AMD EPYC 9005 Turin vs. NVIDIA GH200 Grace CPU Performance Benchmarks

Benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2411074-NE-MERGE254331
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
NVIDIA GH200 Grace CPU
October 28
  3 Hours, 34 Minutes
EPYC 9575F
October 02
  3 Hours, 20 Minutes
EPYC 9655
October 24
  3 Hours, 14 Minutes
EPYC 9755
September 26
  3 Hours, 14 Minutes
Invert Behavior (Only Show Selected Data)
  3 Hours, 20 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

EPYC 9755

Processor: AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

EPYC 9575F

Changed Processor to AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads).

EPYC 9655

Changed Processor to AMD EPYC 9655 96-Core @ 2.60GHz (96 Cores / 192 Threads).

NVIDIA GH200 Grace CPU

Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550

OS: Ubuntu 24.04, Kernel: 6.8.0-47-generic-64k (aarch64), Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.6.65, Compiler: GCC 13.2.0 + CUDA 11.8, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v
Processor Notes: Scaling Governor: cppc_cpufreq performance (Boost: Disabled)
Python Notes: Python 3.12.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC 9005 Turin vs. NVIDIA GH200 Grace CPU Performance BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionDisplay DriverOpenCLEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPUAMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads)AMD VOLCANO (RVOT1000D BIOS)AMD Device 153a12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC2 x 1920GB KIOXIA KCD8XPUG1T92ASPEEDBroadcom NetXtreme BCM5720 PCIeUbuntu 24.046.10.0-phx (x86_64)GCC 13.2.0ext41920x1200AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads)AMD EPYC 9655 96-Core @ 2.60GHz (96 Cores / 192 Threads)ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores)Pegatron JIMBO P4352 (00022432 BIOS)1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC11000GB CT1000T700SSD3NVIDIA GH200 144G HBM3e 143GB2 x Intel X5506.8.0-47-generic-64k (aarch64)NVIDIAOpenCL 3.0 CUDA 12.6.65GCC 13.2.0 + CUDA 11.8OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- EPYC 9755: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 - EPYC 9575F: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 - EPYC 9655: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 - NVIDIA GH200 Grace CPU: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v Processor Details- EPYC 9755: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110- EPYC 9575F: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110- EPYC 9655: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110- NVIDIA GH200 Grace CPU: Scaling Governor: cppc_cpufreq performance (Boost: Disabled)Java Details- EPYC 9755, EPYC 9575F, EPYC 9655: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Details- EPYC 9755: Python 3.12.2- EPYC 9575F: Python 3.12.2- EPYC 9655: Python 3.12.2- NVIDIA GH200 Grace CPU: Python 3.12.6Security Details- EPYC 9755: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9575F: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 9655: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - NVIDIA GH200 Grace CPU: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPULogarithmic Result OverviewPhoronix Test SuiteminiBUDEOpenSSLXmrigMemcachedJohn The RipperGROMACSStockfishCoremarkASTC Encoder7-Zip CompressionOpenFOAMLiquid-DSPTimed Node.js CompilationParallel BZIP2 CompressionQuantLibPrimesieveSpeedbRocksDBPennantHelsingAlgebraic Multi-Grid BenchmarkNumpy BenchmarkClickHouseTimed Gem5 CompilationGraphicsMagickLAMMPS Molecular Dynamics SimulatorXcompact3d Incompact3dQMCPACKNWChem

EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPULogarithmic Per Watt Result OverviewPhoronix Test SuiteminiBUDEOpenSSLGROMACSClickHouseNumpy BenchmarkStockfishLAMMPS Molecular Dynamics SimulatorMemcachedASTC EncoderGraphicsMagickSpeedbXmrigAlgebraic Multi-Grid BenchmarkCoremark7-Zip CompressionJohn The RipperRocksDBLiquid-DSPQuantLibP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

