Xeon Cascade Lake R Ubuntu 18.04 vs. 20.04 LTS

2 x Intel Xeon Gold 5220R Ubuntu benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2003242-NI-XEONCASCA60
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 2 Tests
Timed Code Compilation 2 Tests
C/C++ Compiler Tests 15 Tests
Compression Tests 2 Tests
CPU Massive 28 Tests
Creator Workloads 15 Tests
Cryptography 2 Tests
Database Test Suite 5 Tests
Encoding 4 Tests
Fortran Tests 2 Tests
Game Development 3 Tests
HPC - High Performance Computing 14 Tests
Java 2 Tests
Common Kernel Benchmarks 7 Tests
Machine Learning 5 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 3 Tests
Multi-Core 26 Tests
Networking Test Suite 2 Tests
NVIDIA GPU Compute 7 Tests
Intel oneAPI 4 Tests
OpenCL 2 Tests
OpenMPI Tests 4 Tests
Programmer / Developer System Benchmarks 5 Tests
Python 4 Tests
Raytracing 2 Tests
Renderers 7 Tests
Scientific Computing 5 Tests
Server 6 Tests
Server CPU Tests 25 Tests
Single-Threaded 4 Tests
Video Encoding 4 Tests
Common Workstation Benchmarks 5 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Ubuntu 18.04.4 LTS
March 22 2020
  1 Day, 1 Hour, 13 Minutes
Ubuntu 20.04
March 23 2020
  1 Day, 4 Hours, 26 Minutes
Invert Hiding All Results Option
  1 Day, 2 Hours, 50 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):

Ubuntu 18.04.4 LTS

Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 18.04, Kernel: 5.3.0-42-generic (x86_64), Desktop: GNOME Shell 3.28.4, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, Compiler: GCC 7.5.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c
Java Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu118.04.1)
Python Notes: Python 2.7.17 + Python 3.6.9
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled

Ubuntu 20.04

Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe 377GB, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.35.91, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.0.0 (LLVM 9.0.1 256 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --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: intel_pstate powersave - CPU Microcode: 0x500002c
Java Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)
Python Notes: + Python 3.8.2
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled

Xeon Cascade Lake R Ubuntu 18.04 vs. 20.04 LTSProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionOpenGLUbuntu 18.04.4 LTSUbuntu 20.042 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers378GB280GB INTEL SSDPED1D280GAASPEEDVE2282 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 18.045.3.0-42-generic (x86_64)GNOME Shell 3.28.4X Server 1.20.5modesetting 1.20.5GCC 7.5.0ext41920x1080llvmpipe 377GBUbuntu 20.045.4.0-18-generic (x86_64)GNOME Shell 3.35.91X Server 1.20.7modesetting 1.20.73.3 Mesa 20.0.0 (LLVM 9.0.1 256 bits)GCC 9.3.01024x768OpenBenchmarking.orgCompiler Details- Ubuntu 18.04.4 LTS: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v - Ubuntu 20.04: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --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: intel_pstate powersave - CPU Microcode: 0x500002cJava Details- Ubuntu 18.04.4 LTS: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu118.04.1)- Ubuntu 20.04: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)Python Details- Ubuntu 18.04.4 LTS: Python 2.7.17 + Python 3.6.9- Ubuntu 20.04: + Python 3.8.2Security Details- itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled

Ubuntu 18.04.4 LTS vs. Ubuntu 20.04 ComparisonPhoronix Test SuiteBaseline+114006%+114006%+228012%+228012%+342018%+342018%79312.6%78941.9%519.9%456023.8%238792.7%159.5%151.2%148.8%142.3%117.4%97%81.9%81.8%69.5%68.3%67.5%52.6%51.8%36%35.8%34.3%31.6%26.2%26%25%24.8%24.8%24.3%18.9%17.2%16.4%15.9%15.2%15.2%14.3%13.8%13.7%13.5%12.4%11.9%11.9%11.3%11.2%11%10.1%10.1%9.7%9.4%8.6%8.5%8.3%8.2%7.9%6.7%6.4%6.4%6.1%6.1%5.9%5.8%5.7%5.7%5.6%5.6%5.2%4.7%4.6%4.6%4.5%4.5%4.4%3.7%3.2%3.1%3%3%3%3%2.9%2.8%2.8%2.6%2.6%2.5%2.4%2.2%2.1%sincosContext SwitchingexpsincosOpenMP LavaMDEP.DEP.Cscikit_qdaRand Fill SyncSocket ActivityRand Write - IO_uring - Yes - No - 4KBRand Write - IO_uring - Yes - No - 4KBscikit_linearridgeregressionasinhP.B.SSeq Write - IO_uring - Yes - No - 2MBSeq Write - IO_uring - Yes - No - 2MB5201 - 10 Seconds - TCP - 64sinhBuffer Test - Heavy Contention - Read WriteRand Write - IO_uring - Yes - No - 2MBRand Write - IO_uring - Yes - No - 2MBFill SyncFill SyncBuffer Test - Normal Load - Read WriteTradebeanslog2Buffer Test - Heavy Contention - Read OnlyBuffer Test - Normal Load - Read OnlyTradesoapTime To Compile15.4%Rand Write - 64FT.CRand Write - 64Seq Write - IO_uring - Yes - No - 4KBI.M.D.SSeq Write - IO_uring - Yes - No - 4KBR.N.N.T - f3213.2%Rand ForestSeq FillRand FillSavina Reactors.IOIP Batch All - bf16bf16bf16Total Time - 4.1.R.P.PSP.BTCP - Latency - 64IP Batch 1D - f32Seq Fill9.7%Rand Delete9.7%Seq Fill9.4%Rand ReadSeq Read - IO_uring - Yes - No - 4KB8.9%Seq Read - IO_uring - Yes - No - 4KB8.8%Rand ReadLU.CT.B.T8.4%Rand Fill8.3%Hot ReadOpenMP LBMScala DottyRand Fill7.9%OpenMP CUTCP7.8%Overwrite7.5%Overwrite7.3%OpenMP Stencilwyhash6.5%Read While WritingT.F.A.T.Tscikit_svm256U.L.2.R.P.PS.C.c.jO.M.GBT.CS.C.m.j128Enc Mode 8 - 1080p5.2%Seek RandApache Spark ALSForking4.6%t1ha2_atonceMaterial TesterWater CausticApache Spark Bayest1ha0_aes_avx2wyhash3.6%IMB-MPI1 Sendrecv3.6%IMB-MPI1 Exchange3.5%Non-Exponential3.4%G.A.U.J.FWater Benchmark3.1%MeowHashC.u.1.0.3.s.i.i.C.L.1Jythont1ha2_atonceIMB-MPI1 PingPong2.9%Spooky32OpenMP CFD SolveratanhD.B.d - f322.7%fasthash32t1ha0_aes_avx2MeowHashEmilyEnc Mode 4 - 1080p2.4%H.2.V.E2.2%S.V.M.PD.B.d - bf16bf16bf16Spooky322%glibc benchglibc benchStress-NGglibc benchglibc benchRodiniaNAS Parallel BenchmarksNAS Parallel BenchmarksMlpack BenchmarkFacebook RocksDBStress-NGFlexible IO TesterFlexible IO TesterMlpack Benchmarkglibc benchPHPBenchFlexible IO TesterFlexible IO TesterScikit-LearniPerfglibc benchPostgreSQL pgbenchFlexible IO TesterFlexible IO TesterLevelDBLevelDBPostgreSQL pgbenchDaCapo Benchmarkglibc benchPostgreSQL pgbenchPostgreSQL pgbenchDaCapo BenchmarkTimed Linux Kernel CompilationApache HBaseNAS Parallel BenchmarksApache HBaseFlexible IO TesterRenaissanceFlexible IO TesterMKL-DNN DNNLRenaissanceFacebook RocksDBFacebook RocksDBRenaissanceMKL-DNN DNNLC-RayNAS Parallel BenchmarksEthrMKL-DNN DNNLLevelDBLevelDBLevelDBFacebook RocksDBFlexible IO TesterFlexible IO TesterLevelDBNAS Parallel BenchmarksRawTherapeeLevelDBLevelDBParboilRenaissanceLevelDBParboilLevelDBLevelDBParboilSMHasherFacebook RocksDBPyBenchMlpack BenchmarkMariaDBBasis UniversalSPECjbb 2015ParboilNAS Parallel BenchmarksSPECjbb 2015MariaDBSVT-AV1LevelDBRenaissanceStress-NGSMHasherAppleseedTungsten RendererRenaissanceNumpy BenchmarkSMHasherSMHasherIntel MPI BenchmarksIntel MPI BenchmarksTungsten RendererRenaissanceGROMACSNebular Empirical Analysis ToolSMHasherZstd CompressionDaCapo BenchmarkSMHasherIntel MPI BenchmarksSMHasherRodiniaglibc benchMKL-DNN DNNLSMHasherSMHasherSMHasherAppleseedSVT-AV1x264Stress-NGMKL-DNN DNNLSMHasherUbuntu 18.04.4 LTSUbuntu 20.04

