.4 182536509 2.560 199 34.209 16.207 607 136 505 98.839 642 127.811 29.9 24.561 189492.52 5929.3 526 165577 39507.12 722404 199.600 383.23 0.27247 32700.5 104.002 9.069 462 72.841 980 24.351 125 25.3 143 301 9863087 210 1751650.19 1492781.42 2033925.82 2482298.75 8.823 28356 3.186 31408 2243 77.594 7003.2 1245.1 7.935 88493.51 8858.02 OpenBenchmarking.org
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read Random Write Random Xeon 8380 2P EPYC 7763 2P 600K 1200K 1800K 2400K 3000K SE +/- 7187.45, N = 3 SE +/- 5393.40, N = 3 SE +/- 3677.40, N = 3 SE +/- 1551.48, N = 3 924973 2736354 2296152 842654 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Debian 10.10 Debian 11.0 OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Update Random Xeon 8380 2P EPYC 7763 2P 50K 100K 150K 200K 250K SE +/- 229.83, N = 3 SE +/- 2421.52, N = 15 SE +/- 2364.67, N = 3 SE +/- 231.53, N = 3 98999 227942 188028 89854 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing Xeon 8380 2P EPYC 7763 2P 3M 6M 9M 12M 15M SE +/- 89010.61, N = 3 SE +/- 103831.56, N = 15 SE +/- 124919.37, N = 15 SE +/- 82511.89, N = 3 6811966.15 10330862.26 15918301.22 8987819.52 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: In-Memory Database Shootout Xeon 8380 2P EPYC 7763 2P 4K 8K 12K 16K 20K SE +/- 113.86, N = 3 SE +/- 95.08, N = 3 SE +/- 75.93, N = 3 SE +/- 180.05, N = 3 18344.4 8362.2 9020.6 18748.4
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency Xeon 8380 2P EPYC 7763 2P 0.045 0.09 0.135 0.18 0.225 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 5 SE +/- 0.000, N = 3 0.200 0.092 0.090 0.090 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Debian 10.10 Debian 11.0 OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only Xeon 8380 2P EPYC 7763 2P 200K 400K 600K 800K 1000K SE +/- 2917.23, N = 3 SE +/- 6710.36, N = 3 SE +/- 12260.17, N = 5 SE +/- 4824.14, N = 3 500723 1089858 1109390 1106588 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto Xeon 8380 2P EPYC 7763 2P 6K 12K 18K 24K 30K SE +/- 41.95, N = 3 SE +/- 156.93, N = 3 SE +/- 33.31, N = 3 SE +/- 56.52, N = 3 12801.98 27404.94 28094.72 13490.32 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p Xeon 8380 2P EPYC 7763 2P 120 240 360 480 600 SE +/- 2.91, N = 4 SE +/- 3.22, N = 3 SE +/- 2.37, N = 3 SE +/- 1.92, N = 15 262.59 505.94 572.17 267.46 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Fill Xeon 8380 2P EPYC 7763 2P 40K 80K 120K 160K 200K SE +/- 6.33, N = 3 SE +/- 1692.24, N = 9 SE +/- 169.49, N = 3 SE +/- 336.83, N = 3 105709 204348 181629 93862 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Xeon 8380 2P EPYC 7763 2P 100 200 300 400 500 SE +/- 1.53, N = 3 SE +/- 2.19, N = 3 SE +/- 3.16, N = 3 SE +/- 2.65, N = 3 212.26 392.19 438.74 207.43 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Random Read Xeon 8380 2P EPYC 7763 2P 140M 280M 420M 560M 700M SE +/- 939653.16, N = 3 SE +/- 1133761.15, N = 3 SE +/- 3465595.70, N = 3 SE +/- 3332857.15, N = 15 315786554 605696264 647540344 367360276 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p Xeon 8380 2P EPYC 7763 2P 100 200 300 400 500 SE +/- 1.99, N = 7 SE +/- 2.40, N = 3 SE +/- 3.54, N = 3 SE +/- 2.06, N = 3 214.28 391.63 438.77 216.76 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -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 select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Xeon 8380 2P EPYC 7763 2P 10 20 30 40 50 SE +/- 0.19, N = 3 SE +/- 0.19, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 44.97 26.93 22.03 37.78 1. (CXX) g++ options: -O2 -lOpenCL
