CentOS Stream 9, Clear Linux, and Ubuntu 22.04 LTS (both stock and with performance governor "perf" run) benchmarks on Xeon Sapphire Rapids and EPYC Genoa. Benchmarks by Michael Larabel for a future article on Phoronix.com
CentOS Stream 9: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: CentOS Stream 9, Kernel: 5.14.0-239.el9.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server, Compiler: GCC 11.3.1 20221121, File-System: xfs, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.18.0.9-0.3.ea.el9) (build 11.0.18-ea+9-LTS)Python Notes: Python 3.9.16Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
CentOS Stream 9: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) , Motherboard: AMD Titanite_4G (RTI1002E BIOS) , Chipset: AMD Device 14a4 , Memory: 1520GB , Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 257GB Flash Drive , Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: CentOS Stream 9, Kernel: 5.14.0-239.el9.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server, Compiler: GCC 11.3.1 20221121, File-System: xfs, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (Red_Hat-11.0.18.0.9-0.3.ea.el9) (build 11.0.18-ea+9-LTS)Python Notes: Python 3.9.16Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Clear Linux: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) , Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) , Chipset: Intel Device 1bce , Memory: 1008GB , Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 , Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: Clear Linux OS 38100, Kernel: 6.1.7-1247.native (x86_64), Display Server: X Server 1.21.1.6, Compiler: GCC 12.2.1 20230112 releases/gcc-12.2.0-345-gc142b30b3a + Clang 15.0.6 + LLVM 15.0.6, File-System: ext4, Screen Resolution: 640x480
Kernel Notes: Transparent Huge Pages: alwaysEnvironment Notes: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop -fvisibility-inlines-hidden -Wl,--enable-new-dtags -std=gnu++17" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""Compiler Notes: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=sapphirerapids --with-zstdProcessor Notes: Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 18.0.2-internal+0-adhoc.mockbuild.corretto-18-18.0.2.9.1)Python Notes: Python 3.11.0Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Clear Linux: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) , Motherboard: AMD Titanite_4G (RTI1002E BIOS) , Chipset: AMD Device 14a4 , Memory: 1520GB , Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 , Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
Kernel Notes: Transparent Huge Pages: alwaysEnvironment Notes: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop -fvisibility-inlines-hidden -Wl,--enable-new-dtags -std=gnu++17" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""Compiler Notes: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=sapphirerapids --with-zstdProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 18.0.2-internal+0-adhoc.mockbuild.corretto-18-18.0.2.9.1)Python Notes: Python 3.11.0Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 22.04.1 LTS: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) , Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) , Chipset: Intel Device 1bce , Memory: 1008GB , Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 , Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 22.04, Kernel: 5.15.0-58-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1600x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 (EPP: balance_performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 22.04.1 LTS: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads) , Motherboard: AMD Titanite_4G (RTI1002E BIOS) , Chipset: AMD Device 14a4 , Memory: 1520GB , Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 , Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) , Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) , Chipset: Intel Device 1bce , Memory: 1008GB , Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 , Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads) , Motherboard: AMD Titanite_4G (RTI1002E BIOS) , Chipset: AMD Device 14a4 , Memory: 1520GB , Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 , Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + 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 CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Xeon 8490H 2P EPYC 9654 2P Xeon 8490H 2P EPYC 9654 2P Xeon 8490H 2P EPYC 9654 2P Xeon 8490H 2P EPYC 9654 2P 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) Intel Device 1bce 1008GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 ASPEED VGA HDMI 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T CentOS Stream 9 5.14.0-239.el9.x86_64 (x86_64) GNOME Shell 40.10 X Server GCC 11.3.1 20221121 xfs 1920x1080 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1002E BIOS) AMD Device 14a4 1520GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 257GB Flash Drive Broadcom NetXtreme BCM5720 PCIe 1024x768 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) Intel Device 1bce 1008GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T Clear Linux OS 38100 6.1.7-1247.native (x86_64) X Server 1.21.1.6 GCC 12.2.1 20230112 releases/gcc-12.2.0-345-gc142b30b3a + Clang 15.0.6 + LLVM 15.0.6 ext4 640x480 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1002E BIOS) AMD Device 14a4 1520GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 Broadcom NetXtreme BCM5720 PCIe 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) Intel Device 1bce 1008GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T Ubuntu 22.04 5.15.0-58-generic (x86_64) GNOME Shell 42.5 X Server 1.21.1.3 1.2.204 GCC 11.3.0 1600x1200 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1002E BIOS) AMD Device 14a4 1520GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 Broadcom NetXtreme BCM5720 PCIe 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS) Intel Device 1bce 1008GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads) AMD Titanite_4G (RTI1002E BIOS) AMD Device 14a4 1520GB 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 Broadcom NetXtreme BCM5720 PCIe OpenBenchmarking.org Kernel Details - CentOS Stream 9: Xeon 8490H 2P: Transparent Huge Pages: always - CentOS Stream 9: EPYC 9654 2P: Transparent Huge Pages: always - Clear Linux: Xeon 8490H 2P: Transparent Huge Pages: always - Clear Linux: EPYC 9654 2P: Transparent Huge Pages: always - Ubuntu 22.04.1 LTS: Xeon 8490H 2P: Transparent Huge Pages: madvise - Ubuntu 22.04.1 LTS: EPYC 9654 2P: Transparent Huge Pages: madvise - Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P: Transparent Huge Pages: madvise - Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P: Transparent Huge Pages: madvise Compiler Details - CentOS Stream 9: Xeon 8490H 2P: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl - CentOS Stream 9: EPYC 9654 2P: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-isl - Clear Linux: Xeon 8490H 2P: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=sapphirerapids --with-zstd - Clear Linux: EPYC 9654 2P: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=sapphirerapids --with-zstd - Ubuntu 22.04.1 LTS: Xeon 8490H 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Ubuntu 22.04.1 LTS: EPYC 9654 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 - CentOS Stream 9: Xeon 8490H 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0 - CentOS Stream 9: EPYC 9654 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110d - Clear Linux: Xeon 8490H 2P: Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x2b0000c0 - Clear Linux: EPYC 9654 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110d - Ubuntu 22.04.1 LTS: Xeon 8490H 2P: Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x2b0000c0 - Ubuntu 22.04.1 LTS: EPYC 9654 2P: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa10110d - Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0 - Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110d Java Details - CentOS Stream 9: Xeon 8490H 2P: OpenJDK Runtime Environment (Red_Hat-11.0.18.0.9-0.3.ea.el9) (build 11.0.18-ea+9-LTS) - CentOS Stream 9: EPYC 9654 2P: OpenJDK Runtime Environment (Red_Hat-11.0.18.0.9-0.3.ea.el9) (build 11.0.18-ea+9-LTS) - Clear Linux: Xeon 8490H 2P: OpenJDK Runtime Environment (build 18.0.2-internal+0-adhoc.mockbuild.corretto-18-18.0.2.9.1) - Clear Linux: EPYC 9654 2P: OpenJDK Runtime Environment (build 18.0.2-internal+0-adhoc.mockbuild.corretto-18-18.0.2.9.1) - Ubuntu 22.04.1 LTS: Xeon 8490H 2P: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04) - Ubuntu 22.04.1 LTS: EPYC 9654 2P: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04) - Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04) - Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04) Python Details - CentOS Stream 9: Xeon 8490H 2P: Python 3.9.16 - CentOS Stream 9: EPYC 9654 2P: Python 3.9.16 - Clear Linux: Xeon 8490H 2P: Python 3.11.0 - Clear Linux: EPYC 9654 2P: Python 3.11.0 - Ubuntu 22.04.1 LTS: Xeon 8490H 2P: Python 3.10.6 - Ubuntu 22.04.1 LTS: EPYC 9654 2P: Python 3.10.6 - Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P: Python 3.10.6 - Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P: Python 3.10.6 Security Details - CentOS Stream 9: Xeon 8490H 2P: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - CentOS Stream 9: EPYC 9654 2P: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Clear Linux: Xeon 8490H 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - Clear Linux: EPYC 9654 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Ubuntu 22.04.1 LTS: Xeon 8490H 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - Ubuntu 22.04.1 LTS: EPYC 9654 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected - Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected Environment Details - Clear Linux: Xeon 8490H 2P, Clear Linux: EPYC 9654 2P: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop -fvisibility-inlines-hidden -Wl,--enable-new-dtags -std=gnu++17" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""
mysqlslap: 1024 renaissance: Akka Unbalanced Cobwebbed Tree brl-cad: VGR Performance Metric nwchem: C240 Buckyball renaissance: ALS Movie Lens openvkl: vklBenchmark ISPC lczero: Eigen renaissance: Apache Spark PageRank hpcg: onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU renaissance: Finagle HTTP Requests onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU renaissance: Scala Dotty ospray: particle_volume/ao/real_time renaissance: Apache Spark ALS clickhouse: 100M Rows Hits Dataset, First Run / Cold Cache clickhouse: 100M Rows Hits Dataset, Second Run clickhouse: 100M Rows Hits Dataset, Third Run onnx: super-resolution-10 - CPU - Standard onnx: yolov4 - CPU - Standard onnx: fcn-resnet101-11 - CPU - Standard numenta-nab: KNN CAD renaissance: Genetic Algorithm Using Jenetics + Futures compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed ospray: gravity_spheres_volume/dim_512/ao/real_time blender: Barbershop - CPU-Only stress-ng: System V Message Passing numenta-nab: Bayesian Changepoint stress-ng: Mutex compress-zstd: 8 - Decompression Speed compress-zstd: 8 - Compression Speed pyperformance: python_startup stress-ng: Memory Copying renaissance: Apache Spark Bayes avifenc: 0 renaissance: Rand Forest simdjson: PartialTweets onednn: IP Shapes 1D - bf16bf16bf16 - CPU pyperformance: go simdjson: TopTweet stress-ng: CPU Cache numenta-nab: Earthgecko Skyline pyperformance: raytrace dacapobench: H2 pyperformance: django_template pyperformance: 2to3 pyperformance: regex_compile pyperformance: json_loads simdjson: LargeRand stress-ng: Glibc C String Functions numenta-nab: Contextual Anomaly Detector OSE namd: ATPase Simulation - 327,506 Atoms stress-ng: Context Switching stress-ng: Matrix Math pyperformance: nbody pyperformance: chaos compress-zstd: 8, Long Mode - Decompression Speed compress-zstd: 8, Long Mode - Compression Speed onednn: IP Shapes 3D - bf16bf16bf16 - CPU pyperformance: pathlib avifenc: 2 gromacs: MPI CPU - water_GMX50_bare cpuminer-opt: LBC, LBRY Credits stress-ng: Semaphores stress-ng: Malloc stress-ng: MEMFD stress-ng: Crypto stress-ng: Vector Math stress-ng: SENDFILE cpuminer-opt: x25x blender: Classroom - CPU-Only minibude: OpenMP - BM2 minibude: OpenMP - BM2 pyperformance: crypto_pyaes pyperformance: float svt-av1: Preset 12 - Bosphorus 4K uvg266: Bosphorus 4K - Ultra Fast kvazaar: Bosphorus 4K - Super Fast pyperformance: pickle_pure_python numenta-nab: Relative Entropy kvazaar: Bosphorus 4K - Very Fast uvg266: Bosphorus 4K - Medium uvg266: Bosphorus 4K - Super Fast astcenc: Fast onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU phpbench: PHP Benchmark Suite kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 4K - Medium oidn: RT.hdr_alb_nrm.3840x2160 liquid-dsp: 240 - 256 - 57 liquid-dsp: 128 - 256 - 57 kvazaar: Bosphorus 4K - Ultra Fast pybench: Total For Average Test Times astcenc: Thorough embree: Pathtracer ISPC - Asian Dragon Obj uvg266: Bosphorus 4K - Very Fast onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU incompact3d: input.i3d 193 Cells Per Direction dacapobench: Jython astcenc: Exhaustive embree: Pathtracer ISPC - Crown numenta-nab: Windowed Gaussian astcenc: Medium minibude: OpenMP - BM1 minibude: OpenMP - BM1 embree: Pathtracer ISPC - Asian Dragon avifenc: 6 CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Xeon 8490H 2P EPYC 9654 2P Xeon 8490H 2P EPYC 9654 2P Xeon 8490H 2P EPYC 9654 2P Xeon 8490H 2P EPYC 9654 2P 783 17316.2 4501622 6971.5 1235 11414 3085.4 61.7915 1057.93 13983.0 831.677 707.2 34.3762 1913.8 479.86 512.55 517.57 12655 695 538 69.233 1980.2 2655.3 103.3 2774.0 51.4 37.4028 146.50 8259465.89 20.664 49660511.45 3309.9 2938.4 8.00 13073.75 510.0 66.660 632.7 5.29 5.50540 209 6.61 15.92 65.661 385 2784 39.7 267 144 18.1 1.25 18252310.23 45.754 0.25725 2738337.84 539344.94 103 88.2 3408.4 754.5 3.08892 13.9 36.134 13.852 661557 8648758.12 345237484.97 3275.84 151720.93 593402.97 2072504.17 4099.70 36.66 140.033 3500.813 91.4 94.1 225.765 57.98 70.45 359 10.188 70.95 29.09 57.30 816.9936 0.617234 900784 33.77 34.44 4.20 6372366667 6188900000 72.98 860 78.8095 104.0872 56.05 0.267685 7.01116741 2596 7.6361 91.1013 4.212 493.9025 130.032 3250.798 122.7954 2.503 486 29061.4 6458256 5887.3 1318 9118 2898.4 81.3487 1833.35 12381.5 2043.99 666.6 42.3857 1573.0 513.38 519.83 538.01 7282 293 267 68.131 1742.0 3891.9 114.3 3809.3 54.6 43.8713 78.63 8701537.46 19.224 89560948.40 4667.3 4941.1 7.51 27013.11 469.9 61.306 595.5 5.71 16.5253 231 6.75 43.37 64.356 462 4286 44.2 274 135 18.4 1.2 31441183.86 46.606 0.12879 9627445.14 749386.41 129 97.9 5015.4 979.5 3.38338 15.5 33.246 16.877 1062223 14681906.13 732089658.78 2602.69 303693.84 1105767.24 3485006.39 7862.40 20.53 323.078 8076.934 103 101 247.280 58.19 77.57 390 10.674 76.62 47.57 57.86 758.6416 2.81446 772354 65.67 65.49 3.00 10269333333 7972200000 79.64 977 107.2162 183.9064 56.88 0.477561 4.74432603 3346 11.9486 179.5503 3.984 530.7310 277.181 6929.524 212.2641 2.053 792 17042.9 4231422 1834.3 9105.6 1142 11894 2704.1 62.4462 586.438 10387.6 489.127 644.9 34.6997 2073.0 504.28 530.44 535.16 11707 564 507 86.275 2026.2 2635.9 97.8 2795.3 51.6 38.0961 147.37 34967285.00 21.695 59688403.75 3204.2 2942.9 8.36 7851.21 449.0 67.334 646.5 5.79 0.976622 109 6.74 15.90 66.814 214 2494 26.7 201 104 18.3 1.29 19260094.31 32.442 0.26307 27204245.35 551787.07 63.3 52.2 3243.6 822.5 1.51936 11.9 37.557 14.980 667438 20839432.55 363422967.84 3631.89 203339.63 534773.07 2140625.32 5002.69 36.53 183.963 4599.072 58.6 53.7 224.364 57.28 70.41 219 10.759 70.58 29.13 56.85 821.5846 0.560616 2022000 33.27 33.92 4.28 7209766667 7172733333 72.14 664 85.8491 114.2266 