GCE c3d-standard-60

KVM testing on Ubuntu 22.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2310039-NE-2310031NE80
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

Limit displaying results to tests within:

Timed Code Compilation 3 Tests
C/C++ Compiler Tests 7 Tests
CPU Massive 12 Tests
Creator Workloads 4 Tests
Database Test Suite 3 Tests
Fortran Tests 4 Tests
HPC - High Performance Computing 10 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 2 Tests
Molecular Dynamics 3 Tests
MPI Benchmarks 4 Tests
Multi-Core 15 Tests
NVIDIA GPU Compute 3 Tests
OpenMPI Tests 11 Tests
Programmer / Developer System Benchmarks 4 Tests
Python Tests 4 Tests
Scientific Computing 4 Tests
Server 5 Tests
Server CPU Tests 7 Tests
Common Workstation Benchmarks 3 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
c3d-standard-60 AMD Genoa
October 03 2023
  10 Hours, 30 Minutes
t2d-standard-60 AMD Milan
October 03 2023
  13 Hours, 23 Minutes
Invert Hiding All Results Option
  11 Hours, 57 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):

c3d-standard-60 AMD Genoa

Processor: AMD EPYC 9B14 (30 Cores / 60 Threads), Motherboard: Google Compute Engine c3d-standard-60, Chipset: Intel 440FX 82441FX PMC, Memory: 240GB, Disk: 215GB nvme_card-pd, Network: Google Compute Engine Virtual

OS: Ubuntu 22.04, Kernel: 6.2.0-1014-gcp (x86_64), Vulkan: 1.3.238, Compiler: GCC 11.4.0, File-System: ext4, System Layer: KVM

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: CPU Microcode: 0xffffffff
Java Notes: OpenJDK Runtime Environment (build 11.0.20.1+1-post-Ubuntu-0ubuntu122.04)
Python Notes: Python 3.10.12
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_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

t2d-standard-60 AMD Milan

Processor: AMD EPYC 7B13 (60 Cores), Motherboard: Google Compute Engine t2d-standard-60, Chipset: Intel 440FX 82441FX PMC, Memory: 240GB, Disk: 215GB PersistentDisk, Network: Red Hat Virtio device

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: CPU Microcode: 0xffffffff
Java Notes: OpenJDK Runtime Environment (build 11.0.20.1+1-post-Ubuntu-0ubuntu122.04)
Python Notes: Python 3.10.12
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_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

GCE c3d-standard-60ProcessorMotherboardChipsetMemoryDiskNetworkOSKernelVulkanCompilerFile-SystemSystem Layerc3d-standard-60 AMD Genoat2d-standard-60 AMD MilanAMD EPYC 9B14 (30 Cores / 60 Threads)Google Compute Engine c3d-standard-60Intel 440FX 82441FX PMC240GB215GB nvme_card-pdGoogle Compute Engine VirtualUbuntu 22.046.2.0-1014-gcp (x86_64)1.3.238GCC 11.4.0ext4KVMAMD EPYC 7B13 (60 Cores)Google Compute Engine t2d-standard-60215GB PersistentDiskRed Hat Virtio deviceOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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- CPU Microcode: 0xffffffffJava Details- OpenJDK Runtime Environment (build 11.0.20.1+1-post-Ubuntu-0ubuntu122.04)Python Details- Python 3.10.12Security Details- c3d-standard-60 AMD Genoa: 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_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - t2d-standard-60 AMD Milan: 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_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

