Microsoft Azure EPYC 7003 HPC HBv3 Benchmarks

Azure HBv3 benchmarks against other Microsoft Azure HPC instance types. Benchmarks by Michael Larabel for a future article on phoronix.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2104153-PTS-AZUREHPC42
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

Timed Code Compilation 3 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 14 Tests
Creator Workloads 4 Tests
Encoding 3 Tests
Finance 2 Tests
Fortran Tests 4 Tests
HPC - High Performance Computing 14 Tests
Machine Learning 5 Tests
Molecular Dynamics 6 Tests
MPI Benchmarks 5 Tests
Multi-Core 14 Tests
NVIDIA GPU Compute 4 Tests
OpenMPI Tests 8 Tests
Programmer / Developer System Benchmarks 4 Tests
Python Tests 3 Tests
Scientific Computing 6 Tests
Server CPU Tests 10 Tests
Single-Threaded 2 Tests
Video Encoding 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
Azure HBv3 - EPYC 7V13
April 09 2021
  7 Hours, 20 Minutes
Azure HBv2 - EPYC 7V12
April 10 2021
  7 Hours, 28 Minutes
Azure HBv1 - EPYC 7551
April 11 2021
  9 Hours, 51 Minutes
Azure HC - Xeon 8168
April 12 2021
  4 Hours, 24 Minutes
Azure H - Xeon E5-2667 v3
April 14 2021
  9 Hours, 51 Minutes
Invert Hiding All Results Option
  7 Hours, 47 Minutes

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


Microsoft Azure EPYC 7003 HPC HBv3 BenchmarksProcessorMotherboardMemoryDiskGraphicsChipsetOSKernelCompilerFile-SystemScreen ResolutionSystem LayerAzure HBv3 - EPYC 7V13Azure HBv2 - EPYC 7V12Azure HBv1 - EPYC 7551Azure HC - Xeon 8168Azure H - Xeon E5-2667 v32 x AMD EPYC 7V13 64-Core (120 Cores)Microsoft Virtual Machine (Hyper-V UEFI v4.1 BIOS)442GB2 x 960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual Diskhyperv_fbCentOS Linux 84.18.0-147.8.1.el8_1.x86_64 (x86_64)GCC 8.3.1 20190507nfs1152x864microsoft2 x AMD EPYC 7V12 64-Core (120 Cores)Microsoft Virtual Machine (Hyper-V UEFI v4.0 BIOS)450GB960GB Microsoft NVMe Direct Disk + 32GB Virtual Disk + 515GB Virtual Disk2 x AMD EPYC 7551 32-Core (60 Cores)226GB32GB Virtual Disk + 752GB Virtual Disk2 x Intel Xeon Platinum 8168 (44 Cores)348GB2 x Intel Xeon E5-2667 v3 (16 Cores)Microsoft Virtual Machine v7.0 (090007 BIOS)Intel 440BX/ZX/DX222GB32GB Virtual Disk + 2199GB Virtual DiskMicrosoft Hyper-V virtual VGAMicrosoft Hyper-V ServerOpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --build=x86_64-redhat-linux --disable-libmpx --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-gcc-major-version-only --with-isl --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Processor Details- CPU Microcode: 0xffffffffPython Details- Python 3.6.8Security Details- Azure HBv3 - EPYC 7V13: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + tsx_async_abort: Not affected- Azure HBv2 - EPYC 7V12: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + tsx_async_abort: Not affected- Azure HBv1 - EPYC 7551: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + tsx_async_abort: Not affected- Azure HC - Xeon 8168: itlb_multihit: vulnerable + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT Host state unknown + meltdown: Mitigation of PTI + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT Host state unknown - Azure H - Xeon E5-2667 v3: itlb_multihit: vulnerable + l1tf: Mitigation of PTE Inversion + mds: Mitigation of Clear buffers; SMT Host state unknown + meltdown: Mitigation of PTI + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline STIBP: disabled RSB filling + tsx_async_abort: Not affected

Azure HBv3 - EPYC 7V13Azure HBv2 - EPYC 7V12Azure HBv1 - EPYC 7551Azure HC - Xeon 8168Azure H - Xeon E5-2667 v3Logarithmic Result OverviewPhoronix Test SuiteoneDNNGROMACSCloverLeafLULESHNAMDTimed Node.js CompilationSVT-HEVCSVT-VP9Xcompact3d Incompact3dHigh Performance Conjugate GradientTimed LLVM CompilationRodiniaTimed Linux Kernel CompilationSVT-AV1Mobile Neural NetworkZstd CompressionTensorFlow LitePennantPlaidMLQuantLibBotanGNU GMP GMPbenchTNNFinanceBench