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Sequential Fill Xeon 8380 2P EPYC 7763 2P 40K 80K 120K 160K 200K SE +/- 38.55, N = 3 SE +/- 191.32, N = 3 SE +/- 141.18, N = 3 SE +/- 203.10, N = 3 106954 198990 190362 98770 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc Xeon 8380 2P EPYC 7763 2P 600M 1200M 1800M 2400M 3000M SE +/- 1935415.45, N = 3 SE +/- 7005388.59, N = 3 SE +/- 2079960.32, N = 3 SE +/- 1322257.28, N = 3 1431913434.68 2869325583.07 2837926434.87 1439057052.08 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 8 - Input: Bosphorus 4K Xeon 8380 2P EPYC 7763 2P 15 30 45 60 75 SE +/- 0.13, N = 3 SE +/- 0.32, N = 3 SE +/- 0.29, N = 3 SE +/- 0.22, N = 3 32.93 57.44 65.21 32.55 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions Xeon 8380 2P EPYC 7763 2P 3M 6M 9M 12M 15M SE +/- 71343.56, N = 3 SE +/- 10977.89, N = 3 SE +/- 29361.60, N = 3 SE +/- 83997.23, N = 3 7441922.78 12069712.93 14357589.21 7917452.97 1. (CC) gcc options: -O2 -std=gnu99 -lm -lcrypt -lrt -lz -ldl -lpthread -lc
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p Xeon 8380 2P EPYC 7763 2P 70 140 210 280 350 SE +/- 2.16, N = 3 SE +/- 0.94, N = 3 SE +/- 2.23, N = 3 SE +/- 1.85, N = 4 169.31 297.04 325.76 171.38 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Xeon 8380 2P EPYC 7763 2P 70 140 210 280 350 SE +/- 1.38, N = 15 SE +/- 3.96, N = 3 SE +/- 2.26, N = 3 SE +/- 0.36, N = 3 178.29 316.11 337.18 183.67 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p Xeon 8380 2P EPYC 7763 2P 11 22 33 44 55 SE +/- 0.11, N = 3 SE +/- 0.21, N = 3 SE +/- 0.28, N = 3 SE +/- 0.29, N = 3 29.07 46.18 46.57 27.96 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Savina Reactors.IO Xeon 8380 2P EPYC 7763 2P 5K 10K 15K 20K 25K SE +/- 209.23, N = 6 SE +/- 110.92, N = 12 SE +/- 65.28, N = 3 SE +/- 135.17, N = 3 21135.0 12875.0 13591.6 21000.4
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time Xeon 8380 2P EPYC 7763 2P 60M 120M 180M 240M 300M SE +/- 1879580.86, N = 15 SE +/- 2732137.08, N = 15 SE +/- 1249676.02, N = 3 SE +/- 1241246.00, N = 13 181927486 293175558 297021258 182536509 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8.7 Encoder Mode: Preset 4 - Input: Bosphorus 4K Xeon 8380 2P EPYC 7763 2P 0.92 1.84 2.76 3.68 4.6 SE +/- 0.031, N = 3 SE +/- 0.017, N = 3 SE +/- 0.009, N = 3 SE +/- 0.016, N = 3 2.666 3.808 4.089 2.560 1. (CXX) g++ options: -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Timed Node.js Compilation This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile Xeon 8380 2P EPYC 7763 2P 20 40 60 80 100 SE +/- 0.97, N = 3 SE +/- 0.19, N = 3 SE +/- 0.60, N = 3 SE +/- 0.26, N = 3 91.86 66.73 71.57 98.84
ViennaCL ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T Xeon 8380 2P EPYC 7763 2P 200 400 600 800 1000 SE +/- 1.96, N = 5 SE +/- 5.85, N = 12 SE +/- 7.43, N = 15 SE +/- 2.51, N = 12 634 783 930 642 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Xeon 8380 2P EPYC 7763 2P 60K 120K 180K 240K 300K SE +/- 395.43, N = 3 SE +/- 197.74, N = 2 SE +/- 283.81, N = 3 SE +/- 2528.51, N = 3 196078.72 259687.67 257121.36 189492.52 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Apache Spark PageRank Xeon 8380 2P EPYC 7763 2P 1300 2600 3900 5200 6500 SE +/- 73.30, N = 12 SE +/- 29.40, N = 3 SE +/- 51.18, N = 3 SE +/- 62.80, N = 3 5161.7 4363.1 4550.5 5929.3
ViennaCL ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sDOT Xeon 8380 2P EPYC 7763 2P 110 220 330 440 550 SE +/- 5.14, N = 5 SE +/- 1.84, N = 12 SE +/- 5.74, N = 15 SE +/- 2.72, N = 12 518 402 470 526 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Xeon 8380 2P EPYC 7763 2P 11K 22K 33K 44K 55K SE +/- 206.96, N = 3 SE +/- 37.63, N = 2 SE +/- 696.79, N = 15 SE +/- 240.20, N = 3 40281.43 46540.98 49354.99 39507.12 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Xeon 8380 2P EPYC 7763 2P 150K 300K 450K 600K 750K SE +/- 5555.16, N = 3 SE +/- 4097.68, N = 3 SE +/- 2571.82, N = 3 SE +/- 4567.18, N = 3 696512 583370 607606 722404
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.