AMD EPYC 9005 Turin vs. NVIDIA GH200 Grace CPU Performance Benchmarksopenssl: ChaCha20minibude: OpenMP - BM2minibude: OpenMP - BM2memcached: 1:100john-the-ripper: bcryptjohn-the-ripper: Blowfishgromacs: MPI CPU - water_GMX50_bareopenssl: AES-256-GCMcoremark: CoreMark Size 666 - Iterations Per Secondastcenc: Very Thoroughastcenc: Exhaustiveastcenc: Thoroughopenfoam: drivaerFastback, Medium Mesh Size - Execution Timecompress-7zip: Compression Ratingcompress-7zip: Decompression Ratingliquid-dsp: 256 - 256 - 32build-nodejs: Time To Compileopenfoam: drivaerFastback, Small Mesh Size - Execution Timecompress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressionquantlib: Multi-Threadedprimesieve: 1e13primesieve: 1e12speedb: Rand Readrocksdb: Rand Readhelsing: 14 digitgraphics-magick: Sharpenamg: graphics-magick: Noise-Gaussianlammps: Rhodopsin Proteinnumpy: clickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, Third Rungraphics-magick: Enhancedclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachebuild-gem5: Time To Compilelammps: 20k Atomsincompact3d: X3D-benchmarking input.i3dqmcpack: Li2_STO_aenwchem: C240 Buckyballstockfish: Chess Benchmarkxmrig: GhostRider - 1Mpennant: sedovbigpennant: leblancbigspeedb: Read While WritingEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU11863592944509654.576386.18313316660.1032300032301022.72918377658507476042366.34304715.71959.6576110.0383160.373789081598467368494733333109.56120.5970890.934896465436.817.9681.55382210282878689658043.057403317708200031355.791795.83729.56724.64455698.12128.13267.776199.84458979.0201326.230734392319873.04.3936062.761260186878977330602860536101.793244.07213808558.4219907819895414.65111936992449903884226.12849710.11976.203572.3773233.11516552415270375265866667133.85725.604241.263408297665.125.3972.12352667179250573352561.827301319761125029142.850962.28809.27809.87336779.31130.79954.786217.38342372.9331225.718213596711601.96.2211083.238866107832819054096342136705.147268.20612513777.6923773923782317.63213445994030874550652.09896411.57577.105381.6844195.147567628916266006327600000118.69824.0717521.131325341991.724.2152.04260776965057721537459.286320307673966728445.222870.03755.69763.39364740.48126.33356.103201.84742282.2111334.121918954314312.35.4787083.136517150039651492551695431366.39554.6563049705.5474749747566.0025156805063102396678.9962526.58854.066046.4120362.267124366004246434502400000202.93737.3738061.682797261141.531.4642.66756902111156833946356.972428225645466739759.841699.30594.01596.49369581.59166.09758.143240.28580269.6091214.7981468584015.56.4303044.47377910241042OpenBenchmarking.org

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU300000M600000M900000M1200000M1500000MSE +/- 507390352.95, N = 3SE +/- 24295011.71, N = 3SE +/- 211781187.22, N = 3SE +/- 3236084.95, N = 31186359294450733060286053905409634213149255169543-m64-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: ChaCha20EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU600M1200M1800M2400M3000M2532659749.391908650939.882590512735.18768573496.68
MinAvgMaxEPYC 975545.0468.4501.0EPYC 9575F38.6384.1401.2EPYC 965542.6349.5368.4NVIDIA GH200 Grace CPU43.4194.2217.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor130260390520650

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.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2K4K6K8K10KSE +/- 76.86, N = 4SE +/- 15.38, N = 3SE +/- 42.42, N = 3SE +/- 0.49, N = 39654.586101.796705.151366.40-march=native-march=native-march=native1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU80160240320400SE +/- 3.07, N = 4SE +/- 0.62, N = 3SE +/- 1.70, N = 3SE +/- 0.02, N = 3386.18244.07268.2154.66-march=native-march=native-march=native-mcpu=native1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.24460.48920.73380.97841.2231.0870.7630.9480.255
MinAvgMaxEPYC 975544.7355.4459.9EPYC 9575F38.3319.7382.8EPYC 965542.0282.8341.8NVIDIA GH200 Grace CPU41.1214.0244.9OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor120240360480600