55.89 0.249854 6.18280959 2679 8.4382 99.1441 4.270 525.4013 132.289 3307.227 131.3481 2.453 696 29003.5 1458.3 8651.9 1334 8815 2450.5 85.8376 1052.702 10800.0 1540.56 578.0 42.6274 1912.5 5417 232 243 66.693 1665.0 3845.5 116.0 3842.2 55.7 44.4272 78.95 34562392.22 18.272 127500171.07 4638.3 4933.4 7.88 25149.30 387.6 60.803 584.2 5.93 4.16919 112 6.65 51.20 53.139 224 3422 27.4 192 88.2 16.2 1.24 34041789.97 30.212 0.12863 113443848.34 823465.88 75.8 52.2 4978.1 1080.8 1.75315 12.1 33.135 17.828 1075000 38317964.95 779076525.72 2737.60 310982.35 1003872.99 3745383.09 7584.87 20.43 342.450 8561.237 60.3 57.1 236.887 60.02 78.48 227 9.654 76.91 48.07 60.13 672.1021 2.37655 1979213 65.01 65.54 3.05 13047666667 9886800000 79.76 749 114.7892 184.1431 59.27 0.448353 4.17020929 3111 12.0706 181.4164 3.641 500.6625 289.299 7232.468 212.9215 2.007 92 58150.3 4542520 3857 48438.2 971 10159 5533.6 62.1561 1147.86 27619.8 821.834 1070.1 22.1674 8695.6 188.06 215.98 221.01 11858 579 626 71.566 7369.2 2620.6 85.3 2680.6 44.5 36.2963 151.91 4635974.39 23.792 62213974.80 3085.9 1986.1 18.7 11788.71 1870.4 73.638 1654.4 5.44 6.81303 299 6.82 15.81 61.821 360 14555 63.8 513 214 32.3 1.27 16468545.30 44.143 0.26910 2832828.30 480961.67 160 133 3217.6 130.8 3.48128 24.5 41.838 14.484 672720 9091560.92 354331976.06 3170.33 155922.29 584432.47 2036351.59 4184.79 38.55 144.372 3609.288 146 152 112.550 21.72 30.19 566 12.959 25.43 11.22 21.57 689.9724 0.592698 930634 12.88 13.16 3.66 6349300000 6259700000 30.33 760 63.0203 79.8936 20.80 0.275719 6.65763593 5314 7.3573 63.8284 6.601 382.5386 137.224 3430.604 96.9887 4.414 188 32070.2 6185427 1639.3 21380.6 1496 8626 3180.2 43.5140 2088.03 12748.3 2519.75 708.8 42.7821 4574.8 355.94 387.76 401.21 5524 240 336 70.562 2921.4 3664.7 90.2 3682.6 38.5 44.1386 83.56 10148150.82 18.648 100696804.72 4139.7 4092.4 10.1 19656.50 765.9 64.139 796.4 5.76 22.6776 183 6.75 38.89 57.230 356 6109 36.3 262 116 17.0 1.21 28086931.75 37.786 0.12886 6936812.28 765004.64 112 76.6 4437.9 217.5 4.13974 15.0 34.763 18.334 1058290 20580638.57 755056251.17 2452.79 312079.56 1107161.31 3637914.88 7769.11 21.19 325.094 8127.346 88.2 84.0 174.180 48.35 68.02 330 10.079 68.90 31.79 48.69 801.0943 2.35757 840445 38.66 39.52 3.45 10008533333 7902500000 68.86 844 107.3206 182.9154 48.81 0.435699 5.50633752 3460 11.9780 180.0514 4.091 573.5736 277.680 6941.996 212.0178 2.472 700 17823.0 4422357 3831.4 22265.6 1132 11357 3186.3 62.4473 1235.78 13307.0 892.279 725.5 34.7789 5174.8 442.95 489.34 498.19 11912 560 625 69.067 1873.4 2581.8 87.4 2646.9 46.3 36.3900 149.07 4695295.44 21.105 69190781.46 3058.0 2600.2 7.77 11615.68 608.8 70.580 671.3 5.44 5.73088 185 6.81 15.89 58.780 351 2857 37.5 263 134 19.1 1.27 16455712.87 41.043 0.24942 3022658.91 482740.91 94.1 74.2 3202.4 397.8 3.45576 14.1 39.495 14.488 668323 9824585.26 352485778.28 3144.15 156719.16 587905.66 1977544.11 4064.51 37.14 136.905 3422.632 79.7 80.3 207.081 53.34 68.57 326 10.303 66.88 27.77 53.36 797.2018 0.581093 950645 31.71 32.43 4.22 6398333333 6284000000 71.20 760 78.2826 102.3872 50.03 0.262386 6.45621212 2662 7.5595 91.6250 4.143 489.5836 136.185 3404.634 121.7435 3.164 212 28536.2 6158933 1621.8 20121.8 1524 9286 3181.7 82.8521 1874.19 12533.1 2238.85 642.7 42.7726 4301.7 474.37 510.31 535.54 6136 296 347 70.837 1533.6 3696.2 91.2 3704.5 40.5 44.1011 81.75 10720272.61 18.398 101234172.17 4162.1 4235.4 6.78 19719.42 512.3 63.410 587.3 5.78 16.8110 184 6.75 39.27 57.109 355 3831 36.0 252 116 17.0 1.20 28055874.74 36.752 0.12831 7387215.19 751969.87 112 76.5 4429.4 388.3 3.60476 15.1 35.097 18.368 1060570 20869223.44 757554642.77 2520.75 316020.79 1111519.06 3684920.70 7612.66 20.86 298.431 7460.780 88.8 84.4 230.054 55.36 74.30 329 9.954 74.30 48.57 56.91 726.3567 2.29906 852671 62.52 63.33 3.54 10025000000 7899633333 79.87 853 107.8175 184.8392 56.20 0.426703 4.53648717 3273 12.0141 181.6829 3.894 507.3579 272.728 6818.209 212.4943 2.393 OpenBenchmarking.org
MariaDB This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.8.2 Clients: 1024 Xeon 8490H 2P EPYC 9654 2P 200 400 600 800 1000 SE +/- 0.29, N = 3 SE +/- 5.61, N = 9 SE +/- 18.88, N = 6 SE +/- 6.13, N = 8 SE +/- 2.66, N = 3 SE +/- 8.63, N = 5 SE +/- 7.35, N = 3 SE +/- 5.90, N = 3 92 188 212 700 486 783 696 792 1. (CXX) g++ options: -fPIC -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -pie -fstack-protector -shared -lrt -lpthread -lz -ldl -lm -lstdc++
Queries Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Queries Per Second Per Watt, More Is Better MariaDB 10.8.2 Clients: 1024 Xeon 8490H 2P EPYC 9654 2P 0.5378 1.0756 1.6134 2.1512 2.689 0.450 0.529 0.598 1.729 1.604 1.880 1.952 2.390
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better MariaDB 10.8.2 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 197.9 / Avg: 416.48 / Max: 430.44 Min: 56.4 / Avg: 303.02 / Max: 331.21 Min: 135.48 / Avg: 405.78 / Max: 421.46 Min: 52.94 / Avg: 291.22 / Max: 340.46 Min: 198.29 / Avg: 404.92 / Max: 599.32 Min: 53.13 / Avg: 354.63 / Max: 474.68 Min: 55.45 / Avg: 355.17 / Max: 502.86 Min: 96.3 / Avg: 204.25 / Max: 567.06
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.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Akka Unbalanced Cobwebbed Tree Xeon 8490H 2P EPYC 9654 2P 12K 24K 36K 48K 60K SE +/- 632.06, N = 4 SE +/- 308.95, N = 6 SE +/- 277.60, N = 3 SE +/- 176.71, N = 3 SE +/- 296.83, N = 3 SE +/- 128.63, N = 3 SE +/- 391.06, N = 9 SE +/- 117.51, N = 3 58150.3 32070.2 29061.4 17316.2 29003.5 17042.9 28536.2 17823.0
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 199.99 / Avg: 452.31 / Max: 597.83 Min: 57.82 / Avg: 338.04 / Max: 430.75 Min: 128.65 / Avg: 439.5 / Max: 560.12 Min: 52.48 / Avg: 329.16 / Max: 426.35 Min: 189.41 / Avg: 436.17 / Max: 548.62 Min: 49.39 / Avg: 321.49 / Max: 422.4 Min: 52.01 / Avg: 311.92 / Max: 417.34 Min: 99.22 / Avg: 244.07 / Max: 459.61
NWChem NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.
Input: C240 Buckyball
CentOS Stream 9: Xeon 8490H 2P: The test quit with a non-zero exit status. E: /nwchem-7.0.2/bin/LINUX64/nwchem: error while loading shared libraries: libmpi_usempif08.so.40: cannot open shared object file: No such file or directory
CentOS Stream 9: EPYC 9654 2P: The test quit with a non-zero exit status. E: /nwchem-7.0.2/bin/LINUX64/nwchem: error while loading shared libraries: libmpi_usempif08.so.40: cannot open shared object file: No such file or directory
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.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: ALS Movie Lens Xeon 8490H 2P EPYC 9654 2P 10K 20K 30K 40K 50K SE +/- 289.18, N = 3 SE +/- 262.79, N = 3 SE +/- 238.51, N = 9 SE +/- 81.73, N = 3 SE +/- 95.99, N = 4 SE +/- 118.91, N = 9 SE +/- 25.04, N = 3 SE +/- 20.73, N = 3 48438.2 21380.6 22265.6 20121.8 9105.6 8651.9 6971.5 5887.3
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 80 160 240 320 400 Min: 132.33 / Avg: 396.19 / Max: 412.62 Min: 46.55 / Avg: 229.5 / Max: 249.95 Min: 198.79 / Avg: 387.75 / Max: 421.11 Min: 56.47 / Avg: 239.1 / Max: 263.38 Min: 186.74 / Avg: 372.14 / Max: 440.89 Min: 50.46 / Avg: 227.3 / Max: 276.93 Min: 99.12 / Avg: 226.89 / Max: 355.21 Min: 55.05 / Avg: 218.48 / Max: 261.36
OpenVKL OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Xeon 8490H 2P EPYC 9654 2P 300 600 900 1200 1500 SE +/- 8.02, N = 3 SE +/- 6.89, N = 3 SE +/- 2.91, N = 3 SE +/- 10.35, N = 3 SE +/- 4.33, N = 3 SE +/- 16.23, N = 3 SE +/- 4.06, N = 3 SE +/- 12.30, N = 7 971 1496 1132 1524 1142 1334 1235 1318
Items / Sec Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Items / Sec Per Watt, More Is Better OpenVKL 1.3.1 Benchmark: vklBenchmark ISPC Xeon 8490H 2P EPYC 9654 2P 0.7119 1.4238 2.1357 2.8476 3.5595 1.812 3.164 2.030 3.111 2.042 2.703 2.129 2.733
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better OpenVKL 1.3.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 198.39 / Avg: 580.05 / Max: 729.72 Min: 58.27 / Avg: 482.31 / Max: 665.47 Min: 62.29 / Avg: 559.18 / Max: 732.51 Min: 52.67 / Avg: 493.46 / Max: 664.3 Min: 189.77 / Avg: 557.69 / Max: 727.44 Min: 50.14 / Avg: 489.89 / Max: 660.01 Min: 145.22 / Avg: 535.76 / Max: 729.72 Min: 53.48 / Avg: 472.79 / Max: 657.75
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen EPYC 9654 2P Xeon 8490H 2P 3K 6K 9K 12K 15K SE +/- 96.15, N = 9 SE +/- 107.17, N = 3 SE +/- 49.36, N = 3 SE +/- 139.81, N = 3 SE +/- 40.28, N = 3 SE +/- 106.72, N = 3 SE +/- 102.39, N = 3 SE +/- 104.41, N = 3 8626 10159 8815 11894 9118 11414 9286 11357 1. (CXX) g++ options: -flto -pthread
Nodes Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: Eigen Xeon 8490H 2P EPYC 9654 2P 6 12 18 24 30 19.93 24.05 21.26 24.43 21.48 25.03 22.10 23.49
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 128.05 / Avg: 538.22 / Max: 703.22 Min: 52.8 / Avg: 375.29 / Max: 509.44 Min: 196 / Avg: 536.88 / Max: 714.5 Min: 57.62 / Avg: 373.21 / Max: 513.77 Min: 199.71 / Avg: 528.73 / Max: 748.75 Min: 48.34 / Avg: 370.98 / Max: 507.08 Min: 140.61 / Avg: 509.76 / Max: 674.15 Min: 54.62 / Avg: 358.63 / Max: 499.95
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.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark PageRank Xeon 8490H 2P EPYC 9654 2P 1200 2400 3600 4800 6000 SE +/- 107.02, N = 12 SE +/- 44.09, N = 15 SE +/- 24.66, N = 10 SE +/- 19.16, N = 3 SE +/- 8.12, N = 3 SE +/- 27.73, N = 15 SE +/- 29.19, N = 3 SE +/- 28.19, N = 15 5533.6 3180.2 3186.3 3181.7 3085.4 2898.4 2704.1 2450.5
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 200.21 / Avg: 386.39 / Max: 584.25 Min: 55.59 / Avg: 236.59 / Max: 383.42 Min: 193.72 / Avg: 378.52 / Max: 582.1 Min: 43.31 / Avg: 231.38 / Max: 366.89 Min: 131.4 / Avg: 375.6 / Max: 398.59 Min: 41.93 / Avg: 219.98 / Max: 244.59 Min: 98.72 / Avg: 286.86 / Max: 580.91 Min: 48.27 / Avg: 221.88 / Max: 374.47
High Performance Conjugate Gradient HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 EPYC 9654 2P Xeon 8490H 2P 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.20, N = 3 SE +/- 0.28, N = 3 SE +/- 3.82, N = 11 SE +/- 0.14, N = 3 SE +/- 0.42, N = 3 SE +/- 0.33, N = 3 SE +/- 3.56, N = 10 43.51 62.16 61.79 81.35 62.45 85.84 62.45 82.85 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi
GFLOP/s Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org GFLOP/s Per Watt, More Is Better High Performance Conjugate Gradient 3.1 EPYC 9654 2P Xeon 8490H 2P 0.0329 0.0658 0.0987 0.1316 0.1645 0.072 0.091 0.091 0.138 0.091 0.146 0.091 0.140
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS CentOS Stream 9 OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 192.72 / Avg: 685.48 / Max: 722.57 Min: 50.42 / Avg: 592.41 / Max: 661.69 Min: 126.84 / Avg: 684.12 / Max: 719.71 Min: 42.84 / Avg: 588.35 / Max: 683.13 Min: 200.1 / Avg: 682.72 / Max: 730.51 Min: 57.27 / Avg: 606.26 / Max: 653.62 Min: 189.13 / Avg: 680.16 / Max: 717.83 Min: 56.5 / Avg: 588.86 / Max: 651.95
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU EPYC 9654 2P Xeon 8490H 2P 400 800 1200 1600 2000 SE +/- 23.53, N = 15 SE +/- 24.46, N = 15 SE +/- 39.27, N = 15 SE +/- 22.05, N = 15 SE +/- 24.31, N = 3 SE +/- 8.60, N = 15 SE +/- 9.48, N = 15 SE +/- 0.10, N = 3 2088.03 1147.86 1874.19 1235.78 1833.35 1057.93 1052.70 586.44 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 129.79 / Avg: 653.09 / Max: 752.92 Min: 16.12 / Avg: 500.76 / Max: 585.4 Min: 194.13 / Avg: 586.56 / Max: 753.75 Min: 57.51 / Avg: 409.21 / Max: 525.78 Min: 195.85 / Avg: 580.12 / Max: 754.49 Min: 48.15 / Avg: 412.89 / Max: 544.36 Min: 192.79 / Avg: 577.03 / Max: 754.18 Min: 50.13 / Avg: 402.22 / Max: 545.29
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.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Finagle HTTP Requests Xeon 8490H 2P EPYC 9654 2P 6K 12K 18K 24K 30K SE +/- 3656.98, N = 6 SE +/- 86.47, N = 3 SE +/- 156.38, N = 3 SE +/- 96.86, N = 3 SE +/- 159.68, N = 3 SE +/- 83.65, N = 3 SE +/- 113.71, N = 4 SE +/- 131.33, N = 12 27619.8 12748.3 13983.0 12381.5 13307.0 12533.1 10800.0 10387.6
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 135.75 / Avg: 640.36 / Max: 702.13 Min: 30.3 / Avg: 494.69 / Max: 554.76 Min: 204.25 / Avg: 629.11 / Max: 666.82 Min: 56.69 / Avg: 507.89 / Max: 563.45 Min: 197.31 / Avg: 617.07 / Max: 660.12 Min: 51.02 / Avg: 484.59 / Max: 541.98 Min: 54.4 / Avg: 469.58 / Max: 542.33 Min: 114.54 / Avg: 347.6 / Max: 524.63
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU EPYC 9654 2P Xeon 8490H 2P 500 1000 1500 2000 2500 SE +/- 39.34, N = 12 SE +/- 25.86, N = 15 SE +/- 20.80, N = 15 SE +/- 11.42, N = 15 SE +/- 14.19, N = 3 SE +/- 8.90, N = 15 SE +/- 17.06, N = 3 SE +/- 2.29, N = 3 2519.75 821.83 2238.85 892.28 2043.99 831.68 1540.56 489.13 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 131.03 / Avg: 653.19 / Max: 755.01 Min: 50.34 / Avg: 490.64 / Max: 597.54 Min: 195.55 / Avg: 576.26 / Max: 728.19 Min: 59.43 / Avg: 408.24 / Max: 566.65 Min: 196.63 / Avg: 573.36 / Max: 730.55 Min: 52.24 / Avg: 408.36 / Max: 587.91 Min: 187.4 / Avg: 570.8 / Max: 736.13 Min: 32.6 / Avg: 395.34 / Max: 587.57
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.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Scala Dotty Xeon 8490H 2P EPYC 9654 2P 200 400 600 800 1000 SE +/- 53.95, N = 15 SE +/- 12.71, N = 15 SE +/- 11.33, N = 15 SE +/- 4.56, N = 15 SE +/- 8.77, N = 15 SE +/- 10.19, N = 15 SE +/- 10.05, N = 15 SE +/- 2.60, N = 3 1070.1 708.8 725.5 642.7 707.2 666.6 644.9 578.0
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 80 160 240 320 400 Min: 199.84 / Avg: 363.21 / Max: 437.33 Min: 56.65 / Avg: 217.9 / Max: 271.87 Min: 134.46 / Avg: 361.05 / Max: 422.67 Min: 52.47 / Avg: 211.77 / Max: 260.06 Min: 191.84 / Avg: 355.12 / Max: 423.4 Min: 50.74 / Avg: 214.77 / Max: 266.97 Min: 101.79 / Avg: 253.44 / Max: 373.96 Min: 53.2 / Avg: 207.22 / Max: 263.3
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: particle_volume/ao/real_time Xeon 8490H 2P EPYC 9654 2P 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.24, N = 3 22.17 42.78 34.38 42.39 34.70 42.63 34.78 42.77
Items Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: particle_volume/ao/real_time Xeon 8490H 2P EPYC 9654 2P 0.0169 0.0338 0.0507 0.0676 0.0845 0.041 0.074 0.050 0.072 0.050 0.074 0.051 0.075
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 193.28 / Avg: 688.91 / Max: 724.52 Min: 58.26 / Avg: 586.89 / Max: 603.51 Min: 196.62 / Avg: 688.91 / Max: 717.36 Min: 55.47 / Avg: 578.09 / Max: 594.66 Min: 127.71 / Avg: 686.69 / Max: 727.8 Min: 50.44 / Avg: 570.65 / Max: 588.18 Min: 53.26 / Avg: 576.39 / Max: 594.59 Min: 113.66 / Avg: 536.33 / Max: 557.87
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.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark ALS Xeon 8490H 2P EPYC 9654 2P 2K 4K 6K 8K 10K SE +/- 31.90, N = 3 SE +/- 113.52, N = 12 SE +/- 7.13, N = 3 SE +/- 138.36, N = 9 SE +/- 5.16, N = 3 SE +/- 20.05, N = 3 SE +/- 6.75, N = 3 SE +/- 3.17, N = 3 8695.6 4574.8 5174.8 4301.7 2073.0 1912.5 1913.8 1573.0
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 80 160 240 320 400 Min: 131.32 / Avg: 397.96 / Max: 426.54 Min: 48.55 / Avg: 235.02 / Max: 255.18 Min: 193.17 / Avg: 394.27 / Max: 421.12 Min: 58.07 / Avg: 241.9 / Max: 270.85 Min: 193.99 / Avg: 380.16 / Max: 432.31 Min: 49.55 / Avg: 231.97 / Max: 264.98 Min: 97.44 / Avg: 260.45 / Max: 364.62 Min: 53.77 / Avg: 223.63 / Max: 257.05
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 SE +/- 0.83, N = 3 SE +/- 2.63, N = 3 SE +/- 3.33, N = 3 SE +/- 2.33, N = 3 SE +/- 2.76, N = 3 SE +/- 3.37, N = 3 SE +/- 1.60, N = 3 188.06 355.94 442.95 474.37 479.86 513.38 504.28
100M Rows Hits Dataset, First Run / Cold Cache
Clear Linux: EPYC 9654 2P: The test run did not produce a result.