Xeon Cascade Lake R Ubuntu 18.04 vs. 20.04 LTSglibc-bench: singlibc-bench: cosglibc-bench: expglibc-bench: sincosrodinia: OpenMP LavaMDnpb: EP.Dnpb: EP.Cmlpack: scikit_qdarocksdb: Rand Fill Syncstress-ng: Socket Activityfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directoryfio: Rand Write - IO_uring - Yes - No - 4KB - Default Test Directorymlpack: scikit_linearridgeregressionglibc-bench: asinhphpbench: PHP Benchmark Suitefio: Seq Write - IO_uring - Yes - No - 2MB - Default Test Directoryfio: Seq Write - IO_uring - Yes - No - 2MB - Default Test Directoryscikit-learn: iperf: 5201 - 10 Seconds - TCP - 64glibc-bench: sinhpgbench: Buffer Test - Heavy Contention - Read Writefio: Rand Write - IO_uring - Yes - No - 2MB - Default Test Directoryfio: Rand Write - IO_uring - Yes - No - 2MB - Default Test Directoryleveldb: Fill Syncleveldb: Fill Syncpgbench: Buffer Test - Normal Load - Read Writedacapobench: Tradebeansglibc-bench: log2pgbench: Buffer Test - Heavy Contention - Read Onlypgbench: Buffer Test - Normal Load - Read Onlydacapobench: Tradesoapbuild-linux-kernel: Time To Compilenpb: FT.Cfio: Seq Write - IO_uring - Yes - No - 4KB - Default Test Directoryrenaissance: In-Memory Database Shootoutfio: Seq Write - IO_uring - Yes - No - 4KB - Default Test Directorymkl-dnn: Recurrent Neural Network Training - f32renaissance: Rand Forestrocksdb: Seq Fillrocksdb: Rand Fillmkl-dnn: IP Batch All - bf16bf16bf16c-ray: Total Time - 4K, 16 Rays Per Pixelnpb: SP.Bleveldb: Seq Fillleveldb: Rand Deleteleveldb: Seq Fillrocksdb: Rand Readfio: Seq Read - IO_uring - Yes - No - 4KB - Default Test Directoryfio: Seq Read - IO_uring - Yes - No - 4KB - Default Test Directoryleveldb: Rand Readnpb: LU.Crawtherapee: Total Benchmark Timeleveldb: Rand Fillleveldb: Hot Readrenaissance: Scala Dottyleveldb: Rand Fillparboil: OpenMP CUTCPleveldb: Overwriteleveldb: Overwritesmhasher: wyhashrocksdb: Read While Writingpybench: Total For Average Test Timesmlpack: scikit_svmmysqlslap: 256basis: UASTC Level 2 + RDO Post-Processingspec-jbb2015: SPECjbb2015-Composite critical-jOPSparboil: OpenMP MRI Griddingnpb: BT.Cspec-jbb2015: SPECjbb2015-Composite max-jOPSmysqlslap: 128svt-av1: Enc Mode 8 - 1080pleveldb: Seek Randrenaissance: Apache Spark ALSstress-ng: Forkingsmhasher: t1ha2_atonceappleseed: Material Testertungsten: Water Causticrenaissance: Apache Spark Bayesnumpy: smhasher: t1ha0_aes_avx2smhasher: wyhashintel-mpi: IMB-MPI1 Sendrecvintel-mpi: IMB-MPI1 Exchangerenaissance: Genetic Algorithm Using Jenetics + Futuresgromacs: Water Benchmarkneat: smhasher: MeowHashcompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19dacapobench: Jythonsmhasher: t1ha2_atonceintel-mpi: IMB-MPI1 PingPongsmhasher: Spooky32rodinia: OpenMP CFD Solverglibc-bench: atanhmkl-dnn: Deconvolution Batch deconv_all - f32smhasher: fasthash32smhasher: t1ha0_aes_avx2smhasher: MeowHashappleseed: Emilysvt-av1: Enc Mode 4 - 1080px264: H.264 Video Encodingstress-ng: System V Message Passingmkl-dnn: Deconvolution Batch deconv_1d - bf16bf16bf16smhasher: Spooky32renaissance: Apache Spark PageRankoidn: Memorialarrayfire: Conjugate Gradient CPUtungsten: Hairtungsten: Volumetric Causticctx-clock: Context Switch Timerenaissance: Akka Unbalanced Cobwebbed Treemkl-dnn: IP Batch All - f32intel-mpi: IMB-MPI1 Exchangestress-ng: Semaphoresdacapobench: H2appleseed: Disney Materialintel-mpi: IMB-MPI1 Sendrecvfio: Rand Read - IO_uring - Yes - No - 4KB - Default Test Directoryembree: Pathtracer - Crownfio: Rand Read - IO_uring - Yes - No - 4KB - Default Test Directorynpb: MG.Cfio: Rand Read - IO_uring - Yes - No - 2MB - Default Test Directoryfio: Rand Read - IO_uring - Yes - No - 2MB - Default Test Directorybasis: ETC1Ssmhasher: fasthash32namd: ATPase Simulation - 327,506 Atomsmkl-dnn: Deconvolution Batch deconv_1d - f32basis: UASTC Level 3mkl-dnn: Convolution Batch conv_3d - f32embree: Pathtracer ISPC - Asian Dragon Objtoybrot: C++ Threadsmkl-dnn: Deconvolution Batch deconv_3d - f32rav1e: 10intel-mpi: IMB-P2P PingPongv-ray: CPUluxcorerender: Rainbow Colors and Prismmkl-dnn: Convolution Batch conv_googlenet_v3 - f32plaidml: No - Inference - IMDB LSTM - CPUembree: Pathtracer ISPC - Crownospray: XFrog Forest - SciViscompress-7zip: Compress Speed Testmkl-dnn: Deconvolution Batch deconv_3d - bf16bf16bf16rodinia: OpenMP Streamclustertoybrot: C++ Tasksplaidml: No - Inference - VGG16 - CPUnettle: sha512ospray: San Miguel - Path Tracermkl-dnn: Convolution Batch conv_3d - bf16bf16bf16nettle: chacharav1e: 6blender: Pabellon Barcelona - CPU-Onlyhimeno: Poisson Pressure Solvermkl-dnn: Deconvolution Batch deconv_all - bf16bf16bf16plaidml: No - Inference - Inception V3 - CPUblender: Classroom - CPU-Onlyblender: BMW27 - CPU-Onlymkl-dnn: Convolution Batch conv_alexnet - f32mkl-dnn: Convolution Batch conv_googlenet_v3 - bf16bf16bf16ethr: TCP - Bandwidth - 64mkl-dnn: IP Batch 1D - bf16bf16bf16blender: Fishy Cat - CPU-Onlyospray: NASA Streamlines - Path Tracermkl-dnn: Convolution Batch conv_all - bf16bf16bf16mkl-dnn: Convolution Batch conv_alexnet - bf16bf16bf16mkl-dnn: Convolution Batch conv_all - f32ospray: XFrog Forest - Path Tracernettle: poly1305-aesplaidml: No - Inference - ResNet 50 - CPUx265: H.265 1080p Video Encodingluxcorerender: DLSCfio: Seq Read - IO_uring - Yes - No - 2MB - Default Test Directoryembree: Pathtracer - Asian Dragon Objfio: Seq Read - IO_uring - Yes - No - 2MB - Default Test Directoryglibc-bench: pthread_onceblender: Barbershop - CPU-Onlyglibc-bench: tanhbuild-gcc: Time To Compileembree: Pathtracer - Asian Dragontoybrot: OpenMPbasis: UASTC Level 0nettle: aes256basis: UASTC Level 2embree: Pathtracer ISPC - Asian Dragonarrayfire: BLAS CPUglibc-bench: ffstensorflow: Cifar10ospray: Magnetic Reconnection - Path Tracerospray: Magnetic Reconnection - SciVisospray: NASA Streamlines - SciVisospray: San Miguel - SciVisiperf: 5201 - 10 Seconds - UDP - 64hbase: Rand Write - 64hbase: Rand Write - 64stress-ng: Context Switchingtungsten: Non-Exponentialmkl-dnn: IP Batch 1D - f32renaissance: Savina Reactors.IOparboil: OpenMP Stencilparboil: OpenMP LBMethr: TCP - Latency - 64Ubuntu 18.04.4 LTSUbuntu 20.0438994.239004.126423.338002.128.0531543.541516.56107.699540011070.951140004453.8317.840438417732966614.3862584312.661524824.0673983978016.81148.07627144.30921157459.41367529078.994353513646.202225839331.76443794.2518400016166.267720205.2116599.70416119516018137.939027.29846533.05760.471724.43110.5131641327405333158397.390100250.9959.71410.497.1577881.489765.0541.650149770.72410.317.9574917396117219.03392796.82933239370.65379995421.886317248251.832116.5797196.69177947.3622675.14193.09455624.63163859.123294.7325.84226540.312761.604079.196865.3033.70633.66853520.1410.417502425.3552839.5032.8009.54912.87481245.019877.8168156.4041.497185.4613376.346120.465890811.797.3692121044.2024412.59827.619.65310.819613.806411022869.68710.8549311.452101976.06875690.617827163.4133033329.0693129059085.362285113953.83425.0880.595792.1066328.2406.3840736.8134380692.730782.17619857439.231884399504.7955.1025850.2033.40817.141461449.4721611.5563814825.42486.753.9415.29341021.011.067209.433431.8433893137.905.38166.3260.84123.345187.854285432.833333335.8246398.4010.353924.66714.3871002.633.972790.374.3034.674.44235432.245611731.72961262.1213.60491064.94135.6791411758.7046156.9417.73042.99652382.601.7142876.2850047.6255.5643.4867.15391218443667714.386.937962.6002229170.9503.72233720.92304520.2449.103349.34615.7930115.907610.8113878.093772.8244.4420736721810.672073338092.2610.6000643680502101110.576350929.4257232671.53294550110098.5919.75133865.831471126637.91968619958.812512598121.393735724036.64050433.0020933314216.088817232.2765873.69318037817917334.128124.59551237.26834.142794.4839.6143977817372333145589.671108730.0764.7159.689.6907304.691825.1561.779553828.6129.619.1215231313110217.93416752.23335158350.608032100827.206672150949.258110.8116874.80074501.8423717.88184.66044423.56883694.303307.7524.90925612.522666.013940.766654.0073.59332.66555148.9610.115487924.6262758.2931.8679.28812.52291278.1810138.2069938.8940.485181.1841736.200117.836020407.717.2195720624.8923948.91128.149.83111.017614.057811222467.58510.6644316.832066514.87860989.13855166.0733566729.5266131059982.582318115554.56824.7650.602482.1300927.9406.3176237.1807384472.704202.15519682714.057971402844.8354.6589857.0233.16047.191470999.4181711.4923795225.29489.243.9615.21801025.9931.072208.463416.1927743149.575.40165.7160.62122.911187.199284466.222222225.8049598.1110.383914.06712.5111000.0733.982797.154.3134.754.45234932.304211711.72689261.8113.59021063.80935.7140412068.7106160.3417.72143.01372383.321.7140350047.6255.5643.4867.146813922922737428.147.171322.3696426200.9223.48966419.34039818.39OpenBenchmarking.org

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: sinUbuntu 18.04.4 LTSUbuntu 20.048K16K24K32K40KSE +/- 11.73, N = 3SE +/- 0.14, N = 338994.2049.10
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KMin: 38979.6 / Avg: 38994.2 / Max: 39017.4Min: 48.97 / Avg: 49.1 / Max: 49.38

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cosUbuntu 18.04.4 LTSUbuntu 20.048K16K24K32K40KSE +/- 10.33, N = 3SE +/- 0.01, N = 339004.1049.35
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cosUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KMin: 38988.9 / Avg: 39004.07 / Max: 39023.8Min: 49.34 / Avg: 49.35 / Max: 49.36

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: expUbuntu 18.04.4 LTSUbuntu 20.046K12K18K24K30KSE +/- 5.14922, N = 3SE +/- 0.00974, N = 326423.300005.79301
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: expUbuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KMin: 26414.7 / Avg: 26423.27 / Max: 26432.5Min: 5.77 / Avg: 5.79 / Max: 5.81

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sincosUbuntu 18.04.4 LTSUbuntu 20.048K16K24K32K40KSE +/- 53.71, N = 3SE +/- 0.00, N = 338002.1015.91
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sincosUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KMin: 37947.1 / Avg: 38002.1 / Max: 38109.5Min: 15.91 / Avg: 15.91 / Max: 15.91

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDUbuntu 18.04.4 LTSUbuntu 20.04714212835SE +/- 0.07, N = 3SE +/- 0.05, N = 328.0510.811. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDUbuntu 18.04.4 LTSUbuntu 20.04612182430Min: 27.95 / Avg: 28.05 / Max: 28.18Min: 10.75 / Avg: 10.81 / Max: 10.91. (CXX) g++ options: -O2 -lOpenCL

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DUbuntu 18.04.4 LTSUbuntu 20.048001600240032004000SE +/- 4.71, N = 3SE +/- 55.56, N = 41543.543878.091. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DUbuntu 18.04.4 LTSUbuntu 20.047001400210028003500Min: 1535.7 / Avg: 1543.54 / Max: 1551.99Min: 3713.12 / Avg: 3878.09 / Max: 3948.681. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CUbuntu 18.04.4 LTSUbuntu 20.048001600240032004000SE +/- 24.21, N = 3SE +/- 46.97, N = 31516.563772.821. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CUbuntu 18.04.4 LTSUbuntu 20.047001400210028003500Min: 1469.6 / Avg: 1516.56 / Max: 1550.26Min: 3679.16 / Avg: 3772.82 / Max: 3825.891. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaUbuntu 18.04.4 LTSUbuntu 20.0420406080100SE +/- 1.17, N = 3SE +/- 0.64, N = 4107.6944.44
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaUbuntu 18.04.4 LTSUbuntu 20.0420406080100Min: 105.98 / Avg: 107.69 / Max: 109.94Min: 43.06 / Avg: 44.44 / Max: 46.14

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 Fill SyncUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KSE +/- 137.09, N = 3SE +/- 322.11, N = 3954002073671. (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 SyncUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KMin: 95206 / Avg: 95400.33 / Max: 95665Min: 206771 / Avg: 207366.67 / Max: 2078771. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -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: Socket ActivityUbuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KSE +/- 40.05, N = 3SE +/- 150.25, N = 311070.9521810.671. (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 ActivityUbuntu 18.04.4 LTSUbuntu 20.044K8K12K16K20KMin: 10990.99 / Avg: 11070.95 / Max: 11115.09Min: 21559.18 / Avg: 21810.67 / Max: 22078.871. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KSE +/- 1154.70, N = 3SE +/- 881.92, N = 31140002073331. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KMin: 112000 / Avg: 114000 / Max: 116000Min: 206000 / Avg: 207333.33 / Max: 2090001. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 3.48, N = 3SE +/- 2.96, N = 34458091. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.04140280420560700Min: 439 / Avg: 445.33 / Max: 451Min: 805 / Avg: 809.33 / Max: 8151. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionUbuntu 18.04.4 LTSUbuntu 20.040.86181.72362.58543.44724.309SE +/- 0.05, N = 3SE +/- 0.03, N = 33.832.26
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 3.74 / Avg: 3.83 / Max: 3.88Min: 2.21 / Avg: 2.26 / Max: 2.31

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: asinhUbuntu 18.04.4 LTSUbuntu 20.0448121620SE +/- 0.02, N = 3SE +/- 0.00, N = 317.8410.60
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: asinhUbuntu 18.04.4 LTSUbuntu 20.04510152025Min: 17.82 / Avg: 17.84 / Max: 17.87Min: 10.6 / Avg: 10.6 / Max: 10.61

PHPBench

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

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteUbuntu 18.04.4 LTSUbuntu 20.04140K280K420K560K700KSE +/- 446.81, N = 3SE +/- 879.62, N = 3384177643680
OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteUbuntu 18.04.4 LTSUbuntu 20.04110K220K330K440K550KMin: 383285 / Avg: 384177.33 / Max: 384665Min: 642290 / Avg: 643680.33 / Max: 645309

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.04110220330440550SE +/- 2.19, N = 3SE +/- 2.33, N = 33295021. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0490180270360450Min: 325 / Avg: 329.33 / Max: 332Min: 498 / Avg: 501.67 / Max: 5061. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 4.04, N = 3SE +/- 4.67, N = 366610111. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 658 / Avg: 666 / Max: 671Min: 1004 / Avg: 1011.33 / Max: 10201. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Scikit-Learn

Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.1Ubuntu 18.04.4 LTSUbuntu 20.0448121620SE +/- 0.14, N = 3SE +/- 0.06, N = 314.3910.58
OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.1Ubuntu 18.04.4 LTSUbuntu 20.0448121620Min: 14.22 / Avg: 14.39 / Max: 14.66Min: 10.51 / Avg: 10.58 / Max: 10.7

iPerf

iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64Ubuntu 18.04.4 LTSUbuntu 20.048K16K24K32K40KSE +/- 28.47, N = 3SE +/- 224.99, N = 325843350921. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64Ubuntu 18.04.4 LTSUbuntu 20.046K12K18K24K30KMin: 25800 / Avg: 25843.33 / Max: 25897Min: 34648 / Avg: 35092.33 / Max: 353761. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm

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: sinhUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.01505, N = 3SE +/- 0.00382, N = 312.661509.42572
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinhUbuntu 18.04.4 LTSUbuntu 20.0448121620Min: 12.64 / Avg: 12.66 / Max: 12.69Min: 9.42 / Avg: 9.43 / Max: 9.43