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU3M6M9M12M15MSE +/- 136953.60, N = 3SE +/- 30489.72, N = 3SE +/- 51257.47, N = 3SE +/- 22880.28, N = 313316660.1013808558.4212513777.693049705.541. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU10K20K30K40K50K37790.6239869.2747921.2427521.07
MinAvgMaxEPYC 975544.5352.4409.0EPYC 9575F38.3346.3402.0EPYC 965542.2261.1299.8NVIDIA GH200 Grace CPU39.5110.8124.9OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor110220330440550

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU70K140K210K280K350KSE +/- 45.32, N = 3SE +/- 77.93, N = 3SE +/- 23.62, N = 3SE +/- 31.26, N = 332300019907823773974749-m64 -lgmp -lbz2-m64 -lgmp -lbz2-m64 -lgmp -lbz21. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: bcryptEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2004006008001000782.32561.71789.71517.44

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU70K140K210K280K350KSE +/- 53.35, N = 3SE +/- 41.32, N = 3SE +/- 7.33, N = 3SE +/- 19.86, N = 332301019895423782374756-m64 -lgmp -lbz2-m64 -lgmp -lbz2-m64 -lgmp -lbz21. (CC) gcc options: -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2004006008001000778.22562.77792.83508.72
MinAvgMaxXeon 6980P50.8445.3539.8Xeon 6980P - DDR5-640050.4446.6539.6NVIDIA GH200 144G HBM3e41.0144.5164.9EPYC 9575F38.3354.4400.5EPYC 965542.3301.0337.8EPYC 975544.7412.9469.2NVIDIA GH200 Grace CPU42.2146.9165.2OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor140280420560700

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU510152025SE +/- 0.035, N = 3SE +/- 0.053, N = 3SE +/- 0.014, N = 3SE +/- 0.005, N = 322.72914.65117.6326.002-O3 -lm-O3 -lm-O3 -lm1. (CXX) g++ options:
OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.01490.02980.04470.05960.07450.0650.0460.0660.028
MinAvgMaxEPYC 975544.6349.2487.2EPYC 9575F38.3315.2400.1EPYC 965542.2266.4347.6NVIDIA GH200 Grace CPU40.8212.1289.0OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2024CPU Power Consumption Monitor130260390520650

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU400000M800000M1200000M1600000M2000000MSE +/- 2482404044.78, N = 3SE +/- 947677989.11, N = 3SE +/- 243566219.34, N = 3SE +/- 82190365.25, N = 3183776585074711936992449901344599403087515680506310-m64-m64-m641. (CC) gcc options: -pthread -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU900M1800M2700M3600M4500M4339501704.863325699800.964358545440.701809281985.06
MinAvgMaxEPYC 975544.7423.5443.3EPYC 9575F38.4358.9382.8EPYC 965542.3308.5324.7NVIDIA GH200 Grace CPU43.5285.0293.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor120240360480600

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU1.3M2.6M3.9M5.2M6.5MSE +/- 10789.95, N = 3SE +/- 4584.67, N = 3SE +/- 8964.82, N = 3SE +/- 24238.24, N = 36042366.343884226.134550652.102396679.001. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec Per Watt, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU4K8K12K16K20K14585.7412356.0814303.0320070.84
MinAvgMaxEPYC 975544.7414.3479.8EPYC 9575F38.0314.4399.6EPYC 965541.8318.2348.1NVIDIA GH200 Grace CPU38.8119.4159.8OpenBenchmarking.orgWatts, Fewer Is BetterCoremark 1.0CPU Power Consumption Monitor120240360480600