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 SE +/- 2.22, N = 3 SE +/- 2.69, N = 3 SE +/- 2.06, N = 3 SE +/- 2.37, N = 3 SE +/- 4.05, N = 3 SE +/- 9.47, N = 3 SE +/- 2.62, N = 3 215.98 387.76 489.34 510.31 512.55 519.83 530.44
100M Rows Hits Dataset, Second Run
Clear Linux: EPYC 9654 2P: The test run did not produce a result.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 SE +/- 0.44, N = 3 SE +/- 2.73, N = 3 SE +/- 2.10, N = 3 SE +/- 3.59, N = 3 SE +/- 2.04, N = 3 SE +/- 2.16, N = 3 SE +/- 1.04, N = 3 221.01 401.21 498.19 535.54 517.57 538.01 535.16
Queries Per Minute, Geo Mean Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Queries Per Minute, Geo Mean Per Watt, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Xeon 8490H 2P EPYC 9654 2P 0.4619 0.9238 1.3857 1.8476 2.3095 0.715 1.653 1.226 2.053 1.245 2.006 1.297
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better ClickHouse 22.12.3.5 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 199.79 / Avg: 415.82 / Max: 691.24 Min: 56.63 / Avg: 268.24 / Max: 531.29 Min: 127.93 / Avg: 412.58 / Max: 677.78 Min: 196.75 / Avg: 406.31 / Max: 655.19 Min: 52.32 / Avg: 260.81 / Max: 526.66 Min: 114.95 / Avg: 308.96 / Max: 511.62 Min: 48.35 / Avg: 242.67 / Max: 506.22
100M Rows Hits Dataset, Third Run
Clear Linux: EPYC 9654 2P: The test run did not produce a result.
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.
Result
Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard EPYC 9654 2P Xeon 8490H 2P 3K 6K 9K 12K 15K SE +/- 28.14, N = 3 SE +/- 76.22, N = 3 SE +/- 143.65, N = 12 SE +/- 32.08, N = 3 SE +/- 249.63, N = 12 SE +/- 50.63, N = 3 SE +/- 96.75, N = 3 SE +/- 86.36, N = 3 5417 11707 5524 11858 6136 11912 7282 12655 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Inferences Per Minute Per Watt
Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: super-resolution-10 - Device: CPU - Executor: Standard EPYC 9654 2P Xeon 8490H 2P 7 14 21 28 35 21.48 27.06 22.74 27.58 24.02 27.63 27.87 29.25
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 80 160 240 320 400 Min: 192.9 / Avg: 432.65 / Max: 443.94 Min: 59.11 / Avg: 261.3 / Max: 269.29 Min: 128.48 / Avg: 432.58 / Max: 443.54 Min: 46.08 / Avg: 252.25 / Max: 261.93 Min: 190.62 / Avg: 431.18 / Max: 442.3 Min: 43.43 / Avg: 255.47 / Max: 270.55 Min: 115.76 / Avg: 430.03 / Max: 442.46 Min: 54.62 / Avg: 242.94 / Max: 261.8
Result
Clear Linux Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard EPYC 9654 2P Xeon 8490H 2P 150 300 450 600 750 SE +/- 0.60, N = 3 SE +/- 0.17, N = 3 SE +/- 3.22, N = 3 SE +/- 11.97, N = 12 SE +/- 3.52, N = 4 SE +/- 0.73, N = 3 SE +/- 2.75, N = 3 SE +/- 8.02, N = 3 232 564 240 579 293 695 296 560 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Inferences Per Minute Per Watt
Clear Linux Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: yolov4 - Device: CPU - Executor: Standard EPYC 9654 2P Xeon 8490H 2P 0.2554 0.5108 0.7662 1.0216 1.277 0.533 0.930 0.546 0.945 0.658 1.135 0.666 0.912
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 200.65 / Avg: 613.77 / Max: 634.06 Min: 48.37 / Avg: 444.34 / Max: 464.07 Min: 113.32 / Avg: 612.65 / Max: 633.87 Min: 53.11 / Avg: 439.73 / Max: 460.04 Min: 195.02 / Avg: 612.24 / Max: 631.66 Min: 56.03 / Avg: 445.57 / Max: 466.42 Min: 124.82 / Avg: 606.23 / Max: 628.66 Min: 52.98 / Avg: 435.02 / Max: 455.32
Result
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Inferences Per Minute, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard EPYC 9654 2P Xeon 8490H 2P 140 280 420 560 700 SE +/- 1.45, N = 3 SE +/- 2.92, N = 3 SE +/- 3.22, N = 3 SE +/- 9.74, N = 12 SE +/- 1.80, N = 3 SE +/- 1.17, N = 3 SE +/- 4.19, N = 3 SE +/- 2.02, N = 3 243 507 267 538 336 626 347 625 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
Inferences Per Minute Per Watt
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Inferences Per Minute Per Watt, More Is Better ONNX Runtime 1.11 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard EPYC 9654 2P Xeon 8490H 2P 0.2099 0.4198 0.6297 0.8396 1.0495 0.495 0.775 0.530 0.812 0.651 0.933 0.665 0.927
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.11 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 199.89 / Avg: 674.04 / Max: 703.87 Min: 51.34 / Avg: 522.07 / Max: 554.24 Min: 177.47 / Avg: 671.25 / Max: 705.43 Min: 52.88 / Avg: 515.93 / Max: 545.52 Min: 197.28 / Avg: 662.29 / Max: 701.58 Min: 58.39 / Avg: 503.93 / Max: 528.85 Min: 122.77 / Avg: 653.91 / Max: 681.69 Min: 52.98 / Avg: 491.19 / Max: 516.55
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
Result
Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: KNN CAD Xeon 8490H 2P EPYC 9654 2P 20 40 60 80 100 SE +/- 0.58, N = 3 SE +/- 0.23, N = 3 SE +/- 0.75, N = 15 SE +/- 0.17, N = 3 SE +/- 0.77, N = 3 SE +/- 0.51, N = 15 SE +/- 0.70, N = 6 SE +/- 0.14, N = 3 86.28 66.69 71.57 70.56 70.84 69.07 69.23 68.13
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 197.05 / Avg: 544.63 / Max: 751.47 Min: 55.97 / Avg: 357.57 / Max: 633.29 Min: 197.95 / Avg: 535.7 / Max: 754.29 Min: 54.28 / Avg: 348.11 / Max: 647.02 Min: 61.23 / Avg: 491.4 / Max: 748.22 Min: 54.74 / Avg: 351.53 / Max: 642.65 Min: 133.06 / Avg: 462.18 / Max: 704.23 Min: 49.88 / Avg: 279.94 / Max: 487.98
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.
Result
Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Genetic Algorithm Using Jenetics + Futures Xeon 8490H 2P EPYC 9654 2P 1600 3200 4800 6400 8000 SE +/- 76.08, N = 3 SE +/- 19.04, N = 3 SE +/- 23.45, N = 3 SE +/- 5.95, N = 3 SE +/- 15.29, N = 3 SE +/- 4.99, N = 3 SE +/- 18.85, N = 5 SE +/- 6.68, N = 3 7369.2 2921.4 2026.2 1665.0 1980.2 1742.0 1873.4 1533.6
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 70 140 210 280 350 Min: 206.41 / Avg: 370.8 / Max: 388.51 Min: 59.12 / Avg: 229.61 / Max: 245.07 Min: 135.71 / Avg: 362.77 / Max: 407.14 Min: 45.67 / Avg: 222.33 / Max: 251.44 Min: 193.57 / Avg: 355.59 / Max: 372.56 Min: 54.2 / Avg: 226.81 / Max: 240.32 Min: 53.73 / Avg: 208.6 / Max: 255.7 Min: 97.69 / Avg: 194.22 / Max: 197.19
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 800 1600 2400 3200 4000 SE +/- 3.07, N = 3 SE +/- 13.99, N = 12 SE +/- 2.34, N = 3 SE +/- 10.55, N = 15 SE +/- 18.09, N = 15 SE +/- 1.71, N = 15 SE +/- 5.73, N = 3 SE +/- 5.81, N = 12 2581.8 3696.2 2620.6 3664.7 2635.9 3845.5 2655.3 3891.9 1. *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
MB/s Per Watt
Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 19 - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 4 8 12 16 20 6.692 15.841 6.846 16.856 6.932 16.959 7.271 16.066
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 90 180 270 360 450 Min: 198.62 / Avg: 385.81 / Max: 502.5 Min: 30.79 / Avg: 233.33 / Max: 298.95 Min: 128.24 / Avg: 385.01 / Max: 500.09 Min: 45.52 / Avg: 228.13 / Max: 299.99 Min: 194.54 / Avg: 383.06 / Max: 496.23 Min: 54.21 / Avg: 229.49 / Max: 298.39 Min: 114.72 / Avg: 360.44 / Max: 502.88 Min: 49.96 / Avg: 228.11 / Max: 294.8
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19 - Compression Speed Xeon 8490H 2P EPYC 9654 2P 30 60 90 120 150 SE +/- 0.49, N = 3 SE +/- 1.38, N = 15 SE +/- 0.43, N = 3 SE +/- 1.70, N = 12 SE +/- 0.74, N = 15 SE +/- 0.96, N = 15 SE +/- 0.61, N = 3 SE +/- 1.90, N = 12 85.3 90.2 87.4 91.2 97.8 116.0 103.3 114.3 1. Xeon 8490H 2P: *** zstd command line interface 64-bits v1.5.1, by Yann Collet *** 2. EPYC 9654 2P: *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
Result
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 800 1600 2400 3200 4000 SE +/- 0.55, N = 3 SE +/- 30.30, N = 3 SE +/- 5.70, N = 3 SE +/- 19.16, N = 9 SE +/- 2.26, N = 15 SE +/- 2.39, N = 15 SE +/- 4.60, N = 12 SE +/- 2.85, N = 15 2646.9 3704.5 2680.6 3682.6 2774.0 3809.3 2795.3 3842.2 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
MB/s Per Watt
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 19, Long Mode - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 4 8 12 16 20 7.245 16.791 7.594 17.415 7.655 17.713 7.827 17.195
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 80 160 240 320 400 Min: 195.98 / Avg: 365.33 / Max: 423.3 Min: 53.66 / Avg: 220.62 / Max: 258.1 Min: 190.96 / Avg: 365.3 / Max: 423.32 Min: 54.08 / Avg: 218.74 / Max: 258.06 Min: 126.95 / Avg: 365.14 / Max: 426.34 Min: 38.12 / Avg: 216.92 / Max: 258.92 Min: 113.3 / Avg: 342.47 / Max: 425.34 Min: 51.4 / Avg: 214.16 / Max: 253.8
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 19, Long Mode - Compression Speed EPYC 9654 2P Xeon 8490H 2P 13 26 39 52 65 SE +/- 0.31, N = 9 SE +/- 0.47, N = 3 SE +/- 0.49, N = 3 SE +/- 0.13, N = 3 SE +/- 0.57, N = 15 SE +/- 0.71, N = 15 SE +/- 0.86, N = 12 SE +/- 0.96, N = 15 38.5 44.5 40.5 46.3 51.4 54.6 51.6 55.7 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Items Per Second, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Xeon 8490H 2P EPYC 9654 2P 10 20 30 40 50 SE +/- 0.22, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 36.30 44.14 36.39 44.10 37.40 43.87 38.10 44.43
Items Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Xeon 8490H 2P EPYC 9654 2P 0.0176 0.0352 0.0528 0.0704 0.088 0.055 0.076 0.055 0.076 0.056 0.075 0.058 0.078
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 197.47 / Avg: 665.83 / Max: 742.33 Min: 57.67 / Avg: 585.2 / Max: 627.48 Min: 194.5 / Avg: 662.94 / Max: 733.54 Min: 50.15 / Avg: 581.49 / Max: 626.21 Min: 120.24 / Avg: 662.46 / Max: 740.11 Min: 19.34 / Avg: 572.72 / Max: 614.26 Min: 111.27 / Avg: 654.11 / Max: 732.96 Min: 52.32 / Avg: 579.37 / Max: 625.29
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Barbershop - Compute: CPU-Only Xeon 8490H 2P EPYC 9654 2P 30 60 90 120 150 SE +/- 1.72, N = 3 SE +/- 0.32, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 1.23, N = 3 SE +/- 0.03, N = 3 SE +/- 0.84, N = 3 SE +/- 0.28, N = 3 151.91 83.56 149.07 81.75 147.37 78.95 146.50 78.63
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Blender 3.4 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 201.58 / Avg: 671.9 / Max: 754.49 Min: 58.51 / Avg: 633.24 / Max: 697.61 Min: 191.72 / Avg: 667.24 / Max: 755.08 Min: 55.57 / Avg: 617.04 / Max: 695.15 Min: 127.99 / Avg: 667.09 / Max: 753.73 Min: 53.18 / Avg: 622.85 / Max: 684.92 Min: 188.71 / Avg: 657.32 / Max: 751.98 Min: 56.43 / Avg: 606.22 / Max: 693.72
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: System V Message Passing Xeon 8490H 2P EPYC 9654 2P 7M 14M 21M 28M 35M SE +/- 54215.68, N = 3 SE +/- 4940.80, N = 3 SE +/- 3635.47, N = 3 SE +/- 80759.94, N = 13 SE +/- 2447520.93, N = 15 SE +/- 110038.02, N = 13 SE +/- 35838.24, N = 3 SE +/- 273980.47, N = 10 4635974.39 10148150.82 4695295.44 10720272.61 8259465.89 8701537.46 34562392.22 34967285.00 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: System V Message Passing Xeon 8490H 2P EPYC 9654 2P 20K 40K 60K 80K 100K 9376.48 30811.27 9708.51 29867.05 16291.35 23085.63 62111.25 90475.76
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 128.39 / Avg: 562.98 / Max: 631.71 Min: 46.78 / Avg: 382.01 / Max: 432.1 Min: 195.57 / Avg: 506.98 / Max: 568.05 Min: 58.53 / Avg: 376.92 / Max: 424.76 Min: 195.63 / Avg: 500.75 / Max: 554.9 Min: 46.69 / Avg: 347.93 / Max: 401.59 Min: 166.44 / Avg: 477.52 / Max: 538.1 Min: 56.88 / Avg: 339.78 / Max: 400.06
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Clear Linux Ubuntu 22.04.1 LTS - perf CentOS Stream 9 OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Xeon 8490H 2P EPYC 9654 2P 6 12 18 24 30 SE +/- 0.23, N = 15 SE +/- 0.15, N = 10 SE +/- 0.25, N = 15 SE +/- 0.17, N = 15 SE +/- 0.23, N = 15 SE +/- 0.19, N = 5 SE +/- 0.14, N = 3 SE +/- 0.13, N = 15 23.79 18.65 21.70 18.27 21.11 18.40 20.66 19.22
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 207.31 / Avg: 374.32 / Max: 536.98 Min: 56.22 / Avg: 226.93 / Max: 403.22 Min: 194.66 / Avg: 370.04 / Max: 549.59 Min: 52.43 / Avg: 222.5 / Max: 384.13 Min: 129.85 / Avg: 360.51 / Max: 549.21 Min: 52.28 / Avg: 217.22 / Max: 387.98 Min: 112.55 / Avg: 333.08 / Max: 477.1 Min: 28.81 / Avg: 218.04 / Max: 389.24
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Mutex Xeon 8490H 2P EPYC 9654 2P 30M 60M 90M 120M 150M SE +/- 514997.53, N = 15 SE +/- 2089836.46, N = 15 SE +/- 124816.60, N = 3 SE +/- 71254.14, N = 3 SE +/- 1747717.60, N = 12 SE +/- 1071328.86, N = 3 SE +/- 94000.81, N = 3 SE +/- 1072855.14, N = 4 49660511.45 89560948.40 59688403.75 127500171.07 62213974.80 100696804.72 69190781.46 101234172.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lz -pthread
Bogo Ops/s Per Watt
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Mutex Xeon 8490H 2P EPYC 9654 2P 50K 100K 150K 200K 250K 77196.99 151706.21 93528.29 215853.94 97489.78 167198.12 107989.85 167482.89
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 198.91 / Avg: 643.3 / Max: 750.12 Min: 58.57 / Avg: 590.36 / Max: 686.91 Min: 192.44 / Avg: 640.72 / Max: 706.85 Min: 48.78 / Avg: 604.44 / Max: 692.02 Min: 129.28 / Avg: 638.19 / Max: 753.68 Min: 47.18 / Avg: 590.68 / Max: 679.35 Min: 197.53 / Avg: 638.16 / Max: 736.49 Min: 58.45 / Avg: 602.26 / Max: 694.12
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 1000 2000 3000 4000 5000 SE +/- 3.41, N = 3 SE +/- 38.01, N = 3 SE +/- 6.72, N = 15 SE +/- 44.27, N = 3 SE +/- 23.01, N = 3 SE +/- 4.71, N = 3 SE +/- 5.24, N = 15 SE +/- 15.84, N = 3 3058.0 4162.1 3085.9 4139.7 3204.2 4638.3 3309.9 4667.3 1. *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
MB/s Per Watt
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 8 - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 5 10 15 20 25 7.678 18.602 7.992 18.529 8.056 17.440 9.829 17.732
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 128.22 / Avg: 417.3 / Max: 573.25 Min: 34.5 / Avg: 249.35 / Max: 345.42 Min: 194.96 / Avg: 414.17 / Max: 579.28 Min: 55.9 / Avg: 251.89 / Max: 348.07 Min: 189.75 / Avg: 379.59 / Max: 494.71 Min: 52.96 / Avg: 238.65 / Max: 316.3 Min: 113.28 / Avg: 313.96 / Max: 430.07 Min: 54.37 / Avg: 233.47 / Max: 309.5
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8 - Compression Speed Xeon 8490H 2P EPYC 9654 2P 1100 2200 3300 4400 5500 SE +/- 34.37, N = 15 SE +/- 44.08, N = 3 SE +/- 21.08, N = 3 SE +/- 24.50, N = 3 SE +/- 28.84, N = 15 SE +/- 48.49, N = 3 SE +/- 33.68, N = 3 SE +/- 15.70, N = 3 1986.1 4092.4 2600.2 4235.4 2938.4 4941.1 2942.9 4933.4 1. Xeon 8490H 2P: *** zstd command line interface 64-bits v1.5.2, by Yann Collet *** 2. EPYC 9654 2P: *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: python_startup Xeon 8490H 2P EPYC 9654 2P 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 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 18.70 10.10 8.36 7.88 8.00 7.51 7.77 6.78
