AMD EPYC Zen

Benchmarks for a future article. AMD EPYC 8534PN 64-Core testing with a AMD Cinnabar (RCB1009C BIOS) and ASPEED on Ubuntu 23.10 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 2401092-NE-AMDEPYCZE04
Jump To Table - Results

View

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

Statistics

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

Graph Settings

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

Additional Graphs

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Zen 1 - EPYC 7601
January 06
  1 Day, 1 Hour, 51 Minutes
Zen 4C - EPYC 8534PN
January 08
  16 Hours, 31 Minutes
Invert Behavior (Only Show Selected Data)
  21 Hours, 11 Minutes
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):

Zen 1 - EPYC 7601

Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD 17h, Memory: 128GB, Disk: 280GB INTEL SSDPE21D280GA + 1000GB INTEL SSDPE2KX010T8, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, 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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: 0x800126e
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Mitigation of Safe RET + 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 STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Zen 4C - EPYC 8534PN

Processor: AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC ZenProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionZen 1 - EPYC 7601Zen 4C - EPYC 8534PNAMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads)TYAN B8026T70AE24HR (V1.02.B10 BIOS)AMD 17h128GB280GB INTEL SSDPE21D280GA + 1000GB INTEL SSDPE2KX010T8llvmpipeVE2282 x Broadcom NetXtreme BCM5720 PCIeUbuntu 23.106.6.9-060609-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.74.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits)GCC 13.2.0ext41920x1080AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads)AMD Cinnabar (RCB1009C BIOS)AMD Device 14a46 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG1000GB INTEL SSDPE2KX010T8ASPEED1920x1200OpenBenchmarking.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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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- Zen 1 - EPYC 7601: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x800126e- Zen 4C - EPYC 8534PN: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212Java Details- OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)Python Details- Python 3.11.6Security Details- Zen 1 - EPYC 7601: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Mitigation of Safe RET + 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 STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - Zen 4C - EPYC 8534PN: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Zen 1 - EPYC 7601 vs. Zen 4C - EPYC 8534PN ComparisonPhoronix Test SuiteBaseline+588.7%+588.7%+1177.4%+1177.4%+1766.1%+1766.1%881.3%726.8%726.8%720.4%720.4%649.8%607.4%589%588.6%581.4%570.9%553.6%550.2%521.7%505.5%473.6%459%455.2%452.1%440.9%428.6%412.3%411.9%396.6%373.5%357.7%356.8%331.9%326.9%314.7%308.9%305%303.3%283.3%281.1%280.8%280.8%269.8%256.9%255.5%253.5%251.4%250.6%243.6%241.8%241.6%239.6%235%231.5%226.5%225.3%223.3%221.1%219.2%215.9%213.6%212.6%207.8%202.5%202.1%201.9%2354.6%198.7%197.5%195.1%194.1%190.1%189.1%188.9%186.1%185.8%185.6%183.9%179.9%177.6%175.9%169.7%165.7%164.6%164.2%160.6%156%154.8%153.9%150.2%150.1%147.8%145.4%141.2%136.1%134.7%131.3%127.6%125.5%123.5%123.3%123.3%123.1%120.3%118%110.7%105.7%105.2%102.8%1300.8%1298%1128.6%907.5%97.4%95.4%90.8%89.7%89.3%87.5%82.9%79.5%79.2%78.7%78.1%78%78%77.6%77.2%77.2%76.9%75.9%74.6%73.9%73.9%73.5%72.4%70.7%70.4%69.8%68.9%68.8%67.7%67.5%66.3%65.7%65.5%64.5%64.1%63.7%63.3%62.8%61.8%61.1%61%60.7%59.2%59.1%58.4%57%56.4%53.7%51.5%47.8%47.5%47.5%45.5%45.2%45.1%43.6%42.8%38.8%38.3%37.7%32.8%32%30.1%28.2%27.7%25%24.8%24.2%23.9%17.8%7.7%V.D.F.I - CPUOpenMP - BM2OpenMP - BM2OpenMP - BM1OpenMP - BM1M.T.E.T.D.F - CPUW.P.D.F.I - CPUChaCha20-Poly1305C.S.9.P.Y.P - A.M.Sgravity_spheres_volume/dim_512/scivis/real_timegravity_spheres_volume/dim_512/ao/real_timeR.S.A.F.I - CPUH.E.R.F.I - CPUChaCha20S.F.P.RA.G.R.R.0.F.I - CPURSA4096N.T.C.B.b.u.S.S.I - A.M.SP.V.B.D.F - CPUAES-128-GCMB.L.N.Q.A.S.I - A.M.SAES-256-GCMCPU - 16 - ResNet-50P.D.F - CPUgravity_spheres_volume/dim_512/pathtracer/real_time3 - 4K - 1 - Path Tracer - CPU1 - 4K - 1 - Path Tracer - CPU3 - 4K - 32 - Path Tracer - CPU1 - 4K - 32 - Path Tracer - CPU3 - 4K - 16 - Path Tracer - CPUGhostRider - 1MA.G.R.R.0.F.I - CPU1 - 4K - 16 - Path Tracer - CPURT.ldr_alb_nrm.3840x2160 - CPU-OnlyPathtracer ISPC - Asian DragonWownero - 1Me.G.B.S - 1200Pathtracer ISPC - CrownRand ReadN.T.C.D.m - A.M.SB.L.N.Q.A - A.M.SF.D.F.I - CPURand ReadC.S.9.P.Y.P - A.M.SN.T.C.B.b.u.c - A.M.SN.D.C.o.b.u.o.I - A.M.SR.5.B - A.M.SC.C.R.5.I - A.M.S1Bparticle_volume/scivis/real_timeH.E.R.F.I - CPUparticle_volume/ao/real_timee.G.B.S - 2400Barbershop - CPU-OnlySHA512C.D.Y.C.S.I - A.M.SC.D.Y.C - A.M.S500MRSA4096D.RCPUR.5.S.I - A.M.SKawPow - 1MC.F.U - 1MSHA256Monero - 1MCryptoNight-Heavy - 1MPreset 13 - Bosphorus 4KCompression RatingFishy Cat - CPU-OnlyCPU - SupercarPabellon Barcelona - CPU-OnlyClassroom - CPU-OnlyCPU - BedroomN.T.C.B.b.u.S.S.I - A.M.SPreset 12 - Bosphorus 4KBMW27 - CPU-OnlyMulti-Threaded1000B.L.N.Q.A.S.I - A.M.SRedis - 100 - 1:10Preset 8 - Bosphorus 4K500Redis - 100 - 1:5NinjaATPase Simulation - 327,506 AtomsV.D.F.I - CPUallmodconfigTime To CompileBosphorus 4K - Very FastBosphorus 4K - Super Fastd.S.M.S - Execution TimeBosphorus 4K - MediumCarbon Nanotube20k Atomslibx265 - Platformlibx265 - Video On Demandlibx265 - UploadTime To CompilePreset 4 - Bosphorus 4KRead While WritingBosphorus 4K - Ultra FastRead While WritingUnix MakefilesF.D.F.I - CPUW.P.D.F.I - CPUR.5.S.I - A.M.SF.D.R.F.I - CPUlibx265 - Liveclover_bm16Bosphorus 4K - FastBosphorus 4Kclover_bm64_shortM.T.E.T.D.F - CPUdefconfigR.R.W.Ri.i.1.C.P.DTime To CompileBosphorus 4K - FasterN.T.C.D.m - A.M.SB.L.N.Q.A - A.M.S500 - 100 - 800 - 100500 - 100 - 800 - 10010Update RandR.R.W.R800 - 100 - 500 - 100500 - 100 - 800 - 400800 - 100 - 500 - 100d.M.M.S - Execution TimeCPU - 256 - ResNet-50N.D.C.o.b.u.o.I - A.M.SN.T.C.B.b.u.c - A.M.SR.5.B - A.M.SCPU - 1 - ResNet-50particle_volume/pathtracer/real_timeChrysler Neon 1MC.C.R.5.I - A.M.SUpdate Rand500 - 100 - 800 - 4006WritesCORAL2 P1R.S.A.F.I - CPU500 - 100 - 500 - 400800 - 100 - 500 - 400800 - 100 - 500 - 400500 - 100 - 500 - 100500 - 100 - 500 - 1005IMDBP.P.AC.D.Y.C.S.I - A.M.SC.D.Y.C - A.M.S500 - 100 - 500 - 40011000800 - 100 - 200 - 100800 - 100 - 200 - 400X.b.i.id.M.M.S - Mesh Time800 - 100 - 200 - 100d.S.M.S - Mesh TimeCTS2P.V.B.D.F - CPU800 - 100 - 200 - 400TPC-H Parquet500 - 100 - 200 - 100500 - 100 - 200 - 400500 - 100 - 200 - 100F.D.R.F.I - CPU800 - 100 - 800 - 100800 - 100 - 800 - 100500 - 100 - 200 - 400P.D.F - CPU800 - 100 - 800 - 400800 - 100 - 800 - 400CORAL2 P2OpenVINOminiBUDEminiBUDEminiBUDEminiBUDEOpenVINOOpenVINOOpenSSLNeural Magic DeepSparseOSPRayOSPRayOpenVINOOpenVINOOpenSSLACES DGEMMOpenVINOOpenSSLNeural Magic DeepSparseOpenVINOOpenSSLNeural Magic DeepSparseOpenSSLTensorFlowOpenVINOOSPRayOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioXmrigOpenVINOOSPRay StudioIntel Open Image DenoiseEmbreeXmrigeasyWaveEmbreeRocksDBNeural Magic DeepSparseNeural Magic DeepSparseOpenVINOSpeedbNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseY-CruncherOSPRayOpenVINOOSPRayeasyWaveBlenderOpenSSLNeural Magic DeepSparseNeural Magic DeepSparseY-CruncherOpenSSL7-Zip CompressionChaos Group V-RAYNeural Magic DeepSparseXmrigXmrigOpenSSLXmrigXmrigSVT-AV17-Zip CompressionBlenderIndigoBenchBlenderBlenderIndigoBenchNeural Magic DeepSparseSVT-AV1BlenderQuantLibnginxNeural Magic DeepSparseRedis 7.0.12 + memtier_benchmarkSVT-AV1nginxRedis 7.0.12 + memtier_benchmarkTimed LLVM CompilationNAMDOpenVINOTimed Linux Kernel CompilationTimed Node.js Compilationuvg266uvg266OpenFOAMuvg266GPAWLAMMPS Molecular Dynamics SimulatorFFmpegFFmpegFFmpegTimed FFmpeg CompilationSVT-AV1Speedbuvg266RocksDBTimed LLVM CompilationOpenVINOOpenVINONeural Magic DeepSparseOpenVINOFFmpegCloverLeafVVenCx265CloverLeafOpenVINOTimed Linux Kernel CompilationSpeedbXcompact3d Incompact3dTimed Gem5 CompilationVVenCNeural Magic DeepSparseNeural Magic DeepSparseApache IoTDBApache IoTDBrav1eSpeedbRocksDBApache IoTDBApache IoTDBApache IoTDBOpenFOAMPyTorchNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparsePyTorchOSPRayOpenRadiossNeural Magic DeepSparseRocksDBApache IoTDBrav1eApache CassandraQuicksilverOpenVINOApache IoTDBApache IoTDBKripkeApache IoTDBApache IoTDBApache IoTDBrav1eDuckDBTimed MrBayes AnalysisNeural Magic DeepSparseNeural Magic DeepSparseApache IoTDBrav1eApache HTTP ServerApache IoTDBApache IoTDBXcompact3d Incompact3dOpenFOAMApache IoTDBOpenFOAMQuicksilverOpenVINOApache IoTDBDuckDBApache IoTDBApache IoTDBApache IoTDBOpenVINOApache IoTDBApache IoTDBApache IoTDBOpenVINOApache IoTDBApache IoTDBQuicksilverZen 1 - EPYC 7601Zen 4C - EPYC 8534PN

