AMD EPYC Milan-X Mid-2022 Refresh Performance Benchmarks

AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 22.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2207022-NE-AMDEPYCMI39
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

Limit displaying results to tests within:

AV1 3 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 4 Tests
C++ Boost Tests 3 Tests
Chess Test Suite 4 Tests
Timed Code Compilation 8 Tests
C/C++ Compiler Tests 21 Tests
CPU Massive 33 Tests
Creator Workloads 28 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 4 Tests
Database Test Suite 6 Tests
Encoding 7 Tests
Fortran Tests 7 Tests
Game Development 8 Tests
Go Language Tests 2 Tests
HPC - High Performance Computing 25 Tests
Imaging 4 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 4 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Linear Algebra 2 Tests
Machine Learning 4 Tests
Molecular Dynamics 9 Tests
MPI Benchmarks 9 Tests
Multi-Core 48 Tests
NVIDIA GPU Compute 5 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 17 Tests
Programmer / Developer System Benchmarks 11 Tests
Python 2 Tests
Raytracing 6 Tests
Renderers 8 Tests
Scientific Computing 13 Tests
Server 9 Tests
Server CPU Tests 23 Tests
Single-Threaded 3 Tests
Texture Compression 4 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 5 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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

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
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 7773X 2P
June 29 2022
  1 Day, 10 Hours, 44 Minutes
EPYC 7773X
July 01 2022
  1 Day, 7 Hours, 18 Minutes
Invert Hiding All Results Option
  1 Day, 9 Hours, 1 Minute
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 7773X 2P

Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc4daily20220628-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler 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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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-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 Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229
Java Notes: OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)
Python Notes: Python 3.10.4
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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 + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7773X

Changed Processor to AMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads).

Changed Memory to 256GB.

AMD EPYC Milan-X Mid-2022 Refresh Performance BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionEPYC 7773X 2PEPYC 7773X2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RYM1009B BIOS)AMD Starship/Matisse512GB3841GB Micron_9300_MTFDHAL3T8TDPASPEEDVE2282 x Mellanox MT27710Ubuntu 22.045.19.0-051900rc4daily20220628-generic (x86_64)GNOME Shell 42.2X Server 1.21.1.31.2.204GCC 11.2.0ext41920x1080AMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads)256GBOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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-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- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229Java Details- OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)Python Details- Python 3.10.4Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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 + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7773X 2P vs. EPYC 7773X ComparisonPhoronix Test SuiteBaseline+361.5%+361.5%+723%+723%+1084.5%+1084.5%893.7%247.3%246.6%234.5%234.3%230.9%230.9%181%156.7%145.3%143.3%103.1%99.6%97.9%93.7%75.7%69%68.8%65%54.9%54.8%44.1%42.1%42%40.6%39.9%39.6%38.7%37.9%36.2%34.2%32.5%31.9%31.4%28.9%26.5%24.4%23.8%23.2%22.8%22.5%22.2%21.8%16%15.5%14.7%14.4%14%12.7%11.1%9.6%8.6%8.2%5.9%5.8%5%4.5%3.5%3.1%3.1%3.1%2.7%2.6%2.6%2.4%2.4%2%ResizingV.P.M320.6%1000 - 250 - Read Write - Average Latency1000 - 250 - Read Write100 - 250 - Read Write - Average Latency100 - 250 - Read Write1000 - 500 - Read Write - Average Latency1000 - 500 - Read WriteSkeincoin212.3%R.N.N.T - bf16bf16bf16 - CPUM.M.B.S.T - u8s8f32 - CPUSP.C154.6%100 - 500 - Read Write - Average Latency100 - 500 - Read Writed.L.M.S - Execution Time131.2%Q.S.2.P128.4%BT.C122.1%X.b.i.i116.4%T.S.2.O115.8%d.M.M.S - Execution Time115.5%d.S.M.S - Execution Time115.2%1 - 4K - 32 - Path Tracer114.3%Blake-2 S112.6%LBC, LBRY Credits112.6%3 - 4K - 32 - Path Tracer111.5%2 - 4K - 32 - Path Tracer111%conus 2.5km109%MG.C103.4%500i.i.1.C.P.D102.7%Magi102.5%RSA4096101.2%RSA4096100.8%SHA256100.8%Total Time100.2%Throughput100.1%Garlicoin1446%1000Rand Read99.4%CPU99.3%200FT.C97.3%1 - 4K - 16 - Path Tracer97.1%Classroom - CPU-Only97%3 - 4K - 16 - Path Tracer96.8%tConvolve MPI - Gridding96.6%3 - 1080p - 16 - Path Tracer96.4%Basic - CPU96.3%3 - 1080p - 32 - Path Tracer96.2%3 - 4K - 1 - Path Tracer96.2%Exhaustive96.2%256 - 256 - 5796.1%tConvolve MPI - Degridding96%1 - 4K - 1 - Path Tracer96%1 - 1080p - 16 - Path Tracer95.8%1 - 1080p - 32 - Path Tracer95.8%3 - 1080p - 1 - Path Tracer95.4%Pabellon Barcelona - CPU-Only95.3%Total Time - 4.1.R.P.P95.1%1 - 1080p - 1 - Path Tracer94.6%TBB94.4%2 - 4K - 16 - Path Tracer94.4%2 - 1080p - 16 - Path Tracer93.8%2 - 1080p - 32 - Path Tracer93.7%H.C.Ox25x93.3%Barbershop - CPU-Only93%Total Time92.4%2 - 4K - 1 - Path Tracer92%2 - 1080p - 1 - Path Tracer91.6%Large Scene91.4%91.4%Time To Solve91.3%128 - 256 - 5790.7%Fishy Cat - CPU-Only90.1%90.1%BMW27 - CPU-Only90%89.6%EP.D89.4%1.P.N.G89.3%sedovbig89.1%gravity_spheres_volume/dim_512/pathtracer/real_time89.1%Pathtracer - Crown89.1%EP.C88.2%Pathtracer ISPC - Crown86.9%1.H.M.2.D86.6%particle_volume/ao/real_time86.2%particle_volume/scivis/real_time85.7%OpenMP85.6%C++ Tasks85.6%C++ Threads85.2%gravity_spheres_volume/dim_512/ao/real_time83.2%gravity_spheres_volume/dim_512/scivis/real_time82.8%U.4.Z.C.178.1%OpenMP LavaMD76.1%tConvolve OpenMP - GriddingRead While Writing74.8%IS.D74.5%S.F.P.R71.9%Deepcoin70.5%i.i.1.C.P.D69.9%ATPase Simulation - 327,506 Atoms69.2%1000 - 250 - Read Only - Average Latency1000 - 250 - Read Onlyallmodconfig67.3%leblancbig66.4%ArcFace ResNet-100 - CPU - StandardOrange Juice - CPU62%1 - Bosphorus 4K60.4%Bosphorus 4K - Medium59.9%LU.C56.6%100 - 500 - Read Only - Average Latency56.2%100 - 500 - Read Only55.5%512256100 - 250 - Read Only54.4%Carbon Nanotube53.8%100 - 250 - Read Only - Average Latency53.6%MPI CPU - water_GMX50_bare53.6%DLSC - CPU52.4%Sharpen49.6%Ninja48.3%R.R.W.RvklBenchmark ISPC43.1%yolov4 - CPU - Standardsuper-resolution-10 - CPU - StandardRingcointConvolve OpenMP - DegriddingGPT-2 - CPU - StandardTime To Compile38.9%bertsquad-12 - CPU - StandardTrace Time37.9%Speed 6 Realtime - Bosphorus 4KEnhanced36.7%10 - Bosphorus 4K1000tConvolve MT - Degridding34.1%defconfig33.5%RAM / MemoryCG.C32.5%O.SPathtracer ISPC - Asian Dragon31.8%Update RandPathtracer ISPC - Asian Dragon Obj31.2%Bosphorus 4K - Very Fast30%particle_volume/pathtracer/real_timefcn-resnet101-11 - CPU - Standard28.9%Bosphorus 4KWownero - 1M25.8%20k Atoms25.7%WritesHWB Color SpacePathtracer - Asian Dragon23.7%Time To Compile23.2%Speed 9 Realtime - Bosphorus 4KR.C.a.P - CPUSpeed 8 Realtime - Bosphorus 4KMonero - 1M22.2%Speed 10 Realtime - Bosphorus 4K50064 - 256 - 5720.8%RT.hdr_alb_nrm.3840x216019.8%RT.ldr_alb_nrm.3840x216019.6%d.L.M.S - Mesh Time18.9%2618%RTLightmap.hdr.4096x409617.5%2616.3%Eigen16.3%DefaultUnix Makefiles15.9%motorBike - Execution TimePathtracer - Asian Dragon Obj15.2%Speed 4 Two-Pass - Bosphorus 4KSpeed 6 Two-Pass - Bosphorus 4KBLAS14.2%200UASTC 314%Bosphorus 4K - Ultra FastSwirl12.7%C240 Buckyball12.6%Time To Compile12.5%12.1%SP.B11.4%Preset 12 - Bosphorus 4KThorough10.2%Time To Compile10.2%OpenMP CFD Solver10.1%Danish Mood - CPU9.9%d.M.M.S - Mesh Time9.6%Preset 10 - Bosphorus 4KTime To Compile9.5%OpenMP LeukocyteSmall8.4%Myriad-GroestlU.3.Z.C.17.7%d.S.M.S - Mesh Time7.5%1.R.W.A.D.F.R.C.C10, LosslessmotorBike - Mesh TimeGET4.5%6, LosslessTime To Compile4.1%19 - Compression Speed3.9%6Q.1.C.E.5267 - Bosphorus 4KN.2.3.C.F.R1.R.W.A.D.T.RBosphorus 4K2CPU - Numpy - 4194304 - Equation of State26GraphicsMagickBRL-CADPostgreSQL pgbenchPostgreSQL pgbenchPostgreSQL pgbenchPostgreSQL pgbenchPostgreSQL pgbenchPostgreSQL pgbenchCpuminer-OptoneDNNoneDNNNAS Parallel BenchmarksPostgreSQL pgbenchPostgreSQL pgbenchOpenFOAMCpuminer-OptNAS Parallel BenchmarksXcompact3d Incompact3dCpuminer-OptOpenFOAMOpenFOAMOSPRay StudioCpuminer-OptCpuminer-OptOSPRay StudioOSPRay StudioWRFNAS Parallel BenchmarksnginxXcompact3d Incompact3dCpuminer-OptOpenSSLOpenSSLOpenSSLStockfishJava JMHCpuminer-OptnginxFacebook RocksDBSysbenchnginxNAS Parallel BenchmarksOSPRay StudioBlenderOSPRay StudioASKAPOSPRay StudioRELIONOSPRay StudioOSPRay StudioASTC EncoderLiquid-DSPASKAPOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioBlenderC-RayOSPRay StudiotoyBrot Fractal GeneratorOSPRay StudioOSPRay StudioOSPRay StudioASKAPCpuminer-OptBlenderTachyonOSPRay StudioOSPRay Studiorays1benchHigh Performance Conjugate Gradientm-queensLiquid-DSPBlenderAlgebraic Multi-Grid BenchmarkBlenderLULESHNAS Parallel BenchmarksPrimesievePennantOSPRayEmbreeNAS Parallel BenchmarksEmbreeasmFishOSPRayOSPRaytoyBrot Fractal GeneratortoyBrot Fractal GeneratortoyBrot Fractal GeneratorOSPRayOSPRayKTX-Software toktxRodiniaASKAPFacebook RocksDBNAS Parallel BenchmarksACES DGEMMCpuminer-OptXcompact3d Incompact3dNAMDPostgreSQL pgbenchPostgreSQL pgbenchTimed Linux Kernel CompilationPennantONNX RuntimeLuxCoreRenderSVT-HEVCKvazaarNAS Parallel BenchmarksPostgreSQL pgbenchPostgreSQL pgbenchMariaDBMariaDBPostgreSQL pgbenchGPAWPostgreSQL pgbenchGROMACSLuxCoreRenderGraphicsMagickTimed LLVM CompilationFacebook RocksDBOpenVKLONNX RuntimeONNX RuntimeCpuminer-OptASKAPONNX RuntimeTimed Node.js CompilationONNX RuntimePOV-RayAOM AV1GraphicsMagickSVT-HEVCApache HTTP ServerASKAPTimed Linux Kernel CompilationSysbenchNAS Parallel BenchmarksRodiniaEmbreeFacebook RocksDBEmbreeKvazaarOSPRayONNX Runtimex265XmrigLAMMPS Molecular Dynamics SimulatorApache CassandraGraphicsMagickEmbreeTimed MPlayer CompilationAOM AV1LuxCoreRenderAOM AV1XmrigAOM AV1Apache HTTP ServerLiquid-DSPIntel Open Image DenoiseIntel Open Image DenoiseOpenFOAMGraph500Intel Open Image DenoiseGraph500LeelaChessZeroWebP2 Image EncodeTimed LLVM CompilationOpenFOAMEmbreeAOM AV1AOM AV1LeelaChessZeroApache HTTP ServerKTX-Software toktxKvazaarGraphicsMagickNWChemTimed Gem5 CompilationAircrack-ngNAS Parallel BenchmarksSVT-AV1ASTC EncoderTimed ImageMagick CompilationRodiniaLuxCoreRenderOpenFOAMSVT-AV1Timed Mesa CompilationRodiniaminiFECpuminer-OptKTX-Software toktxOpenFOAMClickHouselibavif avifencOpenFOAMRedislibavif avifencTimed Godot Game Engine CompilationZstd Compressionlibavif avifencWebP2 Image EncodeGraph500SVT-HEVCFFTEClickHousex264libavif avifencPyHPC BenchmarksGraph500EPYC 7773X 2PEPYC 7773X

AMD EPYC Milan-X Mid-2022 Refresh Performance Benchmarkswrf: conus 2.5kmopenfoam: drivaerFastback, Large Mesh Size - Execution Timeopenfoam: drivaerFastback, Large Mesh Size - Mesh Timeopenvkl: vklBenchmark ISPCaskap: tConvolve MT - Degriddingaskap: tConvolve MT - Griddingnwchem: C240 Buckyballospray: particle_volume/pathtracer/real_timewebp2: Quality 100, Lossless Compressionpgbench: 1000 - 250 - Read Write - Average Latencypgbench: 1000 - 250 - Read Writepgbench: 1000 - 250 - Read Only - Average Latencypgbench: 1000 - 250 - Read Onlymysqlslap: 256relion: Basic - CPUlczero: BLASonnx: fcn-resnet101-11 - CPU - Standardincompact3d: X3D-benchmarking input.i3dbrl-cad: VGR Performance Metricrodinia: OpenMP HotSpot3Dmysqlslap: 512ospray: particle_volume/scivis/real_timelczero: Eigenpgbench: 100 - 500 - Read Write - Average Latencypgbench: 100 - 500 - Read Writeonnx: GPT-2 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardgraphics-magick: Resizinggraph500: 26graph500: 26graph500: 26graph500: 26hpcg: onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUlammps: 20k Atomsospray: particle_volume/ao/real_timepgbench: 100 - 250 - Read Write - Average Latencypgbench: 100 - 250 - Read Writestockfish: Total Timeonnx: yolov4 - CPU - Standardonnx: super-resolution-10 - CPU - Standardwebp2: Quality 95, Compression Effort 7blender: Barbershop - CPU-Onlyaom-av1: Speed 6 Two-Pass - Bosphorus 4Kpgbench: 1000 - 500 - Read Write - Average Latencypgbench: 1000 - 500 - Read Writenumpy: luxcorerender: Orange Juice - CPUluxcorerender: Danish Mood - CPUluxcorerender: LuxCore Benchmark - CPUbuild-linux-kernel: allmodconfigbuild-llvm: Unix Makefilesrocksdb: Update Randrocksdb: Read While Writingopenssl: SHA256java-jmh: Throughputclickhouse: 100M Rows Web Analytics Dataset, Third Runclickhouse: 100M Rows Web Analytics Dataset, Second Runclickhouse: 100M Rows Web Analytics Dataset, First Run / Cold Cachepgbench: 100 - 250 - Read Only - Average Latencypgbench: 100 - 250 - Read Onlyonnx: bertsquad-12 - CPU - Standardbuild-gem5: Time To Compileospray-studio: 3 - 1080p - 16 - Path Tracerospray-studio: 1 - 1080p - 16 - Path Tracerospray-studio: 2 - 4K - 16 - Path Tracerospray-studio: 2 - 1080p - 16 - Path Tracerospray-studio: 1 - 1080p - 32 - Path Tracerpgbench: 100 - 500 - Read Only - Average Latencypgbench: 100 - 500 - Read Onlyospray-studio: 2 - 1080p - 32 - Path Tracerospray-studio: 3 - 1080p - 32 - Path Traceropenfoam: drivaerFastback, Small Mesh Size - Execution Timeopenfoam: drivaerFastback, Small Mesh Size - Mesh Timeopenfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timecassandra: Writesospray-studio: 3 - 1080p - 1 - Path Tracerospray-studio: 1 - 4K - 16 - Path Tracerasmfish: 1024 Hash Memory, 26 Depthospray-studio: 2 - 1080p - 1 - Path Tracerospray-studio: 1 - 1080p - 1 - Path Tracerospray-studio: 3 - 4K - 1 - Path Tracerapache: 500ospray-studio: 3 - 4K - 32 - Path Tracerospray-studio: 2 - 4K - 1 - Path Tracerospray-studio: 3 - 4K - 16 - Path Tracerospray: gravity_spheres_volume/dim_512/pathtracer/real_timeospray-studio: 1 - 4K - 1 - Path Tracerbuild-llvm: Ninjabuild-nodejs: Time To Compilewebp2: Quality 75, Compression Effort 7aom-av1: Speed 4 Two-Pass - Bosphorus 4Kospray-studio: 2 - 4K - 32 - Path Tracerpyhpc: CPU - Numpy - 4194304 - Isoneutral Mixingospray-studio: 1 - 4K - 32 - Path Tracerospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timeaom-av1: Speed 0 Two-Pass - Bosphorus 4Kapache: 1000cpuminer-opt: Triple SHA-256, Onecoincpuminer-opt: Blake-2 Scpuminer-opt: LBC, LBRY Creditscpuminer-opt: Deepcoinnginx: 1000nginx: 500nginx: 200apache: 200sysbench: CPUx265: Bosphorus 4Kavifenc: 0blender: Pabellon Barcelona - CPU-Onlyluxcorerender: DLSC - CPUrocksdb: Read Rand Write Randgraphics-magick: Noise-Gaussiangraphics-magick: Sharpengraphics-magick: HWB Color Spaceopenssl: RSA4096openssl: RSA4096rocksdb: Rand Readgraphics-magick: Enhancedgraphics-magick: Swirlblender: Classroom - CPU-Onlybuild-linux-kernel: defconfignpb: EP.Dgpaw: Carbon Nanotuberedis: GETtoktx: UASTC 4 + Zstd Compression 19aom-av1: Speed 10 Realtime - Bosphorus 4Ksvt-hevc: 1 - Bosphorus 4Kluxcorerender: Rainbow Colors and Prism - CPUsvt-av1: Preset 4 - Bosphorus 4Kredis: SETrodinia: OpenMP Leukocytecompress-zstd: 19 - Decompression Speedcompress-zstd: 19 - Compression Speedminife: Smallavifenc: 2aom-av1: Speed 8 Realtime - Bosphorus 4Kcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 19, Long Mode - Compression Speedbuild-godot: Time To Compileonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUwebp: Quality 100, Lossless, Highest Compressionopenfoam: motorBike - Execution Timeopenfoam: motorBike - Mesh Timeamg: aom-av1: Speed 9 Realtime - Bosphorus 4Krodinia: OpenMP LavaMDoidn: RTLightmap.hdr.4096x4096kvazaar: Bosphorus 4K - Ultra Fastaskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddingpyhpc: CPU - Numpy - 4194304 - Equation of Stategromacs: MPI CPU - water_GMX50_barecpuminer-opt: Magicpuminer-opt: x25xcpuminer-opt: Ringcoincpuminer-opt: Myriad-Groestlcpuminer-opt: Garlicoincpuminer-opt: Quad SHA-256, Pyritecpuminer-opt: Skeincoinaircrack-ng: blender: Fishy Cat - CPU-Onlynpb: IS.Dx264: Bosphorus 4Ktoybrot: TBBxmrig: Monero - 1Membree: Pathtracer ISPC - Asian Dragonaskap: tConvolve OpenMP - Degriddingaskap: tConvolve OpenMP - Griddingpennant: leblancbigtachyon: Total Timeblender: BMW27 - CPU-Onlyembree: Pathtracer - Asian Dragonnamd: ATPase Simulation - 327,506 Atomskvazaar: Bosphorus 4K - Mediumrodinia: OpenMP Streamclusterxmrig: Wownero - 1Maom-av1: Speed 6 Realtime - Bosphorus 4Kembree: Pathtracer - Asian Dragon Objsvt-hevc: 10 - Bosphorus 4Klulesh: embree: Pathtracer ISPC - Asian Dragon Objsvt-av1: Preset 12 - Bosphorus 4Kliquid-dsp: 256 - 256 - 57liquid-dsp: 128 - 256 - 57liquid-dsp: 64 - 256 - 57oidn: RT.hdr_alb_nrm.3840x2160oidn: RT.ldr_alb_nrm.3840x2160mt-dgemm: Sustained Floating-Point Rateastcenc: Exhaustiveaskap: Hogbom Clean OpenMPbuild-mesa: Time To Compilewebp: Quality 100, Losslessincompact3d: input.i3d 193 Cells Per Directionkvazaar: Bosphorus 4K - Very Fasttoktx: Zstd Compression 19build-imagemagick: Time To Compilesysbench: RAM / Memorypovray: Trace Timesvt-av1: Preset 8 - Bosphorus 4Kc-ray: Total Time - 4K, 16 Rays Per Pixelnpb: BT.Cm-queens: Time To Solvebuild-mplayer: Time To Compileembree: Pathtracer ISPC - Crownnpb: SP.Ctoktx: UASTC 3 + Zstd Compression 19pennant: sedovbigwebp2: Defaultavifenc: 6, Losslessembree: Pathtracer - Crownnpb: LU.Cincompact3d: input.i3d 129 Cells Per Directiondraco: Liondraco: Church Facaderodinia: OpenMP CFD Solveravifenc: 6avifenc: 10, Losslesstoybrot: OpenMPastcenc: Thoroughnpb: FT.Cnpb: SP.Btoybrot: C++ Taskssvt-av1: Preset 10 - Bosphorus 4Ktoybrot: C++ Threadssvt-hevc: 7 - Bosphorus 4Kffte: N=256, 3D Complex FFT Routinenpb: CG.Cnpb: MG.Ctoktx: UASTC 3webp2: Quality 100, Compression Effort 5rays1bench: Large Sceneprimesieve: 1e12 Prime Number Generationetcpak: Multi-Threaded - ETC2npb: EP.Ctoktx: Zstd Compression 9EPYC 7773X 2PEPYC 7773X7433.9895370.47611.0824911138.85535.391996.4149.181551.02910.595236410.355704940436148.3155923259265.204936308865289.97443232.2495589515.777319428884101915839336500031297800062549900059699600037.66346807.6037.38732.61059.489263603200245542924940238.324148.6912.3924.66020277475.5121.818.097.52139.948171.30228051717337506153461007540156410828590.72421.77421.91394.480.0972585661543151.2685262445217942453289150.1942571222907110515170.52105.26169.8104.4421654732817575284279174285278129797855.034154111312078925.7049109992.54995.050112.1656.60359442.0193528715.573116.40260.2186754.44310169672771902923588177487065.3385974.9987686.13117068.34528284.4221.9577.12248.8114.0429872026018816851784848.527099.35524775391431243538.7919.98010096.2137.7562402083.0733.90355.8517.5319.043.7051849652.5443.7473320.7107.524565.641.68341.313308.958.938.07729.763637.64971.0940.64200191600057.0425.2260.9454.3670367.562354.40.89411.0744517.512992.653318.68133732479010370771337547196064.49519.795085.9772.93366543888.393.451313593.111786.83.39373015.397115.5196.35740.2255430.647.47349710.622.1082.0747177.7042133.73482.6563174.2775826033333555293333333488333331.941.9550.5621175.9316417.20017.96618.1529.9588691952.2017.4699.8587808.757.44965.6965.741373690.155.7238.490115.9876228945.277.5275.0940682.9507.533127.3588394724.962.31085810493458305.9103.8945.86741105.3049127926.74152554.573993144.7793844152.60225092.7391202850299.77123826.943.8843.511582.922.4556969.9329459.242.93715534.38412416.89726.691748306.985488.052248192.268549.7263.051819450.2101189985675291.1265188201573.98079473435888.56466917.364650706.43377720123981681157033815500026514600063812800061565500019.68142423.0629.73917.51092.837881101598210654157013238.331286.9114.177.45267097471.9713.467.367.61234.164198.50236867199196717642496641078156370321.981432.79428.41417.810.1491674853753170.172103328717348818785174530.30316536021757520634366.98113.12366114.51269401641346491523353215465412545119227.938787621724092213.59532154137.238131.978112.5587.57758362.014756268.520128.953050.21116446.751437047342271113750747973173749.58174606.51173501.45133507.87265124.9427.7676.49195.339.214305549590589848886927.913493.22770758791047216176.4126.6775329.6558.0672297790.3060.38768.2310.9323.383.7041862390.4740.2833293.9103.522670.940.70150.603316.757.839.64611.595737.63161.5638.72105324600070.2544.4270.8061.2835783.631805.50.8737.2102230.721548.224667.60144671603.52453993428330174912.57837.632913.8874.82712635903.770.929819018.320708.85.64605429.618429.4777.86490.3816919.165.66439506.630.4871.2285242.0422217.30463.0073193.5382970400000291203333327730666671.621.6329.40919411.6387808.11719.67218.25216.923784940.1417.47910.86610345.8210.27565.42111.202168289.2810.94710.46262.066689936.498.1059.6335872.5447.20767.3669251998.614.68347120489558096.5093.7635.54676305.848364849.86136930.607411158.6397121157.29231182.7252669637967.9660883.144.4283.404304.614.6487076.1385025.592.966OpenBenchmarking.org