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 70 140 210 280 350 Min: 134.34 / Avg: 351.12 / Max: 366.5 Min: 49.5 / Avg: 207.71 / Max: 217.53 Min: 200.7 / Avg: 350.82 / Max: 360.24 Min: 56.06 / Avg: 211.51 / Max: 220.99 Min: 195.27 / Avg: 344.39 / Max: 355.11 Min: 49.33 / Avg: 204.87 / Max: 218.09 Min: 51.9 / Avg: 199.97 / Max: 208.92 Min: 113.28 / Avg: 188.27 / Max: 194.42
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Result
Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Memory Copying Xeon 8490H 2P EPYC 9654 2P 6K 12K 18K 24K 30K SE +/- 8.38, N = 3 SE +/- 102.52, N = 3 SE +/- 36.52, N = 3 SE +/- 728.20, N = 15 SE +/- 36.22, N = 3 SE +/- 801.68, N = 12 SE +/- 1.04, N = 3 SE +/- 1668.62, N = 15 7851.21 25149.30 11615.68 19719.42 11788.71 19656.50 13073.75 27013.11 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lz -pthread
Bogo Ops/s Per Watt
Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Memory Copying Xeon 8490H 2P EPYC 9654 2P 12 24 36 48 60 12.54 52.72 18.14 41.42 18.44 40.73 20.37 54.82
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 195.74 / Avg: 641.89 / Max: 754.66 Min: 58.54 / Avg: 492.8 / Max: 569.11 Min: 197.67 / Avg: 640.23 / Max: 753.3 Min: 46.62 / Avg: 476.04 / Max: 569.95 Min: 191.47 / Avg: 639.26 / Max: 751.39 Min: 56.47 / Avg: 482.56 / Max: 565.02 Min: 130.7 / Avg: 626.05 / Max: 720.5 Min: 47.25 / Avg: 477 / Max: 546.07
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.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Apache Spark Bayes Xeon 8490H 2P EPYC 9654 2P 400 800 1200 1600 2000 SE +/- 54.63, N = 12 SE +/- 6.00, N = 3 SE +/- 4.62, N = 3 SE +/- 5.07, N = 3 SE +/- 1.02, N = 3 SE +/- 1.17, N = 3 SE +/- 1.22, N = 3 SE +/- 4.04, N = 3 1870.4 765.9 608.8 512.3 510.0 469.9 449.0 387.6
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 132.92 / Avg: 462.69 / Max: 670.95 Min: 50.79 / Avg: 291.08 / Max: 447.45 Min: 206.91 / Avg: 462.48 / Max: 607.81 Min: 57.32 / Avg: 303.18 / Max: 429.3 Min: 199.58 / Avg: 452.25 / Max: 602.87 Min: 54.21 / Avg: 287.94 / Max: 405.88 Min: 47.95 / Avg: 244.58 / Max: 354.86 Min: 109.87 / Avg: 238.73 / Max: 459.05
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 0 Xeon 8490H 2P EPYC 9654 2P 16 32 48 64 80 SE +/- 0.35, N = 3 SE +/- 0.54, N = 3 SE +/- 0.31, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.29, N = 3 SE +/- 0.09, N = 3 73.64 64.14 70.58 63.41 67.33 60.80 66.66 61.31 1. (CXX) g++ options: -O3 -fPIC -lm
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 0.11 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 173.05 / Avg: 436.8 / Max: 705.99 Min: 55.29 / Avg: 275.14 / Max: 473.13 Min: 133.66 / Avg: 432.67 / Max: 723.73 Min: 45.13 / Avg: 273.37 / Max: 475.8 Min: 205.62 / Avg: 418.17 / Max: 660.81 Min: 42.52 / Avg: 268.96 / Max: 463.77 Min: 115.81 / Avg: 402.39 / Max: 642.21 Min: 52.73 / Avg: 268.27 / Max: 477.47
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.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.14 Test: Random Forest Xeon 8490H 2P EPYC 9654 2P 400 800 1200 1600 2000 SE +/- 15.56, N = 7 SE +/- 7.96, N = 3 SE +/- 6.62, N = 3 SE +/- 1.64, N = 3 SE +/- 6.37, N = 5 SE +/- 5.64, N = 6 SE +/- 3.05, N = 3 SE +/- 0.65, N = 3 1654.4 796.4 671.3 587.3 646.5 584.2 632.7 595.5
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Renaissance 0.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 70 140 210 280 350 Min: 206.32 / Avg: 367.61 / Max: 414.04 Min: 55.97 / Avg: 215.12 / Max: 253.1 Min: 137.77 / Avg: 365.91 / Max: 407.58 Min: 50.94 / Avg: 210.87 / Max: 246.58 Min: 193.63 / Avg: 348.87 / Max: 395.91 Min: 42.37 / Avg: 210.95 / Max: 250.21 Min: 104.71 / Avg: 205.45 / Max: 354.29 Min: 54.57 / Avg: 201.34 / Max: 233.43
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Xeon 8490H 2P EPYC 9654 2P 1.3343 2.6686 4.0029 5.3372 6.6715 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 +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 5.29 5.71 5.44 5.76 5.44 5.78 5.79 5.93 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
GB/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: PartialTweets Xeon 8490H 2P EPYC 9654 2P 0.0065 0.013 0.0195 0.026 0.0325 0.016 0.027 0.016 0.028 0.016 0.028 0.017 0.029
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 199.29 / Avg: 340.31 / Max: 353.73 Min: 58.69 / Avg: 212.57 / Max: 226.1 Min: 198.37 / Avg: 333.69 / Max: 347.43 Min: 47.75 / Avg: 210.01 / Max: 222.52 Min: 127.72 / Avg: 332.37 / Max: 349.63 Min: 29.67 / Avg: 208.03 / Max: 218.81 Min: 115.8 / Avg: 329.84 / Max: 345.96 Min: 55.29 / Avg: 204.78 / Max: 221.3
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU EPYC 9654 2P Xeon 8490H 2P 5 10 15 20 25 SE +/- 1.817118, N = 15 SE +/- 0.946742, N = 15 SE +/- 0.798600, N = 15 SE +/- 0.176078, N = 12 SE +/- 0.901191, N = 12 SE +/- 0.063853, N = 15 SE +/- 0.272228, N = 12 SE +/- 0.004589, N = 4 22.677600 6.813030 16.811000 5.730880 16.525300 5.505400 4.169190 0.976622 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 124.51 / Avg: 579.66 / Max: 751.66 Min: 42.71 / Avg: 428.14 / Max: 606.18 Min: 194.29 / Avg: 497.2 / Max: 605.72 Min: 57.37 / Avg: 336.2 / Max: 489.73 Min: 195.14 / Avg: 490.41 / Max: 590.97 Min: 45.64 / Avg: 327.01 / Max: 469.94 Min: 132.09 / Avg: 472.8 / Max: 605.7 Min: 52.12 / Avg: 283.01 / Max: 450.99
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: go Xeon 8490H 2P EPYC 9654 2P 70 140 210 280 350 SE +/- 6.38, N = 15 SE +/- 0.00, N = 3 SE +/- 0.33, 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 = 3 299 183 231 209 185 184 112 109
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 200.2 / Avg: 280.19 / Max: 346.06 Min: 56.3 / Avg: 205.19 / Max: 219.79 Min: 186.04 / Avg: 245.37 / Max: 270.74 Min: 52.26 / Avg: 197.02 / Max: 217.74 Min: 130.63 / Avg: 234.28 / Max: 354.48 Min: 42.19 / Avg: 189.4 / Max: 217.44 Min: 96.03 / Avg: 190.91 / Max: 234.95 Min: 53.85 / Avg: 190.3 / Max: 211.36
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Xeon 8490H 2P EPYC 9654 2P 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.07, 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 6.61 6.75 6.65 6.74 6.75 6.82 6.75 6.81 1. (CXX) g++ options: -O3
GB/s Per Watt
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: TopTweet Xeon 8490H 2P EPYC 9654 2P 0.0077 0.0154 0.0231 0.0308 0.0385 0.020 0.032 0.020 0.032 0.021 0.032 0.023 0.034
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 199.33 / Avg: 336.67 / Max: 353.78 Min: 55.21 / Avg: 211.27 / Max: 220.3 Min: 129.67 / Avg: 333.55 / Max: 351.13 Min: 52.42 / Avg: 208.09 / Max: 218.03 Min: 198.7 / Avg: 331.81 / Max: 349.62 Min: 54.01 / Avg: 208.34 / Max: 219.46 Min: 116.78 / Avg: 302.41 / Max: 346.69 Min: 51.47 / Avg: 199.99 / Max: 210.39
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: CPU Cache Xeon 8490H 2P EPYC 9654 2P 12 24 36 48 60 SE +/- 0.00, N = 3 SE +/- 0.19, N = 3 SE +/- 0.00, N = 3 SE +/- 0.28, N = 3 SE +/- 0.01, N = 3 SE +/- 0.83, N = 15 SE +/- 0.01, N = 3 SE +/- 1.22, N = 15 15.81 38.89 15.89 39.27 15.90 51.20 15.92 43.37 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lz -pthread
Bogo Ops/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: CPU Cache Xeon 8490H 2P EPYC 9654 2P 0.054 0.108 0.162 0.216 0.27 0.044 0.201 0.044 0.187 0.046 0.240 0.046 0.187
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 205.82 / Avg: 359.21 / Max: 754.01 Min: 56.79 / Avg: 215.48 / Max: 477.68 Min: 195.02 / Avg: 358.61 / Max: 753.83 Min: 51.5 / Avg: 209.87 / Max: 420.57 Min: 130.35 / Avg: 349.16 / Max: 755.08 Min: 45.68 / Avg: 213.73 / Max: 471.43 Min: 112.1 / Avg: 342.5 / Max: 753.42 Min: 56.14 / Avg: 208 / Max: 452.74
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
Result
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Xeon 8490H 2P EPYC 9654 2P 15 30 45 60 75 SE +/- 0.64, N = 3 SE +/- 0.74, N = 3 SE +/- 0.60, N = 3 SE +/- 0.07, N = 3 SE +/- 0.77, N = 3 SE +/- 0.13, N = 3 SE +/- 0.48, N = 3 SE +/- 0.25, N = 3 66.81 53.14 65.66 64.36 61.82 57.23 58.78 57.11
CPU Power Consumption
Clear Linux Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 124.83 / Avg: 412.03 / Max: 552.76 Min: 44 / Avg: 249.29 / Max: 416.12 Min: 197.99 / Avg: 410.66 / Max: 551.85 Min: 51.48 / Avg: 256.16 / Max: 410.32 Min: 200.27 / Avg: 407.75 / Max: 556.53 Min: 58.63 / Avg: 256.83 / Max: 417.57 Min: 114.93 / Avg: 391.81 / Max: 546.34 Min: 54.5 / Avg: 253.55 / Max: 409.57
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: raytrace EPYC 9654 2P Xeon 8490H 2P 100 200 300 400 500 SE +/- 1.33, N = 3 SE +/- 0.33, N = 3 SE +/- 2.60, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 462 385 360 356 355 351 224 214
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 107.24 / Avg: 264.5 / Max: 345.38 Min: 55.66 / Avg: 211.93 / Max: 220.05 Min: 192.26 / Avg: 241.61 / Max: 295.87 Min: 44.69 / Avg: 205.97 / Max: 218.51 Min: 131.36 / Avg: 234.03 / Max: 350.51 Min: 39.77 / Avg: 201.56 / Max: 218 Min: 106.95 / Avg: 212.61 / Max: 252.26 Min: 52.81 / Avg: 198.21 / Max: 212.45
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.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Xeon 8490H 2P EPYC 9654 2P 3K 6K 9K 12K 15K SE +/- 142.99, N = 20 SE +/- 118.31, N = 20 SE +/- 56.33, N = 16 SE +/- 27.80, N = 20 SE +/- 108.76, N = 20 SE +/- 18.75, N = 20 SE +/- 21.28, N = 20 SE +/- 30.82, N = 20 14555 6109 4286 2784 3831 2857 3422 2494
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better DaCapo Benchmark 9.12-MR1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 80 160 240 320 400 Min: 193.83 / Avg: 324.32 / Max: 427.32 Min: 55.74 / Avg: 178.5 / Max: 267.58 Min: 135.04 / Avg: 310.84 / Max: 402.88 Min: 36.95 / Avg: 164.95 / Max: 262.63 Min: 182.92 / Avg: 308.54 / Max: 390.97 Min: 49.26 / Avg: 173.1 / Max: 266.89 Min: 112.37 / Avg: 188.59 / Max: 350.73 Min: 49.78 / Avg: 169.43 / Max: 251.29
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template Xeon 8490H 2P EPYC 9654 2P 14 28 42 56 70 SE +/- 1.57, N = 15 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 63.8 36.3 44.2 39.7 37.5 36.0 27.4 26.7
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 198.4 / Avg: 310.84 / Max: 350.13 Min: 57.22 / Avg: 205.39 / Max: 219.87 Min: 132.52 / Avg: 289.8 / Max: 356.07 Min: 48.05 / Avg: 195.41 / Max: 217.76 Min: 199 / Avg: 281.15 / Max: 335.84 Min: 50.39 / Avg: 197.43 / Max: 217.75 Min: 54.22 / Avg: 190.88 / Max: 211.6 Min: 97.68 / Avg: 190.8 / Max: 320.52
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: 2to3 Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 SE +/- 2.91, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 513 262 274 267 263 252 201 192
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 196.7 / Avg: 344.12 / Max: 357.75 Min: 56 / Avg: 208.35 / Max: 221.13 Min: 198.43 / Avg: 338.07 / Max: 351.4 Min: 51.94 / Avg: 202.05 / Max: 218.02 Min: 134.94 / Avg: 333.43 / Max: 358.42 Min: 26.13 / Avg: 200.64 / Max: 217.54 Min: 53.38 / Avg: 196.68 / Max: 211.22 Min: 96.42 / Avg: 191.95 / Max: 343.23
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Xeon 8490H 2P EPYC 9654 2P 50 100 150 200 250 SE +/- 2.87, N = 15 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.12, N = 3 214.0 116.0 144.0 135.0 134.0 116.0 104.0 88.2
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 200.52 / Avg: 291.51 / Max: 348.36 Min: 55.98 / Avg: 200.04 / Max: 219.72 Min: 194.65 / Avg: 253.16 / Max: 317.98 Min: 49.03 / Avg: 190.58 / Max: 217.53 Min: 136.34 / Avg: 234.34 / Max: 320.13 Min: 47.93 / Avg: 199.02 / Max: 217.81 Min: 112.11 / Avg: 189.63 / Max: 230.46 Min: 54.75 / Avg: 185.23 / Max: 211.64
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: json_loads Xeon 8490H 2P EPYC 9654 2P 8 16 24 32 40 SE +/- 0.62, N = 15 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 32.3 17.0 19.1 17.0 18.4 18.1 18.3 16.2
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 211.13 / Avg: 289.45 / Max: 348.84 Min: 57.21 / Avg: 203.34 / Max: 219.64 Min: 203.83 / Avg: 243.94 / Max: 281.09 Min: 51.84 / Avg: 196.77 / Max: 217.89 Min: 133.2 / Avg: 234.55 / Max: 348.44 Min: 29.15 / Avg: 196.64 / Max: 217.35 Min: 54.47 / Avg: 189.73 / Max: 210.88 Min: 112.36 / Avg: 187.65 / Max: 235.45
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom EPYC 9654 2P Xeon 8490H 2P 0.2903 0.5806 0.8709 1.1612 1.4515 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 1.20 1.25 1.20 1.27 1.21 1.27 1.24 1.29 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17
GB/s Per Watt
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: LargeRandom Xeon 8490H 2P EPYC 9654 2P 0.0014 0.0028 0.0042 0.0056 0.007 0.004 0.006 0.004 0.006 0.004 0.006 0.004 0.006
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 199.99 / Avg: 340.85 / Max: 356.84 Min: 56.25 / Avg: 209.37 / Max: 221.23 Min: 186 / Avg: 338.58 / Max: 353.24 Min: 42.3 / Avg: 207.62 / Max: 220.16 Min: 130.58 / Avg: 333.34 / Max: 358.88 Min: 45.49 / Avg: 205.72 / Max: 219.06 Min: 113.44 / Avg: 329.81 / Max: 350.36 Min: 54.83 / Avg: 198.71 / Max: 211.18
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions Xeon 8490H 2P EPYC 9654 2P 7M 14M 21M 28M 35M SE +/- 18523.30, N = 3 SE +/- 216107.71, N = 3 SE +/- 132563.87, N = 3 SE +/- 254282.15, N = 3 SE +/- 196074.19, N = 5 SE +/- 346478.07, N = 5 SE +/- 247947.31, N = 3 SE +/- 281854.05, N = 15 16455712.87 28055874.74 16468545.30 28086931.75 18252310.23 31441183.86 19260094.31 34041789.97 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Glibc C String Functions Xeon 8490H 2P EPYC 9654 2P 11K 22K 33K 44K 55K 25682.27 43797.32 25831.49 43721.94 28542.49 48760.17 30597.48 53681.46
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor EPYC 9654 2P Xeon 8490H 2P 130 260 390 520 650 Min: 57.21 / Avg: 644.81 / Max: 735.35 Min: 198.92 / Avg: 639.48 / Max: 754.41 Min: 56.53 / Avg: 642.4 / Max: 730.63 Min: 160.55 / Avg: 637.54 / Max: 753.73 Min: 197.51 / Avg: 640.74 / Max: 753.82 Min: 53.76 / Avg: 640.58 / Max: 727.9 Min: 40.84 / Avg: 634.14 / Max: 720.88 Min: 128.89 / Avg: 629.47 / Max: 754.04
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE EPYC 9654 2P Xeon 8490H 2P 11 22 33 44 55 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.41, N = 7 SE +/- 0.27, N = 3 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 SE +/- 0.39, N = 4 SE +/- 0.10, N = 3 46.61 45.75 44.14 37.79 41.04 36.75 32.44 30.21
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 197.35 / Avg: 360.54 / Max: 551.46 Min: 56.25 / Avg: 224.06 / Max: 387.69 Min: 198.26 / Avg: 357.34 / Max: 550.96 Min: 53.91 / Avg: 218.87 / Max: 371.12 Min: 133.14 / Avg: 348.31 / Max: 540.66 Min: 46.29 / Avg: 209.7 / Max: 375.93 Min: 115.35 / Avg: 334.06 / Max: 481.26 Min: 54.51 / Avg: 212.64 / Max: 381.28
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.
