Extra EPYC Rome Benchmarks

2 x Intel Xeon Platinum 8280 testing with a GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS) and llvmpipe 377GB on Ubuntu 19.04 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 1908130-AS-EXTRAEPYC84
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:

Audio Encoding 3 Tests
AV1 2 Tests
Bioinformatics 2 Tests
C++ Boost Tests 2 Tests
Chess Test Suite 4 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 25 Tests
Compression Tests 4 Tests
CPU Massive 64 Tests
Creator Workloads 22 Tests
Cryptography 5 Tests
Database Test Suite 3 Tests
Encoding 10 Tests
Fortran Tests 3 Tests
HPC - High Performance Computing 12 Tests
Imaging 4 Tests
Java 5 Tests
Common Kernel Benchmarks 7 Tests
Memory Test Suite 4 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 3 Tests
Multi-Core 34 Tests
NVIDIA GPU Compute 4 Tests
OpenCL 3 Tests
OpenMPI Tests 5 Tests
Programmer / Developer System Benchmarks 7 Tests
Python 2 Tests
Raytracing 2 Tests
Renderers 7 Tests
Scientific Computing 7 Tests
Server 9 Tests
Server CPU Tests 42 Tests
Single-Threaded 16 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 5 Tests

Statistics

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

Graph Settings

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

Additional Graphs

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
2 x EPYC 7502
July 25 2019
  2 Days, 7 Hours, 4 Minutes
2 x EPYC 7742
July 28 2019
  4 Hours, 46 Minutes
2 x Xeon Platinum 8280
August 11 2019
  1 Day, 21 Hours, 18 Minutes
Invert Hiding All Results Option
  1 Day, 11 Hours, 3 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):

2 x EPYC 7502

Processor: 2 x AMD EPYC 7502 32-Core @ 2.50GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 5 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.2 (LLVM 8.0 128 bits), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1)
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

2 x EPYC 7742

Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 5 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.3.0-rc1-power (x86_64) 20190728, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

2 x Xeon Platinum 8280

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 386048MB, Disk: 280GB INTEL SSDPED1D280GA + 32GB Flash Disk, Graphics: llvmpipe 377GB, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.2 (LLVM 8.0 256 bits), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave
Java Notes: OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04)
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling

Extra EPYC Rome BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82802 x AMD EPYC 7502 32-Core @ 2.50GHz (64 Cores / 128 Threads)AMD DAYTONA_X (RDY1001C BIOS)AMD Device 1480516096MB280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 5 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFDllvmpipe 504GBVE2282 x Mellanox MT27710Ubuntu 19.045.2.0-050200rc7-generic (x86_64) 20190630GNOME Shell 3.32.1X Server 1.20.4modesetting 1.20.43.3 Mesa 19.0.2 (LLVM 8.0 128 bits)GCC 8.3.0ext41920x10802 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads)ASPEED5.3.0-rc1-power (x86_64) 201907282 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers386048MB280GB INTEL SSDPED1D280GA + 32GB Flash Diskllvmpipe 377GB2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE5.2.0-050200rc7-generic (x86_64) 20190630GNOME Shell 3.32.23.3 Mesa 19.0.2 (LLVM 8.0 256 bits)OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Disk Details- NONE / errors=remount-ro,relatime,rwProcessor Details- 2 x EPYC 7502: Scaling Governor: acpi-cpufreq ondemand- 2 x EPYC 7742: Scaling Governor: acpi-cpufreq ondemand- 2 x Xeon Platinum 8280: Scaling Governor: intel_pstate powersaveJava Details- 2 x EPYC 7502: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1)- 2 x EPYC 7742: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1)- 2 x Xeon Platinum 8280: OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04)Python Details- Python 2.7.16 + Python 3.7.3Security Details- 2 x EPYC 7502: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling - 2 x EPYC 7742: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling - 2 x Xeon Platinum 8280: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling

2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 8280Result OverviewPhoronix Test Suite100%148%196%244%292%CP2K Molecular DynamicsHigh Performance Conjugate GradientMBWBLAKE2CLOMPNAMDBlogBenchBork File EncrypterTimed MAFFT AlignmentTinymembenchRAMspeed SMPParboilRodiniaStreamDaCapo BenchmarkGNU GMP GMPbenchJava SciMarklzbenchSockperfFFTWRenaissance

Extra EPYC Rome Benchmarksmkl-dnn: Deconvolution Batch deconv_1d - f32mkl-dnn: Convolution Batch conv_alexnet - u8s8u8s32mkl-dnn: Convolution Batch conv_alexnet - u8s8f32s32parboil: OpenMP MRI Griddingmkl-dnn: Deconvolution Batch deconv_all - u8s8u8s32mkl-dnn: Deconvolution Batch deconv_1d - u8s8u8s32mkl-dnn: IP Batch All - u8s8f32s32mkl-dnn: IP Batch All - u8s8u8s32mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32s32mkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8u8s32mkl-dnn: Deconvolution Batch deconv_3d - f32mbw: Memory Copy - 8192 MiBmbw: Memory Copy - 1024 MiBmbw: Memory Copy - 4096 MiBmbw: Memory Copy - 512 MiBmkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8f32s32cp2k: Fayalite-FIST Datahimeno: Poisson Pressure Solvermcperf: Replacemcperf: Prependmcperf: Getmcperf: Appendmkl-dnn: IP Batch 1D - u8s8f32s32mkl-dnn: IP Batch 1D - u8s8u8s32mkl-dnn: Convolution Batch conv_all - u8s8u8s32mkl-dnn: Convolution Batch conv_all - u8s8f32s32hpcc: G-Fftehpcc: G-Ffteblake2: mbw: Memory Copy, Fixed Block Size - 512 MiBstress-ng: System V Message Passingmbw: Memory Copy, Fixed Block Size - 1024 MiBmcperf: Addmcperf: Setmbw: Memory Copy, Fixed Block Size - 128 MiBmbw: Memory Copy - 128 MiBmbw: Memory Copy, Fixed Block Size - 4096 MiBmbw: Memory Copy, Fixed Block Size - 8192 MiBapache-siege: 1mysqlslap: 4blogbench: Readramspeed: Add - Floating Pointmysqlslap: 16mkl-dnn: Convolution Batch conv_alexnet - f32mysqlslap: 32hpcc: Rand Ring Bandwidthosbench: Create Threadsramspeed: Triad - Floating Pointmysqlslap: 8mkl-dnn: Convolution Batch conv_all - f32mysqlslap: 256dav1d: Summer Nature 1080pparboil: OpenMP CUTCPmkl-dnn: Convolution Batch conv_googlenet_v3 - f32stress-ng: Tsearchstress-ng: Forkinghpcc: Max Ping Pong Bandwidthmysqlslap: 128dacapobench: Tradebeansstress-ng: Socket Activityhpcc: Rand Ring Latencyramspeed: Scale - Floating Pointsvt-av1: 1080p 8-bit YUV To AV1 Video Encodemysqlslap: 64appleseed: Material Testerfftw: Float + SSE - 2D FFT Size 512vpxenc: vpxenc VP9 1080p Video Encoderamspeed: Average - Floating Pointbork: File Encryption Timefftw: Float + SSE - 2D FFT Size 1024fftw: Float + SSE - 1D FFT Size 1024stress-ng: Semaphoresfftw: Float + SSE - 1D FFT Size 512ramspeed: Add - Integertinymembench: Standard Memsetmkl-dnn: Convolution Batch conv_3d - u8s8u8s32ttsiod-renderer: Phong Rendering With Soft-Shadow Mappingmkl-dnn: Convolution Batch conv_3d - u8s8f32s32osbench: Launch Programsnpb: FT.Bfftw: Float + SSE - 1D FFT Size 2048npb: FT.Ablogbench: Writefftw: Float + SSE - 1D FFT Size 4096fftw: Float + SSE - 2D FFT Size 256osbench: Create Processesdav1d: Summer Nature 4Kjava-scimark2: Monte Carlosvt-vp9: 1080p 8-bit YUV To VP9 Video Encodemkl-dnn: Deconvolution Batch deconv_3d - u8s8f32s32numpy: stress-ng: Cryptomkl-dnn: Deconvolution Batch deconv_3d - u8s8u8s32ramspeed: Triad - Integerm-queens: Time To Solveramspeed: Average - Integersockperf: Latency Ping Pongx265: H.265 1080p Video Encodingramspeed: Copy - Integerramspeed: Scale - Integerdacapobench: Tradesoapc-ray: Total Time - 4K, 16 Rays Per Pixeltinymembench: Standard Memcpysvt-hevc: 1080p 8-bit YUV To HEVC Video Encodejohn-the-ripper: Blowfishphpbench: PHP Benchmark Suiteapache-siege: 10php: Zend micro_benchfftw: Float + SSE - 2D FFT Size 32stress-ng: Hsearchapache-siege: 50lzbench: XZ 0 - Compressionindigobench: Bedroompts-self-test: Info Commandindigobench: Supercardacapobench: H2renaissance: In-Memory Database Shootoutfftw: Float + SSE - 2D FFT Size 2048cython-bench: apache-siege: 100rodinia: OpenMP CFD Solvercompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19x264: H.264 Video Encodingminion: Quasigrouppts-self-test: Merge Resultsdcraw: RAW To PPM Image Conversionmkl-dnn: IP Batch All - f32darktable: Boat - CPU-onlyfftw: Float + SSE - 2D FFT Size 128botan: Blowfish - Encryptmkl-dnn: IP Batch 1D - f32tscp: AI Chess Performancebotan: AES-256 - Decryptfftw: Float + SSE - 1D FFT Size 32lzbench: Libdeflate 1 - Decompressionbotan: Blowfish - Decryptphp: Zend benchbotan: AES-256 - Encryptcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9build-gcc: Time To Compilespec-jbb2015: SPECjbb2015-Composite critical-jOPSstream: Scalestress-ng: Glibc Qsort Data Sortingdacapobench: Jythonredis: SADDfftw: Stock - 2D FFT Size 2048lzbench: Brotli 0 - Decompressionpts-self-test: Total Timeramspeed: Copy - Floating Pointbotan: Twofish - Decryptapache-siege: 200blender: Classroom - CPU-Onlyjava-scimark2: Fast Fourier Transformpts-self-test: Render Testbotan: Twofish - Encrypthpcc: G-HPLbotan: KASUMI - Decrypthpcc: G-Rand Accessapache-siege: 250botan: KASUMI - Encryptblender: Pabellon Barcelona - CPU-Onlystress-ng: Memory Copyingmencoder: AVI To LAVCbotan: CAST-256 - Decryptbotan: CAST-256 - Encryptspec-jbb2015: SPECjbb2015-Composite max-jOPSgmpbench: Total Timedarktable: Masskrug - CPU-onlyappleseed: Disney Materialhpcc: EP-DGEMMfftw: Stock - 2D FFT Size 4096primesieve: 1e12 Prime Number Generationpovray: Trace Timelzbench: Libdeflate 1 - Compressionbuild-llvm: Time To Compilejava-scimark2: Dense LU Matrix Factorizationblender: Pabellon Barcelona - CPU-Onlytjbench: Decompression Throughputencode-ogg: WAV To Oggappleseed: Emilycoremark: CoreMark Size 666 - Iterations Per Secondjava-scimark2: Compositefftw: Float + SSE - 2D FFT Size 4096fftw: Stock - 1D FFT Size 64encode-mp3: WAV To MP3osbench: Create Filesfftw: Stock - 1D FFT Size 512osbench: Memory Allocationsctx-clock: Context Switch Timeblender: Classroom - CPU-Onlyfftw: Stock - 2D FFT Size 128fftw: Float + SSE - 2D FFT Size 64compress-7zip: Compress Speed Testblender: Fishy Cat - CPU-Onlystress-ng: Glibc C String Functionslzbench: XZ 0 - Decompressionblender: Fishy Cat - CPU-Onlygimp: rotatenpb: EP.Cbuild-imagemagick: Time To Compilegimp: unsharp-maskfftw: Stock - 1D FFT Size 4096blender: BMW27 - CPU-Onlypgbench: Buffer Test - Normal Load - Read Writegimp: auto-levelsstress-ng: Vector Mathfftw: Stock - 1D FFT Size 2048stockfish: Total Timepgbench: Buffer Test - Single Thread - Read Onlyhpcc: EP-STREAM Triadgimp: resizetesseract-ocr: Time To OCR 7 Imagesstress-ng: Lsearchpgbench: Buffer Test - Normal Load - Read Onlystress-ng: CPU Stressfftw: Stock - 1D FFT Size 1024lzbench: Zstd 1 - Compressionstress-ng: Bsearchrenaissance: Scala Dottyfftw: Stock - 2D FFT Size 512fftw: Stock - 2D FFT Size 256encode-flac: WAV To FLACjava-scimark2: Jacobi Successive Over-Relaxationv-ray: CPUblender: BMW27 - CPU-Onlynpb: LU.Copenssl: RSA 4096-bit Performancenpb: SP.Apts-self-test: List Suitesjava-scimark2: Sparse Matrix Multiplyfftw: Stock - 2D FFT Size 1024fftw: Stock - 1D FFT Size 128lzbench: Zstd 1 - Decompressionfftw: Float + SSE - 1D FFT Size 128fftw: Stock - 2D FFT Size 64minion: Solitairey-cruncher: Calculating 500M Pi Digitslzbench: Brotli 0 - Compressionblender: Barbershop - CPU-Onlyfftw: Stock - 2D FFT Size 32stress-ng: Matrix Mathfftw: Stock - 1D FFT Size 256blender: Barbershop - CPU-Onlypgbench: Buffer Test - Single Thread - Read Writebuild-php: Time To Compileminion: Gracefulasmfish: 1024 Hash Memory, 26 Depthnpb: BT.Apts-self-test: Peak Memory Usageffte: N=256, 1D Complex FFT Routinesunflow: Global Illumination + Image Synthesismcperf: Deletestress-ng: Context Switchingredis: SETredis: GETredis: LPUSHredis: LPOPdarktable: Server Room - CPU-onlydarktable: Server Rack - CPU-onlybuild-linux-kernel: Time To Compilemkl-dnn: Deconvolution Batch deconv_all - f32mkl-dnn: Convolution Batch conv_3d - f32renaissance: Akka Unbalanced Cobwebbed Treerenaissance: Apache Spark PageRankrenaissance: Savina Reactors.IOrenaissance: Apache Spark Bayesrenaissance: Apache Spark ALSmafft: Multiple Sequence Alignmentfftw: Float + SSE - 1D FFT Size 256fftw: Float + SSE - 1D FFT Size 64fftw: Stock - 1D FFT Size 32namd: ATPase Simulation - 327,506 Atomsclomp: Static OMP Speeduphpcg: rodinia: OpenMP Streamclusterrodinia: OpenMP LavaMDparboil: OpenMP Stencilparboil: OpenMP LBMhpcc: G-Ptransnpb: LU.Asockperf: Latency Under Loadsockperf: Throughputstream: Addstream: Triadstream: Copy2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82808.11947.22941.69120.9215306.87881.33778.49772.47795.681752.473.8615674.9415711.4815471.5215670.901764.58580.451004.4628323.3328279.2053649.7134849.6768.2868.4720800.0720777.7333.3048333.304837.469125.6212216044.869093.1933157.2333580.368983.598985.679017.439041.734559.867634127205648546.84371380.9317571.3838533.7932247.206397621.172705.691.0434.661752.3943020.8110781.240342741923811.441.7797640026.1394.99835284.1933879145.2944274.7010.7733251430781398972.493772247552.0415239.772437.57693.212447.4378.173660.37449153332.6043807416183358663.3113.241333.85197.261377.00721657714305.841507.2340110.2912.1042022.604.8543.4642739.1238464.73560110.909148.30340.9410936349491019907.862.6634572388395.9821691.56284.783.087.72691113682.672610928.6826655.068.8711.20148.94137.894.8451.4381.933.3034549231.139.4710360784639.8211848841228.060.544585.3826.97746.4460218155497.48931.2754661800546.075815.06441253.0530275.11299.1728568.9780.601623.5969.67298.82169.9226775.240.2023330036.7077.84102.359822.8120.20120.28120.1710664545194.2459.8022.389705115.504.2910.3219096.435269.70100.13168.836.81172.662101299.252388.93170048081.5033.1715.237052.3396.59150122.646787.603589725549270.164908942.298766.5216.752283.0321.3930.606709.2747.3221936.2424.62130504.956858.4013522371020388.112.8020711.6734.90708.05858391.7619072.647128.9735433172.627326.306632.836614.6710.091506.026229745.2033940.8114388.43396.260.742211.496098.836766.47932209607299.9382.078.89383236.538823.93375524.897126.70220.692688.9049.1452.78136257996834.43502.557639.450.7440802.7362075360.401463245.891897043.391375852.722170359.023.030.1119.744229.493.6730303.9424726.3028404.303594.6238777.963.4227950164478740.570.413490.370.4613.576.115.6425.001.3688231119.4622.42484363164104.50166118.74150788.38182.8315555.6715602.4415436.0515464.17611.296.609188.179153.109053.089065.609031.529050.79116406748530.1446521.150.80774336195.503417840959.6310.7333895438693892248252.9316030.50453373822643038342841355.5243023.1342271.585.3041104.7137700.409130.6035028288226266619.103500311985867177028.6652645992.5044635526.371621.844588.705213.901915364.162423.28178658203.207123.536947.8037011886814.277006.207207.203607276.016716.706744.301528.572246.316146.206899.00961210597399.833838982.477216.9024411.7931114.634126.1837538.963.4127860160328867.970.265890.230.3510.434.334.0235.9722.16454195194680.20200966.20185817.540.9514.2318.95513.313711.530.2320.4820.420.235.771.114747.424774.794751.934819.266.231698.722794.4071185.2370627.73111929.9070477.973.553.641722.341756.2716.9060316.906033.874910.016551713.524916.2661510.2762020.774917.774975.465053.225135.382606.4813278199523928399.71634748.5729050.8373020.5128432.4710422382.234389.201.2921.531090.9468990.1617273.8195441178037540.181.1335625821.8861.531286184.902228994.8229059.507.1022351647322098938.525598332779.2310920.173576.181010.283538.2354.512556.20639082378.8053516582222485345.9218.25984.07271.631890.00526221610503.092041.2531863.5516.3031645.323.9832.7332285.2529096.35740414.406933.10260.318357864673826011.632.0627128301307.7627914.68366.142.409.88877317337.652119822.9733241.867.319.01120.04111.213.9141.77100.804.0528613282.4311.5612574893827.96143171016274.680.453822.6622.50891.6650770149490.08787.1146292122727.275090.45519215.4232109.91350.8333431.8694.291391.5759.80347.48146.4503387.030.1754034607.8089.63117.4111263.4817.69137.30136.52939955098.404.7767.2425.173534640.204.8211.57213107.934793.41112.00188.496.12155.241890648.692181.97160997403.9029.9713.777792.6787.57136135.027470.233364823262676.824483652.609572.5418.252486.0519.6728.187273.7751.1523702.9622.79120956.957392.0012594750519015.963.0026912.4832.79665.35912805.5217955.137554.5337535115.696929.506354.606386.179.561585.246547647.4532373.0213753.10379.980.712155.576339.637023.80967203437180.6784.349.12391240.948898.43380876.397199.60223.422656.2748.5953.28137371669834.30502.550.86113028.6326550213.141752859.752299348.831656464.102475213.881.920.1021.451055.123.3024372.7223691.4526058.053282.5549161.185.1636704169847178.600.359230.430.9411.796.962.6022.4315.0181730471.2035.39448019156319.26154124.58168489.97OpenBenchmarking.org

