ltoize

i9-7980XE 44x -9/-9 DDR4-3200 Optane

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1910276-HV-LTOIZE49411
Jump To Table - Results

View

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

Limit displaying results to tests within:

Audio Encoding 3 Tests
Bioinformatics 3 Tests
Chess Test Suite 5 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 26 Tests
Compression Tests 6 Tests
CPU Massive 71 Tests
Creator Workloads 19 Tests
Cryptography 5 Tests
Disk Test Suite 5 Tests
Encoding 7 Tests
Fortran Tests 2 Tests
Game Development 2 Tests
HPC - High Performance Computing 12 Tests
Imaging 3 Tests
Java 5 Tests
Common Kernel Benchmarks 10 Tests
Machine Learning 3 Tests
Memory Test Suite 6 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 2 Tests
Multi-Core 31 Tests
NVIDIA GPU Compute 4 Tests
OpenCL 3 Tests
OpenMPI Tests 5 Tests
Programmer / Developer System Benchmarks 6 Tests
Python 4 Tests
Raytracing 2 Tests
Renderers 7 Tests
Rust Tests 2 Tests
Scientific Computing 6 Tests
Server 9 Tests
Server CPU Tests 35 Tests
Single-Threaded 35 Tests
Video Encoding 4 Tests
Common Workstation Benchmarks 8 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
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Comparison
Transpose Comparison

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
O3: LTO GRAPHITE
August 20 2019
  18 Hours, 46 Minutes
O3: LTO
August 21 2019
  19 Hours, 54 Minutes
O3: GRAPHITE
August 23 2019
  18 Hours, 29 Minutes
O3:
August 25 2019
  18 Hours, 38 Minutes
O2: LTO GRAPHITE
August 26 2019
  19 Hours, 11 Minutes
O2: LTO
September 01 2019
  18 Hours, 52 Minutes
O2: GRAPHITE
September 02 2019
  18 Hours, 37 Minutes
O2:
August 29 2019
  19 Hours, 36 Minutes
Invert Hiding All Results Option
  19 Hours