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: Heavy Contention - Mode: Read WriteUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KSE +/- 333.98, N = 3SE +/- 65.46, N = 324824.0732671.531. (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: Heavy Contention - Mode: Read WriteUbuntu 18.04.4 LTSUbuntu 20.046K12K18K24K30KMin: 24157.57 / Avg: 24824.07 / Max: 25195.51Min: 32557.07 / Avg: 32671.53 / Max: 32783.791. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.04110220330440550SE +/- 2.52, N = 3SE +/- 1.73, N = 33975011. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0490180270360450Min: 392 / Avg: 397 / Max: 400Min: 498 / Avg: 501 / Max: 5041. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 4.67, N = 3SE +/- 3.46, N = 380110091. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 792 / Avg: 801.33 / Max: 806Min: 1003 / Avg: 1009 / Max: 10151. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncUbuntu 18.04.4 LTSUbuntu 20.04246810SE +/- 0.07, N = 3SE +/- 0.09, N = 36.88.51. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill SyncUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 6.7 / Avg: 6.83 / Max: 6.9Min: 8.4 / Avg: 8.53 / Max: 8.71. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 17.38, N = 3SE +/- 7.63, N = 31148.08919.751. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill SyncUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1130.35 / Avg: 1148.08 / Max: 1182.83Min: 905.38 / Avg: 919.75 / Max: 931.361. (CXX) g++ options: -O3 -lsnappy -lpthread

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 WriteUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KSE +/- 27.08, N = 3SE +/- 410.50, N = 627144.3133865.831. (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 WriteUbuntu 18.04.4 LTSUbuntu 20.046K12K18K24K30KMin: 27112.67 / Avg: 27144.31 / Max: 27198.21Min: 32650.24 / Avg: 33865.83 / Max: 35073.21. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansUbuntu 18.04.4 LTSUbuntu 20.043K6K9K12K15KSE +/- 113.06, N = 20SE +/- 117.20, N = 201574512663
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansUbuntu 18.04.4 LTSUbuntu 20.043K6K9K12K15KMin: 14976 / Avg: 15745.45 / Max: 16941Min: 12065 / Avg: 12662.8 / Max: 13822

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: log2Ubuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.00067, N = 3SE +/- 0.02357, N = 39.413677.91968
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: log2Ubuntu 18.04.4 LTSUbuntu 20.043691215Min: 9.41 / Avg: 9.41 / Max: 9.42Min: 7.89 / Avg: 7.92 / Max: 7.96

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: Heavy Contention - Mode: Read OnlyUbuntu 18.04.4 LTSUbuntu 20.04130K260K390K520K650KSE +/- 1214.19, N = 3SE +/- 998.62, N = 3529078.99619958.811. (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: Heavy Contention - Mode: Read OnlyUbuntu 18.04.4 LTSUbuntu 20.04110K220K330K440K550KMin: 527785.08 / Avg: 529078.99 / Max: 531505.59Min: 618259.05 / Avg: 619958.81 / Max: 621716.891. (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 OnlyUbuntu 18.04.4 LTSUbuntu 20.04130K260K390K520K650KSE +/- 1232.50, N = 3SE +/- 1598.05, N = 3513646.20598121.391. (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 OnlyUbuntu 18.04.4 LTSUbuntu 20.04100K200K300K400K500KMin: 511219.89 / Avg: 513646.2 / Max: 515236.12Min: 596218.31 / Avg: 598121.39 / Max: 601296.671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapUbuntu 18.04.4 LTSUbuntu 20.042K4K6K8K10KSE +/- 63.00, N = 3SE +/- 56.81, N = 483937240
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapUbuntu 18.04.4 LTSUbuntu 20.0415003000450060007500Min: 8267 / Avg: 8393 / Max: 8456Min: 7089 / Avg: 7240 / Max: 7355

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 CompileUbuntu 18.04.4 LTSUbuntu 20.04816243240SE +/- 0.26, N = 13SE +/- 0.28, N = 1331.7636.64
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileUbuntu 18.04.4 LTSUbuntu 20.04816243240Min: 31.41 / Avg: 31.76 / Max: 34.91Min: 36.27 / Avg: 36.64 / Max: 39.95

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.CUbuntu 18.04.4 LTSUbuntu 20.0411K22K33K44K55KSE +/- 78.80, N = 3SE +/- 164.88, N = 343794.2550433.001. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CUbuntu 18.04.4 LTSUbuntu 20.049K18K27K36K45KMin: 43661.92 / Avg: 43794.25 / Max: 43934.54Min: 50110.5 / Avg: 50433 / Max: 50653.81. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KSE +/- 1000.00, N = 3SE +/- 2027.59, N = 31840002093331. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KMin: 183000 / Avg: 184000 / Max: 186000Min: 206000 / Avg: 209333.33 / Max: 2130001. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database ShootoutUbuntu 18.04.4 LTSUbuntu 20.043K6K9K12K15KSE +/- 62.14, N = 5SE +/- 125.24, N = 516166.2714216.09
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database ShootoutUbuntu 18.04.4 LTSUbuntu 20.043K6K9K12K15KMin: 16010.94 / Avg: 16166.27 / Max: 16303.19Min: 13850.07 / Avg: 14216.09 / Max: 14563.79

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 4.26, N = 3SE +/- 7.54, N = 37208171. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.04140280420560700Min: 714 / Avg: 719.67 / Max: 728Min: 805 / Avg: 817.33 / Max: 8311. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -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: Recurrent Neural Network Training - Data Type: f32Ubuntu 18.04.4 LTSUbuntu 20.0450100150200250SE +/- 2.63, N = 5SE +/- 2.71, N = 3205.21232.28MIN: 194.86MIN: 220.41. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.044080120160200Min: 198.93 / Avg: 205.21 / Max: 211.42Min: 227.44 / Avg: 232.28 / Max: 236.821. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Random ForestUbuntu 18.04.4 LTSUbuntu 20.0414002800420056007000SE +/- 78.18, N = 5SE +/- 66.22, N = 76599.705873.69
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Random ForestUbuntu 18.04.4 LTSUbuntu 20.0411002200330044005500Min: 6357.18 / Avg: 6599.7 / Max: 6846.26Min: 5650.91 / Avg: 5873.69 / Max: 6079.83

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 FillUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KSE +/- 116.86, N = 3SE +/- 265.64, N = 31611951803781. (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 FillUbuntu 18.04.4 LTSUbuntu 20.0430K60K90K120K150KMin: 160966 / Avg: 161195 / Max: 161350Min: 180091 / Avg: 180378.33 / Max: 1809091. (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 FillUbuntu 18.04.4 LTSUbuntu 20.0440K80K120K160K200KSE +/- 180.36, N = 3SE +/- 186.85, N = 31601811791731. (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 FillUbuntu 18.04.4 LTSUbuntu 20.0430K60K90K120K150KMin: 159823 / Avg: 160180.67 / Max: 160400Min: 178911 / Avg: 179173.33 / Max: 1795351. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.04918273645SE +/- 0.33, N = 3SE +/- 0.38, N = 337.9434.13MIN: 28.05MIN: 22.841. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.04816243240Min: 37.28 / Avg: 37.94 / Max: 38.38Min: 33.46 / Avg: 34.13 / Max: 34.781. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

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 PixelUbuntu 18.04.4 LTSUbuntu 20.04612182430SE +/- 0.01, N = 3SE +/- 0.23, N = 1527.3024.601. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelUbuntu 18.04.4 LTSUbuntu 20.04612182430Min: 27.28 / Avg: 27.3 / Max: 27.32Min: 23.99 / Avg: 24.59 / Max: 26.981. (CC) gcc options: -lm -lpthread -O3

NAS Parallel Benchmarks

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

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BUbuntu 18.04.4 LTSUbuntu 20.0411K22K33K44K55KSE +/- 79.92, N = 3SE +/- 85.67, N = 346533.0551237.261. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BUbuntu 18.04.4 LTSUbuntu 20.049K18K27K36K45KMin: 46384.95 / Avg: 46533.05 / Max: 46659.16Min: 51100.99 / Avg: 51237.26 / Max: 51395.351. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 3.49, N = 3SE +/- 0.98, N = 3760.47834.141. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential FillUbuntu 18.04.4 LTSUbuntu 20.04150300450600750Min: 756.93 / Avg: 760.47 / Max: 767.46Min: 833.12 / Avg: 834.14 / Max: 836.111. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 3.47, N = 3SE +/- 1.29, N = 3724.43794.481. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random DeleteUbuntu 18.04.4 LTSUbuntu 20.04140280420560700Min: 720.6 / Avg: 724.43 / Max: 731.35Min: 792.47 / Avg: 794.48 / Max: 796.891. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.03, N = 3SE +/- 0.03, N = 310.59.61. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential FillUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 10.4 / Avg: 10.47 / Max: 10.5Min: 9.5 / Avg: 9.57 / Max: 9.61. (CXX) g++ options: -O3 -lsnappy -lpthread

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 ReadUbuntu 18.04.4 LTSUbuntu 20.0430M60M90M120M150MSE +/- 88585.09, N = 3SE +/- 198479.03, N = 31316413271439778171. (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 ReadUbuntu 18.04.4 LTSUbuntu 20.0420M40M60M80M100MMin: 131516608 / Avg: 131641327.33 / Max: 131812663Min: 143582084 / Avg: 143977816.67 / Max: 1442026741. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0490K180K270K360K450KSE +/- 333.33, N = 3SE +/- 666.67, N = 34053333723331. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0470K140K210K280K350KMin: 405000 / Avg: 405333.33 / Max: 406000Min: 371000 / Avg: 372333.33 / Max: 3730001. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0430060090012001500SE +/- 1.86, N = 3SE +/- 3.06, N = 3158314551. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0430060090012001500Min: 1581 / Avg: 1583.33 / Max: 1587Min: 1449 / Avg: 1455 / Max: 14591. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadUbuntu 18.04.4 LTSUbuntu 20.0420406080100SE +/- 0.38, N = 3SE +/- 0.57, N = 397.3989.671. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random ReadUbuntu 18.04.4 LTSUbuntu 20.0420406080100Min: 96.81 / Avg: 97.39 / Max: 98.11Min: 88.56 / Avg: 89.67 / Max: 90.451. (CXX) g++ options: -O3 -lsnappy -lpthread

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.CUbuntu 18.04.4 LTSUbuntu 20.0420K40K60K80K100KSE +/- 220.22, N = 3SE +/- 76.90, N = 3100250.99108730.071. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CUbuntu 18.04.4 LTSUbuntu 20.0420K40K60K80K100KMin: 99815.87 / Avg: 100250.99 / Max: 100527.68Min: 108593.08 / Avg: 108730.07 / Max: 108859.121. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4