WRF

WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5kmEPYC 7773X 2PEPYC 7773X3K6K9K12K15K7433.9915534.381. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.orgWatts, Fewer Is BetterWRF 4.2.2CPU Power Consumption MonitorEPYC 7773X50100150200250Min: 34.63 / Avg: 243.49 / Max: 286.97

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 9Input: drivaerFastback, Large Mesh Size - Execution TimeEPYC 7773X 2PEPYC 7773X3K6K9K12K15K5370.4712416.891. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 9CPU Power Consumption MonitorEPYC 7773X50100150200250Min: 33.89 / Avg: 244.95 / Max: 286.71

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Large Mesh Size - Mesh TimeEPYC 7773X 2PEPYC 7773X160320480640800611.08726.691. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ISPCEPYC 7773X 2PEPYC 7773X50100150200250SE +/- 0.33, N = 3SE +/- 0.00, N = 3249174MIN: 24 / MAX: 4546MIN: 19 / MAX: 4370
OpenBenchmarking.orgItems / Sec Per Watt, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ISPCEPYC 7773X 2PEPYC 7773X0.26660.53320.79981.06641.3331.0021.185
OpenBenchmarking.orgWatts, Fewer Is BetterOpenVKL 1.0CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X100200300400500Min: 66.33 / Avg: 248.48 / Max: 573.81Min: 34.31 / Avg: 146.84 / Max: 286.751. EPYC 7773X 2P: Approximate power consumption of 330152 Joules per run.2. EPYC 7773X: Approximate power consumption of 129558 Joules per run.
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.0Benchmark: vklBenchmark ISPCEPYC 7773X 2PEPYC 7773X50100150200250Min: 249 / Avg: 249.33 / Max: 250Min: 174 / Avg: 174 / Max: 174

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 7773X 2PEPYC 7773X2K4K6K8K10KSE +/- 291.26, N = 9SE +/- 1.79, N = 311138.808306.981. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second Per Watt, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 7773X 2PEPYC 7773X153045607549.2367.86
OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X90180270360450Min: 66.34 / Avg: 226.27 / Max: 500.55Min: 34.58 / Avg: 122.41 / Max: 244.081. EPYC 7773X 2P: Approximate power consumption of 117633 Joules per run.2. EPYC 7773X: Approximate power consumption of 33417 Joules per run.
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingEPYC 7773X 2PEPYC 7773X2K4K6K8K10KMin: 10066.7 / Avg: 11138.79 / Max: 12653Min: 8304.28 / Avg: 8306.98 / Max: 8310.361. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingEPYC 7773X 2PEPYC 7773X12002400360048006000SE +/- 44.86, N = 9SE +/- 2.22, N = 35535.395488.051. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingEPYC 7773X 2PEPYC 7773X10002000300040005000Min: 5330.95 / Avg: 5535.39 / Max: 5744.27Min: 5485.4 / Avg: 5488.05 / Max: 5492.471. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 7773X 2PEPYC 7773X50010001500200025001996.42248.01. (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 -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
OpenBenchmarking.orgWatts, Fewer Is BetterNWChem 7.0.2CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X100200300400500Min: 73.41 / Avg: 539.36 / Max: 573.12Min: 34.32 / Avg: 276.98 / Max: 286.99

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/pathtracer/real_timeEPYC 7773X 2PEPYC 7773X4080120160200SE +/- 6.07, N = 9SE +/- 0.69, N = 3149.18192.27
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.10Benchmark: particle_volume/pathtracer/real_timeEPYC 7773X 2PEPYC 7773X0.19730.39460.59190.78920.98650.3220.877
OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.10CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X100200300400500Min: 76.35 / Avg: 463.15 / Max: 574.88Min: 34.59 / Avg: 219.31 / Max: 275.311. EPYC 7773X 2P: Approximate power consumption of 133695 Joules per run.2. EPYC 7773X: Approximate power consumption of 78877 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/pathtracer/real_timeEPYC 7773X 2PEPYC 7773X4080120160200Min: 129.81 / Avg: 149.18 / Max: 174.55Min: 190.97 / Avg: 192.27 / Max: 193.34

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Lossless CompressionEPYC 7773X 2PEPYC 7773X120240360480600SE +/- 0.30, N = 3SE +/- 1.66, N = 3551.03549.731. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
OpenBenchmarking.orgWatts, Fewer Is BetterWebP2 Image Encode 20220422CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X4080120160200Min: 73.81 / Avg: 218.1 / Max: 235.15Min: 33.81 / Avg: 149.8 / Max: 161.971. EPYC 7773X 2P: Approximate power consumption of 120679 Joules per run.2. EPYC 7773X: Approximate power consumption of 82741 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Lossless CompressionEPYC 7773X 2PEPYC 7773X100200300400500Min: 550.45 / Avg: 551.03 / Max: 551.41Min: 546.43 / Avg: 549.73 / Max: 551.771. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.135, N = 12SE +/- 0.018, N = 310.5953.0511. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 14.0CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X80160240320400Min: 75.52 / Avg: 249.68 / Max: 425.1Min: 34.66 / Avg: 169.14 / Max: 268.051. EPYC 7773X 2P: Approximate power consumption of 54637 Joules per run.2. EPYC 7773X: Approximate power consumption of 36422 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X3691215Min: 9.28 / Avg: 10.6 / Max: 11.15Min: 3.03 / Avg: 3.05 / Max: 3.091. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X20K40K60K80K100KSE +/- 329.58, N = 12SE +/- 491.57, N = 323641819451. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X14K28K42K56K70KMin: 22425.63 / Avg: 23641.4 / Max: 26950.7Min: 80966.65 / Avg: 81944.98 / Max: 82518.331. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773X0.07990.15980.23970.31960.3995SE +/- 0.004, N = 12SE +/- 0.001, N = 30.3550.2101. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 14.0CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X100200300400500Min: 75.46 / Avg: 376.06 / Max: 585.49Min: 34.62 / Avg: 190.97 / Max: 287.721. EPYC 7773X 2P: Approximate power consumption of 81793 Joules per run.2. EPYC 7773X: Approximate power consumption of 40677 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773X12345Min: 0.33 / Avg: 0.36 / Max: 0.38Min: 0.21 / Avg: 0.21 / Max: 0.211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773X300K600K900K1200K1500KSE +/- 7420.45, N = 12SE +/- 2502.46, N = 370494011899851. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 250 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773X200K400K600K800K1000KMin: 656687.92 / Avg: 704940.4 / Max: 754698.04Min: 1185393.39 / Avg: 1189984.87 / Max: 1194005.621. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 256EPYC 7773X 2PEPYC 7773X150300450600750SE +/- 5.01, N = 4SE +/- 0.30, N = 34366751. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 10.8.2Clients: 256EPYC 7773X 2PEPYC 7773X1.21372.42743.64114.85486.06851.8915.394
OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 10.8.2CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X4080120160200Min: 73.32 / Avg: 230.57 / Max: 239.21Min: 34.45 / Avg: 125.14 / Max: 132.91. EPYC 7773X 2P: Approximate power consumption of 109350 Joules per run.2. EPYC 7773X: Approximate power consumption of 39378 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 256EPYC 7773X 2PEPYC 7773X120240360480600Min: 422.12 / Avg: 436 / Max: 444.84Min: 674.31 / Avg: 674.92 / Max: 675.221. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl

RELION

RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 3.1.1Test: Basic - Device: CPUEPYC 7773X 2PEPYC 7773X60120180240300SE +/- 1.22, N = 12SE +/- 3.94, N = 3148.32291.131. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -lmpi_cxx -lmpi
OpenBenchmarking.orgWatts, Fewer Is BetterRELION 3.1.1CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X100200300400500Min: 77.05 / Avg: 547.26 / Max: 575.33Min: 35.42 / Avg: 277.9 / Max: 286.861. EPYC 7773X 2P: Approximate power consumption of 82682 Joules per run.2. EPYC 7773X: Approximate power consumption of 81702 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 3.1.1Test: Basic - Device: CPUEPYC 7773X 2PEPYC 7773X50100150200250Min: 146.37 / Avg: 148.32 / Max: 161.63Min: 286.67 / Avg: 291.13 / Max: 298.981. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -lmpi_cxx -lmpi

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.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASEPYC 7773X 2PEPYC 7773X13002600390052006500SE +/- 61.47, N = 3SE +/- 57.25, N = 4592351881. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.28Backend: BLASEPYC 7773X 2PEPYC 7773X61218243018.4023.70
MinAvgMaxEPYC 7773X 2P73.7322.0527.2EPYC 7773X34.6218.9286.5OpenBenchmarking.orgWatts, Fewer Is BetterLeelaChessZero 0.28CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 119660 Joules per run.2. EPYC 7773X: Approximate power consumption of 81257 Joules per run.
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASEPYC 7773X 2PEPYC 7773X10002000300040005000Min: 5855 / Avg: 5923.33 / Max: 6046Min: 5019 / Avg: 5188 / Max: 52731. (CXX) g++ options: -flto -pthread

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X60120180240300SE +/- 5.67, N = 12SE +/- 9.87, N = 92592011. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X0.20810.41620.62430.83241.04050.5480.925
OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.11CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X90180270360450Min: 74.62 / Avg: 472.56 / Max: 501.41Min: 34.59 / Avg: 217.18 / Max: 249.471. EPYC 7773X 2P: Approximate power consumption of 58755 Joules per run.2. EPYC 7773X: Approximate power consumption of 27100 Joules per run.
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X50100150200250Min: 241.5 / Avg: 258.58 / Max: 316Min: 183 / Avg: 200.56 / Max: 274.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

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 7773X 2PEPYC 7773X120240360480600SE +/- 0.88, N = 3SE +/- 0.02, N = 3265.20573.981. (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 7773X 2P73.8499.4545.2EPYC 7773X35.1232.4262.7OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 134510 Joules per run.2. EPYC 7773X: Approximate power consumption of 134700 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dEPYC 7773X 2PEPYC 7773X100200300400500Min: 264.13 / Avg: 265.2 / Max: 266.96Min: 573.94 / Avg: 573.98 / Max: 574.011. (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

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.32.2VGR Performance MetricEPYC 7773X 2PEPYC 7773X700K1400K2100K2800K3500K30886527343581. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -ldl -lm
OpenBenchmarking.orgVGR Performance Metric Per Watt, More Is BetterBRL-CAD 7.32.2VGR Performance MetricEPYC 7773X 2PEPYC 7773X4K8K12K16K20K18077.972813.55
OpenBenchmarking.orgWatts, Fewer Is BetterBRL-CAD 7.32.2CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X70140210280350Min: 73.96 / Avg: 170.85 / Max: 366.6Min: 33.66 / Avg: 261.01 / Max: 285.71

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DEPYC 7773X 2PEPYC 7773X20406080100SE +/- 1.61, N = 15SE +/- 1.58, N = 1289.9788.561. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X60120180240300Min: 73.76 / Avg: 168.72 / Max: 351.42Min: 33.87 / Avg: 87.48 / Max: 180.481. EPYC 7773X 2P: Approximate power consumption of 15815 Joules per run.2. EPYC 7773X: Approximate power consumption of 8092 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DEPYC 7773X 2PEPYC 7773X20406080100Min: 84.14 / Avg: 89.97 / Max: 99.64Min: 84.11 / Avg: 88.56 / Max: 98.931. (CXX) g++ options: -O2 -lOpenCL

MariaDB

This is a MariaDB MySQL database server benchmark making use of mysqlslap. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 512EPYC 7773X 2PEPYC 7773X140280420560700SE +/- 1.31, N = 3SE +/- 0.39, N = 34326691. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl
OpenBenchmarking.orgQueries Per Second Per Watt, More Is BetterMariaDB 10.8.2Clients: 512EPYC 7773X 2PEPYC 7773X1.20422.40843.61264.81686.0211.8875.352
OpenBenchmarking.orgWatts, Fewer Is BetterMariaDB 10.8.2CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X4080120160200Min: 78.76 / Avg: 228.93 / Max: 244.03Min: 33.92 / Avg: 125 / Max: 156.751. EPYC 7773X 2P: Approximate power consumption of 110648 Joules per run.2. EPYC 7773X: Approximate power consumption of 39750 Joules per run.
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.8.2Clients: 512EPYC 7773X 2PEPYC 7773X120240360480600Min: 429.18 / Avg: 431.79 / Max: 433.28Min: 668.45 / Avg: 669.05 / Max: 669.791. (CXX) g++ options: -pie -fPIC -fstack-protector -O3 -lnuma -lpcre2-8 -lcrypt -laio -lz -lm -lssl -lcrypto -lpthread -ldl

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/scivis/real_timeEPYC 7773X 2PEPYC 7773X714212835SE +/- 0.02, N = 3SE +/- 0.01, N = 332.2517.36
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.10Benchmark: particle_volume/scivis/real_timeEPYC 7773X 2PEPYC 7773X0.01690.03380.05070.06760.08450.0680.075
MinAvgMaxEPYC 7773X 2P75.1471.1566.5EPYC 7773X35.2231.0276.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.10CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 158297 Joules per run.2. EPYC 7773X: Approximate power consumption of 98786 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/scivis/real_timeEPYC 7773X 2PEPYC 7773X714212835Min: 32.21 / Avg: 32.25 / Max: 32.27Min: 17.35 / Avg: 17.36 / Max: 17.38

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.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenEPYC 7773X 2PEPYC 7773X13002600390052006500SE +/- 52.39, N = 3SE +/- 24.02, N = 3589550701. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.28Backend: EigenEPYC 7773X 2PEPYC 7773X51015202517.7121.71
MinAvgMaxEPYC 7773X 2P73.4332.8552.7EPYC 7773X34.8233.6287.0OpenBenchmarking.orgWatts, Fewer Is BetterLeelaChessZero 0.28CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 124467 Joules per run.2. EPYC 7773X: Approximate power consumption of 87285 Joules per run.
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenEPYC 7773X 2PEPYC 7773X10002000300040005000Min: 5828 / Avg: 5894.67 / Max: 5998Min: 5035 / Avg: 5070 / Max: 51161. (CXX) g++ options: -flto -pthread

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.468, N = 12SE +/- 0.013, N = 315.7776.4331. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 14.0CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X90180270360450Min: 75.46 / Avg: 411.25 / Max: 514.21Min: 34.62 / Avg: 239.74 / Max: 283.731. EPYC 7773X 2P: Approximate power consumption of 58912 Joules per run.2. EPYC 7773X: Approximate power consumption of 34203 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X48121620Min: 14.72 / Avg: 15.78 / Max: 20.65Min: 6.41 / Avg: 6.43 / Max: 6.451. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X17K34K51K68K85KSE +/- 769.35, N = 12SE +/- 158.53, N = 331942777201. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X13K26K39K52K65KMin: 24215.91 / Avg: 31941.97 / Max: 33958.96Min: 77544.64 / Avg: 77720.16 / Max: 78036.591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X3K6K9K12K15KSE +/- 597.46, N = 12SE +/- 19.68, N = 38884123981. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X2040608010041.2593.17
OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.11CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X4080120160200Min: 75.48 / Avg: 215.38 / Max: 248.21Min: 34.33 / Avg: 133.07 / Max: 137.731. EPYC 7773X 2P: Approximate power consumption of 26959 Joules per run.2. EPYC 7773X: Approximate power consumption of 16678 Joules per run.
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: GPT-2 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X2K4K6K8K10KMin: 5434.5 / Avg: 8883.63 / Max: 12236Min: 12366.5 / Avg: 12397.5 / Max: 124341. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X400800120016002000SE +/- 17.04, N = 12SE +/- 4.97, N = 3101916811. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X2468102.567.65
OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.11CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X80160240320400Min: 77.39 / Avg: 398.08 / Max: 435.92Min: 34.61 / Avg: 219.75 / Max: 228.661. EPYC 7773X 2P: Approximate power consumption of 49628 Joules per run.2. EPYC 7773X: Approximate power consumption of 27469 Joules per run.
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X30060090012001500Min: 938.5 / Avg: 1019.33 / Max: 1104Min: 1671 / Avg: 1680.67 / Max: 1687.51. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingEPYC 7773X 2PEPYC 7773X30060090012001500SE +/- 9.91, N = 15SE +/- 24.62, N = 1515815701. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.33Operation: ResizingEPYC 7773X 2PEPYC 7773X2468100.5618.351
MinAvgMaxEPYC 7773X 2P75.1281.8365.0EPYC 7773X35.3188.0259.5OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.33CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 18051 Joules per run.2. EPYC 7773X: Approximate power consumption of 12032 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingEPYC 7773X 2PEPYC 7773X30060090012001500Min: 109 / Avg: 158.4 / Max: 249Min: 1417 / Avg: 1569.67 / Max: 17421. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773X80M160M240M320M400M3933650003381550001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
OpenBenchmarking.orgsssp max_TEPS Per Watt, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773X300K600K900K1200K1500K769319.941230698.99
MinAvgMaxEPYC 7773X 2P77.1511.3573.2EPYC 7773X33.8274.8286.7OpenBenchmarking.orgWatts, Fewer Is BetterGraph500 3.0CPU Power Consumption Monitor140280420560700

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773X70M140M210M280M350M3129780002651460001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

OpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773X140M280M420M560M700M6254990006381280001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

OpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7773X 2PEPYC 7773X130M260M390M520M650M5969960006156550001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

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.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1EPYC 7773X 2PEPYC 7773X918273645SE +/- 0.46, N = 4SE +/- 0.01, N = 337.6619.681. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHigh Performance Conjugate Gradient 3.1EPYC 7773X 2PEPYC 7773X0.01980.03960.05940.07920.0990.0800.088
MinAvgMaxEPYC 7773X 2P73.1468.8563.2EPYC 7773X33.8223.8283.5OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 116724 Joules per run.2. EPYC 7773X: Approximate power consumption of 53850 Joules per run.
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1EPYC 7773X 2PEPYC 7773X816243240Min: 36.29 / Avg: 37.66 / Max: 38.25Min: 19.66 / Avg: 19.68 / Max: 19.71. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of Intel oneAPI. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUEPYC 7773X 2PEPYC 7773X15003000450060007500SE +/- 66.69, N = 15SE +/- 15.92, N = 36807.602423.06MIN: 5996.67MIN: 2337.771. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 2.6CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X70140210280350Min: 76.99 / Avg: 303.21 / Max: 421.48Min: 34.04 / Avg: 168.52 / Max: 213.71. EPYC 7773X 2P: Approximate power consumption of 28037 Joules per run.2. EPYC 7773X: Approximate power consumption of 13987 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUEPYC 7773X 2PEPYC 7773X12002400360048006000Min: 6263.1 / Avg: 6807.6 / Max: 7423.61Min: 2402.48 / Avg: 2423.06 / Max: 2454.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