Microsoft Azure EPYC 7003 HPC HBv3 Benchmarksrodinia: OpenMP LavaMDgromacs: Water Benchmarknpb: LU.Clulesh: svt-hevc: 1 - Bosphorus 1080pcompress-zstd: 8 - Compression Speedbuild-nodejs: Time To Compilesvt-vp9: Visual Quality Optimized - Bosphorus 1080pincompact3d: X3D-benchmarking input.i3dhpcg: build-llvm: Time To Compilesvt-av1: Enc Mode 8 - 1080pbuild-linux-kernel: Time To Compileplaidml: No - Inference - VGG19 - CPUplaidml: No - Inference - VGG16 - CPUbotan: ChaCha20Poly1305botan: ChaCha20Poly1305 - Decryptsvt-av1: Enc Mode 0 - 1080ppennant: leblancbigpennant: sedovbigcompress-zstd: 19 - Decompression Speedcompress-zstd: 19, Long Mode - Decompression Speedbotan: AES-256botan: AES-256 - Decryptcompress-zstd: 8, Long Mode - Decompression Speedfinancebench: Bonds OpenMPquantlib: financebench: Repo OpenMProdinia: OpenMP HotSpot3Dcompress-zstd: 8, Long Mode - Compression Speedgmpbench: Total Timebotan: Twofishbotan: Twofish - Decryptbotan: Blowfish - Decryptbotan: Blowfishtnn: CPU - SqueezeNet v1.1botan: CAST-256botan: KASUMIbotan: CAST-256 - Decryptbotan: KASUMI - Decryptplaidml: No - Inference - ResNet 50 - CPUmnn: inception-v3mnn: resnet-v2-50mnn: SqueezeNetV1.0tensorflow-lite: SqueezeNetonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: IP Shapes 3D - u8s8f32 - CPUonednn: IP Shapes 3D - f32 - CPUsvt-hevc: 10 - Bosphorus 1080psvt-hevc: 7 - Bosphorus 1080psvt-av1: Enc Mode 4 - 1080pcompress-zstd: 19 - Compression Speednamd: ATPase Simulation - 327,506 Atomscloverleaf: Lagrangian-Eulerian HydrodynamicsAzure HBv3 - EPYC 7V13Azure HBv2 - EPYC 7V12Azure HBv1 - EPYC 7551Azure HC - Xeon 8168Azure H - Xeon E5-2667 v337.8039.04156682.8241636.60345.393184.2111.327337.71287.59950839.0620163.76094.02842.00834.5338.39667.765658.3700.1613.3372015.8334193717.53727.55412.1315407.4774256.8104884.2942712299.359196.54687582.489771.94893.4346.319345.776425.158424.738272.614133.69187.480133.66584.0596.2734.71029.0868.22466320.40.445223540.194843.1030.255501561.773962.336530.898875.1660.4556820.4066860.3838553.21204548.33378.0112.27578.20.2756616.6639.1988.45853829.3434803.53936.122653.1118.969140.59318.90500937.2686174.74378.10444.92223.1225.57615.795610.8610.1243.4865036.0264492631.02674.23934.4013938.4443037.5133719.3281251725.275154.257813107.976588.04155.5280.902283.257349.147348.425323.615113.60073.175113.72471.1015.6055.35652.53314.13674885.40.524737796.8161294.530.350347791.4601287.03778.3051314.000.7321301.0319420.4410129.68321379.91166.909.51269.50.3005623.7890.1753.28825304.1919011.45821.12920.1194.550129.44455.81237830.4314283.29140.14658.73815.9719.88303.243300.1780.07610.3376415.528992005.42019.33144.3133151.2282339.6195702.7968751251.7108606.502604145.569468.83021.3217.312218.034272.733273.039420.04788.54557.95088.55555.9804.8076.79962.44617.19495206.21.154653423.155355.241.512713373.885539.483344.145524.502.736212.405611.7635510.22263141.93119.204.66948.50.7094725.0094.1194.86620846.59023.871188.2189.096299.95507.29597026.0381251.74457.37755.32434.6641.54633.217626.9190.11110.5292023.871261903.91991.33155.3913159.8522350.2130250.4492191812.971609.065104115.832649.34196.5293.551294.381365.547367.942398.404116.63076.149116.57374.2874.9135.67329.0068.22673517.30.398005458.201753.3560.352180459.576746.464462.855744.3550.6686410.5514670.4743113.28160480.79256.287.62176.30.5256920.19284.1871.2297870.046444.24638.12582.7469.94283.401157.9332710.19951599.91326.835134.74014.8018.12551.827544.5840.08945.6774279.648781934.32006.32891.8462892.7192279.8147211.2395831505.180350.648438126.185567.43942.7270.067269.659327.093322.924335.411103.37270.985103.25168.3494.4840.58631.5048.9761754854.013922802.874495.904.233823198.074449.573117.454793.755.987126.924717.328628.70022172.1695.143.49039.81.71710111.14OpenBenchmarking.org

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 LavaMDAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1360120180240300SE +/- 3.12, N = 3SE +/- 0.02, N = 3SE +/- 0.39, N = 3SE +/- 0.20, N = 3SE +/- 0.23, N = 3284.1994.1290.1839.2037.801. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP LavaMDAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1350100150200250Min: 279.93 / Avg: 284.19 / Max: 290.26Min: 94.09 / Avg: 94.12 / Max: 94.15Min: 89.43 / Avg: 90.18 / Max: 90.73Min: 38.79 / Avg: 39.2 / Max: 39.41Min: 37.37 / Avg: 37.8 / Max: 38.121. (CXX) g++ options: -O2 -lOpenCL

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.025, N = 15SE +/- 0.009, N = 3SE +/- 0.009, N = 31.2294.8663.2888.4589.0411. (CXX) g++ options: -O2 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.3Water BenchmarkAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215Min: 1.23 / Avg: 1.23 / Max: 1.23Min: 4.86 / Avg: 4.87 / Max: 4.87Min: 3.16 / Avg: 3.29 / Max: 3.56Min: 8.45 / Avg: 8.46 / Max: 8.48Min: 9.03 / Avg: 9.04 / Max: 9.061. (CXX) g++ options: -O2 -pthread -lrt -lpthread -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: LU.CAzure H - Xeon E5-2667 v3Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1312K24K36K48K60KSE +/- 33.92, N = 3SE +/- 114.01, N = 3SE +/- 21.24, N = 3SE +/- 428.57, N = 147870.0425304.1953829.3456682.821. (F9X) gfortran options: -O3 -march=native -fexceptions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CAzure H - Xeon E5-2667 v3Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1310K20K30K40K50KMin: 7807.52 / Avg: 7870.04 / Max: 7924.1Min: 25096.86 / Avg: 25304.19 / Max: 25490.03Min: 53787.12 / Avg: 53829.34 / Max: 53854.58Min: 51213.56 / Avg: 56682.82 / Max: 57398.811. (F9X) gfortran options: -O3 -march=native -fexceptions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

LULESH

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

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V139K18K27K36K45KSE +/- 28.01, N = 3SE +/- 25.50, N = 3SE +/- 81.47, N = 3SE +/- 44.77, N = 3SE +/- 476.10, N = 36444.2520846.5919011.4634803.5441636.601. (CXX) g++ options: -O3 -fopenmp -lm -fexceptions -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V137K14K21K28K35KMin: 6401.94 / Avg: 6444.25 / Max: 6497.19Min: 20796.32 / Avg: 20846.59 / Max: 20879.16Min: 18850.32 / Avg: 19011.46 / Max: 19112.96Min: 34743.07 / Avg: 34803.54 / Max: 34890.96Min: 40950.33 / Avg: 41636.6 / Max: 42551.381. (CXX) g++ options: -O3 -fopenmp -lm -fexceptions -pthread -lmpi_cxx -lmpi