RawTherapee

RawTherapee is a cross-platform, open-source multi-threaded RAW image processing program. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeUbuntu 18.04.4 LTSUbuntu 20.041428425670SE +/- 0.28, N = 3SE +/- 0.29, N = 359.7164.721. Ubuntu 18.04.4 LTS: RawTherapee, version 5.3, command line An advanced, cross-platform program for developing raw photos. Website: http://www.rawtherapee.com/ Documentation: http://rawpedia.rawtherapee.com/ Forum: https://discuss.pixls.us/c/software/rawtherapee Code and bug reports: https://github.com/Beep6581/RawTherapee Symbols: <Chevrons> indicate parameters you can change. [Square brackets] mean the parameter is optional. The pipe symbol | indicates a choice of one or the other. The dash symbol - denotes a range of possible values from one to the other. Usage: rawtherapee-cli -c <dir>|<files> Convert files in batch with default parameters. rawtherapee-cli <other options> -c <dir>|<files> Convert files in batch with your own settings. Options: rawtherapee-cli[-o <output>|-O <output>] [-q] [-a] [-s|-S] [-p <one.pp3> [-p <two.pp3> ...] ] [-d] [ -j[1-100] [-js<1-3>] | [-b<8|16>] [-t[z] | [-n]] ] [-Y] [-f] -c <input> -c <files> Specify one or more input files or directory. When specifying directories, Rawtherapee will look for images files that comply with the selected extensions (see also '-a'). -c must be the last option. -o <file>|<dir> Set output file or folder. Saves output file alongside input file if -o is not specified. -O <file>|<dir> Set output file or folder and copy pp3 file into it. Saves output file alongside input file if -O is not specified. -q Quick-start mode. Does not load cached files to speedup start time. -a Process all supported image file types when specifying a folder, even those not currently selected in Preferences > File Browser > Parsed Extensions. -s Use the existing sidecar file to build the processing parameters, e.g. for photo.raw there should be a photo.raw.pp3 file in the same folder. If the sidecar file does not exist, neutral values will be used. -S Like -s but skip if the sidecar file does not exist. -p <file.pp3> Specify processing profile to be used for all conversions. You can specify as many sets of "-p <file.pp3>" options as you like, each will be built on top of the previous one, as explained below. -d Use the default raw or non-raw processing profile as set in Preferences > Image Processing > Default Processing Profile -j[1-100] Specify output to be JPEG (default, if -t and -n are not set). Optionally, specify compression 1-100 (default value: 92). -js<1-3> Specify the JPEG chroma subsampling parameter, where: 1 = Best compression: 2x2, 1x1, 1x1 (4:2:0) Chroma halved vertically and horizontally. 2 = Balanced (default): 2x1, 1x1, 1x1 (4:2:2) Chroma halved horizontally. 3 = Best quality: 1x1, 1x1, 1x1 (4:4:4) No chroma subsampling. -b<8|16> Specify bit depth per channel (default value: 16 for TIFF, 8 for PNG). Only applies to TIFF and PNG output, JPEG is always 8. -t[z] Specify output to be TIFF. Uncompressed by default, or deflate compression with 'z'. -n Specify output to be compressed PNG. Compression is hard-coded to 6. -Y Overwrite output if present. -f Use the custom fast-export processing pipeline. Your pp3 files can be incomplete, RawTherapee will build the final values as follows: 1- A new processing profile is created using neutral values, 2- If the "-d" option is set, the values are overridden by those found in the default raw or non-raw processing profile. 3- If one or more "-p" options are set, the values are overridden by those found in these processing profiles. 4- If the "-s" or "-S" options are set, the values are finally overridden by those found in the sidecar files. The processing profiles are processed in the order specified on the command line. 2. Ubuntu 20.04: RawTherapee, version 5.8, command line.
OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark TimeUbuntu 18.04.4 LTSUbuntu 20.041326395265Min: 59.15 / Avg: 59.71 / Max: 60.01Min: 64.34 / Avg: 64.72 / Max: 65.291. Ubuntu 18.04.4 LTS: RawTherapee, version 5.3, command line An advanced, cross-platform program for developing raw photos. Website: http://www.rawtherapee.com/ Documentation: http://rawpedia.rawtherapee.com/ Forum: https://discuss.pixls.us/c/software/rawtherapee Code and bug reports: https://github.com/Beep6581/RawTherapee Symbols: <Chevrons> indicate parameters you can change. [Square brackets] mean the parameter is optional. The pipe symbol | indicates a choice of one or the other. The dash symbol - denotes a range of possible values from one to the other. Usage: rawtherapee-cli -c <dir>|<files> Convert files in batch with default parameters. rawtherapee-cli <other options> -c <dir>|<files> Convert files in batch with your own settings. Options: rawtherapee-cli[-o <output>|-O <output>] [-q] [-a] [-s|-S] [-p <one.pp3> [-p <two.pp3> ...] ] [-d] [ -j[1-100] [-js<1-3>] | [-b<8|16>] [-t[z] | [-n]] ] [-Y] [-f] -c <input> -c <files> Specify one or more input files or directory. When specifying directories, Rawtherapee will look for images files that comply with the selected extensions (see also '-a'). -c must be the last option. -o <file>|<dir> Set output file or folder. Saves output file alongside input file if -o is not specified. -O <file>|<dir> Set output file or folder and copy pp3 file into it. Saves output file alongside input file if -O is not specified. -q Quick-start mode. Does not load cached files to speedup start time. -a Process all supported image file types when specifying a folder, even those not currently selected in Preferences > File Browser > Parsed Extensions. -s Use the existing sidecar file to build the processing parameters, e.g. for photo.raw there should be a photo.raw.pp3 file in the same folder. If the sidecar file does not exist, neutral values will be used. -S Like -s but skip if the sidecar file does not exist. -p <file.pp3> Specify processing profile to be used for all conversions. You can specify as many sets of "-p <file.pp3>" options as you like, each will be built on top of the previous one, as explained below. -d Use the default raw or non-raw processing profile as set in Preferences > Image Processing > Default Processing Profile -j[1-100] Specify output to be JPEG (default, if -t and -n are not set). Optionally, specify compression 1-100 (default value: 92). -js<1-3> Specify the JPEG chroma subsampling parameter, where: 1 = Best compression: 2x2, 1x1, 1x1 (4:2:0) Chroma halved vertically and horizontally. 2 = Balanced (default): 2x1, 1x1, 1x1 (4:2:2) Chroma halved horizontally. 3 = Best quality: 1x1, 1x1, 1x1 (4:4:4) No chroma subsampling. -b<8|16> Specify bit depth per channel (default value: 16 for TIFF, 8 for PNG). Only applies to TIFF and PNG output, JPEG is always 8. -t[z] Specify output to be TIFF. Uncompressed by default, or deflate compression with 'z'. -n Specify output to be compressed PNG. Compression is hard-coded to 6. -Y Overwrite output if present. -f Use the custom fast-export processing pipeline. Your pp3 files can be incomplete, RawTherapee will build the final values as follows: 1- A new processing profile is created using neutral values, 2- If the "-d" option is set, the values are overridden by those found in the default raw or non-raw processing profile. 3- If one or more "-p" options are set, the values are overridden by those found in these processing profiles. 4- If the "-s" or "-S" options are set, the values are finally overridden by those found in the sidecar files. The processing profiles are processed in the order specified on the command line. 2. Ubuntu 20.04: RawTherapee, version 5.8, command line.

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.03, N = 3SE +/- 0.03, N = 310.49.61. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random FillUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 10.3 / Avg: 10.37 / Max: 10.4Min: 9.6 / Avg: 9.63 / Max: 9.71. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadUbuntu 18.04.4 LTSUbuntu 20.0420406080100SE +/- 0.87, N = 12SE +/- 1.28, N = 497.1689.691. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot ReadUbuntu 18.04.4 LTSUbuntu 20.0420406080100Min: 88.32 / Avg: 97.16 / Max: 100.12Min: 86.03 / Avg: 89.69 / Max: 91.711. (CXX) g++ options: -O3 -lsnappy -lpthread

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Scala DottyUbuntu 18.04.4 LTSUbuntu 20.042K4K6K8K10KSE +/- 58.54, N = 5SE +/- 84.37, N = 57881.497304.69
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Scala DottyUbuntu 18.04.4 LTSUbuntu 20.0414002800420056007000Min: 7701.74 / Avg: 7881.49 / Max: 8017.12Min: 7132.9 / Avg: 7304.69 / Max: 7556.96

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 2.37, N = 3SE +/- 3.99, N = 3765.05825.161. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random FillUbuntu 18.04.4 LTSUbuntu 20.04140280420560700Min: 761.32 / Avg: 765.05 / Max: 769.44Min: 818.11 / Avg: 825.16 / Max: 831.931. (CXX) g++ options: -O3 -lsnappy -lpthread

Parboil

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

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPUbuntu 18.04.4 LTSUbuntu 20.040.40040.80081.20121.60162.002SE +/- 0.010399, N = 3SE +/- 0.020126, N = 71.6501491.7795531. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 1.64 / Avg: 1.65 / Max: 1.67Min: 1.73 / Avg: 1.78 / Max: 1.871. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 1.17, N = 3SE +/- 2.58, N = 3770.72828.611. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: OverwriteUbuntu 18.04.4 LTSUbuntu 20.04150300450600750Min: 768.4 / Avg: 770.72 / Max: 772.07Min: 824.75 / Avg: 828.61 / Max: 833.511. (CXX) g++ options: -O3 -lsnappy -lpthread

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.03, N = 3SE +/- 0.03, N = 310.39.61. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: OverwriteUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 10.3 / Avg: 10.33 / Max: 10.4Min: 9.5 / Avg: 9.57 / Max: 9.61. (CXX) g++ options: -O3 -lsnappy -lpthread

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: wyhashUbuntu 18.04.4 LTSUbuntu 20.04510152025SE +/- 0.00, N = 3SE +/- 0.29, N = 317.9619.121. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: wyhashUbuntu 18.04.4 LTSUbuntu 20.04510152025Min: 17.95 / Avg: 17.96 / Max: 17.96Min: 18.83 / Avg: 19.12 / Max: 19.711. (CXX) g++ options: -march=native -O3 -lpthread

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 WritingUbuntu 18.04.4 LTSUbuntu 20.041.1M2.2M3.3M4.4M5.5MSE +/- 41549.28, N = 3SE +/- 39541.61, N = 3491739652313131. (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 WritingUbuntu 18.04.4 LTSUbuntu 20.04900K1800K2700K3600K4500KMin: 4841616 / Avg: 4917395.67 / Max: 4984817Min: 5180741 / Avg: 5231312.67 / Max: 53092531. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesUbuntu 18.04.4 LTSUbuntu 20.0430060090012001500SE +/- 1.20, N = 311721102
OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1170 / Avg: 1172.33 / Max: 1174

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmUbuntu 18.04.4 LTSUbuntu 20.04510152025SE +/- 0.03, N = 3SE +/- 0.07, N = 319.0317.93
OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmUbuntu 18.04.4 LTSUbuntu 20.04510152025Min: 18.96 / Avg: 19.03 / Max: 19.07Min: 17.79 / Avg: 17.93 / Max: 18.02

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 256Ubuntu 18.04.4 LTSUbuntu 20.0490180270360450SE +/- 0.42, N = 3SE +/- 0.72, N = 33924161. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -lbz2 -lsnappy -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 256Ubuntu 18.04.4 LTSUbuntu 20.0470140210280350Min: 390.93 / Avg: 391.75 / Max: 392.31Min: 414.94 / Avg: 416.38 / Max: 417.191. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -lbz2 -lsnappy -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-ProcessingUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 7.30, N = 3SE +/- 0.93, N = 3796.83752.231. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-ProcessingUbuntu 18.04.4 LTSUbuntu 20.04140280420560700Min: 788.8 / Avg: 796.83 / Max: 811.41Min: 750.43 / Avg: 752.23 / Max: 753.541. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

SPECjbb 2015

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

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite critical-jOPSUbuntu 18.04.4 LTSUbuntu 20.048K16K24K32K40K3323935158

Parboil

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

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingUbuntu 18.04.4 LTSUbuntu 20.0480160240320400SE +/- 3.22, N = 3SE +/- 2.22, N = 3370.65350.611. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingUbuntu 18.04.4 LTSUbuntu 20.0470140210280350Min: 365.55 / Avg: 370.65 / Max: 376.6Min: 346.6 / Avg: 350.61 / Max: 354.251. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

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.CUbuntu 18.04.4 LTSUbuntu 20.0420K40K60K80K100KSE +/- 160.56, N = 3SE +/- 104.39, N = 395421.88100827.201. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CUbuntu 18.04.4 LTSUbuntu 20.0420K40K60K80K100KMin: 95243.41 / Avg: 95421.88 / Max: 95742.31Min: 100647.17 / Avg: 100827.2 / Max: 101008.781. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4

SPECjbb 2015

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

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite max-jOPSUbuntu 18.04.4 LTSUbuntu 20.0414K28K42K56K70K6317266721

MariaDB

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

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 128Ubuntu 18.04.4 LTSUbuntu 20.04110220330440550SE +/- 1.10, N = 3SE +/- 0.15, N = 34825091. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -lbz2 -lsnappy -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 128Ubuntu 18.04.4 LTSUbuntu 20.0490180270360450Min: 480.08 / Avg: 482.17 / Max: 483.79Min: 508.65 / Avg: 508.91 / Max: 509.161. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -lbz2 -lsnappy -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pUbuntu 18.04.4 LTSUbuntu 20.041224364860SE +/- 0.70, N = 3SE +/- 0.23, N = 351.8349.261. (CXX) g++ options: -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pUbuntu 18.04.4 LTSUbuntu 20.041020304050Min: 50.5 / Avg: 51.83 / Max: 52.85Min: 48.9 / Avg: 49.26 / Max: 49.681. (CXX) g++ options: -fPIE -fPIC -pie

LevelDB

LevelDB is a key-value storage library developed by Google that supports making use of Snappy for data compression and has other modern features. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomUbuntu 18.04.4 LTSUbuntu 20.04306090120150SE +/- 0.27, N = 3SE +/- 1.04, N = 3116.58110.811. (CXX) g++ options: -O3 -lsnappy -lpthread
OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek RandomUbuntu 18.04.4 LTSUbuntu 20.0420406080100Min: 116.05 / Avg: 116.58 / Max: 116.97Min: 109.43 / Avg: 110.81 / Max: 112.851. (CXX) g++ options: -O3 -lsnappy -lpthread

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSUbuntu 18.04.4 LTSUbuntu 20.0415003000450060007500SE +/- 83.03, N = 5SE +/- 68.38, N = 57196.696874.80
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALSUbuntu 18.04.4 LTSUbuntu 20.0412002400360048006000Min: 7041.28 / Avg: 7196.69 / Max: 7491.65Min: 6720.15 / Avg: 6874.8 / Max: 7071.5

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: ForkingUbuntu 18.04.4 LTSUbuntu 20.0420K40K60K80K100KSE +/- 499.77, N = 3SE +/- 1261.17, N = 377947.3674501.841. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: ForkingUbuntu 18.04.4 LTSUbuntu 20.0414K28K42K56K70KMin: 77358.89 / Avg: 77947.36 / Max: 78941.29Min: 72500.24 / Avg: 74501.84 / Max: 76831.881. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: t1ha2_atonceUbuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KSE +/- 6.26, N = 3SE +/- 1.86, N = 322675.1423717.881. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: t1ha2_atonceUbuntu 18.04.4 LTSUbuntu 20.044K8K12K16K20KMin: 22668.86 / Avg: 22675.14 / Max: 22687.66Min: 23715.89 / Avg: 23717.88 / Max: 23721.591. (CXX) g++ options: -march=native -O3 -lpthread

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 TesterUbuntu 18.04.4 LTSUbuntu 20.044080120160200193.09184.66

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 CausticUbuntu 18.04.4 LTSUbuntu 20.04612182430SE +/- 0.16, N = 3SE +/- 0.14, N = 324.6323.571. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water CausticUbuntu 18.04.4 LTSUbuntu 20.04612182430Min: 24.34 / Avg: 24.63 / Max: 24.91Min: 23.29 / Avg: 23.57 / Max: 23.771. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark BayesUbuntu 18.04.4 LTSUbuntu 20.048001600240032004000SE +/- 43.93, N = 5SE +/- 49.41, N = 203859.123694.30
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark BayesUbuntu 18.04.4 LTSUbuntu 20.047001400210028003500Min: 3720.31 / Avg: 3859.12 / Max: 3993.63Min: 3349.62 / Avg: 3694.3 / Max: 4273.33

Numpy Benchmark

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

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkUbuntu 18.04.4 LTSUbuntu 20.0470140210280350SE +/- 0.38, N = 3SE +/- 0.56, N = 3294.73307.75
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkUbuntu 18.04.4 LTSUbuntu 20.0460120180240300Min: 293.98 / Avg: 294.73 / Max: 295.26Min: 307.08 / Avg: 307.75 / Max: 308.86