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


ltoizeOpenBenchmarking.orgPhoronix Test SuiteIntel Core i9-7980XE @ 4.40GHz (18 Cores / 36 Threads)ASRock X299 Taichi XE (P1.60 BIOS)Intel Sky Lake-E DMI3 Registers129024MB960GB INTEL SSDPED1D960GAY + 2000GB Western Digital WD20EARS-00S + 2000GB Seagate ST2000DM001-1CH1 + 3 x 2000GB Seagate ST2000DM001-1ER1 + 2000GB Western Digital WD20EARS-00M + 250GB HITACHI HTS54322eVGA NVIDIA GeForce GTX 970 4GBRealtek ALC1220Intel I219-V + Intel I211 + Intel Dual Band-AC 3168NGWGentoo/Linux5.0.17-gentoo (x86_64)X Server 1.20.5modesetting 1.20.51.1.99GCC 9.2.0 + Clang 8.0.1 + LLVM 8.0.1 + CUDA 10.1ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDisplay ServerDisplay DriverVulkanCompilerFile-SystemScreen ResolutionLtoize BenchmarksSystem Logs- O3: LTO GRAPHITE: FFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize CXXFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize CFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize - O3: LTO: FFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin CXXFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin CFLAGS=-march=native-pipe-O3-flto=36-fuse-linker-plugin- O3: GRAPHITE: FFLAGS=-march=native-pipe-O3-fgraphite-identity-floop-nest-optimize CXXFLAGS=-march=native-pipe-O3-fgraphite-identity-floop-nest-optimize LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O3-fgraphite-identity-floop-nest-optimize CFLAGS=-march=native-pipe-O3-fgraphite-identity-floop-nest-optimize - O3:: FFLAGS=-march=native-pipe-O3 CXXFLAGS=-march=native-pipe-O3 LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O3 CFLAGS=-march=native-pipe-O3- O2: LTO GRAPHITE: FFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize CXXFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize CFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin-fgraphite-identity-floop-nest-optimize - O2: LTO: FFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin CXXFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin CFLAGS=-march=native-pipe-O2-ftree-vectorize-flto=36-fuse-linker-plugin - O2: GRAPHITE: FFLAGS=-march=native-pipe-O2-ftree-vectorize-fgraphite-identity-floop-nest-optimize CXXFLAGS=-march=native-pipe-O2-ftree-vectorize-fgraphite-identity-floop-nest-optimize LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O2-ftree-vectorize-fgraphite-identity-floop-nest-optimize CFLAGS=-march=native-pipe-O2-ftree-vectorize-fgraphite-identity-floop-nest-optimize - O2:: FFLAGS=-march=native-pipe-O2-ftree-vectorize CXXFLAGS=-march=native-pipe-O2-ftree-vectorize LDFLAGS=-Wl-O1-Wl--as-needed FCFLAGS=-march=native-pipe-O2-ftree-vectorize CFLAGS=-march=native-pipe-O2-ftree-vectorize- --bindir=/usr/x86_64-pc-linux-gnu/gcc-bin/9.2.0 --build=x86_64-pc-linux-gnu --datadir=/usr/share/gcc-data/x86_64-pc-linux-gnu/9.2.0 --disable-altivec --disable-esp --disable-fixed-point --disable-isl-version-check --disable-libmudflap --disable-libssp --disable-systemtap --disable-werror --enable-__cxa_atexit --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-languages=c,c++,d,fortran --enable-libgomp --enable-libstdcxx-time --enable-lto --enable-multilib --enable-nls --enable-obsolete --enable-secureplt --enable-shared --enable-targets=all --enable-threads=posix --enable-vtable-verify --host=x86_64-pc-linux-gnu --includedir=/usr/lib/gcc/x86_64-pc-linux-gnu/9.2.0/include --mandir=/usr/share/gcc-data/x86_64-pc-linux-gnu/9.2.0/man --with-build-config=bootstrap-lto --with-isl --with-multilib-list=m32,m64 --with-python-dir=/share/gcc-data/x86_64-pc-linux-gnu/9.2.0/python - NONE / noatime,rw- Scaling Governor: intel_pstate performance- OpenJDK Runtime Environment (IcedTea 3.12.0) (Gentoo icedtea-3.12.0)- Python 3.6.9- l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

