AMD EPYC 7642 2P

2 x AMD EPYC 7642 48-Core testing with a AMD DAYTONA_X (RDY1001C BIOS) and llvmpipe 504GB on Ubuntu 19.10 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1910192-HU-AMDEPYC7668
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 3 Tests
Chess Test Suite 2 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 15 Tests
CPU Massive 20 Tests
Creator Workloads 16 Tests
Database Test Suite 5 Tests
Encoding 8 Tests
Game Development 2 Tests
HPC - High Performance Computing 5 Tests
Common Kernel Benchmarks 5 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 3 Tests
Multi-Core 26 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 4 Tests
Programmer / Developer System Benchmarks 5 Tests
Raytracing 2 Tests
Renderers 6 Tests
Scientific Computing 4 Tests
Server 5 Tests
Server CPU Tests 17 Tests
Single-Threaded 5 Tests
Video Encoding 7 Tests
Common Workstation Benchmarks 2 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

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
EPYC 7642 2P
October 17 2019
  12 Hours, 1 Minute
Linux 5.4 Git
October 18 2019
  12 Hours, 38 Minutes
Invert Hiding All Results Option
  12 Hours, 20 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

EPYC 7642 2P

Processor: 2 x AMD EPYC 7642 48-Core @ 2.30GHz (96 Cores / 192 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Starship/Matisse, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.10, Kernel: 5.3.0-18-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.1 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008, 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --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=auto --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 11.0.5-ea+9-post-Ubuntu-1ubuntu1)
Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1
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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Linux 5.4 Git

Processor: 2 x AMD EPYC 7642 48-Core @ 2.30GHz (96 Cores / 192 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Starship/Matisse, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.10, Kernel: 5.4.0-999-generic (x86_64) 20191017, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.1 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008, 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --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=auto --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 11.0.5-ea+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1
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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

AMD EPYC 7642 2PProcessorMotherboardChipsetMemoryDiskGraphicsNetworkMonitorOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionEPYC 7642 2PLinux 5.4 Git2 x AMD EPYC 7642 48-Core @ 2.30GHz (96 Cores / 192 Threads)AMD DAYTONA_X (RDY1001C BIOS)AMD Starship/Matisse516096MB280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFDllvmpipe 504GB2 x Mellanox MT27710Ubuntu 19.105.3.0-18-generic (x86_64)GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.53.3 Mesa 19.2.1 (LLVM 9.0 128 bits)GCC 9.2.1 20191008ext41920x1080VE2285.4.0-999-generic (x86_64) 20191017OpenBenchmarking.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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --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=auto --with-tune=generic --without-cuda-driver -v Disk Details- NONE / errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: acpi-cpufreq ondemandJava Details- EPYC 7642 2P: OpenJDK Runtime Environment (build 11.0.5-ea+9-post-Ubuntu-1ubuntu1)- Linux 5.4 Git: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Details- Python 2.7.17rc1 + Python 3.7.5rc1Security Details- l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

EPYC 7642 2P vs. Linux 5.4 Git ComparisonPhoronix Test SuiteBaseline+925.4%+925.4%+1850.8%+1850.8%+2776.2%+2776.2%131.2%45.1%34.1%16.7%5.7%5.5%4.1%3.7%3.5%3.4%3.1%3.1%2.8%2.8%2.4%2%2%Reads3701.4%ForkingMixed 1:1112.3%Context Switching91.5%LPOP69.6%Mixed 1:366.1%IP Batch 1D - f3259.3%S.V.M.PNon-ExponentialR.C.a.PIP Batch All - f3211.1%GET10.8%Seq Fill6.7%Buffer Test - Single Thread - Read Write6.2%Rand Fill SyncEnc Mode 4 - 1080pTsearch4.9%R.N.N.T - f32DLSC4%Buffer Test - Normal Load - Read WriteRand ReadD.B.d - f32BMW27 - CPU-Only3.3%V.Q.O - Bosphorus 1080pVMAF Optimized - Bosphorus 1080pElapsed Time3.1%Classroom - CPU-Only3%Read While WritingMemorialSummer Nature 4K2.7%H.2.V.E2.6%CoreMark Size 666 - I.P.SBarbershop - CPU-Only2.3%Socket Activity2.2%LU.C2.1%S.F.P.R2.1%SET2%Read TestEmilyApache CassandraStress-NGApache CassandraStress-NGRedisApache CassandraMKL-DNN DNNLStress-NGTungsten RendererLuxCoreRenderMKL-DNN DNNLRedisFacebook RocksDBPostgreSQL pgbenchFacebook RocksDBSVT-AV1Stress-NGMKL-DNN DNNLLuxCoreRenderPostgreSQL pgbenchFacebook RocksDBMKL-DNN DNNLBlenderSVT-VP9SVT-VP9N-QueensBlenderFacebook RocksDBIntel Open Image Denoisedav1dx264CoremarkBlenderStress-NGNAS Parallel BenchmarksACES DGEMMRedisIORAppleseedEPYC 7642 2PLinux 5.4 Git

AMD EPYC 7642 2Predis: LPOPmkl-dnn: IP Batch 1D - f32stress-ng: System V Message Passingtungsten: Non-Exponentialmkl-dnn: IP Batch All - f32redis: GETrocksdb: Seq Fillrocksdb: Rand Fill Syncsvt-av1: Enc Mode 4 - 1080pstress-ng: Tsearchmkl-dnn: Recurrent Neural Network Training - f32rocksdb: Rand Readblender: BMW27 - CPU-Onlysvt-vp9: Visual Quality Optimized - Bosphorus 1080psvt-vp9: VMAF Optimized - Bosphorus 1080pn-queens: Elapsed Timeblender: Classroom - CPU-Onlyoidn: Memorialdav1d: Summer Nature 4Kx264: H.264 Video Encodingcoremark: CoreMark Size 666 - Iterations Per Secondblender: Barbershop - CPU-Onlystress-ng: Socket Activitynpb: LU.Cmt-dgemm: Sustained Floating-Point Rateredis: SETior: Read Testappleseed: Emilystress-ng: Memory Copyingnpb: SP.Bdav1d: Summer Nature 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pstress-ng: Matrix Mathblender: Pabellon Barcelona - CPU-Onlyembree: Pathtracer ISPC - Asian Dragonospray: San Miguel - Path Tracerospray: NASA Streamlines - SciVisstress-ng: Lsearchmkl-dnn: Deconvolution Batch deconv_1d - f32stress-ng: Semaphoresnpb: MG.Cmrbayes: Primate Phylogeny Analysisbuild-llvm: Time To Compilepgbench: Buffer Test - Normal Load - Read Onlyembree: Pathtracer - Asian Dragonmkl-dnn: Convolution Batch conv_all - f32mkl-dnn: Convolution Batch conv_3d - f32x265: H.265 1080p Video Encodingembree: Pathtracer - Asian Dragon Objc-ray: Total Time - 4K, 16 Rays Per Pixelblender: Fishy Cat - CPU-Onlyoptcarrot: Optimized Benchmarkrocksdb: Rand Filllibgav1: Summer Nature 4Kdav1d: Chimera 1080pstress-ng: Bsearchembree: Pathtracer ISPC - Asian Dragon Objappleseed: Material Testerredis: LPUSHmkl-dnn: Convolution Batch conv_alexnet - f32appleseed: Disney Materialcassandra: Writesnpb: EP.Credis: SADDglibc-bench: sinhpgbench: Buffer Test - Single Thread - Read Onlyvpxenc: vpxenc VP9 1080p Video Encodelibgav1: Chimera 1080pbuild-linux-kernel: Time To Compilepennant: sedovbigembree: Pathtracer - Crownpennant: leblancbignpb: BT.Cnamd: ATPase Simulation - 327,506 Atomslibgav1: Summer Nature 1080psqlite-speedtest: Timed Time - Size 1,000stress-ng: Hsearchstress-ng: Glibc Qsort Data Sortingglibc-bench: exptscp: AI Chess Performanceglibc-bench: pthread_onceglibc-bench: ffsllglibc-bench: costungsten: Water Causticembree: Pathtracer ISPC - Crownstress-ng: Vector Mathglibc-bench: sqrttungsten: Hairdav1d: Chimera 1080p 10-bitencode-mp3: WAV To MP3stress-ng: Cryptoospray: XFrog Forest - Path Tracertungsten: Volumetric Causticglibc-bench: tanhstress-ng: CPU Stressmkl-dnn: Deconvolution Batch deconv_all - f32glibc-bench: log2sudokut: Total Timenpb: FT.Cbuild-gcc: Time To Compilelibgav1: Chimera 1080p 10-bitglibc-bench: sincosmkl-dnn: Convolution Batch conv_googlenet_v3 - f32npb: EP.Dior: Write Testglibc-bench: sinsvt-av1: Enc Mode 8 - 1080pctx-clock: Context Switch Timeglibc-bench: atanhglibc-bench: asinhglibc-bench: modfglibc-bench: ffssvt-av1: Enc Mode 0 - 1080pospray: Magnetic Reconnection - Path Tracerospray: NASA Streamlines - Path Tracerospray: Magnetic Reconnection - SciVisospray: XFrog Forest - SciVisospray: San Miguel - SciVisrocksdb: Read While Writingcassandra: Mixed 1:3cassandra: Mixed 1:1cassandra: Readsstress-ng: Glibc C String Functionsstress-ng: Context Switchingstress-ng: Forkingpgbench: Buffer Test - Single Thread - Read Writepgbench: Buffer Test - Normal Load - Read Writeluxcorerender: Rainbow Colors and Prismluxcorerender: DLSCmkl-dnn: Deconvolution Batch deconv_3d - f32EPYC 7642 2PLinux 5.4 Git2145929.251.8921122449.002.4410.331978766.832672791686449.642800.13666.6235552465229.16249.96299.851.9657.2426.07325.32150.022974027.49149.0130423.84230894.3220.551434092.451853.75175.6012383.11123514.78753.59308.06465311.0485.1055.077.01101.48957.832.821371739.8599614.54107.5193.10901340.2257.18472.704.1547.4650.257.9349.2779.5124753115.57582.3946032.7247.54299.611259232.8859.5459.411842606390.631678729.1410.1020533.90134.3634.0319.75185.8468.62177.25201645.450.3054448.2478.15529090.471041.206.3510095012.312.3155.4523.5864.84195708.792.915.8698.999.3920351.948.904.6013.9728442.232217.917.6316.7079464.67743.4714.8915.9432.066617.271217.8855.13103.7213813.2111.062.922.320.05333.3324.395016.3976.92982172645089682496777365.7180545931.2516624.842288.4617610.430.180.263.011265416.743.0130647604.051.8211.481785900.3825042017828410.172669.96640.6636799210030.12257.69309.032.0258.9426.79316.86146.193044058.43152.5129774.33226057.6220.131405847.781890.73172.2312624.52125854.29739.75313.82473539.5186.5555.986.90100971.982.781352785.79101007.73106.0891.88913157.6657.90478.494.1048.0350.857.8449.8280.3624494615.41576.7346467.6547.94302.041269417.1359.0758.961856596343.741666898.1210.1720674.99135.2834.2619.62187.0768.19178.36202866.240.3072448.5277.71531774.861046.166.3210139582.322.3255.6923.6865.10195037.072.925.8498.669.4220296.038.884.5914.0028397.902220.967.6216.6879548.06744.0514.9015.9532.046620.181217.4155.11103.7413813.2111.062.922.320.05333.3324.395016.3976.92100977612714222176666704.1142061807.0338433.072154.4518259.700.210.252.91OpenBenchmarking.org