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131020304050SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.60, N = 38.1223.8721.1236.1245.391. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13918273645Min: 8.01 / Avg: 8.12 / Max: 8.2Min: 23.83 / Avg: 23.87 / Max: 23.91Min: 20.89 / Avg: 21.12 / Max: 21.27Min: 35.86 / Avg: 36.12 / Max: 36.3Min: 44.65 / Avg: 45.39 / Max: 46.571. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V137001400210028003500SE +/- 1.83, N = 3SE +/- 6.93, N = 3SE +/- 6.06, N = 3SE +/- 33.03, N = 15SE +/- 45.10, N = 3582.71188.2920.12653.13184.21. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8 - Compression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V136001200180024003000Min: 580 / Avg: 582.7 / Max: 586.2Min: 1174.3 / Avg: 1188.17 / Max: 1195.2Min: 911.5 / Avg: 920.1 / Max: 931.8Min: 2446.8 / Avg: 2653.14 / Max: 2850.1Min: 3127 / Avg: 3184.2 / Max: 3273.21. (CC) gcc options: -O3 -pthread -lz -llzma

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 15.11Time To CompileAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13100200300400500SE +/- 0.95, N = 3SE +/- 0.40, N = 3SE +/- 0.16, N = 3SE +/- 0.83, N = 3SE +/- 1.09, N = 3469.94189.10194.55118.97111.33
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 15.11Time To CompileAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1380160240320400Min: 468.49 / Avg: 469.94 / Max: 471.74Min: 188.62 / Avg: 189.1 / Max: 189.89Min: 194.23 / Avg: 194.55 / Max: 194.72Min: 118.09 / Avg: 118.97 / Max: 120.62Min: 110.23 / Avg: 111.33 / Max: 113.5

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1370140210280350SE +/- 1.28, N = 15SE +/- 4.18, N = 3SE +/- 1.10, N = 8SE +/- 0.20, N = 3SE +/- 4.36, N = 383.40299.95129.44140.59337.711. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -O2 -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1360120180240300Min: 72.48 / Avg: 83.4 / Max: 89.51Min: 292.23 / Avg: 299.95 / Max: 306.61Min: 125.4 / Avg: 129.44 / Max: 134.34Min: 140.32 / Avg: 140.59 / Max: 140.98Min: 329.01 / Avg: 337.71 / Max: 342.571. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -O2 -pie -rdynamic -lpthread -lrt -lm

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.i3dAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V132004006008001000SE +/- 12.66, N = 3SE +/- 7.11, N = 3SE +/- 2.96, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 31157.93507.30455.81318.91287.601. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -fexceptions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V132004006008001000Min: 1140.28 / Avg: 1157.93 / Max: 1182.48Min: 494.7 / Avg: 507.3 / Max: 519.32Min: 449.89 / Avg: 455.81 / Max: 458.88Min: 318.81 / Avg: 318.91 / Max: 319.04Min: 287.31 / Avg: 287.6 / Max: 287.891. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -fexceptions -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13918273645SE +/- 0.09, N = 8SE +/- 0.01, N = 3SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 310.2026.0430.4337.2739.061. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -fexceptions -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13816243240Min: 9.76 / Avg: 10.2 / Max: 10.61Min: 26.02 / Avg: 26.04 / Max: 26.07Min: 30.1 / Avg: 30.43 / Max: 30.68Min: 37.16 / Avg: 37.27 / Max: 37.36Min: 38.95 / Avg: 39.06 / Max: 39.141. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -fexceptions -pthread -lmpi_cxx -lmpi

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13130260390520650SE +/- 2.26, N = 3SE +/- 2.31, N = 3SE +/- 3.41, N = 4SE +/- 1.99, N = 3SE +/- 1.89, N = 3599.91251.74283.29174.74163.76
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To CompileAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13110220330440550Min: 596.97 / Avg: 599.91 / Max: 604.35Min: 247.13 / Avg: 251.74 / Max: 254.37Min: 276.76 / Avg: 283.29 / Max: 292.78Min: 172.31 / Avg: 174.74 / Max: 178.69Min: 160.99 / Avg: 163.76 / Max: 167.37

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100SE +/- 0.35, N = 3SE +/- 0.24, N = 3SE +/- 0.54, N = 12SE +/- 0.65, N = 3SE +/- 0.34, N = 326.8457.3840.1578.1094.031. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100Min: 26.39 / Avg: 26.84 / Max: 27.53Min: 56.97 / Avg: 57.38 / Max: 57.8Min: 36.81 / Avg: 40.15 / Max: 44.64Min: 76.81 / Avg: 78.1 / Max: 78.78Min: 93.43 / Avg: 94.03 / Max: 94.591. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150SE +/- 1.07, N = 12SE +/- 0.60, N = 15SE +/- 0.45, N = 13SE +/- 0.58, N = 13SE +/- 0.58, N = 15134.7455.3258.7444.9242.01
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.10.20Time To CompileAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150Min: 130.36 / Avg: 134.74 / Max: 142.34Min: 52.95 / Avg: 55.32 / Max: 63.01Min: 58.06 / Avg: 58.74 / Max: 64.17Min: 43.11 / Avg: 44.92 / Max: 50.84Min: 39.43 / Avg: 42.01 / Max: 49.12

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13816243240SE +/- 0.18, N = 4SE +/- 0.19, N = 3SE +/- 0.21, N = 12SE +/- 0.31, N = 15SE +/- 0.42, N = 414.8034.6615.9723.1234.53
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG19 - Device: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13714212835Min: 14.32 / Avg: 14.8 / Max: 15.11Min: 34.38 / Avg: 34.66 / Max: 35.03Min: 14.37 / Avg: 15.97 / Max: 16.97Min: 20.74 / Avg: 23.12 / Max: 25.41Min: 33.43 / Avg: 34.53 / Max: 35.48

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13918273645SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.21, N = 15SE +/- 0.21, N = 3SE +/- 0.39, N = 318.1241.5419.8825.5738.39
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13918273645Min: 18.09 / Avg: 18.12 / Max: 18.18Min: 41.2 / Avg: 41.54 / Max: 41.95Min: 18.51 / Avg: 19.88 / Max: 21.43Min: 25.32 / Avg: 25.57 / Max: 25.98Min: 37.7 / Avg: 38.39 / Max: 39.06