Result
Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Xeon 8490H 2P EPYC 9654 2P 0.0605 0.121 0.1815 0.242 0.3025 SE +/- 0.00375, N = 3 SE +/- 0.00009, N = 3 SE +/- 0.00330, N = 3 SE +/- 0.00011, N = 3 SE +/- 0.00097, N = 3 SE +/- 0.00019, N = 3 SE +/- 0.00250, N = 5 SE +/- 0.00024, N = 3 0.26910 0.12886 0.26307 0.12863 0.25725 0.12879 0.24942 0.12831
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Watts, Fewer Is Better NAMD 2.14 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 203.39 / Avg: 604.52 / Max: 754.58 Min: 56.34 / Avg: 316.14 / Max: 683.86 Min: 123.08 / Avg: 587.27 / Max: 753.37 Min: 47.83 / Avg: 315.41 / Max: 676.16 Min: 193.03 / Avg: 581.54 / Max: 751.66 Min: 54.85 / Avg: 321.21 / Max: 682.41 Min: 197.79 / Avg: 548.7 / Max: 753.04 Min: 53.16 / Avg: 336.01 / Max: 681.29
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Context Switching Xeon 8490H 2P EPYC 9654 2P 20M 40M 60M 80M 100M SE +/- 4453.96, N = 3 SE +/- 237350.06, N = 15 SE +/- 3802.45, N = 3 SE +/- 68900.18, N = 3 SE +/- 3152.41, N = 3 SE +/- 88991.61, N = 3 SE +/- 118201.25, N = 3 SE +/- 330195.92, N = 3 2738337.84 9627445.14 2832828.30 6936812.28 3022658.91 7387215.19 27204245.35 113443848.34 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Context Switching Xeon 8490H 2P EPYC 9654 2P 40K 80K 120K 160K 200K 4930.43 23980.44 5245.66 17667.29 5500.14 18367.29 43149.70 194395.73
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 135.01 / Avg: 630.46 / Max: 754.01 Min: 27.97 / Avg: 583.57 / Max: 674.39 Min: 197.66 / Avg: 555.4 / Max: 601.91 Min: 58.59 / Avg: 401.47 / Max: 475.56 Min: 195.67 / Avg: 549.56 / Max: 599.39 Min: 47.04 / Avg: 402.19 / Max: 454.79 Min: 194.99 / Avg: 540.03 / Max: 596.61 Min: 56.16 / Avg: 392.64 / Max: 452.11
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Matrix Math Xeon 8490H 2P EPYC 9654 2P 200K 400K 600K 800K 1000K SE +/- 1110.12, N = 3 SE +/- 15430.39, N = 14 SE +/- 695.19, N = 3 SE +/- 84.69, N = 3 SE +/- 1166.29, N = 3 SE +/- 12.02, N = 3 SE +/- 234.85, N = 3 SE +/- 14.38, N = 3 480961.67 765004.64 482740.91 751969.87 539344.94 749386.41 551787.07 823465.88 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Matrix Math Xeon 8490H 2P EPYC 9654 2P 300 600 900 1200 1500 751.87 1364.21 752.96 1340.93 844.26 1337.79 877.21 1461.74
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 193.75 / Avg: 641.12 / Max: 754.28 Min: 47.92 / Avg: 560.78 / Max: 631.57 Min: 186.92 / Avg: 639.69 / Max: 753.88 Min: 57.06 / Avg: 560.77 / Max: 635 Min: 190.7 / Avg: 638.84 / Max: 754.3 Min: 61.3 / Avg: 560.17 / Max: 630.81 Min: 134.14 / Avg: 629.03 / Max: 754.42 Min: 46.52 / Avg: 563.35 / Max: 651.34
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: nbody Xeon 8490H 2P EPYC 9654 2P 40 80 120 160 200 SE +/- 1.76, N = 15 SE +/- 0.58, N = 3 SE +/- 1.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.36, N = 3 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 160.0 112.0 129.0 103.0 112.0 94.1 75.8 63.3
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 201.18 / Avg: 299.39 / Max: 347.26 Min: 56.43 / Avg: 197.24 / Max: 219.71 Min: 196.3 / Avg: 246.72 / Max: 308.97 Min: 52.12 / Avg: 188.31 / Max: 218.01 Min: 132.74 / Avg: 234.42 / Max: 343.71 Min: 50.57 / Avg: 195.05 / Max: 217.72 Min: 96.08 / Avg: 185.95 / Max: 227.22 Min: 54.35 / Avg: 182.45 / Max: 209.63
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: chaos Xeon 8490H 2P EPYC 9654 2P 30 60 90 120 150 SE +/- 1.91, N = 13 SE +/- 0.12, N = 3 SE +/- 0.25, N = 3 SE +/- 0.15, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 133.0 76.6 97.9 88.2 76.5 74.2 52.2 52.2
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 203.76 / Avg: 296.16 / Max: 346.61 Min: 55.33 / Avg: 204.73 / Max: 219.94 Min: 203.55 / Avg: 251.08 / Max: 296.07 Min: 52.11 / Avg: 195.32 / Max: 218.24 Min: 123.47 / Avg: 232.69 / Max: 353.54 Min: 34.04 / Avg: 189.24 / Max: 217.82 Min: 54.92 / Avg: 187.9 / Max: 212.05 Min: 112.55 / Avg: 183.43 / Max: 212.85
Zstd Compression This test measures the time needed to compress/decompress a sample input file using Zstd compression supplied by the system or otherwise externally of the test profile. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 1100 2200 3300 4400 5500 SE +/- 11.93, N = 3 SE +/- 55.66, N = 3 SE +/- 2.24, N = 3 SE +/- 47.37, N = 3 SE +/- 40.64, N = 6 SE +/- 12.23, N = 3 SE +/- 22.09, N = 3 SE +/- 5.34, N = 3 3202.4 4429.4 3217.6 4437.9 3243.6 4978.1 3408.4 5015.4 1. *** zstd command line interface 64-bits v1.5.1, by Yann Collet ***
MB/s Per Watt
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression Compression Level: 8, Long Mode - Decompression Speed Xeon 8490H 2P EPYC 9654 2P 6 12 18 24 30 8.781 22.757 9.248 23.476 9.341 21.476 12.965 22.667
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 80 160 240 320 400 Min: 127.97 / Avg: 369.37 / Max: 416.66 Min: 47.27 / Avg: 218.75 / Max: 264.15 Min: 196.96 / Avg: 368.56 / Max: 443.48 Min: 55 / Avg: 213.64 / Max: 244.07 Min: 194.19 / Avg: 342.83 / Max: 380.2 Min: 51.86 / Avg: 206.25 / Max: 230.76 Min: 115.47 / Avg: 248.18 / Max: 348.7 Min: 52.67 / Avg: 195.79 / Max: 218.68
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org MB/s, More Is Better Zstd Compression Compression Level: 8, Long Mode - Compression Speed Xeon 8490H 2P EPYC 9654 2P 200 400 600 800 1000 SE +/- 0.46, N = 3 SE +/- 1.94, N = 3 SE +/- 2.61, N = 3 SE +/- 0.82, N = 3 SE +/- 7.79, N = 3 SE +/- 1.70, N = 3 SE +/- 7.71, N = 6 SE +/- 3.44, N = 3 130.8 217.5 388.3 397.8 754.5 979.5 822.5 1080.8 1. *** zstd command line interface 64-bits v1.5.2, by Yann Collet ***
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU EPYC 9654 2P Xeon 8490H 2P 0.9314 1.8628 2.7942 3.7256 4.657 SE +/- 0.12128, N = 12 SE +/- 0.14220, N = 15 SE +/- 0.06244, N = 15 SE +/- 0.03599, N = 15 SE +/- 0.03385, N = 15 SE +/- 0.08245, N = 12 SE +/- 0.08522, N = 15 SE +/- 0.00444, N = 5 4.13974 3.48128 3.60476 3.45576 3.38338 3.08892 1.75315 1.51936 1. (CXX) g++ options: -O3 -march=native -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 123.2 / Avg: 529.51 / Max: 749.76 Min: 42.43 / Avg: 388.69 / Max: 610.63 Min: 193.87 / Avg: 497.42 / Max: 712.24 Min: 56.36 / Avg: 321.76 / Max: 506.14 Min: 195.19 / Avg: 491.2 / Max: 701.2 Min: 47.97 / Avg: 313.29 / Max: 511.81 Min: 143.09 / Avg: 484.51 / Max: 706.72 Min: 52.85 / Avg: 299.51 / Max: 513.75
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib Xeon 8490H 2P EPYC 9654 2P 6 12 18 24 30 SE +/- 0.50, N = 12 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 24.5 15.0 15.5 13.9 15.1 14.1 12.1 11.9
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 210.65 / Avg: 340.32 / Max: 358.86 Min: 43.59 / Avg: 198.79 / Max: 220.24 Min: 135.82 / Avg: 335.2 / Max: 363.03 Min: 44.38 / Avg: 199.52 / Max: 217.55 Min: 193.47 / Avg: 329.21 / Max: 351.19 Min: 53.28 / Avg: 193.26 / Max: 217.58 Min: 111.18 / Avg: 196.58 / Max: 337.96 Min: 54.32 / Avg: 185.47 / Max: 208.91
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 2 Xeon 8490H 2P EPYC 9654 2P 10 20 30 40 50 SE +/- 0.21, N = 3 SE +/- 0.02, N = 3 SE +/- 0.30, N = 3 SE +/- 0.15, N = 3 SE +/- 0.15, N = 3 SE +/- 0.15, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 41.84 34.76 39.50 35.10 37.56 33.14 36.13 33.25 1. (CXX) g++ options: -O3 -fPIC -lm
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 0.11 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 197.41 / Avg: 406 / Max: 715.18 Min: 55.13 / Avg: 246.97 / Max: 463.69 Min: 133.27 / Avg: 397.03 / Max: 737.4 Min: 44.55 / Avg: 246.06 / Max: 472.17 Min: 200.36 / Avg: 387.74 / Max: 604.4 Min: 54.71 / Avg: 242.86 / Max: 459.54 Min: 111.06 / Avg: 368.42 / Max: 570.84 Min: 54.36 / Avg: 239.22 / Max: 447.94
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.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Xeon 8490H 2P EPYC 9654 2P 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.90, N = 12 13.85 16.88 14.48 18.33 14.49 18.37 14.98 17.83 1. (CXX) g++ options: -O3
Ns Per Day Per Watt
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Ns Per Day Per Watt, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Xeon 8490H 2P EPYC 9654 2P 0.0079 0.0158 0.0237 0.0316 0.0395 0.024 0.035 0.024 0.034 0.024 0.035 0.024 0.035
CPU Power Consumption
Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 OpenBenchmarking.org Watts, Fewer Is Better GROMACS 2022.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 124.19 / Avg: 612.99 / Max: 754.09 Min: 44.84 / Avg: 530.08 / Max: 710.58 Min: 195.67 / Avg: 609.4 / Max: 753.87 Min: 55.05 / Avg: 526.31 / Max: 696.3 Min: 190.84 / Avg: 593.5 / Max: 752.51 Min: 55.13 / Avg: 523.95 / Max: 695.03 Min: 204.99 / Avg: 566.94 / Max: 753.12 Min: 57.59 / Avg: 483.92 / Max: 691.43
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits Xeon 8490H 2P EPYC 9654 2P 200K 400K 600K 800K 1000K SE +/- 3989.40, N = 3 SE +/- 1773.93, N = 3 SE +/- 7329.77, N = 5 SE +/- 1402.08, N = 3 SE +/- 571.59, N = 3 SE +/- 117.90, N = 3 SE +/- 893.70, N = 3 SE +/- 608.71, N = 3 661557 1062223 667438 1075000 668323 1060570 672720 1058290 1. (CXX) g++ options: -lcurl -lz -lpthread -lssl -lcrypto -lgmp
kH/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.20.3 Algorithm: LBC, LBRY Credits Xeon 8490H 2P EPYC 9654 2P 400 800 1200 1600 2000 1033.11 1674.53 1051.07 1671.74 1056.75 1675.74 1060.18 1741.63
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.20.3 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 201.56 / Avg: 640.36 / Max: 750.16 Min: 59.87 / Avg: 634.34 / Max: 729.64 Min: 197.57 / Avg: 636.59 / Max: 749.67 Min: 56.64 / Avg: 631.53 / Max: 725.52 Min: 191.48 / Avg: 635.85 / Max: 752.58 Min: 53.26 / Avg: 634.41 / Max: 727.11 Min: 125.57 / Avg: 629.55 / Max: 752.78 Min: 44.48 / Avg: 617.24 / Max: 726.53
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Semaphores Xeon 8490H 2P EPYC 9654 2P 8M 16M 24M 32M 40M SE +/- 4223.75, N = 3 SE +/- 39253.65, N = 3 SE +/- 25202.57, N = 3 SE +/- 22409.16, N = 3 SE +/- 15421.51, N = 3 SE +/- 248572.94, N = 4 SE +/- 22111.46, N = 3 SE +/- 169599.87, N = 3 8648758.12 14681906.13 9091560.92 20580638.57 9824585.26 20869223.44 20839432.55 38317964.95 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Semaphores Xeon 8490H 2P EPYC 9654 2P 20K 40K 60K 80K 100K 15857.91 38982.66 17124.19 52364.99 18256.75 57330.11 42351.88 93551.52
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 207.8 / Avg: 545.39 / Max: 592.6 Min: 57.9 / Avg: 376.63 / Max: 421.71 Min: 196.11 / Avg: 538.13 / Max: 586.2 Min: 54.39 / Avg: 364.02 / Max: 440.56 Min: 164.19 / Avg: 530.92 / Max: 588.78 Min: 56.1 / Avg: 393.02 / Max: 446.26 Min: 128.2 / Avg: 492.05 / Max: 551.44 Min: 36.39 / Avg: 409.59 / Max: 478.48
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Malloc Xeon 8490H 2P EPYC 9654 2P 200M 400M 600M 800M 1000M SE +/- 1357150.06, N = 3 SE +/- 535455.09, N = 3 SE +/- 945911.95, N = 3 SE +/- 472865.20, N = 3 SE +/- 700407.15, N = 3 SE +/- 1309615.37, N = 3 SE +/- 1102560.16, N = 3 SE +/- 1128975.32, N = 3 345237484.97 732089658.78 352485778.28 757554642.77 354331976.06 755056251.17 363422967.84 779076525.72 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Malloc Xeon 8490H 2P EPYC 9654 2P 300K 600K 900K 1200K 1500K 538561.51 1186170.12 553166.92 1219368.29 562884.08 1223251.74 577946.03 1284436.46
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 196.1 / Avg: 641.04 / Max: 751.19 Min: 58.3 / Avg: 617.19 / Max: 707.51 Min: 193.6 / Avg: 637.21 / Max: 752.17 Min: 55.17 / Avg: 621.27 / Max: 709.79 Min: 112.21 / Avg: 629.49 / Max: 751.89 Min: 55.69 / Avg: 617.25 / Max: 710.08 Min: 130.98 / Avg: 628.82 / Max: 751 Min: 46.5 / Avg: 606.55 / Max: 706.41
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: MEMFD EPYC 9654 2P Xeon 8490H 2P 800 1600 2400 3200 4000 SE +/- 9.25, N = 3 SE +/- 0.51, N = 3 SE +/- 2.06, N = 3 SE +/- 5.86, N = 3 SE +/- 0.64, N = 3 SE +/- 1.99, N = 3 SE +/- 5.64, N = 3 SE +/- 1.38, N = 3 2452.79 3170.33 2520.75 3144.15 2602.69 3275.84 2737.60 3631.89 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: MEMFD Xeon 8490H 2P EPYC 9654 2P 2 4 6 8 10 5.565 6.783 5.630 6.620 5.776 6.905 6.245 6.870
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 132.66 / Avg: 581.61 / Max: 654.06 Min: 44.92 / Avg: 398.46 / Max: 455.06 Min: 207.39 / Avg: 567.12 / Max: 619.34 Min: 61.5 / Avg: 376.95 / Max: 425.8 Min: 195.62 / Avg: 564.96 / Max: 616.51 Min: 51.34 / Avg: 371.63 / Max: 418.04 Min: 185.76 / Avg: 563.12 / Max: 616.48 Min: 57.37 / Avg: 370.51 / Max: 419.86
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Crypto Xeon 8490H 2P EPYC 9654 2P 70K 140K 210K 280K 350K SE +/- 93.48, N = 3 SE +/- 1209.90, N = 3 SE +/- 291.93, N = 3 SE +/- 153.29, N = 3 SE +/- 35.55, N = 3 SE +/- 1136.96, N = 3 SE +/- 149.73, N = 3 SE +/- 116.86, N = 3 151720.93 303693.84 155922.29 312079.56 156719.16 316020.79 203339.63 310982.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lz -pthread
Bogo Ops/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Crypto Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 239.23 525.18 247.02 545.95 247.47 539.64 324.94 567.41
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 201.58 / Avg: 634.45 / Max: 707.16 Min: 53.03 / Avg: 578.85 / Max: 659.39 Min: 198.35 / Avg: 634.2 / Max: 713.82 Min: 56.31 / Avg: 578.27 / Max: 656.34 Min: 111.16 / Avg: 630.07 / Max: 707.77 Min: 48.7 / Avg: 578.31 / Max: 661.75 Min: 127.35 / Avg: 625.78 / Max: 710.51 Min: 44.23 / Avg: 548.08 / Max: 629.63
Result
Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: Vector Math Xeon 8490H 2P EPYC 9654 2P 200K 400K 600K 800K 1000K SE +/- 110.65, N = 3 SE +/- 23.11, N = 3 SE +/- 1874.24, N = 3 SE +/- 89.65, N = 3 SE +/- 623.96, N = 3 SE +/- 15.81, N = 3 SE +/- 2581.60, N = 3 SE +/- 86.45, N = 3 534773.07 1003872.99 584432.47 1107161.31 587905.66 1111519.06 593402.97 1105767.24 1. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -latomic -lc -lcrypt -ldl -lEGL -lGLESv2 -ljpeg -lrt -lz -pthread
Bogo Ops/s Per Watt
Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: Vector Math Xeon 8490H 2P EPYC 9654 2P 400 800 1200 1600 2000 848.12 1883.36 920.78 1960.01 923.19 1956.54 928.23 1940.68
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 194.87 / Avg: 639.28 / Max: 752.68 Min: 59.57 / Avg: 569.78 / Max: 643.44 Min: 192.84 / Avg: 638.49 / Max: 753.01 Min: 56.39 / Avg: 567.1 / Max: 641.32 Min: 190.7 / Avg: 633.06 / Max: 753.22 Min: 56.09 / Avg: 565.88 / Max: 642.66 Min: 127.44 / Avg: 630.54 / Max: 720.84 Min: 38.77 / Avg: 533.02 / Max: 626.22
Result
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.14.06 Test: SENDFILE Xeon 8490H 2P EPYC 9654 2P 800K 1600K 2400K 3200K 4000K SE +/- 4733.49, N = 3 SE +/- 11901.28, N = 3 SE +/- 1788.96, N = 3 SE +/- 9331.54, N = 3 SE +/- 5361.79, N = 3 SE +/- 34161.07, N = 3 SE +/- 5240.70, N = 3 SE +/- 45875.47, N = 3 1977544.11 3684920.70 2036351.59 3637914.88 2072504.17 3485006.39 2140625.32 3745383.09 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -O2 -std=gnu99 -lm -fuse-ld=gold -laio -latomic -lc -lcrypt -ldl -lEGL -lgbm -lGLESv2 -ljpeg -lkmod -lrt -lz -pthread
Bogo Ops/s Per Watt
Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS CentOS Stream 9 Clear Linux OpenBenchmarking.org Bogo Ops/s Per Watt, More Is Better Stress-NG 0.14.06 Test: SENDFILE Xeon 8490H 2P EPYC 9654 2P 1300 2600 3900 5200 6500 3086.56 6053.22 3204.19 5943.66 3243.34 5635.08 3409.28 6257.35
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Stress-NG 0.14.06 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 187.73 / Avg: 640.69 / Max: 752.7 Min: 54.5 / Avg: 608.75 / Max: 692.71 Min: 198.76 / Avg: 639 / Max: 753.75 Min: 59.01 / Avg: 618.45 / Max: 703.32 Min: 111.62 / Avg: 635.07 / Max: 753.55 Min: 55.13 / Avg: 612.07 / Max: 696.86 Min: 129.14 / Avg: 627.88 / Max: 752.38 Min: 48.21 / Avg: 598.56 / Max: 688.76
Cpuminer-Opt Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org kH/s, More Is Better Cpuminer-Opt 3.20.3 Algorithm: x25x Xeon 8490H 2P EPYC 9654 2P 2K 4K 6K 8K 10K SE +/- 24.35, N = 3 SE +/- 36.77, N = 3 SE +/- 13.40, N = 3 SE +/- 93.60, N = 3 SE +/- 23.25, N = 3 SE +/- 69.06, N = 3 SE +/- 1.75, N = 3 SE +/- 29.73, N = 3 4064.51 7612.66 4099.70 7862.40 4184.79 7769.11 5002.69 7584.87 1. (CXX) g++ options: -lcurl -lz -lpthread -lssl -lcrypto -lgmp
kH/s Per Watt
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org kH/s Per Watt, More Is Better Cpuminer-Opt 3.20.3 Algorithm: x25x Xeon 8490H 2P EPYC 9654 2P 4 8 12 16 20 6.350 13.424 6.409 13.802 6.592 13.754 7.984 13.661
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Cpuminer-Opt 3.20.3 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 191.45 / Avg: 640.03 / Max: 753.46 Min: 57.26 / Avg: 567.1 / Max: 647.06 Min: 190.86 / Avg: 639.65 / Max: 752.65 Min: 60.39 / Avg: 569.64 / Max: 648.5 Min: 202.38 / Avg: 634.8 / Max: 752.81 Min: 56.25 / Avg: 564.87 / Max: 649.01 Min: 127.59 / Avg: 626.63 / Max: 753.88 Min: 52.93 / Avg: 555.24 / Max: 638.63
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.4 Blend File: Classroom - Compute: CPU-Only Xeon 8490H 2P EPYC 9654 2P 9 18 27 36 45 SE +/- 0.24, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 38.55 21.19 37.14 20.86 36.66 20.53 36.53 20.43
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Blender 3.4 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 195.77 / Avg: 641.15 / Max: 752.61 Min: 59.41 / Avg: 562.17 / Max: 678.04 Min: 189.88 / Avg: 640.22 / Max: 754.12 Min: 58.24 / Avg: 555.26 / Max: 675.92 Min: 129.97 / Avg: 631.04 / Max: 753.82 Min: 47.75 / Avg: 539.4 / Max: 669.57 Min: 106.61 / Avg: 621.07 / Max: 733.39 Min: 57.42 / Avg: 553.92 / Max: 673.48
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon 8490H 2P EPYC 9654 2P 70 140 210 280 350 SE +/- 1.61, N = 3 SE +/- 3.13, N = 3 SE +/- 1.68, N = 4 SE +/- 1.56, N = 4 SE +/- 1.03, N = 3 SE +/- 3.57, N = 4 SE +/- 1.55, N = 3 SE +/- 1.97, N = 4 136.91 298.43 140.03 323.08 144.37 325.09 183.96 342.45 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Billion Interactions/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Billion Interactions/s Per Watt, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon 8490H 2P EPYC 9654 2P 0.1622 0.3244 0.4866 0.6488 0.811 0.237 0.634 0.237 0.635 0.253 0.666 0.333 0.721
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better miniBUDE 20210901 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 197 / Avg: 590.13 / Max: 754.77 Min: 58.74 / Avg: 509.31 / Max: 654.44 Min: 187.09 / Avg: 577.4 / Max: 755.09 Min: 55.83 / Avg: 470.28 / Max: 635.79 Min: 191.88 / Avg: 571.01 / Max: 754.78 Min: 55.44 / Avg: 487.89 / Max: 637.29 Min: 129.62 / Avg: 552.3 / Max: 756.4 Min: 42.63 / Avg: 474.82 / Max: 637.54
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon 8490H 2P EPYC 9654 2P 2K 4K 6K 8K 10K SE +/- 40.18, N = 3 SE +/- 78.13, N = 3 SE +/- 42.11, N = 4 SE +/- 38.90, N = 4 SE +/- 25.87, N = 3 SE +/- 89.21, N = 4 SE +/- 38.68, N = 3 SE +/- 49.24, N = 4 3422.63 7460.78 3500.81 8076.93 3609.29 8127.35 4599.07 8561.24 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes Xeon 8490H 2P EPYC 9654 2P 30 60 90 120 150 SE +/- 0.58, N = 3 SE +/- 0.15, N = 3 SE +/- 0.33, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 146.0 88.2 103.0 91.4 88.8 79.7 60.3 58.6
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 195.99 / Avg: 281.28 / Max: 345.24 Min: 56.24 / Avg: 194.29 / Max: 219.85 Min: 203.36 / Avg: 251.16 / Max: 295.89 Min: 46.82 / Avg: 196.78 / Max: 217.84 Min: 134.54 / Avg: 231.91 / Max: 299.41 Min: 46.48 / Avg: 191.24 / Max: 217.57 Min: 52.52 / Avg: 190.74 / Max: 211.3 Min: 113.84 / Avg: 182.63 / Max: 193.16
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Xeon 8490H 2P EPYC 9654 2P 30 60 90 120 150 SE +/- 1.86, N = 3 SE +/- 0.15, N = 3 SE +/- 0.33, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 SE +/- 0.07, N = 3 152.0 84.0 101.0 94.1 84.4 80.3 57.1 53.7
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 200.98 / Avg: 337.75 / Max: 356.18 Min: 55.84 / Avg: 193.95 / Max: 219.75 Min: 199.24 / Avg: 332.02 / Max: 351.21 Min: 48.97 / Avg: 196.07 / Max: 217.92 Min: 133.16 / Avg: 316.25 / Max: 359.54 Min: 43.39 / Avg: 190.53 / Max: 217.69 Min: 50.34 / Avg: 190.32 / Max: 211.49 Min: 113.45 / Avg: 184.93 / Max: 274.74
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.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Xeon 8490H 2P EPYC 9654 2P 50 100 150 200 250 SE +/- 3.77, N = 15 SE +/- 5.69, N = 15 SE +/- 7.70, N = 15 SE +/- 10.47, N = 15 SE +/- 1.05, N = 6 SE +/- 5.47, N = 15 SE +/- 0.50, N = 7 SE +/- 5.98, N = 15 112.55 174.18 207.08 230.05 224.36 236.89 225.77 247.28 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 1.4 Encoder Mode: Preset 12 - Input: Bosphorus 4K Xeon 8490H 2P EPYC 9654 2P 0.3211 0.6422 0.9633 1.2844 1.6055 0.475 1.051 0.640 1.300 0.684 1.373 0.752 1.427
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 1.4 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 90 180 270 360 450 Min: 190.47 / Avg: 330.05 / Max: 521.85 Min: 30.39 / Avg: 180.13 / Max: 332.18 Min: 193.28 / Avg: 323.68 / Max: 495.1 Min: 48.85 / Avg: 177.01 / Max: 327.29 Min: 130.23 / Avg: 298.18 / Max: 506.41 Min: 41.96 / Avg: 166.05 / Max: 322.48 Min: 114.51 / Avg: 236.95 / Max: 404.42 Min: 54.44 / Avg: 165.7 / Max: 281.87
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Xeon 8490H 2P EPYC 9654 2P 13 26 39 52 65 SE +/- 0.10, N = 3 SE +/- 0.20, N = 4 SE +/- 0.29, N = 5 SE +/- 0.54, N = 5 SE +/- 0.52, N = 5 SE +/- 0.62, N = 15 SE +/- 0.20, N = 5 SE +/- 0.42, N = 15 21.72 48.35 53.34 55.36 57.28 60.02 57.98 58.19 1. (CXX) g++ options:
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Xeon 8490H 2P EPYC 9654 2P 0.0497 0.0994 0.1491 0.1988 0.2485 0.097 0.209 0.125 0.209 0.129 0.208 0.133 0.221
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 191.91 / Avg: 448.95 / Max: 561.13 Min: 55.02 / Avg: 280.16 / Max: 384.92 Min: 132.69 / Avg: 430.91 / Max: 534.12 Min: 41.87 / Avg: 271.54 / Max: 377.21 Min: 189.45 / Avg: 427.03 / Max: 519.9 Min: 50.64 / Avg: 264.78 / Max: 371.63 Min: 54.86 / Avg: 231.29 / Max: 314.89 Min: 116.5 / Avg: 224 / Max: 245.4
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Xeon 8490H 2P EPYC 9654 2P 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.48, N = 15 SE +/- 0.45, N = 14 SE +/- 0.64, N = 8 SE +/- 0.55, N = 10 SE +/- 0.24, N = 6 SE +/- 0.42, N = 5 SE +/- 0.35, N = 6 30.19 68.02 68.57 74.30 70.41 78.48 70.45 77.57 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Xeon 8490H 2P EPYC 9654 2P 0.0686 0.1372 0.2058 0.2744 0.343 0.135 0.301 0.161 0.287 0.163 0.290 0.171 0.305
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 199.57 / Avg: 436.89 / Max: 563.97 Min: 54.92 / Avg: 270.31 / Max: 382.93 Min: 194.43 / Avg: 420.99 / Max: 540.41 Min: 48 / Avg: 256.39 / Max: 366.35 Min: 132.34 / Avg: 411.3 / Max: 535.04 Min: 49.22 / Avg: 257.3 / Max: 387.12 Min: 54.5 / Avg: 225.61 / Max: 327.48 Min: 115.95 / Avg: 223.76 / Max: 252.59
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pickle_pure_python Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 SE +/- 5.04, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 566 330 390 359 329 326 227 219
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 Min: 208.08 / Avg: 302.9 / Max: 349.01 Min: 56.19 / Avg: 196.61 / Max: 219.75 Min: 195.51 / Avg: 257.97 / Max: 319.81 Min: 47.91 / Avg: 187.1 / Max: 217.69 Min: 135.35 / Avg: 232.26 / Max: 296.76 Min: 48.26 / Avg: 196.06 / Max: 217.86 Min: 111.98 / Avg: 185.79 / Max: 208.58 Min: 54.45 / Avg: 181.43 / Max: 209.55
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Xeon 8490H 2P EPYC 9654 2P 3 6 9 12 15 SE +/- 0.138, N = 15 SE +/- 0.056, N = 5 SE +/- 0.038, N = 5 SE +/- 0.098, N = 6 SE +/- 0.069, N = 5 SE +/- 0.034, N = 5 SE +/- 0.025, N = 5 SE +/- 0.084, N = 5 12.959 10.079 10.759 9.654 10.674 10.188 10.303 9.954
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 90 180 270 360 450 Min: 197.37 / Avg: 336.51 / Max: 534.4 Min: 49.89 / Avg: 200.77 / Max: 331.07 Min: 196.51 / Avg: 333.07 / Max: 526.3 Min: 56.34 / Avg: 204.7 / Max: 369.85 Min: 128.26 / Avg: 318.62 / Max: 527.62 Min: 43.81 / Avg: 194.14 / Max: 355.81 Min: 112.69 / Avg: 280.01 / Max: 473.42 Min: 54.02 / Avg: 196.89 / Max: 355.99
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon 8490H 2P EPYC 9654 2P 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.47, N = 15 SE +/- 0.35, N = 5 SE +/- 0.65, N = 15 SE +/- 0.66, N = 6 SE +/- 0.55, N = 6 SE +/- 0.69, N = 5 SE +/- 0.51, N = 6 25.43 68.90 66.88 74.30 70.58 76.91 70.95 76.62 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon 8490H 2P EPYC 9654 2P 0.0657 0.1314 0.1971 0.2628 0.3285 0.112 0.292 0.153 0.270 0.156 0.267 0.163 0.276
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 197.4 / Avg: 456.23 / Max: 596.33 Min: 56.72 / Avg: 287.25 / Max: 410.74 Min: 196.92 / Avg: 437.06 / Max: 569.17 Min: 44.81 / Avg: 275.69 / Max: 399.04 Min: 128.82 / Avg: 433.2 / Max: 568.35 Min: 44.63 / Avg: 278.37 / Max: 421.18 Min: 49.71 / Avg: 236.35 / Max: 353.6 Min: 116.34 / Avg: 226.51 / Max: 256.62
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Xeon 8490H 2P EPYC 9654 2P 11 22 33 44 55 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.28, N = 4 SE +/- 0.07, N = 3 SE +/- 0.21, N = 4 SE +/- 0.03, N = 3 SE +/- 0.18, N = 4 11.22 31.79 27.77 48.57 29.09 47.57 29.13 48.07 1. (CXX) g++ options:
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Xeon 8490H 2P EPYC 9654 2P 0.0252 0.0504 0.0756 0.1008 0.126 0.042 0.096 0.051 0.107 0.051 0.110 0.053 0.112
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 194.41 / Avg: 572.25 / Max: 659.87 Min: 54.72 / Avg: 446.3 / Max: 595.91 Min: 128.53 / Avg: 550.04 / Max: 644.07 Min: 47.89 / Avg: 428.84 / Max: 596.74 Min: 192.49 / Avg: 542.12 / Max: 630.64 Min: 47.34 / Avg: 442 / Max: 604.34 Min: 56.36 / Avg: 331.8 / Max: 425.18 Min: 115.71 / Avg: 266.5 / Max: 476.65
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Xeon 8490H 2P EPYC 9654 2P 13 26 39 52 65 SE +/- 0.03, N = 3 SE +/- 0.21, N = 4 SE +/- 0.12, N = 5 SE +/- 0.61, N = 5 SE +/- 0.44, N = 5 SE +/- 0.39, N = 15 SE +/- 0.29, N = 5 SE +/- 0.32, N = 5 21.57 48.69 53.36 56.91 56.85 60.13 57.30 57.86 1. (CXX) g++ options:
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Xeon 8490H 2P EPYC 9654 2P 0.0461 0.0922 0.1383 0.1844 0.2305 0.094 0.202 0.119 0.199 0.122 0.193 0.129 0.205
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 100 200 300 400 500 Min: 196.32 / Avg: 469.79 / Max: 592.5 Min: 55.12 / Avg: 300.56 / Max: 400.55 Min: 190.45 / Avg: 449.72 / Max: 553.76 Min: 52.35 / Avg: 285.5 / Max: 396.67 Min: 130.85 / Avg: 441.21 / Max: 561.4 Min: 44.63 / Avg: 292.68 / Max: 408.13 Min: 52.3 / Avg: 240.7 / Max: 349.35 Min: 116.06 / Avg: 229.2 / Max: 253.68
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Fast EPYC 9654 2P Xeon 8490H 2P 200 400 600 800 1000 SE +/- 2.57, N = 5 SE +/- 6.31, N = 6 SE +/- 38.25, N = 15 SE +/- 2.93, N = 6 SE +/- 6.13, N = 5 SE +/- 4.99, N = 5 SE +/- 1.97, N = 6 SE +/- 1.20, N = 6 672.10 821.58 689.97 801.09 726.36 797.20 758.64 816.99 1. (CXX) g++ options: -O3 -flto -pthread