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 29Oct2020Model: 20k AtomsEPYC 7773X 2PEPYC 7773X918273645SE +/- 0.40, N = 3SE +/- 0.10, N = 337.3929.741. (CXX) g++ options: -O3 -lm
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsEPYC 7773X 2PEPYC 7773X0.02360.04720.07080.09440.1180.0670.105
MinAvgMaxEPYC 7773X 2P75.9560.0572.8EPYC 7773X35.8282.5286.7OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 131221 Joules per run.2. EPYC 7773X: Approximate power consumption of 83150 Joules per run.
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: 20k AtomsEPYC 7773X 2PEPYC 7773X816243240Min: 36.6 / Avg: 37.39 / Max: 37.9Min: 29.61 / Avg: 29.74 / Max: 29.931. (CXX) g++ options: -O3 -lm

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/ao/real_timeEPYC 7773X 2PEPYC 7773X816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 332.6117.51
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.10Benchmark: particle_volume/ao/real_timeEPYC 7773X 2PEPYC 7773X0.01460.02920.04380.05840.0730.0590.065
MinAvgMaxEPYC 7773X 2P78.2551.5566.1EPYC 7773X34.3270.2276.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.10CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 128501 Joules per run.2. EPYC 7773X: Approximate power consumption of 77468 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/ao/real_timeEPYC 7773X 2PEPYC 7773X714212835Min: 32.59 / Avg: 32.61 / Max: 32.64Min: 17.5 / Avg: 17.51 / Max: 17.53

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.080, N = 8SE +/- 0.016, N = 39.4892.8371. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 7773X 2P74.9331.9449.7EPYC 7773X34.6233.9284.4OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 14.0CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 47502 Joules per run.2. EPYC 7773X: Approximate power consumption of 33285 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X3691215Min: 9.11 / Avg: 9.49 / Max: 9.81Min: 2.82 / Avg: 2.84 / Max: 2.871. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X20K40K60K80K100KSE +/- 223.37, N = 8SE +/- 488.29, N = 326360881101. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X15K30K45K60K75KMin: 25475.49 / Avg: 26360.27 / Max: 27450.42Min: 87166.32 / Avg: 88109.87 / Max: 88799.751. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total TimeEPYC 7773X 2PEPYC 7773X70M140M210M280M350MSE +/- 5231696.32, N = 15SE +/- 697166.64, N = 33200245541598210651. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 15Total TimeEPYC 7773X 2PEPYC 7773X130K260K390K520K650K593736.64625390.99
OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 15CPU Power Consumption MonitorEPYC 7773X 2PEPYC 7773X100200300400500Min: 75.31 / Avg: 539 / Max: 573.98Min: 35.21 / Avg: 255.55 / Max: 285.71. EPYC 7773X 2P: Approximate power consumption of 47109 Joules per run.2. EPYC 7773X: Approximate power consumption of 20444 Joules per run.
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total TimeEPYC 7773X 2PEPYC 7773X60M120M180M240M300MMin: 288141582 / Avg: 320024554.07 / Max: 355720468Min: 158427123 / Avg: 159821064.67 / Max: 1605466531. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X90180270360450SE +/- 11.96, N = 9SE +/- 3.61, N = 32924151. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X0.46670.93341.40011.86682.33350.7342.074
MinAvgMaxEPYC 7773X 2P76.0398.0429.0EPYC 7773X34.1200.1209.1OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.11CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 49577 Joules per run.2. EPYC 7773X: Approximate power consumption of 25010 Joules per run.
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: yolov4 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X70140210280350Min: 257.5 / Avg: 291.83 / Max: 354Min: 408.5 / Avg: 414.67 / Max: 4211. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X15003000450060007500SE +/- 252.84, N = 9SE +/- 0.88, N = 3494070131. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X112233445522.5450.93
MinAvgMaxEPYC 7773X 2P75.3219.2246.7EPYC 7773X34.4137.7143.9OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.11CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 27081 Joules per run.2. EPYC 7773X: Approximate power consumption of 17076 Joules per run.
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X12002400360048006000Min: 4524.5 / Avg: 4939.72 / Max: 6835.5Min: 7012 / Avg: 7013.33 / Max: 70151. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 95, Compression Effort 7EPYC 7773X 2PEPYC 7773X50100150200250SE +/- 0.40, N = 3SE +/- 0.14, N = 3238.32238.331. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
MinAvgMaxEPYC 7773X 2P74.1218.0237.2EPYC 7773X34.0150.4162.5OpenBenchmarking.orgWatts, Fewer Is BetterWebP2 Image Encode 20220422CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 52690 Joules per run.2. EPYC 7773X: Approximate power consumption of 36356 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 95, Compression Effort 7EPYC 7773X 2PEPYC 7773X4080120160200Min: 237.52 / Avg: 238.32 / Max: 238.74Min: 238.18 / Avg: 238.33 / Max: 238.611. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Barbershop - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X60120180240300SE +/- 0.10, N = 3SE +/- 0.74, N = 3148.69286.91
MinAvgMaxEPYC 7773X 2P75.3536.1573.5EPYC 7773X34.8263.9273.4OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 82745 Joules per run.2. EPYC 7773X: Approximate power consumption of 76982 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Barbershop - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X50100150200250Min: 148.51 / Avg: 148.69 / Max: 148.85Min: 285.44 / Avg: 286.91 / Max: 287.7

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.15, N = 15SE +/- 0.14, N = 612.3914.171. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.02520.05040.07560.10080.1260.0590.112
MinAvgMaxEPYC 7773X 2P77.1209.3251.2EPYC 7773X34.2126.7157.2OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.4CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 14025 Joules per run.2. EPYC 7773X: Approximate power consumption of 7644 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X48121620Min: 11.51 / Avg: 12.39 / Max: 13.11Min: 13.71 / Avg: 14.17 / Max: 14.471. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X612182430SE +/- 0.128, N = 3SE +/- 0.030, N = 324.6607.4521. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 7773X 2P76.9243.0395.9EPYC 7773X34.6162.8269.8OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 14.0CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 52805 Joules per run.2. EPYC 7773X: Approximate power consumption of 34953 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read Write - Average LatencyEPYC 7773X 2PEPYC 7773X612182430Min: 24.47 / Avg: 24.66 / Max: 24.9Min: 7.4 / Avg: 7.45 / Max: 7.511. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X14K28K42K56K70KSE +/- 104.40, N = 3SE +/- 275.42, N = 320277670971. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 1000 - Clients: 500 - Mode: Read WriteEPYC 7773X 2PEPYC 7773X12K24K36K48K60KMin: 20077.33 / Avg: 20277.08 / Max: 20429.61Min: 66600.94 / Avg: 67097.23 / Max: 67552.341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

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 7773X 2PEPYC 7773X100200300400500SE +/- 1.12, N = 3SE +/- 1.20, N = 3475.51471.97
OpenBenchmarking.orgScore Per Watt, More Is BetterNumpy BenchmarkEPYC 7773X 2PEPYC 7773X2468103.5587.047
MinAvgMaxEPYC 7773X 2P75.7133.6141.9EPYC 7773X33.867.072.2OpenBenchmarking.orgWatts, Fewer Is BetterNumpy BenchmarkCPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 27127 Joules per run.2. EPYC 7773X: Approximate power consumption of 13663 Joules per run.
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkEPYC 7773X 2PEPYC 7773X80160240320400Min: 473.32 / Avg: 475.51 / Max: 477.04Min: 470.35 / Avg: 471.97 / Max: 474.3

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 7773X 2PEPYC 7773X510152025SE +/- 0.24, N = 15SE +/- 0.16, N = 321.8113.46MIN: 18.56 / MAX: 28.77MIN: 11.7 / MAX: 15.61
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 7773X 2PEPYC 7773X0.01190.02380.03570.04760.05950.0420.053
MinAvgMaxEPYC 7773X 2P75.2520.6579.0EPYC 7773X35.4253.0280.7OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor1603204806408001. EPYC 7773X 2P: Approximate power consumption of 35265 Joules per run.2. EPYC 7773X: Approximate power consumption of 17201 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 7773X 2PEPYC 7773X510152025Min: 20.81 / Avg: 21.81 / Max: 23.26Min: 13.18 / Avg: 13.46 / Max: 13.73

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUEPYC 7773X 2PEPYC 7773X246810SE +/- 0.15, N = 15SE +/- 0.04, N = 38.097.36MIN: 2.98 / MAX: 10.76MIN: 3 / MAX: 8.65
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUEPYC 7773X 2PEPYC 7773X0.00650.0130.01950.0260.03250.0170.029
MinAvgMaxEPYC 7773X 2P76.0484.6577.4EPYC 7773X35.1256.0288.7OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 32405 Joules per run.2. EPYC 7773X: Approximate power consumption of 16898 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUEPYC 7773X 2PEPYC 7773X3691215Min: 7.25 / Avg: 8.09 / Max: 9.14Min: 7.3 / Avg: 7.36 / Max: 7.45

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 7773X 2PEPYC 7773X246810SE +/- 0.10, N = 15SE +/- 0.04, N = 37.527.61MIN: 2.55 / MAX: 10.2MIN: 2.95 / MAX: 8.96
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 7773X 2PEPYC 7773X0.00680.01360.02040.02720.0340.0160.030
MinAvgMaxEPYC 7773X 2P76.0460.8558.4EPYC 7773X35.1252.7284.4OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 30503 Joules per run.2. EPYC 7773X: Approximate power consumption of 16764 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 7773X 2PEPYC 7773X3691215Min: 7.03 / Avg: 7.52 / Max: 8.58Min: 7.56 / Avg: 7.61 / Max: 7.68

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: allmodconfigEPYC 7773X 2PEPYC 7773X50100150200250SE +/- 0.50, N = 3SE +/- 0.44, N = 3139.95234.16
MinAvgMaxEPYC 7773X 2P75.2432.8574.0EPYC 7773X34.3246.8286.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 5.18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 66366 Joules per run.2. EPYC 7773X: Approximate power consumption of 60711 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: allmodconfigEPYC 7773X 2PEPYC 7773X4080120160200Min: 139.45 / Avg: 139.95 / Max: 140.94Min: 233.67 / Avg: 234.16 / Max: 235.04

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesEPYC 7773X 2PEPYC 7773X4080120160200SE +/- 0.65, N = 3SE +/- 0.51, N = 3171.30198.50
MinAvgMaxEPYC 7773X 2P74.8284.7573.2EPYC 7773X34.5185.0287.0OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 13.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 54471 Joules per run.2. EPYC 7773X: Approximate power consumption of 40259 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesEPYC 7773X 2PEPYC 7773X4080120160200Min: 170.4 / Avg: 171.3 / Max: 172.58Min: 197.94 / Avg: 198.5 / Max: 199.51

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Update RandomEPYC 7773X 2PEPYC 7773X80K160K240K320K400KSE +/- 2263.57, N = 15SE +/- 2059.34, N = 32805173686711. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterFacebook RocksDB 7.0.1Test: Update RandomEPYC 7773X 2PEPYC 7773X400800120016002000931.911839.09
MinAvgMaxEPYC 7773X 2P77.1301.0366.4EPYC 7773X34.4200.5232.0OpenBenchmarking.orgWatts, Fewer Is BetterFacebook RocksDB 7.0.1CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 19466 Joules per run.2. EPYC 7773X: Approximate power consumption of 12830 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Update RandomEPYC 7773X 2PEPYC 7773X60K120K180K240K300KMin: 268590 / Avg: 280516.73 / Max: 301011Min: 364717 / Avg: 368670.67 / Max: 3716471. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read While WritingEPYC 7773X 2PEPYC 7773X4M8M12M16M20MSE +/- 238031.79, N = 15SE +/- 57459.78, N = 31733750699196711. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterFacebook RocksDB 7.0.1Test: Read While WritingEPYC 7773X 2PEPYC 7773X8K16K24K32K40K35478.9437230.01
MinAvgMaxEPYC 7773X 2P77.5488.7569.5EPYC 7773X34.5266.4286.6OpenBenchmarking.orgWatts, Fewer Is BetterFacebook RocksDB 7.0.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 31079 Joules per run.2. EPYC 7773X: Approximate power consumption of 16964 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read While WritingEPYC 7773X 2PEPYC 7773X3M6M9M12M15MMin: 15515086 / Avg: 17337506.07 / Max: 19606230Min: 9819808 / Avg: 9919670.67 / Max: 100188511. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

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 3.0Algorithm: SHA256EPYC 7773X 2PEPYC 7773X30000M60000M90000M120000M150000MSE +/- 77628222.70, N = 3SE +/- 138355411.89, N = 3153461007540764249664101. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.0Algorithm: SHA256EPYC 7773X 2PEPYC 7773X60M120M180M240M300M285495262.23281777244.03
MinAvgMaxEPYC 7773X 2P76.4537.5573.2EPYC 7773X33.9271.2286.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 98188 Joules per run.2. EPYC 7773X: Approximate power consumption of 49725 Joules per run.
OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256EPYC 7773X 2PEPYC 7773X30000M60000M90000M120000M150000MMin: 153361691510 / Avg: 153461007540 / Max: 153614012870Min: 76243179650 / Avg: 76424966410 / Max: 766965303201. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Java JMH

This very basic test profile runs the stock benchmark of the Java JMH benchmark via Maven. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/s, More Is BetterJava JMHThroughputEPYC 7773X 2PEPYC 7773X30000M60000M90000M120000M150000M156410828590.7278156370321.98
OpenBenchmarking.orgOps/s Per Watt, More Is BetterJava JMHThroughputEPYC 7773X 2PEPYC 7773X70M140M210M280M350M335004508.26337310574.34
MinAvgMaxEPYC 7773X 2P75.8466.9534.3EPYC 7773X35.5231.7267.4OpenBenchmarking.orgWatts, Fewer Is BetterJava JMHCPU Power Consumption Monitor140280420560700

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/ with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all queries performed. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, Third RunEPYC 7773X 2PEPYC 7773X90180270360450SE +/- 2.94, N = 13SE +/- 2.22, N = 13421.77432.79MIN: 72.82 / MAX: 20000MIN: 46.66 / MAX: 200001. ClickHouse server version 22.7.1.687 (official build).
OpenBenchmarking.orgQueries Per Minute, Geo Mean Per Watt, More Is BetterClickHouse100M Rows Web Analytics Dataset, Third RunEPYC 7773X 2PEPYC 7773X0.66111.32221.98332.64443.30551.6162.938
MinAvgMaxEPYC 7773X 2P75.7260.9403.2EPYC 7773X34.4147.3242.9OpenBenchmarking.orgWatts, Fewer Is BetterClickHouseCPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 10799 Joules per run.2. EPYC 7773X: Approximate power consumption of 6120 Joules per run.
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, Third RunEPYC 7773X 2PEPYC 7773X80160240320400Min: 402.04 / Avg: 421.77 / Max: 434.7Min: 419.73 / Avg: 432.79 / Max: 445.671. ClickHouse server version 22.7.1.687 (official build).

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, Second RunEPYC 7773X 2PEPYC 7773X90180270360450SE +/- 2.37, N = 13SE +/- 2.18, N = 13421.91428.41MIN: 74.91 / MAX: 20000MIN: 47.36 / MAX: 200001. ClickHouse server version 22.7.1.687 (official build).
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, Second RunEPYC 7773X 2PEPYC 7773X80160240320400Min: 409.74 / Avg: 421.91 / Max: 437.49Min: 417.47 / Avg: 428.41 / Max: 440.331. ClickHouse server version 22.7.1.687 (official build).

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, First Run / Cold CacheEPYC 7773X 2PEPYC 7773X90180270360450SE +/- 6.54, N = 13SE +/- 5.65, N = 13394.48417.81MIN: 49.46 / MAX: 20000MIN: 42.31 / MAX: 200001. ClickHouse server version 22.7.1.687 (official build).
OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse100M Rows Web Analytics Dataset, First Run / Cold CacheEPYC 7773X 2PEPYC 7773X70140210280350Min: 321.24 / Avg: 394.48 / Max: 411.18Min: 355.93 / Avg: 417.81 / Max: 436.371. ClickHouse server version 22.7.1.687 (official build).

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773X0.03350.0670.10050.1340.1675SE +/- 0.001, N = 4SE +/- 0.001, N = 30.0970.1491. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 7773X 2P75.2498.0577.8EPYC 7773X33.9248.7291.2OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 14.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 70722 Joules per run.2. EPYC 7773X: Approximate power consumption of 35316 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773X12345Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.15 / Avg: 0.15 / Max: 0.151. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773X600K1200K1800K2400K3000KSE +/- 30252.52, N = 4SE +/- 10683.27, N = 3258566116748531. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 250 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773X400K800K1200K1600K2000KMin: 2503169.79 / Avg: 2585661.33 / Max: 2638436.93Min: 1653528.35 / Avg: 1674852.69 / Max: 1686677.311. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X160320480640800SE +/- 5.60, N = 5SE +/- 0.76, N = 35437531. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute Per Watt, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X0.77511.55022.32533.10043.87551.3743.445
MinAvgMaxEPYC 7773X 2P75.7395.2417.6EPYC 7773X34.6218.6227.1OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.11CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 49238 Joules per run.2. EPYC 7773X: Approximate power consumption of 27323 Joules per run.
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardEPYC 7773X 2PEPYC 7773X130260390520650Min: 531 / Avg: 543.2 / Max: 563Min: 751.5 / Avg: 753 / Max: 7541. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt

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 21.2Time To CompileEPYC 7773X 2PEPYC 7773X4080120160200SE +/- 1.68, N = 3SE +/- 1.30, N = 3151.27170.17
MinAvgMaxEPYC 7773X 2P76.2232.2574.0EPYC 7773X33.9142.7288.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 21.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 36307 Joules per run.2. EPYC 7773X: Approximate power consumption of 24975 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To CompileEPYC 7773X 2PEPYC 7773X306090120150Min: 147.93 / Avg: 151.27 / Max: 153.32Min: 168.78 / Avg: 170.17 / Max: 172.78

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X2K4K6K8K10KSE +/- 10.17, N = 3SE +/- 12.25, N = 35262103321. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.5510.0573.4EPYC 7773X35.0247.5275.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 73782 Joules per run.2. EPYC 7773X: Approximate power consumption of 40253 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X2K4K6K8K10KMin: 5251 / Avg: 5261.67 / Max: 5282Min: 10315 / Avg: 10332.33 / Max: 103561. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X2K4K6K8K10KSE +/- 1.53, N = 3SE +/- 16.19, N = 3445287171. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P75.2501.5573.5EPYC 7773X35.3247.2272.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 69713 Joules per run.2. EPYC 7773X: Approximate power consumption of 41116 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X15003000450060007500Min: 4449 / Avg: 4452 / Max: 4454Min: 8693 / Avg: 8717.33 / Max: 87481. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X7K14K21K28K35KSE +/- 62.00, N = 3SE +/- 29.13, N = 317942348811. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P77.1523.9573.9EPYC 7773X34.9240.4274.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 94300 Joules per run.2. EPYC 7773X: Approximate power consumption of 29567 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X6K12K18K24K30KMin: 17850 / Avg: 17942 / Max: 18060Min: 34843 / Avg: 34880.67 / Max: 349381. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X2K4K6K8K10KSE +/- 8.39, N = 3SE +/- 5.13, N = 3453287851. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.2506.4573.6EPYC 7773X35.0248.1274.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 69209 Joules per run.2. EPYC 7773X: Approximate power consumption of 40775 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X15003000450060007500Min: 4517 / Avg: 4532 / Max: 4546Min: 8778 / Avg: 8785 / Max: 87951. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X4K8K12K16K20KSE +/- 5.03, N = 3SE +/- 31.65, N = 38915174531. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P74.9516.8573.5EPYC 7773X35.0241.1273.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 83034 Joules per run.2. EPYC 7773X: Approximate power consumption of 31025 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X3K6K9K12K15KMin: 8909 / Avg: 8915 / Max: 8925Min: 17391 / Avg: 17453.33 / Max: 174941. (CXX) g++ options: -O3 -ldl

PostgreSQL pgbench

This is a benchmark of PostgreSQL using pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773X0.06820.13640.20460.27280.341SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1940.3031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxEPYC 7773X 2P74.9497.1574.3EPYC 7773X34.7249.0286.6OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL pgbench 14.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 70760 Joules per run.2. EPYC 7773X: Approximate power consumption of 35447 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average LatencyEPYC 7773X 2PEPYC 7773X12345Min: 0.19 / Avg: 0.19 / Max: 0.2Min: 0.3 / Avg: 0.3 / Max: 0.31. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773X600K1200K1800K2400K3000KSE +/- 8094.03, N = 3SE +/- 7129.48, N = 3257122216536021. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 14.0Scaling Factor: 100 - Clients: 500 - Mode: Read OnlyEPYC 7773X 2PEPYC 7773X400K800K1200K1600K2000KMin: 2559032.2 / Avg: 2571222.48 / Max: 2586541.92Min: 1645774.16 / Avg: 1653602.22 / Max: 1667837.561. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X4K8K12K16K20KSE +/- 11.72, N = 3SE +/- 11.79, N = 39071175751. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P77.3516.2573.4EPYC 7773X35.0242.3274.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 79832 Joules per run.2. EPYC 7773X: Approximate power consumption of 31416 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X3K6K9K12K15KMin: 9053 / Avg: 9071 / Max: 9093Min: 17560 / Avg: 17574.67 / Max: 175981. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X4K8K12K16K20KSE +/- 7.31, N = 3SE +/- 35.14, N = 310515206341. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.9519.1573.8EPYC 7773X35.0232.5273.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 86162 Joules per run.2. EPYC 7773X: Approximate power consumption of 23481 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X4K8K12K16K20KMin: 10504 / Avg: 10515.33 / Max: 10529Min: 20587 / Avg: 20634.33 / Max: 207031. (CXX) g++ options: -O3 -ldl