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOPEPYC 7642 2PLinux 5.4 Git500K1000K1500K2000K2500KSE +/- 2658.70, N = 3SE +/- 20622.51, N = 122145929.251265416.741. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOPEPYC 7642 2PLinux 5.4 Git400K800K1200K1600K2000KMin: 2141327.5 / Avg: 2145929.25 / Max: 2150537.5Min: 1154734.38 / Avg: 1265416.74 / Max: 1379310.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: f32EPYC 7642 2PLinux 5.4 Git0.67731.35462.03192.70923.3865SE +/- 0.01, N = 3SE +/- 0.01, N = 31.893.01MIN: 1.62MIN: 2.71. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: f32EPYC 7642 2PLinux 5.4 Git246810Min: 1.88 / Avg: 1.89 / Max: 1.91Min: 2.98 / Avg: 3.01 / Max: 3.031. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -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: System V Message PassingEPYC 7642 2PLinux 5.4 Git7M14M21M28M35MSE +/- 270855.79, N = 15SE +/- 322145.83, N = 721122449.0030647604.051. (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 PassingEPYC 7642 2PLinux 5.4 Git5M10M15M20M25MMin: 19738630.48 / Avg: 21122449 / Max: 24008125.2Min: 29751682.84 / Avg: 30647604.05 / Max: 32346324.471. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-ExponentialEPYC 7642 2PLinux 5.4 Git0.5491.0981.6472.1962.745SE +/- 0.01, N = 3SE +/- 0.01, N = 32.441.821. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-ExponentialEPYC 7642 2PLinux 5.4 Git246810Min: 2.43 / Avg: 2.44 / Max: 2.47Min: 1.8 / Avg: 1.82 / Max: 1.831. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: f32EPYC 7642 2PLinux 5.4 Git3691215SE +/- 0.10, N = 3SE +/- 0.13, N = 310.3311.48MIN: 9.3MIN: 10.421. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: f32EPYC 7642 2PLinux 5.4 Git3691215Min: 10.12 / Avg: 10.33 / Max: 10.46Min: 11.3 / Avg: 11.48 / Max: 11.741. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETEPYC 7642 2PLinux 5.4 Git400K800K1200K1600K2000KSE +/- 34040.00, N = 3SE +/- 12889.65, N = 31978766.831785900.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETEPYC 7642 2PLinux 5.4 Git300K600K900K1200K1500KMin: 1915708.75 / Avg: 1978766.83 / Max: 2032520.25Min: 1763668.5 / Avg: 1785900.38 / Max: 1808318.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillEPYC 7642 2PLinux 5.4 Git60K120K180K240K300KSE +/- 983.91, N = 3SE +/- 1876.47, N = 32672792504201. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillEPYC 7642 2PLinux 5.4 Git50K100K150K200K250KMin: 265766 / Avg: 267278.67 / Max: 269125Min: 246837 / Avg: 250420.33 / Max: 2531781. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncEPYC 7642 2PLinux 5.4 Git40K80K120K160K200KSE +/- 1172.48, N = 3SE +/- 923.11, N = 31686441782841. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncEPYC 7642 2PLinux 5.4 Git30K60K90K120K150KMin: 166664 / Avg: 168643.67 / Max: 170722Min: 176743 / Avg: 178283.67 / Max: 1799351. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

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 0.7Encoder Mode: Enc Mode 4 - Input: 1080pEPYC 7642 2PLinux 5.4 Git3691215SE +/- 0.07, N = 3SE +/- 0.06, N = 39.6410.171. (CXX) g++ options: -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.7Encoder Mode: Enc Mode 4 - Input: 1080pEPYC 7642 2PLinux 5.4 Git3691215Min: 9.51 / Avg: 9.64 / Max: 9.77Min: 10.06 / Avg: 10.17 / Max: 10.271. (CXX) g++ options: -fPIE -fPIC -pie

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: TsearchEPYC 7642 2PLinux 5.4 Git6001200180024003000SE +/- 16.20, N = 3SE +/- 11.22, N = 32800.132669.961. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: TsearchEPYC 7642 2PLinux 5.4 Git5001000150020002500Min: 2771.98 / Avg: 2800.13 / Max: 2828.09Min: 2652.49 / Avg: 2669.96 / Max: 2690.91. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Recurrent Neural Network Training - Data Type: f32EPYC 7642 2PLinux 5.4 Git140280420560700SE +/- 6.71, N = 3SE +/- 7.23, N = 3666.62640.66MIN: 603.35MIN: 598.41. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Recurrent Neural Network Training - Data Type: f32EPYC 7642 2PLinux 5.4 Git120240360480600Min: 659.02 / Avg: 666.62 / Max: 680.01Min: 628.52 / Avg: 640.66 / Max: 653.531. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadEPYC 7642 2PLinux 5.4 Git80M160M240M320M400MSE +/- 2904879.33, N = 3SE +/- 1347156.76, N = 33555246523679921001. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadEPYC 7642 2PLinux 5.4 Git60M120M180M240M300MMin: 352060427 / Avg: 355524652.33 / Max: 361295865Min: 365841767 / Avg: 367992100 / Max: 3704731631. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -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 via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: BMW27 - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git714212835SE +/- 0.05, N = 3SE +/- 0.08, N = 329.1630.12
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: BMW27 - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git714212835Min: 29.08 / Avg: 29.16 / Max: 29.24Min: 29.99 / Avg: 30.12 / Max: 30.25