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13140280420560700SE +/- 2.26, N = 3SE +/- 0.30, N = 3SE +/- 1.39, N = 3SE +/- 0.90, N = 3SE +/- 0.27, N = 3551.83633.22303.24615.80667.771. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13120240360480600Min: 547.37 / Avg: 551.83 / Max: 554.66Min: 632.67 / Avg: 633.22 / Max: 633.7Min: 300.93 / Avg: 303.24 / Max: 305.73Min: 614.01 / Avg: 615.79 / Max: 616.82Min: 667.33 / Avg: 667.77 / Max: 668.251. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13140280420560700SE +/- 1.38, N = 3SE +/- 0.55, N = 3SE +/- 1.37, N = 3SE +/- 0.78, N = 3SE +/- 0.06, N = 3544.58626.92300.18610.86658.371. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: ChaCha20Poly1305 - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13120240360480600Min: 542.18 / Avg: 544.58 / Max: 546.96Min: 625.83 / Avg: 626.92 / Max: 627.6Min: 298.15 / Avg: 300.18 / Max: 302.8Min: 609.48 / Avg: 610.86 / Max: 612.17Min: 658.25 / Avg: 658.37 / Max: 658.441. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V130.03620.07240.10860.14480.181SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.0890.1110.0760.1240.1611. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1312345Min: 0.09 / Avg: 0.09 / Max: 0.09Min: 0.11 / Avg: 0.11 / Max: 0.11Min: 0.08 / Avg: 0.08 / Max: 0.08Min: 0.12 / Avg: 0.12 / Max: 0.13Min: 0.16 / Avg: 0.16 / Max: 0.161. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Pennant

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

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131020304050SE +/- 0.671685, N = 12SE +/- 0.037598, N = 3SE +/- 0.027196, N = 3SE +/- 0.009939, N = 3SE +/- 0.017738, N = 345.67742010.52920010.3376403.4865033.3372011. (CXX) g++ options: -fopenmp -fexceptions -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13918273645Min: 42.82 / Avg: 45.68 / Max: 51.12Min: 10.49 / Avg: 10.53 / Max: 10.6Min: 10.3 / Avg: 10.34 / Max: 10.39Min: 3.47 / Avg: 3.49 / Max: 3.51Min: 3.3 / Avg: 3.34 / Max: 3.361. (CXX) g++ options: -fopenmp -fexceptions -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100SE +/- 0.744226, N = 15SE +/- 0.048781, N = 3SE +/- 0.085157, N = 3SE +/- 0.012548, N = 3SE +/- 0.003905, N = 379.64878023.87126015.5289906.0264495.8334191. (CXX) g++ options: -fopenmp -fexceptions -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131530456075Min: 76.62 / Avg: 79.65 / Max: 84.61Min: 23.78 / Avg: 23.87 / Max: 23.94Min: 15.38 / Avg: 15.53 / Max: 15.68Min: 6 / Avg: 6.03 / Max: 6.05Min: 5.83 / Avg: 5.83 / Max: 5.841. (CXX) g++ options: -fopenmp -fexceptions -pthread -lmpi_cxx -lmpi

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V138001600240032004000SE +/- 2.70, N = 3SE +/- 2.22, N = 15SE +/- 0.66, N = 15SE +/- 1.17, N = 15SE +/- 6.14, N = 151934.31903.92005.42631.03717.51. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Decompression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V136001200180024003000Min: 1928.9 / Avg: 1934.3 / Max: 1937.2Min: 1887.5 / Avg: 1903.87 / Max: 1914.3Min: 2002 / Avg: 2005.4 / Max: 2009.2Min: 2621.5 / Avg: 2631.01 / Max: 2637.8Min: 3679.6 / Avg: 3717.45 / Max: 37521. (CC) gcc options: -O3 -pthread -lz -llzma

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V138001600240032004000SE +/- 2.28, N = 5SE +/- 2.46, N = 15SE +/- 0.32, N = 12SE +/- 2.70, N = 15SE +/- 12.70, N = 152006.31991.32019.32674.23727.51. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19, Long Mode - Decompression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V136001200180024003000Min: 2002.4 / Avg: 2006.3 / Max: 2015.2Min: 1978.3 / Avg: 1991.33 / Max: 2007.9Min: 2017.1 / Avg: 2019.28 / Max: 2020.7Min: 2640.1 / Avg: 2674.21 / Max: 2684.6Min: 3565.1 / Avg: 3727.52 / Max: 3764.51. (CC) gcc options: -O3 -pthread -lz -llzma

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1312002400360048006000SE +/- 4.69, N = 3SE +/- 0.18, N = 3SE +/- 16.79, N = 3SE +/- 2.68, N = 3SE +/- 3.73, N = 32891.853155.393144.313934.405412.131. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V139001800270036004500Min: 2884.15 / Avg: 2891.85 / Max: 2900.33Min: 3155.19 / Avg: 3155.39 / Max: 3155.74Min: 3110.74 / Avg: 3144.31 / Max: 3161.45Min: 3929.32 / Avg: 3934.4 / Max: 3938.41Min: 5405.03 / Avg: 5412.13 / Max: 5417.661. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1312002400360048006000SE +/- 5.16, N = 3SE +/- 0.03, N = 3SE +/- 1.16, N = 3SE +/- 3.26, N = 3SE +/- 7.85, N = 32892.723159.853151.233938.445407.481. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: AES-256 - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V139001800270036004500Min: 2886.59 / Avg: 2892.72 / Max: 2902.98Min: 3159.82 / Avg: 3159.85 / Max: 3159.91Min: 3149.12 / Avg: 3151.23 / Max: 3153.12Min: 3931.93 / Avg: 3938.44 / Max: 3941.77Min: 5393.16 / Avg: 5407.48 / Max: 5420.231. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V139001800270036004500SE +/- 13.10, N = 3SE +/- 2.50, N = 3SE +/- 1.19, N = 15SE +/- 4.57, N = 3SE +/- 4.89, N = 72279.82350.22339.63037.54256.81. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Decompression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V137001400210028003500Min: 2264.8 / Avg: 2279.8 / Max: 2305.9Min: 2347.3 / Avg: 2350.23 / Max: 2355.2Min: 2328.6 / Avg: 2339.59 / Max: 2344.6Min: 3028.9 / Avg: 3037.5 / Max: 3044.5Min: 4238.7 / Avg: 4256.83 / Max: 4275.71. (CC) gcc options: -O3 -pthread -lz -llzma

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1340K80K120K160K200KSE +/- 150.66, N = 3SE +/- 1475.96, N = 4SE +/- 1191.05, N = 3SE +/- 476.22, N = 3SE +/- 454.05, N = 3147211.24130250.45195702.80133719.33104884.291. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Bonds OpenMPAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1330K60K90K120K150KMin: 147007.98 / Avg: 147211.24 / Max: 147505.5Min: 128723.8 / Avg: 130250.45 / Max: 134677.39Min: 194234.83 / Avg: 195702.8 / Max: 198061.47Min: 132784.52 / Avg: 133719.33 / Max: 134344.66Min: 104078.39 / Avg: 104884.29 / Max: 105649.71. (CXX) g++ options: -O3 -march=native -fopenmp