c3d-standard-60 AMD Genoa vs. t2d-standard-60 AMD Milan ComparisonPhoronix Test SuiteBaseline+93%+93%+186%+186%+279%+279%104.3%74.6%59.7%51.3%40.5%38.3%36.1%35.2%32.6%30.4%28.9%28.7%28.1%27.5%27.2%24.4%23.7%23.2%22.7%20.5%19.7%19.2%14%13.3%13.2%13.2%10.7%10.1%9.3%8.3%8.3%8.3%6.7%6.4%4.8%4.3%3.6%3.5%3.4%3.2%3%2.6%V.D.F - CPU371.8%F.D.R.F - CPU305.9%V.D.F - CPU277.2%P.V.B.D.F - CPU248.2%CPU - 64 - ResNet-50233.4%F.D.R.F - CPU224.1%R.S.A.F - CPU220%CPU - 32 - ResNet-50208.2%CPU - 16 - ResNet-50178.8%P.V.B.D.F - CPU178.4%H.E.R.F - CPU160.6%H.E.R.F - CPU160.6%R.S.A.F - CPU155.9%P.D.F - CPU148.2%M.T.E.T.D.F - CPU139.8%P.D.F - CPU130.5%F.D.F - CPU114.8%S.R.EH.E.R.F.I - CPU94.8%H.E.R.F.I - CPU94.8%P.D.F - CPU93.6%M.T.E.T.D.F - CPU91.9%A.G.R.R.0.F - CPU90.4%W.P.D.F - CPU84.8%P.D.F - CPU81%RSA4096TurboPipe Periodic73%F.D.F - CPU71.4%V.D.F.I - CPU68.9%F.D.F.I - CPU67.1%Rhodopsin ProteinF.D.R.F.I - CPU55.8%RSA409654.8%A.G.R.R.0.F.I - CPU52.5%SHA512A.G.R.R.0.F - CPU47%AES-128-GCM46.2%R.S.A.F.I - CPU42.8%S.B.W.u.mFT.CIS.D38.2%W.P.D.F.I - CPU38%W.P.D.F.I - CPU37.9%OpenMP CFD SolverAES-256-GCM35.8%20k AtomsV.D.F.I - CPU35.1%F.D.F.I - CPU33.9%r2c - FFTW - float - 128EP.DC.P.D.TF.D.R.F.I - CPULU.CBT.COpenMP LavaMDA.G.R.R.0.F.I - CPU24.8%R.O.R.S.Ic2c - FFTW - float - 128V.P.MBumper BeamWrites22.2%MPI CPU - water_GMX50_bareCoreMark Size 666 - I.P.SB.S.o.WCG.C17.7%Kershaw16.5%100016%50015%R.S.A.F.I - CPU14.2%i.i.1.C.P.Dr2c - FFTW - double - 12832646, Lossless10.9%MG.CSHA256D.ROpenMP LeukocyteSP.CW.P.D.F - CPUTotal TimeT.P.POpenMP HotSpot3D5.2%c2c - FFTW - double - 1284.6%i.i.1.C.P.D800 - 100 - 800 - 4004%ChaCha20ChaCha20-Poly13053.6%Time To CompileTime To Compile800 - 100 - 500 - 400Chrysler Neon 1MCompression RatingOpenVINOOpenVINOOpenVINOOpenVINOTensorFlowOpenVINOOpenVINOTensorFlowTensorFlowOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINORemhosOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenSSLnekRSOpenVINOOpenVINOOpenVINOLAMMPS Molecular Dynamics SimulatorOpenVINOOpenSSLOpenVINOOpenSSLOpenVINOOpenSSLOpenVINOLaghosNAS Parallel BenchmarksNAS Parallel BenchmarksOpenVINOOpenVINORodiniaOpenSSLLAMMPS Molecular Dynamics SimulatorOpenVINOOpenVINOHeFFTe - Highly Efficient FFT for ExascaleNAS Parallel BenchmarksOpenRadiossOpenVINONAS Parallel BenchmarksNAS Parallel BenchmarksRodiniaOpenVINOOpenRadiossHeFFTe - Highly Efficient FFT for ExascaleBRL-CADOpenRadiossApache CassandraGROMACSCoremarkOpenRadiossNAS Parallel BenchmarksnekRSnginxnginxOpenVINOXcompact3d Incompact3dHeFFTe - Highly Efficient FFT for Exascalelibxsmmlibxsmmlibavif avifencNAS Parallel BenchmarksOpenSSL7-Zip CompressionRodiniaNAS Parallel BenchmarksOpenVINOStockfishLaghosRodiniaHeFFTe - Highly Efficient FFT for ExascaleAlgebraic Multi-Grid BenchmarkXcompact3d Incompact3dApache IoTDBOpenSSLOpenSSLTimed Node.js CompilationTimed Gem5 CompilationApache IoTDBOpenRadioss7-Zip Compressionc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan

GCE c3d-standard-60openvino: Vehicle Detection FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUtensorflow: CPU - 64 - ResNet-50openvino: Face Detection Retail FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUtensorflow: CPU - 32 - ResNet-50tensorflow: CPU - 16 - ResNet-50openvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Face Detection FP16 - CPUremhos: Sample Remap Exampleopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenssl: RSA4096openvino: Face Detection FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenssl: RSA4096openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenssl: SHA512openvino: Age Gender Recognition Retail 0013 FP16 - CPUopenssl: AES-128-GCMopenvino: Road Segmentation ADAS FP16-INT8 - CPUlaghos: Sedov Blast Wave, ube_922_hex.meshnpb: FT.Copenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUrodinia: OpenMP CFD Solveropenssl: AES-256-GCMlammps: 20k Atomsopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUheffte: r2c - FFTW - float - 128npb: EP.Dopenvino: Face Detection Retail FP16-INT8 - CPUnpb: BT.Crodinia: OpenMP LavaMDopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUheffte: c2c - FFTW - float - 128brl-cad: VGR Performance Metriccassandra: Writesgromacs: MPI CPU - water_GMX50_barecoremark: CoreMark Size 666 - Iterations Per Secondnginx: 1000nginx: 500openvino: Road Segmentation ADAS FP16-INT8 - CPUincompact3d: input.i3d 193 Cells Per Directionlibxsmm: 32libxsmm: 64avifenc: 6, Losslessnpb: MG.Copenssl: SHA256compress-7zip: Decompression Ratingrodinia: OpenMP Leukocytenpb: SP.Copenvino: Weld Porosity Detection FP16 - CPUstockfish: Total Timelaghos: Triple Point Problemamg: incompact3d: input.i3d 129 Cells Per Directionopenssl: ChaCha20openssl: ChaCha20-Poly1305build-nodejs: Time To Compilebuild-gem5: Time To Compileopenradioss: Chrysler Neon 1Mcompress-7zip: Compression Ratingapache-iotdb: 500 - 100 - 800 - 400avifenc: 6avifenc: 2apache-iotdb: 500 - 100 - 500 - 400apache-iotdb: 800 - 100 - 800 - 400apache-iotdb: 800 - 100 - 500 - 400apache-iotdb: 500 - 100 - 500 - 400apache-iotdb: 500 - 100 - 800 - 400avifenc: 0pgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 800 - Read Write - Average Latencypgbench: 100 - 1000 - Read Only - Average Latencypgbench: 100 - 800 - Read Only - Average Latencyblender: Pabellon Barcelona - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Classroom - CPU-Onlyblender: BMW27 - CPU-Onlypgbench: 100 - 1000 - Read Writepgbench: 100 - 800 - Read Writepgbench: 100 - 1000 - Read Onlypgbench: 100 - 800 - Read Onlybuild-linux-kernel: allmodconfigbuild-linux-kernel: defconfigopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUapache-iotdb: 800 - 100 - 800 - 400apache-iotdb: 800 - 100 - 500 - 400lammps: Rhodopsin Proteinnekrs: TurboPipe Periodicnekrs: Kershawopenradioss: Rubber O-Ring Seal Installationopenradioss: Bird Strike on Windshieldopenradioss: Cell Phone Drop Testopenradioss: Bumper Beamheffte: r2c - FFTW - double - 128heffte: c2c - FFTW - double - 128rodinia: OpenMP Streamclusterrodinia: OpenMP HotSpot3Dnpb: LU.Cnpb: IS.Dnpb: CG.Cc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan8.622.871389.696.7969.684166.3920.7762.7450.991764.21964.4631.08576.9464.70648.8133.36239.38761.14185.290.521875.28493077.618.395.86340.296605.1220079.50.41470227057343607.0434309528444018.56259.5539647.478.203650.5710.02529332804849719.7762043.0535.19148.5753783.604.5396257.4864.86254971.2688.63015108192286404.3911445843.521552180537.84187350.44645.7428.0196877255.4489.76.88942701.834621182131322621145.49839919.7115.98105894457209.009628898335.87157885173980949893123909304773198.394176.767337.70271795623.893.25041.538418.593535988434332237332681583476256578.06883.91142.9083.99142.75682.12447.6817.4234723940000428985833389.65147.3138.8292.8793.600557.31166.44884.16673563.132422.4019597.8640.6711.65368.3923.6420.901285.4766.4620.3618.29633.76370.0381.00225.48155.141393.5616.32676.72390.7296.580.991014.70860844.610.739.90568.774239.5212973.00.612224480418329668.1223460408261026.50364.6454846.1811.322646.587.36821602596764026.7341512.5726.28196.9484935.683.52122720.6150.97444049.15109.6766293631871695.2891730658.449440155609.04162957.75565.3424.5721181289.2554.27.63947291.965088499710324725542.01043228.1114.76112958788222.309204277675.63057327180249145770119647720337191.706170.930327.88278973633.583.20541.989415.083506855734123810334668043492589978.350172.717140.9160.4980.399112.64351.5845.2289.3534.275793568220081862003784333.35133.399193.4578.96208.4773.74709.46433.9627.8282730620000368193583372.06123.6130.1275.68106.02960.03436.42388.53594247.771752.6216649.37OpenBenchmarking.org

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan918273645SE +/- 0.04, N = 3SE +/- 0.17, N = 38.6240.67MIN: 5.74 / MAX: 36.03MIN: 12.07 / MAX: 59.441. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan3691215SE +/- 0.01, N = 3SE +/- 0.14, N = 32.8711.65MIN: 1.77 / MAX: 11.42MIN: 3.76 / MAX: 29.11. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan30060090012001500SE +/- 6.33, N = 3SE +/- 1.55, N = 31389.69368.391. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Vehicle Bike Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan612182430SE +/- 0.02, N = 3SE +/- 0.14, N = 36.7923.64MIN: 4.45 / MAX: 24.38MIN: 9.57 / MAX: 42.221. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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: 64 - Model: ResNet-50c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan1632486480SE +/- 0.07, N = 3SE +/- 0.03, N = 369.6820.90

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan9001800270036004500SE +/- 8.74, N = 3SE +/- 15.96, N = 34166.391285.471. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan1530456075SE +/- 0.04, N = 3SE +/- 0.27, N = 320.7766.46MIN: 11.01 / MAX: 36.69MIN: 25.85 / MAX: 122.21. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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: 32 - Model: ResNet-50c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan1428425670SE +/- 0.10, N = 3SE +/- 0.06, N = 362.7420.36

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan1224364860SE +/- 0.04, N = 3SE +/- 0.05, N = 350.9918.29