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU48121620SE +/- 0.0025, N = 3SE +/- 0.0104, N = 3SE +/- 0.0010, N = 3SE +/- 0.0008, N = 315.719510.119711.57576.58851. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: Very ThoroughEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.01130.02260.03390.04520.05650.0500.0320.0450.030
MinAvgMaxEPYC 975544.5317.5448.4EPYC 9575F38.4314.2390.3EPYC 965542.4254.7323.1NVIDIA GH200 Grace CPU39.8218.7261.2OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU3691215SE +/- 0.0004, N = 3SE +/- 0.0055, N = 3SE +/- 0.0012, N = 3SE +/- 0.0036, N = 39.65766.20357.10534.06601. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ExhaustiveEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.00680.01360.02040.02720.0340.0300.0200.0280.018
MinAvgMaxEPYC 975544.7318.6450.4EPYC 9575F38.4312.4391.4EPYC 965542.6256.3324.5NVIDIA GH200 Grace CPU42.1223.2267.3OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU20406080100SE +/- 0.02, N = 6SE +/- 0.06, N = 5SE +/- 0.01, N = 5SE +/- 0.06, N = 4110.0472.3881.6846.411. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ThoroughEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.12170.24340.36510.48680.60850.5410.3290.4580.286
MinAvgMaxEPYC 975544.5203.3437.2EPYC 9575F38.2219.9386.4EPYC 965542.2178.3319.1NVIDIA GH200 Grace CPU39.1162.3263.1OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor110220330440550

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU80160240320400160.37233.12195.15362.27-m64 -lfiniteVolume -lmeshTools -lparallel -lregionModels-m64 -lfiniteVolume -lmeshTools -lparallel -lregionModels-m64 -lfiniteVolume -lmeshTools -lparallel -lregionModels-mcpu=native -lfoamToVTK -ldynamicMesh -lfileFormats1. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 975544.6450.2489.9EPYC 9575F38.2388.3399.8EPYC 965542.3331.2360.0NVIDIA GH200 Grace CPU41.1200.9291.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor130260390520650

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU200K400K600K800K1000KSE +/- 3530.77, N = 3SE +/- 4011.15, N = 3SE +/- 660.09, N = 3SE +/- 652.77, N = 39081596552417628914366001. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU200K400K600K800K1000KSE +/- 276.36, N = 3SE +/- 344.02, N = 3SE +/- 257.58, N = 3SE +/- 414.91, N = 38467365270376266004246431. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU60012001800240030002269.161634.382211.882612.52
MinAvgMaxEPYC 975544.7373.2482.8EPYC 9575F38.4322.5400.8EPYC 965542.5283.3363.2NVIDIA GH200 Grace CPU42.0162.5246.0OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption Monitor120240360480600

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 32EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2000M4000M6000M8000M10000MSE +/- 14339494.80, N = 3SE +/- 6072982.06, N = 3SE +/- 6065476.07, N = 3SE +/- 3002221.40, N = 384947333335265866667632760000045024000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 32EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU4M8M12M16M20M20115931.6314781256.8820685459.0517535441.66
MinAvgMaxEPYC 975545.2422.3487.6EPYC 9575F38.4356.3401.0EPYC 965542.5305.9344.2NVIDIA GH200 Grace CPU41.2256.8292.1OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor130260390520650

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 21.7.2Time To CompileEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU4080120160200SE +/- 0.21, N = 3SE +/- 0.26, N = 3SE +/- 0.12, N = 3SE +/- 0.15, N = 3109.56133.86118.70202.94
MinAvgMaxEPYC 975544.5304.2485.2EPYC 9575F38.6313.9401.2EPYC 965542.1265.8361.5NVIDIA GH200 Grace CPU39.2181.0279.3OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 21.7.2CPU Power Consumption Monitor120240360480600

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU91827364520.6025.6024.0737.37-m64 -lfiniteVolume -lmeshTools -lparallel -lregionModels-m64 -lfiniteVolume -lmeshTools -lparallel -lregionModels-m64 -lfiniteVolume -lmeshTools -lparallel -lregionModels-mcpu=native -lfoamToVTK -ldynamicMesh -lfileFormats1. (CXX) g++ options: -std=c++14 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 975544.4396.4492.6EPYC 9575F38.8346.4399.6EPYC 965542.3304.0363.0NVIDIA GH200 Grace CPU41.1200.0287.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor130260390520650

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.37860.75721.13581.51441.893SE +/- 0.010948, N = 15SE +/- 0.009364, N = 15SE +/- 0.014837, N = 15SE +/- 0.004252, N = 150.9348961.2634081.1313251.6827971. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
MinAvgMaxEPYC 975544.597.5319.0EPYC 9575F38.2104.3361.5EPYC 965542.489.6271.2NVIDIA GH200 Grace CPU40.068.7207.5OpenBenchmarking.orgWatts, Fewer Is BetterParallel BZIP2 Compression 1.1.13CPU Power Consumption Monitor100200300400500