AMD EPYC Zenopenvino: Vehicle Detection FP16-INT8 - CPUminibude: OpenMP - BM2minibude: OpenMP - BM2minibude: OpenMP - BM1minibude: OpenMP - BM1openvino: Machine Translation EN To DE FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenssl: ChaCha20-Poly1305deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: gravity_spheres_volume/dim_512/ao/real_timeopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenssl: ChaCha20mt-dgemm: Sustained Floating-Point Rateopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenssl: RSA4096deepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamopenvino: Person Vehicle Bike Detection FP16 - CPUopenssl: AES-128-GCMdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamopenssl: AES-256-GCMtensorflow: CPU - 16 - ResNet-50openvino: Person Detection FP16 - CPUospray: gravity_spheres_volume/dim_512/pathtracer/real_timeospray-studio: 3 - 4K - 1 - Path Tracer - CPUospray-studio: 1 - 4K - 1 - Path Tracer - CPUospray-studio: 3 - 4K - 32 - Path Tracer - CPUospray-studio: 1 - 4K - 32 - Path Tracer - CPUospray-studio: 3 - 4K - 16 - Path Tracer - CPUxmrig: GhostRider - 1Mopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUospray-studio: 1 - 4K - 16 - Path Tracer - CPUoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyembree: Pathtracer ISPC - Asian Dragonxmrig: Wownero - 1Measywave: e2Asean Grid + BengkuluSept2007 Source - 1200embree: Pathtracer ISPC - Crownrocksdb: Rand Readdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamopenvino: Face Detection FP16-INT8 - CPUspeedb: Rand Readdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamy-cruncher: 1Bospray: particle_volume/scivis/real_timeopenvino: Handwritten English Recognition FP16-INT8 - CPUospray: particle_volume/ao/real_timeeasywave: e2Asean Grid + BengkuluSept2007 Source - 2400blender: Barbershop - CPU-Onlyopenssl: SHA512deepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamy-cruncher: 500Mopenssl: RSA4096compress-7zip: Decompression Ratingv-ray: CPUdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamxmrig: KawPow - 1Mxmrig: CryptoNight-Femto UPX2 - 1Mopenssl: SHA256xmrig: Monero - 1Mxmrig: CryptoNight-Heavy - 1Mcompress-7zip: Compression Ratingblender: Fishy Cat - CPU-Onlyindigobench: CPU - Supercarblender: Pabellon Barcelona - CPU-Onlyblender: Classroom - CPU-Onlyindigobench: CPU - Bedroomdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamsvt-av1: Preset 12 - Bosphorus 4Kblender: BMW27 - CPU-Onlyquantlib: Multi-Threadednginx: 1000deepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streammemtier-benchmark: Redis - 100 - 1:10svt-av1: Preset 8 - Bosphorus 4Knginx: 500memtier-benchmark: Redis - 100 - 1:5build-llvm: Ninjanamd: ATPase Simulation - 327,506 Atomsopenvino: Vehicle Detection FP16-INT8 - CPUbuild-linux-kernel: allmodconfigbuild-nodejs: Time To Compileuvg266: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Super Fastopenfoam: drivaerFastback, Small Mesh Size - Execution Timeuvg266: Bosphorus 4K - Mediumgpaw: Carbon Nanotubelammps: 20k Atomsffmpeg: libx265 - Platformffmpeg: libx265 - Video On Demandffmpeg: libx265 - Uploadbuild-ffmpeg: Time To Compilesvt-av1: Preset 4 - Bosphorus 4Kspeedb: Read While Writinguvg266: Bosphorus 4K - Ultra Fastbuild-llvm: Unix Makefilesopenvino: Face Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamopenvino: Face Detection Retail FP16-INT8 - CPUffmpeg: libx265 - Livecloverleaf: clover_bm16vvenc: Bosphorus 4K - Fastx265: Bosphorus 4Kcloverleaf: clover_bm64_shortopenvino: Machine Translation EN To DE FP16 - CPUbuild-linux-kernel: defconfigspeedb: Read Rand Write Randincompact3d: input.i3d 193 Cells Per Directionbuild-gem5: Time To Compilevvenc: Bosphorus 4K - Fasterdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamapache-iotdb: 500 - 100 - 800 - 100apache-iotdb: 500 - 100 - 800 - 100rav1e: 10speedb: Update Randrocksdb: Read Rand Write Randapache-iotdb: 800 - 100 - 500 - 100apache-iotdb: 500 - 100 - 800 - 400apache-iotdb: 800 - 100 - 500 - 100openfoam: drivaerFastback, Medium Mesh Size - Execution Timepytorch: CPU - 256 - ResNet-50deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streampytorch: CPU - 1 - ResNet-50ospray: particle_volume/pathtracer/real_timeopenradioss: Chrysler Neon 1Mdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamrocksdb: Update Randapache-iotdb: 500 - 100 - 800 - 400rav1e: 6cassandra: Writesquicksilver: CORAL2 P1openvino: Road Segmentation ADAS FP16-INT8 - CPUapache-iotdb: 500 - 100 - 500 - 400kripke: apache-iotdb: 500 - 100 - 500 - 100apache-iotdb: 500 - 100 - 500 - 100rav1e: 5duckdb: IMDBdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamapache-iotdb: 500 - 100 - 500 - 400rav1e: 1apache: 1000apache-iotdb: 800 - 100 - 200 - 100apache-iotdb: 800 - 100 - 200 - 400incompact3d: X3D-benchmarking input.i3dopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeapache-iotdb: 800 - 100 - 200 - 100openfoam: drivaerFastback, Small Mesh Size - Mesh Timequicksilver: CTS2openvino: Person Vehicle Bike Detection FP16 - CPUapache-iotdb: 800 - 100 - 200 - 400duckdb: TPC-H Parquetapache-iotdb: 500 - 100 - 200 - 100apache-iotdb: 500 - 100 - 200 - 400apache-iotdb: 500 - 100 - 200 - 100openvino: Face Detection Retail FP16-INT8 - CPUapache-iotdb: 800 - 100 - 800 - 100apache-iotdb: 500 - 100 - 200 - 400openvino: Person Detection FP16 - CPUapache-iotdb: 800 - 100 - 800 - 400apache-iotdb: 800 - 100 - 800 - 400quicksilver: CORAL2 P2gromacs: MPI CPU - water_GMX50_barespecfem3d: Tomographic Modelspecfem3d: Mount St. Helensspecfem3d: Homogeneous Halfspacespecfem3d: Water-layered Halfspacespecfem3d: Layered Halfspacesvt-av1: Preset 13 - Bosphorus 4Kmrbayes: Primate Phylogeny Analysisrocksdb: Read While Writingapache-iotdb: 800 - 100 - 800 - 100apache-iotdb: 800 - 100 - 500 - 400apache-iotdb: 800 - 100 - 500 - 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN295.8014.220355.501356.12214.24541.3284.68303154906909.29922.466922.57829149.49189.05479200259673.79079913011.104510.7260.2496471.3897645009487131.7605899484286979.8243.914.148411005084783316432806061711881070.12.431455280.4821.831510414.7148.07718.36138479820490.662413.25972094.21868670411701.374710.754510.8070142.7964144.682933.9235.22116169.045.28931352.687767.15831618417070.558670.339515.693293924.113441720175155.70196937.96957.2270568304007044.27081.0123934101.208.580247.24192.803.99161.393470.52573.0064481.7100664.35121.20931183656.9726.252103269.831142464.16435.0540.9795927.01755.017387.65222.2723.44126.19088.73142.16513.87221.0321.0410.3939.7893.060614567927.21529.7173.82377.40102.6582877.4958.23971.503.29114.52108.60193.3376.300143607437.4064191388.0236.493176.43171200.1003127.26587740906.9712015551509184569938115944433482.071179.254121.211460.70411457.9155111.898826.7298.4413499.30110.4484290618421.302.9371528871299666753.47528491251873759335375994085.072.249199.014226.3744226.9518294.750.56388038.284604958945921074818.054118231.7444639.4044.445311142666716.95147.89245.742387122633817645646.299.158403756166.00181.92488.6460237625150133331.99230.28359304029.95188620338.06317925074.95062589678.67990438467.934201.1823371876129.77318.24570374412902.57117.5742939.3562921.653116.866309.8211.9720887725424764.036116.808917.2986977.071229.1629791535049322.95331574625.6125217.01444.90672602.27528178897353696.514646081485319050.27218.0719.6434219618567678565725412784376.00.60360851.8483.197539663.338.88467.9033302674440322.281346.8734595.92304542944495.144236.755536.9206484.8697484.732610.23317.048451.9617.0993109.847240.3526271960547221.3018219.91195.099889214.2406021609113821.924120720.820699.57985740178320716.520541.835809335.3724.52286.5767.9111.17222.1179194.54727.07171336.6266322.5545.88183084431.3767.209263177.492901182.23173.8680.3917510.90307.653160.72552.5955.0154.55916819.8763.04531.00746.9646.9823.1818.0616.6721294750755.98261.16153.515276.118.35608840.41114.95497.096.28027.5457.38103.1241.709257756420.8747749217.12611.56499.1066674.260871.6710417322012.35535660226542869953170910339763847.19679.7899236.56855.9304855.734065.913945.13166.152297.7265.9305483387254.314.8612514342132666732.67862783483031072008653027252.953.581125.100144.1447145.1134191.770.853130116.686793722667712944562.359884159.5742927.1630.9512471631666712.21106.91178.435513966985039688435.587.1073031288133.01146.53394.517098416616176667196.423126.9696918267101.60195.4991869780OpenBenchmarking.org