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 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pEPYC 7642 2PLinux 5.4 Git60120180240300SE +/- 3.42, N = 3SE +/- 3.00, N = 3249.96257.691. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pEPYC 7642 2PLinux 5.4 Git50100150200250Min: 243.11 / Avg: 249.96 / Max: 253.49Min: 251.78 / Avg: 257.69 / Max: 261.551. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pEPYC 7642 2PLinux 5.4 Git70140210280350SE +/- 2.66, N = 3SE +/- 4.29, N = 3299.85309.031. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pEPYC 7642 2PLinux 5.4 Git60120180240300Min: 295.86 / Avg: 299.85 / Max: 304.88Min: 300.75 / Avg: 309.03 / Max: 315.131. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

N-Queens

This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed TimeEPYC 7642 2PLinux 5.4 Git0.45450.9091.36351.8182.2725SE +/- 0.03, N = 15SE +/- 0.02, N = 151.962.021. (CC) gcc options: -static -fopenmp -O3 -march=native
OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed TimeEPYC 7642 2PLinux 5.4 Git246810Min: 1.79 / Avg: 1.96 / Max: 2.11Min: 1.92 / Avg: 2.02 / Max: 2.151. (CC) gcc options: -static -fopenmp -O3 -march=native

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 2.80Blend File: Classroom - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git1326395265SE +/- 0.09, N = 3SE +/- 0.18, N = 357.2458.94
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Classroom - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git1224364860Min: 57.06 / Avg: 57.24 / Max: 57.38Min: 58.6 / Avg: 58.94 / Max: 59.21

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.0.0Scene: MemorialEPYC 7642 2PLinux 5.4 Git612182430SE +/- 0.43, N = 3SE +/- 0.21, N = 326.0726.79
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.0.0Scene: MemorialEPYC 7642 2PLinux 5.4 Git612182430Min: 25.21 / Avg: 26.07 / Max: 26.55Min: 26.55 / Avg: 26.79 / Max: 27.22

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 4KEPYC 7642 2PLinux 5.4 Git70140210280350SE +/- 1.29, N = 3SE +/- 1.24, N = 3325.32316.86MIN: 73.11 / MAX: 396.1MIN: 72.13 / MAX: 389.591. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 4KEPYC 7642 2PLinux 5.4 Git60120180240300Min: 323.19 / Avg: 325.32 / Max: 327.65Min: 314.64 / Avg: 316.86 / Max: 318.921. (CC) gcc options: -pthread

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 EncodingEPYC 7642 2PLinux 5.4 Git306090120150SE +/- 0.46, N = 3SE +/- 1.92, N = 12150.02146.191. (CC) gcc options: -ldl -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 EncodingEPYC 7642 2PLinux 5.4 Git306090120150Min: 149.22 / Avg: 150.02 / Max: 150.83Min: 126.48 / Avg: 146.19 / Max: 152.971. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

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 SecondEPYC 7642 2PLinux 5.4 Git700K1400K2100K2800K3500KSE +/- 44284.65, N = 3SE +/- 38536.01, N = 32974027.493044058.431. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondEPYC 7642 2PLinux 5.4 Git500K1000K1500K2000K2500KMin: 2899754.58 / Avg: 2974027.49 / Max: 3052949.59Min: 2967198.55 / Avg: 3044058.43 / Max: 3087437.191. (CC) gcc options: -O2 -lrt" -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 2.80Blend File: Barbershop - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git306090120150SE +/- 0.37, N = 3SE +/- 1.10, N = 3149.01152.51
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Barbershop - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git306090120150Min: 148.35 / Avg: 149.01 / Max: 149.62Min: 150.31 / Avg: 152.51 / Max: 153.69

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 ActivityEPYC 7642 2PLinux 5.4 Git7K14K21K28K35KSE +/- 365.28, N = 15SE +/- 39.14, N = 330423.8429774.331. (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 ActivityEPYC 7642 2PLinux 5.4 Git5K10K15K20K25KMin: 28081.23 / Avg: 30423.84 / Max: 32849.02Min: 29721.53 / Avg: 29774.33 / Max: 29850.781. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 7642 2PLinux 5.4 Git50K100K150K200K250KSE +/- 448.47, N = 3SE +/- 2752.49, N = 3230894.32226057.621. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CEPYC 7642 2PLinux 5.4 Git40K80K120K160K200KMin: 230008.02 / Avg: 230894.32 / Max: 231456.75Min: 220580.07 / Avg: 226057.62 / Max: 229271.751. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

ACES DGEMM

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

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 7642 2PLinux 5.4 Git510152025SE +/- 0.33, N = 3SE +/- 0.20, N = 320.5520.131. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 7642 2PLinux 5.4 Git510152025Min: 20.01 / Avg: 20.55 / Max: 21.14Min: 19.73 / Avg: 20.13 / Max: 20.361. (CC) gcc options: -O3 -march=native -fopenmp

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETEPYC 7642 2PLinux 5.4 Git300K600K900K1200K1500KSE +/- 21744.22, N = 12SE +/- 20373.34, N = 151434092.451405847.781. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETEPYC 7642 2PLinux 5.4 Git200K400K600K800K1000KMin: 1288659.75 / Avg: 1434092.45 / Max: 1547987.5Min: 1269035.5 / Avg: 1405847.78 / Max: 1540832.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

IOR

IOR is a parallel I/O storage benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read TestEPYC 7642 2PLinux 5.4 Git400800120016002000SE +/- 5.47, N = 3SE +/- 11.37, N = 31853.751890.73MIN: 947.1 / MAX: 2038.08MIN: 1432.14 / MAX: 1992.751. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read TestEPYC 7642 2PLinux 5.4 Git30060090012001500Min: 1846.01 / Avg: 1853.75 / Max: 1864.31Min: 1876.23 / Avg: 1890.73 / Max: 1913.141. (CC) gcc options: -O2 -lm -pthread -lmpi

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: EmilyEPYC 7642 2PLinux 5.4 Git4080120160200175.60172.23

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: Memory CopyingEPYC 7642 2PLinux 5.4 Git3K6K9K12K15KSE +/- 80.12, N = 3SE +/- 54.92, N = 312383.1112624.521. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Memory CopyingEPYC 7642 2PLinux 5.4 Git2K4K6K8K10KMin: 12299.76 / Avg: 12383.11 / Max: 12543.31Min: 12551.98 / Avg: 12624.52 / Max: 12732.211. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 7642 2PLinux 5.4 Git30K60K90K120K150KSE +/- 1182.49, N = 9SE +/- 1727.61, N = 14123514.78125854.291. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BEPYC 7642 2PLinux 5.4 Git20K40K60K80K100KMin: 117304.53 / Avg: 123514.78 / Max: 127209.87Min: 105185.02 / Avg: 125854.29 / Max: 132887.11. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 1080pEPYC 7642 2PLinux 5.4 Git160320480640800SE +/- 3.89, N = 3SE +/- 5.57, N = 3753.59739.75MIN: 173.57 / MAX: 911.57MIN: 165.87 / MAX: 907.21. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 1080pEPYC 7642 2PLinux 5.4 Git130260390520650Min: 748.24 / Avg: 753.59 / Max: 761.16Min: 732.31 / Avg: 739.75 / Max: 750.641. (CC) gcc options: -pthread

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 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pEPYC 7642 2PLinux 5.4 Git70140210280350SE +/- 3.89, N = 3SE +/- 1.49, N = 3308.06313.821. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pEPYC 7642 2PLinux 5.4 Git60120180240300Min: 302.27 / Avg: 308.06 / Max: 315.46Min: 312.17 / Avg: 313.82 / Max: 316.791. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -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 MathEPYC 7642 2PLinux 5.4 Git100K200K300K400K500KSE +/- 7826.09, N = 3SE +/- 7843.47, N = 3465311.04473539.511. (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 MathEPYC 7642 2PLinux 5.4 Git80K160K240K320K400KMin: 449711.66 / Avg: 465311.04 / Max: 474223.29Min: 458193.65 / Avg: 473539.51 / Max: 484029.951. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

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 2.80Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git20406080100SE +/- 0.25, N = 3SE +/- 0.32, N = 385.1086.55
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git1632486480Min: 84.61 / Avg: 85.1 / Max: 85.38Min: 86.15 / Avg: 86.55 / Max: 87.18