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 9Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 7773X 2PEPYC 7773X80160240320400170.52366.981. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 7773X35.3261.3286.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 9CPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Small Mesh Size - Mesh TimeEPYC 7773X 2PEPYC 7773X306090120150105.26113.121. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Medium Mesh Size - Execution TimeEPYC 7773X 2PEPYC 7773X80160240320400169.8366.01. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 7773X35.5261.7286.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 9CPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: drivaerFastback, Medium Mesh Size - Mesh TimeEPYC 7773X 2PEPYC 7773X306090120150104.44114.511. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesEPYC 7773X 2PEPYC 7773X60K120K180K240K300KSE +/- 2805.95, N = 3SE +/- 1619.13, N = 3216547269401
OpenBenchmarking.orgOp/s Per Watt, More Is BetterApache Cassandra 4.0Test: WritesEPYC 7773X 2PEPYC 7773X30060090012001500616.531342.68
MinAvgMaxEPYC 7773X 2P75.5351.2420.8EPYC 7773X34.9200.6260.6OpenBenchmarking.orgWatts, Fewer Is BetterApache Cassandra 4.0CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 50929 Joules per run.2. EPYC 7773X: Approximate power consumption of 28826 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: WritesEPYC 7773X 2PEPYC 7773X50K100K150K200K250KMin: 212660 / Avg: 216547 / Max: 221996Min: 266216 / Avg: 269401.33 / Max: 271499

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X140280420560700SE +/- 0.67, N = 3SE +/- 0.67, N = 33286411. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.5513.7573.7EPYC 7773X35.1236.4273.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 76543 Joules per run.2. EPYC 7773X: Approximate power consumption of 26323 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X110220330440550Min: 327 / Avg: 328.33 / Max: 329Min: 640 / Avg: 641.33 / Max: 6421. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X7K14K21K28K35KSE +/- 4.06, N = 3SE +/- 45.85, N = 317575346491. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P75.7504.2573.6EPYC 7773X35.0239.2272.8OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 65716 Joules per run.2. EPYC 7773X: Approximate power consumption of 29263 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X6K12K18K24K30KMin: 17568 / Avg: 17575.33 / Max: 17582Min: 34558 / Avg: 34649.33 / Max: 347021. (CXX) g++ options: -O3 -ldl

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthEPYC 7773X 2PEPYC 7773X60M120M180M240M300MSE +/- 1637427.52, N = 3SE +/- 1583098.25, N = 3284279174152335321
OpenBenchmarking.orgNodes/second Per Watt, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthEPYC 7773X 2PEPYC 7773X120K240K360K480K600K518317.82556381.67
MinAvgMaxEPYC 7773X 2P74.9548.5573.4EPYC 7773X35.5273.8286.6OpenBenchmarking.orgWatts, Fewer Is BetterasmFish 2018-07-23CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 64536 Joules per run.2. EPYC 7773X: Approximate power consumption of 36689 Joules per run.
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthEPYC 7773X 2PEPYC 7773X50M100M150M200M250MMin: 281019497 / Avg: 284279173.67 / Max: 286181753Min: 149523388 / Avg: 152335320.67 / Max: 155001595

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X120240360480600SE +/- 0.33, N = 3SE +/- 0.67, N = 32855461. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.6512.4573.8EPYC 7773X35.0237.7275.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 72419 Joules per run.2. EPYC 7773X: Approximate power consumption of 26152 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X100200300400500Min: 284 / Avg: 284.67 / Max: 285Min: 545 / Avg: 545.67 / Max: 5471. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X120240360480600SE +/- 0.00, N = 3SE +/- 0.33, N = 32785411. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.8510.6573.8EPYC 7773X34.8235.9273.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 71478 Joules per run.2. EPYC 7773X: Approximate power consumption of 26032 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X100200300400500Min: 278 / Avg: 278 / Max: 278Min: 541 / Avg: 541.33 / Max: 5421. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X5001000150020002500SE +/- 1.15, N = 3SE +/- 5.04, N = 3129725451. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.9497.4573.7EPYC 7773X35.1241.7273.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 58198 Joules per run.2. EPYC 7773X: Approximate power consumption of 31415 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X400800120016002000Min: 1295 / Avg: 1297 / Max: 1299Min: 2535 / Avg: 2544.67 / Max: 25521. (CXX) g++ options: -O3 -ldl

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500EPYC 7773X 2PEPYC 7773X30K60K90K120K150KSE +/- 769.49, N = 3SE +/- 1223.82, N = 597855.03119227.931. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500EPYC 7773X 2PEPYC 7773X120240360480600243.72537.59
MinAvgMaxEPYC 7773X 2P76.2401.5433.7EPYC 7773X34.5221.8240.1OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.48CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 38679 Joules per run.2. EPYC 7773X: Approximate power consumption of 21247 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 500EPYC 7773X 2PEPYC 7773X20K40K60K80K100KMin: 96342.22 / Avg: 97855.03 / Max: 98856.18Min: 116839.17 / Avg: 119227.93 / Max: 123919.411. (CC) gcc options: -shared -fPIC -O2

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X20K40K60K80K100KSE +/- 34.53, N = 3SE +/- 111.57, N = 341541878761. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.1511.0573.7EPYC 7773X35.1233.1273.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 73409 Joules per run.2. EPYC 7773X: Approximate power consumption of 23305 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X15K30K45K60K75KMin: 41490 / Avg: 41541.33 / Max: 41607Min: 87674 / Avg: 87876.33 / Max: 880591. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X5001000150020002500SE +/- 1.20, N = 3SE +/- 2.91, N = 3113121721. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P77.2500.4574.0EPYC 7773X35.0241.9274.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 58376 Joules per run.2. EPYC 7773X: Approximate power consumption of 30723 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X400800120016002000Min: 1129 / Avg: 1130.67 / Max: 1133Min: 2167 / Avg: 2172.33 / Max: 21771. (CXX) g++ options: -O3 -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X9K18K27K36K45KSE +/- 26.19, N = 3SE +/- 69.29, N = 320789409221. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P75.9488.2573.9EPYC 7773X35.0243.3272.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 49475 Joules per run.2. EPYC 7773X: Approximate power consumption of 34229 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X7K14K21K28K35KMin: 20754 / Avg: 20788.67 / Max: 20840Min: 40786 / Avg: 40922.33 / Max: 410121. (CXX) g++ options: -O3 -ldl

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 7773X 2PEPYC 7773X612182430SE +/- 0.02, N = 3SE +/- 0.01, N = 325.7013.60
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 7773X 2PEPYC 7773X0.01190.02380.03570.04760.05950.0480.053
MinAvgMaxEPYC 7773X 2P74.8533.2573.7EPYC 7773X35.2255.1276.8OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.10CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 73754 Joules per run.2. EPYC 7773X: Approximate power consumption of 26019 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 7773X 2PEPYC 7773X612182430Min: 25.68 / Avg: 25.7 / Max: 25.73Min: 13.58 / Avg: 13.6 / Max: 13.62

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X5001000150020002500SE +/- 0.88, N = 3SE +/- 0.33, N = 3109921541. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P76.4499.1573.8EPYC 7773X34.2239.5274.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 57568 Joules per run.2. EPYC 7773X: Approximate power consumption of 29855 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X400800120016002000Min: 1097 / Avg: 1098.67 / Max: 1100Min: 2153 / Avg: 2153.67 / Max: 21541. (CXX) g++ options: -O3 -ldl

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaEPYC 7773X 2PEPYC 7773X306090120150SE +/- 0.84, N = 3SE +/- 0.08, N = 392.55137.24
MinAvgMaxEPYC 7773X 2P74.5346.1574.3EPYC 7773X34.5214.8286.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 13.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 38306 Joules per run.2. EPYC 7773X: Approximate power consumption of 33217 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaEPYC 7773X 2PEPYC 7773X306090120150Min: 91.35 / Avg: 92.55 / Max: 94.16Min: 137.08 / Avg: 137.24 / Max: 137.32

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 17.3Time To CompileEPYC 7773X 2PEPYC 7773X306090120150SE +/- 0.31, N = 3SE +/- 1.33, N = 395.05131.98
MinAvgMaxEPYC 7773X 2P75.9337.3575.4EPYC 7773X34.2208.5286.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 17.3CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 34631 Joules per run.2. EPYC 7773X: Approximate power consumption of 29046 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 17.3Time To CompileEPYC 7773X 2PEPYC 7773X20406080100Min: 94.44 / Avg: 95.05 / Max: 95.42Min: 130.29 / Avg: 131.98 / Max: 134.6

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 75, Compression Effort 7EPYC 7773X 2PEPYC 7773X306090120150SE +/- 0.06, N = 3SE +/- 0.08, N = 3112.17112.561. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
MinAvgMaxEPYC 7773X 2P75.0214.4235.6EPYC 7773X33.7146.0160.3OpenBenchmarking.orgWatts, Fewer Is BetterWebP2 Image Encode 20220422CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 24871 Joules per run.2. EPYC 7773X: Approximate power consumption of 17084 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 75, Compression Effort 7EPYC 7773X 2PEPYC 7773X20406080100Min: 112.05 / Avg: 112.17 / Max: 112.26Min: 112.46 / Avg: 112.56 / Max: 112.711. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X246810SE +/- 0.06, N = 3SE +/- 0.08, N = 36.607.571. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.4Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.01310.02620.03930.05240.06550.0310.058
MinAvgMaxEPYC 7773X 2P75.4213.8270.6EPYC 7773X34.1130.4175.0OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.4CPU Power Consumption Monitor701402102803501. EPYC 7773X 2P: Approximate power consumption of 24590 Joules per run.2. EPYC 7773X: Approximate power consumption of 13392 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X3691215Min: 6.54 / Avg: 6.6 / Max: 6.71Min: 7.48 / Avg: 7.57 / Max: 7.731. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X16K32K48K64K80KSE +/- 175.50, N = 3SE +/- 53.03, N = 335944758361. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P75.5503.7573.2EPYC 7773X35.0228.5273.8OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 63796 Joules per run.2. EPYC 7773X: Approximate power consumption of 20107 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X13K26K39K52K65KMin: 35743 / Avg: 35944.33 / Max: 36294Min: 75730 / Avg: 75836 / Max: 758921. (CXX) g++ options: -O3 -ldl

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral MixingEPYC 7773X 2PEPYC 7773X0.45430.90861.36291.81722.2715SE +/- 0.001, N = 3SE +/- 0.001, N = 32.0192.014
MinAvgMaxEPYC 7773X 2P75.9143.4152.4EPYC 7773X33.775.584.0OpenBenchmarking.orgWatts, Fewer Is BetterPyHPC Benchmarks 3.0CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 15348 Joules per run.2. EPYC 7773X: Approximate power consumption of 8083 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral MixingEPYC 7773X 2PEPYC 7773X246810Min: 2.02 / Avg: 2.02 / Max: 2.02Min: 2.01 / Avg: 2.01 / Max: 2.02

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity 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.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X16K32K48K64K80KSE +/- 78.94, N = 3SE +/- 257.72, N = 335287756261. (CXX) g++ options: -O3 -ldl
MinAvgMaxEPYC 7773X 2P75.4501.7573.9EPYC 7773X35.1226.7273.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 62550 Joules per run.2. EPYC 7773X: Approximate power consumption of 19874 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerEPYC 7773X 2PEPYC 7773X13K26K39K52K65KMin: 35146 / Avg: 35287 / Max: 35419Min: 75164 / Avg: 75625.67 / Max: 760551. (CXX) g++ options: -O3 -ldl

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.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.01406, N = 3SE +/- 0.00607, N = 315.573108.52012
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 7773X 2PEPYC 7773X0.00720.01440.02160.02880.0360.0300.032
MinAvgMaxEPYC 7773X 2P74.9526.8573.4EPYC 7773X35.2262.5286.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.10CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 53386 Joules per run.2. EPYC 7773X: Approximate power consumption of 27909 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 7773X 2PEPYC 7773X48121620Min: 15.55 / Avg: 15.57 / Max: 15.6Min: 8.51 / Avg: 8.52 / Max: 8.53

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.00699, N = 3SE +/- 0.01748, N = 316.402608.95305
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 7773X 2PEPYC 7773X0.00770.01540.02310.03080.03850.0310.034
MinAvgMaxEPYC 7773X 2P76.2524.4573.7EPYC 7773X34.2262.8286.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.10CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 52615 Joules per run.2. EPYC 7773X: Approximate power consumption of 27949 Joules per run.
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 7773X 2PEPYC 7773X48121620Min: 16.39 / Avg: 16.4 / Max: 16.42Min: 8.92 / Avg: 8.95 / Max: 8.98

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.04730.09460.14190.18920.2365SE +/- 0.00, N = 3SE +/- 0.00, N = 30.210.211. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.4Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.00050.0010.00150.0020.00250.0010.002
MinAvgMaxEPYC 7773X 2P76.7188.8337.9EPYC 7773X34.1117.0238.9OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.4CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 18565 Joules per run.2. EPYC 7773X: Approximate power consumption of 11468 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X12345Min: 0.21 / Avg: 0.21 / Max: 0.21Min: 0.21 / Avg: 0.21 / Max: 0.211. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773X20K40K60K80K100KSE +/- 484.05, N = 3SE +/- 321.37, N = 386754.44116446.751. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773X120240360480600214.85544.85
MinAvgMaxEPYC 7773X 2P75.6403.8443.1EPYC 7773X34.4213.7236.3OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.48CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 39842 Joules per run.2. EPYC 7773X: Approximate power consumption of 21372 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773X20K40K60K80K100KMin: 86038.98 / Avg: 86754.44 / Max: 87676.96Min: 115805.52 / Avg: 116446.75 / Max: 116805.561. (CC) gcc options: -shared -fPIC -O2

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Triple SHA-256, OnecoinEPYC 7773X 2PEPYC 7773X700K1400K2100K2800K3500KSE +/- 21172.95, N = 15SE +/- 8814.76, N = 3310169614370471. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: Triple SHA-256, OnecoinEPYC 7773X 2PEPYC 7773X3K6K9K12K15K14294.6413218.96
MinAvgMaxEPYC 7773X 2P77.1217.0318.8EPYC 7773X34.0108.7201.7OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 7565 Joules per run.2. EPYC 7773X: Approximate power consumption of 3805 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Triple SHA-256, OnecoinEPYC 7773X 2PEPYC 7773X500K1000K1500K2000K2500KMin: 2913160 / Avg: 3101696 / Max: 3230830Min: 1422220 / Avg: 1437046.67 / Max: 14527201. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Blake-2 SEPYC 7773X 2PEPYC 7773X1.6M3.2M4.8M6.4M8MSE +/- 62791.55, N = 3SE +/- 37457.49, N = 15727719034227111. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: Blake-2 SEPYC 7773X 2PEPYC 7773X7K14K21K28K35K33911.1331337.68
MinAvgMaxEPYC 7773X 2P76.1214.6266.7EPYC 7773X34.1109.2157.3OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor701402102803501. EPYC 7773X 2P: Approximate power consumption of 7511 Joules per run.2. EPYC 7773X: Approximate power consumption of 3815 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Blake-2 SEPYC 7773X 2PEPYC 7773X1.3M2.6M3.9M5.2M6.5MMin: 7154580 / Avg: 7277190 / Max: 7362020Min: 3053590 / Avg: 3422711.33 / Max: 36032601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: LBC, LBRY CreditsEPYC 7773X 2PEPYC 7773X60K120K180K240K300KSE +/- 5037.87, N = 15SE +/- 803.87, N = 32923581375071. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: LBC, LBRY CreditsEPYC 7773X 2PEPYC 7773X300600900120015001260.631158.82
MinAvgMaxEPYC 7773X 2P76.3231.9505.3EPYC 7773X33.9118.7223.5OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 8086 Joules per run.2. EPYC 7773X: Approximate power consumption of 4114 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: LBC, LBRY CreditsEPYC 7773X 2PEPYC 7773X50K100K150K200K250KMin: 265910 / Avg: 292358 / Max: 336330Min: 136400 / Avg: 137506.67 / Max: 1390701. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: DeepcoinEPYC 7773X 2PEPYC 7773X20K40K60K80K100KSE +/- 922.21, N = 15SE +/- 69.36, N = 381774479731. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: DeepcoinEPYC 7773X 2PEPYC 7773X70140210280350302.72323.29
MinAvgMaxEPYC 7773X 2P75.5270.1468.3EPYC 7773X34.6148.4193.7OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 9400 Joules per run.2. EPYC 7773X: Approximate power consumption of 5144 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: DeepcoinEPYC 7773X 2PEPYC 7773X14K28K42K56K70KMin: 76870 / Avg: 81774 / Max: 92080Min: 47850 / Avg: 47973.33 / Max: 480901. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773X40K80K120K160K200KSE +/- 131.31, N = 3SE +/- 47.00, N = 387065.33173749.581. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.21.1Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773X2004006008001000270.121112.78
MinAvgMaxEPYC 7773X 2P75.5322.3345.9EPYC 7773X34.1156.1169.2OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.21.1CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 31050 Joules per run.2. EPYC 7773X: Approximate power consumption of 15094 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 1000EPYC 7773X 2PEPYC 7773X30K60K90K120K150KMin: 86933.42 / Avg: 87065.33 / Max: 87327.95Min: 173660.66 / Avg: 173749.58 / Max: 173820.441. (CC) gcc options: -lcrypt -lz -O3 -march=native

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500EPYC 7773X 2PEPYC 7773X40K80K120K160K200KSE +/- 120.41, N = 3SE +/- 178.28, N = 385974.99174606.511. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.21.1Concurrent Requests: 500EPYC 7773X 2PEPYC 7773X2004006008001000267.551104.73
MinAvgMaxEPYC 7773X 2P78.1321.3344.2EPYC 7773X34.1158.1169.9OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.21.1CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 30956 Joules per run.2. EPYC 7773X: Approximate power consumption of 15279 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 500EPYC 7773X 2PEPYC 7773X30K60K90K120K150KMin: 85755.68 / Avg: 85974.99 / Max: 86170.79Min: 174266.33 / Avg: 174606.51 / Max: 174869.151. (CC) gcc options: -lcrypt -lz -O3 -march=native

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200EPYC 7773X 2PEPYC 7773X40K80K120K160K200KSE +/- 126.91, N = 3SE +/- 275.30, N = 387686.13173501.451. (CC) gcc options: -lcrypt -lz -O3 -march=native
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.21.1Concurrent Requests: 200EPYC 7773X 2PEPYC 7773X2004006008001000279.751099.04
MinAvgMaxEPYC 7773X 2P76.3313.4337.6EPYC 7773X33.9157.9170.0OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.21.1CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 30195 Joules per run.2. EPYC 7773X: Approximate power consumption of 15260 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.21.1Concurrent Requests: 200EPYC 7773X 2PEPYC 7773X30K60K90K120K150KMin: 87474 / Avg: 87686.13 / Max: 87912.91Min: 173055.85 / Avg: 173501.45 / Max: 174004.331. (CC) gcc options: -lcrypt -lz -O3 -march=native

Apache HTTP Server

This is a test of the Apache HTTPD web server. This Apache HTTPD web server benchmark test profile makes use of the Golang "Bombardier" program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200EPYC 7773X 2PEPYC 7773X30K60K90K120K150KSE +/- 1253.21, N = 3SE +/- 459.18, N = 3117068.34133507.871. (CC) gcc options: -shared -fPIC -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200EPYC 7773X 2PEPYC 7773X130260390520650291.40593.26
MinAvgMaxEPYC 7773X 2P76.6401.7443.4EPYC 7773X34.0225.0241.7OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.48CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 38702 Joules per run.2. EPYC 7773X: Approximate power consumption of 21679 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterApache HTTP Server 2.4.48Concurrent Requests: 200EPYC 7773X 2PEPYC 7773X20K40K60K80K100KMin: 114566.83 / Avg: 117068.34 / Max: 118454.8Min: 132622.32 / Avg: 133507.87 / Max: 134161.321. (CC) gcc options: -shared -fPIC -O2

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPUEPYC 7773X 2PEPYC 7773X110K220K330K440K550KSE +/- 548.86, N = 3SE +/- 26.49, N = 3528284.42265124.941. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second Per Watt, More Is BetterSysbench 1.0.20Test: CPUEPYC 7773X 2PEPYC 7773X20040060080010001130.911140.37
MinAvgMaxEPYC 7773X 2P79.2467.1498.2EPYC 7773X34.2232.5242.8OpenBenchmarking.orgWatts, Fewer Is BetterSysbench 1.0.20CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 43599 Joules per run.2. EPYC 7773X: Approximate power consumption of 21777 Joules per run.
OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 1.0.20Test: CPUEPYC 7773X 2PEPYC 7773X90K180K270K360K450KMin: 527604.73 / Avg: 528284.42 / Max: 529370.77Min: 265072.82 / Avg: 265124.94 / Max: 265159.291. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X714212835SE +/- 0.17, N = 15SE +/- 0.05, N = 321.9527.761. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.04390.08780.13170.17560.21950.0970.195
MinAvgMaxEPYC 7773X 2P76.3227.4282.9EPYC 7773X34.3142.0187.1OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor701402102803501. EPYC 7773X 2P: Approximate power consumption of 7184 Joules per run.2. EPYC 7773X: Approximate power consumption of 3645 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X612182430Min: 20.88 / Avg: 21.95 / Max: 23.34Min: 27.65 / Avg: 27.76 / Max: 27.821. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0EPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.27, N = 3SE +/- 0.10, N = 377.1276.491. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 7773X 2P68.1208.4424.6EPYC 7773X34.4135.3286.4OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.10CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 16879 Joules per run.2. EPYC 7773X: Approximate power consumption of 10915 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0EPYC 7773X 2PEPYC 7773X1530456075Min: 76.66 / Avg: 77.12 / Max: 77.6Min: 76.3 / Avg: 76.49 / Max: 76.631. (CXX) g++ options: -O3 -fPIC -lm

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.05, N = 3SE +/- 0.07, N = 348.8195.33
MinAvgMaxEPYC 7773X 2P76.9515.4572.7EPYC 7773X35.0255.0269.7OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 27318 Joules per run.2. EPYC 7773X: Approximate power consumption of 25416 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X20406080100Min: 48.71 / Avg: 48.81 / Max: 48.87Min: 95.24 / Avg: 95.33 / Max: 95.47

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.17, N = 3SE +/- 0.11, N = 314.049.21MIN: 13.1 / MAX: 17.6MIN: 8.85 / MAX: 9.82
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUEPYC 7773X 2PEPYC 7773X0.00810.01620.02430.03240.04050.0260.036
MinAvgMaxEPYC 7773X 2P75.6534.0578.7EPYC 7773X34.1257.3279.4OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor1603204806408001. EPYC 7773X 2P: Approximate power consumption of 34712 Joules per run.2. EPYC 7773X: Approximate power consumption of 16813 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUEPYC 7773X 2PEPYC 7773X48121620Min: 13.78 / Avg: 14.04 / Max: 14.35Min: 9 / Avg: 9.21 / Max: 9.36