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 1.21Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V135001000150020002500SE +/- 4.07, N = 3SE +/- 7.80, N = 3SE +/- 1.79, N = 3SE +/- 0.77, N = 3SE +/- 4.80, N = 31505.11812.91251.71725.22299.31. (CXX) g++ options: -O3 -march=native -O2 -rdynamic -lboost_timer -lboost_system -lboost_chrono
OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.21Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13400800120016002000Min: 1497.6 / Avg: 1505.07 / Max: 1511.6Min: 1797.3 / Avg: 1812.9 / Max: 1821Min: 1249 / Avg: 1251.73 / Max: 1255.1Min: 1724.1 / Avg: 1725.23 / Max: 1726.7Min: 2290.1 / Avg: 2299.27 / Max: 2306.31. (CXX) g++ options: -O3 -march=native -O2 -rdynamic -lboost_timer -lboost_system -lboost_chrono

FinanceBench

FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320K40K60K80K100KSE +/- 85.66, N = 3SE +/- 15.23, N = 3SE +/- 324.87, N = 3SE +/- 166.77, N = 3SE +/- 228.72, N = 380350.6571609.07108606.5075154.2659196.551. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Repo OpenMPAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320K40K60K80K100KMin: 80186.23 / Avg: 80350.65 / Max: 80474.55Min: 71583.8 / Avg: 71609.07 / Max: 71636.45Min: 107956.81 / Avg: 108606.5 / Max: 108937.86Min: 74919.02 / Avg: 75154.26 / Max: 75476.66Min: 58815.6 / Avg: 59196.55 / Max: 59606.331. (CXX) g++ options: -O3 -march=native -fopenmp

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 HotSpot3DAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150SE +/- 0.43, N = 3SE +/- 0.21, N = 3SE +/- 1.35, N = 3SE +/- 0.89, N = 3SE +/- 1.18, N = 15126.19115.83145.57107.9882.491. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP HotSpot3DAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150Min: 125.68 / Avg: 126.19 / Max: 127.04Min: 115.57 / Avg: 115.83 / Max: 116.24Min: 142.93 / Avg: 145.57 / Max: 147.39Min: 106.46 / Avg: 107.98 / Max: 109.52Min: 77.17 / Avg: 82.49 / Max: 91.091. (CXX) g++ options: -O2 -lOpenCL

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13170340510680850SE +/- 1.99, N = 3SE +/- 6.29, N = 3SE +/- 3.02, N = 15SE +/- 0.81, N = 3SE +/- 6.99, N = 7567.4649.3468.8588.0771.91. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 8, Long Mode - Compression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13140280420560700Min: 564.3 / Avg: 567.4 / Max: 571.1Min: 642.4 / Avg: 649.33 / Max: 661.9Min: 450.5 / Avg: 468.85 / Max: 490.8Min: 586.7 / Avg: 588 / Max: 589.5Min: 748.6 / Avg: 771.91 / Max: 801.21. (CC) gcc options: -O3 -pthread -lz -llzma

GNU GMP GMPbench

GMPbench is a test of the GNU Multiple Precision Arithmetic (GMP) Library. GMPbench is a single-threaded integer benchmark that leverages the GMP library to stress the CPU with widening integer multiplication. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.2.1Total TimeAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13100020003000400050003942.74196.53021.34155.54893.41. (CC) gcc options: -O3 -fomit-frame-pointer -lm

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: TwofishAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1380160240320400SE +/- 0.46, N = 3SE +/- 0.20, N = 3SE +/- 2.54, N = 4SE +/- 0.15, N = 3SE +/- 1.10, N = 3270.07293.55217.31280.90346.321. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: TwofishAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1360120180240300Min: 269.31 / Avg: 270.07 / Max: 270.9Min: 293.16 / Avg: 293.55 / Max: 293.83Min: 209.7 / Avg: 217.31 / Max: 220.28Min: 280.75 / Avg: 280.9 / Max: 281.2Min: 344.13 / Avg: 346.32 / Max: 347.561. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1380160240320400SE +/- 0.99, N = 3SE +/- 0.13, N = 3SE +/- 2.43, N = 4SE +/- 0.22, N = 3SE +/- 0.77, N = 3269.66294.38218.03283.26345.781. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Twofish - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1360120180240300Min: 267.69 / Avg: 269.66 / Max: 270.77Min: 294.14 / Avg: 294.38 / Max: 294.56Min: 210.76 / Avg: 218.03 / Max: 220.81Min: 282.85 / Avg: 283.26 / Max: 283.6Min: 344.23 / Avg: 345.78 / Max: 346.561. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1390180270360450SE +/- 0.55, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.56, N = 3SE +/- 0.42, N = 3327.09365.55272.73349.15425.161. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: Blowfish - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1380160240320400Min: 326.3 / Avg: 327.09 / Max: 328.15Min: 365.3 / Avg: 365.55 / Max: 365.68Min: 272.59 / Avg: 272.73 / Max: 272.85Min: 348.3 / Avg: 349.15 / Max: 350.2Min: 424.32 / Avg: 425.16 / Max: 425.591. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: BlowfishAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1390180270360450SE +/- 0.68, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.42, N = 3SE +/- 0.47, N = 3322.92367.94273.04348.43424.741. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: BlowfishAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1380160240320400Min: 321.7 / Avg: 322.92 / Max: 324.03Min: 367.73 / Avg: 367.94 / Max: 368.06Min: 272.87 / Avg: 273.04 / Max: 273.21Min: 347.64 / Avg: 348.43 / Max: 349.09Min: 423.81 / Avg: 424.74 / Max: 425.221. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1390180270360450SE +/- 0.39, N = 3SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.19, N = 3SE +/- 0.15, N = 3335.41398.40420.05323.62272.61MIN: 329.82 / MAX: 368.39MIN: 398 / MAX: 399.03MIN: 418.9 / MAX: 430.09MIN: 322.04 / MAX: 326.05MIN: 272.1 / MAX: 273.51. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O2 -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1370140210280350Min: 334.98 / Avg: 335.41 / Max: 336.19Min: 398.3 / Avg: 398.4 / Max: 398.5Min: 419.85 / Avg: 420.05 / Max: 420.37Min: 323.35 / Avg: 323.62 / Max: 323.97Min: 272.47 / Avg: 272.61 / Max: 272.911. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O2 -rdynamic -ldl