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: t1ha0_aes_avx2Ubuntu 18.04.4 LTSUbuntu 20.04612182430SE +/- 0.02, N = 3SE +/- 0.01, N = 325.8424.911. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: t1ha0_aes_avx2Ubuntu 18.04.4 LTSUbuntu 20.04612182430Min: 25.82 / Avg: 25.84 / Max: 25.88Min: 24.89 / Avg: 24.91 / Max: 24.931. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: wyhashUbuntu 18.04.4 LTSUbuntu 20.046K12K18K24K30KSE +/- 4.26, N = 3SE +/- 5.85, N = 326540.3125612.521. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: wyhashUbuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KMin: 26533.09 / Avg: 26540.31 / Max: 26547.85Min: 25600.82 / Avg: 25612.52 / Max: 25618.591. (CXX) g++ options: -march=native -O3 -lpthread

Intel MPI Benchmarks

Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 SendrecvUbuntu 18.04.4 LTSUbuntu 20.046001200180024003000SE +/- 5.97, N = 3SE +/- 12.41, N = 32761.602666.01MAX: 10486.15MAX: 9882.11. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 SendrecvUbuntu 18.04.4 LTSUbuntu 20.045001000150020002500Min: 2753.4 / Avg: 2761.6 / Max: 2773.21Min: 2643.95 / Avg: 2666.01 / Max: 2686.91. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 ExchangeUbuntu 18.04.4 LTSUbuntu 20.049001800270036004500SE +/- 27.54, N = 3SE +/- 9.13, N = 34079.193940.76MAX: 18359.49MAX: 17730.281. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 ExchangeUbuntu 18.04.4 LTSUbuntu 20.047001400210028003500Min: 4024.2 / Avg: 4079.19 / Max: 4109.4Min: 3927.96 / Avg: 3940.76 / Max: 3958.441. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Genetic Algorithm Using Jenetics + FuturesUbuntu 18.04.4 LTSUbuntu 20.0415003000450060007500SE +/- 33.79, N = 5SE +/- 32.60, N = 56865.306654.01
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Genetic Algorithm Using Jenetics + FuturesUbuntu 18.04.4 LTSUbuntu 20.0412002400360048006000Min: 6739.57 / Avg: 6865.3 / Max: 6941.44Min: 6584.37 / Avg: 6654.01 / Max: 6741.05

GROMACS

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

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020Water BenchmarkUbuntu 18.04.4 LTSUbuntu 20.040.83391.66782.50173.33564.1695SE +/- 0.011, N = 3SE +/- 0.006, N = 33.7063.5931. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020Water BenchmarkUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 3.69 / Avg: 3.71 / Max: 3.73Min: 3.58 / Avg: 3.59 / Max: 3.61. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Nebular Empirical Analysis Tool

NEAT is the Nebular Empirical Analysis Tool for empirical analysis of ionised nebulae, with uncertainty propagation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-29Ubuntu 18.04.4 LTSUbuntu 20.04816243240SE +/- 0.28, N = 15SE +/- 0.05, N = 333.6732.671. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace
OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-29Ubuntu 18.04.4 LTSUbuntu 20.04714212835Min: 31.91 / Avg: 33.67 / Max: 35.3Min: 32.6 / Avg: 32.67 / Max: 32.751. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: MeowHashUbuntu 18.04.4 LTSUbuntu 20.0412K24K36K48K60KSE +/- 92.78, N = 3SE +/- 2.02, N = 353520.1455148.961. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: MeowHashUbuntu 18.04.4 LTSUbuntu 20.0410K20K30K40K50KMin: 53335.19 / Avg: 53520.14 / Max: 53625.63Min: 55144.92 / Avg: 55148.96 / Max: 55151.131. (CXX) g++ options: -march=native -O3 -lpthread

Zstd Compression

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

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Ubuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.04, N = 3SE +/- 0.11, N = 810.4210.121. (CC) gcc options: -O3 -pthread -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Ubuntu 18.04.4 LTSUbuntu 20.043691215Min: 10.37 / Avg: 10.42 / Max: 10.5Min: 9.41 / Avg: 10.12 / Max: 10.351. (CC) gcc options: -O3 -pthread -lz

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonUbuntu 18.04.4 LTSUbuntu 20.0411002200330044005500SE +/- 64.96, N = 4SE +/- 19.25, N = 450244879
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonUbuntu 18.04.4 LTSUbuntu 20.049001800270036004500Min: 4883 / Avg: 5024 / Max: 5162Min: 4843 / Avg: 4878.5 / Max: 4931

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: t1ha2_atonceUbuntu 18.04.4 LTSUbuntu 20.04612182430SE +/- 0.00, N = 3SE +/- 0.00, N = 325.3624.631. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: t1ha2_atonceUbuntu 18.04.4 LTSUbuntu 20.04612182430Min: 25.36 / Avg: 25.36 / Max: 25.36Min: 24.62 / Avg: 24.63 / Max: 24.631. (CXX) g++ options: -march=native -O3 -lpthread

Intel MPI Benchmarks

Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 PingPongUbuntu 18.04.4 LTSUbuntu 20.046001200180024003000SE +/- 6.28, N = 3SE +/- 15.82, N = 32839.502758.29MIN: 3.03 / MAX: 8819.93MIN: 2.85 / MAX: 8898.751. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 PingPongUbuntu 18.04.4 LTSUbuntu 20.045001000150020002500Min: 2827.61 / Avg: 2839.5 / Max: 2848.96Min: 2727.14 / Avg: 2758.29 / Max: 2778.71. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: Spooky32Ubuntu 18.04.4 LTSUbuntu 20.04816243240SE +/- 0.02, N = 3SE +/- 0.00, N = 332.8031.871. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: Spooky32Ubuntu 18.04.4 LTSUbuntu 20.04714212835Min: 32.77 / Avg: 32.8 / Max: 32.83Min: 31.86 / Avg: 31.87 / Max: 31.871. (CXX) g++ options: -march=native -O3 -lpthread

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.085, N = 15SE +/- 0.103, N = 159.5499.2881. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 9.13 / Avg: 9.55 / Max: 10.14Min: 8.42 / Avg: 9.29 / Max: 9.921. (CXX) g++ options: -O2 -lOpenCL

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: atanhUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.00, N = 3SE +/- 0.00, N = 312.8712.52
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: atanhUbuntu 18.04.4 LTSUbuntu 20.0448121620Min: 12.87 / Avg: 12.87 / Max: 12.88Min: 12.52 / Avg: 12.52 / Max: 12.52

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: f32Ubuntu 18.04.4 LTSUbuntu 20.0430060090012001500SE +/- 8.68, N = 3SE +/- 0.49, N = 31245.011278.18MIN: 1231.08MIN: 1272.141. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1235.5 / Avg: 1245.01 / Max: 1262.34Min: 1277.32 / Avg: 1278.18 / Max: 1279.021. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: fasthash32Ubuntu 18.04.4 LTSUbuntu 20.042K4K6K8K10KSE +/- 0.10, N = 3SE +/- 0.08, N = 39877.8110138.201. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: fasthash32Ubuntu 18.04.4 LTSUbuntu 20.042K4K6K8K10KMin: 9877.61 / Avg: 9877.81 / Max: 9877.91Min: 10138.04 / Avg: 10138.2 / Max: 10138.291. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: t1ha0_aes_avx2Ubuntu 18.04.4 LTSUbuntu 20.0415K30K45K60K75KSE +/- 89.27, N = 3SE +/- 108.49, N = 368156.4069938.891. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: t1ha0_aes_avx2Ubuntu 18.04.4 LTSUbuntu 20.0412K24K36K48K60KMin: 67986.83 / Avg: 68156.4 / Max: 68289.59Min: 69824.51 / Avg: 69938.89 / Max: 70155.751. (CXX) g++ options: -march=native -O3 -lpthread

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: MeowHashUbuntu 18.04.4 LTSUbuntu 20.04918273645SE +/- 0.01, N = 3SE +/- 0.00, N = 341.5040.491. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: MeowHashUbuntu 18.04.4 LTSUbuntu 20.04918273645Min: 41.48 / Avg: 41.5 / Max: 41.51Min: 40.48 / Avg: 40.49 / Max: 40.491. (CXX) g++ options: -march=native -O3 -lpthread

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: EmilyUbuntu 18.04.4 LTSUbuntu 20.044080120160200185.46181.18

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pUbuntu 18.04.4 LTSUbuntu 20.04246810SE +/- 0.065, N = 3SE +/- 0.022, N = 36.3466.2001. (CXX) g++ options: -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 6.28 / Avg: 6.35 / Max: 6.48Min: 6.16 / Avg: 6.2 / Max: 6.241. (CXX) g++ options: -fPIE -fPIC -pie

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 2019-12-17H.264 Video EncodingUbuntu 18.04.4 LTSUbuntu 20.04306090120150SE +/- 0.47, N = 3SE +/- 1.24, N = 8120.46117.831. (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 2019-12-17H.264 Video EncodingUbuntu 18.04.4 LTSUbuntu 20.0420406080100Min: 119.78 / Avg: 120.46 / Max: 121.35Min: 111.69 / Avg: 117.83 / Max: 120.511. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

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 PassingUbuntu 18.04.4 LTSUbuntu 20.041.3M2.6M3.9M5.2M6.5MSE +/- 28308.55, N = 3SE +/- 25683.75, N = 35890811.796020407.711. (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 PassingUbuntu 18.04.4 LTSUbuntu 20.041000K2000K3000K4000K5000KMin: 5852280.25 / Avg: 5890811.79 / Max: 5946002.66Min: 5970201.45 / Avg: 6020407.71 / Max: 6054916.391. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.04246810SE +/- 0.00227, N = 3SE +/- 0.00733, N = 37.369217.21957MIN: 7.26MIN: 7.131. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.043691215Min: 7.37 / Avg: 7.37 / Max: 7.37Min: 7.21 / Avg: 7.22 / Max: 7.231. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: Spooky32Ubuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KSE +/- 10.40, N = 3SE +/- 3.97, N = 321044.2020624.891. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2020-02-29Hash: Spooky32Ubuntu 18.04.4 LTSUbuntu 20.044K8K12K16K20KMin: 21024.93 / Avg: 21044.2 / Max: 21060.63Min: 20620.64 / Avg: 20624.89 / Max: 20632.811. (CXX) g++ options: -march=native -O3 -lpthread

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRankUbuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KSE +/- 166.64, N = 5SE +/- 184.20, N = 524412.6023948.91
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRankUbuntu 18.04.4 LTSUbuntu 20.044K8K12K16K20KMin: 23979.54 / Avg: 24412.6 / Max: 24727.07Min: 23242.81 / Avg: 23948.91 / Max: 24328.59

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: MemorialUbuntu 18.04.4 LTSUbuntu 20.04714212835SE +/- 0.07, N = 3SE +/- 0.12, N = 327.6128.14
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.0.0Scene: MemorialUbuntu 18.04.4 LTSUbuntu 20.04612182430Min: 27.52 / Avg: 27.61 / Max: 27.75Min: 27.92 / Avg: 28.14 / Max: 28.33

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient CPUUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.058, N = 3SE +/- 0.127, N = 159.6539.8311. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient CPUUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 9.59 / Avg: 9.65 / Max: 9.77Min: 9.19 / Avg: 9.83 / Max: 10.841. (CXX) g++ options: -rdynamic

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: HairUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.07, N = 3SE +/- 0.01, N = 310.8211.021. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: HairUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 10.68 / Avg: 10.82 / Max: 10.89Min: 11 / Avg: 11.02 / Max: 11.041. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric CausticUbuntu 18.04.4 LTSUbuntu 20.0448121620SE +/- 0.08, N = 3SE +/- 0.09, N = 313.8114.061. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric CausticUbuntu 18.04.4 LTSUbuntu 20.0448121620Min: 13.66 / Avg: 13.81 / Max: 13.92Min: 13.88 / Avg: 14.06 / Max: 14.191. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl

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 TimeUbuntu 18.04.4 LTSUbuntu 20.04306090120150110112

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed TreeUbuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KSE +/- 213.27, N = 10SE +/- 259.44, N = 622869.6922467.59
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed TreeUbuntu 18.04.4 LTSUbuntu 20.044K8K12K16K20KMin: 21758.23 / Avg: 22869.69 / Max: 23849.57Min: 21444.6 / Avg: 22467.59 / Max: 22992.73

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: f32Ubuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.04, N = 3SE +/- 0.01, N = 310.8510.66MIN: 10.38MIN: 10.391. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.043691215Min: 10.78 / Avg: 10.85 / Max: 10.92Min: 10.66 / Avg: 10.66 / Max: 10.671. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Intel MPI Benchmarks

Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage usec, Fewer Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 ExchangeUbuntu 18.04.4 LTSUbuntu 20.0470140210280350SE +/- 1.04, N = 3SE +/- 0.42, N = 3311.45316.83MIN: 1.45 / MAX: 5735.78MIN: 1.59 / MAX: 5911.151. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgAverage usec, Fewer Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 ExchangeUbuntu 18.04.4 LTSUbuntu 20.0460120180240300Min: 309.56 / Avg: 311.45 / Max: 313.15Min: 315.98 / Avg: 316.83 / Max: 317.291. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

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: SemaphoresUbuntu 18.04.4 LTSUbuntu 20.04500K1000K1500K2000K2500KSE +/- 24343.06, N = 3SE +/- 12492.62, N = 32101976.062066514.871. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: SemaphoresUbuntu 18.04.4 LTSUbuntu 20.04400K800K1200K1600K2000KMin: 2064478.13 / Avg: 2101976.06 / Max: 2147617.09Min: 2043570.69 / Avg: 2066514.87 / Max: 2086552.581. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