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read Random Write RandomEPYC 7773X 2PEPYC 7773X900K1800K2700K3600K4500KSE +/- 5452.38, N = 3SE +/- 20018.04, N = 3298720243055491. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterFacebook RocksDB 7.0.1Test: Read Random Write RandomEPYC 7773X 2PEPYC 7773X3K6K9K12K15K7031.6016100.67
MinAvgMaxEPYC 7773X 2P76.5424.8488.8EPYC 7773X35.0267.4286.8OpenBenchmarking.orgWatts, Fewer Is BetterFacebook RocksDB 7.0.1CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 27330 Joules per run.2. EPYC 7773X: Approximate power consumption of 17025 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Read Random Write RandomEPYC 7773X 2PEPYC 7773X700K1400K2100K2800K3500KMin: 2977459 / Avg: 2987202.33 / Max: 2996315Min: 4283693 / Avg: 4305549 / Max: 43455271. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianEPYC 7773X 2PEPYC 7773X130260390520650SE +/- 4.84, N = 3SE +/- 1.33, N = 36015901. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianEPYC 7773X 2PEPYC 7773X0.95241.90482.85723.80964.7622.3224.233
MinAvgMaxEPYC 7773X 2P75.8258.8280.9EPYC 7773X34.6139.4149.3OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.33CPU Power Consumption Monitor701402102803501. EPYC 7773X 2P: Approximate power consumption of 16478 Joules per run.2. EPYC 7773X: Approximate power consumption of 8967 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianEPYC 7773X 2PEPYC 7773X110220330440550Min: 591 / Avg: 600.67 / Max: 606Min: 587 / Avg: 589.67 / Max: 5911. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenEPYC 7773X 2PEPYC 7773X2004006008001000SE +/- 1.45, N = 3SE +/- 0.67, N = 38815891. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.33Operation: SharpenEPYC 7773X 2PEPYC 7773X0.51821.03641.55462.07282.5911.9432.303
MinAvgMaxEPYC 7773X 2P76.6453.4487.4EPYC 7773X35.2255.7274.2OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.33CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 28867 Joules per run.2. EPYC 7773X: Approximate power consumption of 16367 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenEPYC 7773X 2PEPYC 7773X150300450600750Min: 878 / Avg: 880.67 / Max: 883Min: 588 / Avg: 588.67 / Max: 5901. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceEPYC 7773X 2PEPYC 7773X2004006008001000SE +/- 1.53, N = 3SE +/- 0.88, N = 36858481. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceEPYC 7773X 2PEPYC 7773X2468103.2488.845
MinAvgMaxEPYC 7773X 2P77.1210.9229.4EPYC 7773X34.395.9103.8OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.33CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 13498 Joules per run.2. EPYC 7773X: Approximate power consumption of 6136 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceEPYC 7773X 2PEPYC 7773X150300450600750Min: 682 / Avg: 685 / Max: 687Min: 847 / Avg: 848.33 / Max: 8501. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

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.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7773X 2PEPYC 7773X400K800K1200K1600K2000KSE +/- 260.75, N = 3SE +/- 187.94, N = 31784848.5886927.91. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgverify/s Per Watt, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7773X 2PEPYC 7773X70014002100280035003422.753386.05
MinAvgMaxEPYC 7773X 2P77.0521.5556.3EPYC 7773X35.1261.9279.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 33200 Joules per run.2. EPYC 7773X: Approximate power consumption of 16764 Joules per run.
OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7773X 2PEPYC 7773X300K600K900K1200K1500KMin: 1784468.7 / Avg: 1784848.5 / Max: 1785347.9Min: 886712.8 / Avg: 886927.9 / Max: 887302.41. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7773X 2PEPYC 7773X6K12K18K24K30KSE +/- 27.52, N = 3SE +/- 11.72, N = 327099.313493.21. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7773X 2PEPYC 7773X5K10K15K20K25KMin: 27044.3 / Avg: 27099.27 / Max: 27129.1Min: 13471.2 / Avg: 13493.2 / Max: 13511.21. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Random ReadEPYC 7773X 2PEPYC 7773X120M240M360M480M600MSE +/- 520325.54, N = 3SE +/- 151537.43, N = 35524775392770758791. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterFacebook RocksDB 7.0.1Test: Random ReadEPYC 7773X 2PEPYC 7773X200K400K600K800K1000K1161305.261159352.26
MinAvgMaxEPYC 7773X 2P76.3475.7513.4EPYC 7773X34.5239.0254.5OpenBenchmarking.orgWatts, Fewer Is BetterFacebook RocksDB 7.0.1CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 30289 Joules per run.2. EPYC 7773X: Approximate power consumption of 15375 Joules per run.
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.0.1Test: Random ReadEPYC 7773X 2PEPYC 7773X100M200M300M400M500MMin: 551501793 / Avg: 552477539.33 / Max: 553278710Min: 276872032 / Avg: 277075878.67 / Max: 2773720331. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedEPYC 7773X 2PEPYC 7773X30060090012001500SE +/- 1.86, N = 3SE +/- 0.88, N = 3143110471. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedEPYC 7773X 2PEPYC 7773X0.9451.892.8353.784.7253.334.20
MinAvgMaxEPYC 7773X 2P75.2429.7461.2EPYC 7773X35.5249.3265.4OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.33CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 27501 Joules per run.2. EPYC 7773X: Approximate power consumption of 15873 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedEPYC 7773X 2PEPYC 7773X2004006008001000Min: 1429 / Avg: 1431.33 / Max: 1435Min: 1046 / Avg: 1047.33 / Max: 10491. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlEPYC 7773X 2PEPYC 7773X5001000150020002500SE +/- 19.04, N = 3SE +/- 11.85, N = 3243521611. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.33Operation: SwirlEPYC 7773X 2PEPYC 7773X36912156.0609.128
MinAvgMaxEPYC 7773X 2P76.3401.8431.7EPYC 7773X34.7236.7258.3OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.33CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 25581 Joules per run.2. EPYC 7773X: Approximate power consumption of 15151 Joules per run.
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlEPYC 7773X 2PEPYC 7773X400800120016002000Min: 2397 / Avg: 2435 / Max: 2456Min: 2138 / Avg: 2160.67 / Max: 21781. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Classroom - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.04, N = 3SE +/- 0.05, N = 338.7976.41
MinAvgMaxEPYC 7773X 2P76.8503.3566.3EPYC 7773X34.9253.9269.7OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 21809 Joules per run.2. EPYC 7773X: Approximate power consumption of 20480 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Classroom - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X1530456075Min: 38.72 / Avg: 38.79 / Max: 38.87Min: 76.32 / Avg: 76.41 / Max: 76.49

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: defconfigEPYC 7773X 2PEPYC 7773X612182430SE +/- 0.17, N = 9SE +/- 0.28, N = 519.9826.68
MinAvgMaxEPYC 7773X 2P75.7253.4573.8EPYC 7773X34.3155.7286.7OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 5.18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 7125 Joules per run.2. EPYC 7773X: Approximate power consumption of 5511 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.18Build: defconfigEPYC 7773X 2PEPYC 7773X612182430Min: 19.72 / Avg: 19.98 / Max: 21.29Min: 26.35 / Avg: 26.68 / Max: 27.8

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7773X 2PEPYC 7773X2K4K6K8K10KSE +/- 162.83, N = 15SE +/- 30.95, N = 310096.215329.651. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7773X 2PEPYC 7773X51015202522.6421.40
MinAvgMaxEPYC 7773X 2P74.2445.9572.9EPYC 7773X34.1249.1286.6OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 8234 Joules per run.2. EPYC 7773X: Approximate power consumption of 7556 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7773X 2PEPYC 7773X2K4K6K8K10KMin: 8962.74 / Avg: 10096.21 / Max: 10685.1Min: 5272.97 / Avg: 5329.65 / Max: 5379.521. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 22.1Input: Carbon NanotubeEPYC 7773X 2PEPYC 7773X1326395265SE +/- 0.15, N = 3SE +/- 0.32, N = 337.7658.071. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
MinAvgMaxEPYC 7773X 2P73.4475.7568.7EPYC 7773X33.6248.2285.9OpenBenchmarking.orgWatts, Fewer Is BetterGPAW 22.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 20454 Joules per run.2. EPYC 7773X: Approximate power consumption of 15555 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 22.1Input: Carbon NanotubeEPYC 7773X 2PEPYC 7773X1122334455Min: 37.46 / Avg: 37.76 / Max: 37.94Min: 57.43 / Avg: 58.07 / Max: 58.411. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETEPYC 7773X 2PEPYC 7773X500K1000K1500K2000K2500KSE +/- 21745.09, N = 15SE +/- 23060.14, N = 52402083.072297790.301. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 6.0.9Test: GETEPYC 7773X 2PEPYC 7773X12K24K36K48K60K26186.7154198.17
MinAvgMaxEPYC 7773X 2P74.091.7136.9EPYC 7773X33.742.469.7OpenBenchmarking.orgWatts, Fewer Is BetterRedis 6.0.9CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 1663 Joules per run.2. EPYC 7773X: Approximate power consumption of 780 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETEPYC 7773X 2PEPYC 7773X400K800K1200K1600K2000KMin: 2255314.5 / Avg: 2402083.07 / Max: 2500625Min: 2229704.25 / Avg: 2297790.3 / Max: 2365214.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19EPYC 7773X 2PEPYC 7773X1428425670SE +/- 0.07, N = 3SE +/- 0.08, N = 333.9060.39
MinAvgMaxEPYC 7773X 2P76.8424.6555.7EPYC 7773X33.9239.1278.2OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 16134 Joules per run.2. EPYC 7773X: Approximate power consumption of 15381 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 4 + Zstd Compression 19EPYC 7773X 2PEPYC 7773X1224364860Min: 33.79 / Avg: 33.9 / Max: 34.04Min: 60.25 / Avg: 60.39 / Max: 60.51

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1530456075SE +/- 0.66, N = 15SE +/- 0.49, N = 1255.8568.231. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.4Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.16670.33340.50010.66680.83350.3260.741
MinAvgMaxEPYC 7773X 2P77.6171.6221.9EPYC 7773X34.192.1120.6OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.4CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 2631 Joules per run.2. EPYC 7773X: Approximate power consumption of 1228 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1326395265Min: 51.97 / Avg: 55.85 / Max: 61.04Min: 65.76 / Avg: 68.23 / Max: 70.231. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.03, N = 3SE +/- 0.02, N = 317.5310.931. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.01040.02080.03120.04160.0520.0380.046
MinAvgMaxEPYC 7773X 2P74.4460.5573.3EPYC 7773X34.2239.6285.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 19186 Joules per run.2. EPYC 7773X: Approximate power consumption of 14695 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X48121620Min: 17.49 / Avg: 17.53 / Max: 17.58Min: 10.9 / Avg: 10.93 / Max: 10.971. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 7773X 2PEPYC 7773X612182430SE +/- 0.32, N = 15SE +/- 0.70, N = 1519.0423.38MIN: 16.18 / MAX: 20.84MIN: 18.62 / MAX: 26.34
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 7773X 2PEPYC 7773X0.02930.05860.08790.11720.14650.0610.130
MinAvgMaxEPYC 7773X 2P76.4310.7438.2EPYC 7773X35.0179.7280.3OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 4371 Joules per run.2. EPYC 7773X: Approximate power consumption of 2252 Joules per run.
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 7773X 2PEPYC 7773X510152025Min: 17.49 / Avg: 19.04 / Max: 20.58Min: 20.22 / Avg: 23.38 / Max: 26.22

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.83361.66722.50083.33444.168SE +/- 0.015, N = 3SE +/- 0.014, N = 33.7053.7041. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.00560.01120.01680.02240.0280.0160.025
MinAvgMaxEPYC 7773X 2P75.1237.6354.5EPYC 7773X34.4146.0220.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.0CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 11880 Joules per run.2. EPYC 7773X: Approximate power consumption of 7104 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X246810Min: 3.69 / Avg: 3.71 / Max: 3.74Min: 3.68 / Avg: 3.7 / Max: 3.731. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETEPYC 7773X 2PEPYC 7773X400K800K1200K1600K2000KSE +/- 33749.09, N = 13SE +/- 12740.72, N = 41849652.541862390.471. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 6.0.9Test: SETEPYC 7773X 2PEPYC 7773X9K18K27K36K45K19608.0742504.85
MinAvgMaxEPYC 7773X 2P74.194.3136.6EPYC 7773X33.643.869.5OpenBenchmarking.orgWatts, Fewer Is BetterRedis 6.0.9CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 1836 Joules per run.2. EPYC 7773X: Approximate power consumption of 865 Joules per run.
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETEPYC 7773X 2PEPYC 7773X300K600K900K1200K1500KMin: 1736730.88 / Avg: 1849652.54 / Max: 2196906.75Min: 1838585 / Avg: 1862390.47 / Max: 1893288.881. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteEPYC 7773X 2PEPYC 7773X1020304050SE +/- 0.16, N = 3SE +/- 0.55, N = 343.7540.281. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxEPYC 7773X 2P74.3243.3270.3EPYC 7773X33.8166.8194.7OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor701402102803501. EPYC 7773X 2P: Approximate power consumption of 11598 Joules per run.2. EPYC 7773X: Approximate power consumption of 7338 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LeukocyteEPYC 7773X 2PEPYC 7773X918273645Min: 43.44 / Avg: 43.75 / Max: 43.96Min: 39.26 / Avg: 40.28 / Max: 41.141. (CXX) g++ options: -O2 -lOpenCL

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedEPYC 7773X 2PEPYC 7773X7001400210028003500SE +/- 40.59, N = 3SE +/- 41.59, N = 33320.73293.91. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedEPYC 7773X 2PEPYC 7773X71421283519.1531.90
MinAvgMaxEPYC 7773X 2P75.6173.4266.1EPYC 7773X34.7103.3173.3OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.0CPU Power Consumption Monitor701402102803501. EPYC 7773X 2P: Approximate power consumption of 7975 Joules per run.2. EPYC 7773X: Approximate power consumption of 4784 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedEPYC 7773X 2PEPYC 7773X6001200180024003000Min: 3240 / Avg: 3320.67 / Max: 3368.9Min: 3249.9 / Avg: 3293.87 / Max: 33771. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.28, N = 3SE +/- 1.17, N = 3107.5103.51. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedEPYC 7773X 2PEPYC 7773X20406080100Min: 106.9 / Avg: 107.47 / Max: 107.8Min: 102.2 / Avg: 103.47 / Max: 105.81. (CC) gcc options: -O3 -pthread -lz -llzma

miniFE

MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 7773X 2PEPYC 7773X5K10K15K20K25KSE +/- 385.10, N = 12SE +/- 41.69, N = 424565.622670.91. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
OpenBenchmarking.orgCG Mflops Per Watt, More Is BetterminiFE 2.2Problem Size: SmallEPYC 7773X 2PEPYC 7773X30609012015088.38150.31
MinAvgMaxEPYC 7773X 2P72.4278.0465.9EPYC 7773X34.9150.8231.2OpenBenchmarking.orgWatts, Fewer Is BetterminiFE 2.2CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 5397 Joules per run.2. EPYC 7773X: Approximate power consumption of 3017 Joules per run.
OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallEPYC 7773X 2PEPYC 7773X4K8K12K16K20KMin: 22286.7 / Avg: 24565.6 / Max: 26643.8Min: 22589.8 / Avg: 22670.9 / Max: 22754.61. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2EPYC 7773X 2PEPYC 7773X1020304050SE +/- 0.13, N = 3SE +/- 0.02, N = 341.6840.701. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 7773X 2P74.6186.3402.4EPYC 7773X34.1118.0286.5OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.10CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 8568 Joules per run.2. EPYC 7773X: Approximate power consumption of 5272 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2EPYC 7773X 2PEPYC 7773X918273645Min: 41.45 / Avg: 41.68 / Max: 41.92Min: 40.66 / Avg: 40.7 / Max: 40.731. (CXX) g++ options: -O3 -fPIC -lm

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1122334455SE +/- 0.37, N = 4SE +/- 0.40, N = 1541.3150.601. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.4Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.10910.21820.32730.43640.54550.2230.485
MinAvgMaxEPYC 7773X 2P76.7185.4223.4EPYC 7773X34.3104.2131.8OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.4CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 3523 Joules per run.2. EPYC 7773X: Approximate power consumption of 1703 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1020304050Min: 40.38 / Avg: 41.31 / Max: 42.18Min: 47.8 / Avg: 50.6 / Max: 52.621. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Zstd Compression

This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedEPYC 7773X 2PEPYC 7773X7001400210028003500SE +/- 0.84, N = 3SE +/- 11.85, N = 33308.93316.71. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s Per Watt, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedEPYC 7773X 2PEPYC 7773X91827364520.7237.60
MinAvgMaxEPYC 7773X 2P76.8159.7217.0EPYC 7773X34.388.2127.5OpenBenchmarking.orgWatts, Fewer Is BetterZstd Compression 1.5.0CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 6921 Joules per run.2. EPYC 7773X: Approximate power consumption of 3852 Joules per run.
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedEPYC 7773X 2PEPYC 7773X6001200180024003000Min: 3307.4 / Avg: 3308.9 / Max: 3310.3Min: 3303 / Avg: 3316.7 / Max: 3340.31. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedEPYC 7773X 2PEPYC 7773X1326395265SE +/- 0.43, N = 3SE +/- 0.20, N = 358.957.81. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedEPYC 7773X 2PEPYC 7773X1224364860Min: 58 / Avg: 58.87 / Max: 59.3Min: 57.6 / Avg: 57.8 / Max: 58.21. (CC) gcc options: -O3 -pthread -lz -llzma

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileEPYC 7773X 2PEPYC 7773X918273645SE +/- 0.16, N = 3SE +/- 0.09, N = 338.0839.65
MinAvgMaxEPYC 7773X 2P76.7254.8569.7EPYC 7773X33.8164.6286.7OpenBenchmarking.orgWatts, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 10957 Joules per run.2. EPYC 7773X: Approximate power consumption of 7354 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To CompileEPYC 7773X 2PEPYC 7773X816243240Min: 37.8 / Avg: 38.08 / Max: 38.34Min: 39.48 / Avg: 39.65 / Max: 39.81

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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUEPYC 7773X 2PEPYC 7773X714212835SE +/- 0.05, N = 4SE +/- 0.17, N = 1529.7611.60MIN: 23.56MIN: 9.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
MinAvgMaxEPYC 7773X 2P77.4245.1309.9EPYC 7773X34.3115.6154.3OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 2.6CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 3983 Joules per run.2. EPYC 7773X: Approximate power consumption of 1865 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.6Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUEPYC 7773X 2PEPYC 7773X714212835Min: 29.65 / Avg: 29.76 / Max: 29.91Min: 10.29 / Avg: 11.6 / Max: 12.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 7773X 2PEPYC 7773X918273645SE +/- 0.01, N = 3SE +/- 0.03, N = 337.6537.631. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff
MinAvgMaxEPYC 7773X 2P75.7132.1143.4EPYC 7773X34.167.475.2OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.1CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 5548 Joules per run.2. EPYC 7773X: Approximate power consumption of 2809 Joules per run.
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 7773X 2PEPYC 7773X816243240Min: 37.63 / Avg: 37.65 / Max: 37.68Min: 37.58 / Avg: 37.63 / Max: 37.681. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

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 9Input: motorBike - Execution TimeEPYC 7773X 2PEPYC 7773X163248648071.0961.561. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 7773X35.098.2107.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 9CPU Power Consumption Monitor20406080100

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 9Input: motorBike - Mesh TimeEPYC 7773X 2PEPYC 7773X91827364540.6438.721. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -ldynamicMesh -ldecompose -lgenericPatchFields -lmetisDecomp -lscotchDecomp -llagrangian -lregionModels -lOpenFOAM -ldl -lm

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 7773X 2PEPYC 7773X400M800M1200M1600M2000MSE +/- 948996.49, N = 3SE +/- 200642.30, N = 3200191600010532460001. (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 7773X 2PEPYC 7773X1.1M2.2M3.3M4.4M5.5M4656882.105270168.88
MinAvgMaxEPYC 7773X 2P73.7429.9559.9EPYC 7773X34.2199.9263.4OpenBenchmarking.orgWatts, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 17625 Joules per run.2. EPYC 7773X: Approximate power consumption of 7661 Joules per run.
OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2EPYC 7773X 2PEPYC 7773X300M600M900M1200M1500MMin: 2000202000 / Avg: 2001916000 / Max: 2003479000Min: 1052910000 / Avg: 1053246000 / Max: 10536040001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1632486480SE +/- 0.82, N = 15SE +/- 0.48, N = 557.0470.251. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.4Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.17170.34340.51510.68680.85850.3310.763
MinAvgMaxEPYC 7773X 2P76.5172.2220.1EPYC 7773X34.192.1122.3OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.4CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 2606 Joules per run.2. EPYC 7773X: Approximate power consumption of 1215 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1428425670Min: 51.54 / Avg: 57.04 / Max: 62.92Min: 69.24 / Avg: 70.25 / Max: 71.521. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDEPYC 7773X 2PEPYC 7773X1020304050SE +/- 0.11, N = 3SE +/- 0.08, N = 325.2344.431. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxEPYC 7773X 2P75.0383.5527.1EPYC 7773X34.3218.6259.1OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 11248 Joules per run.2. EPYC 7773X: Approximate power consumption of 10493 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDEPYC 7773X 2PEPYC 7773X918273645Min: 25.04 / Avg: 25.23 / Max: 25.4Min: 44.28 / Avg: 44.43 / Max: 44.531. (CXX) g++ options: -O2 -lOpenCL

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096EPYC 7773X 2PEPYC 7773X0.21150.4230.63450.8461.0575SE +/- 0.01, N = 3SE +/- 0.00, N = 30.940.80
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096EPYC 7773X 2PEPYC 7773X0.00090.00180.00270.00360.00450.0030.004
MinAvgMaxEPYC 7773X 2P75.4307.9489.6EPYC 7773X34.3178.0275.3OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 1.4.0CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 11289 Joules per run.2. EPYC 7773X: Approximate power consumption of 7417 Joules per run.
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096EPYC 7773X 2PEPYC 7773X246810Min: 0.94 / Avg: 0.94 / Max: 0.95Min: 0.8 / Avg: 0.8 / Max: 0.8