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN6001200180024003000SE +/- 0.35, N = 3SE +/- 5.14, N = 3295.802902.571. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 0.01, N = 3SE +/- 0.10, N = 314.22117.571. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.16670.33340.50010.66680.83350.0210.741
MinAvgMaxZen 1 - EPYC 7601263678697Zen 4C - EPYC 8534PN14159175OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN6001200180024003000SE +/- 0.27, N = 3SE +/- 2.46, N = 3355.502939.361. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN6001200180024003000SE +/- 0.94, N = 3SE +/- 5.71, N = 6356.122921.651. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 0.04, N = 3SE +/- 0.23, N = 614.25116.871. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.23290.46580.69870.93161.16450.0221.035
MinAvgMaxZen 1 - EPYC 7601266655707Zen 4C - EPYC 8534PN15113173OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN70140210280350SE +/- 0.10, N = 3SE +/- 0.68, N = 341.32309.821. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.00, N = 3SE +/- 0.01, N = 384.6811.97MIN: 84.05 / MAX: 93.44MIN: 6.19 / MAX: 26.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601262601630Zen 4C - EPYC 8534PN15153164OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

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 3.1Algorithm: ChaCha20-Poly1305Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN40000M80000M120000M160000M200000MSE +/- 12075597.72, N = 3SE +/- 493572176.62, N = 3303154906902088772542471. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN300M600M900M1200M1500M44247682.051253276194.47
MinAvgMaxZen 1 - EPYC 7601265685711Zen 4C - EPYC 8534PN14167178OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1428425670SE +/- 0.0191, N = 3SE +/- 0.1281, N = 39.299264.0361

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 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN48121620SE +/- 0.01722, N = 3SE +/- 0.01858, N = 32.4669216.80890
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.02540.05080.07620.10160.1270.0040.113
MinAvgMaxZen 1 - EPYC 7601264621710Zen 4C - EPYC 8534PN14148175OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN48121620SE +/- 0.00282, N = 3SE +/- 0.03849, N = 32.5782917.29860
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.02630.05260.07890.10520.13150.0040.117
MinAvgMaxZen 1 - EPYC 7601163621710Zen 4C - EPYC 8534PN14148176OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN2004006008001000SE +/- 0.14, N = 3SE +/- 2.89, N = 3149.49977.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30060090012001500SE +/- 0.70, N = 3SE +/- 0.72, N = 3189.051229.161. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 3.1Algorithm: ChaCha20Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN60000M120000M180000M240000M300000MSE +/- 23640894.78, N = 3SE +/- 69144081.68, N = 3479200259672979153504931. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: ChaCha20Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN400M800M1200M1600M2000M69962511.271780848824.50
MinAvgMaxZen 1 - EPYC 7601265685711Zen 4C - EPYC 8534PN13167179OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor2004006008001000

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 RateZen 1 - EPYC 7601Zen 4C - EPYC 8534PN510152025SE +/- 0.057778, N = 15SE +/- 0.145648, N = 53.79079922.9533151. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.04590.09180.13770.18360.22950.0060.204
MinAvgMaxZen 1 - EPYC 7601264618679Zen 4C - EPYC 8534PN12113175OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN16K32K48K64K80KSE +/- 3.60, N = 3SE +/- 275.21, N = 313011.1074625.611. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN5K10K15K20K25KSE +/- 8.66, N = 3SE +/- 24.99, N = 34510.725217.01. (CC) gcc options: -pthread -m64 -O3 -ldl

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30060090012001500SE +/- 1.56, N = 3SE +/- 0.50, N = 3260.251444.91

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN6001200180024003000SE +/- 1.63, N = 3SE +/- 1.69, N = 3471.382602.271. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 3.1Algorithm: AES-128-GCMZen 1 - EPYC 7601Zen 4C - EPYC 8534PN110000M220000M330000M440000M550000MSE +/- 101833027.65, N = 3SE +/- 261674063.26, N = 3976450094875281788973531. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMZen 1 - EPYC 7601Zen 4C - EPYC 8534PN700M1400M2100M2800M3500M139836719.653235378886.06
MinAvgMaxZen 1 - EPYC 7601264698712Zen 4C - EPYC 8534PN14163170OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN150300450600750SE +/- 1.27, N = 3SE +/- 1.12, N = 3131.76696.51

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 3.1Algorithm: AES-256-GCMZen 1 - EPYC 7601Zen 4C - EPYC 8534PN100000M200000M300000M400000M500000MSE +/- 95870018.66, N = 3SE +/- 158535708.73, N = 3899484286974608148531901. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMZen 1 - EPYC 7601Zen 4C - EPYC 8534PN600M1200M1800M2400M3000M128846358.682821056038.23
MinAvgMaxZen 1 - EPYC 7601264698712Zen 4C - EPYC 8534PN14163170OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor2004006008001000

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN1122334455SE +/- 0.04, N = 3SE +/- 0.04, N = 39.8250.27
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.13430.26860.40290.53720.67150.0190.597
MinAvgMaxZen 1 - EPYC 7601262.6524.0574.5Zen 4C - EPYC 8534PN13.684.2118.3OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.12CPU Power Consumption Monitor140280420560700

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250SE +/- 0.09, N = 3SE +/- 0.21, N = 343.91218.071. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN510152025SE +/- 0.01550, N = 3SE +/- 0.02744, N = 34.1484119.64340
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.03080.06160.09240.12320.1540.0070.137
MinAvgMaxZen 1 - EPYC 7601263635708Zen 4C - EPYC 8534PN14143171OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor2004006008001000

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 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN2K4K6K8K10KSE +/- 34.23, N = 3SE +/- 3.51, N = 3100502196
MinAvgMaxZen 1 - EPYC 7601146579715Zen 4C - EPYC 8534PN14129165OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN2K4K6K8K10KSE +/- 16.50, N = 3SE +/- 2.08, N = 384781856
MinAvgMaxZen 1 - EPYC 7601263579715Zen 4C - EPYC 8534PN14128164OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN70K140K210K280K350KSE +/- 188.22, N = 3SE +/- 336.36, N = 333164376785
MinAvgMaxZen 1 - EPYC 7601261670715Zen 4C - EPYC 8534PN15134164OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN60K120K180K240K300KSE +/- 353.76, N = 3SE +/- 237.26, N = 328060665725
MinAvgMaxZen 1 - EPYC 7601263664715Zen 4C - EPYC 8534PN14130163OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN40K80K120K160K200KSE +/- 133.22, N = 3SE +/- 228.15, N = 317118841278
MinAvgMaxZen 1 - EPYC 7601262638714Zen 4C - EPYC 8534PN14117164OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor2004006008001000

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 Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN9001800270036004500SE +/- 6.67, N = 3SE +/- 5.88, N = 31070.14376.01. (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 6.21Variant: GhostRider - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN8162432401.91435.252
OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN100200300400500Min: 265.39 / Avg: 559.12 / Max: 586.02Min: 14.85 / Avg: 124.14 / Max: 127.72

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.54681.09361.64042.18722.734SE +/- 0.00, N = 3SE +/- 0.00, N = 32.430.60MIN: 2.39 / MAX: 10.02MIN: 0.27 / MAX: 24.871. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601259630678Zen 4C - EPYC 8534PN14140152OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

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 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30K60K90K120K150KSE +/- 81.84, N = 3SE +/- 45.84, N = 314552836085
MinAvgMaxZen 1 - EPYC 7601264631714Zen 4C - EPYC 8534PN14111163OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor2004006008001000

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.4140.8281.2421.6562.07SE +/- 0.00, N = 3SE +/- 0.00, N = 30.481.84
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.00340.00680.01020.01360.0170.0010.015
MinAvgMaxZen 1 - EPYC 7601263656700Zen 4C - EPYC 8534PN14123153OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.1CPU Power Consumption Monitor2004006008001000