DaCapo Benchmark

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

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Ubuntu 18.04.4 LTSUbuntu 20.042K4K6K8K10KSE +/- 70.30, N = 4SE +/- 56.68, N = 487568609
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Ubuntu 18.04.4 LTSUbuntu 20.0415003000450060007500Min: 8574 / Avg: 8755.75 / Max: 8913Min: 8510 / Avg: 8608.5 / Max: 8772

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 MaterialUbuntu 18.04.4 LTSUbuntu 20.042040608010090.6289.14

Intel MPI Benchmarks

Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage usec, Fewer Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 SendrecvUbuntu 18.04.4 LTSUbuntu 20.044080120160200SE +/- 3.05, N = 3SE +/- 3.21, N = 3163.41166.07MIN: 0.86 / MAX: 3175.19MIN: 1.02 / MAX: 3575.21. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgAverage usec, Fewer Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 SendrecvUbuntu 18.04.4 LTSUbuntu 20.04306090120150Min: 159.58 / Avg: 163.41 / Max: 169.44Min: 159.81 / Avg: 166.07 / Max: 170.41. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0470K140K210K280K350KSE +/- 4409.59, N = 3SE +/- 3527.67, N = 33303333356671. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0460K120K180K240K300KMin: 322000 / Avg: 330333.33 / Max: 337000Min: 329000 / Avg: 335666.67 / Max: 3410001. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -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 - Model: CrownUbuntu 18.04.4 LTSUbuntu 20.04714212835SE +/- 0.14, N = 3SE +/- 0.06, N = 329.0729.53MIN: 28.34 / MAX: 29.69MIN: 29.05 / MAX: 30.07
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: CrownUbuntu 18.04.4 LTSUbuntu 20.04714212835Min: 28.83 / Avg: 29.07 / Max: 29.32Min: 29.4 / Avg: 29.53 / Max: 29.59

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0430060090012001500SE +/- 17.29, N = 3SE +/- 14.05, N = 3129013101. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1257 / Avg: 1290.33 / Max: 1315Min: 1284 / Avg: 1310.33 / Max: 13321. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -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: MG.CUbuntu 18.04.4 LTSUbuntu 20.0413K26K39K52K65KSE +/- 350.05, N = 3SE +/- 315.95, N = 359085.3659982.581. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CUbuntu 18.04.4 LTSUbuntu 20.0410K20K30K40K50KMin: 58415.58 / Avg: 59085.36 / Max: 59596.77Min: 59628.24 / Avg: 59982.58 / Max: 60612.871. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Ubuntu 18.04.4 LTS: Open MPI 2.1.13. Ubuntu 20.04: Open MPI 4.0.3rc4

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.045001000150020002500SE +/- 22.40, N = 3SE +/- 12.01, N = 3228523181. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.04400800120016002000Min: 2260 / Avg: 2285.33 / Max: 2330Min: 2294 / Avg: 2318 / Max: 23311. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 10.87, N = 3SE +/- 6.17, N = 3113911551. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1127 / Avg: 1139.33 / Max: 1161Min: 1143 / Avg: 1155.33 / Max: 11621. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1SUbuntu 18.04.4 LTSUbuntu 20.041224364860SE +/- 0.08, N = 3SE +/- 0.09, N = 353.8354.571. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: ETC1SUbuntu 18.04.4 LTSUbuntu 20.041122334455Min: 53.69 / Avg: 53.83 / Max: 53.96Min: 54.39 / Avg: 54.57 / Max: 54.71. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

SMHasher

SMHasher is a hash function tester. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: fasthash32Ubuntu 18.04.4 LTSUbuntu 20.04612182430SE +/- 0.00, N = 3SE +/- 0.01, N = 325.0924.771. (CXX) g++ options: -march=native -O3 -lpthread
OpenBenchmarking.orgcycles/hash, Fewer Is BetterSMHasher 2020-02-29Hash: fasthash32Ubuntu 18.04.4 LTSUbuntu 20.04612182430Min: 25.09 / Avg: 25.09 / Max: 25.09Min: 24.76 / Avg: 24.77 / Max: 24.771. (CXX) g++ options: -march=native -O3 -lpthread

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 2.13ATPase Simulation - 327,506 AtomsUbuntu 18.04.4 LTSUbuntu 20.040.13560.27120.40680.54240.678SE +/- 0.00016, N = 3SE +/- 0.00704, N = 30.595790.60248
OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13ATPase Simulation - 327,506 AtomsUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 0.6 / Avg: 0.6 / Max: 0.6Min: 0.59 / Avg: 0.6 / Max: 0.62

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: f32Ubuntu 18.04.4 LTSUbuntu 20.040.47930.95861.43791.91722.3965SE +/- 0.00505, N = 3SE +/- 0.00305, N = 32.106632.13009MIN: 2.04MIN: 2.071. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.04246810Min: 2.1 / Avg: 2.11 / Max: 2.12Min: 2.12 / Avg: 2.13 / Max: 2.141. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 3Ubuntu 18.04.4 LTSUbuntu 20.04714212835SE +/- 0.06, N = 3SE +/- 0.02, N = 328.2427.941. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 3Ubuntu 18.04.4 LTSUbuntu 20.04612182430Min: 28.11 / Avg: 28.24 / Max: 28.31Min: 27.91 / Avg: 27.94 / Max: 27.971. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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_3d - Data Type: f32Ubuntu 18.04.4 LTSUbuntu 20.04246810SE +/- 0.00377, N = 3SE +/- 0.00312, N = 36.384076.31762MIN: 6.25MIN: 6.211. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.043691215Min: 6.38 / Avg: 6.38 / Max: 6.39Min: 6.31 / Avg: 6.32 / Max: 6.321. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -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: Asian Dragon ObjUbuntu 18.04.4 LTSUbuntu 20.04918273645SE +/- 0.28, N = 3SE +/- 0.04, N = 336.8137.18MIN: 35.67 / MAX: 37.58MIN: 36.79 / MAX: 37.69
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjUbuntu 18.04.4 LTSUbuntu 20.04816243240Min: 36.26 / Avg: 36.81 / Max: 37.13Min: 37.14 / Avg: 37.18 / Max: 37.26

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Threaded Building Blocks, and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal GeneratorImplementation: C++ ThreadsUbuntu 18.04.4 LTSUbuntu 20.048K16K24K32K40KSE +/- 102.41, N = 3SE +/- 124.26, N = 338069384471. (CXX) g++ options: -lpthread
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal GeneratorImplementation: C++ ThreadsUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KMin: 37924 / Avg: 38069.33 / Max: 38267Min: 38309 / Avg: 38447 / Max: 386951. (CXX) g++ options: -lpthread

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: f32Ubuntu 18.04.4 LTSUbuntu 20.040.61441.22881.84322.45763.072SE +/- 0.00062, N = 3SE +/- 0.00440, N = 32.730782.70420MIN: 2.67MIN: 2.661. (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: Deconvolution Batch deconv_3d - Data Type: f32Ubuntu 18.04.4 LTSUbuntu 20.04246810Min: 2.73 / Avg: 2.73 / Max: 2.73Min: 2.7 / Avg: 2.7 / Max: 2.711. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.3.0Speed: 10Ubuntu 18.04.4 LTSUbuntu 20.040.48960.97921.46881.95842.448SE +/- 0.009, N = 3SE +/- 0.002, N = 32.1762.155
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.3.0Speed: 10Ubuntu 18.04.4 LTSUbuntu 20.04246810Min: 2.16 / Avg: 2.18 / Max: 2.19Min: 2.15 / Avg: 2.16 / Max: 2.16

Intel MPI Benchmarks

Intel MPI Benchmarks for stressing MPI implementations. At this point the test profile aggregates results for some common MPI functionality. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Msg/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-P2P PingPongUbuntu 18.04.4 LTSUbuntu 20.044M8M12M16M20MSE +/- 114986.66, N = 3SE +/- 24631.07, N = 319857439.2319682714.06MIN: 8103 / MAX: 45931269MIN: 8118 / MAX: 562781831. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
OpenBenchmarking.orgAverage Msg/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-P2P PingPongUbuntu 18.04.4 LTSUbuntu 20.043M6M9M12M15MMin: 19642323.26 / Avg: 19857439.23 / Max: 20035421.91Min: 19633542.04 / Avg: 19682714.06 / Max: 19709879.431. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Chaos Group V-RAY

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

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPUUbuntu 18.04.4 LTSUbuntu 20.049K18K27K36K45KSE +/- 58.85, N = 3SE +/- 159.09, N = 33995040284
OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPUUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KMin: 39840 / Avg: 39950.33 / Max: 40041Min: 40005 / Avg: 40283.67 / Max: 40556

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 2.3Scene: Rainbow Colors and PrismUbuntu 18.04.4 LTSUbuntu 20.041.08682.17363.26044.34725.434SE +/- 0.02, N = 3SE +/- 0.03, N = 34.794.83MIN: 4.64 / MAX: 4.85MIN: 4.11 / MAX: 4.89
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: Rainbow Colors and PrismUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 4.77 / Avg: 4.79 / Max: 4.83Min: 4.77 / Avg: 4.83 / Max: 4.86

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: f32Ubuntu 18.04.4 LTSUbuntu 20.041224364860SE +/- 0.03, N = 3SE +/- 0.07, N = 355.1054.66MIN: 54.25MIN: 54.041. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.041122334455Min: 55.05 / Avg: 55.1 / Max: 55.15Min: 54.54 / Avg: 54.66 / Max: 54.771. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 6.89, N = 15SE +/- 8.24, N = 15850.20857.02
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.04150300450600750Min: 787.23 / Avg: 850.2 / Max: 881.05Min: 810.57 / Avg: 857.02 / Max: 906.95

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: CrownUbuntu 18.04.4 LTSUbuntu 20.04816243240SE +/- 0.03, N = 3SE +/- 0.26, N = 333.4133.16MIN: 32.87 / MAX: 34.07MIN: 31.84 / MAX: 34.23
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: CrownUbuntu 18.04.4 LTSUbuntu 20.04714212835Min: 33.38 / Avg: 33.41 / Max: 33.46Min: 32.64 / Avg: 33.16 / Max: 33.46

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: SciVisUbuntu 18.04.4 LTSUbuntu 20.04246810SE +/- 0.00, N = 7SE +/- 0.00, N = 67.147.19MIN: 6.33 / MAX: 7.25MIN: 6.17 / MAX: 7.25
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 7.14 / Avg: 7.14 / Max: 7.14Min: 7.19 / Avg: 7.19 / Max: 7.19

7-Zip Compression

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

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestUbuntu 18.04.4 LTSUbuntu 20.0430K60K90K120K150KSE +/- 2000.87, N = 3SE +/- 547.64, N = 31461441470991. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestUbuntu 18.04.4 LTSUbuntu 20.0430K60K90K120K150KMin: 144033 / Avg: 146144.33 / Max: 150144Min: 146232 / Avg: 147098.67 / Max: 1481121. (CXX) g++ options: -pipe -lpthread

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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.00613, N = 3SE +/- 0.00975, N = 39.472169.41817MIN: 9.37MIN: 9.311. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.043691215Min: 9.47 / Avg: 9.47 / Max: 9.48Min: 9.4 / Avg: 9.42 / Max: 9.441. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Rodinia

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

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.11, N = 10SE +/- 0.14, N = 1511.5611.491. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 11.09 / Avg: 11.56 / Max: 12.27Min: 10.77 / Avg: 11.49 / Max: 12.411. (CXX) g++ options: -O2 -lOpenCL

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Threaded Building Blocks, and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal GeneratorImplementation: C++ TasksUbuntu 18.04.4 LTSUbuntu 20.048K16K24K32K40KSE +/- 181.04, N = 3SE +/- 110.94, N = 338148379521. (CXX) g++ options: -lpthread
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal GeneratorImplementation: C++ TasksUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KMin: 37831 / Avg: 38148.33 / Max: 38458Min: 37732 / Avg: 37952 / Max: 380871. (CXX) g++ options: -lpthread

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.04612182430SE +/- 0.32, N = 4SE +/- 0.18, N = 325.4225.29
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.04612182430Min: 24.86 / Avg: 25.42 / Max: 26.3Min: 25.04 / Avg: 25.29 / Max: 25.64

Nettle

GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: sha512Ubuntu 18.04.4 LTSUbuntu 20.04110220330440550SE +/- 0.31, N = 3SE +/- 0.25, N = 3486.75489.24-lhogweed1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: sha512Ubuntu 18.04.4 LTSUbuntu 20.0490180270360450Min: 486.14 / Avg: 486.75 / Max: 487.12Min: 488.93 / Avg: 489.24 / Max: 489.741. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

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 TracerUbuntu 18.04.4 LTSUbuntu 20.040.8911.7822.6733.5644.455SE +/- 0.01, N = 3SE +/- 0.01, N = 33.943.96MIN: 3.5 / MAX: 3.97MIN: 3.41 / MAX: 3.98
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 3.94 / Avg: 3.94 / Max: 3.95Min: 3.95 / Avg: 3.96 / Max: 3.97

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_3d - Data Type: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.0448121620SE +/- 0.01, N = 3SE +/- 0.00, N = 315.2915.22MIN: 15.07MIN: 15.051. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.0448121620Min: 15.28 / Avg: 15.29 / Max: 15.3Min: 15.21 / Avg: 15.22 / Max: 15.221. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Nettle

GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: chachaUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 1.80, N = 3SE +/- 0.13, N = 31021.011025.99-lhogweed - MIN: 520.47 / MAX: 2790.93MIN: 522.62 / MAX: 2798.981. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: chachaUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1017.41 / Avg: 1021.01 / Max: 1022.86Min: 1025.86 / Avg: 1025.99 / Max: 1026.261. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.3.0Speed: 6Ubuntu 18.04.4 LTSUbuntu 20.040.24120.48240.72360.96481.206SE +/- 0.001, N = 3SE +/- 0.000, N = 31.0671.072
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.3.0Speed: 6Ubuntu 18.04.4 LTSUbuntu 20.04246810Min: 1.07 / Avg: 1.07 / Max: 1.07Min: 1.07 / Avg: 1.07 / Max: 1.07

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 2.82Blend File: Pabellon Barcelona - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.0450100150200250SE +/- 0.16, N = 3SE +/- 0.11, N = 3209.43208.46
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Pabellon Barcelona - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.044080120160200Min: 209.19 / Avg: 209.43 / Max: 209.74Min: 208.25 / Avg: 208.46 / Max: 208.58

Himeno Benchmark

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

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverUbuntu 18.04.4 LTSUbuntu 20.047001400210028003500SE +/- 6.10, N = 3SE +/- 2.48, N = 33431.843416.191. (CC) gcc options: -O3 -mavx2
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverUbuntu 18.04.4 LTSUbuntu 20.046001200180024003000Min: 3419.64 / Avg: 3431.84 / Max: 3438.07Min: 3412 / Avg: 3416.19 / Max: 3420.581. (CC) gcc options: -O3 -mavx2

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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.047001400210028003500SE +/- 0.32, N = 3SE +/- 2.96, N = 33137.903149.57MIN: 3128.23MIN: 3139.281. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.045001000150020002500Min: 3137.28 / Avg: 3137.9 / Max: 3138.35Min: 3145.87 / Avg: 3149.57 / Max: 3155.421. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.041.2152.433.6454.866.075SE +/- 0.01, N = 3SE +/- 0.05, N = 35.385.40
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: Inception V3 - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 5.37 / Avg: 5.38 / Max: 5.4Min: 5.29 / Avg: 5.4 / Max: 5.47

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 2.82Blend File: Classroom - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.044080120160200SE +/- 0.36, N = 3SE +/- 0.18, N = 3166.32165.71
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Classroom - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.04306090120150Min: 165.87 / Avg: 166.32 / Max: 167.04Min: 165.41 / Avg: 165.71 / Max: 166.04

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: BMW27 - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.041428425670SE +/- 0.07, N = 3SE +/- 0.08, N = 360.8460.62
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: BMW27 - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.041224364860Min: 60.75 / Avg: 60.84 / Max: 60.98Min: 60.51 / Avg: 60.62 / Max: 60.77

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: f32Ubuntu 18.04.4 LTSUbuntu 20.04306090120150SE +/- 0.12, N = 3SE +/- 0.10, N = 3123.35122.91MIN: 122.04MIN: 121.61. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.0420406080100Min: 123.19 / Avg: 123.35 / Max: 123.57Min: 122.8 / Avg: 122.91 / Max: 123.121. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.044080120160200SE +/- 0.08, N = 3SE +/- 0.06, N = 3187.85187.20MIN: 186.72MIN: 186.341. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.04306090120150Min: 187.76 / Avg: 187.85 / Max: 188.02Min: 187.09 / Avg: 187.2 / Max: 187.271. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Ethr

Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 64Ubuntu 18.04.4 LTSUbuntu 20.0460K120K180K240K300KSE +/- 3564.46, N = 4SE +/- 1353.74, N = 3285432.83284466.22MIN: 248250 / MAX: 297960MIN: 267310 / MAX: 294100
OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 64Ubuntu 18.04.4 LTSUbuntu 20.0450K100K150K200K250KMin: 275471.33 / Avg: 285432.83 / Max: 292399.33Min: 282185.33 / Avg: 284466.22 / Max: 286870

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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.041.31052.6213.93155.2426.5525SE +/- 0.01135, N = 3SE +/- 0.00690, N = 35.824635.80495MIN: 5.58MIN: 5.611. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.04246810Min: 5.81 / Avg: 5.82 / Max: 5.85Min: 5.8 / Avg: 5.8 / Max: 5.821. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

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 2.82Blend File: Fishy Cat - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.0420406080100SE +/- 0.13, N = 3SE +/- 0.26, N = 398.4098.11
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Fishy Cat - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.0420406080100Min: 98.19 / Avg: 98.4 / Max: 98.63Min: 97.74 / Avg: 98.11 / Max: 98.61

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: NASA Streamlines - Renderer: Path TracerUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.04, N = 3SE +/- 0.04, N = 310.3510.38MIN: 8.47 / MAX: 10.53MIN: 8.93 / MAX: 10.53
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 10.31 / Avg: 10.35 / Max: 10.42Min: 10.31 / Avg: 10.38 / Max: 10.42

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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.048001600240032004000SE +/- 0.90, N = 3SE +/- 1.78, N = 33924.663914.06MIN: 3917MIN: 3906.431. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.047001400210028003500Min: 3923.41 / Avg: 3924.66 / Max: 3926.4Min: 3912.24 / Avg: 3914.06 / Max: 3917.621. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.04150300450600750SE +/- 0.16, N = 3SE +/- 0.22, N = 3714.39712.51MIN: 712.91MIN: 711.011. (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: bf16bf16bf16Ubuntu 18.04.4 LTSUbuntu 20.04130260390520650Min: 714.07 / Avg: 714.39 / Max: 714.58Min: 712.14 / Avg: 712.51 / Max: 712.891. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 0.60, N = 3SE +/- 1.05, N = 31002.631000.07MIN: 997.21MIN: 993.461. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1001.44 / Avg: 1002.63 / Max: 1003.24Min: 998.87 / Avg: 1000.07 / Max: 1002.161. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

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 TracerUbuntu 18.04.4 LTSUbuntu 20.040.89551.7912.68653.5824.4775SE +/- 0.00, N = 12SE +/- 0.00, N = 123.973.98MIN: 3.72 / MAX: 4MIN: 3.64 / MAX: 4.02
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 3.97 / Avg: 3.97 / Max: 3.97Min: 3.98 / Avg: 3.98 / Max: 3.98

Nettle

GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: poly1305-aesUbuntu 18.04.4 LTSUbuntu 20.046001200180024003000SE +/- 0.58, N = 3SE +/- 0.80, N = 32790.372797.15-lhogweed1. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: poly1305-aesUbuntu 18.04.4 LTSUbuntu 20.045001000150020002500Min: 2789.21 / Avg: 2790.37 / Max: 2790.98Min: 2795.88 / Avg: 2797.15 / Max: 2798.631. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

PlaidML

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

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.040.96981.93962.90943.87924.849SE +/- 0.05, N = 3SE +/- 0.02, N = 34.304.31
OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 4.22 / Avg: 4.3 / Max: 4.39Min: 4.28 / Avg: 4.31 / Max: 4.33

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 EncodingUbuntu 18.04.4 LTSUbuntu 20.04816243240SE +/- 0.07, N = 3SE +/- 0.20, N = 334.6734.751. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video EncodingUbuntu 18.04.4 LTSUbuntu 20.04714212835Min: 34.58 / Avg: 34.67 / Max: 34.82Min: 34.36 / Avg: 34.75 / Max: 35.021. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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 2.3Scene: DLSCUbuntu 18.04.4 LTSUbuntu 20.041.00132.00263.00394.00525.0065SE +/- 0.01, N = 3SE +/- 0.01, N = 34.444.45MIN: 4.34 / MAX: 4.62MIN: 4.35 / MAX: 4.63
OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.3Scene: DLSCUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 4.42 / Avg: 4.44 / Max: 4.45Min: 4.43 / Avg: 4.45 / Max: 4.46

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.045001000150020002500SE +/- 8.08, N = 3SE +/- 2.03, N = 3235423491. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.04400800120016002000Min: 2344 / Avg: 2354 / Max: 2370Min: 2345 / Avg: 2348.67 / Max: 23521. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -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 - Model: Asian Dragon ObjUbuntu 18.04.4 LTSUbuntu 20.04816243240SE +/- 0.07, N = 3SE +/- 0.01, N = 332.2532.30MIN: 31.91 / MAX: 32.76MIN: 32.03 / MAX: 32.79
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon ObjUbuntu 18.04.4 LTSUbuntu 20.04714212835Min: 32.16 / Avg: 32.25 / Max: 32.39Min: 32.29 / Avg: 32.3 / Max: 32.32

Flexible IO Tester

Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.0430060090012001500SE +/- 3.93, N = 3SE +/- 0.88, N = 3117311711. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1168 / Avg: 1173.33 / Max: 1181Min: 1169 / Avg: 1170.67 / Max: 11721. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lpthread -lm -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: pthread_onceUbuntu 18.04.4 LTSUbuntu 20.040.38920.77841.16761.55681.946SE +/- 0.00025, N = 3SE +/- 0.00029, N = 31.729611.72689
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 1.73 / Avg: 1.73 / Max: 1.73Min: 1.73 / Avg: 1.73 / Max: 1.73

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 2.82Blend File: Barbershop - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.0460120180240300SE +/- 0.51, N = 3SE +/- 0.42, N = 3262.12261.81
OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Barbershop - Compute: CPU-OnlyUbuntu 18.04.4 LTSUbuntu 20.0450100150200250Min: 261.39 / Avg: 262.12 / Max: 263.09Min: 261.28 / Avg: 261.81 / Max: 262.64

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: tanhUbuntu 18.04.4 LTSUbuntu 20.043691215SE +/- 0.00, N = 3SE +/- 0.00, N = 313.6013.59
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanhUbuntu 18.04.4 LTSUbuntu 20.0448121620Min: 13.6 / Avg: 13.6 / Max: 13.61Min: 13.59 / Avg: 13.59 / Max: 13.59

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 9.3.0Time To CompileUbuntu 18.04.4 LTSUbuntu 20.042004006008001000SE +/- 0.45, N = 3SE +/- 1.91, N = 31064.941063.81
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 9.3.0Time To CompileUbuntu 18.04.4 LTSUbuntu 20.042004006008001000Min: 1064.07 / Avg: 1064.94 / Max: 1065.56Min: 1061.34 / Avg: 1063.81 / Max: 1067.56

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 DragonUbuntu 18.04.4 LTSUbuntu 20.04816243240SE +/- 0.02, N = 3SE +/- 0.11, N = 335.6835.71MIN: 35.4 / MAX: 36.11MIN: 35.3 / MAX: 36.32
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian DragonUbuntu 18.04.4 LTSUbuntu 20.04816243240Min: 35.66 / Avg: 35.68 / Max: 35.71Min: 35.56 / Avg: 35.71 / Max: 35.93

toyBrot Fractal Generator

ToyBrot is a Mandelbrot fractal generator supporting C++ threads/tasks, OpenMP, Threaded Building Blocks, and other targets. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal GeneratorImplementation: OpenMPUbuntu 18.04.4 LTSUbuntu 20.049K18K27K36K45KSE +/- 166.14, N = 3SE +/- 104.46, N = 341175412061. (CXX) g++ options: -lpthread
OpenBenchmarking.orgms, Fewer Is BettertoyBrot Fractal GeneratorImplementation: OpenMPUbuntu 18.04.4 LTSUbuntu 20.047K14K21K28K35KMin: 40943 / Avg: 41175 / Max: 41497Min: 40999 / Avg: 41206 / Max: 413341. (CXX) g++ options: -lpthread

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 0Ubuntu 18.04.4 LTSUbuntu 20.04246810SE +/- 0.039, N = 3SE +/- 0.024, N = 38.7048.7101. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 0Ubuntu 18.04.4 LTSUbuntu 20.043691215Min: 8.67 / Avg: 8.7 / Max: 8.78Min: 8.66 / Avg: 8.71 / Max: 8.741. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

Nettle

GNU Nettle is a low-level cryptographic library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: aes256Ubuntu 18.04.4 LTSUbuntu 20.0413002600390052006500SE +/- 0.43, N = 3SE +/- 1.73, N = 36156.946160.34-lhogweed - MIN: 4148.88 / MAX: 10190.34MIN: 4152.55 / MAX: 10202.921. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto
OpenBenchmarking.orgMbyte/s, More Is BetterNettle 3.5.1Test: aes256Ubuntu 18.04.4 LTSUbuntu 20.0411002200330044005500Min: 6156.44 / Avg: 6156.94 / Max: 6157.78Min: 6157.39 / Avg: 6160.34 / Max: 6163.371. (CC) gcc options: -O2 -ggdb3 -lnettle -lgmp -lm -lcrypto

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2Ubuntu 18.04.4 LTSUbuntu 20.0448121620SE +/- 0.03, N = 3SE +/- 0.05, N = 317.7317.721. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2Ubuntu 18.04.4 LTSUbuntu 20.0448121620Min: 17.7 / Avg: 17.73 / Max: 17.79Min: 17.67 / Avg: 17.72 / Max: 17.821. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

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 DragonUbuntu 18.04.4 LTSUbuntu 20.041020304050SE +/- 0.05, N = 3SE +/- 0.02, N = 343.0043.01MIN: 42.49 / MAX: 43.68MIN: 42.62 / MAX: 43.61
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian DragonUbuntu 18.04.4 LTSUbuntu 20.04918273645Min: 42.9 / Avg: 43 / Max: 43.08Min: 42.98 / Avg: 43.01 / Max: 43.05