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.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 7773X 2PEPYC 7773X1428425670SE +/- 0.32, N = 5SE +/- 0.66, N = 1554.3661.281. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 7773X 2PEPYC 7773X0.09050.1810.27150.3620.45250.2220.402
MinAvgMaxEPYC 7773X 2P76.4244.9324.2EPYC 7773X34.5152.3217.9OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 3674 Joules per run.2. EPYC 7773X: Approximate power consumption of 2112 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 7773X 2PEPYC 7773X1224364860Min: 53.57 / Avg: 54.36 / Max: 55.28Min: 57.23 / Avg: 61.28 / Max: 65.21. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 7773X 2PEPYC 7773X15K30K45K60K75KSE +/- 395.30, N = 3SE +/- 204.47, N = 370367.535783.61. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec Per Watt, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 7773X 2PEPYC 7773X4080120160200163.67168.51
MinAvgMaxEPYC 7773X 2P74.5429.9549.4EPYC 7773X34.5212.4272.3OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 15908 Joules per run.2. EPYC 7773X: Approximate power consumption of 7574 Joules per run.
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingEPYC 7773X 2PEPYC 7773X12K24K36K48K60KMin: 69972.2 / Avg: 70367.5 / Max: 71158.1Min: 35579.1 / Avg: 35783.57 / Max: 36192.51. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 7773X 2PEPYC 7773X13K26K39K52K65KSE +/- 307.17, N = 3SE +/- 0.00, N = 362354.431805.51. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingEPYC 7773X 2PEPYC 7773X11K22K33K44K55KMin: 61740.1 / Avg: 62354.43 / Max: 62661.6Min: 31805.5 / Avg: 31805.5 / Max: 31805.51. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of StateEPYC 7773X 2PEPYC 7773X0.20120.40240.60360.80481.006SE +/- 0.001, N = 3SE +/- 0.003, N = 30.8940.873
MinAvgMaxEPYC 7773X 2P74.7146.0177.5EPYC 7773X33.681.5109.2OpenBenchmarking.orgWatts, Fewer Is BetterPyHPC Benchmarks 3.0CPU Power Consumption Monitor501001502002501. EPYC 7773X 2P: Approximate power consumption of 5257 Joules per run.2. EPYC 7773X: Approximate power consumption of 2851 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of StateEPYC 7773X 2PEPYC 7773X246810Min: 0.89 / Avg: 0.89 / Max: 0.9Min: 0.87 / Avg: 0.87 / Max: 0.88

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 2022.1Implementation: MPI CPU - Input: water_GMX50_bareEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.008, N = 3SE +/- 0.022, N = 311.0747.2101. (CXX) g++ options: -O3
OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_bareEPYC 7773X 2PEPYC 7773X0.00650.0130.01950.0260.03250.0230.029
MinAvgMaxEPYC 7773X 2P75.6477.8572.9EPYC 7773X35.1249.3286.9OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2022.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 15448 Joules per run.2. EPYC 7773X: Approximate power consumption of 9558 Joules per run.
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_bareEPYC 7773X 2PEPYC 7773X3691215Min: 11.06 / Avg: 11.07 / Max: 11.09Min: 7.17 / Avg: 7.21 / Max: 7.251. (CXX) g++ options: -O3

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: MagiEPYC 7773X 2PEPYC 7773X10002000300040005000SE +/- 4.06, N = 3SE +/- 2.00, N = 34517.512230.721. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: MagiEPYC 7773X 2PEPYC 7773X36912159.7528.997
MinAvgMaxEPYC 7773X 2P75.3463.2572.9EPYC 7773X34.7247.9284.1OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 16213 Joules per run.2. EPYC 7773X: Approximate power consumption of 8595 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: MagiEPYC 7773X 2PEPYC 7773X8001600240032004000Min: 4509.57 / Avg: 4517.51 / Max: 4522.99Min: 2227.38 / Avg: 2230.72 / Max: 2234.311. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: x25xEPYC 7773X 2PEPYC 7773X6001200180024003000SE +/- 26.49, N = 3SE +/- 1.16, N = 32992.651548.221. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: x25xEPYC 7773X 2PEPYC 7773X2468106.3356.399
MinAvgMaxEPYC 7773X 2P74.5472.4572.9EPYC 7773X34.7241.9272.7OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 16219 Joules per run.2. EPYC 7773X: Approximate power consumption of 8468 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: x25xEPYC 7773X 2PEPYC 7773X5001000150020002500Min: 2944.63 / Avg: 2992.65 / Max: 3036.05Min: 1545.93 / Avg: 1548.22 / Max: 1549.71. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: RingcoinEPYC 7773X 2PEPYC 7773X10002000300040005000SE +/- 23.95, N = 3SE +/- 3.41, N = 33318.684667.601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: RingcoinEPYC 7773X 2PEPYC 7773X61218243010.6924.44
MinAvgMaxEPYC 7773X 2P78.7310.4373.4EPYC 7773X34.0191.0229.0OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 10864 Joules per run.2. EPYC 7773X: Approximate power consumption of 6620 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: RingcoinEPYC 7773X 2PEPYC 7773X8001600240032004000Min: 3279.97 / Avg: 3318.68 / Max: 3362.48Min: 4661.53 / Avg: 4667.6 / Max: 4673.311. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Myriad-GroestlEPYC 7773X 2PEPYC 7773X3K6K9K12K15KSE +/- 179.38, N = 3SE +/- 53.33, N = 313373144671. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: Myriad-GroestlEPYC 7773X 2PEPYC 7773X2040608010052.50107.63
MinAvgMaxEPYC 7773X 2P78.4254.7311.8EPYC 7773X33.9134.4182.5OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 8915 Joules per run.2. EPYC 7773X: Approximate power consumption of 4705 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Myriad-GroestlEPYC 7773X 2PEPYC 7773X3K6K9K12K15KMin: 13120 / Avg: 13373.33 / Max: 13720Min: 14360 / Avg: 14466.67 / Max: 145201. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: GarlicoinEPYC 7773X 2PEPYC 7773X5K10K15K20K25KSE +/- 65.06, N = 3SE +/- 10.68, N = 324790.001603.521. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: GarlicoinEPYC 7773X 2PEPYC 7773X2040608010083.1857.397
MinAvgMaxEPYC 7773X 2P77.9298.0462.1EPYC 7773X33.9216.8247.0OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 10232 Joules per run.2. EPYC 7773X: Approximate power consumption of 7587 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: GarlicoinEPYC 7773X 2PEPYC 7773X4K8K12K16K20KMin: 24660 / Avg: 24790 / Max: 24860Min: 1592.69 / Avg: 1603.52 / Max: 1624.881. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Quad SHA-256, PyriteEPYC 7773X 2PEPYC 7773X200K400K600K800K1000KSE +/- 13218.24, N = 3SE +/- 36.67, N = 310370774539931. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: Quad SHA-256, PyriteEPYC 7773X 2PEPYC 7773X100020003000400050004763.574122.16
MinAvgMaxEPYC 7773X 2P77.0217.7387.4EPYC 7773X33.8110.1233.5OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 7620 Joules per run.2. EPYC 7773X: Approximate power consumption of 3855 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: Quad SHA-256, PyriteEPYC 7773X 2PEPYC 7773X200K400K600K800K1000KMin: 1010890 / Avg: 1037076.67 / Max: 1053310Min: 453920 / Avg: 453993.33 / Max: 4540301. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: SkeincoinEPYC 7773X 2PEPYC 7773X300K600K900K1200K1500KSE +/- 8275.58, N = 3SE +/- 4254.67, N = 313375474283301. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s Per Watt, More Is BetterCpuminer-Opt 3.18Algorithm: SkeincoinEPYC 7773X 2PEPYC 7773X130026003900520065006154.333852.47
MinAvgMaxEPYC 7773X 2P76.9217.3363.5EPYC 7773X34.2111.2213.5OpenBenchmarking.orgWatts, Fewer Is BetterCpuminer-Opt 3.18CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 7607 Joules per run.2. EPYC 7773X: Approximate power consumption of 3891 Joules per run.
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.18Algorithm: SkeincoinEPYC 7773X 2PEPYC 7773X200K400K600K800K1000KMin: 1324020 / Avg: 1337546.67 / Max: 1352570Min: 422660 / Avg: 428330 / Max: 4366601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Aircrack-ng

Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.2EPYC 7773X 2PEPYC 7773X40K80K120K160K200KSE +/- 829.37, N = 3SE +/- 951.80, N = 3196064.50174912.581. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
OpenBenchmarking.orgk/s Per Watt, More Is BetterAircrack-ng 1.5.2EPYC 7773X 2PEPYC 7773X150300450600750415.38695.51
MinAvgMaxEPYC 7773X 2P74.8472.0533.1EPYC 7773X34.0251.5286.7OpenBenchmarking.orgWatts, Fewer Is BetterAircrack-ng 1.5.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 16206 Joules per run.2. EPYC 7773X: Approximate power consumption of 8634 Joules per run.
OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.2EPYC 7773X 2PEPYC 7773X30K60K90K120K150KMin: 194413.7 / Avg: 196064.49 / Max: 197030.33Min: 173757.48 / Avg: 174912.58 / Max: 176800.51. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X918273645SE +/- 0.11, N = 3SE +/- 0.03, N = 319.7937.63
MinAvgMaxEPYC 7773X 2P76.0448.0570.8EPYC 7773X34.9235.5268.1OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 11050 Joules per run.2. EPYC 7773X: Approximate power consumption of 9893 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X816243240Min: 19.57 / Avg: 19.79 / Max: 19.95Min: 37.6 / Avg: 37.63 / Max: 37.69

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 7773X 2PEPYC 7773X11002200330044005500SE +/- 50.11, N = 15SE +/- 23.58, N = 45085.972913.881. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 7773X 2PEPYC 7773X4812162016.2115.60
MinAvgMaxEPYC 7773X 2P74.0313.8548.1EPYC 7773X34.4186.9280.8OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3724 Joules per run.2. EPYC 7773X: Approximate power consumption of 3270 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DEPYC 7773X 2PEPYC 7773X9001800270036004500Min: 4830.37 / Avg: 5085.97 / Max: 5438.38Min: 2876.7 / Avg: 2913.88 / Max: 2979.531. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

x264

This is a multi-threaded test of the x264 video encoder run on the CPU with a choice of 1080p or 4K video input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.54, N = 6SE +/- 1.20, N = 1572.9374.821. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx264 2022-02-22Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.10760.21520.32280.43040.5380.3100.478
MinAvgMaxEPYC 7773X 2P75.8235.1358.5EPYC 7773X34.3156.6261.5OpenBenchmarking.orgWatts, Fewer Is Betterx264 2022-02-22CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 2899 Joules per run.2. EPYC 7773X: Approximate power consumption of 1900 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2022-02-22Video Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1428425670Min: 71.4 / Avg: 72.93 / Max: 74.69Min: 58.56 / Avg: 74.82 / Max: 77.571. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBBEPYC 7773X 2PEPYC 7773X15003000450060007500SE +/- 28.15, N = 15SE +/- 53.34, N = 15366571261. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
MinAvgMaxEPYC 7773X 2P73.1292.9551.4EPYC 7773X34.8185.5277.4OpenBenchmarking.orgWatts, Fewer Is BettertoyBrot Fractal Generator 2020-11-18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 2246 Joules per run.2. EPYC 7773X: Approximate power consumption of 2065 Joules per run.
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: TBBEPYC 7773X 2PEPYC 7773X12002400360048006000Min: 3527 / Avg: 3665.2 / Max: 3920Min: 6902 / Avg: 7125.67 / Max: 76861. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MEPYC 7773X 2PEPYC 7773X9K18K27K36K45KSE +/- 194.70, N = 3SE +/- 30.70, N = 343888.335903.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MEPYC 7773X 2PEPYC 7773X30609012015092.78143.19
MinAvgMaxEPYC 7773X 2P77.4473.1575.2EPYC 7773X34.0250.7286.6OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.12.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 13561 Joules per run.2. EPYC 7773X: Approximate power consumption of 8275 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MEPYC 7773X 2PEPYC 7773X8K16K24K32K40KMin: 43516.1 / Avg: 43888.33 / Max: 44173.5Min: 35847.4 / Avg: 35903.67 / Max: 35953.11. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.82, N = 15SE +/- 0.06, N = 593.4570.93MIN: 83.86 / MAX: 101.24MIN: 69.44 / MAX: 73.45
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7773X 2PEPYC 7773X0.07810.15620.23430.31240.39050.2440.347
MinAvgMaxEPYC 7773X 2P76.1383.5573.3EPYC 7773X34.5204.4286.7OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.13CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 4449 Joules per run.2. EPYC 7773X: Approximate power consumption of 2739 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7773X 2PEPYC 7773X20406080100Min: 87.95 / Avg: 93.45 / Max: 98.55Min: 70.76 / Avg: 70.93 / Max: 71.12

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingEPYC 7773X 2PEPYC 7773X4K8K12K16K20KSE +/- 171.64, N = 5SE +/- 0.00, N = 1413593.119018.31. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second Per Watt, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingEPYC 7773X 2PEPYC 7773X70140210280350100.42302.71
MinAvgMaxEPYC 7773X 2P75.7135.4213.6EPYC 7773X33.862.8101.6OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 1949 Joules per run.2. EPYC 7773X: Approximate power consumption of 749 Joules per run.
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingEPYC 7773X 2PEPYC 7773X3K6K9K12K15KMin: 13312.8 / Avg: 13593.08 / Max: 14013.5Min: 19018.3 / Avg: 19018.3 / Max: 19018.31. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingEPYC 7773X 2PEPYC 7773X4K8K12K16K20KSE +/- 128.89, N = 5SE +/- 155.07, N = 1511786.820708.81. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingEPYC 7773X 2PEPYC 7773X4K8K12K16K20KMin: 11576.3 / Avg: 11786.78 / Max: 12102.5Min: 20481.2 / Avg: 20708.77 / Max: 221881. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 7773X 2PEPYC 7773X1.27042.54083.81125.08166.352SE +/- 0.058068, N = 15SE +/- 0.044579, N = 153.3937305.6460541. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxEPYC 7773X 2P74.0278.5561.9EPYC 7773X34.4165.8277.9OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 2303 Joules per run.2. EPYC 7773X: Approximate power consumption of 1680 Joules per run.
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 7773X 2PEPYC 7773X246810Min: 3.02 / Avg: 3.39 / Max: 3.86Min: 5.43 / Avg: 5.65 / Max: 6.021. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

Tachyon

This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. The sample scene used is the Teapot scene ray-traced to 8K x 8K with 32 samples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99.2Total TimeEPYC 7773X 2PEPYC 7773X714212835SE +/- 0.07, N = 4SE +/- 0.03, N = 315.4029.621. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
MinAvgMaxEPYC 7773X 2P75.7416.4547.8EPYC 7773X34.5233.9275.7OpenBenchmarking.orgWatts, Fewer Is BetterTachyon 0.99.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 8432 Joules per run.2. EPYC 7773X: Approximate power consumption of 7951 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99.2Total TimeEPYC 7773X 2PEPYC 7773X714212835Min: 15.27 / Avg: 15.4 / Max: 15.6Min: 29.57 / Avg: 29.62 / Max: 29.671. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported and HIP for AMD Radeon GPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: BMW27 - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X714212835SE +/- 0.03, N = 4SE +/- 0.04, N = 315.5129.47
MinAvgMaxEPYC 7773X 2P74.5435.1572.5EPYC 7773X35.0233.7269.3OpenBenchmarking.orgWatts, Fewer Is BetterBlender 3.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 8594 Joules per run.2. EPYC 7773X: Approximate power consumption of 7947 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.2Blend File: BMW27 - Compute: CPU-OnlyEPYC 7773X 2PEPYC 7773X714212835Min: 15.42 / Avg: 15.51 / Max: 15.58Min: 29.42 / Avg: 29.47 / Max: 29.55

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.81, N = 15SE +/- 0.44, N = 596.3677.86MIN: 88.29 / MAX: 104.54MIN: 75.45 / MAX: 79.73
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonEPYC 7773X 2PEPYC 7773X0.08840.17680.26520.35360.4420.2550.393
MinAvgMaxEPYC 7773X 2P47.2377.7572.8EPYC 7773X34.6198.2286.6OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.13CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 4305 Joules per run.2. EPYC 7773X: Approximate power consumption of 2457 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian DragonEPYC 7773X 2PEPYC 7773X20406080100Min: 91.71 / Avg: 96.36 / Max: 101.73Min: 76.68 / Avg: 77.86 / Max: 78.68

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEPYC 7773X 2PEPYC 7773X0.08590.17180.25770.34360.4295SE +/- 0.00014, N = 3SE +/- 0.00018, N = 30.225540.38169
MinAvgMaxEPYC 7773X 2P75.2484.8565.4EPYC 7773X34.0238.6285.0OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 2.14CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 15676 Joules per run.2. EPYC 7773X: Approximate power consumption of 6363 Joules per run.
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEPYC 7773X 2PEPYC 7773X12345Min: 0.23 / Avg: 0.23 / Max: 0.23Min: 0.38 / Avg: 0.38 / Max: 0.38

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.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: MediumEPYC 7773X 2PEPYC 7773X714212835SE +/- 0.10, N = 3SE +/- 0.03, N = 330.6419.161. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: MediumEPYC 7773X 2PEPYC 7773X0.02320.04640.06960.09280.1160.0880.103
MinAvgMaxEPYC 7773X 2P76.4346.9427.0EPYC 7773X34.3185.7222.6OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 8095 Joules per run.2. EPYC 7773X: Approximate power consumption of 6500 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: MediumEPYC 7773X 2PEPYC 7773X714212835Min: 30.47 / Avg: 30.64 / Max: 30.81Min: 19.13 / Avg: 19.16 / Max: 19.211. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterEPYC 7773X 2PEPYC 7773X246810SE +/- 0.118, N = 15SE +/- 0.038, N = 77.4735.6641. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxEPYC 7773X 2P74.6213.7355.9EPYC 7773X34.2111.0193.6OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 2451 Joules per run.2. EPYC 7773X: Approximate power consumption of 1078 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterEPYC 7773X 2PEPYC 7773X3691215Min: 6.82 / Avg: 7.47 / Max: 8.44Min: 5.54 / Avg: 5.66 / Max: 5.781. (CXX) g++ options: -O2 -lOpenCL

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MEPYC 7773X 2PEPYC 7773X11K22K33K44K55KSE +/- 231.73, N = 3SE +/- 58.89, N = 349710.639506.61. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MEPYC 7773X 2PEPYC 7773X4080120160200106.92158.88
MinAvgMaxEPYC 7773X 2P77.2464.9573.4EPYC 7773X35.2248.7286.6OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.12.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 12243 Joules per run.2. EPYC 7773X: Approximate power consumption of 7460 Joules per run.
OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MEPYC 7773X 2PEPYC 7773X9K18K27K36K45KMin: 49249 / Avg: 49710.57 / Max: 49977.5Min: 39396.4 / Avg: 39506.6 / Max: 39597.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X714212835SE +/- 0.17, N = 3SE +/- 0.33, N = 322.1030.481. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.06230.12460.18690.24920.31150.1160.277
MinAvgMaxEPYC 7773X 2P76.3190.9222.6EPYC 7773X34.1109.9127.9OpenBenchmarking.orgWatts, Fewer Is BetterAOM AV1 3.4CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 6047 Joules per run.2. EPYC 7773X: Approximate power consumption of 2637 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.4Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X714212835Min: 21.77 / Avg: 22.1 / Max: 22.36Min: 29.85 / Avg: 30.48 / Max: 30.981. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -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.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.94, N = 4SE +/- 0.06, N = 382.0771.23MIN: 74.39 / MAX: 90.19MIN: 69.67 / MAX: 73.01
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773X0.11250.2250.33750.450.56250.3090.500
MinAvgMaxEPYC 7773X 2P76.3265.4569.5EPYC 7773X34.6142.3286.7OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.13CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 6171 Joules per run.2. EPYC 7773X: Approximate power consumption of 3464 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773X1632486480Min: 79.52 / Avg: 82.07 / Max: 83.87Min: 71.13 / Avg: 71.23 / Max: 71.34

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X50100150200250SE +/- 2.92, N = 15SE +/- 0.57, N = 9177.70242.041. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.49430.98861.48291.97722.47150.9802.197
MinAvgMaxEPYC 7773X 2P76.6181.3367.6EPYC 7773X34.4110.2271.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 2103 Joules per run.2. EPYC 7773X: Approximate power consumption of 845 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X4080120160200Min: 166.62 / Avg: 177.7 / Max: 205.34Min: 240.1 / Avg: 242.04 / Max: 244.61. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

LULESH

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3EPYC 7773X 2PEPYC 7773X9K18K27K36K45KSE +/- 203.54, N = 3SE +/- 29.30, N = 342133.7322217.301. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
OpenBenchmarking.orgz/s Per Watt, More Is BetterLULESH 2.0.3EPYC 7773X 2PEPYC 7773X306090120150111.79119.17
MinAvgMaxEPYC 7773X 2P76.1376.9548.7EPYC 7773X35.6186.4267.3OpenBenchmarking.orgWatts, Fewer Is BetterLULESH 2.0.3CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 9673 Joules per run.2. EPYC 7773X: Approximate power consumption of 4537 Joules per run.
OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3EPYC 7773X 2PEPYC 7773X7K14K21K28K35KMin: 41735.7 / Avg: 42133.73 / Max: 42406.67Min: 22159.44 / Avg: 22217.3 / Max: 22254.231. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773X20406080100SE +/- 0.52, N = 3SE +/- 0.05, N = 382.6663.01MIN: 76.95 / MAX: 87.29MIN: 61.66 / MAX: 64.62
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773X0.09560.19120.28680.38240.4780.3030.425
MinAvgMaxEPYC 7773X 2P78.0272.4573.1EPYC 7773X34.6148.1286.8OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.13CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 6446 Joules per run.2. EPYC 7773X: Approximate power consumption of 3801 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 7773X 2PEPYC 7773X1632486480Min: 81.77 / Avg: 82.66 / Max: 83.57Min: 62.9 / Avg: 63.01 / Max: 63.07