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: f322 x Xeon Platinum 82802 x EPYC 7502246810SE +/- 0.01, N = 3SE +/- 0.08, N = 30.958.11MIN: 0.91MIN: 6.891. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: f322 x Xeon Platinum 82802 x EPYC 75023691215Min: 0.94 / Avg: 0.95 / Max: 0.96Min: 8 / Avg: 8.11 / Max: 8.271. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75022004006008001000SE +/- 0.03, N = 3SE +/- 0.75, N = 314.23947.22MIN: 931.031. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 7502170340510680850Min: 14.17 / Avg: 14.23 / Max: 14.27Min: 946.15 / Avg: 947.22 / Max: 948.671. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 75022004006008001000SE +/- 0.05, N = 3SE +/- 2.17, N = 318.95941.69MIN: 927.131. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 7502170340510680850Min: 18.86 / Avg: 18.95 / Max: 19.01Min: 938.08 / Avg: 941.69 / Max: 945.571. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Parboil

The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI Gridding2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 8280110220330440550SE +/- 0.54, N = 3SE +/- 2.09, N = 6SE +/- 7.08, N = 9120.92182.83513.311. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI Gridding2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 828090180270360450Min: 119.84 / Avg: 120.92 / Max: 121.54Min: 175.13 / Avg: 182.83 / Max: 188Min: 476.6 / Avg: 513.31 / Max: 537.381. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75023K6K9K12K15KSE +/- 45.90, N = 9SE +/- 81.72, N = 33711.5315306.87MIN: 3606.98MIN: 13751.81. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75023K6K9K12K15KMin: 3647.94 / Avg: 3711.53 / Max: 4077.36Min: 15204.5 / Avg: 15306.87 / Max: 15468.41. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75022004006008001000SE +/- 0.00, N = 3SE +/- 1.86, N = 30.23881.33MIN: 872.841. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 7502150300450600750Min: 0.23 / Avg: 0.23 / Max: 0.23Min: 877.74 / Avg: 881.33 / Max: 883.951. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 75022004006008001000SE +/- 0.27, N = 3SE +/- 5.40, N = 320.48778.49MIN: 664.031. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 7502140280420560700Min: 19.94 / Avg: 20.48 / Max: 20.8Min: 769.64 / Avg: 778.49 / Max: 788.281. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 7502170340510680850SE +/- 0.05, N = 3SE +/- 13.00, N = 320.42772.47MIN: 607.021. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 7502140280420560700Min: 20.34 / Avg: 20.42 / Max: 20.51Min: 755.59 / Avg: 772.47 / Max: 798.041. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 75022004006008001000SE +/- 0.00, N = 4SE +/- 0.82, N = 30.23795.68MIN: 791.731. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 7502140280420560700Min: 0.23 / Avg: 0.23 / Max: 0.23Min: 794.5 / Avg: 795.68 / Max: 797.251. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 7502400800120016002000SE +/- 0.01, N = 3SE +/- 14.43, N = 35.771752.47MIN: 1493.251. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 750230060090012001500Min: 5.75 / Avg: 5.77 / Max: 5.79Min: 1724.56 / Avg: 1752.47 / Max: 1772.771. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: f322 x Xeon Platinum 82802 x EPYC 75020.86851.7372.60553.4744.3425SE +/- 0.00, N = 3SE +/- 0.05, N = 31.113.86MIN: 1.07MIN: 2.261. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: f322 x Xeon Platinum 82802 x EPYC 7502246810Min: 1.11 / Avg: 1.11 / Max: 1.11Min: 3.81 / Avg: 3.86 / Max: 3.961. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 8192 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KSE +/- 51.91, N = 3SE +/- 38.55, N = 3SE +/- 0.90, N = 315674.9415555.674747.421. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 8192 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KMin: 15618.28 / Avg: 15674.94 / Max: 15778.61Min: 15484.54 / Avg: 15555.67 / Max: 15617Min: 4745.62 / Avg: 4747.42 / Max: 4748.321. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 1024 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KSE +/- 66.85, N = 3SE +/- 35.67, N = 3SE +/- 1.38, N = 315711.4815602.444774.791. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 1024 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KMin: 15577.8 / Avg: 15711.48 / Max: 15780.21Min: 15532.77 / Avg: 15602.44 / Max: 15650.58Min: 4773.38 / Avg: 4774.79 / Max: 4777.551. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KSE +/- 23.34, N = 3SE +/- 51.75, N = 3SE +/- 2.51, N = 315471.5215436.054751.931. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KMin: 15427.96 / Avg: 15471.52 / Max: 15507.82Min: 15332.84 / Avg: 15436.05 / Max: 15494.46Min: 4747.05 / Avg: 4751.93 / Max: 4755.411. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 512 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KSE +/- 59.01, N = 3SE +/- 48.20, N = 3SE +/- 2.75, N = 315670.9015464.174819.261. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 512 MiB2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KMin: 15555.46 / Avg: 15670.9 / Max: 15749.9Min: 15367.77 / Avg: 15464.17 / Max: 15512.4Min: 4816.12 / Avg: 4819.26 / Max: 4824.731. (CC) gcc options: -O3 -march=native

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 7502400800120016002000SE +/- 0.00, N = 3SE +/- 14.62, N = 36.231764.58MIN: 1518.911. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 750230060090012001500Min: 6.23 / Avg: 6.23 / Max: 6.24Min: 1742.56 / Avg: 1764.58 / Max: 1792.241. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. This test profile currently makes use of the OpenMP implementation and using the Fayalite-FIST molecular dynamics run and measures the total time to complete. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST Data2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 8280400800120016002000580.45611.291698.72

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver2 x Xeon Platinum 82802 x EPYC 75026001200180024003000SE +/- 4.24, N = 3SE +/- 4.17, N = 32794.401004.461. (CC) gcc options: -O3 -mavx2
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver2 x Xeon Platinum 82802 x EPYC 75025001000150020002500Min: 2785.95 / Avg: 2794.4 / Max: 2799.03Min: 998.9 / Avg: 1004.46 / Max: 1012.631. (CC) gcc options: -O3 -mavx2

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Replace2 x Xeon Platinum 82802 x EPYC 750215K30K45K60K75KSE +/- 251.51, N = 3SE +/- 86.93, N = 371185.2328323.331. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Replace2 x Xeon Platinum 82802 x EPYC 750212K24K36K48K60KMin: 70769.2 / Avg: 71185.23 / Max: 71638.1Min: 28154.7 / Avg: 28323.33 / Max: 28444.31. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Prepend2 x Xeon Platinum 82802 x EPYC 750215K30K45K60K75KSE +/- 200.54, N = 3SE +/- 158.97, N = 370627.7328279.201. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Prepend2 x Xeon Platinum 82802 x EPYC 750212K24K36K48K60KMin: 70229.5 / Avg: 70627.73 / Max: 70868.1Min: 27967.6 / Avg: 28279.2 / Max: 28489.71. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Get2 x Xeon Platinum 82802 x EPYC 750220K40K60K80K100KSE +/- 712.60, N = 3SE +/- 464.12, N = 15111929.9053649.711. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Get2 x Xeon Platinum 82802 x EPYC 750220K40K60K80K100KMin: 111019.9 / Avg: 111929.9 / Max: 113334.8Min: 51261.4 / Avg: 53649.71 / Max: 56795.81. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Append2 x Xeon Platinum 82802 x EPYC 750215K30K45K60K75KSE +/- 150.54, N = 3SE +/- 247.66, N = 370477.9734849.671. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Append2 x Xeon Platinum 82802 x EPYC 750212K24K36K48K60KMin: 70268.8 / Avg: 70477.97 / Max: 70770.1Min: 34459.3 / Avg: 34849.67 / Max: 35308.91. (CC) gcc options: -O2 -lm -rdynamic

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 75021530456075SE +/- 0.04, N = 8SE +/- 1.00, N = 43.5568.28MIN: 481. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 75021326395265Min: 3.32 / Avg: 3.55 / Max: 3.65Min: 65.59 / Avg: 68.28 / Max: 69.971. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75021530456075SE +/- 0.03, N = 3SE +/- 0.66, N = 153.6468.47MIN: 47.151. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75021326395265Min: 3.6 / Avg: 3.64 / Max: 3.7Min: 65.13 / Avg: 68.47 / Max: 73.71. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75024K8K12K16K20KSE +/- 7.41, N = 3SE +/- 105.95, N = 31722.3420800.07MIN: 19093.51. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: u8s8u8s322 x Xeon Platinum 82802 x EPYC 75024K8K12K16K20KMin: 1713.77 / Avg: 1722.34 / Max: 1737.1Min: 20589.6 / Avg: 20800.07 / Max: 20926.61. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 75024K8K12K16K20KSE +/- 6.52, N = 3SE +/- 183.52, N = 31756.2720777.73MIN: 18988.31. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: u8s8f32s322 x Xeon Platinum 82802 x EPYC 75024K8K12K16K20KMin: 1747.52 / Avg: 1756.27 / Max: 1769.02Min: 20529.5 / Avg: 20777.73 / Max: 211361. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ffte2 x EPYC 75022 x Xeon Platinum 8280816243240SE +/- 0.16, N = 3SE +/- 0.05, N = 333.3016.911. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGFLOP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ffte2 x EPYC 75022 x Xeon Platinum 8280714212835Min: 33.01 / Avg: 33.3 / Max: 33.56Min: 16.83 / Avg: 16.91 / Max: 17.011. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ffte2 x EPYC 75022 x Xeon Platinum 8280816243240SE +/- 0.16, N = 3SE +/- 0.05, N = 333.3016.911. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ffte2 x EPYC 75022 x Xeon Platinum 8280714212835Min: 33.01 / Avg: 33.3 / Max: 33.56Min: 16.83 / Avg: 16.91 / Max: 17.011. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

BLAKE2

This is a benchmark of BLAKE2 using the blake2s binary. BLAKE2 is a high-performance crypto alternative to MD5 and SHA-2/3. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 201703072 x Xeon Platinum 82802 x EPYC 77422 x EPYC 7502246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.876.607.461. (CC) gcc options: -O3 -march=native -lcrypto -lz
OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 201703072 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75023691215Min: 3.87 / Avg: 3.87 / Max: 3.87Min: 6.6 / Avg: 6.6 / Max: 6.61Min: 7.46 / Avg: 7.46 / Max: 7.461. (CC) gcc options: -O3 -march=native -lcrypto -lz

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 17.16, N = 3SE +/- 3.34, N = 3SE +/- 1.22, N = 39188.179125.624910.011. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828016003200480064008000Min: 9153.86 / Avg: 9188.17 / Max: 9205.78Min: 9119.03 / Avg: 9125.62 / Max: 9129.82Min: 4907.65 / Avg: 4910.01 / Max: 4911.761. (CC) gcc options: -O3 -march=native

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message Passing2 x EPYC 75022 x Xeon Platinum 82803M6M9M12M15MSE +/- 99301.92, N = 15SE +/- 79946.02, N = 312216044.866551713.521. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message Passing2 x EPYC 75022 x Xeon Platinum 82802M4M6M8M10MMin: 11547203.28 / Avg: 12216044.86 / Max: 12752659.03Min: 6406289.62 / Avg: 6551713.52 / Max: 6681984.271. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 3.77, N = 3SE +/- 4.01, N = 3SE +/- 12.12, N = 39153.109093.194916.261. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828016003200480064008000Min: 9145.68 / Avg: 9153.1 / Max: 9157.91Min: 9085.87 / Avg: 9093.19 / Max: 9099.69Min: 4892.28 / Avg: 4916.26 / Max: 4931.341. (CC) gcc options: -O3 -march=native

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Add2 x Xeon Platinum 82802 x EPYC 750213K26K39K52K65KSE +/- 153.08, N = 3SE +/- 537.65, N = 361510.2733157.231. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Add2 x Xeon Platinum 82802 x EPYC 750211K22K33K44K55KMin: 61247.7 / Avg: 61510.27 / Max: 61777.9Min: 32490.9 / Avg: 33157.23 / Max: 34221.31. (CC) gcc options: -O2 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Set2 x Xeon Platinum 82802 x EPYC 750213K26K39K52K65KSE +/- 106.71, N = 3SE +/- 423.60, N = 562020.7733580.361. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Set2 x Xeon Platinum 82802 x EPYC 750211K22K33K44K55KMin: 61880.5 / Avg: 62020.77 / Max: 62230.2Min: 32873.3 / Avg: 33580.36 / Max: 35217.31. (CC) gcc options: -O2 -lm -rdynamic

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 9.56, N = 3SE +/- 30.78, N = 3SE +/- 10.85, N = 39053.088983.594917.771. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828016003200480064008000Min: 9042.13 / Avg: 9053.08 / Max: 9072.13Min: 8924.01 / Avg: 8983.59 / Max: 9026.81Min: 4904.33 / Avg: 4917.77 / Max: 4939.241. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 128 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 16.75, N = 3SE +/- 5.56, N = 3SE +/- 3.38, N = 39065.608985.674975.461. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 128 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828016003200480064008000Min: 9042.7 / Avg: 9065.6 / Max: 9098.23Min: 8979.85 / Avg: 8985.67 / Max: 8996.79Min: 4968.85 / Avg: 4975.46 / Max: 49801. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 7.99, N = 3SE +/- 16.61, N = 3SE +/- 22.38, N = 39031.529017.435053.221. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828016003200480064008000Min: 9015.66 / Avg: 9031.52 / Max: 9041.11Min: 8999.49 / Avg: 9017.43 / Max: 9050.62Min: 5009.62 / Avg: 5053.22 / Max: 5083.81. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 16.13, N = 3SE +/- 19.23, N = 3SE +/- 9.79, N = 39050.799041.735135.381. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828016003200480064008000Min: 9019.1 / Avg: 9050.79 / Max: 9071.85Min: 9004.17 / Avg: 9041.73 / Max: 9067.69Min: 5117.36 / Avg: 5135.38 / Max: 5151.011. (CC) gcc options: -O3 -march=native

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 12 x EPYC 75022 x Xeon Platinum 828010002000300040005000SE +/- 36.83, N = 3SE +/- 8.15, N = 34559.862606.481. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 12 x EPYC 75022 x Xeon Platinum 82808001600240032004000Min: 4504.5 / Avg: 4559.86 / Max: 4629.63Min: 2590.67 / Avg: 2606.48 / Max: 2617.81. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 42 x Xeon Platinum 82802 x EPYC 75023K6K9K12K15KSE +/- 154.49, N = 3SE +/- 33.65, N = 31327876341. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 42 x Xeon Platinum 82802 x EPYC 75022K4K6K8K10KMin: 12987.01 / Avg: 13277.95 / Max: 13513.51Min: 7575.76 / Avg: 7633.88 / Max: 7692.311. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

BlogBench

BlogBench is designed to replicate the load of a real-world busy file server by stressing the file-system with multiple threads of random reads, writes, and rewrites. The behavior is mimicked of that of a blog by creating blogs with content and pictures, modifying blog posts, adding comments to these blogs, and then reading the content of the blogs. All of these blogs generated are created locally with fake content and pictures. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: Read2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 7742400K800K1200K1600K2000KSE +/- 20800.00, N = 3SE +/- 4626.16, N = 3SE +/- 14055.95, N = 31995239127205611640671. (CC) gcc options: -O2 -pthread
OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: Read2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 7742300K600K900K1200K1500KMin: 1961669 / Avg: 1995239 / Max: 2033301Min: 1263240 / Avg: 1272055.67 / Max: 1278896Min: 1136088 / Avg: 1164067 / Max: 11804211. (CC) gcc options: -O2 -pthread