ArrayFire

ArrayFire is an GPU and CPU numeric processing library, this test uses the built-in CPU and OpenCL ArrayFire benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterArrayFire 3.7Test: BLAS CPUUbuntu 18.04.4 LTSUbuntu 20.045001000150020002500SE +/- 1.45, N = 3SE +/- 5.38, N = 32382.602383.321. (CXX) g++ options: -rdynamic
OpenBenchmarking.orgGFLOPS, More Is BetterArrayFire 3.7Test: BLAS CPUUbuntu 18.04.4 LTSUbuntu 20.04400800120016002000Min: 2379.78 / Avg: 2382.6 / Max: 2384.63Min: 2376.58 / Avg: 2383.32 / Max: 2393.961. (CXX) g++ options: -rdynamic

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: ffsUbuntu 18.04.4 LTSUbuntu 20.040.38570.77141.15711.54281.9285SE +/- 0.00103, N = 3SE +/- 0.00013, N = 31.714281.71403
OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 1.71 / Avg: 1.71 / Max: 1.72Min: 1.71 / Avg: 1.71 / Max: 1.71

Tensorflow

This is a benchmark of the Tensorflow deep learning framework using the CIFAR10 data set. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTensorflowBuild: Cifar10Ubuntu 18.04.4 LTS20406080100SE +/- 0.27, N = 376.28

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 TracerUbuntu 18.04.4 LTSUbuntu 20.04110220330440550500500MIN: 250MIN: 250

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisUbuntu 18.04.4 LTSUbuntu 20.041122334455SE +/- 0.00, N = 12SE +/- 0.00, N = 1247.6247.62MIN: 17.54 / MAX: 50MIN: 18.52 / MAX: 50
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisUbuntu 18.04.4 LTSUbuntu 20.041020304050Min: 47.62 / Avg: 47.62 / Max: 47.62Min: 47.62 / Avg: 47.62 / Max: 47.62

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisUbuntu 18.04.4 LTSUbuntu 20.041224364860SE +/- 0.00, N = 15SE +/- 0.00, N = 1555.5655.56MIN: 25.64MIN: 24.39
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisUbuntu 18.04.4 LTSUbuntu 20.041122334455Min: 55.56 / Avg: 55.56 / Max: 55.56Min: 55.56 / Avg: 55.56 / Max: 55.56

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisUbuntu 18.04.4 LTSUbuntu 20.041020304050SE +/- 0.00, N = 12SE +/- 0.00, N = 1243.4843.48MIN: 27.03 / MAX: 45.45MIN: 27.03 / MAX: 45.45
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisUbuntu 18.04.4 LTSUbuntu 20.04918273645Min: 43.48 / Avg: 43.48 / Max: 43.48Min: 43.48 / Avg: 43.48 / Max: 43.48

iPerf

iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64Ubuntu 18.04.4 LTSUbuntu 20.041530456075SE +/- 0.00, N = 3SE +/- 0.00, N = 367.167.11. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64Ubuntu 18.04.4 LTSUbuntu 20.041326395265Min: 67.1 / Avg: 67.1 / Max: 67.1Min: 67.1 / Avg: 67.1 / Max: 67.11. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm

Apache HBase

This is a benchmark of the Apache HBase non-relational distributed database system inspired from Google's Bigtable. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Random Write - Clients: 64Ubuntu 18.04.4 LTSUbuntu 20.04120240360480600SE +/- 51.78, N = 4SE +/- 37.03, N = 4539468
OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Random Write - Clients: 64Ubuntu 18.04.4 LTSUbuntu 20.04100200300400500Min: 385 / Avg: 538.5 / Max: 612Min: 370 / Avg: 467.5 / Max: 550

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Random Write - Clients: 64Ubuntu 18.04.4 LTSUbuntu 20.0430K60K90K120K150KSE +/- 14162.25, N = 4SE +/- 11839.14, N = 4121844139229
OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Random Write - Clients: 64Ubuntu 18.04.4 LTSUbuntu 20.0420K40K60K80K100KMin: 103973 / Avg: 121843.5 / Max: 164140Min: 116035 / Avg: 139229.25 / Max: 172292

Stress-NG

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

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context SwitchingUbuntu 18.04.4 LTSUbuntu 20.045M10M15M20M25MSE +/- 237443.56, N = 15SE +/- 816166.85, N = 123667714.3822737428.141. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context SwitchingUbuntu 18.04.4 LTSUbuntu 20.044M8M12M16M20MMin: 2402530.72 / Avg: 3667714.38 / Max: 5053209.46Min: 15734790.25 / Avg: 22737428.14 / Max: 26127322.131. (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-ExponentialUbuntu 18.04.4 LTSUbuntu 20.04246810SE +/- 0.27781, N = 15SE +/- 0.37966, N = 136.937967.171321. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lpthread -ldl
OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-ExponentialUbuntu 18.04.4 LTSUbuntu 20.043691215Min: 5.43 / Avg: 6.94 / Max: 8.96Min: 6.04 / Avg: 7.17 / Max: 10.941. (CXX) g++ options: -std=c++0x -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -mfma -mbmi2 -mavx512f -mavx512vl -mavx512cd -mavx512dq -mavx512bw -mno-sse4a -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512pf -mno-avx512er -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -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 1D - Data Type: f32Ubuntu 18.04.4 LTSUbuntu 20.040.5851.171.7552.342.925SE +/- 0.28200, N = 15SE +/- 0.01737, N = 32.600222.36964MIN: 1.83MIN: 1.931. (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: f32Ubuntu 18.04.4 LTSUbuntu 20.04246810Min: 2.17 / Avg: 2.6 / Max: 6.54Min: 2.34 / Avg: 2.37 / Max: 2.41. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Renaissance

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

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IOUbuntu 18.04.4 LTSUbuntu 20.046K12K18K24K30KSE +/- 485.45, N = 25SE +/- 600.11, N = 2529170.9526200.92
OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IOUbuntu 18.04.4 LTSUbuntu 20.045K10K15K20K25KMin: 22914.76 / Avg: 29170.95 / Max: 33870.61Min: 21252.34 / Avg: 26200.92 / Max: 32179.18

Parboil

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

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilUbuntu 18.04.4 LTSUbuntu 20.040.83751.6752.51253.354.1875SE +/- 0.048897, N = 15SE +/- 0.071535, N = 153.7223373.4896641. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilUbuntu 18.04.4 LTSUbuntu 20.04246810Min: 3.18 / Avg: 3.72 / Max: 4.02Min: 3.02 / Avg: 3.49 / Max: 3.881. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMUbuntu 18.04.4 LTSUbuntu 20.04510152025SE +/- 0.33, N = 15SE +/- 0.19, N = 320.9219.341. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMUbuntu 18.04.4 LTSUbuntu 20.04510152025Min: 19 / Avg: 20.92 / Max: 23.31Min: 19.06 / Avg: 19.34 / Max: 19.711. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Ethr

Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 64Ubuntu 18.04.4 LTSUbuntu 20.04510152025SE +/- 0.53, N = 15SE +/- 0.05, N = 320.2418.39MIN: 11.99 / MAX: 43.24MIN: 12.53 / MAX: 35.06
OpenBenchmarking.orgMicroseconds, Fewer Is BetterEthr 2019-01-02Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 64Ubuntu 18.04.4 LTSUbuntu 20.04510152025Min: 18.53 / Avg: 20.24 / Max: 24.06Min: 18.29 / Avg: 18.39 / Max: 18.44

200 Results Shown

glibc bench:
  sin
  cos
  exp
  sincos
Rodinia
NAS Parallel Benchmarks:
  EP.D
  EP.C
Mlpack Benchmark
Facebook RocksDB
Stress-NG
Flexible IO Tester:
  Rand Write - IO_uring - Yes - No - 4KB - Default Test Directory:
    IOPS
    MB/s
Mlpack Benchmark
glibc bench
PHPBench
Flexible IO Tester:
  Seq Write - IO_uring - Yes - No - 2MB - Default Test Directory:
    IOPS
    MB/s
Scikit-Learn
iPerf
glibc bench
PostgreSQL pgbench
Flexible IO Tester:
  Rand Write - IO_uring - Yes - No - 2MB - Default Test Directory:
    IOPS
    MB/s
LevelDB:
  Fill Sync:
    MB/s
    Microseconds Per Op
PostgreSQL pgbench
DaCapo Benchmark
glibc bench
PostgreSQL pgbench:
  Buffer Test - Heavy Contention - Read Only
  Buffer Test - Normal Load - Read Only
DaCapo Benchmark
Timed Linux Kernel Compilation
NAS Parallel Benchmarks
Flexible IO Tester
Renaissance
Flexible IO Tester
MKL-DNN DNNL
Renaissance
Facebook RocksDB:
  Seq Fill
  Rand Fill
MKL-DNN DNNL
C-Ray
NAS Parallel Benchmarks
LevelDB:
  Seq Fill
  Rand Delete
  Seq Fill
Facebook RocksDB
Flexible IO Tester:
  Seq Read - IO_uring - Yes - No - 4KB - Default Test Directory:
    IOPS
    MB/s
LevelDB
NAS Parallel Benchmarks
RawTherapee
LevelDB:
  Rand Fill
  Hot Read
Renaissance
LevelDB
Parboil
LevelDB:
  Overwrite:
    Microseconds Per Op
    MB/s
SMHasher
Facebook RocksDB
PyBench
Mlpack Benchmark
MariaDB
Basis Universal
SPECjbb 2015
Parboil
NAS Parallel Benchmarks
SPECjbb 2015
MariaDB
SVT-AV1
LevelDB
Renaissance
Stress-NG
SMHasher
Appleseed
Tungsten Renderer
Renaissance
Numpy Benchmark
SMHasher:
  t1ha0_aes_avx2
  wyhash
Intel MPI Benchmarks:
  IMB-MPI1 Sendrecv
  IMB-MPI1 Exchange
Renaissance
GROMACS
Nebular Empirical Analysis Tool
SMHasher
Zstd Compression
DaCapo Benchmark
SMHasher
Intel MPI Benchmarks
SMHasher
Rodinia
glibc bench
MKL-DNN DNNL
SMHasher:
  fasthash32
  t1ha0_aes_avx2
  MeowHash
Appleseed
SVT-AV1
x264
Stress-NG
MKL-DNN DNNL
SMHasher
Renaissance
Intel Open Image Denoise
ArrayFire
Tungsten Renderer:
  Hair
  Volumetric Caustic
ctx_clock
Renaissance
MKL-DNN DNNL
Intel MPI Benchmarks
Stress-NG
DaCapo Benchmark
Appleseed
Intel MPI Benchmarks
Flexible IO Tester
Embree
Flexible IO Tester
NAS Parallel Benchmarks
Flexible IO Tester:
  Rand Read - IO_uring - Yes - No - 2MB - Default Test Directory:
    MB/s
    IOPS
Basis Universal
SMHasher
NAMD
MKL-DNN DNNL
Basis Universal
MKL-DNN DNNL
Embree
toyBrot Fractal Generator
MKL-DNN DNNL
rav1e
Intel MPI Benchmarks
Chaos Group V-RAY
LuxCoreRender
MKL-DNN DNNL
PlaidML
Embree
OSPray
7-Zip Compression
MKL-DNN DNNL
Rodinia
toyBrot Fractal Generator
PlaidML
Nettle
OSPray
MKL-DNN DNNL
Nettle
rav1e
Blender
Himeno Benchmark
MKL-DNN DNNL
PlaidML
Blender:
  Classroom - CPU-Only
  BMW27 - CPU-Only
MKL-DNN DNNL:
  Convolution Batch conv_alexnet - f32
  Convolution Batch conv_googlenet_v3 - bf16bf16bf16
Ethr
MKL-DNN DNNL
Blender
OSPray
MKL-DNN DNNL:
  Convolution Batch conv_all - bf16bf16bf16
  Convolution Batch conv_alexnet - bf16bf16bf16
  Convolution Batch conv_all - f32
OSPray
Nettle
PlaidML
x265
LuxCoreRender
Flexible IO Tester
Embree
Flexible IO Tester
glibc bench
Blender
glibc bench
Timed GCC Compilation
Embree
toyBrot Fractal Generator
Basis Universal
Nettle
Basis Universal
Embree
ArrayFire
glibc bench
Tensorflow
OSPray:
  Magnetic Reconnection - Path Tracer
  Magnetic Reconnection - SciVis
  NASA Streamlines - SciVis
  San Miguel - SciVis
iPerf
Apache HBase:
  Rand Write - 64:
    Microseconds - Average Latency
    Rows Per Second
Stress-NG
Tungsten Renderer
MKL-DNN DNNL
Renaissance
Parboil:
  OpenMP Stencil
  OpenMP LBM
Ethr

Ubuntu 18.04.4 LTS

Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 18.04, Kernel: 5.3.0-42-generic (x86_64), Desktop: GNOME Shell 3.28.4, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, Compiler: GCC 7.5.0, File-System: ext4, Screen Resolution: 1920x1080

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v
Disk Notes: NONE / errors=remount-ro,relatime,rw
Processor Notes: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c
Java Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu118.04.1)
Python Notes: Python 2.7.17 + Python 3.6.9
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 22 March 2020 16:57 by user phoronix.

Ubuntu 20.04

Processor: 2 x Intel Xeon Gold 5220R @ 3.90GHz (36 Cores / 72 Threads), Motherboard: GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS), Chipset: Intel Sky Lake-E DMI3 Registers, Memory: 378GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe 377GB, Monitor: VE228, Network: 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE

OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: GNOME Shell 3.35.91, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.0.0 (LLVM 9.0.1 256 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --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: intel_pstate powersave - CPU Microcode: 0x500002c
Java Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-2ubuntu2)
Python Notes: + Python 3.8.2
Security Notes: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled

Testing initiated at 23 March 2020 18:33 by user phoronix.