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X4080120160200SE +/- 2.17, N = 15SE +/- 0.60, N = 8174.28193.541. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.47050.9411.41151.8822.35251.0732.091
MinAvgMaxEPYC 7773X 2P75.7162.3313.9EPYC 7773X34.192.6198.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.0CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 1743 Joules per run.2. EPYC 7773X: Approximate power consumption of 787 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X4080120160200Min: 161.96 / Avg: 174.28 / Max: 188.5Min: 190.21 / Avg: 193.54 / Max: 195.841. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

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 2021.01.31Threads: 256 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X1200M2400M3600M4800M6000MSE +/- 1241414.96, N = 3SE +/- 2542308.66, N = 3582603333329704000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 256 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X3M6M9M12M15M13362176.8813579038.54
MinAvgMaxEPYC 7773X 2P76.8436.0512.4EPYC 7773X34.6218.7257.0OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 10319 Joules per run.2. EPYC 7773X: Approximate power consumption of 5396 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 256 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X1000M2000M3000M4000M5000MMin: 5823900000 / Avg: 5826033333.33 / Max: 5828200000Min: 2966100000 / Avg: 2970400000 / Max: 29749000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X1200M2400M3600M4800M6000MSE +/- 9081911.20, N = 3SE +/- 1271918.94, N = 3555293333329120333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X3M6M9M12M15M12303109.6013427397.82
MinAvgMaxEPYC 7773X 2P74.6451.3534.8EPYC 7773X34.6216.9257.1OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 10832 Joules per run.2. EPYC 7773X: Approximate power consumption of 5205 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 128 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X1000M2000M3000M4000M5000MMin: 5538200000 / Avg: 5552933333.33 / Max: 5569500000Min: 2909900000 / Avg: 2912033333.33 / Max: 29143000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X700M1400M2100M2800M3500MSE +/- 4642317.43, N = 3SE +/- 2887521.04, N = 3334883333327730666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X3M6M9M12M15M8353346.3112157115.14
MinAvgMaxEPYC 7773X 2P76.0400.9469.1EPYC 7773X34.9228.1268.5OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 2021.01.31CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 9622 Joules per run.2. EPYC 7773X: Approximate power consumption of 5474 Joules per run.
OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 64 - Buffer Length: 256 - Filter Length: 57EPYC 7773X 2PEPYC 7773X600M1200M1800M2400M3000MMin: 3343700000 / Avg: 3348833333.33 / Max: 3358100000Min: 2768000000 / Avg: 2773066666.67 / Max: 27780000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160EPYC 7773X 2PEPYC 7773X0.43650.8731.30951.7462.1825SE +/- 0.01, N = 4SE +/- 0.00, N = 31.941.62
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160EPYC 7773X 2PEPYC 7773X0.00230.00460.00690.00920.01150.0070.010
MinAvgMaxEPYC 7773X 2P76.2291.7495.3EPYC 7773X34.4166.9277.8OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 1.4.0CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 5688 Joules per run.2. EPYC 7773X: Approximate power consumption of 3783 Joules per run.
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160EPYC 7773X 2PEPYC 7773X246810Min: 1.93 / Avg: 1.94 / Max: 1.95Min: 1.62 / Avg: 1.62 / Max: 1.63

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160EPYC 7773X 2PEPYC 7773X0.43880.87761.31641.75522.194SE +/- 0.01, N = 4SE +/- 0.00, N = 31.951.63
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160EPYC 7773X 2PEPYC 7773X0.00230.00460.00690.00920.01150.0070.010
MinAvgMaxEPYC 7773X 2P76.6288.4496.9EPYC 7773X34.4166.6278.4OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 1.4.0CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 5696 Joules per run.2. EPYC 7773X: Approximate power consumption of 3776 Joules per run.
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160EPYC 7773X 2PEPYC 7773X246810Min: 1.93 / Avg: 1.95 / Max: 1.98Min: 1.62 / Avg: 1.63 / Max: 1.63

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 7773X 2PEPYC 7773X1122334455SE +/- 0.40, N = 15SE +/- 0.26, N = 650.5629.411. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 7773X 2PEPYC 7773X0.03740.07480.11220.14960.1870.1660.161
MinAvgMaxEPYC 7773X 2P76.5304.7551.4EPYC 7773X34.3183.1281.7OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 2621 Joules per run.2. EPYC 7773X: Approximate power consumption of 2197 Joules per run.
OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 7773X 2PEPYC 7773X1020304050Min: 48.19 / Avg: 50.56 / Max: 52.95Min: 28.21 / Avg: 29.41 / Max: 30.061. (CC) gcc options: -O3 -march=native -fopenmp

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.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ExhaustiveEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.0015, N = 5SE +/- 0.0055, N = 45.931611.63871. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxEPYC 7773X 2P75.6293.6572.9EPYC 7773X33.8177.5272.1OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 3.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 4228 Joules per run.2. EPYC 7773X: Approximate power consumption of 3595 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ExhaustiveEPYC 7773X 2PEPYC 7773X3691215Min: 5.93 / Avg: 5.93 / Max: 5.94Min: 11.62 / Avg: 11.64 / Max: 11.651. (CXX) g++ options: -O3 -flto -pthread

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPEPYC 7773X 2PEPYC 7773X2004006008001000SE +/- 3.71, N = 4SE +/- 3.12, N = 4417.20808.121. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgIterations Per Second Per Watt, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPEPYC 7773X 2PEPYC 7773X36912152.70911.453
MinAvgMaxEPYC 7773X 2P75.8154.0366.8EPYC 7773X33.970.6219.1OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 2964 Joules per run.2. EPYC 7773X: Approximate power consumption of 1270 Joules per run.
OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPEPYC 7773X 2PEPYC 7773X140280420560700Min: 408.16 / Avg: 417.2 / Max: 425.53Min: 800 / Avg: 808.12 / Max: 813.011. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompileEPYC 7773X 2PEPYC 7773X510152025SE +/- 0.02, N = 3SE +/- 0.03, N = 317.9719.67
MinAvgMaxEPYC 7773X 2P74.7200.2573.2EPYC 7773X34.4126.9286.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed Mesa Compilation 21.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 4739 Joules per run.2. EPYC 7773X: Approximate power consumption of 3215 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To CompileEPYC 7773X 2PEPYC 7773X510152025Min: 17.93 / Avg: 17.97 / Max: 17.99Min: 19.63 / Avg: 19.67 / Max: 19.74

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.10, N = 3SE +/- 0.03, N = 318.1518.251. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff
MinAvgMaxEPYC 7773X 2P74.0123.3136.2EPYC 7773X34.261.168.6OpenBenchmarking.orgWatts, Fewer Is BetterWebP Image Encode 1.1CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 2794 Joules per run.2. EPYC 7773X: Approximate power consumption of 1385 Joules per run.
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessEPYC 7773X 2PEPYC 7773X510152025Min: 17.96 / Avg: 18.15 / Max: 18.26Min: 18.23 / Avg: 18.25 / Max: 18.31. (CC) gcc options: -fvisibility=hidden -O2 -lm -ljpeg -lpng16 -ltiff

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: input.i3d 193 Cells Per DirectionEPYC 7773X 2PEPYC 7773X48121620SE +/- 0.05965355, N = 5SE +/- 0.09430792, N = 39.9588691916.923784901. (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 7773X 2P75.1383.6547.6EPYC 7773X34.3210.8269.1OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 5831 Joules per run.2. EPYC 7773X: Approximate power consumption of 4568 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 7773X 2PEPYC 7773X48121620Min: 9.73 / Avg: 9.96 / Max: 10.08Min: 16.81 / Avg: 16.92 / Max: 17.111. (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

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.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 7773X 2PEPYC 7773X1224364860SE +/- 0.53, N = 4SE +/- 0.06, N = 452.2040.141. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 7773X 2PEPYC 7773X0.05270.10540.15810.21080.26350.1770.234
MinAvgMaxEPYC 7773X 2P76.8294.4394.2EPYC 7773X34.6171.3223.1OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.1CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 4637 Joules per run.2. EPYC 7773X: Approximate power consumption of 3297 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 7773X 2PEPYC 7773X1020304050Min: 50.84 / Avg: 52.2 / Max: 53.32Min: 40.02 / Avg: 40.14 / Max: 40.281. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19EPYC 7773X 2PEPYC 7773X48121620SE +/- 0.02, N = 3SE +/- 0.02, N = 317.4717.48
MinAvgMaxEPYC 7773X 2P76.0123.3134.7EPYC 7773X33.559.465.4OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 2671 Joules per run.2. EPYC 7773X: Approximate power consumption of 1268 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 19EPYC 7773X 2PEPYC 7773X48121620Min: 17.44 / Avg: 17.47 / Max: 17.51Min: 17.45 / Avg: 17.48 / Max: 17.52

Timed ImageMagick Compilation

This test times how long it takes to build ImageMagick. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.046, N = 5SE +/- 0.043, N = 59.85810.866
MinAvgMaxEPYC 7773X 2P75.9175.2568.8EPYC 7773X34.2103.1286.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed ImageMagick Compilation 6.9.0CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3153 Joules per run.2. EPYC 7773X: Approximate power consumption of 1939 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileEPYC 7773X 2PEPYC 7773X3691215Min: 9.7 / Avg: 9.86 / Max: 9.97Min: 10.75 / Avg: 10.87 / Max: 11

Sysbench

This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / MemoryEPYC 7773X 2PEPYC 7773X2K4K6K8K10KSE +/- 62.77, N = 4SE +/- 10.51, N = 57808.7510345.821. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.orgMiB/sec Per Watt, More Is BetterSysbench 1.0.20Test: RAM / MemoryEPYC 7773X 2PEPYC 7773X2040608010032.6991.34
MinAvgMaxEPYC 7773X 2P77.2238.9301.9EPYC 7773X34.4113.3147.2OpenBenchmarking.orgWatts, Fewer Is BetterSysbench 1.0.20CPU Power Consumption Monitor801602403204001. EPYC 7773X 2P: Approximate power consumption of 4121 Joules per run.2. EPYC 7773X: Approximate power consumption of 1586 Joules per run.
OpenBenchmarking.orgMiB/sec, More Is BetterSysbench 1.0.20Test: RAM / MemoryEPYC 7773X 2PEPYC 7773X2K4K6K8K10KMin: 7687.86 / Avg: 7808.75 / Max: 7982.99Min: 10314.69 / Avg: 10345.82 / Max: 10380.781. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.043, N = 5SE +/- 0.077, N = 47.44910.2751. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
MinAvgMaxEPYC 7773X 2P76.0257.2550.0EPYC 7773X34.6161.3274.0OpenBenchmarking.orgWatts, Fewer Is BetterPOV-Ray 3.7.0.7CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3600 Joules per run.2. EPYC 7773X: Approximate power consumption of 2742 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeEPYC 7773X 2PEPYC 7773X3691215Min: 7.29 / Avg: 7.45 / Max: 7.54Min: 10.16 / Avg: 10.28 / Max: 10.51. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1530456075SE +/- 0.64, N = 4SE +/- 0.30, N = 565.7065.421. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.10280.20560.30840.41120.5140.2850.457
MinAvgMaxEPYC 7773X 2P74.4230.2383.3EPYC 7773X34.5143.2246.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.0CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 3625 Joules per run.2. EPYC 7773X: Approximate power consumption of 2119 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X1326395265Min: 63.83 / Avg: 65.7 / Max: 66.71Min: 64.76 / Avg: 65.42 / Max: 66.341. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.036, N = 7SE +/- 0.023, N = 55.74111.2021. (CC) gcc options: -lm -lpthread -O3
MinAvgMaxEPYC 7773X 2P75.9340.9549.0EPYC 7773X35.0205.8275.4OpenBenchmarking.orgWatts, Fewer Is BetterC-Ray 1.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3409 Joules per run.2. EPYC 7773X: Approximate power consumption of 3169 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelEPYC 7773X 2PEPYC 7773X3691215Min: 5.63 / Avg: 5.74 / Max: 5.91Min: 11.15 / Avg: 11.2 / Max: 11.261. (CC) gcc options: -lm -lpthread -O3

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7773X 2PEPYC 7773X80K160K240K320K400KSE +/- 885.81, N = 5SE +/- 783.65, N = 3373690.15168289.281. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7773X 2PEPYC 7773X2004006008001000962.70729.06
MinAvgMaxEPYC 7773X 2P74.2388.2573.6EPYC 7773X34.9230.8286.5OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 4891 Joules per run.2. EPYC 7773X: Approximate power consumption of 5001 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7773X 2PEPYC 7773X60K120K180K240K300KMin: 371240.81 / Avg: 373690.15 / Max: 376277.23Min: 166774.02 / Avg: 168289.28 / Max: 169393.791. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

m-queens

A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.011, N = 7SE +/- 0.031, N = 55.72310.9471. (CXX) g++ options: -fopenmp -O2 -march=native
MinAvgMaxEPYC 7773X 2P76.3349.2568.5EPYC 7773X33.9213.0286.6OpenBenchmarking.orgWatts, Fewer Is Betterm-queens 1.2CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3342 Joules per run.2. EPYC 7773X: Approximate power consumption of 3238 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveEPYC 7773X 2PEPYC 7773X3691215Min: 5.67 / Avg: 5.72 / Max: 5.75Min: 10.83 / Avg: 10.95 / Max: 10.991. (CXX) g++ options: -fopenmp -O2 -march=native

Timed MPlayer Compilation

This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.011, N = 5SE +/- 0.024, N = 58.49010.462
MinAvgMaxEPYC 7773X 2P74.2217.2573.1EPYC 7773X34.3138.1286.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed MPlayer Compilation 1.5CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3171 Joules per run.2. EPYC 7773X: Approximate power consumption of 2265 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To CompileEPYC 7773X 2PEPYC 7773X3691215Min: 8.46 / Avg: 8.49 / Max: 8.52Min: 10.39 / Avg: 10.46 / Max: 10.54

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownEPYC 7773X 2PEPYC 7773X306090120150SE +/- 0.17, N = 7SE +/- 0.06, N = 5115.9962.07MIN: 104.04 / MAX: 128.8MIN: 60.55 / MAX: 65.97
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownEPYC 7773X 2PEPYC 7773X0.07290.14580.21870.29160.36450.3240.293
MinAvgMaxEPYC 7773X 2P75.1358.5573.7EPYC 7773X34.6211.6286.7OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.13CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3585 Joules per run.2. EPYC 7773X: Approximate power consumption of 3090 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownEPYC 7773X 2PEPYC 7773X20406080100Min: 115.34 / Avg: 115.99 / Max: 116.52Min: 61.89 / Avg: 62.07 / Max: 62.24

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 7773X 2PEPYC 7773X50K100K150K200K250KSE +/- 897.94, N = 6SE +/- 124.38, N = 3228945.2789936.491. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 7773X 2PEPYC 7773X140280420560700632.98400.88
MinAvgMaxEPYC 7773X 2P74.0361.7573.7EPYC 7773X34.2224.3284.4OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 4039 Joules per run.2. EPYC 7773X: Approximate power consumption of 4711 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CEPYC 7773X 2PEPYC 7773X40K80K120K160K200KMin: 226332.99 / Avg: 228945.27 / Max: 232405.26Min: 89712.88 / Avg: 89936.49 / Max: 90142.691. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19EPYC 7773X 2PEPYC 7773X246810SE +/- 0.035, N = 6SE +/- 0.008, N = 67.5278.105
MinAvgMaxEPYC 7773X 2P75.5148.1490.9EPYC 7773X33.683.4275.3OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 1703 Joules per run.2. EPYC 7773X: Approximate power consumption of 1015 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3 + Zstd Compression 19EPYC 7773X 2PEPYC 7773X3691215Min: 7.42 / Avg: 7.53 / Max: 7.65Min: 8.09 / Avg: 8.1 / Max: 8.14

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 7773X 2PEPYC 7773X3691215SE +/- 0.023039, N = 7SE +/- 0.048061, N = 55.0940689.6335871. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxEPYC 7773X 2P74.9329.3568.6EPYC 7773X34.1196.2281.9OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3293 Joules per run.2. EPYC 7773X: Approximate power consumption of 2786 Joules per run.
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 7773X 2PEPYC 7773X3691215Min: 5 / Avg: 5.09 / Max: 5.19Min: 9.54 / Avg: 9.63 / Max: 9.811. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: DefaultEPYC 7773X 2PEPYC 7773X0.66381.32761.99142.65523.319SE +/- 0.101, N = 15SE +/- 0.029, N = 152.9502.5441. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
MinAvgMaxEPYC 7773X 2P74.6135.4247.6EPYC 7773X33.972.4159.0OpenBenchmarking.orgWatts, Fewer Is BetterWebP2 Image Encode 20220422CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 966 Joules per run.2. EPYC 7773X: Approximate power consumption of 483 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: DefaultEPYC 7773X 2PEPYC 7773X246810Min: 2.45 / Avg: 2.95 / Max: 3.52Min: 2.37 / Avg: 2.54 / Max: 2.681. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessEPYC 7773X 2PEPYC 7773X246810SE +/- 0.018, N = 6SE +/- 0.026, N = 67.5337.2071. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 7773X 2P75.8157.3355.4EPYC 7773X33.997.9286.6OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.10CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 1835 Joules per run.2. EPYC 7773X: Approximate power consumption of 1093 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessEPYC 7773X 2PEPYC 7773X3691215Min: 7.47 / Avg: 7.53 / Max: 7.59Min: 7.14 / Avg: 7.21 / Max: 7.291. (CXX) g++ options: -O3 -fPIC -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.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownEPYC 7773X 2PEPYC 7773X306090120150SE +/- 0.25, N = 7SE +/- 0.10, N = 5127.3667.37MIN: 114.52 / MAX: 139.8MIN: 65.57 / MAX: 71.96
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownEPYC 7773X 2PEPYC 7773X0.08190.16380.24570.32760.40950.3640.326
MinAvgMaxEPYC 7773X 2P78.4349.7573.3EPYC 7773X33.9206.4286.7OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.13CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3398 Joules per run.2. EPYC 7773X: Approximate power consumption of 2848 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer - Model: CrownEPYC 7773X 2PEPYC 7773X20406080100Min: 126.21 / Avg: 127.36 / Max: 128.2Min: 66.99 / Avg: 67.37 / Max: 67.51

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 7773X 2PEPYC 7773X80K160K240K320K400KSE +/- 2665.84, N = 7SE +/- 1617.25, N = 5394724.96251998.611. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 7773X 2PEPYC 7773X300600900120015001154.281280.23
MinAvgMaxEPYC 7773X 2P73.9342.0572.2EPYC 7773X34.4196.8286.8OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 3469 Joules per run.2. EPYC 7773X: Approximate power consumption of 2559 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 7773X 2PEPYC 7773X70K140K210K280K350KMin: 384641.87 / Avg: 394724.96 / Max: 404755.61Min: 246611.63 / Avg: 251998.61 / Max: 256073.231. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

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: input.i3d 129 Cells Per DirectionEPYC 7773X 2PEPYC 7773X1.05382.10763.16144.21525.269SE +/- 0.02171361, N = 15SE +/- 0.02960455, N = 72.310858104.683471201. (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 7773X 2P73.4245.9569.5EPYC 7773X34.9151.1272.1OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 1803 Joules per run.2. EPYC 7773X: Approximate power consumption of 1382 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionEPYC 7773X 2PEPYC 7773X246810Min: 2.21 / Avg: 2.31 / Max: 2.48Min: 4.53 / Avg: 4.68 / Max: 4.761. (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

Google Draco

Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionEPYC 7773X 2PEPYC 7773X11002200330044005500SE +/- 3.39, N = 7SE +/- 7.08, N = 7493448951. (CXX) g++ options: -O3
MinAvgMaxEPYC 7773X 2P74.1112.1136.7EPYC 7773X34.054.270.0OpenBenchmarking.orgWatts, Fewer Is BetterGoogle Draco 1.5.0CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 1137 Joules per run.2. EPYC 7773X: Approximate power consumption of 549 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionEPYC 7773X 2PEPYC 7773X9001800270036004500Min: 4923 / Avg: 4933.57 / Max: 4947Min: 4862 / Avg: 4894.86 / Max: 49171. (CXX) g++ options: -O3

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeEPYC 7773X 2PEPYC 7773X12002400360048006000SE +/- 10.77, N = 6SE +/- 7.53, N = 6583058091. (CXX) g++ options: -O3
MinAvgMaxEPYC 7773X 2P75.1113.8136.1EPYC 7773X33.754.770.1OpenBenchmarking.orgWatts, Fewer Is BetterGoogle Draco 1.5.0CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 1271 Joules per run.2. EPYC 7773X: Approximate power consumption of 601 Joules per run.
OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeEPYC 7773X 2PEPYC 7773X10002000300040005000Min: 5792 / Avg: 5829.83 / Max: 5858Min: 5787 / Avg: 5809 / Max: 58391. (CXX) g++ options: -O3

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverEPYC 7773X 2PEPYC 7773X246810SE +/- 0.010, N = 7SE +/- 0.009, N = 65.9106.5091. (CXX) g++ options: -O2 -lOpenCL
MinAvgMaxEPYC 7773X 2P73.0252.8468.6EPYC 7773X34.3145.1261.4OpenBenchmarking.orgWatts, Fewer Is BetterRodinia 3.1CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 2492 Joules per run.2. EPYC 7773X: Approximate power consumption of 1548 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverEPYC 7773X 2PEPYC 7773X3691215Min: 5.88 / Avg: 5.91 / Max: 5.95Min: 6.48 / Avg: 6.51 / Max: 6.541. (CXX) g++ options: -O2 -lOpenCL

libavif avifenc

This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6EPYC 7773X 2PEPYC 7773X0.87621.75242.62863.50484.381SE +/- 0.030, N = 8SE +/- 0.026, N = 133.8943.7631. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 7773X 2P75.1165.0358.3EPYC 7773X34.1107.1286.6OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.10CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 1279 Joules per run.2. EPYC 7773X: Approximate power consumption of 832 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6EPYC 7773X 2PEPYC 7773X246810Min: 3.78 / Avg: 3.89 / Max: 4.01Min: 3.66 / Avg: 3.76 / Max: 4.011. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessEPYC 7773X 2PEPYC 7773X1.32012.64023.96035.28046.6005SE +/- 0.022, N = 7SE +/- 0.006, N = 75.8675.5461. (CXX) g++ options: -O3 -fPIC -lm
MinAvgMaxEPYC 7773X 2P76.0129.2237.1EPYC 7773X33.968.3171.9OpenBenchmarking.orgWatts, Fewer Is Betterlibavif avifenc 0.10CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 1273 Joules per run.2. EPYC 7773X: Approximate power consumption of 654 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessEPYC 7773X 2PEPYC 7773X246810Min: 5.78 / Avg: 5.87 / Max: 5.94Min: 5.52 / Avg: 5.55 / Max: 5.581. (CXX) g++ options: -O3 -fPIC -lm