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7642 2PLinux 5.4 Git1326395265SE +/- 0.15, N = 3SE +/- 0.15, N = 355.0755.98MIN: 53.07 / MAX: 58.31MIN: 54.05 / MAX: 58.73
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian DragonEPYC 7642 2PLinux 5.4 Git1122334455Min: 54.77 / Avg: 55.07 / Max: 55.26Min: 55.68 / Avg: 55.98 / Max: 56.14

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git246810SE +/- 0.02, N = 3SE +/- 0.05, N = 37.016.90MIN: 4.41 / MAX: 7.09MIN: 4.24 / MAX: 7.09
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git3691215Min: 6.99 / Avg: 7.01 / Max: 7.04Min: 6.8 / Avg: 6.9 / Max: 6.99

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisEPYC 7642 2PLinux 5.4 Git20406080100SE +/- 1.01, N = 15101.48100.00MIN: 14.71 / MAX: 111.11MIN: 15.63 / MAX: 111.11
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisEPYC 7642 2PLinux 5.4 Git20406080100Min: 100 / Avg: 101.48 / Max: 111.11

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: LsearchEPYC 7642 2PLinux 5.4 Git2004006008001000SE +/- 11.01, N = 3SE +/- 1.38, N = 3957.83971.981. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: LsearchEPYC 7642 2PLinux 5.4 Git2004006008001000Min: 936.83 / Avg: 957.83 / Max: 974.07Min: 970.1 / Avg: 971.98 / Max: 974.671. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: f32EPYC 7642 2PLinux 5.4 Git0.63451.2691.90352.5383.1725SE +/- 0.04, N = 4SE +/- 0.02, N = 32.822.78MIN: 2.52MIN: 2.581. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: f32EPYC 7642 2PLinux 5.4 Git246810Min: 2.72 / Avg: 2.82 / Max: 2.88Min: 2.74 / Avg: 2.78 / Max: 2.81. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -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: SemaphoresEPYC 7642 2PLinux 5.4 Git300K600K900K1200K1500KSE +/- 8569.56, N = 3SE +/- 9614.88, N = 31371739.851352785.791. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: SemaphoresEPYC 7642 2PLinux 5.4 Git200K400K600K800K1000KMin: 1354811.64 / Avg: 1371739.85 / Max: 1382525.32Min: 1336384.17 / Avg: 1352785.79 / Max: 1369680.161. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 7642 2PLinux 5.4 Git20K40K60K80K100KSE +/- 908.49, N = 10SE +/- 1414.68, N = 399614.54101007.731. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CEPYC 7642 2PLinux 5.4 Git20K40K60K80K100KMin: 97011.21 / Avg: 99614.54 / Max: 104607.08Min: 98744.95 / Avg: 101007.73 / Max: 103610.131. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Timed MrBayes Analysis

This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisEPYC 7642 2PLinux 5.4 Git20406080100SE +/- 1.58, N = 4SE +/- 0.23, N = 3107.51106.081. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisEPYC 7642 2PLinux 5.4 Git20406080100Min: 105.76 / Avg: 107.51 / Max: 112.26Min: 105.64 / Avg: 106.08 / Max: 106.41. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm

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 CompileEPYC 7642 2PLinux 5.4 Git2040608010093.1091.88

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 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyEPYC 7642 2PLinux 5.4 Git200K400K600K800K1000KSE +/- 571.53, N = 3SE +/- 3831.25, N = 3901340.22913157.661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyEPYC 7642 2PLinux 5.4 Git160K320K480K640K800KMin: 900722.15 / Avg: 901340.22 / Max: 902481.99Min: 906656.07 / Avg: 913157.66 / Max: 919920.211. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian DragonEPYC 7642 2PLinux 5.4 Git1326395265SE +/- 0.05, N = 3SE +/- 0.06, N = 357.1857.90MIN: 55.25 / MAX: 60.16MIN: 55.91 / MAX: 61.57
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian DragonEPYC 7642 2PLinux 5.4 Git1122334455Min: 57.08 / Avg: 57.18 / Max: 57.25Min: 57.8 / Avg: 57.9 / Max: 58.02

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: f32EPYC 7642 2PLinux 5.4 Git100200300400500SE +/- 7.97, N = 3SE +/- 7.82, N = 3472.70478.49MIN: 440.83MIN: 441.571. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: f32EPYC 7642 2PLinux 5.4 Git80160240320400Min: 460.78 / Avg: 472.7 / Max: 487.83Min: 462.94 / Avg: 478.49 / Max: 487.771. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: f32EPYC 7642 2PLinux 5.4 Git0.93381.86762.80143.73524.669SE +/- 0.02, N = 3SE +/- 0.04, N = 154.154.10MIN: 3.55MIN: 3.181. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: f32EPYC 7642 2PLinux 5.4 Git246810Min: 4.11 / Avg: 4.15 / Max: 4.18Min: 3.66 / Avg: 4.1 / Max: 4.241. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

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 3.1.2H.265 1080p Video EncodingEPYC 7642 2PLinux 5.4 Git1122334455SE +/- 0.10, N = 3SE +/- 0.05, N = 347.4648.031. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video EncodingEPYC 7642 2PLinux 5.4 Git1020304050Min: 47.31 / Avg: 47.46 / Max: 47.64Min: 47.96 / Avg: 48.03 / Max: 48.121. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon ObjEPYC 7642 2PLinux 5.4 Git1122334455SE +/- 0.07, N = 3SE +/- 0.05, N = 350.2550.85MIN: 48.61 / MAX: 53.26MIN: 49.22 / MAX: 53.7
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon ObjEPYC 7642 2PLinux 5.4 Git1020304050Min: 50.1 / Avg: 50.25 / Max: 50.35Min: 50.79 / Avg: 50.85 / Max: 50.95

C-Ray

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

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelEPYC 7642 2PLinux 5.4 Git246810SE +/- 0.03, N = 3SE +/- 0.03, N = 37.937.841. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelEPYC 7642 2PLinux 5.4 Git3691215Min: 7.88 / Avg: 7.93 / Max: 7.99Min: 7.8 / Avg: 7.84 / Max: 7.91. (CC) gcc options: -lm -lpthread -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 2.80Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git1122334455SE +/- 0.19, N = 3SE +/- 0.11, N = 349.2749.82
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 7642 2PLinux 5.4 Git1020304050Min: 49.03 / Avg: 49.27 / Max: 49.65Min: 49.6 / Avg: 49.82 / Max: 49.97

Optcarrot

Optcarrot is an NES emulator benchmark for the Ruby language. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized BenchmarkEPYC 7642 2PLinux 5.4 Git20406080100SE +/- 0.75, N = 4SE +/- 0.30, N = 479.5180.361. ruby 2.5.5p157 (2019-03-15 revision 67260) [x86_64-linux-gnu]
OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized BenchmarkEPYC 7642 2PLinux 5.4 Git1530456075Min: 77.44 / Avg: 79.51 / Max: 80.81Min: 79.66 / Avg: 80.36 / Max: 81.021. ruby 2.5.5p157 (2019-03-15 revision 67260) [x86_64-linux-gnu]

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillEPYC 7642 2PLinux 5.4 Git50K100K150K200K250KSE +/- 3150.69, N = 3SE +/- 3050.09, N = 32475312449461. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillEPYC 7642 2PLinux 5.4 Git40K80K120K160K200KMin: 244222 / Avg: 247531.33 / Max: 253830Min: 240472 / Avg: 244945.67 / Max: 2507741. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 4KEPYC 7642 2PLinux 5.4 Git48121620SE +/- 0.05, N = 3SE +/- 0.05, N = 315.5715.411. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 4KEPYC 7642 2PLinux 5.4 Git48121620Min: 15.47 / Avg: 15.57 / Max: 15.64Min: 15.35 / Avg: 15.41 / Max: 15.511. (CXX) g++ options: -O3 -lpthread

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Chimera 1080pEPYC 7642 2PLinux 5.4 Git130260390520650SE +/- 2.86, N = 3SE +/- 1.77, N = 3582.39576.73MIN: 303.62 / MAX: 727.52MIN: 303.06 / MAX: 720.581. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Chimera 1080pEPYC 7642 2PLinux 5.4 Git100200300400500Min: 576.87 / Avg: 582.39 / Max: 586.45Min: 573.8 / Avg: 576.73 / Max: 579.921. (CC) gcc options: -pthread