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating Point2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 828010K20K30K40K50K48546.8448530.1428399.711. (CC) gcc options: -O3 -march=native

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 162 x Xeon Platinum 82802 x EPYC 750214002800420056007000SE +/- 73.23, N = 6SE +/- 43.08, N = 6634737131. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 162 x Xeon Platinum 82802 x EPYC 750211002200330044005500Min: 6134.97 / Avg: 6346.63 / Max: 6666.67Min: 3521.13 / Avg: 3713.15 / Max: 3802.281. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: f322 x Xeon Platinum 82802 x EPYC 750220406080100SE +/- 0.18, N = 3SE +/- 0.89, N = 348.5780.93MIN: 47.23MIN: 76.841. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: f322 x Xeon Platinum 82802 x EPYC 75021530456075Min: 48.25 / Avg: 48.57 / Max: 48.85Min: 79.27 / Avg: 80.93 / Max: 82.321. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 322 x Xeon Platinum 82802 x EPYC 75026001200180024003000SE +/- 31.65, N = 3SE +/- 23.57, N = 4290517571. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 322 x Xeon Platinum 82802 x EPYC 75025001000150020002500Min: 2849 / Avg: 2904.85 / Max: 2958.58Min: 1686.34 / Avg: 1756.9 / Max: 1782.531. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Bandwidth2 x EPYC 75022 x Xeon Platinum 82800.31140.62280.93421.24561.557SE +/- 0.00593, N = 3SE +/- 0.00164, N = 31.383850.837301. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Bandwidth2 x EPYC 75022 x Xeon Platinum 8280246810Min: 1.37 / Avg: 1.38 / Max: 1.39Min: 0.83 / Avg: 0.84 / Max: 0.841. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threads2 x Xeon Platinum 82802 x EPYC 7502816243240SE +/- 0.06, N = 3SE +/- 0.37, N = 320.5133.791. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threads2 x Xeon Platinum 82802 x EPYC 7502714212835Min: 20.39 / Avg: 20.51 / Max: 20.58Min: 33.12 / Avg: 33.79 / Max: 34.391. (CC) gcc options: -lm

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating Point2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828010K20K30K40K50K46521.1532247.2028432.471. (CC) gcc options: -O3 -march=native

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 82 x Xeon Platinum 82802 x EPYC 75022K4K6K8K10KSE +/- 140.23, N = 4SE +/- 49.47, N = 31042263971. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 82 x Xeon Platinum 82802 x EPYC 75022K4K6K8K10KMin: 10101.01 / Avg: 10422.32 / Max: 10752.69Min: 6329.11 / Avg: 6397.35 / Max: 6493.511. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: f322 x Xeon Platinum 82802 x EPYC 7502130260390520650SE +/- 0.44, N = 3SE +/- 8.02, N = 9382.23621.17MIN: 375.64MIN: 569.481. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: f322 x Xeon Platinum 82802 x EPYC 7502110220330440550Min: 381.35 / Avg: 382.23 / Max: 382.76Min: 585.47 / Avg: 621.17 / Max: 653.741. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 2562 x Xeon Platinum 82802 x EPYC 750290180270360450SE +/- 0.73, N = 3SE +/- 1.96, N = 34382701. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 2562 x Xeon Platinum 82802 x EPYC 750280160240320400Min: 437.25 / Avg: 438.41 / Max: 439.75Min: 266.24 / Avg: 269.93 / Max: 272.931. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode some sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 1080p2 x EPYC 75022 x Xeon Platinum 82803691215SE +/- 0.02, N = 3SE +/- 0.02, N = 35.699.201. (CC) gcc options: -pthread
OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 1080p2 x EPYC 75022 x Xeon Platinum 82803691215Min: 5.66 / Avg: 5.69 / Max: 5.72Min: 9.17 / Avg: 9.2 / Max: 9.241. (CC) gcc options: -pthread

Parboil

The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCP2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82800.29030.58060.87091.16121.4515SE +/- 0.01, N = 3SE +/- 0.02, N = 4SE +/- 0.02, N = 120.801.041.291. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCP2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 8280246810Min: 0.79 / Avg: 0.8 / Max: 0.82Min: 1.02 / Avg: 1.04 / Max: 1.08Min: 1.18 / Avg: 1.29 / Max: 1.451. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: f322 x Xeon Platinum 82802 x EPYC 7502816243240SE +/- 0.20, N = 3SE +/- 0.43, N = 1221.5334.66MIN: 20.76MIN: 30.771. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: f322 x Xeon Platinum 82802 x EPYC 7502714212835Min: 21.23 / Avg: 21.53 / Max: 21.9Min: 32.83 / Avg: 34.66 / Max: 37.051. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Tsearch2 x EPYC 75022 x Xeon Platinum 8280400800120016002000SE +/- 6.47, N = 3SE +/- 0.14, N = 31752.391090.941. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Tsearch2 x EPYC 75022 x Xeon Platinum 828030060090012001500Min: 1739.54 / Avg: 1752.39 / Max: 1760.09Min: 1090.7 / Avg: 1090.94 / Max: 1091.21. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Forking2 x Xeon Platinum 82802 x EPYC 750215K30K45K60K75KSE +/- 870.64, N = 4SE +/- 120.17, N = 368990.1643020.811. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Forking2 x Xeon Platinum 82802 x EPYC 750212K24K36K48K60KMin: 66676.16 / Avg: 68990.16 / Max: 70902.93Min: 42783.05 / Avg: 43020.81 / Max: 43170.121. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Max Ping Pong Bandwidth2 x Xeon Platinum 82802 x EPYC 75024K8K12K16K20KSE +/- 56.79, N = 3SE +/- 77.41, N = 317273.8210781.241. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgMB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Max Ping Pong Bandwidth2 x Xeon Platinum 82802 x EPYC 75023K6K9K12K15KMin: 17160.24 / Avg: 17273.82 / Max: 17331.4Min: 10659.53 / Avg: 10781.24 / Max: 10924.961. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 1282 x Xeon Platinum 82802 x EPYC 7502120240360480600SE +/- 0.98, N = 3SE +/- 3.87, N = 35443421. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 1282 x Xeon Platinum 82802 x EPYC 7502100200300400500Min: 541.71 / Avg: 543.68 / Max: 544.66Min: 338.29 / Avg: 342.28 / Max: 350.021. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradebeans2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82803K6K9K12K15KSE +/- 59.83, N = 4SE +/- 56.27, N = 4SE +/- 98.03, N = 47419774311780
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradebeans2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82802K4K6K8K10KMin: 7307 / Avg: 7418.5 / Max: 7553Min: 7661 / Avg: 7742.5 / Max: 7909Min: 11556 / Avg: 11779.5 / Max: 12013

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket Activity2 x Xeon Platinum 82802 x EPYC 75028K16K24K32K40KSE +/- 497.69, N = 3SE +/- 58.06, N = 337540.1823811.441. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket Activity2 x Xeon Platinum 82802 x EPYC 75027K14K21K28K35KMin: 36567.31 / Avg: 37540.18 / Max: 38208.9Min: 23704.48 / Avg: 23811.44 / Max: 23904.081. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusecs, Fewer Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Latency2 x Xeon Platinum 82802 x EPYC 75020.40040.80081.20121.60162.002SE +/- 0.00802, N = 3SE +/- 0.00742, N = 31.133561.779761. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgusecs, Fewer Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Latency2 x Xeon Platinum 82802 x EPYC 7502246810Min: 1.12 / Avg: 1.13 / Max: 1.14Min: 1.77 / Avg: 1.78 / Max: 1.791. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating Point2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82809K18K27K36K45K40026.1336195.5025821.881. (CC) gcc options: -O3 -march=native

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 0.51080p 8-bit YUV To AV1 Video Encode2 x EPYC 75022 x Xeon Platinum 828020406080100SE +/- 0.46, N = 3SE +/- 0.65, N = 394.9961.531. (CXX) g++ options: -O3 -pie -lpthread -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.51080p 8-bit YUV To AV1 Video Encode2 x EPYC 75022 x Xeon Platinum 828020406080100Min: 94.25 / Avg: 94.99 / Max: 95.83Min: 60.81 / Avg: 61.53 / Max: 62.831. (CXX) g++ options: -O3 -pie -lpthread -lm

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 642 x Xeon Platinum 82802 x EPYC 750230060090012001500SE +/- 18.28, N = 3SE +/- 0.93, N = 312868351. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 642 x Xeon Platinum 82802 x EPYC 75022004006008001000Min: 1256.28 / Avg: 1285.86 / Max: 1319.26Min: 834.03 / Avg: 834.96 / Max: 836.821. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material Tester2 x Xeon Platinum 82802 x EPYC 750260120180240300184.90284.19

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 5122 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82807K14K21K28K35KSE +/- 85.48, N = 3SE +/- 128.07, N = 3SE +/- 15.95, N = 33417833879222891. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 5122 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KMin: 34048 / Avg: 34177.67 / Max: 34339Min: 33623 / Avg: 33878.67 / Max: 34020Min: 22258 / Avg: 22289 / Max: 223111. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format using a sample 1080p video. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video Encode2 x EPYC 75022 x Xeon Platinum 8280306090120150SE +/- 0.79, N = 3SE +/- 1.15, N = 3145.2994.821. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video Encode2 x EPYC 75022 x Xeon Platinum 8280306090120150Min: 143.9 / Avg: 145.29 / Max: 146.62Min: 93.08 / Avg: 94.82 / Max: 96.981. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating Point2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82809K18K27K36K45K44274.7040959.6329059.501. (CC) gcc options: -O3 -march=native

Bork File Encrypter

Bork is a small, cross-platform file encryption utility. It is written in Java and designed to be included along with the files it encrypts for long-term storage. This test measures the amount of time it takes to encrypt a sample file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBork File Encrypter 1.4File Encryption Time2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75023691215SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 37.1010.7310.77
OpenBenchmarking.orgSeconds, Fewer Is BetterBork File Encrypter 1.4File Encryption Time2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75023691215Min: 7.07 / Avg: 7.1 / Max: 7.12Min: 10.67 / Avg: 10.73 / Max: 10.82Min: 10.68 / Avg: 10.77 / Max: 10.87

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 10242 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82807K14K21K28K35KSE +/- 264.46, N = 3SE +/- 141.25, N = 3SE +/- 40.70, N = 33389533251223511. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 10242 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KMin: 33498 / Avg: 33894.67 / Max: 34396Min: 32997 / Avg: 33251.33 / Max: 33485Min: 22290 / Avg: 22350.67 / Max: 224281. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 10242 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750214K28K42K56K70KSE +/- 1102.91, N = 3SE +/- 58.50, N = 3SE +/- 362.20, N = 36473243869430781. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 10242 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750211K22K33K44K55KMin: 63372 / Avg: 64732 / Max: 66916Min: 43773 / Avg: 43869.33 / Max: 43975Min: 42390 / Avg: 43078.33 / Max: 436181. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Semaphores2 x Xeon Platinum 82802 x EPYC 7502400K800K1200K1600K2000KSE +/- 23663.90, N = 6SE +/- 7978.41, N = 32098938.521398972.491. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Semaphores2 x Xeon Platinum 82802 x EPYC 7502400K800K1200K1600K2000KMin: 2007262.83 / Avg: 2098938.52 / Max: 2177944.5Min: 1383697.73 / Avg: 1398972.49 / Max: 1410606.921. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 5122 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750212K24K36K48K60KSE +/- 886.61, N = 3SE +/- 336.45, N = 3SE +/- 56.26, N = 35598338922377221. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 5122 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750210K20K30K40K50KMin: 54859 / Avg: 55983.33 / Max: 57733Min: 38357 / Avg: 38922 / Max: 39521Min: 37613 / Avg: 37722.33 / Max: 378001. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Integer2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828010K20K30K40K50K48252.9347552.0432779.231. (CC) gcc options: -O3 -march=native

Tinymembench

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memset2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82803K6K9K12K15KSE +/- 17.98, N = 3SE +/- 16.26, N = 3SE +/- 67.15, N = 316030.5015239.7710920.171. (CC) gcc options: -O2 -lm
OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memset2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82803K6K9K12K15KMin: 15998.1 / Avg: 16030.5 / Max: 16060.2Min: 15207.3 / Avg: 15239.77 / Max: 15257.5Min: 10785.9 / Avg: 10920.17 / Max: 10989.51. (CC) gcc options: -O2 -lm

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: u8s8u8s322 x EPYC 75022 x Xeon Platinum 82808001600240032004000SE +/- 3.79, N = 3SE +/- 35.12, N = 32437.573576.18MIN: 2414.66MIN: 3520.691. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: u8s8u8s322 x EPYC 75022 x Xeon Platinum 82806001200180024003000Min: 2429.99 / Avg: 2437.57 / Max: 2441.66Min: 3525.87 / Avg: 3576.18 / Max: 3643.771. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

TTSIOD 3D Renderer

A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow Mapping2 x Xeon Platinum 82802 x EPYC 75022004006008001000SE +/- 12.66, N = 3SE +/- 9.93, N = 151010.28693.211. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow Mapping2 x Xeon Platinum 82802 x EPYC 75022004006008001000Min: 987.75 / Avg: 1010.28 / Max: 1031.57Min: 629.49 / Avg: 693.21 / Max: 754.891. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: u8s8f32s322 x EPYC 75022 x Xeon Platinum 82808001600240032004000SE +/- 2.13, N = 3SE +/- 2.31, N = 32447.433538.23MIN: 2424.63MIN: 3524.611. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: u8s8f32s322 x EPYC 75022 x Xeon Platinum 82806001200180024003000Min: 2443.63 / Avg: 2447.43 / Max: 2450.98Min: 3535.87 / Avg: 3538.23 / Max: 3542.841. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programs2 x Xeon Platinum 82802 x EPYC 750220406080100SE +/- 0.52, N = 9SE +/- 0.82, N = 354.5178.171. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programs2 x Xeon Platinum 82802 x EPYC 75021530456075Min: 51.98 / Avg: 54.51 / Max: 56.88Min: 77.27 / Avg: 78.17 / Max: 79.81. (CC) gcc options: -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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: FT.B2 x EPYC 75022 x Xeon Platinum 82808001600240032004000SE +/- 3.88, N = 3SE +/- 4.18, N = 33660.372556.201. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: FT.B2 x EPYC 75022 x Xeon Platinum 82806001200180024003000Min: 3652.68 / Avg: 3660.37 / Max: 3665.07Min: 2548.63 / Avg: 2556.2 / Max: 2563.041. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 20482 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750214K28K42K56K70KSE +/- 650.59, N = 3SE +/- 332.33, N = 3SE +/- 549.65, N = 36390845337449151. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 20482 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750211K22K33K44K55KMin: 62610 / Avg: 63908.33 / Max: 64632Min: 44676 / Avg: 45336.67 / Max: 45730Min: 43857 / Avg: 44914.67 / Max: 457031. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: FT.A2 x EPYC 75022 x Xeon Platinum 82807001400210028003500SE +/- 5.92, N = 3SE +/- 2.56, N = 33332.602378.801. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: FT.A2 x EPYC 75022 x Xeon Platinum 82806001200180024003000Min: 3323.17 / Avg: 3332.6 / Max: 3343.53Min: 2373.77 / Avg: 2378.8 / Max: 2382.11. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

BlogBench

BlogBench is designed to replicate the load of a real-world busy file server by stressing the file-system with multiple threads of random reads, writes, and rewrites. The behavior is mimicked of that of a blog by creating blogs with content and pictures, modifying blog posts, adding comments to these blogs, and then reading the content of the blogs. All of these blogs generated are created locally with fake content and pictures. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: Write2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 774211K22K33K44K55KSE +/- 449.95, N = 3SE +/- 882.24, N = 3SE +/- 7.00, N = 25351643807382261. (CC) gcc options: -O2 -pthread
OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: Write2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77429K18K27K36K45KMin: 52636 / Avg: 53516 / Max: 54119Min: 42467 / Avg: 43806.67 / Max: 45471Min: 38219 / Avg: 38226 / Max: 382331. (CC) gcc options: -O2 -pthread

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 40962 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750212K24K36K48K60KSE +/- 504.24, N = 3SE +/- 395.93, N = 3SE +/- 553.18, N = 35822243038416181. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 40962 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750210K20K30K40K50KMin: 57407 / Avg: 58222.33 / Max: 59144Min: 42271 / Avg: 43038 / Max: 43592Min: 40910 / Avg: 41617.67 / Max: 427081. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2562 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82807K14K21K28K35KSE +/- 194.96, N = 3SE +/- 93.28, N = 3SE +/- 413.74, N = 33428433586248531. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2562 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KMin: 33910 / Avg: 34283.67 / Max: 34567Min: 33427 / Avg: 33586 / Max: 33750Min: 24378 / Avg: 24852.67 / Max: 256771. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processes2 x Xeon Platinum 82802 x EPYC 75021428425670SE +/- 0.79, N = 3SE +/- 0.76, N = 345.9263.311. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processes2 x Xeon Platinum 82802 x EPYC 75021224364860Min: 44.95 / Avg: 45.92 / Max: 47.49Min: 61.85 / Avg: 63.31 / Max: 64.431. (CC) gcc options: -lm