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMPEPYC 7773X 2PEPYC 7773X16003200480064008000SE +/- 13.29, N = 8SE +/- 28.73, N = 6411076301. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
MinAvgMaxEPYC 7773X 2P74.6300.1569.8EPYC 7773X34.4185.0278.7OpenBenchmarking.orgWatts, Fewer Is BettertoyBrot Fractal Generator 2020-11-18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 2476 Joules per run.2. EPYC 7773X: Approximate power consumption of 2158 Joules per run.
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: OpenMPEPYC 7773X 2PEPYC 7773X13002600390052006500Min: 4052 / Avg: 4109.5 / Max: 4162Min: 7591 / Avg: 7629.83 / Max: 77731. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

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.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ThoroughEPYC 7773X 2PEPYC 7773X1.31592.63183.94775.26366.5795SE +/- 0.0083, N = 7SE +/- 0.0027, N = 75.30495.84831. (CXX) g++ options: -O3 -flto -pthread
MinAvgMaxEPYC 7773X 2P77.9143.7419.8EPYC 7773X34.081.0270.1OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 3.2CPU Power Consumption Monitor1102203304405501. EPYC 7773X 2P: Approximate power consumption of 1354 Joules per run.2. EPYC 7773X: Approximate power consumption of 786 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 3.2Preset: ThoroughEPYC 7773X 2PEPYC 7773X246810Min: 5.28 / Avg: 5.3 / Max: 5.35Min: 5.84 / Avg: 5.85 / Max: 5.861. (CXX) g++ options: -O3 -flto -pthread

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CEPYC 7773X 2PEPYC 7773X30K60K90K120K150KSE +/- 1051.45, N = 8SE +/- 237.78, N = 6127926.7464849.861. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CEPYC 7773X 2PEPYC 7773X100200300400500472.53394.01
MinAvgMaxEPYC 7773X 2P73.9270.7545.2EPYC 7773X34.8164.6264.5OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 2233 Joules per run.2. EPYC 7773X: Approximate power consumption of 1865 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CEPYC 7773X 2PEPYC 7773X20K40K60K80K100KMin: 122551.69 / Avg: 127926.74 / Max: 131537.95Min: 63756.36 / Avg: 64849.86 / Max: 65209.191. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 7773X 2PEPYC 7773X30K60K90K120K150KSE +/- 1860.50, N = 15SE +/- 992.33, N = 9152554.57136930.601. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 7773X 2PEPYC 7773X2004006008001000607.301070.69
MinAvgMaxEPYC 7773X 2P74.5251.2573.3EPYC 7773X34.0127.9286.6OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 1809 Joules per run.2. EPYC 7773X: Approximate power consumption of 924 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 7773X 2PEPYC 7773X30K60K90K120K150KMin: 143781.75 / Avg: 152554.57 / Max: 166050.33Min: 133372.14 / Avg: 136930.6 / Max: 141844.341. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ TasksEPYC 7773X 2PEPYC 7773X16003200480064008000SE +/- 12.31, N = 8SE +/- 53.52, N = 6399374111. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
MinAvgMaxEPYC 7773X 2P74.3292.9549.9EPYC 7773X34.3183.0278.4OpenBenchmarking.orgWatts, Fewer Is BettertoyBrot Fractal Generator 2020-11-18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 2343 Joules per run.2. EPYC 7773X: Approximate power consumption of 2104 Joules per run.
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ TasksEPYC 7773X 2PEPYC 7773X13002600390052006500Min: 3941 / Avg: 3992.75 / Max: 4043Min: 7277 / Avg: 7411.33 / Max: 76431. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X4080120160200SE +/- 1.16, N = 6SE +/- 0.61, N = 7144.78158.641. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.32990.65980.98971.31961.64950.7691.466
MinAvgMaxEPYC 7773X 2P74.8188.2348.6EPYC 7773X34.4108.2228.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.0CPU Power Consumption Monitor1002003004005001. EPYC 7773X 2P: Approximate power consumption of 1976 Joules per run.2. EPYC 7773X: Approximate power consumption of 1005 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.0Encoder Mode: Preset 10 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X306090120150Min: 141.7 / Avg: 144.78 / Max: 149.75Min: 156.01 / Avg: 158.64 / Max: 161.061. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Intel Threaded Building Blocks (TBB), and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ ThreadsEPYC 7773X 2PEPYC 7773X15003000450060007500SE +/- 18.57, N = 8SE +/- 8.09, N = 6384471211. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc
MinAvgMaxEPYC 7773X 2P73.6286.5551.0EPYC 7773X34.4185.4276.8OpenBenchmarking.orgWatts, Fewer Is BettertoyBrot Fractal Generator 2020-11-18CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 2256 Joules per run.2. EPYC 7773X: Approximate power consumption of 2070 Joules per run.
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal Generator 2020-11-18Implementation: C++ ThreadsEPYC 7773X 2PEPYC 7773X12002400360048006000Min: 3761 / Avg: 3843.5 / Max: 3910Min: 7100 / Avg: 7121.33 / Max: 71441. (CXX) g++ options: -O3 -lpthread -lm -lgcc -lgcc_s -lc

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X306090120150SE +/- 0.90, N = 5SE +/- 0.12, N = 7152.60157.291. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X0.25070.50140.75211.00281.25350.7311.114
MinAvgMaxEPYC 7773X 2P74.0208.9451.2EPYC 7773X34.8141.2284.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-HEVC 1.5.0CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 2632 Joules per run.2. EPYC 7773X: Approximate power consumption of 1270 Joules per run.
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KEPYC 7773X 2PEPYC 7773X306090120150Min: 150.45 / Avg: 152.6 / Max: 154.76Min: 157.07 / Avg: 157.29 / Max: 157.981. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineEPYC 7773X 2PEPYC 7773X50K100K150K200K250KSE +/- 2779.65, N = 15SE +/- 2168.67, N = 15225092.74231182.731. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineEPYC 7773X 2PEPYC 7773X400800120016002000954.191823.51
MinAvgMaxEPYC 7773X 2P72.9235.9507.3EPYC 7773X34.2126.8286.7OpenBenchmarking.orgWatts, Fewer Is BetterFFTE 7.0CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 1510 Joules per run.2. EPYC 7773X: Approximate power consumption of 811 Joules per run.
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 7.0N=256, 3D Complex FFT RoutineEPYC 7773X 2PEPYC 7773X40K80K120K160K200KMin: 203124.78 / Avg: 225092.74 / Max: 241341.08Min: 222672.08 / Avg: 231182.73 / Max: 256857.961. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 7773X 2PEPYC 7773X11K22K33K44K55KSE +/- 246.00, N = 8SE +/- 286.64, N = 850299.7737967.961. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 7773X 2PEPYC 7773X60120180240300205.28292.74
MinAvgMaxEPYC 7773X 2P74.1245.0487.8EPYC 7773X34.6129.7246.4OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 1960 Joules per run.2. EPYC 7773X: Approximate power consumption of 1119 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.CEPYC 7773X 2PEPYC 7773X9K18K27K36K45KMin: 49427.32 / Avg: 50299.77 / Max: 51219.05Min: 36742.95 / Avg: 37967.96 / Max: 39439.181. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 7773X 2PEPYC 7773X30K60K90K120K150KSE +/- 1172.23, N = 15SE +/- 236.45, N = 9123826.9460883.141. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 7773X 2PEPYC 7773X140280420560700631.61532.13
MinAvgMaxEPYC 7773X 2P74.0196.1534.1EPYC 7773X34.3114.4236.9OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 1255 Joules per run.2. EPYC 7773X: Approximate power consumption of 852 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 7773X 2PEPYC 7773X20K40K60K80K100KMin: 114632.47 / Avg: 123826.94 / Max: 131496.33Min: 59284.65 / Avg: 60883.14 / Max: 61559.041. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3EPYC 7773X 2PEPYC 7773X0.99631.99262.98893.98524.9815SE +/- 0.019, N = 8SE +/- 0.004, N = 83.8844.428
MinAvgMaxEPYC 7773X 2P75.5155.5492.7EPYC 7773X24.191.3275.1OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor1302603905206501. EPYC 7773X 2P: Approximate power consumption of 1225 Joules per run.2. EPYC 7773X: Approximate power consumption of 776 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: UASTC 3EPYC 7773X 2PEPYC 7773X246810Min: 3.82 / Avg: 3.88 / Max: 3.97Min: 4.41 / Avg: 4.43 / Max: 4.44

WebP2 Image Encode

This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Compression Effort 5EPYC 7773X 2PEPYC 7773X0.791.582.373.163.95SE +/- 0.015, N = 9SE +/- 0.002, N = 93.5113.4041. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl
MinAvgMaxEPYC 7773X 2P74.0145.1232.5EPYC 7773X33.986.9156.3OpenBenchmarking.orgWatts, Fewer Is BetterWebP2 Image Encode 20220422CPU Power Consumption Monitor601201802403001. EPYC 7773X 2P: Approximate power consumption of 1113 Joules per run.2. EPYC 7773X: Approximate power consumption of 676 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterWebP2 Image Encode 20220422Encode Settings: Quality 100, Compression Effort 5EPYC 7773X 2PEPYC 7773X246810Min: 3.39 / Avg: 3.51 / Max: 3.54Min: 3.39 / Avg: 3.4 / Max: 3.421. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl

rays1bench

This is a test of rays1bench, a simple path-tracer / ray-tracing that supports SSE and AVX instructions, multi-threading, and other features. This test profile is measuring the performance of the "large scene" in rays1bench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneEPYC 7773X 2PEPYC 7773X130260390520650SE +/- 0.91, N = 9SE +/- 0.40, N = 8582.92304.61
OpenBenchmarking.orgmrays/s Per Watt, More Is Betterrays1bench 2020-01-09Large SceneEPYC 7773X 2PEPYC 7773X0.75671.51342.27013.02683.78353.3632.800
MinAvgMaxEPYC 7773X 2P75.8173.3471.8EPYC 7773X34.2108.8249.9OpenBenchmarking.orgWatts, Fewer Is Betterrays1bench 2020-01-09CPU Power Consumption Monitor1202403604806001. EPYC 7773X 2P: Approximate power consumption of 1252 Joules per run.2. EPYC 7773X: Approximate power consumption of 925 Joules per run.
OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large SceneEPYC 7773X 2PEPYC 7773X100200300400500Min: 578 / Avg: 582.92 / Max: 586.66Min: 302.48 / Avg: 304.61 / Max: 305.75

Primesieve

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

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.71e12 Prime Number GenerationEPYC 7773X 2PEPYC 7773X1.04582.09163.13744.18325.229SE +/- 0.005, N = 10SE +/- 0.004, N = 82.4554.6481. (CXX) g++ options: -O3
MinAvgMaxEPYC 7773X 2P75.8245.1546.6EPYC 7773X17.2150.8264.1OpenBenchmarking.orgWatts, Fewer Is BetterPrimesieve 7.7CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 1569 Joules per run.2. EPYC 7773X: Approximate power consumption of 1301 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.71e12 Prime Number GenerationEPYC 7773X 2PEPYC 7773X246810Min: 2.44 / Avg: 2.45 / Max: 2.49Min: 4.63 / Avg: 4.65 / Max: 4.671. (CXX) g++ options: -O3

Etcpak

Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2EPYC 7773X 2PEPYC 7773X15003000450060007500SE +/- 29.06, N = 8SE +/- 36.09, N = 96969.937076.141. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread
OpenBenchmarking.orgMpx/s Per Watt, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2EPYC 7773X 2PEPYC 7773X2040608010046.0280.14
MinAvgMaxEPYC 7773X 2P71.0151.5278.4EPYC 7773X33.688.3190.5OpenBenchmarking.orgWatts, Fewer Is BetterEtcpak 1.0CPU Power Consumption Monitor701402102803501. EPYC 7773X 2P: Approximate power consumption of 1174 Joules per run.2. EPYC 7773X: Approximate power consumption of 657 Joules per run.
OpenBenchmarking.orgMpx/s, More Is BetterEtcpak 1.0Benchmark: Multi-Threaded - Configuration: ETC2EPYC 7773X 2PEPYC 7773X12002400360048006000Min: 6879.43 / Avg: 6969.93 / Max: 7134.69Min: 6973.07 / Avg: 7076.14 / Max: 7272.311. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 7773X 2PEPYC 7773X2K4K6K8K10KSE +/- 88.67, N = 15SE +/- 50.08, N = 159459.245025.591. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 7773X 2PEPYC 7773X122436486054.2546.02
MinAvgMaxEPYC 7773X 2P74.1174.4538.3EPYC 7773X34.2109.2286.7OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor1402804205607001. EPYC 7773X 2P: Approximate power consumption of 1023 Joules per run.2. EPYC 7773X: Approximate power consumption of 684 Joules per run.
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 7773X 2PEPYC 7773X16003200480064008000Min: 8929.1 / Avg: 9459.24 / Max: 10529.35Min: 4594.16 / Avg: 5025.59 / Max: 5259.621. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

KTX-Software toktx

This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9EPYC 7773X 2PEPYC 7773X0.66741.33482.00222.66963.337SE +/- 0.001, N = 9SE +/- 0.008, N = 92.9372.966
MinAvgMaxEPYC 7773X 2P75.3102.4135.2EPYC 7773X33.748.065.5OpenBenchmarking.orgWatts, Fewer Is BetterKTX-Software toktx 4.0CPU Power Consumption Monitor40801201602001. EPYC 7773X 2P: Approximate power consumption of 706 Joules per run.2. EPYC 7773X: Approximate power consumption of 336 Joules per run.
OpenBenchmarking.orgSeconds, Fewer Is BetterKTX-Software toktx 4.0Settings: Zstd Compression 9EPYC 7773X 2PEPYC 7773X246810Min: 2.93 / Avg: 2.94 / Max: 2.94Min: 2.94 / Avg: 2.97 / Max: 3.02

238 Results Shown

WRF
OpenFOAM:
  drivaerFastback, Large Mesh Size - Execution Time
  drivaerFastback, Large Mesh Size - Mesh Time
OpenVKL
ASKAP:
  tConvolve MT - Degridding
  tConvolve MT - Gridding
NWChem
OSPRay
WebP2 Image Encode
PostgreSQL pgbench:
  1000 - 250 - Read Write - Average Latency
  1000 - 250 - Read Write
  1000 - 250 - Read Only - Average Latency
  1000 - 250 - Read Only
MariaDB
RELION
LeelaChessZero
ONNX Runtime
Xcompact3d Incompact3d
BRL-CAD
Rodinia
MariaDB
OSPRay
LeelaChessZero
PostgreSQL pgbench:
  100 - 500 - Read Write - Average Latency
  100 - 500 - Read Write
ONNX Runtime:
  GPT-2 - CPU - Standard
  ArcFace ResNet-100 - CPU - Standard
GraphicsMagick
Graph500:
  26:
    sssp max_TEPS
    sssp median_TEPS
    bfs max_TEPS
    bfs median_TEPS
High Performance Conjugate Gradient
oneDNN
LAMMPS Molecular Dynamics Simulator
OSPRay
PostgreSQL pgbench:
  100 - 250 - Read Write - Average Latency
  100 - 250 - Read Write
Stockfish
ONNX Runtime:
  yolov4 - CPU - Standard
  super-resolution-10 - CPU - Standard
WebP2 Image Encode
Blender
AOM AV1
PostgreSQL pgbench:
  1000 - 500 - Read Write - Average Latency
  1000 - 500 - Read Write
Numpy Benchmark
LuxCoreRender:
  Orange Juice - CPU
  Danish Mood - CPU
  LuxCore Benchmark - CPU
Timed Linux Kernel Compilation
Timed LLVM Compilation
Facebook RocksDB:
  Update Rand
  Read While Writing
OpenSSL
Java JMH
ClickHouse:
  100M Rows Web Analytics Dataset, Third Run
  100M Rows Web Analytics Dataset, Second Run
  100M Rows Web Analytics Dataset, First Run / Cold Cache
PostgreSQL pgbench:
  100 - 250 - Read Only - Average Latency
  100 - 250 - Read Only
ONNX Runtime
Timed Gem5 Compilation
OSPRay Studio:
  3 - 1080p - 16 - Path Tracer
  1 - 1080p - 16 - Path Tracer
  2 - 4K - 16 - Path Tracer
  2 - 1080p - 16 - Path Tracer
  1 - 1080p - 32 - Path Tracer
PostgreSQL pgbench:
  100 - 500 - Read Only - Average Latency
  100 - 500 - Read Only
OSPRay Studio:
  2 - 1080p - 32 - Path Tracer
  3 - 1080p - 32 - Path Tracer
OpenFOAM:
  drivaerFastback, Small Mesh Size - Execution Time
  drivaerFastback, Small Mesh Size - Mesh Time
  drivaerFastback, Medium Mesh Size - Execution Time
  drivaerFastback, Medium Mesh Size - Mesh Time
Apache Cassandra
OSPRay Studio:
  3 - 1080p - 1 - Path Tracer
  1 - 4K - 16 - Path Tracer
asmFish
OSPRay Studio:
  2 - 1080p - 1 - Path Tracer
  1 - 1080p - 1 - Path Tracer
  3 - 4K - 1 - Path Tracer
Apache HTTP Server
OSPRay Studio:
  3 - 4K - 32 - Path Tracer
  2 - 4K - 1 - Path Tracer
  3 - 4K - 16 - Path Tracer
OSPRay
OSPRay Studio
Timed LLVM Compilation
Timed Node.js Compilation
WebP2 Image Encode
AOM AV1
OSPRay Studio
PyHPC Benchmarks
OSPRay Studio
OSPRay:
  gravity_spheres_volume/dim_512/scivis/real_time
  gravity_spheres_volume/dim_512/ao/real_time
AOM AV1
Apache HTTP Server
Cpuminer-Opt:
  Triple SHA-256, Onecoin
  Blake-2 S
  LBC, LBRY Credits
  Deepcoin
nginx:
  1000
  500
  200
Apache HTTP Server
Sysbench
x265
libavif avifenc
Blender
LuxCoreRender
Facebook RocksDB
GraphicsMagick:
  Noise-Gaussian
  Sharpen
  HWB Color Space
OpenSSL:
  RSA4096:
    verify/s
    sign/s
Facebook RocksDB
GraphicsMagick:
  Enhanced
  Swirl
Blender
Timed Linux Kernel Compilation
NAS Parallel Benchmarks
GPAW
Redis
KTX-Software toktx
AOM AV1
SVT-HEVC
LuxCoreRender
SVT-AV1
Redis
Rodinia
Zstd Compression:
  19 - Decompression Speed
  19 - Compression Speed
miniFE
libavif avifenc
AOM AV1
Zstd Compression:
  19, Long Mode - Decompression Speed
  19, Long Mode - Compression Speed
Timed Godot Game Engine Compilation
oneDNN
WebP Image Encode
OpenFOAM:
  motorBike - Execution Time
  motorBike - Mesh Time
Algebraic Multi-Grid Benchmark
AOM AV1
Rodinia
Intel Open Image Denoise
Kvazaar
ASKAP:
  tConvolve MPI - Gridding
  tConvolve MPI - Degridding
PyHPC Benchmarks
GROMACS
Cpuminer-Opt:
  Magi
  x25x
  Ringcoin
  Myriad-Groestl
  Garlicoin
  Quad SHA-256, Pyrite
  Skeincoin
Aircrack-ng
Blender
NAS Parallel Benchmarks
x264
toyBrot Fractal Generator
Xmrig
Embree
ASKAP:
  tConvolve OpenMP - Degridding
  tConvolve OpenMP - Gridding
Pennant
Tachyon
Blender
Embree
NAMD
Kvazaar
Rodinia
Xmrig
AOM AV1
Embree
SVT-HEVC
LULESH
Embree
SVT-AV1
Liquid-DSP:
  256 - 256 - 57
  128 - 256 - 57
  64 - 256 - 57
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160
  RT.ldr_alb_nrm.3840x2160
ACES DGEMM
ASTC Encoder
ASKAP
Timed Mesa Compilation
WebP Image Encode
Xcompact3d Incompact3d
Kvazaar
KTX-Software toktx
Timed ImageMagick Compilation
Sysbench
POV-Ray
SVT-AV1
C-Ray
NAS Parallel Benchmarks
m-queens
Timed MPlayer Compilation
Embree
NAS Parallel Benchmarks
KTX-Software toktx
Pennant
WebP2 Image Encode
libavif avifenc
Embree
NAS Parallel Benchmarks
Xcompact3d Incompact3d
Google Draco:
  Lion
  Church Facade
Rodinia
libavif avifenc:
  6
  10, Lossless
toyBrot Fractal Generator
ASTC Encoder
NAS Parallel Benchmarks:
  FT.C
  SP.B
toyBrot Fractal Generator
SVT-AV1
toyBrot Fractal Generator
SVT-HEVC
FFTE
NAS Parallel Benchmarks:
  CG.C
  MG.C
KTX-Software toktx
WebP2 Image Encode
rays1bench
Primesieve
Etcpak
NAS Parallel Benchmarks
KTX-Software toktx

EPYC 7773X 2P

Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc4daily20220628-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler 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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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-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 Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229
Java Notes: OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)
Python Notes: Python 3.10.4
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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 + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 29 June 2022 20:43 by user phoronix.

EPYC 7773X

Processor: AMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 22.04, Kernel: 5.19.0-051900rc4daily20220628-generic (x86_64), Desktop: GNOME Shell 42.2, Display Server: X Server 1.21.1.3, Vulkan: 1.2.204, Compiler: GCC 11.2.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler 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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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-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 Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229
Java Notes: OpenJDK Runtime Environment (build 11.0.15+10-Ubuntu-0ubuntu0.22.04.1)
Python Notes: Python 3.10.4
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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 + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 1 July 2022 13:21 by user phoronix.