cpp-perf-bench: Rand Numbersdbench: 48dbench: 12numpy: dbench: 256dbench: 128dbench: 1dbench: 6blender: Fishy Cat - CUDAblender: Fishy Cat - OpenCLblogbench: Readhint: FLOAThint: DOUBLEcpp-perf-bench: Math Librarytinymembench: Standard Memsettinymembench: Standard Memcpyblender: Pabellon Barcelona - OpenCLblender: Pabellon Barcelona - CUDAcompress-rar: Linux Source Tree Archiving To RARfftw: Float + SSE - 2D FFT Size 4096blender: Barbershop - CUDAblender: Barbershop - OpenCLradiance: Serialcompress-lzma: 256MB File Compressionllvm-test-suite: Time To Runfftw: Stock - 2D FFT Size 4096pts-self-test: Total Timescikit-learn: blender: Barbershop - CPU-Onlyschbench: 8 - 6schbench: 32 - 2schbench: 4 - 16gmpbench: Total Timeapache-siege: 200rbenchmark: blender: BMW27 - CUDAblender: BMW27 - OpenCLparboil: OpenMP MRI Griddingcachebench: Read / Modify / Writecachebench: Writecachebench: Readasmfish: 1024 Hash Memory, 26 Depthschbench: 8 - 8schbench: 16 - 6schbench: 2 - 32byte: Floating-Point Arithmeticbyte: Register Arithmeticbyte: Integer Arithmeticbyte: Dhrystone 2build-llvm: Time To Compilefhourstones: Complex Connect-4 Solvingschbench: 16 - 4minion: Quasigroupmbw: Memory Copy - 8192 MiBmbw: Memory Copy, Fixed Block Size - 8192 MiBapache-siege: 250blender: Classroom - OpenCLblender: Classroom - CUDAcpp-perf-bench: Stepanov Vectorblender: Pabellon Barcelona - CPU-Onlyschbench: 2 - 6schbench: 2 - 4perl-benchmark: Pod2htmlblender: Classroom - CPU-Onlyradiance: SMP Parallelcpp-perf-bench: Ctypeminion: Solitairetiobench: Read - 256MB - 16fftw: Float + SSE - 2D FFT Size 2048graphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: Enhancedgraphics-magick: Swirlgraphics-magick: Noise-Gaussiangraphics-magick: Rotategraphics-magick: HWB Color Spacecpp-perf-bench: Atolstockfish: Total Timehimeno: Poisson Pressure Solvernamd: ATPase Simulation - 327,506 Atomsschbench: 2 - 8schbench: 2 - 2perl-benchmark: Interpretermrbayes: Primate Phylogeny Analysissystem-libxml2: 112 MBblender: Fishy Cat - CPU-Onlympcbench: Multi-Precision Benchmarktiobench: Rand Read - 256MB - 32parboil: OpenMP LBMfftw: Stock - 2D FFT Size 2048dacapobench: Tradebeansnpb: LU.Cmbw: Memory Copy - 4096 MiBmbw: Memory Copy, Fixed Block Size - 4096 MiBrodinia: OpenCL Myocytebuild-linux-kernel: Time To Compilerodinia: OpenMP Streamclustertiobench: Rand Read - 256MB - 16hackbench: 32 - Processdacapobench: Tradesoaprust-mandel: Time To Complete Serial/Parallel Mandelbrotschbench: 6 - 2redis: SETpostmark: Disk Transaction Performanceschbench: 32 - 32redis: LPUSHredis: GETsockperf: Latency Ping Ponglzbench: XZ 0 - Decompressionlzbench: XZ 0 - Compressionm-queens: Time To Solveredis: SADDebizzy: redis: LPOPcompress-7zip: Compress Speed Testschbench: 6 - 16schbench: 4 - 2c-ray: Total Time - 4K, 16 Rays Per Pixeljava-scimark2: Compositelzbench: Libdeflate 1 - Decompressionlzbench: Libdeflate 1 - Compressiontiobench: Rand Read - 128MB - 16lzbench: Zstd 1 - Decompressionlzbench: Zstd 1 - Compressiongo-benchmark: buildlzbench: Brotli 0 - Decompressionlzbench: Brotli 0 - Compressionschbench: 4 - 4schbench: 4 - 6compress-gzip: Linux Source Tree Archiving To .tar.gzluajit: Compositeapache-siege: 100schbench: 32 - 8schbench: 6 - 24sunflow: Global Illumination + Image