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode some sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 4K2 x EPYC 75022 x Xeon Platinum 828048121620SE +/- 0.07, N = 3SE +/- 0.04, N = 313.2418.251. (CC) gcc options: -pthread
OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 4K2 x EPYC 75022 x Xeon Platinum 8280510152025Min: 13.17 / Avg: 13.24 / Max: 13.39Min: 18.17 / Avg: 18.25 / Max: 18.291. (CC) gcc options: -pthread

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Monte Carlo2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828030060090012001500SE +/- 0.37, N = 4SE +/- 2.07, N = 4SE +/- 0.22, N = 41355.521333.85984.07
OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Monte Carlo2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802004006008001000Min: 1354.88 / Avg: 1355.52 / Max: 1356.16Min: 1327.66 / Avg: 1333.85 / Max: 1336.33Min: 983.73 / Avg: 984.07 / Max: 984.63

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 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video Encode2 x Xeon Platinum 82802 x EPYC 750260120180240300SE +/- 3.53, N = 4SE +/- 1.34, N = 3271.63197.261. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video Encode2 x Xeon Platinum 82802 x EPYC 750250100150200250Min: 263.5 / Avg: 271.63 / Max: 279.98Min: 195.06 / Avg: 197.26 / Max: 199.671. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx -pie -rdynamic -lpthread -lrt -lm

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32s322 x EPYC 75022 x Xeon Platinum 8280400800120016002000SE +/- 2.32, N = 3SE +/- 1.15, N = 31377.001890.00MIN: 1361.39MIN: 1885.551. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32s322 x EPYC 75022 x Xeon Platinum 828030060090012001500Min: 1372.47 / Avg: 1377 / Max: 1380.17Min: 1888.51 / Avg: 1890 / Max: 1892.271. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Numpy Benchmark

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

OpenBenchmarking.orgNanoseconds, Fewer Is BetterNumpy Benchmark2 x Xeon Platinum 82802 x EPYC 75021.5M3M4.5M6M7.5M52622167216577

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Crypto2 x EPYC 75022 x Xeon Platinum 82803K6K9K12K15KSE +/- 28.56, N = 3SE +/- 24.84, N = 314305.8410503.091. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Crypto2 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KMin: 14260.94 / Avg: 14305.84 / Max: 14358.87Min: 10468.85 / Avg: 10503.09 / Max: 10551.391. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: u8s8u8s322 x EPYC 75022 x Xeon Platinum 8280400800120016002000SE +/- 6.93, N = 3SE +/- 2.38, N = 31507.232041.25MIN: 1483.12MIN: 2036.341. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: u8s8u8s322 x EPYC 75022 x Xeon Platinum 8280400800120016002000Min: 1494.27 / Avg: 1507.23 / Max: 1517.98Min: 2038.69 / Avg: 2041.25 / Max: 20461. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Integer2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82809K18K27K36K45K43023.1340110.2931863.551. (CC) gcc options: -O3 -march=native

m-queens

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

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve2 x EPYC 75022 x Xeon Platinum 828048121620SE +/- 0.10, N = 3SE +/- 0.03, N = 312.1016.301. (CXX) g++ options: -fopenmp -O2 -march=native
OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve2 x EPYC 75022 x Xeon Platinum 828048121620Min: 11.9 / Avg: 12.1 / Max: 12.24Min: 16.26 / Avg: 16.3 / Max: 16.351. (CXX) g++ options: -fopenmp -O2 -march=native

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integer2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82809K18K27K36K45K42271.5842022.6031645.321. (CC) gcc options: -O3 -march=native

Sockperf

This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping Pong2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77421.19252.3853.57754.775.9625SE +/- 0.03, N = 5SE +/- 0.02, N = 5SE +/- 0.02, N = 53.984.855.301. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping Pong2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 7742246810Min: 3.88 / Avg: 3.98 / Max: 4.05Min: 4.8 / Avg: 4.85 / Max: 4.94Min: 5.22 / Avg: 5.3 / Max: 5.351. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

x265

This is a simple test of the x265 encoder run on the CPU with a sample 1080p video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video Encoding2 x EPYC 75022 x Xeon Platinum 82801020304050SE +/- 0.11, N = 3SE +/- 0.10, N = 343.4632.731. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video Encoding2 x EPYC 75022 x Xeon Platinum 8280918273645Min: 43.26 / Avg: 43.46 / Max: 43.65Min: 32.63 / Avg: 32.73 / Max: 32.921. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integer2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82809K18K27K36K45K42739.1241104.7132285.251. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Integer2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82808K16K24K32K40K38464.7337700.4029096.351. (CC) gcc options: -O3 -march=native

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradesoap2 x EPYC 75022 x Xeon Platinum 828016003200480064008000SE +/- 41.94, N = 20SE +/- 75.42, N = 2056017404
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradesoap2 x EPYC 75022 x Xeon Platinum 828013002600390052006500Min: 5373 / Avg: 5600.65 / Max: 5976Min: 6990 / Avg: 7403.95 / Max: 8086

C-Ray

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

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel2 x EPYC 75022 x Xeon Platinum 828048121620SE +/- 0.03, N = 3SE +/- 0.10, N = 310.9014.401. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel2 x EPYC 75022 x Xeon Platinum 828048121620Min: 10.87 / Avg: 10.9 / Max: 10.96Min: 14.27 / Avg: 14.4 / Max: 14.61. (CC) gcc options: -lm -lpthread -O3

Tinymembench

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpy2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82802K4K6K8K10KSE +/- 4.52, N = 3SE +/- 4.70, N = 3SE +/- 51.26, N = 39148.309130.606933.101. (CC) gcc options: -O2 -lm
OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpy2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 828016003200480064008000Min: 9139.8 / Avg: 9148.3 / Max: 9155.2Min: 9125.8 / Avg: 9130.6 / Max: 9140Min: 6858 / Avg: 6933.1 / Max: 7031.11. (CC) gcc options: -O2 -lm

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video Encode2 x EPYC 75022 x Xeon Platinum 828070140210280350SE +/- 2.17, N = 3SE +/- 3.63, N = 4340.94260.311. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video Encode2 x EPYC 75022 x Xeon Platinum 828060120180240300Min: 337.65 / Avg: 340.94 / Max: 345.03Min: 254.78 / Avg: 260.31 / Max: 270.511. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native -pie -rdynamic -lpthread -lrt

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: Blowfish2 x EPYC 75022 x Xeon Platinum 828020K40K60K80K100KSE +/- 1300.44, N = 3SE +/- 567.99, N = 3109363835781. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: Blowfish2 x EPYC 75022 x Xeon Platinum 828020K40K60K80K100KMin: 106790 / Avg: 109363.33 / Max: 110977Min: 82891 / Avg: 83578 / Max: 847051. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite2 x Xeon Platinum 82802 x EPYC 7502140K280K420K560K700KSE +/- 240.33, N = 3SE +/- 1963.83, N = 3646738494910
OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite2 x Xeon Platinum 82802 x EPYC 7502110K220K330K440K550KMin: 646467 / Avg: 646737.67 / Max: 647217Min: 492701 / Avg: 494910 / Max: 498827

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 102 x Xeon Platinum 82802 x EPYC 75026K12K18K24K30KSE +/- 326.78, N = 15SE +/- 86.97, N = 326011.6319907.861. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 102 x Xeon Platinum 82802 x EPYC 75025K10K15K20K25KMin: 23474.18 / Avg: 26011.63 / Max: 27624.31Min: 19801.98 / Avg: 19907.86 / Max: 20080.321. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

PHP Micro Benchmarks

Various small PHP micro-benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPHP Micro BenchmarksTest: Zend micro_bench2 x Xeon Platinum 82802 x EPYC 75020.59851.1971.79552.3942.9925SE +/- 0.01, N = 3SE +/- 0.04, N = 32.062.66
OpenBenchmarking.orgSeconds, Fewer Is BetterPHP Micro BenchmarksTest: Zend micro_bench2 x Xeon Platinum 82802 x EPYC 7502246810Min: 2.05 / Avg: 2.06 / Max: 2.09Min: 2.59 / Avg: 2.66 / Max: 2.74

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 322 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82808K16K24K32K40KSE +/- 76.70, N = 3SE +/- 35.51, N = 3SE +/- 223.03, N = 33502834572271281. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 322 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KMin: 34947 / Avg: 35027.67 / Max: 35181Min: 34501 / Avg: 34572 / Max: 34609Min: 26833 / Avg: 27127.67 / Max: 275651. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Hsearch2 x EPYC 75022 x Xeon Platinum 828080K160K240K320K400KSE +/- 782.39, N = 3SE +/- 1743.97, N = 3388395.98301307.761. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Hsearch2 x EPYC 75022 x Xeon Platinum 828070K140K210K280K350KMin: 386841.34 / Avg: 388395.98 / Max: 389327.32Min: 297978.7 / Avg: 301307.76 / Max: 303873.551. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 502 x Xeon Platinum 82802 x EPYC 75026K12K18K24K30KSE +/- 426.87, N = 3SE +/- 253.10, N = 327914.6821691.561. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 502 x Xeon Platinum 82802 x EPYC 75025K10K15K20K25KMin: 27352.3 / Avg: 27914.68 / Max: 28752.16Min: 21340.16 / Avg: 21691.56 / Max: 22182.791. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: Compression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75028162432403628281. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

IndigoBench

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

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Bedroom2 x Xeon Platinum 82802 x EPYC 7502246810SE +/- 0.01, N = 3SE +/- 0.01, N = 36.144.78
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Bedroom2 x Xeon Platinum 82802 x EPYC 7502246810Min: 6.13 / Avg: 6.14 / Max: 6.15Min: 4.76 / Avg: 4.78 / Max: 4.79

Phoronix Test Suite Self Test

This is a wrapper around the phoronix-test-suite debug-self-test sub-command for testing hot Phoronix Test Suite code paths and if wanting to compare different PHP implementations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Info Command2 x Xeon Platinum 82802 x EPYC 75020.6931.3862.0792.7723.465SE +/- 0.00, N = 2SE +/- 0.05, N = 22.403.08
OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Info Command2 x Xeon Platinum 82802 x EPYC 7502246810Min: 2.4 / Avg: 2.4 / Max: 2.4Min: 3.04 / Avg: 3.08 / Max: 3.13

IndigoBench

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

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Supercar2 x Xeon Platinum 82802 x EPYC 75023691215SE +/- 0.03, N = 3SE +/- 0.01, N = 39.887.72
OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Supercar2 x Xeon Platinum 82802 x EPYC 75023691215Min: 9.84 / Avg: 9.88 / Max: 9.95Min: 7.71 / Avg: 7.72 / Max: 7.74

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H22 x EPYC 75022 x EPYC 77422 x Xeon Platinum 82802K4K6K8K10KSE +/- 92.11, N = 4SE +/- 35.70, N = 4SE +/- 38.38, N = 4691182268773
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H22 x EPYC 75022 x EPYC 77422 x Xeon Platinum 828015003000450060007500Min: 6705 / Avg: 6911 / Max: 7117Min: 8133 / Avg: 8226 / Max: 8307Min: 8679 / Avg: 8773.25 / Max: 8859

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: In-Memory Database Shootout2 x EPYC 75022 x Xeon Platinum 82804K8K12K16K20KSE +/- 120.36, N = 11SE +/- 158.15, N = 1013682.6717337.65
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: In-Memory Database Shootout2 x EPYC 75022 x Xeon Platinum 82803K6K9K12K15KMin: 12765.32 / Avg: 13682.67 / Max: 14098.64Min: 16822.51 / Avg: 17337.65 / Max: 18536.72

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 20482 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KSE +/- 51.68, N = 3SE +/- 195.72, N = 3SE +/- 101.12, N = 32666126109211981. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 20482 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82805K10K15K20K25KMin: 26558 / Avg: 26661.33 / Max: 26715Min: 25719 / Avg: 26109.33 / Max: 26330Min: 21004 / Avg: 21198.33 / Max: 213441. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Cython benchmark

Stress benchmark tests to measure time consumed by cython code Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCython benchmark 0.272 x Xeon Platinum 82802 x EPYC 7502714212835SE +/- 0.05, N = 3SE +/- 0.07, N = 322.9728.68
OpenBenchmarking.orgSeconds, Fewer Is BetterCython benchmark 0.272 x Xeon Platinum 82802 x EPYC 7502612182430Min: 22.92 / Avg: 22.97 / Max: 23.06Min: 28.54 / Avg: 28.68 / Max: 28.78

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 1002 x Xeon Platinum 82802 x EPYC 75027K14K21K28K35KSE +/- 119.32, N = 3SE +/- 186.18, N = 333241.8626655.061. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 1002 x Xeon Platinum 82802 x EPYC 75026K12K18K24K30KMin: 33003.3 / Avg: 33241.86 / Max: 33366.7Min: 26308.87 / Avg: 26655.06 / Max: 26946.911. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

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 the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD Solver2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77423691215SE +/- 0.10, N = 15SE +/- 0.13, N = 15SE +/- 0.13, N = 37.318.879.101. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD Solver2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77423691215Min: 6.57 / Avg: 7.31 / Max: 7.99Min: 8.16 / Avg: 8.87 / Max: 10.36Min: 8.92 / Avg: 9.1 / Max: 9.361. (CXX) g++ options: -O2 -lOpenCL

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu file-system image) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 192 x Xeon Platinum 82802 x EPYC 75023691215SE +/- 0.10, N = 6SE +/- 0.05, N = 39.0111.201. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 192 x Xeon Platinum 82802 x EPYC 75023691215Min: 8.56 / Avg: 9.01 / Max: 9.31Min: 11.11 / Avg: 11.2 / Max: 11.261. (CC) gcc options: -O3 -pthread -lz -llzma

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video Encoding2 x EPYC 75022 x Xeon Platinum 8280306090120150SE +/- 0.99, N = 3SE +/- 1.20, N = 15148.94120.041. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video Encoding2 x EPYC 75022 x Xeon Platinum 8280306090120150Min: 147.1 / Avg: 148.94 / Max: 150.49Min: 114.71 / Avg: 120.04 / Max: 129.051. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

Minion

Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Quasigroup2 x Xeon Platinum 82802 x EPYC 7502306090120150SE +/- 0.23, N = 3SE +/- 0.20, N = 3111.21137.891. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Quasigroup2 x Xeon Platinum 82802 x EPYC 7502306090120150Min: 110.98 / Avg: 111.21 / Max: 111.68Min: 137.68 / Avg: 137.89 / Max: 138.31. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Phoronix Test Suite Self Test

This is a wrapper around the phoronix-test-suite debug-self-test sub-command for testing hot Phoronix Test Suite code paths and if wanting to compare different PHP implementations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Merge Results2 x Xeon Platinum 82802 x EPYC 75021.0892.1783.2674.3565.445SE +/- 0.00, N = 2SE +/- 0.03, N = 23.914.84
OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Merge Results2 x Xeon Platinum 82802 x EPYC 7502246810Min: 3.91 / Avg: 3.91 / Max: 3.91Min: 4.81 / Avg: 4.84 / Max: 4.88

dcraw

This test times how long it takes to convert several high-resolution RAW NEF image files to PPM image format using dcraw. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image Conversion2 x Xeon Platinum 82802 x EPYC 75021224364860SE +/- 0.01, N = 3SE +/- 0.03, N = 341.7751.431. (CC) gcc options: -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image Conversion2 x Xeon Platinum 82802 x EPYC 75021020304050Min: 41.75 / Avg: 41.77 / Max: 41.78Min: 51.39 / Avg: 51.43 / Max: 51.481. (CC) gcc options: -lm

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: f322 x EPYC 75022 x Xeon Platinum 828020406080100SE +/- 0.98, N = 3SE +/- 1.72, N = 381.93100.80MIN: 59.17MIN: 65.661. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: f322 x EPYC 75022 x Xeon Platinum 828020406080100Min: 79.99 / Avg: 81.93 / Max: 83.1Min: 98.3 / Avg: 100.8 / Max: 104.091. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Boat - Acceleration: CPU-only2 x EPYC 75022 x Xeon Platinum 82800.91131.82262.73393.64524.5565SE +/- 0.05, N = 3SE +/- 0.04, N = 33.304.05
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Boat - Acceleration: CPU-only2 x EPYC 75022 x Xeon Platinum 8280246810Min: 3.2 / Avg: 3.3 / Max: 3.37Min: 3.97 / Avg: 4.05 / Max: 4.12

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 1282 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82807K14K21K28K35KSE +/- 152.49, N = 3SE +/- 72.57, N = 3SE +/- 356.69, N = 33500334549286131. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 1282 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KMin: 34768 / Avg: 35003.33 / Max: 35289Min: 34416 / Avg: 34548.67 / Max: 34666Min: 27906 / Avg: 28613 / Max: 290491. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Blowfish - Encrypt2 x Xeon Platinum 82802 x EPYC 750260120180240300SE +/- 0.03, N = 3SE +/- 0.16, N = 3282.43231.131. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Blowfish - Encrypt2 x Xeon Platinum 82802 x EPYC 750250100150200250Min: 282.38 / Avg: 282.43 / Max: 282.47Min: 230.95 / Avg: 231.13 / Max: 231.451. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: f322 x EPYC 75022 x Xeon Platinum 82803691215SE +/- 0.09, N = 3SE +/- 0.15, N = 39.4711.56MIN: 4.89MIN: 6.181. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: f322 x EPYC 75022 x Xeon Platinum 82803691215Min: 9.33 / Avg: 9.47 / Max: 9.64Min: 11.39 / Avg: 11.56 / Max: 11.851. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