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU100K200K300K400K500KSE +/- 401.79, N = 3SE +/- 661.19, N = 3SE +/- 414.37, N = 3SE +/- 316.93, N = 3465436.8297665.1341991.7261141.51. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU300600900120015001146.37897.441136.471209.80
MinAvgMaxEPYC 975544.4406.0483.0EPYC 9575F38.5331.7399.4EPYC 965541.9300.9345.9NVIDIA GH200 Grace CPU41.0215.9290.4OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor120240360480600

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e13EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU714212835SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 317.9725.4024.2231.461. (CXX) g++ options: -O3
MinAvgMaxEPYC 975544.6342.5459.6EPYC 9575F38.3321.0393.1EPYC 965542.2267.8344.1NVIDIA GH200 Grace CPU40.9233.0271.7OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 12.1CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 12.1Length: 1e12EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.60011.20021.80032.40043.0005SE +/- 0.004, N = 12SE +/- 0.003, N = 11SE +/- 0.004, N = 11SE +/- 0.003, N = 101.5532.1232.0422.6671. (CXX) g++ options: -O3
MinAvgMaxEPYC 975544.7147.2431.8EPYC 9575F38.5146.3375.7EPYC 965542.2130.2315.1NVIDIA GH200 Grace CPU41.8111.4254.2OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 12.1CPU Power Consumption Monitor110220330440550

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU200M400M600M800M1000MSE +/- 707549.54, N = 3SE +/- 755684.49, N = 3SE +/- 696066.18, N = 3SE +/- 126199.44, N = 3822102828526671792607769650569021111-lpthread-lpthread-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random ReadEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU500K1000K1500K2000K2500K1969975.351520207.331998985.072132224.78
MinAvgMaxEPYC 975545.3417.3445.7EPYC 9575F38.3346.4371.3EPYC 965542.3304.0324.6NVIDIA GH200 Grace CPU42.0266.9286.5OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor120240360480600

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU200M400M600M800M1000MSE +/- 5260460.78, N = 3SE +/- 1563552.18, N = 3SE +/- 4322874.61, N = 3SE +/- 143829.35, N = 3786896580505733525577215374568339463-lpthread-lpthread-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Random ReadEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU500K1000K1500K2000K2500K1894471.541462898.911918650.382103254.00
MinAvgMaxEPYC 975544.5415.4446.2EPYC 9575F38.3345.7371.1EPYC 965542.4300.8323.1NVIDIA GH200 Grace CPU40.1270.2291.0OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor120240360480600

Helsing

Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHelsing 1.0-betaDigit Range: 14 digitEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU1428425670SE +/- 0.13, N = 3SE +/- 0.23, N = 3SE +/- 0.26, N = 3SE +/- 0.02, N = 343.0661.8359.2956.971. (CC) gcc options: -O2 -pthread
MinAvgMaxEPYC 975544.9388.8429.7EPYC 9575F38.4346.7373.1EPYC 965542.7287.0311.4NVIDIA GH200 Grace CPU40.6266.7291.3OpenBenchmarking.orgWatts, Fewer Is BetterHelsing 1.0-betaCPU Power Consumption Monitor110220330440550

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SharpenEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU90180270360450SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3403301320428-lfreetype -lbz2-lfreetype -lbz2-lfreetype -lbz21. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: SharpenEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.360.721.081.441.81.1700.9041.1881.600
MinAvgMaxEPYC 975545.0344.3371.9EPYC 9575F38.7333.1356.2EPYC 965542.4269.3287.7NVIDIA GH200 Grace CPU42.8267.5300.5OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor100200300400500

Algebraic Multi-Grid Benchmark

AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU700M1400M2100M2800M3500MSE +/- 6342005.91, N = 3SE +/- 7735064.17, N = 4SE +/- 4068843.09, N = 3SE +/- 3694072.61, N = 331770820003197611250307673966722564546671. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU3M6M9M12M15M9501967.5510869334.8311562385.4015435851.48
MinAvgMaxEPYC 975544.4334.4438.6EPYC 9575F38.3294.2401.4EPYC 965541.9266.1338.1NVIDIA GH200 Grace CPU39.8146.2260.2OpenBenchmarking.orgWatts, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2CPU Power Consumption Monitor120240360480600