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: BsearchEPYC 7642 2PLinux 5.4 Git10K20K30K40K50KSE +/- 313.35, N = 3SE +/- 413.24, N = 346032.7246467.651. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: BsearchEPYC 7642 2PLinux 5.4 Git8K16K24K32K40KMin: 45644.09 / Avg: 46032.72 / Max: 46652.82Min: 45642.21 / Avg: 46467.65 / Max: 46916.291. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 7642 2PLinux 5.4 Git1122334455SE +/- 0.06, N = 3SE +/- 0.13, N = 347.5447.94MIN: 46.02 / MAX: 50.79MIN: 46.09 / MAX: 50.73
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjEPYC 7642 2PLinux 5.4 Git1020304050Min: 47.45 / Avg: 47.54 / Max: 47.64Min: 47.7 / Avg: 47.94 / Max: 48.12

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 TesterEPYC 7642 2PLinux 5.4 Git70140210280350299.61302.04

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSHEPYC 7642 2PLinux 5.4 Git300K600K900K1200K1500KSE +/- 14528.15, N = 15SE +/- 19586.59, N = 151259232.881269417.131. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSHEPYC 7642 2PLinux 5.4 Git200K400K600K800K1000KMin: 1140250.88 / Avg: 1259232.88 / Max: 1335113.5Min: 1122334.5 / Avg: 1269417.13 / Max: 1351351.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: f32EPYC 7642 2PLinux 5.4 Git1326395265SE +/- 0.55, N = 15SE +/- 0.52, N = 1559.5459.07MIN: 53.81MIN: 53.661. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: f32EPYC 7642 2PLinux 5.4 Git1224364860Min: 55.88 / Avg: 59.54 / Max: 62.26Min: 56.85 / Avg: 59.07 / Max: 62.851. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -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: Disney MaterialEPYC 7642 2PLinux 5.4 Git132639526559.4158.96

Apache Cassandra

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

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesEPYC 7642 2PLinux 5.4 Git40K80K120K160K200KSE +/- 2802.82, N = 3SE +/- 3072.70, N = 3184260185659
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesEPYC 7642 2PLinux 5.4 Git30K60K90K120K150KMin: 180254 / Avg: 184260.33 / Max: 189659Min: 182561 / Avg: 185658.67 / Max: 191804

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 7642 2PLinux 5.4 Git14002800420056007000SE +/- 33.28, N = 3SE +/- 43.17, N = 36390.636343.741. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CEPYC 7642 2PLinux 5.4 Git11002200330044005500Min: 6341.53 / Avg: 6390.63 / Max: 6454.09Min: 6285.22 / Avg: 6343.74 / Max: 6427.971. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Redis

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

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADDEPYC 7642 2PLinux 5.4 Git400K800K1200K1600K2000KSE +/- 22741.29, N = 15SE +/- 19738.35, N = 151678729.141666898.121. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADDEPYC 7642 2PLinux 5.4 Git300K600K900K1200K1500KMin: 1555209.88 / Avg: 1678729.14 / Max: 1828153.62Min: 1569858.62 / Avg: 1666898.12 / Max: 1818181.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinhEPYC 7642 2PLinux 5.4 Git3691215SE +/- 0.01, N = 3SE +/- 0.03, N = 310.1010.17
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinhEPYC 7642 2PLinux 5.4 Git3691215Min: 10.09 / Avg: 10.1 / Max: 10.12Min: 10.14 / Avg: 10.17 / Max: 10.22

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 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read OnlyEPYC 7642 2PLinux 5.4 Git4K8K12K16K20KSE +/- 126.56, N = 3SE +/- 279.11, N = 920533.9020674.991. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read OnlyEPYC 7642 2PLinux 5.4 Git4K8K12K16K20KMin: 20305.25 / Avg: 20533.9 / Max: 20742.25Min: 19665.7 / Avg: 20674.99 / Max: 21932.821. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -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 1.8.1vpxenc VP9 1080p Video EncodeEPYC 7642 2PLinux 5.4 Git306090120150SE +/- 1.34, N = 9SE +/- 1.73, N = 3134.36135.281. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.1vpxenc VP9 1080p Video EncodeEPYC 7642 2PLinux 5.4 Git306090120150Min: 124.45 / Avg: 134.36 / Max: 138.12Min: 131.92 / Avg: 135.28 / Max: 137.661. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080pEPYC 7642 2PLinux 5.4 Git816243240SE +/- 0.12, N = 3SE +/- 0.21, N = 334.0334.261. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080pEPYC 7642 2PLinux 5.4 Git714212835Min: 33.8 / Avg: 34.03 / Max: 34.18Min: 33.96 / Avg: 34.26 / Max: 34.661. (CXX) g++ options: -O3 -lpthread

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 5.4Time To CompileEPYC 7642 2PLinux 5.4 Git510152025SE +/- 0.19, N = 13SE +/- 0.19, N = 1319.7519.62
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileEPYC 7642 2PLinux 5.4 Git510152025Min: 19.42 / Avg: 19.75 / Max: 22.06Min: 19.33 / Avg: 19.62 / Max: 21.85

Pennant

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

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 7642 2PLinux 5.4 Git4080120160200SE +/- 0.15, N = 3SE +/- 0.46, N = 3185.84187.071. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 7642 2PLinux 5.4 Git306090120150Min: 185.54 / Avg: 185.84 / Max: 186.06Min: 186.48 / Avg: 187.07 / Max: 187.961. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: CrownEPYC 7642 2PLinux 5.4 Git1530456075SE +/- 0.11, N = 3SE +/- 0.53, N = 368.6268.19MIN: 65.5 / MAX: 72.75MIN: 63.35 / MAX: 72.68
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: CrownEPYC 7642 2PLinux 5.4 Git1326395265Min: 68.48 / Avg: 68.62 / Max: 68.84Min: 67.12 / Avg: 68.19 / Max: 68.76

Pennant

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

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 7642 2PLinux 5.4 Git4080120160200SE +/- 0.20, N = 3SE +/- 0.13, N = 3177.25178.361. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 7642 2PLinux 5.4 Git306090120150Min: 176.88 / Avg: 177.25 / Max: 177.56Min: 178.15 / Avg: 178.36 / Max: 178.611. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7642 2PLinux 5.4 Git40K80K120K160K200KSE +/- 114.28, N = 3SE +/- 337.51, N = 3201645.45202866.241. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CEPYC 7642 2PLinux 5.4 Git40K80K120K160K200KMin: 201431.14 / Avg: 201645.45 / Max: 201821.41Min: 202195.65 / Avg: 202866.24 / Max: 203268.41. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

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 AtomsEPYC 7642 2PLinux 5.4 Git0.06910.13820.20730.27640.3455SE +/- 0.00151, N = 3SE +/- 0.00086, N = 50.305440.30724
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsEPYC 7642 2PLinux 5.4 Git12345Min: 0.3 / Avg: 0.31 / Max: 0.31Min: 0.3 / Avg: 0.31 / Max: 0.31

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 1080pEPYC 7642 2PLinux 5.4 Git1122334455SE +/- 0.64, N = 4SE +/- 0.69, N = 348.2448.521. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 1080pEPYC 7642 2PLinux 5.4 Git1020304050Min: 46.8 / Avg: 48.24 / Max: 49.92Min: 47.27 / Avg: 48.52 / Max: 49.651. (CXX) g++ options: -O3 -lpthread

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000EPYC 7642 2PLinux 5.4 Git20406080100SE +/- 0.07, N = 3SE +/- 0.14, N = 378.1577.711. (CC) gcc options: -O2 -ldl -lz -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000EPYC 7642 2PLinux 5.4 Git1530456075Min: 78.02 / Avg: 78.15 / Max: 78.25Min: 77.49 / Avg: 77.71 / Max: 77.981. (CC) gcc options: -O2 -ldl -lz -lpthread