TSCP

This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performance2 x Xeon Platinum 82802 x EPYC 7502300K600K900K1200K1500KSE +/- 1283.95, N = 5SE +/- 778.60, N = 5125748910360781. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performance2 x Xeon Platinum 82802 x EPYC 7502200K400K600K800K1000KMin: 1254619 / Avg: 1257488.8 / Max: 1260361Min: 1033354 / Avg: 1036077.6 / Max: 10372461. (CC) gcc options: -O3 -march=native

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: AES-256 - Decrypt2 x EPYC 75022 x Xeon Platinum 828010002000300040005000SE +/- 4.72, N = 3SE +/- 1.30, N = 34639.823827.961. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: AES-256 - Decrypt2 x EPYC 75022 x Xeon Platinum 82808001600240032004000Min: 4631.29 / Avg: 4639.82 / Max: 4647.57Min: 3825.36 / Avg: 3827.96 / Max: 3829.31. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 322 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75023K6K9K12K15KSE +/- 31.05, N = 3SE +/- 31.83, N = 3SE +/- 10.11, N = 31431711985118481. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 322 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75022K4K6K8K10KMin: 14283 / Avg: 14317 / Max: 14379Min: 11926 / Avg: 11985.33 / Max: 12035Min: 11830 / Avg: 11847.67 / Max: 118651. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: Decompression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75022004006008001000SE +/- 8.00, N = 310168678411. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: Decompression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75022004006008001000Min: 1000 / Avg: 1016 / Max: 10241. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Blowfish - Decrypt2 x Xeon Platinum 82802 x EPYC 750260120180240300SE +/- 0.07, N = 3SE +/- 0.07, N = 3274.68228.061. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Blowfish - Decrypt2 x Xeon Platinum 82802 x EPYC 750250100150200250Min: 274.57 / Avg: 274.68 / Max: 274.81Min: 227.93 / Avg: 228.06 / Max: 228.161. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

PHP Micro Benchmarks

Various small PHP micro-benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPHP Micro BenchmarksTest: Zend bench2 x Xeon Platinum 82802 x EPYC 75020.12150.2430.36450.4860.6075SE +/- 0.00, N = 3SE +/- 0.00, N = 30.450.54
OpenBenchmarking.orgSeconds, Fewer Is BetterPHP Micro BenchmarksTest: Zend bench2 x Xeon Platinum 82802 x EPYC 7502246810Min: 0.44 / Avg: 0.45 / Max: 0.45Min: 0.54 / Avg: 0.54 / Max: 0.55

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: AES-256 - Encrypt2 x EPYC 75022 x Xeon Platinum 828010002000300040005000SE +/- 1.53, N = 3SE +/- 1.15, N = 34585.383822.661. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: AES-256 - Encrypt2 x EPYC 75022 x Xeon Platinum 82808001600240032004000Min: 4583.79 / Avg: 4585.38 / Max: 4588.45Min: 3820.46 / Avg: 3822.66 / Max: 3824.341. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

XZ Compression

This test measures the time needed to compress a sample file (an Ubuntu file-system image) using XZ compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 92 x Xeon Platinum 82802 x EPYC 7502612182430SE +/- 0.19, N = 3SE +/- 0.13, N = 322.5026.971. (CC) gcc options: -pthread -fvisibility=hidden -O2
OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 92 x Xeon Platinum 82802 x EPYC 7502612182430Min: 22.12 / Avg: 22.5 / Max: 22.73Min: 26.71 / Avg: 26.97 / Max: 27.131. (CC) gcc options: -pthread -fvisibility=hidden -O2

Timed GCC Compilation

This test times how long it takes to build the GNU Compiler Collection (GCC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To Compile2 x EPYC 75022 x Xeon Platinum 82802004006008001000SE +/- 0.64, N = 3SE +/- 0.37, N = 3746.44891.66
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To Compile2 x EPYC 75022 x Xeon Platinum 8280160320480640800Min: 745.16 / Avg: 746.44 / Max: 747.18Min: 890.92 / Avg: 891.66 / Max: 892.1

SPECjbb 2015

This is a benchmark of SPECjbb 2015. For this test profile to work, you must have a valid license/copy of the SPECjbb 2015 ISO (SPECjbb2015-1.02.iso) in your Phoronix Test Suite download cache. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite critical-jOPS2 x EPYC 75022 x Xeon Platinum 828013K26K39K52K65K6021850770

Stream

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scale2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828040K80K120K160K200KSE +/- 986.94, N = 5SE +/- 1282.73, N = 5SE +/- 682.69, N = 5177028.66155497.48149490.081. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scale2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828030K60K90K120K150KMin: 173857.2 / Avg: 177028.66 / Max: 179955.1Min: 151244.9 / Avg: 155497.48 / Max: 158290.6Min: 147738.8 / Avg: 149490.08 / Max: 151173.31. (CC) gcc options: -O3 -march=native -fopenmp

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc Qsort Data Sorting2 x EPYC 75022 x Xeon Platinum 82802004006008001000SE +/- 6.92, N = 3SE +/- 1.75, N = 3931.27787.111. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc Qsort Data Sorting2 x EPYC 75022 x Xeon Platinum 8280160320480640800Min: 918.16 / Avg: 931.27 / Max: 941.66Min: 784.23 / Avg: 787.11 / Max: 790.271. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750212002400360048006000SE +/- 36.59, N = 4SE +/- 26.33, N = 4SE +/- 67.79, N = 4462952645466
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75029001800270036004500Min: 4553 / Avg: 4628.75 / Max: 4705Min: 5194 / Avg: 5263.5 / Max: 5313Min: 5303 / Avg: 5465.75 / Max: 5634

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADD2 x Xeon Platinum 82802 x EPYC 7502500K1000K1500K2000K2500KSE +/- 20580.51, N = 15SE +/- 26432.00, N = 152122727.271800546.071. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADD2 x Xeon Platinum 82802 x EPYC 7502400K800K1200K1600K2000KMin: 1980198 / Avg: 2122727.27 / Max: 2217295Min: 1623376.62 / Avg: 1800546.07 / Max: 1956947.251. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 20482 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828013002600390052006500SE +/- 9.32, N = 3SE +/- 71.82, N = 5SE +/- 75.14, N = 45992.505815.065090.451. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 20482 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828010002000300040005000Min: 5978.2 / Avg: 5992.5 / Max: 6010Min: 5588.1 / Avg: 5815.06 / Max: 5981Min: 4955.6 / Avg: 5090.45 / Max: 5272.41. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: Decompression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 7502110220330440550SE +/- 0.88, N = 3SE +/- 0.33, N = 35194464411. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: Decompression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750290180270360450Min: 517 / Avg: 518.67 / Max: 520Min: 445 / Avg: 445.67 / Max: 4461. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Phoronix Test Suite Self Test

This is a wrapper around the phoronix-test-suite debug-self-test sub-command for testing hot Phoronix Test Suite code paths and if wanting to compare different PHP implementations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Total Time2 x Xeon Platinum 82802 x EPYC 750260120180240300SE +/- 1.33, N = 3SE +/- 0.68, N = 3215.42253.05
OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Total Time2 x Xeon Platinum 82802 x EPYC 750250100150200250Min: 213.68 / Avg: 215.42 / Max: 218.03Min: 252.13 / Avg: 253.05 / Max: 254.37

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating Point2 x EPYC 77422 x Xeon Platinum 82802 x EPYC 75028K16K24K32K40K35526.3732109.9130275.111. (CC) gcc options: -O3 -march=native

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Twofish - Decrypt2 x Xeon Platinum 82802 x EPYC 750280160240320400SE +/- 0.19, N = 3SE +/- 0.10, N = 3350.83299.171. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Twofish - Decrypt2 x Xeon Platinum 82802 x EPYC 750260120180240300Min: 350.46 / Avg: 350.83 / Max: 351.07Min: 298.97 / Avg: 299.17 / Max: 299.321. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 2002 x Xeon Platinum 82802 x EPYC 75027K14K21K28K35KSE +/- 38.45, N = 3SE +/- 61.21, N = 333431.8628568.971. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 2002 x Xeon Platinum 82802 x EPYC 75026K12K18K24K30KMin: 33355.57 / Avg: 33431.86 / Max: 33478.41Min: 28494.09 / Avg: 28568.97 / Max: 28690.291. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Classroom - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 82802040608010080.6094.29

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Fast Fourier Transform2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 828030060090012001500SE +/- 7.36, N = 4SE +/- 4.68, N = 4SE +/- 5.82, N = 41623.591621.841391.57
OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Fast Fourier Transform2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 828030060090012001500Min: 1605.38 / Avg: 1623.59 / Max: 1637.02Min: 1614.29 / Avg: 1621.84 / Max: 1635.48Min: 1382.67 / Avg: 1391.57 / Max: 1408.35

Phoronix Test Suite Self Test

This is a wrapper around the phoronix-test-suite debug-self-test sub-command for testing hot Phoronix Test Suite code paths and if wanting to compare different PHP implementations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Render Test2 x Xeon Platinum 82802 x EPYC 75021632486480SE +/- 0.37, N = 2SE +/- 0.25, N = 259.8069.67
OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Render Test2 x Xeon Platinum 82802 x EPYC 75021326395265Min: 59.43 / Avg: 59.8 / Max: 60.18Min: 69.43 / Avg: 69.67 / Max: 69.92

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Twofish - Encrypt2 x Xeon Platinum 82802 x EPYC 750280160240320400SE +/- 0.20, N = 3SE +/- 0.14, N = 3347.48298.821. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Twofish - Encrypt2 x Xeon Platinum 82802 x EPYC 750260120180240300Min: 347.08 / Avg: 347.48 / Max: 347.73Min: 298.58 / Avg: 298.82 / Max: 299.041. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-HPL2 x EPYC 75022 x Xeon Platinum 82804080120160200SE +/- 0.06, N = 3SE +/- 0.03, N = 3169.92146.451. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-HPL2 x EPYC 75022 x Xeon Platinum 8280306090120150Min: 169.84 / Avg: 169.92 / Max: 170.04Min: 146.4 / Avg: 146.45 / Max: 146.511. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: KASUMI - Decrypt2 x Xeon Platinum 82802 x EPYC 750220406080100SE +/- 0.02, N = 3SE +/- 0.03, N = 387.0375.241. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: KASUMI - Decrypt2 x Xeon Platinum 82802 x EPYC 750220406080100Min: 87.01 / Avg: 87.03 / Max: 87.06Min: 75.18 / Avg: 75.24 / Max: 75.271. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGUP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Random Access2 x EPYC 75022 x Xeon Platinum 82800.04550.0910.13650.1820.2275SE +/- 0.00214, N = 3SE +/- 0.00165, N = 30.202330.175401. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGUP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Random Access2 x EPYC 75022 x Xeon Platinum 828012345Min: 0.2 / Avg: 0.2 / Max: 0.2Min: 0.17 / Avg: 0.18 / Max: 0.181. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

Apache Siege

This is a test of the Apache web server performance being facilitated by the Siege web serverb enchmark program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 2502 x Xeon Platinum 82802 x EPYC 75027K14K21K28K35KSE +/- 126.68, N = 3SE +/- 98.88, N = 334607.8030036.701. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 2502 x Xeon Platinum 82802 x EPYC 75026K12K18K24K30KMin: 34354.82 / Avg: 34607.8 / Max: 34746.35Min: 29840.06 / Avg: 30036.7 / Max: 30153.181. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: KASUMI - Encrypt2 x Xeon Platinum 82802 x EPYC 750220406080100SE +/- 0.06, N = 3SE +/- 0.04, N = 389.6377.841. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: KASUMI - Encrypt2 x Xeon Platinum 82802 x EPYC 750220406080100Min: 89.57 / Avg: 89.63 / Max: 89.74Min: 77.77 / Avg: 77.84 / Max: 77.881. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Pabellon Barcelona - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 8280306090120150102.35117.41

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Memory Copying2 x Xeon Platinum 82802 x EPYC 75022K4K6K8K10KSE +/- 108.22, N = 3SE +/- 100.69, N = 311263.489822.811. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Memory Copying2 x Xeon Platinum 82802 x EPYC 75022K4K6K8K10KMin: 11048.82 / Avg: 11263.48 / Max: 11394.76Min: 9665.52 / Avg: 9822.81 / Max: 10010.371. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Mencoder

This test uses mplayer's mencoder utility and the libavcodec family for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMencoder 1.3.0AVI To LAVC2 x Xeon Platinum 82802 x EPYC 7502510152025SE +/- 0.03, N = 3SE +/- 0.01, N = 317.6920.201. (CC) gcc options: -ffast-math -fpie -pie -lncurses -lrt -lpng -lz -ljpeg -lasound -ldl -lpthread -lbz2 -lmad -lvorbisenc -lvorbis -logg -rdynamic -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterMencoder 1.3.0AVI To LAVC2 x Xeon Platinum 82802 x EPYC 7502510152025Min: 17.62 / Avg: 17.69 / Max: 17.73Min: 20.19 / Avg: 20.2 / Max: 20.211. (CC) gcc options: -ffast-math -fpie -pie -lncurses -lrt -lpng -lz -ljpeg -lasound -ldl -lpthread -lbz2 -lmad -lvorbisenc -lvorbis -logg -rdynamic -lm

Botan

Botan is a cross-platform open-source C++ crypto library that supports most all publicly known cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: CAST-256 - Decrypt2 x Xeon Platinum 82802 x EPYC 7502306090120150SE +/- 0.01, N = 3SE +/- 0.03, N = 3137.30120.281. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: CAST-256 - Decrypt2 x Xeon Platinum 82802 x EPYC 7502306090120150Min: 137.28 / Avg: 137.3 / Max: 137.33Min: 120.22 / Avg: 120.28 / Max: 120.321. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: CAST-256 - Encrypt2 x Xeon Platinum 82802 x EPYC 7502306090120150SE +/- 0.57, N = 3SE +/- 0.07, N = 3136.52120.171. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: CAST-256 - Encrypt2 x Xeon Platinum 82802 x EPYC 7502306090120150Min: 135.39 / Avg: 136.52 / Max: 137.11Min: 120.04 / Avg: 120.17 / Max: 120.271. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

SPECjbb 2015

This is a benchmark of SPECjbb 2015. For this test profile to work, you must have a valid license/copy of the SPECjbb 2015 ISO (SPECjbb2015-1.02.iso) in your Phoronix Test Suite download cache. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite max-jOPS2 x EPYC 75022 x Xeon Platinum 828020K40K60K80K100K10664593995

GNU GMP GMPbench

GMPbench is a test of the GMP 6.1.2 math library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.1.2Total Time2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 7502110022003300440055005098.404588.704519.001. (CC) gcc options: -O3 -fomit-frame-pointer -lm

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Masskrug - Acceleration: CPU-only2 x EPYC 75022 x Xeon Platinum 82801.07332.14663.21994.29325.3665SE +/- 0.02, N = 3SE +/- 0.02, N = 34.244.77
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Masskrug - Acceleration: CPU-only2 x EPYC 75022 x Xeon Platinum 8280246810Min: 4.21 / Avg: 4.24 / Max: 4.29Min: 4.74 / Avg: 4.77 / Max: 4.8

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney Material2 x EPYC 75022 x Xeon Platinum 8280153045607559.8067.24

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: EP-DGEMM2 x Xeon Platinum 82802 x EPYC 7502612182430SE +/- 0.05, N = 3SE +/- 0.12, N = 325.1722.391. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: EP-DGEMM2 x Xeon Platinum 82802 x EPYC 7502612182430Min: 25.1 / Avg: 25.17 / Max: 25.28Min: 22.27 / Avg: 22.39 / Max: 22.631. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 40962 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828011002200330044005500SE +/- 10.42, N = 3SE +/- 2.50, N = 3SE +/- 31.33, N = 35213.905115.504640.201. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 40962 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82809001800270036004500Min: 5193.9 / Avg: 5213.9 / Max: 5229Min: 5112.8 / Avg: 5115.5 / Max: 5120.5Min: 4582 / Avg: 4640.2 / Max: 4689.41. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Primesieve

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

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number Generation2 x EPYC 75022 x Xeon Platinum 82801.08452.1693.25354.3385.4225SE +/- 0.05, N = 3SE +/- 0.01, N = 34.294.821. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number Generation2 x EPYC 75022 x Xeon Platinum 8280246810Min: 4.24 / Avg: 4.29 / Max: 4.39Min: 4.81 / Avg: 4.82 / Max: 4.841. (CXX) g++ options: -O3 -lpthread

POV-Ray

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

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time2 x EPYC 75022 x Xeon Platinum 82803691215SE +/- 0.04, N = 3SE +/- 0.12, N = 310.3211.57-lSDL1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lXpm -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time2 x EPYC 75022 x Xeon Platinum 82803691215Min: 10.25 / Avg: 10.32 / Max: 10.39Min: 11.42 / Avg: 11.57 / Max: 11.81. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lXpm -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: Compression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750250100150200250SE +/- 0.33, N = 3SE +/- 1.00, N = 32131911901. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: Compression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75024080120160200Min: 212 / Avg: 212.67 / Max: 213Min: 189 / Avg: 191 / Max: 1921. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

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 6.0.1Time To Compile2 x EPYC 75022 x Xeon Platinum 82802040608010096.43107.93