MT/s Per Watt
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Fast Xeon 8490H 2P EPYC 9654 2P 0.6494 1.2988 1.9482 2.5976 3.247 1.945 2.545 1.994 2.626 2.086 2.347 2.472 2.886
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 200.04 / Avg: 409.78 / Max: 653.05 Min: 46.11 / Avg: 285.43 / Max: 526.45 Min: 195.89 / Avg: 409.73 / Max: 650.55 Min: 54.86 / Avg: 288.89 / Max: 527.18 Min: 130.2 / Avg: 393.86 / Max: 668.31 Min: 44.1 / Avg: 286.42 / Max: 534.32 Min: 112.15 / Avg: 279.1 / Max: 601 Min: 51.86 / Avg: 277.61 / Max: 533.3
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU EPYC 9654 2P Xeon 8490H 2P 0.6333 1.2666 1.8999 2.5332 3.1665 SE +/- 0.027471, N = 3 SE +/- 0.004974, N = 3 SE +/- 0.018337, N = 3 SE +/- 0.007878, N = 3 SE +/- 0.019078, N = 3 SE +/- 0.006205, N = 4 SE +/- 0.003696, N = 3 SE +/- 0.001720, N = 3 2.814460 0.617234 2.376550 0.560616 2.357570 0.592698 2.299060 0.581093 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
CPU Power Consumption
Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 124.59 / Avg: 583.26 / Max: 707.53 Min: 46.42 / Avg: 480.65 / Max: 607.33 Min: 190.5 / Avg: 530.93 / Max: 637.23 Min: 57.38 / Avg: 417.4 / Max: 564.62 Min: 197.01 / Avg: 529.99 / Max: 635.37 Min: 54.4 / Avg: 415.94 / Max: 558.97 Min: 198.13 / Avg: 528.88 / Max: 634.38 Min: 53.63 / Avg: 413.56 / Max: 583.87
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.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite EPYC 9654 2P Xeon 8490H 2P 400K 800K 1200K 1600K 2000K SE +/- 5880.07, N = 3 SE +/- 410.52, N = 3 SE +/- 5482.11, N = 3 SE +/- 11536.02, N = 3 SE +/- 7827.87, N = 3 SE +/- 2731.62, N = 3 SE +/- 19191.23, N = 5 SE +/- 7368.91, N = 5 772354 900784 840445 930634 852671 950645 1979213 2022000
Score Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Score Per Watt, More Is Better PHPBench 0.8.1 PHP Benchmark Suite EPYC 9654 2P Xeon 8490H 2P 2K 4K 6K 8K 10K 3893.47 3940.85 4222.65 4396.93 4528.80 4725.14 9741.06 11452.08
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PHPBench 0.8.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 50 100 150 200 250 Min: 193.52 / Avg: 228.58 / Max: 256.07 Min: 55.77 / Avg: 198.37 / Max: 219.66 Min: 196.05 / Avg: 225.13 / Max: 239.9 Min: 52.17 / Avg: 193.92 / Max: 218.21 Min: 131.78 / Avg: 207.57 / Max: 271.85 Min: 35.22 / Avg: 172.83 / Max: 217.66 Min: 113.85 / Avg: 196.95 / Max: 246.08 Min: 54.29 / Avg: 185.58 / Max: 211.14
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Xeon 8490H 2P EPYC 9654 2P 15 30 45 60 75 SE +/- 0.01, N = 3 SE +/- 0.06, N = 4 SE +/- 0.16, N = 3 SE +/- 0.36, N = 5 SE +/- 0.04, N = 3 SE +/- 0.30, N = 5 SE +/- 0.05, N = 3 SE +/- 0.26, N = 5 12.88 38.66 31.71 62.52 33.27 65.01 33.77 65.67 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Xeon 8490H 2P EPYC 9654 2P 0.038 0.076 0.114 0.152 0.19 0.052 0.130 0.064 0.163 0.064 0.162 0.067 0.169
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 200.94 / Avg: 530.13 / Max: 612.37 Min: 58.03 / Avg: 402.12 / Max: 582.91 Min: 192.65 / Avg: 498.79 / Max: 582.27 Min: 49.28 / Avg: 386.21 / Max: 550.89 Min: 136.32 / Avg: 498.49 / Max: 589.13 Min: 52.94 / Avg: 384.74 / Max: 582.74 Min: 55.74 / Avg: 296.85 / Max: 395.11 Min: 59.45 / Avg: 248.49 / Max: 406.71
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Xeon 8490H 2P EPYC 9654 2P 15 30 45 60 75 SE +/- 0.05, N = 3 SE +/- 0.11, N = 4 SE +/- 0.05, N = 3 SE +/- 0.53, N = 5 SE +/- 0.10, N = 3 SE +/- 0.17, N = 5 SE +/- 0.05, N = 3 SE +/- 0.48, N = 5 13.16 39.52 32.43 63.33 33.92 65.54 34.44 65.49 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Xeon 8490H 2P EPYC 9654 2P 0.0389 0.0778 0.1167 0.1556 0.1945 0.054 0.135 0.065 0.168 0.066 0.167 0.069 0.173
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 202.1 / Avg: 521.43 / Max: 615.44 Min: 55.47 / Avg: 392.9 / Max: 578.39 Min: 197.68 / Avg: 499.55 / Max: 580.94 Min: 46.36 / Avg: 376.79 / Max: 550.82 Min: 128.09 / Avg: 489.51 / Max: 589.9 Min: 51.59 / Avg: 378.46 / Max: 580.85 Min: 53.23 / Avg: 293.29 / Max: 376.64 Min: 115.56 / Avg: 244.6 / Max: 318.35
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 EPYC 9654 2P Xeon 8490H 2P 0.963 1.926 2.889 3.852 4.815 SE +/- 0.00, N = 5 SE +/- 0.01, N = 6 SE +/- 0.01, N = 5 SE +/- 0.01, N = 6 SE +/- 0.01, N = 5 SE +/- 0.04, N = 15 SE +/- 0.01, N = 5 SE +/- 0.01, N = 6 3.00 4.20 3.05 4.28 3.45 3.66 3.54 4.22
Images / Sec Per Watt
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 Xeon 8490H 2P EPYC 9654 2P 0.0027 0.0054 0.0081 0.0108 0.0135 0.010 0.010 0.010 0.011 0.010 0.012 0.010 0.012
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 197.85 / Avg: 414.04 / Max: 731.57 Min: 57.94 / Avg: 299.65 / Max: 571.95 Min: 133.53 / Avg: 413.53 / Max: 726.25 Min: 21.77 / Avg: 278.07 / Max: 564.43 Min: 191.98 / Avg: 412.93 / Max: 725.05 Min: 47.91 / Avg: 285.12 / Max: 576.93 Min: 109.08 / Avg: 351.27 / Max: 700.92 Min: 52.95 / Avg: 290.31 / Max: 569.18
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 240 - Buffer Length: 256 - Filter Length: 57 Xeon 8490H 2P EPYC 9654 2P 3000M 6000M 9000M 12000M 15000M SE +/- 23950017.40, N = 3 SE +/- 4466666.67, N = 3 SE +/- 9740351.35, N = 3 SE +/- 7535103.04, N = 3 SE +/- 6463830.99, N = 3 SE +/- 5507570.55, N = 3 SE +/- 3877427.56, N = 3 SE +/- 13678856.35, N = 3 6349300000 10008533333 6372366667 10269333333 6398333333 10025000000 7209766667 13047666667 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -pthread -lm -lc -lliquid
samples/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 240 - Buffer Length: 256 - Filter Length: 57 Xeon 8490H 2P EPYC 9654 2P 5M 10M 15M 20M 25M 10347201.66 18787322.87 10385408.49 18964055.82 10431258.74 18849486.97 11939483.46 23414150.14
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 193.63 / Avg: 616.09 / Max: 754.06 Min: 54.59 / Avg: 528.63 / Max: 635.69 Min: 197.67 / Avg: 615.85 / Max: 754.47 Min: 58.78 / Avg: 546.61 / Max: 645.97 Min: 166.56 / Avg: 608.68 / Max: 753.54 Min: 55.59 / Avg: 530.97 / Max: 638.8 Min: 119.96 / Avg: 603.86 / Max: 754.41 Min: 46.91 / Avg: 557.26 / Max: 665.99
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon 8490H 2P EPYC 9654 2P 2000M 4000M 6000M 8000M 10000M SE +/- 9963098.58, N = 3 SE +/- 11065260.95, N = 3 SE +/- 16209359.44, N = 3 SE +/- 24755874.72, N = 3 SE +/- 10857255.64, N = 3 SE +/- 35853234.78, N = 3 SE +/- 102638026.31, N = 3 SE +/- 1113552.87, N = 3 6188900000 7972200000 6259700000 7902500000 6284000000 7899633333 7172733333 9886800000 1. (CC) gcc options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -pthread -lm -lc -lliquid
samples/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon 8490H 2P EPYC 9654 2P 4M 8M 12M 16M 20M 9985029.21 15363620.99 10157690.17 15954692.34 10240978.56 15667448.51 11834462.78 19097015.65
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 193.08 / Avg: 619.82 / Max: 753.55 Min: 57.52 / Avg: 518.9 / Max: 616.87 Min: 197.2 / Avg: 618.64 / Max: 752.86 Min: 46.94 / Avg: 495.13 / Max: 599.63 Min: 167.28 / Avg: 611.24 / Max: 752.82 Min: 54.73 / Avg: 504.39 / Max: 598.97 Min: 126.51 / Avg: 606.09 / Max: 752.87 Min: 41.56 / Avg: 517.71 / Max: 629.35
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Xeon 8490H 2P EPYC 9654 2P 20 40 60 80 100 SE +/- 0.03, N = 3 SE +/- 0.66, N = 6 SE +/- 0.52, N = 15 SE +/- 0.47, N = 6 SE +/- 0.65, N = 6 SE +/- 0.81, N = 6 SE +/- 0.71, N = 6 SE +/- 0.45, N = 6 30.33 68.86 71.20 79.87 72.14 79.76 72.98 79.64 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Xeon 8490H 2P EPYC 9654 2P 0.0772 0.1544 0.2316 0.3088 0.386 0.142 0.331 0.177 0.325 0.180 0.343 0.189 0.338
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 90 180 270 360 450 Min: 198.83 / Avg: 413.04 / Max: 528.89 Min: 55.32 / Avg: 245.26 / Max: 350.78 Min: 193.41 / Avg: 394.9 / Max: 496.39 Min: 52.54 / Avg: 232.64 / Max: 334.78 Min: 128.58 / Avg: 381.93 / Max: 492.94 Min: 29.21 / Avg: 235.94 / Max: 354.98 Min: 116.23 / Avg: 212.89 / Max: 237.48 Min: 54.01 / Avg: 207.99 / Max: 297.34
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.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times EPYC 9654 2P Xeon 8490H 2P 200 400 600 800 1000 SE +/- 1.73, N = 3 SE +/- 1.15, N = 3 SE +/- 3.93, N = 3 SE +/- 1.15, N = 3 SE +/- 2.40, N = 3 SE +/- 1.15, N = 3 SE +/- 2.60, N = 3 SE +/- 0.82, N = 4 977 860 853 760 844 760 749 664
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better PyBench 2018-02-16 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 50 100 150 200 250 Min: 196.73 / Avg: 227.54 / Max: 278.84 Min: 53.5 / Avg: 189.4 / Max: 218.25 Min: 193.76 / Avg: 227.47 / Max: 253.78 Min: 54.66 / Avg: 196.22 / Max: 219.65 Min: 130.92 / Avg: 214.39 / Max: 298.49 Min: 39.43 / Avg: 186.76 / Max: 217.76 Min: 112.97 / Avg: 194.08 / Max: 219.47 Min: 55.72 / Avg: 192.24 / Max: 215.76
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Xeon 8490H 2P EPYC 9654 2P 30 60 90 120 150 SE +/- 1.23, N = 15 SE +/- 0.05, N = 7 SE +/- 0.04, N = 6 SE +/- 0.05, N = 7 SE +/- 0.02, N = 6 SE +/- 0.05, N = 7 SE +/- 0.04, N = 6 SE +/- 0.14, N = 7 63.02 107.32 78.28 107.82 78.81 107.22 85.85 114.79 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -flto -pthread
MT/s Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Thorough Xeon 8490H 2P EPYC 9654 2P 0.1051 0.2102 0.3153 0.4204 0.5255 0.174 0.421 0.198 0.415 0.199 0.421 0.228 0.467
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 196.8 / Avg: 398.72 / Max: 735.04 Min: 55.55 / Avg: 258.48 / Max: 649.64 Min: 198.43 / Avg: 393.62 / Max: 739.26 Min: 50.94 / Avg: 256.04 / Max: 652.58 Min: 130.34 / Avg: 377.27 / Max: 738.39 Min: 48.58 / Avg: 245.95 / Max: 653.09 Min: 114.52 / Avg: 362.54 / Max: 746.68 Min: 54.77 / Avg: 254.9 / Max: 653.22
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Xeon 8490H 2P EPYC 9654 2P 40 80 120 160 200 SE +/- 1.08, N = 3 SE +/- 0.37, N = 4 SE +/- 0.92, N = 3 SE +/- 0.49, N = 4 SE +/- 0.60, N = 3 SE +/- 0.60, N = 4 SE +/- 1.61, N = 3 SE +/- 0.32, N = 4 79.89 182.92 102.39 184.84 104.09 183.91 114.23 184.14
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Xeon 8490H 2P EPYC 9654 2P 0.1643 0.3286 0.4929 0.6572 0.8215 0.205 0.730 0.247 0.701 0.250 0.697 0.291 0.708
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 191.19 / Avg: 416.14 / Max: 676.75 Min: 57.29 / Avg: 263.95 / Max: 632.38 Min: 192.77 / Avg: 414.24 / Max: 662.6 Min: 54.53 / Avg: 263.84 / Max: 628.39 Min: 131.88 / Avg: 392.39 / Max: 694.98 Min: 15.47 / Avg: 260.16 / Max: 627.37 Min: 119.51 / Avg: 390.61 / Max: 605.83 Min: 53.65 / Avg: 250.68 / Max: 626.05
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux CentOS Stream 9 OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon 8490H 2P EPYC 9654 2P 13 26 39 52 65 SE +/- 0.03, N = 3 SE +/- 0.52, N = 4 SE +/- 0.33, N = 4 SE +/- 0.34, N = 5 SE +/- 0.39, N = 5 SE +/- 0.36, N = 5 SE +/- 0.22, N = 5 SE +/- 0.24, N = 5 20.80 48.81 50.03 56.20 55.89 59.27 56.05 56.88 1. (CXX) g++ options:
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon 8490H 2P EPYC 9654 2P 0.0446 0.0892 0.1338 0.1784 0.223 0.090 0.198 0.110 0.194 0.117 0.187 0.122 0.198
CPU Power Consumption
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 200.4 / Avg: 478.71 / Max: 596.86 Min: 54.64 / Avg: 304.73 / Max: 408.21 Min: 136.27 / Avg: 457.97 / Max: 573.23 Min: 40.81 / Avg: 298.62 / Max: 418.81 Min: 186.89 / Avg: 455.75 / Max: 549.03 Min: 45.97 / Avg: 289.35 / Max: 402.04 Min: 54.9 / Avg: 247.11 / Max: 353.6 Min: 116.02 / Avg: 231.95 / Max: 268.47
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.0 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU EPYC 9654 2P Xeon 8490H 2P 0.1075 0.215 0.3225 0.43 0.5375 SE +/- 0.002274, N = 7 SE +/- 0.001315, N = 7 SE +/- 0.003761, N = 15 SE +/- 0.001245, N = 7 SE +/- 0.003080, N = 7 SE +/- 0.003793, N = 15 SE +/- 0.003148, N = 7 SE +/- 0.001450, N = 7 0.477561 0.267685 0.448353 0.249854 0.435699 0.275719 0.426703 0.262386 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 194.82 / Avg: 465.97 / Max: 693.9 Min: 59.57 / Avg: 325.81 / Max: 533.91 Min: 194.62 / Avg: 465.12 / Max: 696.01 Min: 53.34 / Avg: 321.46 / Max: 540.85 Min: 123.69 / Avg: 457.61 / Max: 740.63 Min: 30.35 / Avg: 355.38 / Max: 587.33 Min: 190.34 / Avg: 456.24 / Max: 697.18 Min: 54.99 / Avg: 320.93 / Max: 541.22
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction Xeon 8490H 2P EPYC 9654 2P 2 4 6 8 10 SE +/- 0.02209740, N = 4 SE +/- 0.00800088, N = 6 SE +/- 0.05125458, N = 10 SE +/- 0.26681151, N = 12 SE +/- 0.03708790, N = 6 SE +/- 0.02675153, N = 7 SE +/- 0.03285028, N = 6 SE +/- 0.01513938, N = 8 7.01116741 4.74432603 6.65763593 5.50633752 6.45621212 4.53648717 6.18280959 4.17020929 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi
CPU Power Consumption
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 195.35 / Avg: 511.31 / Max: 750.05 Min: 50.78 / Avg: 356.01 / Max: 639.6 Min: 195.6 / Avg: 510.67 / Max: 751.19 Min: 55.93 / Avg: 357.58 / Max: 629.09 Min: 127.18 / Avg: 499.97 / Max: 749.2 Min: 40.58 / Avg: 343.85 / Max: 642.19 Min: 189.15 / Avg: 494.06 / Max: 749.61 Min: 56.69 / Avg: 379.34 / Max: 650.49
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.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Xeon 8490H 2P EPYC 9654 2P 1100 2200 3300 4400 5500 SE +/- 159.79, N = 20 SE +/- 11.32, N = 8 SE +/- 28.63, N = 8 SE +/- 8.81, N = 8 SE +/- 16.28, N = 8 SE +/- 19.79, N = 11 SE +/- 7.25, N = 8 SE +/- 7.23, N = 8 5314 3460 3346 2596 3273 2662 3111 2679