Debian 10.10 Debian 11.0 OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Xeon 8380 2P EPYC 7763 2P 0.0613 0.1226 0.1839 0.2452 0.3065 SE +/- 0.00040, N = 3 SE +/- 0.00014, N = 3 SE +/- 0.00152, N = 3 SE +/- 0.00028, N = 3 0.27214 0.22714 0.22688 0.27247
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Akka Unbalanced Cobwebbed Tree Xeon 8380 2P EPYC 7763 2P 8K 16K 24K 32K 40K SE +/- 70.51, N = 3 SE +/- 225.38, N = 3 SE +/- 328.50, N = 3 SE +/- 388.94, N = 4 32337.8 36698.7 36821.1 32700.5
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D Xeon 8380 2P EPYC 7763 2P 20 40 60 80 100 SE +/- 0.82, N = 10 SE +/- 1.26, N = 15 SE +/- 1.30, N = 13 SE +/- 0.21, N = 3 104.97 94.00 92.59 104.00 1. (CXX) g++ options: -O2 -lOpenCL
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021.2 Implementation: MPI CPU - Input: water_GMX50_bare Xeon 8380 2P EPYC 7763 2P 3 6 9 12 15 SE +/- 0.038, N = 3 SE +/- 0.034, N = 3 SE +/- 0.030, N = 3 9.002 9.959 10.147 9.069 1. (CXX) g++ options: -O3 -pthread
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Xeon 8380 2P EPYC 7763 2P 16 32 48 64 80 SE +/- 0.06, N = 3 SE +/- 0.73, N = 5 SE +/- 0.63, N = 3 SE +/- 0.11, N = 3 72.87 68.78 68.26 72.84 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Xeon 8380 2P EPYC 7763 2P 200 400 600 800 1000 SE +/- 3.38, N = 3 SE +/- 14.52, N = 3 SE +/- 1.53, N = 3 SE +/- 1.76, N = 3 996 1040 982 980
Debian 10.10 Debian 11.0 OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib Xeon 8380 2P EPYC 7763 2P 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.46, N = 12 30.0 19.1 17.7 25.3
Debian 10.10 Debian 11.0 OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: go Xeon 8380 2P EPYC 7763 2P 70 140 210 280 350 SE +/- 3.36, N = 14 SE +/- 0.58, N = 3 SE +/- 6.06, N = 15 281 260 258 301
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.22.1 Test: Read While Writing Xeon 8380 2P EPYC 7763 2P 3M 6M 9M 12M 15M SE +/- 280022.49, N = 14 SE +/- 145400.63, N = 15 SE +/- 342025.49, N = 12 SE +/- 120135.63, N = 4 9456177 15341112 16290934 9863087 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Redis Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET Xeon 8380 2P EPYC 7763 2P 400K 800K 1200K 1600K 2000K SE +/- 36820.67, N = 15 SE +/- 27252.76, N = 15 SE +/- 51019.41, N = 15 SE +/- 21341.26, N = 4 1621978.77 1572054.70 1743277.50 1751650.19 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Debian 10.10 Debian 11.0 OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: LPUSH Xeon 8380 2P EPYC 7763 2P 300K 600K 900K 1200K 1500K SE +/- 24657.83, N = 13 SE +/- 34916.81, N = 12 SE +/- 37826.18, N = 15 SE +/- 10237.69, N = 3 1294255.02 1415875.02 1532789.82 1492781.42 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Debian 10.10 Debian 11.0 OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SADD Xeon 8380 2P EPYC 7763 2P 400K 800K 1200K 1600K 2000K SE +/- 21924.92, N = 3 SE +/- 30995.30, N = 12 SE +/- 75850.49, N = 12 SE +/- 37455.60, N = 12 1704483.96 1621685.12 2004012.64 2033925.82 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Debian 10.10 Debian 11.0 OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: LPOP Xeon 8380 2P EPYC 7763 2P 500K 1000K 1500K 2000K 2500K SE +/- 35378.74, N = 15 SE +/- 57897.76, N = 15 SE +/- 31946.73, N = 15 SE +/- 18880.19, N = 3 2175922.05 2139255.95 2204683.33 2482298.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
PostgreSQL pgbench This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average Latency Xeon 8380 2P EPYC 7763 2P 2 4 6 8 10 SE +/- 0.013, N = 3 SE +/- 0.196, N = 15 SE +/- 0.063, N = 15 SE +/- 0.019, N = 3 8.819 5.725 4.141 8.823 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Debian 10.10 Debian 11.0 OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 250 - Mode: Read Write Xeon 8380 2P EPYC 7763 2P 13K 26K 39K 52K 65K SE +/- 40.32, N = 3 SE +/- 1608.03, N = 15 SE +/- 898.39, N = 15 SE +/- 62.46, N = 3 28364 44469 60608 28356 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency Xeon 8380 2P EPYC 7763 2P 1.0809 2.1618 3.2427 4.3236 5.4045 SE +/- 0.038, N = 3 SE +/- 0.032, N = 3 SE +/- 0.062, N = 15 SE +/- 0.034, N = 3 4.804 2.355 1.765 3.186 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Debian 10.10 Debian 11.0 OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write Xeon 8380 2P EPYC 7763 2P 12K 24K 36K 48K 60K SE +/- 165.20, N = 3 SE +/- 579.08, N = 3 SE +/- 1886.93, N = 15 SE +/- 337.26, N = 3 20823 42490 57604 31408 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