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Dense LU Matrix Factorization2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828011002200330044005500SE +/- 9.32, N = 4SE +/- 9.37, N = 4SE +/- 15.06, N = 45364.165269.704793.41
OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Dense LU Matrix Factorization2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82809001800270036004500Min: 5338.55 / Avg: 5364.16 / Max: 5377.97Min: 5248.76 / Avg: 5269.7 / Max: 5291.99Min: 4751.05 / Avg: 4793.41 / Max: 4815.99

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Pabellon Barcelona - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 8280306090120150SE +/- 0.37, N = 3SE +/- 0.09, N = 3100.13112.00
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Pabellon Barcelona - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 828020406080100Min: 99.53 / Avg: 100.13 / Max: 100.8Min: 111.87 / Avg: 112 / Max: 112.16

libjpeg-turbo tjbench

tjbench is a JPEG decompression/compression benchmark part of libjpeg-turbo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression Throughput2 x Xeon Platinum 82802 x EPYC 75024080120160200SE +/- 0.48, N = 3SE +/- 0.07, N = 3188.49168.831. (CC) gcc options: -O3 -rdynamic
OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression Throughput2 x Xeon Platinum 82802 x EPYC 7502306090120150Min: 187.57 / Avg: 188.49 / Max: 189.18Min: 168.71 / Avg: 168.83 / Max: 168.961. (CC) gcc options: -O3 -rdynamic

Ogg Encoding

This test times how long it takes to encode a sample WAV file to Ogg format using vorbis-tools, libvorbis, and libogg. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.3WAV To Ogg2 x Xeon Platinum 82802 x EPYC 7502246810SE +/- 0.00, N = 3SE +/- 0.02, N = 36.126.811. (CC) gcc options: -O2 -ffast-math -fsigned-char -logg
OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.3WAV To Ogg2 x Xeon Platinum 82802 x EPYC 75023691215Min: 6.11 / Avg: 6.12 / Max: 6.13Min: 6.79 / Avg: 6.81 / Max: 6.841. (CC) gcc options: -O2 -ffast-math -fsigned-char -logg

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Emily2 x Xeon Platinum 82802 x EPYC 75024080120160200155.24172.66

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 Second2 x EPYC 75022 x Xeon Platinum 8280500K1000K1500K2000K2500KSE +/- 6421.46, N = 3SE +/- 20125.94, N = 32101299.251890648.691. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second2 x EPYC 75022 x Xeon Platinum 8280400K800K1200K1600K2000KMin: 2089113.76 / Avg: 2101299.25 / Max: 2110904.97Min: 1850398.58 / Avg: 1890648.69 / Max: 1911099.741. (CC) gcc options: -O2 -lrt" -lrt

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Composite2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82805001000150020002500SE +/- 1.16, N = 4SE +/- 2.65, N = 4SE +/- 4.49, N = 42423.282388.932181.97
OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Composite2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 8280400800120016002000Min: 2421.24 / Avg: 2423.28 / Max: 2425.55Min: 2381.38 / Avg: 2388.93 / Max: 2393.83Min: 2172.13 / Avg: 2181.97 / Max: 2193.46

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 40962 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82804K8K12K16K20KSE +/- 63.98, N = 3SE +/- 214.67, N = 3SE +/- 82.58, N = 31786517004160991. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 40962 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82803K6K9K12K15KMin: 17788 / Avg: 17865 / Max: 17992Min: 16743 / Avg: 17004.33 / Max: 17430Min: 15958 / Avg: 16099.33 / Max: 162441. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 642 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 3.05, N = 3SE +/- 0.58, N = 3SE +/- 5.52, N = 38203.208081.507403.901. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 642 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828014002800420056007000Min: 8197.3 / Avg: 8203.2 / Max: 8207.5Min: 8080.5 / Avg: 8081.5 / Max: 8082.5Min: 7393 / Avg: 7403.9 / Max: 7410.91. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP32 x Xeon Platinum 82802 x EPYC 7502816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 329.9733.171. (CC) gcc options: -lncurses -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP32 x Xeon Platinum 82802 x EPYC 7502714212835Min: 29.95 / Avg: 29.97 / Max: 30Min: 33.16 / Avg: 33.17 / Max: 33.191. (CC) gcc options: -lncurses -lm

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Files2 x Xeon Platinum 82802 x EPYC 750248121620SE +/- 0.04, N = 3SE +/- 0.03, N = 313.7715.231. (CC) gcc options: -lm
OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Files2 x Xeon Platinum 82802 x EPYC 750248121620Min: 13.71 / Avg: 13.77 / Max: 13.83Min: 15.18 / Avg: 15.23 / Max: 15.271. (CC) gcc options: -lm

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 5122 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75022K4K6K8K10KSE +/- 9.12, N = 3SE +/- 15.02, N = 3SE +/- 10.19, N = 37792.677123.537052.331. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 5122 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750214002800420056007000Min: 7783.2 / Avg: 7792.67 / Max: 7810.9Min: 7093.5 / Avg: 7123.53 / Max: 7139.1Min: 7032.7 / Avg: 7052.33 / Max: 7066.91. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations2 x Xeon Platinum 82802 x EPYC 750220406080100SE +/- 0.15, N = 3SE +/- 0.23, N = 387.5796.591. (CC) gcc options: -lm
OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations2 x Xeon Platinum 82802 x EPYC 750220406080100Min: 87.39 / Avg: 87.57 / Max: 87.86Min: 96.22 / Avg: 96.59 / Max: 97.011. (CC) gcc options: -lm

ctx_clock

Ctx_clock is a simple test program to measure the context switch time in clock cycles. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch Time2 x Xeon Platinum 82802 x EPYC 7502306090120150136150

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Classroom - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 8280306090120150SE +/- 0.99, N = 3SE +/- 0.34, N = 3122.64135.02
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Classroom - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 8280306090120150Min: 120.67 / Avg: 122.64 / Max: 123.84Min: 134.49 / Avg: 135.02 / Max: 135.65

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1282 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750216003200480064008000SE +/- 108.79, N = 3SE +/- 15.81, N = 3SE +/- 40.50, N = 37470.236947.806787.601. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1282 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750213002600390052006500Min: 7343 / Avg: 7470.23 / Max: 7686.7Min: 6925.9 / Avg: 6947.8 / Max: 6978.5Min: 6714.3 / Avg: 6787.6 / Max: 6854.11. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 642 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82808K16K24K32K40KSE +/- 22.10, N = 3SE +/- 327.91, N = 3SE +/- 124.46, N = 33701135897336481. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 642 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KMin: 36976 / Avg: 37011.33 / Max: 37052Min: 35264 / Avg: 35897 / Max: 36362Min: 33479 / Avg: 33648.33 / Max: 338911. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test2 x EPYC 75022 x Xeon Platinum 828050K100K150K200K250KSE +/- 3053.66, N = 3SE +/- 924.31, N = 32554922326261. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test2 x EPYC 75022 x Xeon Platinum 828040K80K120K160K200KMin: 249385 / Avg: 255492 / Max: 258599Min: 231004 / Avg: 232626.33 / Max: 2342051. (CXX) g++ options: -pipe -lpthread

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Fishy Cat - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 828020406080100SE +/- 0.10, N = 3SE +/- 0.04, N = 370.1676.82
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Fishy Cat - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 82801530456075Min: 70 / Avg: 70.16 / Max: 70.35Min: 76.74 / Avg: 76.82 / Max: 76.86

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc C String Functions2 x EPYC 75022 x Xeon Platinum 82801.1M2.2M3.3M4.4M5.5MSE +/- 54834.48, N = 6SE +/- 25939.97, N = 34908942.294483652.601. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc C String Functions2 x EPYC 75022 x Xeon Platinum 8280900K1800K2700K3600K4500KMin: 4700026.29 / Avg: 4908942.29 / Max: 5105907.38Min: 4435843.07 / Avg: 4483652.6 / Max: 4525002.51. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: Decompression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 7502204060801009588871. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Fishy Cat - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 8280163248648066.5272.54

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: rotate2 x EPYC 75022 x Xeon Platinum 828048121620SE +/- 0.02, N = 3SE +/- 0.03, N = 316.7518.25
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: rotate2 x EPYC 75022 x Xeon Platinum 8280510152025Min: 16.71 / Avg: 16.75 / Max: 16.78Min: 18.2 / Avg: 18.25 / Max: 18.29

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: EP.C2 x Xeon Platinum 82802 x EPYC 75025001000150020002500SE +/- 22.95, N = 3SE +/- 1.59, N = 32486.052283.031. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: EP.C2 x Xeon Platinum 82802 x EPYC 7502400800120016002000Min: 2443.13 / Avg: 2486.05 / Max: 2521.62Min: 2280.57 / Avg: 2283.03 / Max: 2286.011. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Timed ImageMagick Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compile2 x Xeon Platinum 82802 x EPYC 7502510152025SE +/- 0.21, N = 3SE +/- 0.36, N = 319.6721.39
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compile2 x Xeon Platinum 82802 x EPYC 7502510152025Min: 19.28 / Avg: 19.67 / Max: 19.98Min: 20.92 / Avg: 21.39 / Max: 22.09

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: unsharp-mask2 x Xeon Platinum 82802 x EPYC 7502714212835SE +/- 0.38, N = 3SE +/- 0.11, N = 328.1830.60
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: unsharp-mask2 x Xeon Platinum 82802 x EPYC 7502714212835Min: 27.68 / Avg: 28.18 / Max: 28.93Min: 30.41 / Avg: 30.6 / Max: 30.78

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 40962 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750216003200480064008000SE +/- 20.22, N = 3SE +/- 13.44, N = 3SE +/- 9.28, N = 37273.776814.276709.271. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 40962 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750213002600390052006500Min: 7234.1 / Avg: 7273.77 / Max: 7300.4Min: 6799.4 / Avg: 6814.27 / Max: 6841.1Min: 6692 / Avg: 6709.27 / Max: 6723.81. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: BMW27 - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 82801224364860SE +/- 0.21, N = 3SE +/- 0.05, N = 347.3251.15
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: BMW27 - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 82801020304050Min: 46.99 / Avg: 47.32 / Max: 47.71Min: 51.06 / Avg: 51.15 / Max: 51.24

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Write2 x Xeon Platinum 82802 x EPYC 75025K10K15K20K25KSE +/- 98.31, N = 3SE +/- 151.66, N = 323702.9621936.241. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Write2 x Xeon Platinum 82802 x EPYC 75024K8K12K16K20KMin: 23521.26 / Avg: 23702.96 / Max: 23858.89Min: 21652.57 / Avg: 21936.24 / Max: 22171.11. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: auto-levels2 x Xeon Platinum 82802 x EPYC 7502612182430SE +/- 0.08, N = 3SE +/- 0.29, N = 622.7924.62
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: auto-levels2 x Xeon Platinum 82802 x EPYC 7502612182430Min: 22.65 / Avg: 22.79 / Max: 22.93Min: 23.6 / Avg: 24.62 / Max: 25.48

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Vector Math2 x EPYC 75022 x Xeon Platinum 828030K60K90K120K150KSE +/- 244.96, N = 3SE +/- 433.67, N = 3130504.95120956.951. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Vector Math2 x EPYC 75022 x Xeon Platinum 828020K40K60K80K100KMin: 130055.9 / Avg: 130504.95 / Max: 130899.13Min: 120111.84 / Avg: 120956.95 / Max: 121548.481. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 20482 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750216003200480064008000SE +/- 56.60, N = 3SE +/- 0.67, N = 3SE +/- 15.82, N = 37392.007006.206858.401. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 20482 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750213002600390052006500Min: 7287.3 / Avg: 7392 / Max: 7481.6Min: 7004.9 / Avg: 7006.2 / Max: 7007.1Min: 6840 / Avg: 6858.4 / Max: 6889.91. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time2 x EPYC 75022 x Xeon Platinum 828030M60M90M120M150MSE +/- 810846.41, N = 3SE +/- 879556.81, N = 31352237101259475051. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time2 x EPYC 75022 x Xeon Platinum 828020M40M60M80M100MMin: 134387085 / Avg: 135223710.33 / Max: 136845127Min: 124708632 / Avg: 125947505 / Max: 1276484941. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Only2 x EPYC 75022 x Xeon Platinum 82804K8K12K16K20KSE +/- 102.32, N = 3SE +/- 48.37, N = 320388.1119015.961. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Only2 x EPYC 75022 x Xeon Platinum 82804K8K12K16K20KMin: 20250.16 / Avg: 20388.11 / Max: 20588Min: 18955.91 / Avg: 19015.96 / Max: 19111.681. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: EP-STREAM Triad2 x Xeon Platinum 82802 x EPYC 75020.67561.35122.02682.70243.378SE +/- 0.00024, N = 3SE +/- 0.00633, N = 33.002692.802071. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: EP-STREAM Triad2 x Xeon Platinum 82802 x EPYC 7502246810Min: 3 / Avg: 3 / Max: 3Min: 2.79 / Avg: 2.8 / Max: 2.811. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: resize2 x EPYC 75022 x Xeon Platinum 82803691215SE +/- 0.03, N = 3SE +/- 0.03, N = 311.6712.48
OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: resize2 x EPYC 75022 x Xeon Platinum 828048121620Min: 11.63 / Avg: 11.67 / Max: 11.72Min: 12.42 / Avg: 12.48 / Max: 12.53

Tesseract OCR

Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.0.0Time To OCR 7 Images2 x Xeon Platinum 82802 x EPYC 7502816243240SE +/- 0.03, N = 3SE +/- 0.20, N = 332.7934.90
OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.0.0Time To OCR 7 Images2 x Xeon Platinum 82802 x EPYC 7502714212835Min: 32.74 / Avg: 32.79 / Max: 32.83Min: 34.54 / Avg: 34.9 / Max: 35.23

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Lsearch2 x EPYC 75022 x Xeon Platinum 8280150300450600750SE +/- 1.35, N = 3SE +/- 1.81, N = 3708.05665.351. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Lsearch2 x EPYC 75022 x Xeon Platinum 8280120240360480600Min: 706.2 / Avg: 708.05 / Max: 710.67Min: 662.9 / Avg: 665.35 / Max: 668.871. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Only2 x Xeon Platinum 82802 x EPYC 7502200K400K600K800K1000KSE +/- 3679.97, N = 3SE +/- 8471.64, N = 3912805.52858391.761. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Only2 x Xeon Platinum 82802 x EPYC 7502160K320K480K640K800KMin: 908347.84 / Avg: 912805.52 / Max: 920106.18Min: 841914.85 / Avg: 858391.76 / Max: 870049.21. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CPU Stress2 x EPYC 75022 x Xeon Platinum 82804K8K12K16K20KSE +/- 14.09, N = 3SE +/- 121.24, N = 319072.6417955.131. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CPU Stress2 x EPYC 75022 x Xeon Platinum 82803K6K9K12K15KMin: 19051.75 / Avg: 19072.64 / Max: 19099.47Min: 17803.83 / Avg: 17955.13 / Max: 18194.881. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 10242 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750216003200480064008000SE +/- 81.37, N = 3SE +/- 22.72, N = 3SE +/- 2.19, N = 37554.537207.207128.971. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 10242 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750213002600390052006500Min: 7395.8 / Avg: 7554.53 / Max: 7665Min: 7183 / Avg: 7207.2 / Max: 7252.6Min: 7125.9 / Avg: 7128.97 / Max: 7133.21. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: Compression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 7502801602403204003753603541. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Bsearch2 x Xeon Platinum 82802 x EPYC 75028K16K24K32K40KSE +/- 71.90, N = 3SE +/- 238.75, N = 335115.6933172.621. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Bsearch2 x Xeon Platinum 82802 x EPYC 75026K12K18K24K30KMin: 35004.94 / Avg: 35115.69 / Max: 35250.49Min: 32737.45 / Avg: 33172.62 / Max: 33560.441. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Scala Dotty2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750216003200480064008000SE +/- 55.49, N = 8SE +/- 65.40, N = 40SE +/- 43.69, N = 406929.507276.017326.30
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Scala Dotty2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750213002600390052006500Min: 6672.41 / Avg: 6929.5 / Max: 7103.91Min: 6912.91 / Avg: 7276.01 / Max: 8426.64Min: 6977.66 / Avg: 7326.3 / Max: 8031.3

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 5122 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828014002800420056007000SE +/- 9.03, N = 3SE +/- 3.11, N = 3SE +/- 31.31, N = 36716.706632.836354.601. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 5122 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828012002400360048006000Min: 6699.2 / Avg: 6716.7 / Max: 6729.3Min: 6628.6 / Avg: 6632.83 / Max: 6638.9Min: 6292.7 / Avg: 6354.6 / Max: 6393.81. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2562 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828014002800420056007000SE +/- 18.60, N = 3SE +/- 13.59, N = 3SE +/- 7.72, N = 36744.306614.676386.171. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2562 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828012002400360048006000Min: 6709.3 / Avg: 6744.3 / Max: 6772.7Min: 6587.6 / Avg: 6614.67 / Max: 6630.3Min: 6378.2 / Avg: 6386.17 / Max: 6401.61. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLAC2 x Xeon Platinum 82802 x EPYC 75023691215SE +/- 0.01, N = 5SE +/- 0.02, N = 59.5610.091. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLAC2 x Xeon Platinum 82802 x EPYC 75023691215Min: 9.52 / Avg: 9.56 / Max: 9.57Min: 10.04 / Avg: 10.09 / Max: 10.161. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Jacobi Successive Over-Relaxation2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750230060090012001500SE +/- 6.63, N = 4SE +/- 0.15, N = 4SE +/- 0.00, N = 41585.241528.571506.02
OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Jacobi Successive Over-Relaxation2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750230060090012001500Min: 1578.18 / Avg: 1585.24 / Max: 1605.13Min: 1528.12 / Avg: 1528.57 / Max: 1528.72Min: 1506.02 / Avg: 1506.02 / Max: 1506.02