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU90180270360450SE +/- 0.58, N = 3SE +/- 1.00, N = 3SE +/- 2.08, N = 3SE +/- 0.00, N = 3313291284397-lfreetype -lbz2-lfreetype -lbz2-lfreetype -lbz21. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.53661.07321.60982.14642.6831.5051.2951.5642.385
MinAvgMaxEPYC 975544.7208.0234.1EPYC 9575F38.4224.7243.8EPYC 965542.7181.6199.6NVIDIA GH200 Grace CPU41.9166.4283.3OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor70140210280350

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU1326395265SE +/- 0.31, N = 10SE +/- 0.16, N = 11SE +/- 0.32, N = 15SE +/- 0.13, N = 1155.7942.8545.2259.841. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.21760.43520.65280.87041.0880.4460.4620.4440.967
MinAvgMaxEPYC 975544.5125.0352.9EPYC 9575F38.192.8302.5EPYC 965542.0101.8272.7NVIDIA GH200 Grace CPU39.961.9280.4OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption Monitor100200300400500

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2004006008001000SE +/- 1.03, N = 3SE +/- 3.50, N = 3SE +/- 0.88, N = 3SE +/- 1.78, N = 3795.83962.28870.03699.30
OpenBenchmarking.orgScore Per Watt, More Is BetterNumpy BenchmarkEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU481216208.60310.2919.73916.277
MinAvgMaxEPYC 975544.492.599.7EPYC 9575F38.193.5100.9EPYC 965542.189.396.9NVIDIA GH200 Grace CPU38.743.047.7OpenBenchmarking.orgWatts, Fewer Is BetterNumpy BenchmarkCPU Power Consumption Monitor20406080100

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.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2004006008001000SE +/- 5.27, N = 3SE +/- 3.75, N = 3SE +/- 5.05, N = 3SE +/- 2.22, N = 3729.56809.27755.69594.01MIN: 81.63 / MAX: 7500MIN: 65.65 / MAX: 8571.43MIN: 69.93 / MAX: 7500MIN: 59.29 / MAX: 7500

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2004006008001000SE +/- 4.70, N = 3SE +/- 1.25, N = 3SE +/- 0.75, N = 3SE +/- 2.50, N = 3724.64809.87763.39596.49MIN: 85.11 / MAX: 6666.67MIN: 65.43 / MAX: 10000MIN: 69.36 / MAX: 8571.43MIN: 59.29 / MAX: 7500
OpenBenchmarking.orgQueries Per Minute, Geo Mean Per Watt, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2468104.4314.1814.6157.980
MinAvgMaxEPYC 975544.4163.5407.0EPYC 9575F38.3193.7368.0EPYC 965541.9165.4302.9NVIDIA GH200 Grace CPU40.074.7282.8OpenBenchmarking.orgWatts, Fewer Is BetterClickHouse 22.12.3.5CPU Power Consumption Monitor110220330440550

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU100200300400500SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3455336364369-lfreetype -lbz2-lfreetype -lbz2-lfreetype -lbz21. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lz -lm -lpthread -lgomp
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.3470.6941.0411.3881.7351.4050.9861.4211.542
MinAvgMaxEPYC 975544.7323.9350.4EPYC 9575F38.3340.8367.5EPYC 965542.4256.1275.5NVIDIA GH200 Grace CPU40.7239.3262.5OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor100200300400500

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.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU2004006008001000SE +/- 6.12, N = 3SE +/- 3.67, N = 3SE +/- 1.08, N = 3SE +/- 2.14, N = 3698.12779.31740.48581.59MIN: 80.86 / MAX: 6666.67MIN: 66.01 / MAX: 7500MIN: 68.57 / MAX: 8571.43MIN: 58.94 / MAX: 6666.67