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) 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 4.3Binary: Pathtracer ISPC - Model: Asian DragonZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.05, N = 3SE +/- 0.04, N = 521.8383.20MIN: 21.6 / MAX: 22.16MIN: 82.46 / MAX: 84.5
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.15230.30460.45690.60920.76150.0340.677
MinAvgMaxZen 1 - EPYC 7601266649712Zen 4C - EPYC 8534PN15123180OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor2004006008001000

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 Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN8K16K24K32K40KSE +/- 27.32, N = 3SE +/- 114.17, N = 310414.739663.31. (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 6.21Variant: Wownero - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN6012018024030015.73259.25
MinAvgMaxZen 1 - EPYC 7601264662706Zen 4C - EPYC 8534PN15153180OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor2004006008001000

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 1.77, N = 4SE +/- 0.29, N = 3148.0838.881. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxZen 1 - EPYC 7601265.0522.7590.2Zen 4C - EPYC 8534PN13.989.2104.3OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor160320480640800

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) 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 4.3Binary: Pathtracer ISPC - Model: CrownZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1530456075SE +/- 0.09, N = 3SE +/- 0.09, N = 518.3667.90MIN: 18.01 / MAX: 18.84MIN: 66.05 / MAX: 70.27
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.11680.23360.35040.46720.5840.0280.519
MinAvgMaxZen 1 - EPYC 7601265660715Zen 4C - EPYC 8534PN14131178OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor2004006008001000

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Random ReadZen 1 - EPYC 7601Zen 4C - EPYC 8534PN60M120M180M240M300MSE +/- 416491.60, N = 3SE +/- 1581555.58, N = 3847982043026744401. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 8.0Test: Random ReadZen 1 - EPYC 7601Zen 4C - EPYC 8534PN400K800K1200K1600K2000K125079.641925962.53
MinAvgMaxZen 1 - EPYC 7601259678714Zen 4C - EPYC 8534PN15157169OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 8.0CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN70140210280350SE +/- 0.85, N = 6SE +/- 0.25, N = 390.66322.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1122334455SE +/- 0.06, N = 3SE +/- 0.03, N = 313.2646.87

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN400800120016002000SE +/- 0.06, N = 3SE +/- 2.44, N = 32094.21595.92MIN: 2092.79 / MAX: 2112.41MIN: 511.76 / MAX: 618.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601257592660Zen 4C - EPYC 8534PN14148164OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

Speedb

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

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadZen 1 - EPYC 7601Zen 4C - EPYC 8534PN70M140M210M280M350MSE +/- 795244.11, N = 3SE +/- 908871.00, N = 3868670413045429441. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random ReadZen 1 - EPYC 7601Zen 4C - EPYC 8534PN400K800K1200K1600K2000K128090.201947735.76
MinAvgMaxZen 1 - EPYC 7601259678714Zen 4C - EPYC 8534PN14156169OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN400800120016002000SE +/- 3.29, N = 3SE +/- 1.38, N = 31701.37495.14
MinAvgMaxZen 1 - EPYC 7601264582695Zen 4C - EPYC 8534PN14135164OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN816243240SE +/- 0.04, N = 3SE +/- 0.06, N = 310.7536.76

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN816243240SE +/- 0.07, N = 3SE +/- 0.10, N = 310.8136.92

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN100200300400500SE +/- 1.66, N = 3SE +/- 0.12, N = 3142.80484.87

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN100200300400500SE +/- 0.49, N = 3SE +/- 0.29, N = 3144.68484.73

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1BZen 1 - EPYC 7601Zen 4C - EPYC 8534PN816243240SE +/- 0.09, N = 3SE +/- 0.01, N = 433.9210.23
MinAvgMaxZen 1 - EPYC 7601263602718Zen 4C - EPYC 8534PN1396170OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor2004006008001000

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 2.12Benchmark: particle_volume/scivis/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN48121620SE +/- 0.00822, N = 3SE +/- 0.05559, N = 35.2211617.04840
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.02810.05620.08430.11240.14050.0080.125
MinAvgMaxZen 1 - EPYC 7601263623704Zen 4C - EPYC 8534PN14136173OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 0.65, N = 3SE +/- 0.03, N = 3169.0451.96MIN: 141.74 / MAX: 192.16MIN: 33.44 / MAX: 81.121. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601260670709Zen 4C - EPYC 8534PN15163176OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

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 2.12Benchmark: particle_volume/ao/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN48121620SE +/- 0.01171, N = 3SE +/- 0.01999, N = 35.2893117.09930
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.02340.04680.07020.09360.1170.0080.104
MinAvgMaxZen 1 - EPYC 7601265681703Zen 4C - EPYC 8534PN14164173OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor2004006008001000

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN80160240320400SE +/- 6.02, N = 6SE +/- 0.43, N = 3352.69109.851. (CXX) g++ options: -O3 -fopenmp
OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN100200300400500Min: 247.92 / Avg: 525.08 / Max: 591.62Min: 13.77 / Avg: 94.5 / Max: 104.72

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-OnlyZen 1 - EPYC 7601Zen 4C - EPYC 8534PN170340510680850SE +/- 0.52, N = 3SE +/- 0.15, N = 3767.15240.35
OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN130260390520650Min: 263.91 / Avg: 701.51 / Max: 715.33Min: 14.68 / Avg: 156.64 / Max: 175.71

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 3.1Algorithm: SHA512Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN6000M12000M18000M24000M30000MSE +/- 6971539.66, N = 3SE +/- 5378103.90, N = 38316184170262719605471. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: SHA512Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN30M60M90M120M150M11909195.29154779847.68
MinAvgMaxZen 1 - EPYC 7601264698712Zen 4C - EPYC 8534PN14170178OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250SE +/- 0.11, N = 3SE +/- 0.29, N = 370.56221.30

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250SE +/- 0.21, N = 3SE +/- 0.36, N = 370.34219.91

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN48121620SE +/- 0.118, N = 3SE +/- 0.006, N = 515.6935.099
MinAvgMaxZen 1 - EPYC 7601262543712Zen 4C - EPYC 8534PN1476156OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor2004006008001000

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 3.1Algorithm: RSA4096Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN200K400K600K800K1000KSE +/- 361.69, N = 3SE +/- 395.01, N = 3293924.1889214.21. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgverify/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: RSA4096Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN13002600390052006500432.835928.92
MinAvgMaxZen 1 - EPYC 7601262679712Zen 4C - EPYC 8534PN15150171OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor2004006008001000

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN90K180K270K360K450KSE +/- 1450.84, N = 3SE +/- 942.48, N = 31344174060211. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN6001200180024003000214.292960.25
MinAvgMaxZen 1 - EPYC 7601262627714Zen 4C - EPYC 8534PN13137180OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption Monitor2004006008001000

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5.02Mode: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN13K26K39K52K65KSE +/- 15.72, N = 3SE +/- 764.13, N = 32017560911
OpenBenchmarking.orgvsamples Per Watt, More Is BetterChaos Group V-RAY 5.02Mode: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN10020030040050034.52463.07
MinAvgMaxZen 1 - EPYC 7601259584716Zen 4C - EPYC 8534PN14132176OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 5.02CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN8001600240032004000SE +/- 0.49, N = 3SE +/- 7.35, N = 3155.703821.92

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 Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4K8K12K16K20KSE +/- 60.77, N = 12SE +/- 3.75, N = 36937.920720.81. (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 6.21Variant: KawPow - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30609012015010.77135.71
OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN120240360480600Min: 266.23 / Avg: 644.06 / Max: 679.56Min: 14.84 / Avg: 152.68 / Max: 167.62

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4K8K12K16K20KSE +/- 75.94, N = 12SE +/- 7.38, N = 36957.220699.51. (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 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30609012015010.81136.92
OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN120240360480600Min: 227.27 / Avg: 643.82 / Max: 681.92Min: 14.85 / Avg: 151.18 / Max: 167.35

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 3.1Algorithm: SHA256Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20000M40000M60000M80000M100000MSE +/- 48383276.04, N = 3SE +/- 59376757.34, N = 327056830400798574017831. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: SHA256Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN100M200M300M400M500M38850033.87476985790.76
MinAvgMaxZen 1 - EPYC 7601261696713Zen 4C - EPYC 8534PN14167179OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor2004006008001000

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 Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4K8K12K16K20KSE +/- 58.63, N = 3SE +/- 8.43, N = 37044.220716.51. (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 6.21Variant: Monero - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30609012015010.86140.28
MinAvgMaxZen 1 - EPYC 7601264649683Zen 4C - EPYC 8534PN14148165OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4K8K12K16K20KSE +/- 21.41, N = 3SE +/- 174.63, N = 37081.020541.81. (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 6.21Variant: CryptoNight-Heavy - Hash Count: 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30609012015010.98135.43
MinAvgMaxZen 1 - EPYC 7601266645679Zen 4C - EPYC 8534PN15152168OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor2004006008001000

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN80K160K240K320K400KSE +/- 1034.27, N = 3SE +/- 548.98, N = 31239343580931. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: CPU-OnlyZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.13, N = 3SE +/- 0.08, N = 3101.2035.37
MinAvgMaxZen 1 - EPYC 7601265681714Zen 4C - EPYC 8534PN15147171OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor2004006008001000

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarZen 1 - EPYC 7601Zen 4C - EPYC 8534PN612182430SE +/- 0.050, N = 3SE +/- 0.040, N = 38.58024.522
OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.04190.08380.12570.16760.20950.0130.186
MinAvgMaxZen 1 - EPYC 7601263666719Zen 4C - EPYC 8534PN14132171OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4CPU Power Consumption Monitor2004006008001000