Botan

Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3103.37116.6388.55113.60133.691. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150Min: 103.14 / Avg: 103.37 / Max: 103.61Min: 116.62 / Avg: 116.63 / Max: 116.64Min: 88.52 / Avg: 88.55 / Max: 88.57Min: 113.46 / Avg: 113.6 / Max: 113.69Min: 133.65 / Avg: 133.69 / Max: 133.741. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMIAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100SE +/- 0.25, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 370.9976.1557.9573.1887.481. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMIAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100Min: 70.48 / Avg: 70.99 / Max: 71.28Min: 76.09 / Avg: 76.15 / Max: 76.18Min: 57.95 / Avg: 57.95 / Max: 57.95Min: 73.08 / Avg: 73.18 / Max: 73.31Min: 87.41 / Avg: 87.48 / Max: 87.531. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150SE +/- 0.23, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 2SE +/- 0.01, N = 3SE +/- 0.02, N = 3103.25116.5788.56113.72133.671. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: CAST-256 - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13306090120150Min: 102.82 / Avg: 103.25 / Max: 103.62Min: 116.56 / Avg: 116.57 / Max: 116.58Min: 88.52 / Avg: 88.56 / Max: 88.59Min: 113.71 / Avg: 113.72 / Max: 113.73Min: 133.63 / Avg: 133.67 / Max: 133.691. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100SE +/- 0.16, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 368.3574.2955.9871.1084.061. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.17.3Test: KASUMI - DecryptAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131632486480Min: 68.17 / Avg: 68.35 / Max: 68.68Min: 74.23 / Avg: 74.29 / Max: 74.32Min: 55.97 / Avg: 55.98 / Max: 55.99Min: 71.04 / Avg: 71.1 / Max: 71.18Min: 84.03 / Avg: 84.06 / Max: 84.081. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 94.484.914.805.606.27
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215Min: 4.45 / Avg: 4.48 / Max: 4.5Min: 4.89 / Avg: 4.91 / Max: 4.92Min: 4.77 / Avg: 4.8 / Max: 4.83Min: 5.56 / Avg: 5.6 / Max: 5.65Min: 6.01 / Avg: 6.27 / Max: 7.53

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v3Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100SE +/- 1.56, N = 12SE +/- 0.32, N = 3SE +/- 0.96, N = 12SE +/- 0.95, N = 12SE +/- 0.24, N = 1540.5935.6776.8055.3634.71MIN: 29.94 / MAX: 479.23MIN: 34.52 / MAX: 128.55MIN: 69.85 / MAX: 676.14MIN: 47.56 / MAX: 509.74MIN: 31.09 / MAX: 427.771. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: inception-v3Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131530456075Min: 35.98 / Avg: 40.59 / Max: 57.04Min: 35.14 / Avg: 35.67 / Max: 36.24Min: 71.21 / Avg: 76.8 / Max: 81.76Min: 50 / Avg: 55.36 / Max: 62.27Min: 33.47 / Avg: 34.71 / Max: 36.671. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-50Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131428425670SE +/- 0.34, N = 12SE +/- 0.12, N = 3SE +/- 1.07, N = 12SE +/- 1.18, N = 12SE +/- 0.25, N = 1531.5029.0162.4552.5329.09MIN: 25.12 / MAX: 279.16MIN: 27.94 / MAX: 76.84MIN: 54.15 / MAX: 188.44MIN: 41.27 / MAX: 326.88MIN: 25.79 / MAX: 252.291. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: resnet-v2-50Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131224364860Min: 28.95 / Avg: 31.5 / Max: 32.89Min: 28.76 / Avg: 29.01 / Max: 29.17Min: 55.26 / Avg: 62.45 / Max: 68.96Min: 44.92 / Avg: 52.53 / Max: 56.92Min: 27.82 / Avg: 29.09 / Max: 31.321. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.0Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1348121620SE +/- 0.246, N = 12SE +/- 0.058, N = 3SE +/- 0.162, N = 12SE +/- 0.657, N = 12SE +/- 0.113, N = 158.9768.22617.19414.1368.224MIN: 6.66 / MAX: 318.77MIN: 7.29 / MAX: 23.89MIN: 15.74 / MAX: 54.06MIN: 10.98 / MAX: 78.48MIN: 5.66 / MAX: 54.171. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.1.3Model: SqueezeNetV1.0Azure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1348121620Min: 8.02 / Avg: 8.98 / Max: 10.63Min: 8.12 / Avg: 8.23 / Max: 8.31Min: 16.2 / Avg: 17.19 / Max: 18.03Min: 11.71 / Avg: 14.14 / Max: 19.71Min: 7.01 / Avg: 8.22 / Max: 8.851. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -O2 -rdynamic -pthread -ldl

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1340K80K120K160K200KSE +/- 987.91, N = 3SE +/- 698.77, N = 3SE +/- 1151.23, N = 15SE +/- 1151.94, N = 15SE +/- 2854.14, N = 15175485.073517.395206.274885.466320.4
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1330K60K90K120K150KMin: 173825 / Avg: 175485 / Max: 177243Min: 72138.1 / Avg: 73517.33 / Max: 74402.2Min: 89835.2 / Avg: 95206.24 / Max: 105138Min: 69961.9 / Avg: 74885.4 / Max: 83330.7Min: 48475.2 / Avg: 66320.38 / Max: 78669