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU4080120160200SE +/- 1.52, N = 3SE +/- 0.56, N = 3SE +/- 1.17, N = 3SE +/- 0.26, N = 3128.13130.80126.33166.10
MinAvgMaxEPYC 975544.4195.4485.4EPYC 9575F38.5211.8401.3EPYC 965542.1176.5363.1NVIDIA GH200 Grace CPU39.4118.8239.4OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 23.0.1CPU Power Consumption Monitor130260390520650

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU1530456075SE +/- 0.06, N = 3SE +/- 0.37, N = 3SE +/- 0.52, N = 3SE +/- 0.14, N = 367.7854.7956.1058.141. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU0.04770.09540.14310.19080.23850.1470.1410.1680.212
MinAvgMaxEPYC 975544.3461.9488.1EPYC 9575F38.4388.8399.6EPYC 965542.2334.9355.5NVIDIA GH200 Grace CPU40.1274.7292.0OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption Monitor130260390520650

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU50100150200250SE +/- 0.78, N = 3SE +/- 1.26, N = 3SE +/- 0.55, N = 3SE +/- 0.29, N = 3199.84217.38201.85240.291. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMaxEPYC 975544.9401.7443.9EPYC 9575F38.2389.8399.8EPYC 965542.3324.2343.2NVIDIA GH200 Grace CPU42.2172.9253.2OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor120240360480600

QMCPACK

QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. QMCPACK is an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids. QMCPACK is supported by the U.S. Department of Energy. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.17.1Input: Li2_STO_aeEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU20406080100SE +/- 0.27, N = 3SE +/- 0.39, N = 3SE +/- 0.22, N = 3SE +/- 0.31, N = 379.0272.9382.2169.61-march=native-march=native-march=native-mcpu=native1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -O3 -lm -ldl
MinAvgMaxEPYC 975544.9441.8480.5EPYC 9575F38.7376.4399.8EPYC 965542.8322.1343.9NVIDIA GH200 Grace CPU41.5268.3298.1OpenBenchmarking.orgWatts, Fewer Is BetterQMCPACK 3.17.1CPU Power Consumption Monitor120240360480600

NWChem

NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 BuckyballEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU300600900120015001326.21225.71334.11214.7-m64-m64-m641. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
OpenBenchmarking.orgWatts, Fewer Is BetterNWChem 7.0.2CPU Power Consumption MonitorEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU90180270360450Min: 44.44 / Avg: 477.37 / Max: 499.23Min: 38.3 / Avg: 392.8 / Max: 400.06Min: 42.34 / Avg: 346.39 / Max: 369.48Min: 41.49 / Avg: 226.74 / Max: 281.44

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU90180270360450Min: 44.19 / Avg: 324.1 / Max: 500.98Min: 19.17 / Avg: 313.09 / Max: 403.08Min: 41.04 / Avg: 253.26 / Max: 371.62Min: 38.42 / Avg: 170.19 / Max: 300.47

Stockfish

MinAvgMaxEPYC 975544.8440.6487.2EPYC 9575F38.7371.1401.2EPYC 965542.3328.0363.7NVIDIA GH200 Grace CPU42.7261.4290.6OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 16.1Chess BenchmarkEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU150K300K450K600K750K697627.07490782.75668223.51375426.89

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU70M140M210M280M350MSE +/- 4338134.07, N = 15SE +/- 2577463.33, N = 15SE +/- 3587851.54, N = 15SE +/- 1172057.21, N = 1530734392318213596721918954398146858-m64 -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2-m64 -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2-m64 -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi21. (CXX) g++ options: -lgcov -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -flto -flto-partition=one -flto=jobserver
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 16.1Chess BenchmarkEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU150K300K450K600K750K697627.07490782.75668223.51375426.89
MinAvgMaxEPYC 975544.8440.6487.2EPYC 9575F38.7371.1401.2EPYC 965542.3328.0363.7NVIDIA GH200 Grace CPU42.7261.4290.6OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1CPU Power Consumption Monitor130260390520650

Xmrig

MinAvgMaxEPYC 975544.9425.0482.5EPYC 9575F38.2380.2401.2EPYC 965542.0321.6347.4NVIDIA GH200 Grace CPU41.3140.0146.7OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU112233445546.7730.5244.5028.69