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: HsearchEPYC 7642 2PLinux 5.4 Git110K220K330K440K550KSE +/- 1266.53, N = 3SE +/- 1413.19, N = 3529090.47531774.861. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: HsearchEPYC 7642 2PLinux 5.4 Git90K180K270K360K450KMin: 527601.86 / Avg: 529090.47 / Max: 531609.69Min: 530104.24 / Avg: 531774.86 / Max: 534584.521. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc Qsort Data SortingEPYC 7642 2PLinux 5.4 Git2004006008001000SE +/- 5.73, N = 3SE +/- 9.02, N = 31041.201046.161. (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 SortingEPYC 7642 2PLinux 5.4 Git2004006008001000Min: 1030.33 / Avg: 1041.2 / Max: 1049.8Min: 1028.16 / Avg: 1046.16 / Max: 1056.261. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: expEPYC 7642 2PLinux 5.4 Git246810SE +/- 0.04, N = 6SE +/- 0.08, N = 36.356.32
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: expEPYC 7642 2PLinux 5.4 Git3691215Min: 6.13 / Avg: 6.35 / Max: 6.39Min: 6.17 / Avg: 6.32 / Max: 6.4

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 PerformanceEPYC 7642 2PLinux 5.4 Git200K400K600K800K1000KSE +/- 1723.45, N = 5SE +/- 1367.47, N = 5100950110139581. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceEPYC 7642 2PLinux 5.4 Git200K400K600K800K1000KMin: 1006906 / Avg: 1009501.4 / Max: 1016195Min: 1008750 / Avg: 1013957.6 / Max: 10161951. (CC) gcc options: -O3 -march=native

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceEPYC 7642 2PLinux 5.4 Git0.5221.0441.5662.0882.61SE +/- 0.00, N = 8SE +/- 0.00, N = 122.312.32
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceEPYC 7642 2PLinux 5.4 Git246810Min: 2.31 / Avg: 2.31 / Max: 2.32Min: 2.32 / Avg: 2.32 / Max: 2.32

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsllEPYC 7642 2PLinux 5.4 Git0.5221.0441.5662.0882.61SE +/- 0.00, N = 3SE +/- 0.00, N = 102.312.32
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsllEPYC 7642 2PLinux 5.4 Git246810Min: 2.31 / Avg: 2.31 / Max: 2.32Min: 2.32 / Avg: 2.32 / Max: 2.32

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cosEPYC 7642 2PLinux 5.4 Git1326395265SE +/- 0.02, N = 3SE +/- 0.23, N = 355.4555.69
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cosEPYC 7642 2PLinux 5.4 Git1122334455Min: 55.43 / Avg: 55.45 / Max: 55.48Min: 55.44 / Avg: 55.69 / Max: 56.15

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water CausticEPYC 7642 2PLinux 5.4 Git612182430SE +/- 0.36, N = 3SE +/- 0.26, N = 723.5823.681. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water CausticEPYC 7642 2PLinux 5.4 Git612182430Min: 23.04 / Avg: 23.58 / Max: 24.26Min: 22.98 / Avg: 23.68 / Max: 24.691. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: CrownEPYC 7642 2PLinux 5.4 Git1530456075SE +/- 0.21, N = 3SE +/- 0.13, N = 364.8465.10MIN: 61.46 / MAX: 69.24MIN: 61.9 / MAX: 69.36
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: CrownEPYC 7642 2PLinux 5.4 Git1326395265Min: 64.42 / Avg: 64.84 / Max: 65.06Min: 64.83 / Avg: 65.1 / Max: 65.24

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 MathEPYC 7642 2PLinux 5.4 Git40K80K120K160K200KSE +/- 378.92, N = 3SE +/- 264.39, N = 3195708.79195037.071. (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 MathEPYC 7642 2PLinux 5.4 Git30K60K90K120K150KMin: 194957.55 / Avg: 195708.79 / Max: 196170.8Min: 194771.48 / Avg: 195037.07 / Max: 195565.841. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtEPYC 7642 2PLinux 5.4 Git0.6571.3141.9712.6283.285SE +/- 0.00, N = 3SE +/- 0.00, N = 122.912.92
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtEPYC 7642 2PLinux 5.4 Git246810Min: 2.91 / Avg: 2.91 / Max: 2.92Min: 2.92 / Avg: 2.92 / Max: 2.92

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: HairEPYC 7642 2PLinux 5.4 Git1.31852.6373.95555.2746.5925SE +/- 0.08, N = 3SE +/- 0.07, N = 35.865.841. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: HairEPYC 7642 2PLinux 5.4 Git246810Min: 5.75 / Avg: 5.86 / Max: 6.01Min: 5.73 / Avg: 5.84 / Max: 5.961. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

dav1d

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

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Chimera 1080p 10-bitEPYC 7642 2PLinux 5.4 Git20406080100SE +/- 0.09, N = 3SE +/- 0.12, N = 398.9998.66MIN: 66.44 / MAX: 163.99MIN: 66.35 / MAX: 164.711. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Chimera 1080p 10-bitEPYC 7642 2PLinux 5.4 Git20406080100Min: 98.8 / Avg: 98.99 / Max: 99.09Min: 98.41 / Avg: 98.66 / Max: 98.821. (CC) gcc options: -pthread

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 MP3EPYC 7642 2PLinux 5.4 Git3691215SE +/- 0.00, N = 3SE +/- 0.02, N = 39.399.421. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3EPYC 7642 2PLinux 5.4 Git3691215Min: 9.39 / Avg: 9.39 / Max: 9.4Min: 9.39 / Avg: 9.42 / Max: 9.461. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -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: CryptoEPYC 7642 2PLinux 5.4 Git4K8K12K16K20KSE +/- 37.73, N = 3SE +/- 60.19, N = 320351.9420296.031. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CryptoEPYC 7642 2PLinux 5.4 Git4K8K12K16K20KMin: 20278.1 / Avg: 20351.94 / Max: 20402.36Min: 20216.76 / Avg: 20296.03 / Max: 20414.121. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git246810SE +/- 0.03, N = 3SE +/- 0.03, N = 38.908.88MIN: 7.46 / MAX: 9.01MIN: 7.09 / MAX: 9.01
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git3691215Min: 8.85 / Avg: 8.9 / Max: 8.93Min: 8.85 / Avg: 8.88 / Max: 8.93

Tungsten Renderer

Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric CausticEPYC 7642 2PLinux 5.4 Git1.0352.073.1054.145.175SE +/- 0.01, N = 3SE +/- 0.00, N = 34.604.591. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric CausticEPYC 7642 2PLinux 5.4 Git246810Min: 4.59 / Avg: 4.6 / Max: 4.61Min: 4.59 / Avg: 4.59 / Max: 4.61. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanhEPYC 7642 2PLinux 5.4 Git48121620SE +/- 0.01, N = 3SE +/- 0.02, N = 313.9714.00
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanhEPYC 7642 2PLinux 5.4 Git48121620Min: 13.95 / Avg: 13.97 / Max: 13.99Min: 13.97 / Avg: 14 / Max: 14.03

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 StressEPYC 7642 2PLinux 5.4 Git6K12K18K24K30KSE +/- 30.73, N = 3SE +/- 99.17, N = 328442.2328397.901. (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 StressEPYC 7642 2PLinux 5.4 Git5K10K15K20K25KMin: 28406.64 / Avg: 28442.23 / Max: 28503.43Min: 28292.74 / Avg: 28397.9 / Max: 28596.121. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_all - Data Type: f32EPYC 7642 2PLinux 5.4 Git5001000150020002500SE +/- 26.20, N = 3SE +/- 28.80, N = 52217.912220.96MIN: 2049.87MIN: 2009.541. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_all - Data Type: f32EPYC 7642 2PLinux 5.4 Git400800120016002000Min: 2190.13 / Avg: 2217.91 / Max: 2270.27Min: 2128.03 / Avg: 2220.96 / Max: 2273.411. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: log2EPYC 7642 2PLinux 5.4 Git246810SE +/- 0.00, N = 3SE +/- 0.01, N = 37.637.62
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: log2EPYC 7642 2PLinux 5.4 Git3691215Min: 7.62 / Avg: 7.63 / Max: 7.63Min: 7.61 / Avg: 7.62 / Max: 7.64

Sudokut

This is a test of Sudokut, which is a Sudoku puzzle solver written in Tcl. This test measures how long it takes to solve 100 Sudoku puzzles. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSudokut 0.4Total TimeEPYC 7642 2PLinux 5.4 Git48121620SE +/- 0.00, N = 3SE +/- 0.01, N = 316.7016.68
OpenBenchmarking.orgSeconds, Fewer Is BetterSudokut 0.4Total TimeEPYC 7642 2PLinux 5.4 Git48121620Min: 16.69 / Avg: 16.7 / Max: 16.7Min: 16.67 / Avg: 16.68 / Max: 16.7