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V130.90311.80622.70933.61244.5155SE +/- 0.564166, N = 12SE +/- 0.004555, N = 15SE +/- 0.003421, N = 3SE +/- 0.004967, N = 3SE +/- 0.004912, N = 44.0139200.3980051.1546500.5247370.445223MIN: 2.03MIN: 1.11. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13246810Min: 2.38 / Avg: 4.01 / Max: 9.34Min: 0.37 / Avg: 0.4 / Max: 0.43Min: 1.15 / Avg: 1.15 / Max: 1.16Min: 0.52 / Avg: 0.52 / Max: 0.53Min: 0.43 / Avg: 0.45 / Max: 0.451. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V137001400210028003500SE +/- 133.56, N = 15SE +/- 2.64, N = 3SE +/- 87.86, N = 15SE +/- 6.35, N = 15SE +/- 8.06, N = 152802.87458.203423.15796.82540.19MIN: 1783.32MIN: 2651.39MIN: 726.18MIN: 462.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V136001200180024003000Min: 2209.9 / Avg: 2802.87 / Max: 3882.24Min: 453.88 / Avg: 458.2 / Max: 463Min: 2754.22 / Avg: 3423.15 / Max: 3715.83Min: 756.99 / Avg: 796.82 / Max: 825.98Min: 480.13 / Avg: 540.19 / Max: 601.191. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1311002200330044005500SE +/- 240.85, N = 12SE +/- 4.09, N = 3SE +/- 122.64, N = 15SE +/- 11.10, N = 15SE +/- 14.29, N = 154495.90753.365355.241294.53843.10MIN: 2965.45MIN: 736.05MIN: 4475.57MIN: 1179.19MIN: 711.661. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V139001800270036004500Min: 3646.58 / Avg: 4495.9 / Max: 6299.03Min: 745.42 / Avg: 753.36 / Max: 759.07Min: 4515.02 / Avg: 5355.24 / Max: 5891.59Min: 1239.94 / Avg: 1294.53 / Max: 1401.9Min: 743.86 / Avg: 843.1 / Max: 928.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V130.95261.90522.85783.81044.763SE +/- 0.797911, N = 15SE +/- 0.011574, N = 15SE +/- 0.088179, N = 15SE +/- 0.006544, N = 12SE +/- 0.000278, N = 34.2338200.3521801.5127100.3503470.255501MIN: 1.34MIN: 0.571. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13246810Min: 2.05 / Avg: 4.23 / Max: 12.48Min: 0.29 / Avg: 0.35 / Max: 0.43Min: 1.1 / Avg: 1.51 / Max: 2.11Min: 0.33 / Avg: 0.35 / Max: 0.4Min: 0.26 / Avg: 0.26 / Max: 0.261. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V137001400210028003500SE +/- 215.78, N = 15SE +/- 1.52, N = 3SE +/- 110.58, N = 12SE +/- 5.73, N = 15SE +/- 8.80, N = 153198.07459.583373.88791.46561.77MIN: 1805.4MIN: 2418.62MIN: 718.74MIN: 471.831. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V136001200180024003000Min: 2374.53 / Avg: 3198.07 / Max: 5398.04Min: 457.92 / Avg: 459.58 / Max: 462.62Min: 2468.9 / Avg: 3373.88 / Max: 3730.18Min: 746 / Avg: 791.46 / Max: 823.74Min: 490.11 / Avg: 561.77 / Max: 612.811. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1312002400360048006000SE +/- 213.65, N = 12SE +/- 3.40, N = 3SE +/- 103.35, N = 12SE +/- 13.52, N = 15SE +/- 102.39, N = 144449.57746.465539.481287.03962.34MIN: 2983.77MIN: 4475.65MIN: 1149.25MIN: 722.131. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1310002000300040005000Min: 3763.3 / Avg: 4449.57 / Max: 6176.99Min: 740.76 / Avg: 746.46 / Max: 752.53Min: 4586.46 / Avg: 5539.48 / Max: 5795.86Min: 1207.12 / Avg: 1287.03 / Max: 1368.08Min: 741.04 / Avg: 962.34 / Max: 2245.61. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V137001400210028003500SE +/- 171.94, N = 12SE +/- 2.05, N = 3SE +/- 113.65, N = 12SE +/- 8.13, N = 3SE +/- 8.62, N = 153117.45462.863344.14778.31530.90MIN: 1801.23MIN: 2662.07MIN: 738.78MIN: 458.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V136001200180024003000Min: 2151.94 / Avg: 3117.45 / Max: 4105.12Min: 458.76 / Avg: 462.86 / Max: 465.01Min: 2696.37 / Avg: 3344.14 / Max: 3791.39Min: 765.12 / Avg: 778.31 / Max: 793.12Min: 476.45 / Avg: 530.9 / Max: 573.731. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1312002400360048006000SE +/- 239.22, N = 15SE +/- 4.60, N = 3SE +/- 83.42, N = 13SE +/- 16.54, N = 15SE +/- 25.25, N = 124793.75744.365524.501314.00875.17MIN: 2947.39MIN: 4658.38MIN: 1140.59MIN: 727.381. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1310002000300040005000Min: 3615.97 / Avg: 4793.75 / Max: 7306.78Min: 737.54 / Avg: 744.35 / Max: 753.11Min: 4695.81 / Avg: 5524.5 / Max: 5809.29Min: 1182.01 / Avg: 1314 / Max: 1419.56Min: 755.33 / Avg: 875.17 / Max: 1009.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131.34712.69424.04135.38846.7355SE +/- 1.017585, N = 15SE +/- 0.006150, N = 15SE +/- 0.005596, N = 3SE +/- 0.002363, N = 3SE +/- 0.002442, N = 35.9871200.6686412.7362100.7321300.455682MIN: 3.17MIN: 2.71. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13246810Min: 3.56 / Avg: 5.99 / Max: 15.51Min: 0.65 / Avg: 0.67 / Max: 0.71Min: 2.73 / Avg: 2.74 / Max: 2.75Min: 0.73 / Avg: 0.73 / Max: 0.74Min: 0.45 / Avg: 0.46 / Max: 0.461. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13246810SE +/- 1.264069, N = 15SE +/- 0.003751, N = 3SE +/- 0.045752, N = 12SE +/- 0.030825, N = 15SE +/- 0.004961, N = 36.9247100.5514672.4056101.0319420.406686MIN: 2.2MIN: 1.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215Min: 2.61 / Avg: 6.92 / Max: 14.7Min: 0.55 / Avg: 0.55 / Max: 0.56Min: 2.17 / Avg: 2.41 / Max: 2.78Min: 0.92 / Avg: 1.03 / Max: 1.21Min: 0.4 / Avg: 0.41 / Max: 0.411. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13246810SE +/- 2.687031, N = 12SE +/- 0.017521, N = 12SE +/- 0.040927, N = 15SE +/- 0.003995, N = 7SE +/- 0.009558, N = 127.3286200.4743111.7635500.4410120.383855MIN: 1.37MIN: 0.891. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215Min: 1.87 / Avg: 7.33 / Max: 25.87Min: 0.37 / Avg: 0.47 / Max: 0.57Min: 1.48 / Avg: 1.76 / Max: 2Min: 0.43 / Avg: 0.44 / Max: 0.46Min: 0.35 / Avg: 0.38 / Max: 0.471. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215SE +/- 1.08345, N = 15SE +/- 0.00454, N = 3SE +/- 0.43651, N = 15SE +/- 0.28898, N = 15SE +/- 0.02162, N = 38.700223.2816010.222639.683213.21204MIN: 5.33MIN: 3.2MIN: 4.1MIN: 5.56MIN: 2.581. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.1.2Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215Min: 6.29 / Avg: 8.7 / Max: 21.7Min: 3.28 / Avg: 3.28 / Max: 3.29Min: 9.15 / Avg: 10.22 / Max: 14.07Min: 9.08 / Avg: 9.68 / Max: 12.42Min: 3.17 / Avg: 3.21 / Max: 3.251. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -O2 -pie -lpthread -ldl