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Vehicle Bike Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan400800120016002000SE +/- 4.38, N = 3SE +/- 3.66, N = 31764.21633.761. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan2004006008001000SE +/- 0.60, N = 3SE +/- 0.96, N = 3964.46370.031. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan20406080100SE +/- 0.02, N = 3SE +/- 0.21, N = 331.0881.00MIN: 19.98 / MAX: 50.81MIN: 64.65 / MAX: 134.641. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan120240360480600SE +/- 1.04, N = 3SE +/- 0.93, N = 3576.94225.481. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Machine Translation EN To DE FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan306090120150SE +/- 0.09, N = 3SE +/- 0.58, N = 364.70155.14MIN: 50.24 / MAX: 93.15MIN: 114.75 / MAX: 224.641. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan30060090012001500SE +/- 0.17, N = 3SE +/- 1.32, N = 3648.811393.56MIN: 632.52 / MAX: 677.15MIN: 1290.45 / MAX: 1469.821. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Remhos

Remhos (REMap High-Order Solver) is a miniapp that solves the pure advection equations that are used to perform monotonic and conservative discontinuous field interpolation (remap) as part of the Eulerian phase in Arbitrary Lagrangian Eulerian (ALE) simulations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRemhos 1.0Test: Sample Remap Examplet2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa816243240SE +/- 0.05, N = 3SE +/- 0.17, N = 316.3333.361. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan20406080100SE +/- 0.09, N = 3SE +/- 0.27, N = 339.3876.72MIN: 34.32 / MAX: 53.98MIN: 58.8 / MAX: 121.691. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Handwritten English Recognition FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan160320480640800SE +/- 1.75, N = 3SE +/- 1.37, N = 3761.14390.721. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Machine Translation EN To DE FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan4080120160200SE +/- 0.25, N = 3SE +/- 0.37, N = 3185.2996.581. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan0.22280.44560.66840.89121.114SE +/- 0.00, N = 3SE +/- 0.00, N = 30.520.99MIN: 0.31 / MAX: 8.86MIN: 0.8 / MAX: 13.761. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan400800120016002000SE +/- 0.47, N = 3SE +/- 0.56, N = 31875.281014.701. (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.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa200K400K600K800K1000KSE +/- 644.45, N = 3SE +/- 50.91, N = 3860844.6493077.61. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 318.3910.731. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 35.869.90MIN: 3.22 / MAX: 20.19MIN: 8.13 / MAX: 26.871. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan120240360480600SE +/- 0.21, N = 3SE +/- 0.35, N = 3340.29568.77MIN: 328.52 / MAX: 353.66MIN: 481.12 / MAX: 606.311. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan14002800420056007000SE +/- 6.52, N = 3SE +/- 2.08, N = 36605.124239.521. (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: RSA4096c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan4K8K12K16K20KSE +/- 14.62, N = 3SE +/- 11.58, N = 320079.512973.01. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan0.13730.27460.41190.54920.6865SE +/- 0.00, N = 3SE +/- 0.00, N = 30.400.61MIN: 0.23 / MAX: 7.49MIN: 0.41 / MAX: 264.311. (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: SHA512t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa5000M10000M15000M20000M25000MSE +/- 108274834.92, N = 3SE +/- 4399663.13, N = 322244804183147022705731. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan9K18K27K36K45KSE +/- 18.42, N = 3SE +/- 14.46, N = 343607.0429668.121. (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-GCMc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan70000M140000M210000M280000M350000MSE +/- 342949201.09, N = 3SE +/- 376720190.05, N = 33430952844402346040826101. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 318.5626.50MIN: 15.5 / MAX: 36.36MIN: 19.6 / MAX: 56.621. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Laghos

Laghos (LAGrangian High-Order Solver) is a miniapp that solves the time-dependent Euler equations of compressible gas dynamics in a moving Lagrangian frame using unstructured high-order finite element spatial discretization and explicit high-order time-stepping. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Sedov Blast Wave, ube_922_hex.mesht2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa80160240320400SE +/- 0.62, N = 3SE +/- 0.31, N = 3364.64259.551. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.Ct2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa12K24K36K48K60KSE +/- 137.77, N = 3SE +/- 600.19, N = 1554846.1839647.471. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 38.2011.32MIN: 4.92 / MAX: 14.5MIN: 10.13 / MAX: 30.811. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan8001600240032004000SE +/- 3.28, N = 3SE +/- 3.26, N = 33650.572646.581. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solvert2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa3691215SE +/- 0.034, N = 3SE +/- 0.013, N = 37.36810.0251. (CXX) g++ options: -O2 -lOpenCL

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-GCMc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan60000M120000M180000M240000M300000MSE +/- 71241287.97, N = 3SE +/- 178290221.71, N = 32933280484972160259676401. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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 Atomst2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa612182430SE +/- 0.05, N = 3SE +/- 0.04, N = 326.7319.781. (CXX) g++ options: -O3 -lm -ldl

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Vehicle Detection FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan400800120016002000SE +/- 3.16, N = 3SE +/- 1.12, N = 32043.051512.571. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Face Detection FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan816243240SE +/- 0.02, N = 3SE +/- 0.02, N = 335.1926.281. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa4080120160200SE +/- 0.82, N = 3SE +/- 2.19, N = 12196.95148.581. (CXX) g++ options: -O3