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CEPYC 7642 2PLinux 5.4 Git20K40K60K80K100KSE +/- 119.77, N = 3SE +/- 192.18, N = 379464.6779548.061. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CEPYC 7642 2PLinux 5.4 Git14K28K42K56K70KMin: 79270.41 / Avg: 79464.67 / Max: 79683.18Min: 79240.97 / Avg: 79548.06 / Max: 79901.771. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

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 CompileEPYC 7642 2PLinux 5.4 Git160320480640800SE +/- 0.83, N = 3SE +/- 0.59, N = 3743.47744.05
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To CompileEPYC 7642 2PLinux 5.4 Git130260390520650Min: 741.85 / Avg: 743.47 / Max: 744.58Min: 742.86 / Avg: 744.05 / Max: 744.67

libgav1

Libgav1 is an AV1 decoder developed by Google for AV1 profile 0/1 compliance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080p 10-bitEPYC 7642 2PLinux 5.4 Git48121620SE +/- 0.08, N = 3SE +/- 0.14, N = 314.8914.901. (CXX) g++ options: -O3 -lpthread
OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080p 10-bitEPYC 7642 2PLinux 5.4 Git48121620Min: 14.73 / Avg: 14.89 / Max: 14.98Min: 14.63 / Avg: 14.9 / Max: 15.041. (CXX) g++ options: -O3 -lpthread

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sincosEPYC 7642 2PLinux 5.4 Git48121620SE +/- 0.00, N = 3SE +/- 0.01, N = 315.9415.95
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sincosEPYC 7642 2PLinux 5.4 Git48121620Min: 15.93 / Avg: 15.94 / Max: 15.94Min: 15.94 / Avg: 15.95 / Max: 15.96

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32EPYC 7642 2PLinux 5.4 Git714212835SE +/- 0.54, N = 3SE +/- 0.43, N = 332.0632.04MIN: 28.52MIN: 29.161. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32EPYC 7642 2PLinux 5.4 Git714212835Min: 30.98 / Avg: 32.06 / Max: 32.69Min: 31.54 / Avg: 32.04 / Max: 32.891. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -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. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7642 2PLinux 5.4 Git14002800420056007000SE +/- 4.17, N = 3SE +/- 2.78, N = 36617.276620.181. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DEPYC 7642 2PLinux 5.4 Git11002200330044005500Min: 6609.47 / Avg: 6617.27 / Max: 6623.75Min: 6617.05 / Avg: 6620.18 / Max: 6625.731. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

IOR

IOR is a parallel I/O storage benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Write TestEPYC 7642 2PLinux 5.4 Git30060090012001500SE +/- 8.16, N = 3SE +/- 4.77, N = 31217.881217.41MIN: 34.18 / MAX: 1425.21MIN: 726.49 / MAX: 1385.91. (CC) gcc options: -O2 -lm -pthread -lmpi
OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Write TestEPYC 7642 2PLinux 5.4 Git2004006008001000Min: 1208.81 / Avg: 1217.88 / Max: 1234.16Min: 1210.72 / Avg: 1217.41 / Max: 1226.651. (CC) gcc options: -O2 -lm -pthread -lmpi

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinEPYC 7642 2PLinux 5.4 Git1224364860SE +/- 0.00, N = 3SE +/- 0.00, N = 355.1355.11
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinEPYC 7642 2PLinux 5.4 Git1122334455Min: 55.13 / Avg: 55.13 / Max: 55.14Min: 55.11 / Avg: 55.11 / Max: 55.12

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 0.7Encoder Mode: Enc Mode 8 - Input: 1080pEPYC 7642 2PLinux 5.4 Git20406080100SE +/- 0.50, N = 3SE +/- 0.87, N = 3103.72103.741. (CXX) g++ options: -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.7Encoder Mode: Enc Mode 8 - Input: 1080pEPYC 7642 2PLinux 5.4 Git20406080100Min: 102.76 / Avg: 103.72 / Max: 104.44Min: 102.01 / Avg: 103.74 / Max: 104.681. (CXX) g++ options: -fPIE -fPIC -pie

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 TimeEPYC 7642 2PLinux 5.4 Git306090120150138138

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: atanhEPYC 7642 2PLinux 5.4 Git3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 313.2113.21
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: atanhEPYC 7642 2PLinux 5.4 Git48121620Min: 13.2 / Avg: 13.21 / Max: 13.21Min: 13.2 / Avg: 13.21 / Max: 13.22

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: asinhEPYC 7642 2PLinux 5.4 Git3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 311.0611.06
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: asinhEPYC 7642 2PLinux 5.4 Git3691215Min: 11.05 / Avg: 11.06 / Max: 11.08Min: 11.06 / Avg: 11.06 / Max: 11.07

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: modfEPYC 7642 2PLinux 5.4 Git0.6571.3141.9712.6283.285SE +/- 0.00, N = 12SE +/- 0.00, N = 122.922.92
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: modfEPYC 7642 2PLinux 5.4 Git246810Min: 2.92 / Avg: 2.92 / Max: 2.92Min: 2.92 / Avg: 2.92 / Max: 2.92

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsEPYC 7642 2PLinux 5.4 Git0.5221.0441.5662.0882.61SE +/- 0.00, N = 3SE +/- 0.00, N = 32.322.32
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsEPYC 7642 2PLinux 5.4 Git246810Min: 2.31 / Avg: 2.32 / Max: 2.32Min: 2.32 / Avg: 2.32 / Max: 2.32

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 0.7Encoder Mode: Enc Mode 0 - Input: 1080pEPYC 7642 2PLinux 5.4 Git0.01130.02260.03390.04520.0565SE +/- 0.00, N = 3SE +/- 0.00, N = 30.050.051. (CXX) g++ options: -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.7Encoder Mode: Enc Mode 0 - Input: 1080pEPYC 7642 2PLinux 5.4 Git12345Min: 0.05 / Avg: 0.05 / Max: 0.05Min: 0.05 / Avg: 0.05 / Max: 0.051. (CXX) g++ options: -fPIE -fPIC -pie

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git70140210280350SE +/- 0.00, N = 12SE +/- 0.00, N = 12333.33333.33MIN: 62.5 / MAX: 500MIN: 50 / MAX: 500
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git60120180240300Min: 333.33 / Avg: 333.33 / Max: 333.33Min: 333.33 / Avg: 333.33 / Max: 333.33

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git612182430SE +/- 0.00, N = 12SE +/- 0.00, N = 1224.3924.39MIN: 10.1 / MAX: 25MIN: 10.64 / MAX: 25
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerEPYC 7642 2PLinux 5.4 Git612182430Min: 24.39 / Avg: 24.39 / Max: 24.39Min: 24.39 / Avg: 24.39 / Max: 24.39

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisEPYC 7642 2PLinux 5.4 Git11223344555050MIN: 10.99 / MAX: 52.63MIN: 10.75 / MAX: 52.63

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisEPYC 7642 2PLinux 5.4 Git48121620SE +/- 0.00, N = 12SE +/- 0.00, N = 1216.3916.39MIN: 9.43 / MAX: 16.95MIN: 11.9 / MAX: 16.67
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisEPYC 7642 2PLinux 5.4 Git48121620Min: 16.39 / Avg: 16.39 / Max: 16.39Min: 16.39 / Avg: 16.39 / Max: 16.39

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisEPYC 7642 2PLinux 5.4 Git20406080100SE +/- 0.00, N = 12SE +/- 0.00, N = 1276.9276.92MIN: 23.26 / MAX: 90.91MIN: 32.26 / MAX: 83.33
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisEPYC 7642 2PLinux 5.4 Git1530456075Min: 76.92 / Avg: 76.92 / Max: 76.92Min: 76.92 / Avg: 76.92 / Max: 76.92

Facebook RocksDB

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

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingEPYC 7642 2PLinux 5.4 Git2M4M6M8M10MSE +/- 172564.92, N = 15SE +/- 176907.51, N = 159821726100977611. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingEPYC 7642 2PLinux 5.4 Git2M4M6M8M10MMin: 8367846 / Avg: 9821725.93 / Max: 10684514Min: 8981986 / Avg: 10097760.53 / Max: 116472981. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Apache Cassandra

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

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Mixed 1:3EPYC 7642 2PLinux 5.4 Git100200300400500SE +/- 34.08, N = 9SE +/- 16.75, N = 9450271
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Mixed 1:3EPYC 7642 2PLinux 5.4 Git80160240320400Min: 231 / Avg: 449.56 / Max: 558Min: 178 / Avg: 270.56 / Max: 318