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: CPU-OnlyZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250SE +/- 0.13, N = 3SE +/- 0.13, N = 3247.2486.57
MinAvgMaxZen 1 - EPYC 7601264698715Zen 4C - EPYC 8534PN15152171OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-OnlyZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 1.40, N = 3SE +/- 0.09, N = 3192.8067.91
MinAvgMaxZen 1 - EPYC 7601263696717Zen 4C - EPYC 8534PN15150169OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor2004006008001000

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN3691215SE +/- 0.022, N = 3SE +/- 0.005, N = 33.99111.172
OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.01670.03340.05010.06680.08350.0060.074
MinAvgMaxZen 1 - EPYC 7601263662717Zen 4C - EPYC 8534PN14151166OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1428425670SE +/- 0.36, N = 3SE +/- 0.01, N = 361.3922.12
MinAvgMaxZen 1 - EPYC 7601260558711Zen 4C - EPYC 8534PN14117155OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

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 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 0.80, N = 15SE +/- 1.97, N = 670.53194.551. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.85321.70642.55963.41284.2660.1763.792
MinAvgMaxZen 1 - EPYC 7601144400660Zen 4C - EPYC 8534PN1351122OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor2004006008001000

Blender

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

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-OnlyZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1632486480SE +/- 0.35, N = 3SE +/- 0.12, N = 373.0027.07
MinAvgMaxZen 1 - EPYC 7601261677715Zen 4C - EPYC 8534PN14136169OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor2004006008001000

QuantLib

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

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedZen 1 - EPYC 7601Zen 4C - EPYC 8534PN40K80K120K160K200KSE +/- 8.17, N = 3SE +/- 779.11, N = 364481.7171336.61. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedZen 1 - EPYC 7601Zen 4C - EPYC 8534PN200400600800100095.991133.59
MinAvgMaxZen 1 - EPYC 7601258672716Zen 4C - EPYC 8534PN13151177OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor2004006008001000

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN60K120K180K240K300KSE +/- 212.46, N = 3SE +/- 312.48, N = 3100664.35266322.551. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 1000Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN30060090012001500148.961587.79
MinAvgMaxZen 1 - EPYC 7601258676713Zen 4C - EPYC 8534PN14168180OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 1.16, N = 3SE +/- 0.07, N = 3121.2145.88
MinAvgMaxZen 1 - EPYC 7601265568712Zen 4C - EPYC 8534PN14120157OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

Redis 7.0.12 + memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN700K1400K2100K2800K3500KSE +/- 1850.76, N = 3SE +/- 25227.98, N = 91183656.973084431.371. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN5K10K15K20K25K1836.8623505.65
MinAvgMaxZen 1 - EPYC 7601260644714Zen 4C - EPYC 8534PN14131153OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.12 + memtier_benchmark 2.0CPU Power Consumption Monitor2004006008001000

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 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1530456075SE +/- 0.17, N = 3SE +/- 0.10, N = 426.2567.211. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.2030.4060.6090.8121.0150.0520.902
MinAvgMaxZen 1 - EPYC 7601262502689Zen 4C - EPYC 8534PN1374129OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor2004006008001000

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN60K120K180K240K300KSE +/- 450.48, N = 3SE +/- 1464.33, N = 3103269.83263177.491. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 500Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN30060090012001500153.161570.36
MinAvgMaxZen 1 - EPYC 7601240674714Zen 4C - EPYC 8534PN12168180OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor2004006008001000

Redis 7.0.12 + memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN600K1200K1800K2400K3000KSE +/- 8571.80, N = 11SE +/- 25230.96, N = 31142464.162901182.231. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN5K10K15K20K25K1771.4522203.36
MinAvgMaxZen 1 - EPYC 7601266645715Zen 4C - EPYC 8534PN14131153OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.12 + memtier_benchmark 2.0CPU Power Consumption Monitor2004006008001000

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaZen 1 - EPYC 7601Zen 4C - EPYC 8534PN90180270360450SE +/- 1.49, N = 3SE +/- 0.09, N = 3435.05173.87
OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN130260390520650Min: 257.35 / Avg: 646.98 / Max: 716.05Min: 13.97 / Avg: 137.82 / Max: 180.02

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 AtomsZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.22040.44080.66120.88161.102SE +/- 0.00385, N = 3SE +/- 0.00016, N = 30.979590.39175
MinAvgMaxZen 1 - EPYC 7601265665714Zen 4C - EPYC 8534PN15145168OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 2.14CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 327.0110.90MIN: 26.86 / MAX: 38.57MIN: 5.86 / MAX: 22.421. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601261616662Zen 4C - EPYC 8534PN14147159OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

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 6.1Build: allmodconfigZen 1 - EPYC 7601Zen 4C - EPYC 8534PN160320480640800SE +/- 0.57, N = 3SE +/- 0.63, N = 3755.02307.65
OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN130260390520650Min: 254.27 / Avg: 676.95 / Max: 718.77Min: 13.8 / Avg: 150.86 / Max: 177.47

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 19.8.1Time To CompileZen 1 - EPYC 7601Zen 4C - EPYC 8534PN80160240320400SE +/- 0.64, N = 3SE +/- 0.12, N = 3387.65160.73
MinAvgMaxZen 1 - EPYC 7601144624717Zen 4C - EPYC 8534PN14128180OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 19.8.1CPU Power Consumption Monitor2004006008001000

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1224364860SE +/- 0.08, N = 3SE +/- 0.04, N = 522.2752.59
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.10690.21380.32070.42760.53450.0360.475
MinAvgMaxZen 1 - EPYC 7601260613686Zen 4C - EPYC 8534PN14111151OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1224364860SE +/- 0.01, N = 3SE +/- 0.07, N = 523.4455.01
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.11250.2250.33750.450.56250.0380.500
MinAvgMaxZen 1 - EPYC 7601264618689Zen 4C - EPYC 8534PN14110151OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor2004006008001000

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150126.1954.561. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
MinAvgMaxZen 1 - EPYC 7601262657703Zen 4C - EPYC 8534PN12158176OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor2004006008001000

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumZen 1 - EPYC 7601Zen 4C - EPYC 8534PN510152025SE +/- 0.04, N = 3SE +/- 0.03, N = 38.7319.87
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.03510.07020.10530.14040.17550.0130.156
MinAvgMaxZen 1 - EPYC 7601257656705Zen 4C - EPYC 8534PN13127152OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor2004006008001000

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 23.6Input: Carbon NanotubeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 0.91, N = 3SE +/- 0.20, N = 3142.1763.051. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
MinAvgMaxZen 1 - EPYC 7601258667715Zen 4C - EPYC 8534PN14155177OpenBenchmarking.orgWatts, Fewer Is BetterGPAW 23.6CPU Power Consumption Monitor2004006008001000

LAMMPS Molecular Dynamics Simulator

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

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsZen 1 - EPYC 7601Zen 4C - EPYC 8534PN714212835SE +/- 0.05, N = 3SE +/- 0.03, N = 313.8731.011. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.03960.07920.11880.15840.1980.0200.176
OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN120240360480600Min: 262.81 / Avg: 690.49 / Max: 703.09Min: 14.4 / Avg: 176.23 / Max: 179.18

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1122334455SE +/- 0.02, N = 3SE +/- 0.04, N = 321.0346.961. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.17190.34380.51570.68760.85950.0600.764
MinAvgMaxZen 1 - EPYC 7601178.8350.2501.8Zen 4C - EPYC 8534PN13.161.579.3OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1122334455SE +/- 0.00, N = 3SE +/- 0.01, N = 321.0446.981. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.17190.34380.51570.68760.85950.0600.764
MinAvgMaxZen 1 - EPYC 7601251.1348.9503.6Zen 4C - EPYC 8534PN12.861.578.9OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadZen 1 - EPYC 7601Zen 4C - EPYC 8534PN612182430SE +/- 0.00, N = 3SE +/- 0.02, N = 310.3923.181. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.09020.18040.27060.36080.4510.0310.401
MinAvgMaxZen 1 - EPYC 7601251.3338.9555.2Zen 4C - EPYC 8534PN13.157.890.5OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor140280420560700

Timed FFmpeg Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.1Time To CompileZen 1 - EPYC 7601Zen 4C - EPYC 8534PN918273645SE +/- 0.10, N = 3SE +/- 0.03, N = 339.7918.06
MinAvgMaxZen 1 - EPYC 7601255526717Zen 4C - EPYC 8534PN1385178OpenBenchmarking.orgWatts, Fewer Is BetterTimed FFmpeg Compilation 6.1CPU Power Consumption Monitor2004006008001000

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 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN246810SE +/- 0.011, N = 3SE +/- 0.041, N = 33.0606.6721. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.01940.03880.05820.07760.0970.0060.086
MinAvgMaxZen 1 - EPYC 7601254498687Zen 4C - EPYC 8534PN1377134OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor2004006008001000

Speedb

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

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN3M6M9M12M15MSE +/- 67628.42, N = 3SE +/- 104743.64, N = 156145679129475071. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read While WritingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20K40K60K80K100K9060.4881136.79
MinAvgMaxZen 1 - EPYC 7601260678716Zen 4C - EPYC 8534PN13160180OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor2004006008001000

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1326395265SE +/- 0.04, N = 3SE +/- 0.14, N = 527.2155.98
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.12620.25240.37860.50480.6310.0460.561
MinAvgMaxZen 1 - EPYC 7601264589673Zen 4C - EPYC 8534PN13100137OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor2004006008001000

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesZen 1 - EPYC 7601Zen 4C - EPYC 8534PN110220330440550SE +/- 1.95, N = 3SE +/- 0.55, N = 3529.72261.16
OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN130260390520650Min: 254.39 / Avg: 594.06 / Max: 717.76Min: 13.35 / Avg: 112.54 / Max: 180.07

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsZen 4C - EPYC 8534PNZen 1 - EPYC 76015001000150020002500180.522562.10