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.Dt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa11002200330044005500SE +/- 51.21, N = 5SE +/- 30.67, N = 34935.683783.601. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Face Detection Retail FP16-INT8 - Device: CPUt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa1.01932.03863.05794.07725.0965SE +/- 0.00, N = 3SE +/- 0.01, N = 33.524.53MIN: 2.77 / MAX: 18.76MIN: 2.72 / MAX: 12.381. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.Ct2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa30K60K90K120K150KSE +/- 42.77, N = 3SE +/- 122.23, N = 3122720.6196257.481. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa1428425670SE +/- 0.13, N = 3SE +/- 0.18, N = 350.9764.861. (CXX) g++ options: -O2 -lOpenCL

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan12K24K36K48K60KSE +/- 45.46, N = 3SE +/- 332.93, N = 354971.2644049.151. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: float - X Y Z: 128t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa20406080100SE +/- 0.78, N = 3SE +/- 0.52, N = 3109.6888.631. (CXX) g++ options: -O3

BRL-CAD

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

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.36VGR Performance Metrict2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa130K260K390K520K650K6293635108191. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6

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: Writesc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan50K100K150K200K250KSE +/- 1129.40, N = 3SE +/- 681.76, N = 3228640187169

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_baret2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa1.192.383.574.765.95SE +/- 0.005, N = 3SE +/- 0.011, N = 35.2894.3911. (CXX) g++ options: -O3

Coremark

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

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Secondt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa400K800K1200K1600K2000KSE +/- 9191.61, N = 3SE +/- 1295.68, N = 31730658.451445843.521. (CC) gcc options: -O2 -lrt" -lrt

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: 1000c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan40K80K120K160K200KSE +/- 688.79, N = 3SE +/- 156.32, N = 3180537.84155609.041. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan40K80K120K160K200KSE +/- 126.15, N = 3SE +/- 394.72, N = 3187350.44162957.751. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Road Segmentation ADAS FP16-INT8 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan140280420560700SE +/- 0.79, N = 3SE +/- 0.37, N = 3645.74565.341. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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 Directiont2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa714212835SE +/- 0.31, N = 12SE +/- 0.25, N = 324.5728.021. (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

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 32t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa60120180240300SE +/- 3.60, N = 4SE +/- 0.19, N = 3289.2255.41. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 64t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa120240360480600SE +/- 0.25, N = 3SE +/- 0.12, N = 3554.2489.71. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6, Losslessc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan246810SE +/- 0.099, N = 3SE +/- 0.031, N = 36.8897.6391. (CXX) g++ options: -O3 -fPIC -lm

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.Ct2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa10K20K30K40K50KSE +/- 145.06, N = 3SE +/- 29.69, N = 347291.9642701.831. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

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: SHA256t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa11000M22000M33000M44000M55000MSE +/- 20491615.60, N = 3SE +/- 9562123.40, N = 350884997103462118213131. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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 Ratingt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa50K100K150K200K250KSE +/- 347.74, N = 3SE +/- 519.21, N = 32472552262111. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Leukocytet2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa1020304050SE +/- 0.02, N = 3SE +/- 0.17, N = 342.0145.501. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.Ct2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa9K18K27K36K45KSE +/- 555.92, N = 3SE +/- 45.01, N = 343228.1139919.711. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Weld Porosity Detection FP16 - Device: CPUt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa48121620SE +/- 0.01, N = 3SE +/- 0.00, N = 314.7615.98MIN: 12.71 / MAX: 35.86MIN: 9.37 / MAX: 24.291. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Stockfish

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

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total Timet2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa20M40M60M80M100MSE +/- 1618403.29, N = 14SE +/- 1450871.09, N = 3112958788105894457-mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

Laghos

Laghos (LAGrangian High-Order Solver) is a miniapp that solves the time-dependent Euler equations of compressible gas dynamics in a moving Lagrangian frame using unstructured high-order finite element spatial discretization and explicit high-order time-stepping. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Triple Point Problemt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa50100150200250SE +/- 1.77, N = 3SE +/- 0.22, N = 3222.30209.001. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Algebraic Multi-Grid Benchmark

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

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan200M400M600M800M1000MSE +/- 2060519.90, N = 3SE +/- 1088162.98, N = 39628898339204277671. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

Xcompact3d Incompact3d

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

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per Directiont2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa1.32112.64223.96335.28446.6055SE +/- 0.02210564, N = 3SE +/- 0.04970425, N = 35.630573275.871578851. (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

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: ChaCha20t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa40000M80000M120000M160000M200000MSE +/- 47698640.87, N = 3SE +/- 12326205.97, N = 31802491457701739809498931. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan30000M60000M90000M120000M150000MSE +/- 3664727.47, N = 3SE +/- 198663058.81, N = 31239093047731196477203371. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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 Compilet2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa4080120160200SE +/- 0.05, N = 3SE +/- 0.29, N = 3191.71198.39

Timed Gem5 Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To Compilet2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa4080120160200SE +/- 0.27, N = 3SE +/- 0.07, N = 3170.93176.77

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 1Mt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa70140210280350SE +/- 1.48, N = 3SE +/- 2.03, N = 3327.88337.70