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Mixed 1:1EPYC 7642 2PLinux 5.4 Git2004006008001000SE +/- 34.54, N = 12SE +/- 31.41, N = 9896422
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Mixed 1:1EPYC 7642 2PLinux 5.4 Git160320480640800Min: 630 / Avg: 896.08 / Max: 1070Min: 249 / Avg: 422.22 / Max: 531

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: ReadsEPYC 7642 2PLinux 5.4 Git2K4K6K8K10KSE +/- 6774.17, N = 8SE +/- 15.93, N = 98249217
OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: ReadsEPYC 7642 2PLinux 5.4 Git14002800420056007000Min: 523 / Avg: 8249.25 / Max: 55567Min: 181 / Avg: 217 / Max: 317

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 FunctionsEPYC 7642 2PLinux 5.4 Git1.5M3M4.5M6M7.5MSE +/- 85811.53, N = 15SE +/- 109056.52, N = 156777365.716666704.111. (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 C String FunctionsEPYC 7642 2PLinux 5.4 Git1.2M2.4M3.6M4.8M6MMin: 6108690.91 / Avg: 6777365.71 / Max: 7198267.86Min: 5621306.31 / Avg: 6666704.11 / Max: 7215319.451. (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 SwitchingEPYC 7642 2PLinux 5.4 Git20M40M60M80M100MSE +/- 1932864.46, N = 15SE +/- 706795.29, N = 1580545931.2542061807.031. (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 SwitchingEPYC 7642 2PLinux 5.4 Git14M28M42M56M70MMin: 64169070.11 / Avg: 80545931.25 / Max: 92468517.55Min: 36972977.65 / Avg: 42061807.03 / Max: 46078367.091. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: ForkingEPYC 7642 2PLinux 5.4 Git8K16K24K32K40KSE +/- 314.91, N = 15SE +/- 426.31, N = 316624.8438433.071. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: ForkingEPYC 7642 2PLinux 5.4 Git7K14K21K28K35KMin: 15106.78 / Avg: 16624.84 / Max: 20092.23Min: 37607.03 / Avg: 38433.07 / Max: 39029.011. (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 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read WriteEPYC 7642 2PLinux 5.4 Git5001000150020002500SE +/- 46.47, N = 9SE +/- 10.42, N = 32288.462154.451. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Single Thread - Mode: Read WriteEPYC 7642 2PLinux 5.4 Git400800120016002000Min: 2114.21 / Avg: 2288.46 / Max: 2500.4Min: 2133.8 / Avg: 2154.45 / Max: 2167.21. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteEPYC 7642 2PLinux 5.4 Git4K8K12K16K20KSE +/- 701.38, N = 9SE +/- 831.65, N = 917610.4318259.701. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteEPYC 7642 2PLinux 5.4 Git3K6K9K12K15KMin: 15535.38 / Avg: 17610.43 / Max: 22327.18Min: 16399.95 / Avg: 18259.7 / Max: 23593.161. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

LuxCoreRender

LuxCoreRender is an open-source physically based renderer. This test profile is focused on running LuxCoreRender on the CPU as opposed to the OpenCL version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: Rainbow Colors and PrismEPYC 7642 2PLinux 5.4 Git0.04730.09460.14190.18920.2365SE +/- 0.02, N = 12SE +/- 0.01, N = 120.180.21MIN: 0.1 / MAX: 0.29MIN: 0.1 / MAX: 0.26
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: Rainbow Colors and PrismEPYC 7642 2PLinux 5.4 Git12345Min: 0.1 / Avg: 0.18 / Max: 0.25Min: 0.11 / Avg: 0.21 / Max: 0.24

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: DLSCEPYC 7642 2PLinux 5.4 Git0.05850.1170.17550.2340.2925SE +/- 0.04, N = 12SE +/- 0.04, N = 120.260.25MIN: 0.1 / MAX: 0.41MIN: 0.1 / MAX: 0.44
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: DLSCEPYC 7642 2PLinux 5.4 Git12345Min: 0.1 / Avg: 0.26 / Max: 0.41Min: 0.1 / Avg: 0.25 / Max: 0.43

MKL-DNN DNNL

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: f32EPYC 7642 2PLinux 5.4 Git0.67731.35462.03192.70923.3865SE +/- 0.09, N = 12SE +/- 0.09, N = 153.012.91MIN: 2.28MIN: 2.321. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: f32EPYC 7642 2PLinux 5.4 Git246810Min: 2.57 / Avg: 3.01 / Max: 3.47Min: 2.48 / Avg: 2.91 / Max: 3.61. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

130 Results Shown

Redis
MKL-DNN DNNL
Stress-NG
Tungsten Renderer
MKL-DNN DNNL
Redis
Facebook RocksDB:
  Seq Fill
  Rand Fill Sync
SVT-AV1
Stress-NG
MKL-DNN DNNL
Facebook RocksDB
Blender
SVT-VP9:
  Visual Quality Optimized - Bosphorus 1080p
  VMAF Optimized - Bosphorus 1080p
N-Queens
Blender
Intel Open Image Denoise
dav1d
x264
Coremark
Blender
Stress-NG
NAS Parallel Benchmarks
ACES DGEMM
Redis
IOR
Appleseed
Stress-NG
NAS Parallel Benchmarks
dav1d
SVT-VP9
Stress-NG
Blender
Embree
OSPray:
  San Miguel - Path Tracer
  NASA Streamlines - SciVis
Stress-NG
MKL-DNN DNNL
Stress-NG
NAS Parallel Benchmarks
Timed MrBayes Analysis
Timed LLVM Compilation
PostgreSQL pgbench
Embree
MKL-DNN DNNL:
  Convolution Batch conv_all - f32
  Convolution Batch conv_3d - f32
x265
Embree
C-Ray
Blender
Optcarrot
Facebook RocksDB
libgav1
dav1d
Stress-NG
Embree
Appleseed
Redis
MKL-DNN DNNL
Appleseed
Apache Cassandra
NAS Parallel Benchmarks
Redis
glibc bench
PostgreSQL pgbench
VP9 libvpx Encoding
libgav1
Timed Linux Kernel Compilation
Pennant
Embree
Pennant
NAS Parallel Benchmarks
NAMD
libgav1
SQLite Speedtest
Stress-NG:
  Hsearch
  Glibc Qsort Data Sorting
glibc bench
TSCP
glibc bench:
  pthread_once
  ffsll
  cos
Tungsten Renderer
Embree
Stress-NG
glibc bench
Tungsten Renderer
dav1d
LAME MP3 Encoding
Stress-NG
OSPray
Tungsten Renderer
glibc bench
Stress-NG
MKL-DNN DNNL
glibc bench
Sudokut
NAS Parallel Benchmarks
Timed GCC Compilation
libgav1
glibc bench
MKL-DNN DNNL
NAS Parallel Benchmarks
IOR
glibc bench
SVT-AV1
ctx_clock
glibc bench:
  atanh
  asinh
  modf
  ffs
SVT-AV1
OSPray:
  Magnetic Reconnection - Path Tracer
  NASA Streamlines - Path Tracer
  Magnetic Reconnection - SciVis
  XFrog Forest - SciVis
  San Miguel - SciVis
Facebook RocksDB
Apache Cassandra:
  Mixed 1:3
  Mixed 1:1
  Reads
Stress-NG:
  Glibc C String Functions
  Context Switching
  Forking
PostgreSQL pgbench:
  Buffer Test - Single Thread - Read Write
  Buffer Test - Normal Load - Read Write
LuxCoreRender:
  Rainbow Colors and Prism
  DLSC
MKL-DNN DNNL

EPYC 7642 2P

Processor: 2 x AMD EPYC 7642 48-Core @ 2.30GHz (96 Cores / 192 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Starship/Matisse, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.10, Kernel: 5.3.0-18-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.1 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008, 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --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=auto --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 11.0.5-ea+9-post-Ubuntu-1ubuntu1)
Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1
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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 17 October 2019 08:50 by user phoronix.

Linux 5.4 Git

Processor: 2 x AMD EPYC 7642 48-Core @ 2.30GHz (96 Cores / 192 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Starship/Matisse, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.10, Kernel: 5.4.0-999-generic (x86_64) 20191017, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.1 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008, 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --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=auto --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 11.0.5-ea+10-post-Ubuntu-0ubuntu1)
Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1
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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 18 October 2019 07:09 by user phoronix.