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1224364860SE +/- 0.00, N = 3SE +/- 0.20, N = 33.8253.511. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN11002200330044005500SE +/- 0.02, N = 3SE +/- 6.62, N = 3377.405276.111. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.3037, N = 3SE +/- 0.0152, N = 3102.65828.3560
MinAvgMaxZen 1 - EPYC 7601259630707Zen 4C - EPYC 8534PN14127148OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN2K4K6K8K10KSE +/- 0.26, N = 3SE +/- 14.71, N = 3877.498840.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveZen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 0.07, N = 3SE +/- 0.14, N = 358.23114.951. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.44930.89861.34791.79722.24650.1741.997
MinAvgMaxZen 1 - EPYC 7601261.5334.7472.2Zen 4C - EPYC 8534PN13.757.678.3OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor120240360480600

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm16Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN2004006008001000SE +/- 1.74, N = 3SE +/- 0.79, N = 3971.50497.091. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN110220330440550Min: 263.25 / Avg: 593.38 / Max: 633.3Min: 14.57 / Avg: 130.07 / Max: 135.51

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN246810SE +/- 0.034, N = 3SE +/- 0.008, N = 33.2916.2801. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.01550.0310.04650.0620.07750.0060.069
MinAvgMaxZen 1 - EPYC 7601159513706Zen 4C - EPYC 8534PN1391137OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor2004006008001000

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 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN612182430SE +/- 0.17, N = 4SE +/- 0.05, N = 314.5227.541. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.08080.16160.24240.32320.4040.0280.359
MinAvgMaxZen 1 - EPYC 7601263.4516.7606.4Zen 4C - EPYC 8534PN13.176.798.8OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor160320480640800

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm64_shortZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 1.39, N = 3SE +/- 0.02, N = 3108.6057.381. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
MinAvgMaxZen 1 - EPYC 7601267587649Zen 4C - EPYC 8534PN15119130OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 0.49, N = 3SE +/- 0.21, N = 3193.33103.12MIN: 178.13 / MAX: 252.21MIN: 51.8 / MAX: 150.841. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601261665708Zen 4C - EPYC 8534PN14152170OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

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 6.1Build: defconfigZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.88, N = 3SE +/- 0.50, N = 476.3041.71
MinAvgMaxZen 1 - EPYC 7601257528717Zen 4C - EPYC 8534PN1495176OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption Monitor2004006008001000

Speedb

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

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN600K1200K1800K2400K3000KSE +/- 1989.50, N = 3SE +/- 17447.09, N = 3143607425775641. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read Random Write RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4K8K12K16K20K2268.9316894.41
MinAvgMaxZen 1 - EPYC 7601262633710Zen 4C - EPYC 8534PN15153173OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor2004006008001000

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 DirectionZen 1 - EPYC 7601Zen 4C - EPYC 8534PN918273645SE +/- 0.22, N = 3SE +/- 0.03, N = 337.4120.871. (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
MinAvgMaxZen 1 - EPYC 7601264578640Zen 4C - EPYC 8534PN14119152OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor2004006008001000

Timed Gem5 Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileZen 1 - EPYC 7601Zen 4C - EPYC 8534PN80160240320400SE +/- 4.50, N = 3SE +/- 2.38, N = 3388.02217.13
MinAvgMaxZen 1 - EPYC 7601225533719Zen 4C - EPYC 8534PN1394180OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 23.0.1CPU Power Consumption Monitor2004006008001000

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterZen 1 - EPYC 7601Zen 4C - EPYC 8534PN3691215SE +/- 0.018, N = 3SE +/- 0.020, N = 36.49311.5641. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.02950.0590.08850.1180.14750.0130.131
MinAvgMaxZen 1 - EPYC 7601261519649Zen 4C - EPYC 8534PN1488122OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 1.64, N = 6SE +/- 0.07, N = 3176.4399.11
MinAvgMaxZen 1 - EPYC 7601261604711Zen 4C - EPYC 8534PN14132162OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30060090012001500SE +/- 3.61, N = 3SE +/- 0.35, N = 31200.10674.26
MinAvgMaxZen 1 - EPYC 7601268452713Zen 4C - EPYC 8534PN1498173OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 0.22, N = 3SE +/- 0.06, N = 3127.2671.67MAX: 10220.3MAX: 10076.95
MinAvgMaxZen 1 - EPYC 7601252497735Zen 4C - EPYC 8534PN1370149OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20M40M60M80M100MSE +/- 85534.45, N = 3SE +/- 102156.43, N = 358774090104173220

rav1e

Xiph rav1e is a Rust-written AV1 video encoder that claims to be the fastest and safest AV1 encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 10Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN3691215SE +/- 0.080, N = 3SE +/- 0.020, N = 36.97112.355
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterrav1e 0.7Speed: 10Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.05090.10180.15270.20360.25450.0200.226
MinAvgMaxZen 1 - EPYC 7601252.3344.6364.8Zen 4C - EPYC 8534PN12.554.759.1OpenBenchmarking.orgWatts, Fewer Is Betterrav1e 0.7CPU Power Consumption Monitor100200300400500

Speedb

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

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN80K160K240K320K400KSE +/- 239.59, N = 3SE +/- 832.97, N = 32015553566021. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Update RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN7001400210028003500396.183398.27
MinAvgMaxZen 1 - EPYC 7601261.5508.7579.5Zen 4C - EPYC 8534PN14.4104.9121.7OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor160320480640800

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read Random Write RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN600K1200K1800K2400K3000KSE +/- 4649.81, N = 3SE +/- 22479.06, N = 15150918426542861. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 8.0Test: Read Random Write RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4K8K12K16K20K2244.5516345.97
MinAvgMaxZen 1 - EPYC 7601268672711Zen 4C - EPYC 8534PN14162177OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 8.0CPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20M40M60M80M100MSE +/- 197187.95, N = 3SE +/- 349666.50, N = 35699381199531709

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20M40M60M80M100MSE +/- 470631.65, N = 3SE +/- 417895.46, N = 359444334103397638

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.21, N = 3SE +/- 0.08, N = 382.0747.19MAX: 23993.13MAX: 23867.11
MinAvgMaxZen 1 - EPYC 7601252498718Zen 4C - EPYC 8534PN1369148OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN300600900120015001179.25679.791. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN120240360480600Min: 262.83 / Avg: 640.83 / Max: 704.84Min: 13.48 / Avg: 155.34 / Max: 173.05

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN816243240SE +/- 0.22, N = 3SE +/- 0.11, N = 321.2136.56MIN: 13.9 / MAX: 22.04MIN: 35.25 / MAX: 37.29
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.0880.1760.2640.3520.440.0320.391
MinAvgMaxZen 1 - EPYC 7601261653699Zen 4C - EPYC 8534PN1393106OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption Monitor2004006008001000

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30060090012001500SE +/- 2.60, N = 3SE +/- 0.81, N = 31460.70855.93
MinAvgMaxZen 1 - EPYC 7601261572712Zen 4C - EPYC 8534PN14133175OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN30060090012001500SE +/- 5.55, N = 3SE +/- 0.50, N = 31457.92855.73
MinAvgMaxZen 1 - EPYC 7601262572712Zen 4C - EPYC 8534PN14133176OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 1.29, N = 3SE +/- 0.01, N = 3111.9065.91

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN1020304050SE +/- 0.12, N = 3SE +/- 0.15, N = 326.7245.13MIN: 15.15 / MAX: 28.15MIN: 43.52 / MAX: 46.26
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.15460.30920.46380.61840.7730.0430.687
MinAvgMaxZen 1 - EPYC 7601263620701Zen 4C - EPYC 8534PN136699OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption Monitor2004006008001000

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 2.12Benchmark: particle_volume/pathtracer/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 0.08, N = 3SE +/- 0.13, N = 398.44166.15
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.2630.5260.7891.0521.3150.1621.169
MinAvgMaxZen 1 - EPYC 7601262607699Zen 4C - EPYC 8534PN14142174OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor2004006008001000

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MZen 1 - EPYC 7601Zen 4C - EPYC 8534PN110220330440550SE +/- 0.62, N = 3SE +/- 0.36, N = 3499.30297.72
OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN120240360480600Min: 266.19 / Avg: 628.45 / Max: 689.13Min: 14.51 / Avg: 144.84 / Max: 161.81

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.40, N = 3SE +/- 0.04, N = 3110.4565.93
MinAvgMaxZen 1 - EPYC 7601260637710Zen 4C - EPYC 8534PN14135157OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Update RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN100K200K300K400K500KSE +/- 737.50, N = 3SE +/- 566.63, N = 32906184833871. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 8.0Test: Update RandomZen 1 - EPYC 7601Zen 4C - EPYC 8534PN8001600240032004000502.973799.25
MinAvgMaxZen 1 - EPYC 7601264578641Zen 4C - EPYC 8534PN15127140OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 8.0CPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN90180270360450SE +/- 5.76, N = 3SE +/- 2.13, N = 3421.30254.31MAX: 27834.33MAX: 27111.61
MinAvgMaxZen 1 - EPYC 7601253496697Zen 4C - EPYC 8534PN1371151OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

rav1e

Xiph rav1e is a Rust-written AV1 video encoder that claims to be the fastest and safest AV1 encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 6Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN1.09372.18743.28114.37485.4685SE +/- 0.003, N = 3SE +/- 0.020, N = 32.9374.861
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterrav1e 0.7Speed: 6Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.02030.04060.06090.08120.10150.0080.090
MinAvgMaxZen 1 - EPYC 7601258.0367.6413.4Zen 4C - EPYC 8534PN12.654.362.3OpenBenchmarking.orgWatts, Fewer Is Betterrav1e 0.7CPU Power Consumption Monitor110220330440550