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 Ratingt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa60K120K180K240K300KSE +/- 388.74, N = 3SE +/- 346.51, N = 32789732717951. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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: 400c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan140280420560700SE +/- 3.18, N = 3SE +/- 12.58, N = 3623.89633.58MAX: 41831.2MAX: 54749.7

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 6t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa0.73131.46262.19392.92523.6565SE +/- 0.013, N = 3SE +/- 0.007, N = 33.2053.2501. (CXX) g++ options: -O3 -fPIC -lm

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 2c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan1020304050SE +/- 0.11, N = 3SE +/- 0.03, N = 341.5441.991. (CXX) g++ options: -O3 -fPIC -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: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa90180270360450SE +/- 4.08, N = 3SE +/- 2.14, N = 3415.08418.59MAX: 28810.4MAX: 31920.67

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan8M16M24M32M40MSE +/- 267152.12, N = 3SE +/- 354923.23, N = 33535988435068557

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan7M14M21M28M35MSE +/- 66565.66, N = 3SE +/- 130588.20, N = 33433223734123810

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa7M14M21M28M35MSE +/- 303573.79, N = 3SE +/- 154587.14, N = 33346680433268158

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa7M14M21M28M35MSE +/- 221111.93, N = 3SE +/- 188621.29, N = 33492589934762565

libavif avifenc

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

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 1.0Encoder Speed: 0c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan20406080100SE +/- 0.07, N = 3SE +/- 0.08, N = 378.0778.351. (CXX) g++ options: -O3 -fPIC -lm

PostgreSQL

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latencyt2d-standard-60 AMD Milan4080120160200SE +/- 1.44, N = 8172.721. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Write - Average Latencyt2d-standard-60 AMD Milan306090120150SE +/- 1.23, N = 12140.921. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latencyt2d-standard-60 AMD Milan0.11210.22420.33630.44840.5605SE +/- 0.006, N = 30.4981. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Only - Average Latencyt2d-standard-60 AMD Milan0.08980.17960.26940.35920.449SE +/- 0.004, N = 30.3991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-Onlyt2d-standard-60 AMD Milan306090120150SE +/- 0.03, N = 3112.64

Blend File: Pabellon Barcelona - Compute: CPU-Only

c3d-standard-60 AMD Genoa: The test quit with a non-zero exit status.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-Onlyt2d-standard-60 AMD Milan80160240320400SE +/- 0.60, N = 3351.58

Blend File: Barbershop - Compute: CPU-Only

c3d-standard-60 AMD Genoa: The test quit with a non-zero exit status.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-Onlyt2d-standard-60 AMD Milan1020304050SE +/- 0.13, N = 345.22

Blend File: Fishy Cat - Compute: CPU-Only

c3d-standard-60 AMD Genoa: The test quit with a non-zero exit status.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-Onlyt2d-standard-60 AMD Milan20406080100SE +/- 0.07, N = 389.35

Blend File: Classroom - Compute: CPU-Only

c3d-standard-60 AMD Genoa: The test quit with a non-zero exit status.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-Onlyt2d-standard-60 AMD Milan816243240SE +/- 0.06, N = 334.27

Blend File: BMW27 - Compute: CPU-Only

c3d-standard-60 AMD Genoa: The test quit with a non-zero exit status.

PostgreSQL

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Writet2d-standard-60 AMD Milan12002400360048006000SE +/- 49.93, N = 857931. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Scaling Factor: 100 - Clients: 1000 - Mode: Read Write

c3d-standard-60 AMD Genoa: The test run did not produce a result. E: ./pgbench: 21: pg_/bin/pgbench: not found

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Writet2d-standard-60 AMD Milan12002400360048006000SE +/- 49.28, N = 1256821. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Scaling Factor: 100 - Clients: 800 - Mode: Read Write

c3d-standard-60 AMD Genoa: The test run did not produce a result. E: ./pgbench: 21: pg_/bin/pgbench: not found

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Onlyt2d-standard-60 AMD Milan400K800K1200K1600K2000KSE +/- 22497.42, N = 320081861. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Scaling Factor: 100 - Clients: 1000 - Mode: Read Only

c3d-standard-60 AMD Genoa: The test run did not produce a result. E: ./pgbench: 21: pg_/bin/pgbench: not found

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 800 - Mode: Read Onlyt2d-standard-60 AMD Milan400K800K1200K1600K2000KSE +/- 20558.90, N = 320037841. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Scaling Factor: 100 - Clients: 800 - Mode: Read Only

c3d-standard-60 AMD Genoa: The test run did not produce a result. E: ./pgbench: 21: pg_/bin/pgbench: not found

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: allmodconfigt2d-standard-60 AMD Milan70140210280350SE +/- 1.20, N = 3333.35

Build: allmodconfig

c3d-standard-60 AMD Genoa: The test quit with a non-zero exit status. E: linux-6.1/tools/objtool/include/objtool/elf.h:10:10: fatal error: gelf.h: No such file or directory

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigt2d-standard-60 AMD Milan816243240SE +/- 0.37, N = 533.40

Build: defconfig

c3d-standard-60 AMD Genoa: The test quit with a non-zero exit status. E: linux-6.1/tools/objtool/include/objtool/elf.h:10:10: fatal error: gelf.h: No such file or directory