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU4K8K12K16K20KSE +/- 912.79, N = 15SE +/- 508.75, N = 15SE +/- 672.73, N = 15SE +/- 0.17, N = 319873.011601.914312.34015.5-maes-maes-maes1. (CXX) g++ options: -fexceptions -fno-rtti -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU112233445546.7730.5244.5028.69
MinAvgMaxEPYC 975544.9425.0482.5EPYC 9575F38.2380.2401.2EPYC 965542.0321.6347.4NVIDIA GH200 Grace CPU41.3140.0146.7OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor120240360480600

Pennant

MinAvgMaxEPYC 975544.5248.9471.5EPYC 9575F38.2248.3399.7EPYC 965542.5209.0339.7NVIDIA GH200 Grace CPU41.5150.9252.9OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU246810SE +/- 0.073388, N = 15SE +/- 0.034501, N = 6SE +/- 0.054129, N = 15SE +/- 0.012489, N = 64.3936066.2211085.4787086.4303041. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxEPYC 975544.5248.9471.5EPYC 9575F38.2248.3399.7EPYC 965542.5209.0339.7NVIDIA GH200 Grace CPU41.5150.9252.9OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

MinAvgMaxEPYC 975544.6210.5475.6EPYC 9575F38.2195.5397.8EPYC 965542.5171.4339.9NVIDIA GH200 Grace CPU41.7140.4265.6OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU1.00662.01323.01984.02645.033SE +/- 0.045208, N = 15SE +/- 0.077441, N = 15SE +/- 0.087065, N = 15SE +/- 0.007724, N = 72.7612603.2388663.1365174.4737791. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxEPYC 975544.6210.5475.6EPYC 9575F38.2195.5397.8EPYC 965542.5171.4339.9NVIDIA GH200 Grace CPU41.7140.4265.6OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

Speedb

MinAvgMaxEPYC 975544.6398.2497.6EPYC 9575F38.5375.8400.8EPYC 965542.3313.0351.7NVIDIA GH200 Grace CPU43.4181.9215.8OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU12K24K36K48K60K46936.4428692.8247929.3356303.84

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU4M8M12M16M20MSE +/- 433421.14, N = 12SE +/- 91725.44, N = 15SE +/- 135475.45, N = 3SE +/- 87939.63, N = 1518687897107832811500396510241042-lpthread-lpthread-lpthread1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 9755EPYC 9575FEPYC 9655NVIDIA GH200 Grace CPU12K24K36K48K60K46936.4428692.8247929.3356303.84
MinAvgMaxEPYC 975544.6398.2497.6EPYC 9575F38.5375.8400.8EPYC 965542.3313.0351.7NVIDIA GH200 Grace CPU43.4181.9215.8OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor130260390520650

EPYC 9755

Processor: AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 September 2024 15:49 by user phoronix.

EPYC 9575F

Processor: AMD EPYC 9575F 64-Core @ 3.30GHz (64 Cores / 128 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 2 October 2024 15:16 by user phoronix.

EPYC 9655

Processor: AMD EPYC 9655 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/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-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 Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 24 October 2024 20:58 by user phoronix.

NVIDIA GH200 Grace CPU

Processor: ARMv8 Neoverse-V2 @ 3.47GHz (72 Cores), Motherboard: Pegatron JIMBO P4352 (00022432 BIOS), Memory: 1 x 480GB LPDDR5-6400MT/s NVIDIA 699-2G530-0236-RC1, Disk: 1000GB CT1000T700SSD3, Graphics: NVIDIA GH200 144G HBM3e 143GB, Network: 2 x Intel X550

OS: Ubuntu 24.04, Kernel: 6.8.0-47-generic-64k (aarch64), Display Driver: NVIDIA, OpenCL: OpenCL 3.0 CUDA 12.6.65, Compiler: GCC 13.2.0 + CUDA 11.8, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-dIwDw0/gcc-13-13.2.0/debian/tmp-nvptx/usr --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto --without-cuda-driver -v
Processor Notes: Scaling Governor: cppc_cpufreq performance (Boost: Disabled)
Python Notes: Python 3.12.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 28 October 2024 17:33 by user x.