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.03Mode: CPU2 x Xeon Platinum 82802 x EPYC 750214K28K42K56K70KSE +/- 89.03, N = 3SE +/- 755.94, N = 36547662297
OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.03Mode: CPU2 x Xeon Platinum 82802 x EPYC 750211K22K33K44K55KMin: 65353 / Avg: 65476 / Max: 65649Min: 60839 / Avg: 62296.67 / Max: 63373

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 8280112233445545.2047.45

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: LU.C2 x EPYC 75022 x Xeon Platinum 82807K14K21K28K35KSE +/- 81.55, N = 3SE +/- 34.81, N = 333940.8132373.021. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: LU.C2 x EPYC 75022 x Xeon Platinum 82806K12K18K24K30KMin: 33781.23 / Avg: 33940.81 / Max: 34049.82Min: 32327.84 / Avg: 32373.02 / Max: 32441.471. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x EPYC 75022 x Xeon Platinum 82803K6K9K12K15KSE +/- 40.05, N = 3SE +/- 64.31, N = 314388.4313753.101. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KMin: 14309.4 / Avg: 14388.43 / Max: 14439.2Min: 13670.1 / Avg: 13753.1 / Max: 13879.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: SP.A2 x EPYC 75022 x Xeon Platinum 828090180270360450SE +/- 0.46, N = 3SE +/- 0.55, N = 3396.26379.981. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: SP.A2 x EPYC 75022 x Xeon Platinum 828070140210280350Min: 395.39 / Avg: 396.26 / Max: 396.95Min: 379.07 / Avg: 379.98 / Max: 380.981. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Phoronix Test Suite Self Test

This is a wrapper around the phoronix-test-suite debug-self-test sub-command for testing hot Phoronix Test Suite code paths and if wanting to compare different PHP implementations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: List Suites2 x Xeon Platinum 82802 x EPYC 75020.16650.3330.49950.6660.8325SE +/- 0.00, N = 2SE +/- 0.01, N = 20.710.74
OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: List Suites2 x Xeon Platinum 82802 x EPYC 7502246810Min: 0.71 / Avg: 0.71 / Max: 0.71Min: 0.73 / Avg: 0.74 / Max: 0.75

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Sparse Matrix Multiply2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82805001000150020002500SE +/- 0.56, N = 4SE +/- 1.10, N = 4SE +/- 0.56, N = 42246.312211.492155.57
OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Sparse Matrix Multiply2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 8280400800120016002000Min: 2245.34 / Avg: 2246.31 / Max: 2247.27Min: 2208.46 / Avg: 2211.49 / Max: 2213.12Min: 2154.02 / Avg: 2155.57 / Max: 2156.68

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 10242 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750214002800420056007000SE +/- 33.68, N = 3SE +/- 6.26, N = 3SE +/- 60.11, N = 36339.636146.206098.831. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 10242 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750211002200330044005500Min: 6291 / Avg: 6339.63 / Max: 6404.3Min: 6136.7 / Avg: 6146.2 / Max: 6158Min: 6022.8 / Avg: 6098.83 / Max: 6217.51. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1282 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750215003000450060007500SE +/- 99.21, N = 3SE +/- 55.49, N = 3SE +/- 2.34, N = 37023.806899.006766.471. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1282 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750212002400360048006000Min: 6901.1 / Avg: 7023.8 / Max: 7220.2Min: 6819.7 / Avg: 6899 / Max: 7005.9Min: 6762.5 / Avg: 6766.47 / Max: 6770.61. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: Decompression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75022004006008001000SE +/- 7.88, N = 3SE +/- 0.33, N = 39679619321. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: Decompression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75022004006008001000Min: 951 / Avg: 966.67 / Max: 976Min: 931 / Avg: 931.67 / Max: 9321. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 1282 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82805K10K15K20K25KSE +/- 232.04, N = 7SE +/- 71.04, N = 3SE +/- 316.85, N = 32105920960203431. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 1282 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82804K8K12K16K20KMin: 19684 / Avg: 21058.86 / Max: 21403Min: 20820 / Avg: 20960 / Max: 21051Min: 19750 / Avg: 20343 / Max: 208331. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 642 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828016003200480064008000SE +/- 5.63, N = 3SE +/- 2.64, N = 3SE +/- 55.12, N = 37399.837299.937180.671. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 642 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828013002600390052006500Min: 7388.7 / Avg: 7399.83 / Max: 7406.9Min: 7296.1 / Avg: 7299.93 / Max: 7305Min: 7112.6 / Avg: 7180.67 / Max: 7289.81. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Minion

Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Solitaire2 x EPYC 75022 x Xeon Platinum 828020406080100SE +/- 0.17, N = 3SE +/- 0.48, N = 382.0784.341. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Solitaire2 x EPYC 75022 x Xeon Platinum 82801632486480Min: 81.79 / Avg: 82.07 / Max: 82.36Min: 83.39 / Avg: 84.34 / Max: 84.881. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.7Calculating 500M Pi Digits2 x EPYC 75022 x Xeon Platinum 82803691215SE +/- 0.02, N = 3SE +/- 0.05, N = 38.899.12
OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.7Calculating 500M Pi Digits2 x EPYC 75022 x Xeon Platinum 82803691215Min: 8.87 / Avg: 8.89 / Max: 8.92Min: 9.05 / Avg: 9.12 / Max: 9.22

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: Compression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750280160240320400SE +/- 1.00, N = 3SE +/- 0.67, N = 33913833831. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: Compression2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 750270140210280350Min: 390 / Avg: 391 / Max: 393Min: 382 / Avg: 382.67 / Max: 3841. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Barbershop - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 828050100150200250SE +/- 0.50, N = 3SE +/- 0.08, N = 3236.53240.94
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Barbershop - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 82804080120160200Min: 235.91 / Avg: 236.53 / Max: 237.53Min: 240.79 / Avg: 240.94 / Max: 241.02

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 322 x EPYC 77422 x Xeon Platinum 82802 x EPYC 75022K4K6K8K10KSE +/- 16.76, N = 3SE +/- 69.98, N = 3SE +/- 13.25, N = 38982.478898.438823.931. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 322 x EPYC 77422 x Xeon Platinum 82802 x EPYC 750216003200480064008000Min: 8950.7 / Avg: 8982.47 / Max: 9007.6Min: 8758.6 / Avg: 8898.43 / Max: 8973.7Min: 8803.4 / Avg: 8823.93 / Max: 8848.71. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Matrix Math2 x Xeon Platinum 82802 x EPYC 750280K160K240K320K400KSE +/- 1051.08, N = 3SE +/- 512.79, N = 3380876.39375524.891. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Matrix Math2 x Xeon Platinum 82802 x EPYC 750270K140K210K280K350KMin: 379741.35 / Avg: 380876.39 / Max: 382976.24Min: 374667.69 / Avg: 375524.89 / Max: 376441.091. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2562 x EPYC 77422 x Xeon Platinum 82802 x EPYC 750215003000450060007500SE +/- 14.81, N = 3SE +/- 56.78, N = 3SE +/- 1.71, N = 37216.907199.607126.701. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2562 x EPYC 77422 x Xeon Platinum 82802 x EPYC 750213002600390052006500Min: 7187.6 / Avg: 7216.9 / Max: 7235.3Min: 7088 / Avg: 7199.6 / Max: 7273.6Min: 7124.7 / Avg: 7126.7 / Max: 7130.11. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-Only2 x EPYC 75022 x Xeon Platinum 828050100150200250220.69223.42

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Write2 x EPYC 75022 x Xeon Platinum 82806001200180024003000SE +/- 14.28, N = 3SE +/- 39.04, N = 32688.902656.271. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Write2 x EPYC 75022 x Xeon Platinum 82805001000150020002500Min: 2663.67 / Avg: 2688.9 / Max: 2713.12Min: 2616.76 / Avg: 2656.27 / Max: 2734.331. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Timed PHP Compilation

This test times how long it takes to build PHP 5 with the Zend engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To Compile2 x Xeon Platinum 82802 x EPYC 75021122334455SE +/- 0.17, N = 3SE +/- 0.02, N = 348.5949.141. (CC) gcc options: -O2 -pedantic -ldl -lz -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To Compile2 x Xeon Platinum 82802 x EPYC 75021020304050Min: 48.3 / Avg: 48.59 / Max: 48.89Min: 49.11 / Avg: 49.14 / Max: 49.181. (CC) gcc options: -O2 -pedantic -ldl -lz -lm

Minion

Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Graceful2 x EPYC 75022 x Xeon Platinum 82801224364860SE +/- 0.13, N = 3SE +/- 0.06, N = 352.7853.281. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Graceful2 x EPYC 75022 x Xeon Platinum 82801122334455Min: 52.55 / Avg: 52.78 / Max: 53Min: 53.16 / Avg: 53.28 / Max: 53.381. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

asmFish

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

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth2 x Xeon Platinum 82802 x EPYC 750230M60M90M120M150MSE +/- 1715314.92, N = 3SE +/- 769910.95, N = 3137371669136257996
OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth2 x Xeon Platinum 82802 x EPYC 750220M40M60M80M100MMin: 133984938 / Avg: 137371669 / Max: 139538802Min: 134755480 / Avg: 136257995.67 / Max: 137301013

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: BT.A2 x EPYC 75022 x Xeon Platinum 82802004006008001000SE +/- 0.50, N = 3SE +/- 1.67, N = 3834.43834.301. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: BT.A2 x EPYC 75022 x Xeon Platinum 8280150300450600750Min: 833.71 / Avg: 834.43 / Max: 835.38Min: 832.29 / Avg: 834.3 / Max: 837.621. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Phoronix Test Suite Self Test

This is a wrapper around the phoronix-test-suite debug-self-test sub-command for testing hot Phoronix Test Suite code paths and if wanting to compare different PHP implementations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Peak Memory Usage2 x EPYC 75022 x Xeon Platinum 8280110220330440550SE +/- 0.00, N = 2SE +/- 0.00, N = 2502.55502.55
OpenBenchmarking.orgMB, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Peak Memory Usage2 x EPYC 75022 x Xeon Platinum 828090180270360450Min: 502.55 / Avg: 502.55 / Max: 502.55Min: 502.55 / Avg: 502.55 / Max: 502.55

FFTE

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

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 6.0Test: N=256, 1D Complex FFT Routine2 x EPYC 750216003200480064008000SE +/- 1.52, N = 37639.451. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Sunflow Rendering System

This test runs benchmarks of the Sunflow Rendering System. The Sunflow Rendering System is an open-source render engine for photo-realistic image synthesis with a ray-tracing core. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image Synthesis2 x EPYC 75022 x Xeon Platinum 82800.19350.3870.58050.7740.9675SE +/- 0.01, N = 15SE +/- 0.01, N = 30.740.86
OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image Synthesis2 x EPYC 75022 x Xeon Platinum 8280246810Min: 0.66 / Avg: 0.74 / Max: 0.81Min: 0.84 / Avg: 0.86 / Max: 0.88

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Delete2 x Xeon Platinum 82802 x EPYC 750220K40K60K80K100KSE +/- 309.68, N = 3SE +/- 799.81, N = 15113028.6340802.731. (CC) gcc options: -O2 -lm -rdynamic
OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Delete2 x Xeon Platinum 82802 x EPYC 750220K40K60K80K100KMin: 112420.9 / Avg: 113028.63 / Max: 113435.9Min: 38323.2 / Avg: 40802.73 / Max: 51711.91. (CC) gcc options: -O2 -lm -rdynamic

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context Switching2 x EPYC 75022 x Xeon Platinum 828013M26M39M52M65MSE +/- 2793972.74, N = 13SE +/- 1626045.16, N = 1562075360.4026550213.141. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context Switching2 x EPYC 75022 x Xeon Platinum 828011M22M33M44M55MMin: 34730319.12 / Avg: 62075360.4 / Max: 72527232.52Min: 18415302.13 / Avg: 26550213.14 / Max: 41424261.531. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SET2 x Xeon Platinum 82802 x EPYC 7502400K800K1200K1600K2000KSE +/- 21457.62, N = 3SE +/- 28243.18, N = 151752859.751463245.891. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SET2 x Xeon Platinum 82802 x EPYC 7502300K600K900K1200K1500KMin: 1718213 / Avg: 1752859.75 / Max: 1792114.62Min: 1345895.12 / Avg: 1463245.89 / Max: 1683501.751. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GET2 x Xeon Platinum 82802 x EPYC 7502500K1000K1500K2000K2500KSE +/- 30997.57, N = 15SE +/- 43798.91, N = 152299348.831897043.391. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GET2 x Xeon Platinum 82802 x EPYC 7502400K800K1200K1600K2000KMin: 2083333.38 / Avg: 2299348.83 / Max: 2531645.5Min: 1666666.62 / Avg: 1897043.39 / Max: 2309468.751. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSH2 x Xeon Platinum 82802 x EPYC 7502400K800K1200K1600K2000KSE +/- 18930.27, N = 15SE +/- 26034.52, N = 151656464.101375852.721. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSH2 x Xeon Platinum 82802 x EPYC 7502300K600K900K1200K1500KMin: 1529052 / Avg: 1656464.1 / Max: 1776198.88Min: 1210653.75 / Avg: 1375852.72 / Max: 14970061. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPOP2 x Xeon Platinum 82802 x EPYC 7502500K1000K1500K2000K2500KSE +/- 23924.88, N = 15SE +/- 80051.04, N = 152475213.882170359.021. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPOP2 x Xeon Platinum 82802 x EPYC 7502400K800K1200K1600K2000KMin: 2347417.75 / Avg: 2475213.88 / Max: 2624671.75Min: 1644736.88 / Avg: 2170359.02 / Max: 2597402.751. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Room - Acceleration: CPU-only2 x Xeon Platinum 82802 x EPYC 75020.68181.36362.04542.72723.409SE +/- 0.02, N = 15SE +/- 0.17, N = 151.923.03
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Room - Acceleration: CPU-only2 x Xeon Platinum 82802 x EPYC 7502246810Min: 1.79 / Avg: 1.92 / Max: 2.07Min: 2.05 / Avg: 3.03 / Max: 4.19

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Rack - Acceleration: CPU-only2 x Xeon Platinum 82802 x EPYC 75020.02480.04960.07440.09920.124SE +/- 0.01, N = 12SE +/- 0.01, N = 120.100.11
OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Rack - Acceleration: CPU-only2 x Xeon Platinum 82802 x EPYC 750212345Min: 0.08 / Avg: 0.1 / Max: 0.17Min: 0.09 / Avg: 0.11 / Max: 0.14

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To Compile2 x EPYC 75022 x Xeon Platinum 8280510152025SE +/- 0.25, N = 15SE +/- 0.35, N = 1419.7421.45
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To Compile2 x EPYC 75022 x Xeon Platinum 8280510152025Min: 19.17 / Avg: 19.74 / Max: 23.25Min: 20.95 / Avg: 21.45 / Max: 26

MKL-DNN

This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: f322 x Xeon Platinum 82802 x EPYC 75029001800270036004500SE +/- 6.16, N = 3SE +/- 89.09, N = 91055.124229.49MIN: 961.28MIN: 3301.921. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: f322 x Xeon Platinum 82802 x EPYC 75027001400210028003500Min: 1043.18 / Avg: 1055.12 / Max: 1063.74Min: 4013.03 / Avg: 4229.49 / Max: 4773.941. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: f322 x Xeon Platinum 82802 x EPYC 75020.82581.65162.47743.30324.129SE +/- 0.01, N = 3SE +/- 0.10, N = 153.303.67MIN: 3.16MIN: 2.931. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: f322 x Xeon Platinum 82802 x EPYC 7502246810Min: 3.29 / Avg: 3.3 / Max: 3.31Min: 3.15 / Avg: 3.67 / Max: 4.131. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl

Renaissance

Renaissance is a suite of benchmarks designed to test the Java JVM from Apache Spark to a Twitter-like service to Scala and other features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Akka Unbalanced Cobwebbed Tree2 x Xeon Platinum 82802 x EPYC 75026K12K18K24K30KSE +/- 482.12, N = 32SE +/- 268.51, N = 3224372.7230303.94
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Akka Unbalanced Cobwebbed Tree2 x Xeon Platinum 82802 x EPYC 75025K10K15K20K25KMin: 22292.31 / Avg: 24372.72 / Max: 36746.71Min: 26838.02 / Avg: 30303.94 / Max: 34648.42

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark PageRank2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75025K10K15K20K25KSE +/- 200.36, N = 8SE +/- 224.85, N = 40SE +/- 294.87, N = 3223691.4524411.7924726.30
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark PageRank2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75024K8K12K16K20KMin: 22798.7 / Avg: 23691.45 / Max: 24553.03Min: 22860.71 / Avg: 24411.79 / Max: 29308Min: 22342.3 / Avg: 24726.3 / Max: 29218.88

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Savina Reactors.IO2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77427K14K21K28K35KSE +/- 297.31, N = 40SE +/- 733.25, N = 40SE +/- 831.26, N = 4026058.0528404.3031114.63
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Savina Reactors.IO2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77425K10K15K20K25KMin: 21959.43 / Avg: 26058.05 / Max: 31545.87Min: 19855.21 / Avg: 28404.3 / Max: 40936.68Min: 21252.49 / Avg: 31114.63 / Max: 48647.67