ViennaCL ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY Xeon 8380 2P EPYC 7763 2P 500 1000 1500 2000 2500 SE +/- 2.16, N = 5 SE +/- 13.64, N = 12 SE +/- 13.01, N = 15 SE +/- 27.77, N = 12 627 743 1061 2243 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
YafaRay YafaRay is an open-source physically based montecarlo ray-tracing engine. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.5.1 Total Time For Sample Scene Xeon 8380 2P EPYC 7763 2P 30 60 90 120 150 SE +/- 11.34, N = 15 SE +/- 1.41, N = 3 SE +/- 0.34, N = 3 SE +/- 1.78, N = 15 110.68 137.38 54.25 77.59 1. (CXX) g++ options: -std=c++11 -pthread -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype
Renaissance Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Genetic Algorithm Using Jenetics + Futures Xeon 8380 2P EPYC 7763 2P 1500 3000 4500 6000 7500 SE +/- 49.06, N = 3 SE +/- 57.84, N = 12 SE +/- 54.92, N = 12 SE +/- 33.01, N = 3 6758.7 2928.0 3351.3 7003.2
Debian 10.10 Debian 11.0 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.12 Test: Scala Dotty Xeon 8380 2P EPYC 7763 2P 300 600 900 1200 1500 SE +/- 14.18, N = 3 SE +/- 26.22, N = 12 SE +/- 8.31, N = 3 SE +/- 39.86, N = 12 1300.9 922.6 899.7 1245.1
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Xeon 8380 2P EPYC 7763 2P 2 4 6 8 10 SE +/- 0.054, N = 3 SE +/- 0.140, N = 12 SE +/- 0.070, N = 15 SE +/- 0.101, N = 15 8.061 8.063 7.729 7.935 1. (CXX) g++ options: -O2 -lOpenCL
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Debian 10.10 Debian 11.0 OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Xeon 8380 2P EPYC 7763 2P 30K 60K 90K 120K 150K SE +/- 1673.59, N = 15 SE +/- 1030.14, N = 10 SE +/- 634.26, N = 3 SE +/- 1611.88, N = 15 86158.53 111226.41 123519.45 88493.51 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
Debian 10.10 Debian 11.0 OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Xeon 8380 2P EPYC 7763 2P 2K 4K 6K 8K 10K SE +/- 3.35, N = 3 SE +/- 53.96, N = 5 SE +/- 211.44, N = 15 SE +/- 102.35, N = 4 3586.88 4988.33 9945.18 8858.02 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent_core -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.1.0
Geometric Mean Of All Test Results Debian 10.10 Debian 11.0 OpenBenchmarking.org Geometric Mean, More Is Better Geometric Mean Of All Test Results Result Composite - Debian 11 Benchmarks Xeon 8380 2P EPYC 7763 2P 80 160 240 320 400 226.48 322.82 348.26 249.98
Hide Result
Xeon 8380 2P: Debian 10.10 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Debian 10, Kernel: 4.19.0-17-amd64 (x86_64), Desktop: GNOME Shell 3.30.2, Display Server: X Server, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 14 August 2021 19:12 by user root.
EPYC 7763 2P: Debian 10.10 Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Debian 10, Kernel: 4.19.0-17-amd64 (x86_64), Desktop: GNOME Shell 3.30.2, Display Server: X Server, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2deb10u1)Python Notes: Python 2.7.16 + Python 3.7.3Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 15 August 2021 12:32 by user root.
EPYC 7763 2P: Debian 11.0 Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1001D BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Debian 11, Kernel: 5.10.0-8-amd64 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa001119Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)Python Notes: Python 3.9.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 16 August 2021 08:51 by user root.
Xeon 8380 2P: Debian 11.0 Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Device 0998, Memory: 504GB, Disk: 7682GB INTEL SSDPF2KX076TZ, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Debian 11, Kernel: 5.10.0-8-amd64 (x86_64), Desktop: GNOME Shell 3.38.4, Display Server: X Server 1.20.11, Vulkan: 1.0.2, Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd000270Java Notes: OpenJDK Runtime Environment (build 11.0.12+7-post-Debian-2)Python Notes: Python 3.9.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 17 August 2021 15:03 by user root.