Synthesiscpp-perf-bench: Stepanov Abstractionnamd-cuda: ATPase Simulation - 327,506 Atomsschbench: 6 - 4schbench: 6 - 6node-octane: npb: BT.Ablender: BMW27 - CPU-Onlyschbench: 32 - 16schbench: 32 - 24schbench: 32 - 4schbench: 32 - 6schbench: 16 - 8schbench: 16 - 2schbench: 8 - 4schbench: 8 - 2schbench: 16 - 24schbench: 16 - 16schbench: 6 - 8schbench: 4 - 8schbench: 16 - 32schbench: 4 - 24schbench: 8 - 16schbench: 2 - 16schbench: 8 - 32schbench: 8 - 24schbench: 4 - 32schbench: 6 - 32schbench: 2 - 24scimark2: Compositetiobench: Rand Read - 256MB - 8iozone: 4Kb - 8GB - Read Performanceaobench: 2048 x 2048 - Total Timepybench: Total For Average Test Timesapache: Static Web Page Servingjava-gradle-perf: Reactorespeak: Text-To-Speech Synthesistiobench: Rand Read - 64MB - 16sockperf: Latency Under Loaddacapobench: Eclipseparboil: OpenCL LBMtiobench: Read - 256MB - 32tiobench: Rand Write - 256MB - 32hackbench: 16 - Threadstream: Copytiobench: Write - 256MB - 32hackbench: 16 - Processttsiod-renderer: Phong Rendering With Soft-Shadow Mappinggo-benchmark: httpcython-bench: crafty: Elapsed Timebotan: AES-256 - Decryptbotan: AES-256 - Encryptnpb: SP.Aglibc-bench: singlibc-bench: cosbotan: Twofish - Decryptbotan: Twofish - Encryptbotan: Blowfish - Decryptbotan: Blowfish - Encryptfftw: Stock - 1D FFT Size 4096botan: CAST-256 - Decryptbotan: CAST-256 - Encryptbotan: KASUMI - Decryptbotan: KASUMI - Encryptopenssl: RSA 4096-bit Performanceclpeak: Double-Precision Doubletiobench: Rand Read - 128MB - 32compilebench: Compilemcperf: Setmcperf: Addtiobench: Rand Read - 128MB - 8mcperf: Appendmcperf: Prependmcperf: Replacehackbench: 8 - Processtiobench: Rand Read - 64MB - 32ramspeed: Copy - Floating Pointramspeed: Scale - Floating Pointramspeed: Add - Floating Pointramspeed: Average - Floating Pointramspeed: Triad - Floating Pointramspeed: Copy - Integerramspeed: Add - Integerramspeed: Triad - Integerramspeed: Average - Integerramspeed: Scale - Integertiobench: Rand Read - 256MB - 4fftw: Float + SSE - 2D FFT Size 1024tiobench: Read - 128MB - 16tiobench: Read - 64MB - 16compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9tiobench: Rand Read - 32MB - 16fftw: Stock - 1D FFT Size 2048t-test1: 1hackbench: 8 - Threadtiobench: Rand Read - 64MB - 8tiobench: Rand Write - 256MB - 16encode-flac: WAV To FLACmcperf: Deletemcperf: Getiozone: 1MB - 8GB - Read Performancetiobench: Write - 256MB - 16apache-siege: 50iozone: 64Kb - 8GB - Read Performancefs-mark: 5000 Files, 1MB Size, 4 Threadsbuild-imagemagick: Time To Compileiozone: 4Kb - 8GB - Write Performancexsbench: sockperf: Throughputfftw: Float + SSE - 1D FFT Size 256encode-opus: WAV, Opus Encode, Opus Decodeswet: Averagerodinia: OpenMP LavaMDphpbench: PHP Benchmark Suitecpp-perf-bench: Function Objectsfftw: Float + SSE - 2D FFT Size 64tiobench: Read - 32MB - 16tiobench: Read - 128MB - 32go-benchmark: jsonrodinia: OpenCL Particle Filtertiobench: Rand Write - 128MB - 32iozone: 1MB - 8GB - Write Performanceiozone: 64Kb - 8GB - Write Performancefftw: Float + SSE - 1D FFT Size 512glibc-bench: tanhtiobench: Rand Read - 128MB - 4mbw: Memory Copy - 1024 MiBy-cruncher: Calculating 500M Pi Digitstiobench: Rand Read - 32MB - 8mbw: Memory Copy, Fixed Block Size - 1024 MiBtiobench: Rand Read - 64MB - 