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark Bayes2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77429001800270036004500SE +/- 49.08, N = 32SE +/- 42.13, N = 40SE +/- 69.40, N = 403282.553594.624126.18
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark Bayes2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77427001400210028003500Min: 2863.05 / Avg: 3282.55 / Max: 4026.15Min: 3196.37 / Avg: 3594.62 / Max: 4172.98Min: 3345.28 / Avg: 4126.18 / Max: 5110.83

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark ALS2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828011K22K33K44K55KSE +/- 1216.19, N = 40SE +/- 351.03, N = 40SE +/- 325.62, N = 4037538.9638777.9649161.18
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark ALS2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82809K18K27K36K45KMin: 29842.42 / Avg: 37538.96 / Max: 58512.5Min: 36313.25 / Avg: 38777.96 / Max: 45299.09Min: 43714.31 / Avg: 49161.18 / Max: 52376.33

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence Alignment2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82801.1612.3223.4834.6445.805SE +/- 0.10, N = 15SE +/- 0.03, N = 15SE +/- 0.07, N = 33.413.425.161. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence Alignment2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 8280246810Min: 2.62 / Avg: 3.41 / Max: 4.19Min: 3.17 / Avg: 3.42 / Max: 3.53Min: 5.03 / Avg: 5.16 / Max: 5.271. (CC) gcc options: -std=c99 -O3 -lm -lpthread

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 2562 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77428K16K24K32K40KSE +/- 722.12, N = 15SE +/- 470.01, N = 3SE +/- 247.84, N = 33670427950278601. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 2562 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77426K12K18K24K30KMin: 32005 / Avg: 36704.2 / Max: 41935Min: 27251 / Avg: 27950.33 / Max: 28844Min: 27528 / Avg: 27860.33 / Max: 283451. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 642 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77424K8K12K16K20KSE +/- 219.94, N = 13SE +/- 26.96, N = 3SE +/- 401.12, N = 151698416447160321. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 642 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77423K6K9K12K15KMin: 14519 / Avg: 16984 / Max: 17457Min: 16394 / Avg: 16446.67 / Max: 16483Min: 11999 / Avg: 16032.13 / Max: 167721. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 322 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82802K4K6K8K10KSE +/- 0.23, N = 3SE +/- 2.81, N = 3SE +/- 358.52, N = 158867.978740.577178.601. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 322 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828015003000450060007500Min: 8867.5 / Avg: 8867.97 / Max: 8868.2Min: 8735.2 / Avg: 8740.57 / Max: 8744.7Min: 5904.8 / Avg: 7178.6 / Max: 8848.71. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

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 2.13b1ATPase Simulation - 327,506 Atoms2 x EPYC 77422 x Xeon Platinum 82802 x EPYC 75020.0930.1860.2790.3720.465SE +/- 0.00162, N = 8SE +/- 0.00011, N = 15SE +/- 0.02081, N = 150.265890.359230.41349
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 Atoms2 x EPYC 77422 x Xeon Platinum 82802 x EPYC 750212345Min: 0.26 / Avg: 0.27 / Max: 0.28Min: 0.36 / Avg: 0.36 / Max: 0.36Min: 0.39 / Avg: 0.41 / Max: 0.7

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP Speedup2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77420.09680.19360.29040.38720.484SE +/- 0.00, N = 12SE +/- 0.01, N = 25SE +/- 0.00, N = 50.430.370.231. (CC) gcc options: --openmp -O3 -lm
OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP Speedup2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 774212345Min: 0.41 / Avg: 0.43 / Max: 0.45Min: 0.19 / Avg: 0.37 / Max: 0.45Min: 0.23 / Avg: 0.23 / Max: 0.241. (CC) gcc options: --openmp -O3 -lm

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 3.02 x Xeon Platinum 82802 x EPYC 75022 x EPYC 77420.21150.4230.63450.8461.0575SE +/- 0.01, N = 3SE +/- 0.01, N = 12SE +/- 0.00, N = 30.940.460.35
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.02 x Xeon Platinum 82802 x EPYC 75022 x EPYC 7742246810Min: 0.93 / Avg: 0.94 / Max: 0.95Min: 0.41 / Avg: 0.46 / Max: 0.5Min: 0.35 / Avg: 0.35 / Max: 0.36

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 the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP Streamcluster2 x EPYC 77422 x Xeon Platinum 82802 x EPYC 75023691215SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.38, N = 1510.4311.7913.571. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP Streamcluster2 x EPYC 77422 x Xeon Platinum 82802 x EPYC 750248121620Min: 10.32 / Avg: 10.43 / Max: 10.53Min: 11.78 / Avg: 11.79 / Max: 11.8Min: 11.19 / Avg: 13.57 / Max: 15.871. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMD2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 8280246810SE +/- 0.06, N = 4SE +/- 0.07, N = 15SE +/- 0.12, N = 154.336.116.961. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMD2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 82803691215Min: 4.22 / Avg: 4.33 / Max: 4.51Min: 5.88 / Avg: 6.11 / Max: 6.6Min: 6.63 / Avg: 6.96 / Max: 8.091. (CXX) g++ options: -O2 -lOpenCL

Parboil

The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP Stencil2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 75021.2692.5383.8075.0766.345SE +/- 0.06, N = 15SE +/- 0.01, N = 3SE +/- 0.05, N = 32.604.025.641. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP Stencil2 x Xeon Platinum 82802 x EPYC 77422 x EPYC 7502246810Min: 2.08 / Avg: 2.6 / Max: 2.87Min: 4 / Avg: 4.02 / Max: 4.04Min: 5.53 / Avg: 5.64 / Max: 5.691. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBM2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 7742816243240SE +/- 0.52, N = 15SE +/- 0.29, N = 15SE +/- 0.30, N = 322.4325.0035.971. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBM2 x Xeon Platinum 82802 x EPYC 75022 x EPYC 7742816243240Min: 19.74 / Avg: 22.43 / Max: 26.1Min: 22.55 / Avg: 25 / Max: 26.37Min: 35.61 / Avg: 35.97 / Max: 36.571. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

HPC Challenge

HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ptrans2 x Xeon Platinum 82802 x EPYC 750248121620SE +/- 0.01412, N = 3SE +/- 0.21006, N = 315.018171.368821. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ptrans2 x Xeon Platinum 82802 x EPYC 750248121620Min: 14.99 / Avg: 15.02 / Max: 15.04Min: 1.12 / Avg: 1.37 / Max: 1.791. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

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. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: LU.A2 x EPYC 75022 x Xeon Platinum 82807K14K21K28K35KSE +/- 966.94, N = 12SE +/- 136.93, N = 331119.4630471.201. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: LU.A2 x EPYC 75022 x Xeon Platinum 82805K10K15K20K25KMin: 20809.34 / Avg: 31119.46 / Max: 33900.19Min: 30245.09 / Avg: 30471.2 / Max: 30718.051. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Sockperf

This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under Load2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 8280816243240SE +/- 0.96, N = 25SE +/- 0.38, N = 25SE +/- 1.51, N = 2522.1622.4235.391. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under Load2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 8280816243240Min: 9.53 / Avg: 22.16 / Max: 29.56Min: 19.21 / Avg: 22.42 / Max: 25.07Min: 11.16 / Avg: 35.39 / Max: 44.521. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: Throughput2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 8280100K200K300K400K500KSE +/- 4514.21, N = 5SE +/- 7584.07, N = 25SE +/- 4430.66, N = 94843634541954480191. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: Throughput2 x EPYC 75022 x EPYC 77422 x Xeon Platinum 828080K160K240K320K400KMin: 472781 / Avg: 484363.2 / Max: 494741Min: 394160 / Avg: 454194.6 / Max: 506626Min: 419943 / Avg: 448018.67 / Max: 4649701. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

Stream

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828040K80K120K160K200KSE +/- 713.30, N = 5SE +/- 1387.96, N = 5SE +/- 4249.65, N = 5194680.20164104.50156319.261. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828030K60K90K120K150KMin: 191970 / Avg: 194680.2 / Max: 196175Min: 160568 / Avg: 164104.5 / Max: 168680.2Min: 140524.5 / Avg: 156319.26 / Max: 163165.51. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triad2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828040K80K120K160K200KSE +/- 624.77, N = 5SE +/- 2801.94, N = 5SE +/- 5754.74, N = 5200966.20166118.74154124.581. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triad2 x EPYC 77422 x EPYC 75022 x Xeon Platinum 828030K60K90K120K150KMin: 199120.3 / Avg: 200966.2 / Max: 202909.3Min: 156474.7 / Avg: 166118.74 / Max: 171713Min: 139129.9 / Avg: 154124.58 / Max: 165105.71. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy2 x EPYC 77422 x Xeon Platinum 82802 x EPYC 750240K80K120K160K200KSE +/- 645.18, N = 5SE +/- 4580.61, N = 25SE +/- 1580.30, N = 8185817.54168489.97150788.381. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy2 x EPYC 77422 x Xeon Platinum 82802 x EPYC 750230K60K90K120K150KMin: 184162.6 / Avg: 185817.54 / Max: 188080.1Min: 120264.6 / Avg: 168489.97 / Max: 198365Min: 145229 / Avg: 150788.38 / Max: 1573111. (CC) gcc options: -O3 -march=native -fopenmp

285 Results Shown

MKL-DNN:
  Deconvolution Batch deconv_1d - f32
  Convolution Batch conv_alexnet - u8s8u8s32
  Convolution Batch conv_alexnet - u8s8f32s32
Parboil
MKL-DNN:
  Deconvolution Batch deconv_all - u8s8u8s32
  Deconvolution Batch deconv_1d - u8s8u8s32
  IP Batch All - u8s8f32s32
  IP Batch All - u8s8u8s32
  Deconvolution Batch deconv_1d - u8s8f32s32
  Convolution Batch conv_googlenet_v3 - u8s8u8s32
  Deconvolution Batch deconv_3d - f32
MBW:
  Memory Copy - 8192 MiB
  Memory Copy - 1024 MiB
  Memory Copy - 4096 MiB
  Memory Copy - 512 MiB
MKL-DNN
CP2K Molecular Dynamics
Himeno Benchmark
Memcached mcperf:
  Replace
  Prepend
  Get
  Append
MKL-DNN:
  IP Batch 1D - u8s8f32s32
  IP Batch 1D - u8s8u8s32
  Convolution Batch conv_all - u8s8u8s32
  Convolution Batch conv_all - u8s8f32s32
HPC Challenge:
  G-Ffte:
    GFLOP/s
    GFLOPS
BLAKE2
MBW
Stress-NG
MBW
Memcached mcperf:
  Add
  Set
MBW:
  Memory Copy, Fixed Block Size - 128 MiB
  Memory Copy - 128 MiB
  Memory Copy, Fixed Block Size - 4096 MiB
  Memory Copy, Fixed Block Size - 8192 MiB
Apache Siege
MariaDB
BlogBench
RAMspeed SMP
MariaDB
MKL-DNN
MariaDB
HPC Challenge
OSBench
RAMspeed SMP
MariaDB
MKL-DNN
MariaDB
dav1d
Parboil
MKL-DNN
Stress-NG:
  Tsearch
  Forking
HPC Challenge
MariaDB
DaCapo Benchmark
Stress-NG
HPC Challenge
RAMspeed SMP
SVT-AV1
MariaDB
Appleseed
FFTW
VP9 libvpx Encoding
RAMspeed SMP
Bork File Encrypter
FFTW:
  Float + SSE - 2D FFT Size 1024
  Float + SSE - 1D FFT Size 1024
Stress-NG
FFTW
RAMspeed SMP
Tinymembench
MKL-DNN
TTSIOD 3D Renderer
MKL-DNN
OSBench
NAS Parallel Benchmarks
FFTW
NAS Parallel Benchmarks
BlogBench
FFTW:
  Float + SSE - 1D FFT Size 4096
  Float + SSE - 2D FFT Size 256
OSBench
dav1d
Java SciMark
SVT-VP9
MKL-DNN
Numpy Benchmark
Stress-NG
MKL-DNN
RAMspeed SMP
m-queens
RAMspeed SMP
Sockperf
x265
RAMspeed SMP:
  Copy - Integer
  Scale - Integer
DaCapo Benchmark
C-Ray
Tinymembench
SVT-HEVC
John The Ripper
PHPBench
Apache Siege
PHP Micro Benchmarks
FFTW
Stress-NG
Apache Siege
lzbench
IndigoBench
Phoronix Test Suite Self Test
IndigoBench
DaCapo Benchmark
Renaissance
FFTW
Cython benchmark
Apache Siege
Rodinia
Zstd Compression
x264
Minion
Phoronix Test Suite Self Test
dcraw
MKL-DNN
Darktable
FFTW
Botan
MKL-DNN
TSCP
Botan
FFTW
lzbench
Botan
PHP Micro Benchmarks
Botan
XZ Compression
Timed GCC Compilation
SPECjbb 2015
Stream
Stress-NG
DaCapo Benchmark
Redis
FFTW
lzbench
Phoronix Test Suite Self Test
RAMspeed SMP
Botan
Apache Siege
Blender
Java SciMark
Phoronix Test Suite Self Test
Botan
HPC Challenge
Botan
HPC Challenge
Apache Siege
Botan
Blender
Stress-NG
Mencoder
Botan:
  CAST-256 - Decrypt
  CAST-256 - Encrypt
SPECjbb 2015
GNU GMP GMPbench
Darktable
Appleseed
HPC Challenge
FFTW
Primesieve
POV-Ray
lzbench
Timed LLVM Compilation
Java SciMark
Blender
libjpeg-turbo tjbench
Ogg Encoding
Appleseed
Coremark
Java SciMark
FFTW:
  Float + SSE - 2D FFT Size 4096
  Stock - 1D FFT Size 64
LAME MP3 Encoding
OSBench
FFTW
OSBench
ctx_clock
Blender
FFTW:
  Stock - 2D FFT Size 128
  Float + SSE - 2D FFT Size 64
7-Zip Compression
Blender
Stress-NG
lzbench
Blender
GIMP
NAS Parallel Benchmarks
Timed ImageMagick Compilation
GIMP
FFTW
Blender
PostgreSQL pgbench
GIMP
Stress-NG
FFTW
Stockfish
PostgreSQL pgbench
HPC Challenge
GIMP
Tesseract OCR
Stress-NG
PostgreSQL pgbench
Stress-NG
FFTW
lzbench
Stress-NG
Renaissance
FFTW:
  Stock - 2D FFT Size 512
  Stock - 2D FFT Size 256
FLAC Audio Encoding
Java SciMark
Chaos Group V-RAY
Blender
NAS Parallel Benchmarks
OpenSSL
NAS Parallel Benchmarks
Phoronix Test Suite Self Test
Java SciMark
FFTW:
  Stock - 2D FFT Size 1024
  Stock - 1D FFT Size 128
lzbench
FFTW:
  Float + SSE - 1D FFT Size 128
  Stock - 2D FFT Size 64
Minion
Y-Cruncher
lzbench
Blender
FFTW
Stress-NG
FFTW
Blender
PostgreSQL pgbench
Timed PHP Compilation
Minion
asmFish
NAS Parallel Benchmarks
Phoronix Test Suite Self Test
FFTE
Sunflow Rendering System
Memcached mcperf
Stress-NG
Redis:
  SET
  GET
  LPUSH
  LPOP
Darktable:
  Server Room - CPU-only
  Server Rack - CPU-only
Timed Linux Kernel Compilation
MKL-DNN:
  Deconvolution Batch deconv_all - f32
  Convolution Batch conv_3d - f32
Renaissance:
  Akka Unbalanced Cobwebbed Tree
  Apache Spark PageRank
  Savina Reactors.IO
  Apache Spark Bayes
  Apache Spark ALS
Timed MAFFT Alignment
FFTW:
  Float + SSE - 1D FFT Size 256
  Float + SSE - 1D FFT Size 64
  Stock - 1D FFT Size 32
NAMD
CLOMP
High Performance Conjugate Gradient
Rodinia:
  OpenMP Streamcluster
  OpenMP LavaMD
Parboil:
  OpenMP Stencil
  OpenMP LBM
HPC Challenge
NAS Parallel Benchmarks
Sockperf:
  Latency Under Load
  Throughput
Stream:
  Add
  Triad
  Copy

2 x EPYC 7502

Processor: 2 x AMD EPYC 7502 32-Core @ 2.50GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 5 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.2 (LLVM 8.0 128 bits), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1)
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 25 July 2019 20:33 by user phoronix.

2 x EPYC 7742

Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPE21D280GA + 280GB INTEL SSDPED1D280GA + 5 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.3.0-rc1-power (x86_64) 20190728, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Java Notes: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1)
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 28 July 2019 13:01 by user phoronix.

2 x Xeon Platinum 8280

Processor: 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 386048MB, Disk: 280GB INTEL SSDPED1D280GA + 32GB Flash Disk, Graphics: llvmpipe 377GB, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.2, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, OpenGL: 3.3 Mesa 19.0.2 (LLVM 8.0 256 bits), Compiler: GCC 8.3.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave
Java Notes: OpenJDK Runtime Environment (build 11.0.4+11-post-Ubuntu-1ubuntu219.04)
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling

Testing initiated at 11 August 2019 08:29 by user phoronix.