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13120240360480600SE +/- 1.74, N = 6SE +/- 2.25, N = 3SE +/- 2.68, N = 15SE +/- 21.86, N = 15SE +/- 7.76, N = 3172.16480.79141.93379.91548.331. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13100200300400500Min: 166.34 / Avg: 172.16 / Max: 177.36Min: 476.57 / Avg: 480.79 / Max: 484.26Min: 130.01 / Avg: 141.93 / Max: 170.99Min: 151.29 / Avg: 379.91 / Max: 460.12Min: 532.86 / Avg: 548.33 / Max: 557.11. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1380160240320400SE +/- 1.35, N = 3SE +/- 1.61, N = 3SE +/- 1.15, N = 3SE +/- 6.53, N = 12SE +/- 4.22, N = 395.14256.28119.20166.90378.011. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1370140210280350Min: 92.62 / Avg: 95.14 / Max: 97.23Min: 253.06 / Avg: 256.28 / Max: 257.95Min: 117.12 / Avg: 119.2 / Max: 121.09Min: 129.12 / Avg: 166.9 / Max: 202.77Min: 369.69 / Avg: 378.01 / Max: 383.391. (CC) gcc options: -fPIE -fPIC -O2 -O3 -pie -rdynamic -lpthread -lrt

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V133691215SE +/- 0.022, N = 3SE +/- 0.023, N = 3SE +/- 0.034, N = 11SE +/- 0.218, N = 15SE +/- 0.031, N = 33.4907.6214.6699.51212.2751. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1348121620Min: 3.45 / Avg: 3.49 / Max: 3.51Min: 7.59 / Avg: 7.62 / Max: 7.67Min: 4.52 / Avg: 4.67 / Max: 4.94Min: 7.69 / Avg: 9.51 / Max: 10.39Min: 12.22 / Avg: 12.28 / Max: 12.321. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

Zstd Compression

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

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100SE +/- 0.57, N = 3SE +/- 1.01, N = 15SE +/- 0.83, N = 15SE +/- 1.18, N = 15SE +/- 0.71, N = 1539.876.348.569.578.21. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.9Compression Level: 19 - Compression SpeedAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V131530456075Min: 38.7 / Avg: 39.83 / Max: 40.5Min: 68 / Avg: 76.3 / Max: 81.7Min: 41.8 / Avg: 48.53 / Max: 53.4Min: 61.4 / Avg: 69.51 / Max: 77.6Min: 72.9 / Avg: 78.15 / Max: 83.11. (CC) gcc options: -O3 -pthread -lz -llzma

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 AtomsAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V130.38630.77261.15891.54521.9315SE +/- 0.05413, N = 15SE +/- 0.00126, N = 3SE +/- 0.00507, N = 3SE +/- 0.00059, N = 3SE +/- 0.00027, N = 31.717100.525690.709470.300560.27566
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V13246810Min: 1.5 / Avg: 1.72 / Max: 2.04Min: 0.52 / Avg: 0.53 / Max: 0.53Min: 0.7 / Avg: 0.71 / Max: 0.72Min: 0.3 / Avg: 0.3 / Max: 0.3Min: 0.28 / Avg: 0.28 / Max: 0.28

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm.in input file (Problem 5). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100SE +/- 1.93, N = 14SE +/- 0.26, N = 3SE +/- 0.11, N = 3SE +/- 0.45, N = 12SE +/- 0.83, N = 15111.1420.1925.0023.7816.661. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsAzure H - Xeon E5-2667 v3Azure HC - Xeon 8168Azure HBv1 - EPYC 7551Azure HBv2 - EPYC 7V12Azure HBv3 - EPYC 7V1320406080100Min: 106.93 / Avg: 111.14 / Max: 135.61Min: 19.68 / Avg: 20.19 / Max: 20.46Min: 24.85 / Avg: 25 / Max: 25.21Min: 21.27 / Avg: 23.78 / Max: 26.48Min: 13.14 / Avg: 16.66 / Max: 24.431. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

63 Results Shown

Rodinia
GROMACS
NAS Parallel Benchmarks
LULESH
SVT-HEVC
Zstd Compression
Timed Node.js Compilation
SVT-VP9
Xcompact3d Incompact3d
High Performance Conjugate Gradient
Timed LLVM Compilation
SVT-AV1
Timed Linux Kernel Compilation
PlaidML:
  No - Inference - VGG19 - CPU
  No - Inference - VGG16 - CPU
Botan:
  ChaCha20Poly1305
  ChaCha20Poly1305 - Decrypt
SVT-AV1
Pennant:
  leblancbig
  sedovbig
Zstd Compression:
  19 - Decompression Speed
  19, Long Mode - Decompression Speed
Botan:
  AES-256
  AES-256 - Decrypt
Zstd Compression
FinanceBench
QuantLib
FinanceBench
Rodinia
Zstd Compression
GNU GMP GMPbench
Botan:
  Twofish
  Twofish - Decrypt
  Blowfish - Decrypt
  Blowfish
TNN
Botan:
  CAST-256
  KASUMI
  CAST-256 - Decrypt
  KASUMI - Decrypt
PlaidML
Mobile Neural Network:
  inception-v3
  resnet-v2-50
  SqueezeNetV1.0
TensorFlow Lite
oneDNN:
  Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
  Recurrent Neural Network Inference - u8s8f32 - CPU
  Recurrent Neural Network Training - u8s8f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Deconvolution Batch shapes_3d - u8s8f32 - CPU
  Deconvolution Batch shapes_1d - u8s8f32 - CPU
  IP Shapes 3D - u8s8f32 - CPU
  IP Shapes 3D - f32 - CPU
SVT-HEVC:
  10 - Bosphorus 1080p
  7 - Bosphorus 1080p
SVT-AV1
Zstd Compression
NAMD
CloverLeaf