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 4.1.3Test: WritesZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50K100K150K200K250KSE +/- 702.01, N = 3SE +/- 417.51, N = 3152887251434
OpenBenchmarking.orgOp/s Per Watt, More Is BetterApache Cassandra 4.1.3Test: WritesZen 1 - EPYC 7601Zen 4C - EPYC 8534PN5001000150020002500258.462453.41
MinAvgMaxZen 1 - EPYC 7601259592701Zen 4C - EPYC 8534PN13102131OpenBenchmarking.orgWatts, Fewer Is BetterApache Cassandra 4.1.3CPU Power Consumption Monitor2004006008001000

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN5M10M15M20M25MSE +/- 66916.20, N = 3SE +/- 46666.67, N = 312996667213266671. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterQuicksilver 20230818Input: CORAL2 P1Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN40K80K120K160K200K22248.55201814.40
MinAvgMaxZen 1 - EPYC 7601243584648Zen 4C - EPYC 8534PN13106117OpenBenchmarking.orgWatts, Fewer Is BetterQuicksilver 20230818CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1224364860SE +/- 0.05, N = 3SE +/- 0.10, N = 353.4732.67MIN: 52.68 / MAX: 66.73MIN: 17.88 / MAX: 49.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601262614672Zen 4C - EPYC 8534PN15144157OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20M40M60M80M100MSE +/- 507374.51, N = 3SE +/- 286751.08, N = 35284912586278348

Kripke

Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.6Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN60M120M180M240M300MSE +/- 1601742.67, N = 3SE +/- 668520.88, N = 31873759333031072001. (CXX) g++ options: -O3 -fopenmp -ldl
OpenBenchmarking.orgThroughput FoM Per Watt, More Is BetterKripke 1.2.6Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN500K1000K1500K2000K2500K291422.102221434.65
MinAvgMaxZen 1 - EPYC 7601264643709Zen 4C - EPYC 8534PN15136175OpenBenchmarking.orgWatts, Fewer Is BetterKripke 1.2.6CPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20M40M60M80M100MSE +/- 175336.13, N = 3SE +/- 262330.46, N = 35375994086530272

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20406080100SE +/- 0.50, N = 3SE +/- 0.43, N = 385.0752.95MAX: 11426.59MAX: 10080.74
MinAvgMaxZen 1 - EPYC 7601251458697Zen 4C - EPYC 8534PN958146OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

rav1e

Xiph rav1e is a Rust-written AV1 video encoder that claims to be the fastest and safest AV1 encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 5Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.80571.61142.41713.22284.0285SE +/- 0.014, N = 3SE +/- 0.002, N = 32.2493.581
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterrav1e 0.7Speed: 5Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.01460.02920.04380.05840.0730.0060.065
MinAvgMaxZen 1 - EPYC 7601265.3372.5499.9Zen 4C - EPYC 8534PN12.955.068.3OpenBenchmarking.orgWatts, Fewer Is Betterrav1e 0.7CPU Power Consumption Monitor130260390520650

DuckDB

DuckDB is an in-progress SQL OLAP database management system optimized for analytics and features a vectorized and parallel engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 0.56, N = 3SE +/- 0.24, N = 3199.01125.101. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
MinAvgMaxZen 1 - EPYC 7601211.1418.3590.5Zen 4C - EPYC 8534PN13.164.1104.1OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1CPU Power Consumption Monitor160320480640800

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250SE +/- 0.35, N = 3SE +/- 0.20, N = 3226.37144.14
MinAvgMaxZen 1 - EPYC 7601263635709Zen 4C - EPYC 8534PN14144169OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250SE +/- 0.66, N = 3SE +/- 0.24, N = 3226.95145.11
MinAvgMaxZen 1 - EPYC 7601260632709Zen 4C - EPYC 8534PN14145170OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN60120180240300SE +/- 3.57, N = 3SE +/- 0.93, N = 3294.75191.77MAX: 29204.63MAX: 26841.55
MinAvgMaxZen 1 - EPYC 7601253452694Zen 4C - EPYC 8534PN1359143OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

rav1e

Xiph rav1e is a Rust-written AV1 video encoder that claims to be the fastest and safest AV1 encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 1Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.19190.38380.57570.76760.9595SE +/- 0.001, N = 3SE +/- 0.001, N = 30.5630.853
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterrav1e 0.7Speed: 1Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.00320.00640.00960.01280.0160.0010.014
MinAvgMaxZen 1 - EPYC 7601220.0426.6553.3Zen 4C - EPYC 8534PN12.862.381.6OpenBenchmarking.orgWatts, Fewer Is Betterrav1e 0.7CPU Power Consumption Monitor140280420560700

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 wrk 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 2.4.56Concurrent Requests: 1000Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN30K60K90K120K150KSE +/- 319.15, N = 3SE +/- 1806.36, N = 388038.28130116.681. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterApache HTTP Server 2.4.56Concurrent Requests: 1000Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN2004006008001000132.65921.15
MinAvgMaxZen 1 - EPYC 7601263664709Zen 4C - EPYC 8534PN14141157OpenBenchmarking.orgWatts, Fewer Is BetterApache HTTP Server 2.4.56CPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN15M30M45M60M75MSE +/- 405601.66, N = 3SE +/- 89839.93, N = 34604958967937226

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN15M30M45M60M75MSE +/- 330018.02, N = 3SE +/- 292969.25, N = 34592107467712944

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.i3dZen 1 - EPYC 7601Zen 4C - EPYC 8534PN2004006008001000SE +/- 0.24, N = 3SE +/- 1.66, N = 3818.05562.361. (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
OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN120240360480600Min: 264.43 / Avg: 601.98 / Max: 679.05Min: 14.17 / Avg: 133.33 / Max: 149.74

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250231.74159.571. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN918273645SE +/- 0.33, N = 3SE +/- 0.16, N = 339.4027.16MAX: 23930.49MAX: 23871.38
MinAvgMaxZen 1 - EPYC 7601252418700Zen 4C - EPYC 8534PN1347145OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenFOAM

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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeZen 1 - EPYC 7601Zen 4C - EPYC 8534PN102030405044.4530.951. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN3M6M9M12M15MSE +/- 16666.67, N = 3SE +/- 6666.67, N = 311426667163166671. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterQuicksilver 20230818Input: CTS2Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN30K60K90K120K150K18307.66143547.53
OpenBenchmarking.orgWatts, Fewer Is BetterQuicksilver 20230818CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN120240360480600Min: 258.88 / Avg: 624.15 / Max: 662.04Min: 13.53 / Avg: 113.67 / Max: 117.3

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN48121620SE +/- 0.06, N = 3SE +/- 0.01, N = 316.9512.21MIN: 16.19 / MAX: 27.98MIN: 7.44 / MAX: 23.581. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601260660708Zen 4C - EPYC 8534PN15139153OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 1.86, N = 3SE +/- 0.31, N = 3147.89106.91MAX: 27830.18MAX: 26717.27
MinAvgMaxZen 1 - EPYC 7601252418695Zen 4C - EPYC 8534PN1350146OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

DuckDB

DuckDB is an in-progress SQL OLAP database management system optimized for analytics and features a vectorized and parallel engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: TPC-H ParquetZen 1 - EPYC 7601Zen 4C - EPYC 8534PN50100150200250SE +/- 0.21, N = 3SE +/- 0.17, N = 3245.74178.441. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
MinAvgMaxZen 1 - EPYC 7601262.0320.9559.4Zen 4C - EPYC 8534PN12.953.090.9OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1CPU Power Consumption Monitor140280420560700

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN11M22M33M44M55MSE +/- 524500.20, N = 3SE +/- 567305.29, N = 33871226351396698

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN11M22M33M44M55MSE +/- 325879.11, N = 8SE +/- 524236.55, N = 33817645650396884

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN1020304050SE +/- 0.62, N = 3SE +/- 0.57, N = 346.2935.58MAX: 12751.47MAX: 12564.03
MinAvgMaxZen 1 - EPYC 7601259383699Zen 4C - EPYC 8534PN1543143OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 39.107.10MIN: 9.04 / MAX: 17.25MIN: 4.1 / MAX: 18.361. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601262604653Zen 4C - EPYC 8534PN14149161OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN16M32M48M64M80MSE +/- 295389.20, N = 3SE +/- 1143156.28, N = 125840375673031288

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 200 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 1.86, N = 8SE +/- 1.34, N = 3166.00133.01MAX: 27445.2MAX: 27113.93
MinAvgMaxZen 1 - EPYC 7601259390699Zen 4C - EPYC 8534PN1342145OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 0.36, N = 3SE +/- 0.14, N = 3181.92146.53MIN: 171.42 / MAX: 202.33MIN: 71.86 / MAX: 230.851. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxZen 1 - EPYC 7601260668708Zen 4C - EPYC 8534PN15150168OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor2004006008001000

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN110220330440550SE +/- 3.72, N = 3SE +/- 8.85, N = 3488.64394.51MAX: 28615.16MAX: 32858.26
MinAvgMaxZen 1 - EPYC 7601254530790Zen 4C - EPYC 8534PN1476146OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN15M30M45M60M75MSE +/- 138623.83, N = 3SE +/- 878468.51, N = 36023762570984166

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P2Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN3M6M9M12M15MSE +/- 37118.43, N = 3SE +/- 14529.66, N = 315013333161766671. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterQuicksilver 20230818Input: CORAL2 P2Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN40K80K120K160K200K27116.87175615.65
MinAvgMaxZen 1 - EPYC 7601255.2553.7594.9Zen 4C - EPYC 8534PN13.692.194.5OpenBenchmarking.orgWatts, Fewer Is BetterQuicksilver 20230818CPU Power Consumption Monitor160320480640800