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better DaCapo Benchmark 9.12-MR1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 70 140 210 280 350 Min: 199.72 / Avg: 309.8 / Max: 414.75 Min: 57.15 / Avg: 156.43 / Max: 259.83 Min: 198.76 / Avg: 295.69 / Max: 403.42 Min: 51.64 / Avg: 148.2 / Max: 254.48 Min: 129.85 / Avg: 278.1 / Max: 397.8 Min: 40.22 / Avg: 144.59 / Max: 248.39 Min: 98.4 / Avg: 190.78 / Max: 378.58 Min: 52.19 / Avg: 143.65 / Max: 244.35
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Xeon 8490H 2P EPYC 9654 2P 3 6 9 12 15 SE +/- 0.0065, N = 4 SE +/- 0.0265, N = 6 SE +/- 0.0496, N = 5 SE +/- 0.0243, N = 6 SE +/- 0.0031, N = 5 SE +/- 0.0088, N = 6 SE +/- 0.0035, N = 5 SE +/- 0.0116, N = 6 7.3573 11.9780 7.5595 12.0141 7.6361 11.9486 8.4382 12.0706 1. (CXX) g++ options: -O3 -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -flto -pthread
MT/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Xeon 8490H 2P EPYC 9654 2P 0.0088 0.0176 0.0264 0.0352 0.044 0.016 0.037 0.016 0.038 0.016 0.038 0.020 0.039
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 198.12 / Avg: 464.62 / Max: 753.63 Min: 54.62 / Avg: 319.91 / Max: 662.26 Min: 197.79 / Avg: 463.79 / Max: 754.57 Min: 52.12 / Avg: 319.31 / Max: 665.68 Min: 114.25 / Avg: 448.84 / Max: 752.97 Min: 53.61 / Avg: 316.31 / Max: 667.57 Min: 131.82 / Avg: 430.96 / Max: 754.23 Min: 46.63 / Avg: 306.58 / Max: 666.71
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Xeon 8490H 2P EPYC 9654 2P 40 80 120 160 200 SE +/- 0.26, N = 5 SE +/- 0.71, N = 8 SE +/- 0.46, N = 6 SE +/- 0.48, N = 8 SE +/- 0.39, N = 6 SE +/- 0.46, N = 8 SE +/- 0.40, N = 6 SE +/- 0.55, N = 8 63.83 180.05 91.10 179.55 91.63 181.68 99.14 181.42
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Xeon 8490H 2P EPYC 9654 2P 0.1238 0.2476 0.3714 0.4952 0.619 0.150 0.532 0.191 0.507 0.197 0.525 0.228 0.550
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 110 220 330 440 550 Min: 188.96 / Avg: 477.97 / Max: 647.75 Min: 55.7 / Avg: 354.44 / Max: 646.2 Min: 187.08 / Avg: 464.24 / Max: 625.61 Min: 49.41 / Avg: 345.91 / Max: 646.29 Min: 133.45 / Avg: 435.36 / Max: 638.83 Min: 25.63 / Avg: 329.63 / Max: 647.6 Min: 117.83 / Avg: 426.88 / Max: 574.03 Min: 53.25 / Avg: 338.37 / Max: 647.08
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Clear Linux CentOS Stream 9 Ubuntu 22.04.1 LTS - perf OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Xeon 8490H 2P EPYC 9654 2P 2 4 6 8 10 SE +/- 0.106, N = 15 SE +/- 0.011, N = 8 SE +/- 0.018, N = 8 SE +/- 0.029, N = 9 SE +/- 0.011, N = 8 SE +/- 0.010, N = 8 SE +/- 0.007, N = 8 SE +/- 0.017, N = 8 6.601 4.091 4.270 3.641 4.212 3.984 4.143 3.894
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Numenta Anomaly Benchmark 1.1 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 90 180 270 360 450 Min: 199.6 / Avg: 330.55 / Max: 524.41 Min: 55.36 / Avg: 181.37 / Max: 319.48 Min: 131.3 / Avg: 321.64 / Max: 519.86 Min: 47.49 / Avg: 174.02 / Max: 351.92 Min: 129.03 / Avg: 290.84 / Max: 520.5 Min: 44.79 / Avg: 163.25 / Max: 349.93 Min: 112.95 / Avg: 253.31 / Max: 461.89 Min: 52.13 / Avg: 166.12 / Max: 348.71
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 SE +/- 3.32, N = 8 SE +/- 2.39, N = 8 SE +/- 1.08, N = 7 SE +/- 1.46, N = 8 SE +/- 0.42, N = 7 SE +/- 4.04, N = 8 SE +/- 1.40, N = 8 SE +/- 1.59, N = 7 382.54 573.57 489.58 507.36 493.90 530.73 500.66 525.40 1. (CXX) g++ options: -O3 -flto -pthread
MT/s Per Watt
Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Medium Xeon 8490H 2P EPYC 9654 2P 0.7007 1.4014 2.1021 2.8028 3.5035 1.499 2.577 1.506 2.705 1.551 3.114 1.732 2.763
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 199.25 / Avg: 327.89 / Max: 607.43 Min: 54.1 / Avg: 196.21 / Max: 545.19 Min: 193.07 / Avg: 326.62 / Max: 668.27 Min: 47.93 / Avg: 196.89 / Max: 568.81 Min: 131.27 / Avg: 303.38 / Max: 664.15 Min: 47.52 / Avg: 181.23 / Max: 565.36 Min: 113.43 / Avg: 246.68 / Max: 634.39 Min: 29.05 / Avg: 184.18 / Max: 549.7
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon 8490H 2P EPYC 9654 2P 60 120 180 240 300 SE +/- 0.96, N = 11 SE +/- 0.49, N = 9 SE +/- 1.23, N = 7 SE +/- 0.09, N = 10 SE +/- 0.49, N = 7 SE +/- 0.42, N = 9 SE +/- 1.20, N = 8 SE +/- 1.48, N = 9 130.03 277.18 132.29 289.30 136.19 272.73 137.22 277.68 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Billion Interactions/s Per Watt
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Billion Interactions/s Per Watt, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon 8490H 2P EPYC 9654 2P 0.2403 0.4806 0.7209 0.9612 1.2015 0.266 0.907 0.283 0.942 0.287 0.952 0.352 1.068
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS Clear Linux OpenBenchmarking.org Watts, Fewer Is Better miniBUDE 20210901 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 191.18 / Avg: 489.41 / Max: 692.99 Min: 57.28 / Avg: 305.54 / Max: 634.17 Min: 186.8 / Avg: 480.63 / Max: 689.47 Min: 51.81 / Avg: 289.61 / Max: 626.05 Min: 187.46 / Avg: 477.51 / Max: 685.6 Min: 48.12 / Avg: 291.59 / Max: 626.33 Min: 124.42 / Avg: 376.28 / Max: 582.54 Min: 38.35 / Avg: 270.84 / Max: 616.11
CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon 8490H 2P EPYC 9654 2P 1600 3200 4800 6400 8000 SE +/- 24.08, N = 11 SE +/- 12.29, N = 9 SE +/- 30.77, N = 7 SE +/- 2.25, N = 10 SE +/- 12.17, N = 7 SE +/- 10.42, N = 9 SE +/- 30.07, N = 8 SE +/- 36.96, N = 9 3250.80 6929.52 3307.23 7232.47 3404.63 6818.21 3430.60 6942.00 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon 8490H 2P EPYC 9654 2P 50 100 150 200 250 SE +/- 0.66, N = 5 SE +/- 0.17, N = 9 SE +/- 0.91, N = 6 SE +/- 0.14, N = 9 SE +/- 1.21, N = 6 SE +/- 0.34, N = 9 SE +/- 0.77, N = 7 SE +/- 0.40, N = 9 96.99 212.02 121.74 212.49 122.80 212.26 131.35 212.92
Frames Per Second Per Watt
Ubuntu 22.04.1 LTS CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon 8490H 2P EPYC 9654 2P 0.1667 0.3334 0.5001 0.6668 0.8335 0.230 0.710 0.259 0.668 0.260 0.694 0.296 0.741
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 188.33 / Avg: 473.67 / Max: 678.31 Min: 55.01 / Avg: 317.89 / Max: 631.43 Min: 190.24 / Avg: 467.45 / Max: 666.26 Min: 53.48 / Avg: 306.04 / Max: 630.58 Min: 131.48 / Avg: 444.17 / Max: 683.43 Min: 16.59 / Avg: 287.3 / Max: 629.26 Min: 115.56 / Avg: 421.35 / Max: 621.1 Min: 46.05 / Avg: 298.56 / Max: 628.06
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.11 Encoder Speed: 6 Xeon 8490H 2P EPYC 9654 2P 0.9932 1.9864 2.9796 3.9728 4.966 SE +/- 0.108, N = 15 SE +/- 0.005, N = 10 SE +/- 0.025, N = 9 SE +/- 0.004, N = 10 SE +/- 0.008, N = 10 SE +/- 0.001, N = 11 SE +/- 0.005, N = 10 SE +/- 0.002, N = 7 4.414 2.472 3.164 2.393 2.503 2.053 2.453 2.007 1. (CXX) g++ options: -O3 -fPIC -pipe -fexceptions -m64 -ffat-lto-objects -fno-trapping-math -mrelax-cmpxchg-loop -std=gnu++17 -lm
CPU Power Consumption
CentOS Stream 9 Ubuntu 22.04.1 LTS - perf Clear Linux Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 0.11 CPU Power Consumption Monitor Xeon 8490H 2P EPYC 9654 2P 120 240 360 480 600 Min: 196.02 / Avg: 322.98 / Max: 679.23 Min: 54.05 / Avg: 157.46 / Max: 423.16 Min: 194.22 / Avg: 314.15 / Max: 551.88 Min: 51.21 / Avg: 150.85 / Max: 401.85 Min: 125.43 / Avg: 286.74 / Max: 694.06 Min: 44.47 / Avg: 145.02 / Max: 351.94 Min: 115.2 / Avg: 261.51 / Max: 496.93 Min: 52.41 / Avg: 148.39 / Max: 405.71
CPU Power Consumption Monitor CentOS Stream 9 Clear Linux Ubuntu 22.04.1 LTS - perf Ubuntu 22.04.1 LTS OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring Xeon 8490H 2P EPYC 9654 2P 130 260 390 520 650 Min: 107.24 / Avg: 488.46 / Max: 755.15 Min: 27.85 / Avg: 351.15 / Max: 756.85 Min: 62.29 / Avg: 477.92 / Max: 756.4 Min: 15.47 / Avg: 350.9 / Max: 746.4 Min: 100.89 / Avg: 472.32 / Max: 755.09 Min: 30.79 / Avg: 350.38 / Max: 747.99 Min: 59.45 / Avg: 360.58 / Max: 754.78 Min: 28.81 / Avg: 332.97 / Max: 730.63
Geometric Mean Of All Test Results Ubuntu 22.04.1 LTS Ubuntu 22.04.1 LTS - perf CentOS Stream 9 Clear Linux OpenBenchmarking.org Geometric Mean, More Is Better Geometric Mean Of All Test Results Result Composite - Sapphire Rapids AMD Genoa - CentOS Stream 9, Clear Linux, Ubuntu Xeon 8490H 2P EPYC 9654 2P 30 60 90 120 150 64.83 95.60 88.81 103.01 92.39 105.29 107.75 124.78
Hide Result
CentOS Stream 9: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: CentOS Stream 9, Kernel: 5.14.0-239.el9.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server, Compiler: GCC 11.3.1 20221121, File-System: xfs, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.18.0.9-0.3.ea.el9) (build 11.0.18-ea+9-LTS)Python Notes: Python 3.9.16Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 27 January 2023 15:08 by user .
CentOS Stream 9: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 257GB Flash Drive, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: CentOS Stream 9, Kernel: 5.14.0-239.el9.x86_64 (x86_64), Desktop: GNOME Shell 40.10, Display Server: X Server, Compiler: GCC 11.3.1 20221121, File-System: xfs, Screen Resolution: 1024x768
Kernel Notes: Transparent Huge Pages: alwaysCompiler Notes: --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (Red_Hat-11.0.18.0.9-0.3.ea.el9) (build 11.0.18-ea+9-LTS)Python Notes: Python 3.9.16Security Notes: SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 26 January 2023 19:39 by user .
Clear Linux: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: Clear Linux OS 38100, Kernel: 6.1.7-1247.native (x86_64), Display Server: X Server 1.21.1.6, Compiler: GCC 12.2.1 20230112 releases/gcc-12.2.0-345-gc142b30b3a + Clang 15.0.6 + LLVM 15.0.6, File-System: ext4, Screen Resolution: 640x480
Kernel Notes: Transparent Huge Pages: alwaysEnvironment Notes: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop -fvisibility-inlines-hidden -Wl,--enable-new-dtags -std=gnu++17" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""Compiler Notes: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=sapphirerapids --with-zstdProcessor Notes: Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 18.0.2-internal+0-adhoc.mockbuild.corretto-18-18.0.2.9.1)Python Notes: Python 3.11.0Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 23 January 2023 10:51 by user phoronix.
Clear Linux: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Clear Linux OS 38100, Kernel: 6.1.7-1247.native (x86_64), Display Server: X Server 1.21.1.6, Compiler: GCC 12.2.1 20230112 releases/gcc-12.2.0-345-gc142b30b3a + Clang 15.0.6 + LLVM 15.0.6, File-System: ext4, Screen Resolution: 640x480
Kernel Notes: Transparent Huge Pages: alwaysEnvironment Notes: FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop -fvisibility-inlines-hidden -Wl,--enable-new-dtags -std=gnu++17" FCFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z,now -Wl,-z,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mrelax-cmpxchg-loop" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx""Compiler Notes: --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-gnu-indirect-function --enable-host-shared --enable-languages=c,c++,fortran,go,jit --enable-ld=default --enable-libstdcxx-pch --enable-linux-futex --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=x86-64-v3 --with-gcc-major-version-only --with-glibc-version=2.35 --with-gnu-ld --with-isl --with-pic --with-ppl=yes --with-tune=sapphirerapids --with-zstdProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 18.0.2-internal+0-adhoc.mockbuild.corretto-18-18.0.2.9.1)Python Notes: Python 3.11.0Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 26 January 2023 01:38 by user phoronix.
Ubuntu 22.04.1 LTS: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 22.04, Kernel: 5.15.0-58-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1600x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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 (EPP: balance_performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 28 January 2023 19:46 by user phoronix.
Ubuntu 22.04.1 LTS: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 22.04, Kernel: 5.15.0-58-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1600x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 2 February 2023 11:06 by user phoronix.
Ubuntu 22.04.1 LTS - perf: Xeon 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud S6Q-MB-MPS (3A10.uh BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007 + 960GB INTEL SSDSC2KG96, Graphics: ASPEED, Monitor: VGA HDMI, Network: 4 x Intel E810-C for QSFP + 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 22.04, Kernel: 5.15.0-58-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1600x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b0000c0Java Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 29 January 2023 13:44 by user phoronix.
Ubuntu 22.04.1 LTS - perf: EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB SAMSUNG MZWLJ1T9HBJR-00007, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 22.04, Kernel: 5.15.0-58-generic (x86_64), Desktop: GNOME Shell 42.5, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.3.0, File-System: ext4, Screen Resolution: 1600x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/debian/tmp-gcn/usr --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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu222.04)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 31 January 2023 05:09 by user phoronix.