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Detection FP32 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan4080120160200SE +/- 0.29, N = 3SE +/- 7.79, N = 1583.91193.45MIN: 61.61 / MAX: 119.94MIN: 113.44 / MAX: 315.541. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Detection FP32 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan306090120150SE +/- 0.48, N = 3SE +/- 2.74, N = 15142.9078.961. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.1Model: Person Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan50100150200250SE +/- 0.13, N = 3SE +/- 9.17, N = 1583.99208.47MIN: 64.11 / MAX: 117.81MIN: 119.65 / MAX: 316.011. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.1Model: Person Detection FP16 - Device: CPUc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan306090120150SE +/- 0.23, N = 3SE +/- 3.12, N = 15142.7573.741. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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: 400c3d-standard-60 AMD Genoat2d-standard-60 AMD Milan150300450600750SE +/- 7.53, N = 3SE +/- 25.87, N = 3682.12709.46MAX: 98294.84MAX: 113264.06

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 400t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa100200300400500SE +/- 35.57, N = 3SE +/- 27.08, N = 3433.96447.68MAX: 103381.73MAX: 95136.87

LAMMPS Molecular Dynamics Simulator

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

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin Proteint2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa714212835SE +/- 0.17, N = 3SE +/- 0.54, N = 1227.8317.421. (CXX) g++ options: -O3 -lm -ldl

nekRS

nekRS is an open-source Navier Stokes solver based on the spectral element method. NekRS supports both CPU and GPU/accelerator support though this test profile is currently configured for CPU execution. NekRS is part of Nek5000 of the Mathematics and Computer Science MCS at Argonne National Laboratory. This nekRS benchmark is primarily relevant to large core count HPC servers and otherwise may be very time consuming on smaller systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: TurboPipe Periodicc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan1000M2000M3000M4000M5000MSE +/- 201939132.13, N = 12SE +/- 481352.26, N = 3472394000027306200001. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: Kershawc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan900M1800M2700M3600M4500MSE +/- 57202190.49, N = 12SE +/- 84802173.02, N = 12428985833336819358331. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

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.

Model: INIVOL and Fluid Structure Interaction Drop Container

c3d-standard-60 AMD Genoa: The test run did not produce a result. E: ** ERROR: INPUT FILE /fsi_drop_container NOT FOUND

t2d-standard-60 AMD Milan: The test run did not produce a result. E: ** ERROR: INPUT FILE /fsi_drop_container NOT FOUND

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Rubber O-Ring Seal Installationt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa20406080100SE +/- 0.22, N = 3SE +/- 4.01, N = 1272.0689.65

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bird Strike on Windshieldt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa306090120150SE +/- 0.13, N = 3SE +/- 3.26, N = 9123.61147.31

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Cell Phone Drop Testt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa918273645SE +/- 0.39, N = 15SE +/- 1.27, N = 1530.1238.82

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Bumper Beamt2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa20406080100SE +/- 0.10, N = 3SE +/- 1.56, N = 1575.6892.87

HeFFTe - Highly Efficient FFT for Exascale

HeFFTe is the Highly Efficient FFT for Exascale software developed as part of the Exascale Computing Project. This test profile uses HeFFTe's built-in speed benchmarks under a variety of configuration options and currently catering to CPU/processor testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa20406080100SE +/- 0.91, N = 3SE +/- 1.78, N = 12106.0393.601. (CXX) g++ options: -O3

OpenBenchmarking.orgGFLOP/s, More Is BetterHeFFTe - Highly Efficient FFT for Exascale 2.3Test: c2c - Backend: FFTW - Precision: double - X Y Z: 128t2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa1326395265SE +/- 0.66, N = 3SE +/- 1.29, N = 1560.0357.311. (CXX) g++ options: -O3

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamclustert2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa246810SE +/- 0.009, N = 3SE +/- 0.104, N = 156.4236.4481. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3Dc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan20406080100SE +/- 0.86, N = 15SE +/- 1.83, N = 1284.1788.541. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.Ct2d-standard-60 AMD Milanc3d-standard-60 AMD Genoa20K40K60K80K100KSE +/- 1463.52, N = 15SE +/- 293.57, N = 394247.7773563.131. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.Dc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan5001000150020002500SE +/- 36.45, N = 15SE +/- 142.62, N = 122422.401752.621. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.Cc3d-standard-60 AMD Genoat2d-standard-60 AMD Milan4K8K12K16K20KSE +/- 77.92, N = 3SE +/- 1215.82, N = 1519597.8616649.371. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.2