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 2023Implementation: MPI CPU - Input: water_GMX50_bareZen 1 - EPYC 76010.44820.89641.34461.79282.241SE +/- 0.017, N = 31.9921. (CXX) g++ options: -O3
OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareZen 1 - EPYC 76010.00070.00140.00210.00280.00350.003
MinAvgMaxZen 1 - EPYC 7601263670709OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2023CPU Power Consumption Monitor2004006008001000

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic ModelZen 1 - EPYC 7601714212835SE +/- 0.13, N = 330.281. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMaxZen 1 - EPYC 7601262636714OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. HelensZen 1 - EPYC 7601714212835SE +/- 0.41, N = 329.951. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMaxZen 1 - EPYC 7601261637712OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous HalfspaceZen 1 - EPYC 7601918273645SE +/- 0.31, N = 338.061. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMaxZen 1 - EPYC 7601265650713OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered HalfspaceZen 1 - EPYC 760120406080100SE +/- 0.29, N = 374.951. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMaxZen 1 - EPYC 7601264652704OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered HalfspaceZen 1 - EPYC 760120406080100SE +/- 0.98, N = 378.681. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMaxZen 1 - EPYC 7601260670710OpenBenchmarking.orgWatts, Fewer Is BetterSPECFEM3D 4.0CPU Power Consumption Monitor2004006008001000

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringZen 1 - EPYC 7601Zen 4C - EPYC 8534PN140280420560700Min: 134.19 / Avg: 579.81 / Max: 789.58Min: 7.2 / Avg: 112.32 / Max: 180

SVT-AV1

MinAvgMaxZen 1 - EPYC 7601250387643Zen 4C - EPYC 8534PN1352123OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.84941.69882.54823.39764.2470.1753.775

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 2.72, N = 12SE +/- 1.62, N = 967.93196.421. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 13 - Input: Bosphorus 4KZen 1 - EPYC 7601Zen 4C - EPYC 8534PN0.84941.69882.54823.39764.2470.1753.775
MinAvgMaxZen 1 - EPYC 7601250387643Zen 4C - EPYC 8534PN1352123OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor2004006008001000

Timed MrBayes Analysis

OpenBenchmarking.orgWatts, Fewer Is BetterTimed MrBayes Analysis 3.2.7CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN130260390520650Min: 255.46 / Avg: 673.45 / Max: 711.35Min: 13.87 / Avg: 158.85 / Max: 169.15

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisZen 1 - EPYC 7601Zen 4C - EPYC 8534PN4080120160200SE +/- 4.88, N = 12SE +/- 0.47, N = 3201.18126.97-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm -lreadline
OpenBenchmarking.orgWatts, Fewer Is BetterTimed MrBayes Analysis 3.2.7CPU Power Consumption MonitorZen 1 - EPYC 7601Zen 4C - EPYC 8534PN130260390520650Min: 255.46 / Avg: 673.45 / Max: 711.35Min: 13.87 / Avg: 158.85 / Max: 169.15

RocksDB

MinAvgMaxZen 1 - EPYC 7601262679712Zen 4C - EPYC 8534PN15162179OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 8.0CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 8.0Test: Read While WritingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN9K18K27K36K45K4962.3242709.95

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read While WritingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN1.5M3M4.5M6M7.5MSE +/- 34108.45, N = 3SE +/- 125140.33, N = 12337187669182671. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 8.0Test: Read While WritingZen 1 - EPYC 7601Zen 4C - EPYC 8534PN9K18K27K36K45K4962.3242709.95
MinAvgMaxZen 1 - EPYC 7601262679712Zen 4C - EPYC 8534PN15162179OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 8.0CPU Power Consumption Monitor2004006008001000

Apache IoTDB

MinAvgMaxZen 1 - EPYC 7601252535699Zen 4C - EPYC 8534PN1276147OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN306090120150SE +/- 0.61, N = 3SE +/- 1.78, N = 12129.77101.60MAX: 23980.17MAX: 30258.71
MinAvgMaxZen 1 - EPYC 7601252535699Zen 4C - EPYC 8534PN1276147OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

MinAvgMaxZen 1 - EPYC 7601252501692Zen 4C - EPYC 8534PN1372148OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN70140210280350SE +/- 4.76, N = 5SE +/- 4.45, N = 12318.24195.49MAX: 28518.21MAX: 28108.09
MinAvgMaxZen 1 - EPYC 7601252501692Zen 4C - EPYC 8534PN1372148OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor2004006008001000

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400Zen 1 - EPYC 7601Zen 4C - EPYC 8534PN20M40M60M80M100MSE +/- 596691.26, N = 5SE +/- 1905882.84, N = 125703744191869780

194 Results Shown

OpenVINO
miniBUDE:
  OpenMP - BM2:
    Billion Interactions/s
    GFInst/s
  OpenMP - BM1:
    GFInst/s
    Billion Interactions/s
OpenVINO:
  Machine Translation EN To DE FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
OpenSSL
Neural Magic DeepSparse
OSPRay:
  gravity_spheres_volume/dim_512/scivis/real_time
  gravity_spheres_volume/dim_512/ao/real_time
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
OpenSSL
ACES DGEMM
OpenVINO
OpenSSL
Neural Magic DeepSparse
OpenVINO
OpenSSL
Neural Magic DeepSparse
OpenSSL
TensorFlow
OpenVINO
OSPRay
OSPRay Studio:
  3 - 4K - 1 - Path Tracer - CPU
  1 - 4K - 1 - Path Tracer - CPU
  3 - 4K - 32 - Path Tracer - CPU
  1 - 4K - 32 - Path Tracer - CPU
  3 - 4K - 16 - Path Tracer - CPU
Xmrig
OpenVINO
OSPRay Studio
Intel Open Image Denoise
Embree
Xmrig
easyWave
Embree
RocksDB
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream
OpenVINO
Speedb
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream
Y-Cruncher
OSPRay
OpenVINO
OSPRay
easyWave
Blender
OpenSSL
Neural Magic DeepSparse:
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
Y-Cruncher
OpenSSL
7-Zip Compression
Chaos Group V-RAY
Neural Magic DeepSparse
Xmrig:
  KawPow - 1M
  CryptoNight-Femto UPX2 - 1M
OpenSSL
Xmrig:
  Monero - 1M
  CryptoNight-Heavy - 1M
7-Zip Compression
Blender
IndigoBench
Blender:
  Pabellon Barcelona - CPU-Only
  Classroom - CPU-Only
IndigoBench
Neural Magic DeepSparse
SVT-AV1
Blender
QuantLib
nginx
Neural Magic DeepSparse
Redis 7.0.12 + memtier_benchmark
SVT-AV1
nginx
Redis 7.0.12 + memtier_benchmark
Timed LLVM Compilation
NAMD
OpenVINO
Timed Linux Kernel Compilation
Timed Node.js Compilation
uvg266:
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Super Fast
OpenFOAM
uvg266
GPAW
LAMMPS Molecular Dynamics Simulator
FFmpeg:
  libx265 - Platform
  libx265 - Video On Demand
  libx265 - Upload
Timed FFmpeg Compilation
SVT-AV1
Speedb
uvg266
Timed LLVM Compilation
Meta Performance Per Watts
OpenVINO:
  Face Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
Neural Magic DeepSparse
OpenVINO
FFmpeg
CloverLeaf
VVenC
x265
CloverLeaf
OpenVINO
Timed Linux Kernel Compilation
Speedb
Xcompact3d Incompact3d
Timed Gem5 Compilation
VVenC
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream
Apache IoTDB:
  500 - 100 - 800 - 100:
    Average Latency
    point/sec
rav1e
Speedb
RocksDB
Apache IoTDB:
  800 - 100 - 500 - 100
  500 - 100 - 800 - 400
  800 - 100 - 500 - 100
OpenFOAM
PyTorch
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
PyTorch
OSPRay
OpenRadioss
Neural Magic DeepSparse
RocksDB
Apache IoTDB
rav1e
Apache Cassandra
Quicksilver
OpenVINO
Apache IoTDB
Kripke
Apache IoTDB:
  500 - 100 - 500 - 100:
    point/sec
    Average Latency
rav1e
DuckDB
Neural Magic DeepSparse:
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
Apache IoTDB
rav1e
Apache HTTP Server
Apache IoTDB:
  800 - 100 - 200 - 100
  800 - 100 - 200 - 400
Xcompact3d Incompact3d
OpenFOAM
Apache IoTDB
OpenFOAM
Quicksilver
OpenVINO
Apache IoTDB
DuckDB
Apache IoTDB:
  500 - 100 - 200 - 100
  500 - 100 - 200 - 400
  500 - 100 - 200 - 100
OpenVINO
Apache IoTDB:
  800 - 100 - 800 - 100
  500 - 100 - 200 - 400
OpenVINO
Apache IoTDB:
  800 - 100 - 800 - 400:
    Average Latency
    point/sec
Quicksilver
GROMACS
SPECFEM3D:
  Tomographic Model
  Mount St. Helens
  Homogeneous Halfspace
  Water-layered Halfspace
  Layered Halfspace
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  CPU Power Consumption Monitor
  Preset 13 - Bosphorus 4K
SVT-AV1
Timed MrBayes Analysis
Timed MrBayes Analysis
RocksDB:
  CPU Power Consumption Monitor
  Read While Writing
RocksDB
Apache IoTDB
Apache IoTDB
Apache IoTDB
Apache IoTDB:
  800 - 100 - 500 - 400:
    Average Latency
    point/sec

Zen 1 - EPYC 7601

Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD 17h, Memory: 128GB, Disk: 280GB INTEL SSDPE21D280GA + 1000GB INTEL SSDPE2KX010T8, Graphics: llvmpipe, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, 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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: 0x800126e
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Mitigation of Safe RET + 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 STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 6 January 2024 22:07 by user phoronix.

Zen 4C - EPYC 8534PN

Processor: AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-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: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 8 January 2024 13:44 by user phoronix.