119 Results Shown

OpenVINO:
  Vehicle Detection FP16 - CPU
  Face Detection Retail FP16 - CPU
  Vehicle Detection FP16 - CPU
  Person Vehicle Bike Detection FP16 - CPU
TensorFlow
OpenVINO:
  Face Detection Retail FP16 - CPU
  Road Segmentation ADAS FP16 - CPU
TensorFlow:
  CPU - 32 - ResNet-50
  CPU - 16 - ResNet-50
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU
  Handwritten English Recognition FP16 - CPU
  Handwritten English Recognition FP16 - CPU
  Road Segmentation ADAS FP16 - CPU
  Machine Translation EN To DE FP16 - CPU
  Face Detection FP16 - CPU
Remhos
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
  Machine Translation EN To DE FP16 - CPU:
    FPS
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
  Weld Porosity Detection FP16 - CPU:
    FPS
OpenSSL
OpenVINO:
  Face Detection FP16 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Face Detection FP16-INT8 - CPU
  Face Detection Retail FP16-INT8 - CPU
OpenSSL
OpenVINO
OpenSSL
OpenVINO
OpenSSL
OpenVINO
Laghos
NAS Parallel Benchmarks
OpenVINO:
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
Rodinia
OpenSSL
LAMMPS Molecular Dynamics Simulator
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU
  Face Detection FP16-INT8 - CPU
HeFFTe - Highly Efficient FFT for Exascale
NAS Parallel Benchmarks
OpenVINO
NAS Parallel Benchmarks
Rodinia
OpenVINO
HeFFTe - Highly Efficient FFT for Exascale
BRL-CAD
Apache Cassandra
GROMACS
Coremark
nginx:
  1000
  500
OpenVINO
Xcompact3d Incompact3d
libxsmm:
  32
  64
libavif avifenc
NAS Parallel Benchmarks
OpenSSL
7-Zip Compression
Rodinia
NAS Parallel Benchmarks
OpenVINO
Stockfish
Laghos
Algebraic Multi-Grid Benchmark
Xcompact3d Incompact3d
OpenSSL:
  ChaCha20
  ChaCha20-Poly1305
Timed Node.js Compilation
Timed Gem5 Compilation
OpenRadioss
7-Zip Compression
Apache IoTDB
libavif avifenc:
  6
  2
Apache IoTDB:
  500 - 100 - 500 - 400
  800 - 100 - 800 - 400
  800 - 100 - 500 - 400
  500 - 100 - 500 - 400
  500 - 100 - 800 - 400
libavif avifenc
PostgreSQL:
  100 - 1000 - Read Write - Average Latency
  100 - 800 - Read Write - Average Latency
  100 - 1000 - Read Only - Average Latency
  100 - 800 - Read Only - Average Latency
Blender:
  Pabellon Barcelona - CPU-Only
  Barbershop - CPU-Only
  Fishy Cat - CPU-Only
  Classroom - CPU-Only
  BMW27 - CPU-Only
PostgreSQL:
  100 - 1000 - Read Write
  100 - 800 - Read Write
  100 - 1000 - Read Only
  100 - 800 - Read Only
Timed Linux Kernel Compilation:
  allmodconfig
  defconfig
OpenVINO:
  Person Detection FP32 - CPU:
    ms
    FPS
  Person Detection FP16 - CPU:
    ms
    FPS
Apache IoTDB:
  800 - 100 - 800 - 400
  800 - 100 - 500 - 400
LAMMPS Molecular Dynamics Simulator
nekRS:
  TurboPipe Periodic
  Kershaw
OpenRadioss:
  Rubber O-Ring Seal Installation
  Bird Strike on Windshield
  Cell Phone Drop Test
  Bumper Beam
HeFFTe - Highly Efficient FFT for Exascale:
  r2c - FFTW - double - 128
  c2c - FFTW - double - 128
Rodinia:
  OpenMP Streamcluster
  OpenMP HotSpot3D
NAS Parallel Benchmarks:
  LU.C
  IS.D
  CG.C

c3d-standard-60 AMD Genoa

Processor: AMD EPYC 9B14 (30 Cores / 60 Threads), Motherboard: Google Compute Engine c3d-standard-60, Chipset: Intel 440FX 82441FX PMC, Memory: 240GB, Disk: 215GB nvme_card-pd, Network: Google Compute Engine Virtual

OS: Ubuntu 22.04, Kernel: 6.2.0-1014-gcp (x86_64), Vulkan: 1.3.238, Compiler: GCC 11.4.0, File-System: ext4, System Layer: KVM

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: CPU Microcode: 0xffffffff
Java Notes: OpenJDK Runtime Environment (build 11.0.20.1+1-post-Ubuntu-0ubuntu122.04)
Python Notes: Python 3.10.12
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_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 3 October 2023 00:31 by user michael_larabel.

t2d-standard-60 AMD Milan

Processor: AMD EPYC 7B13 (60 Cores), Motherboard: Google Compute Engine t2d-standard-60, Chipset: Intel 440FX 82441FX PMC, Memory: 240GB, Disk: 215GB PersistentDisk, Network: Red Hat Virtio device

OS: Ubuntu 22.04, Kernel: 6.2.0-1014-gcp (x86_64), Vulkan: 1.3.238, Compiler: GCC 11.4.0, File-System: ext4, System Layer: KVM

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/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: CPU Microcode: 0xffffffff
Java Notes: OpenJDK Runtime Environment (build 11.0.20.1+1-post-Ubuntu-0ubuntu122.04)
Python Notes: Python 3.10.12
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_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 3 October 2023 12:59 by user michael_larabel.