4fftw: Stock - 1D FFT Size 64fftw: Float + SSE - 2D FFT Size 32tiobench: Write - 128MB - 32fs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizenpb: EP.Ctiobench: Read - 256MB - 8fftw: Float + SSE - 1D FFT Size 64dcraw: RAW To PPM Image Conversionencode-wavpack: WAV To WavPacknetwork-loopback: Time To Transfer 10GB Via Loopbacktiobench: Rand Write - 256MB - 8x265: H.265 1080p Video Encodingrodinia: OpenMP CFD Solverclomp: Static OMP Speeduptiobench: Write - 256MB - 8glibc-bench: pthread_onceglibc-bench: ffsllglibc-bench: sqrtglibc-bench: ffsfftw: Stock - 1D FFT Size 1024primesieve: 1e12 Prime Number Generationsysbench: CPUiozone: 4Kb - 4GB - Read Performanceosbench: Create Threadssudokut: Total Timedacapobench: H2fftw: Stock - 2D FFT Size 1024sample-program: compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19go-benchmark: garbagetiobench: Read - 32MB - 32fftw: Stock - 2D FFT Size 32bork: File Encryption Timetiobench: Rand Write - 128MB - 16tiobench: Write - 32MB - 8clpeak: Transfer Bandwidth enqueueReadBufferclpeak: Transfer Bandwidth enqueueWriteBufferfftw: Float + SSE - 1D FFT Size 4096tiobench: Read - 256MB - 4fftw: Stock - 2D FFT Size 64tiobench: Rand Write - 256MB - 4dacapobench: Jythonparboil: OpenMP Stenciltiobench: Write - 128MB - 8npb: FT.Btiobench: Write - 32MB - 32tiobench: Write - 128MB - 16iozone: 1MB - 4GB - Read Performanceiozone: 64Kb - 4GB - Read Performancetiobench: Write - 256MB - 4tiobench: Rand Read - 32MB - 32fftw: Stock - 1D FFT Size 512tiobench: Write - 32MB - 16fftw: Float + SSE - 2D FFT Size 512tiobench: Read - 128MB - 4iozone: 4Kb - 4GB - Write Performancehackbench: 4 - Threadtiobench: Rand Write - 64MB - 32unpack-linux: linux-4.15.tar.xztiobench: Read - 64MB - 32fftw: Float + SSE - 1D FFT Size 32tiobench: Rand Read - 32MB - 4hackbench: 4 - Processtiobench: Write - 64MB - 16fftw: Stock - 1D FFT Size 256rust-prime: Prime Number Test To 200,000,000tiobench: Read - 128MB - 8tiobench: Rand Write - 128MB - 8osbench: Create Processesfftw: Float + SSE - 1D FFT Size 2048iozone: 1MB - 4GB - Write Performanceiozone: 64Kb - 4GB - Write Performancegnupg: 2GB File Encryptiontjbench: Decompression Throughputmbw: Memory Copy, Fixed Block Size - 512 MiBmbw: Memory Copy - 512 MiBtiobench: Write - 64MB - 32osbench: Create Filesfftw: Stock - 1D FFT Size 128t-test1: 2svt-av1: 1080p 8-bit YUV To AV1 Video Encodesysbench: Memoryhackbench: 1 - Processosbench: Launch Programsfftw: Float + SSE - 2D FFT Size 256tiobench: Rand Write - 64MB - 16osbench: Memory Allocationstiobench: Rand Write - 128MB - 4fftw: Stock - 2D FFT Size 512fftw: Float + SSE - 1D FFT Size 1024git: Time To Complete Common Git Commandstiobench: Write - 64MB - 8fftw: Float + SSE - 2D FFT Size 128smallpt: Global Illumination Renderer; 128 Samplesfftw: Stock - 1D FFT Size 32iozone: 4Kb - 2GB - Read Performancefftw: Stock - 2D FFT Size 256apache-siege: 10fftw: Float + SSE - 1D FFT Size 128bullet: 3000 Falltiobench: Read - 64MB - 8tiobench: Rand Write - 64MB - 8tiobench: Write - 128MB - 4hackbench: 2 - Threadtiobench: Rand Write - 32MB - 32hackbench: 2 - Processhackbench: 1 - Threadiozone: 1MB - 2GB - Read Performanceiozone: 64Kb - 2GB - Read Performancehmmer: Pfam Database Searchiozone: 4Kb - 2GB - Write Performancetiobench: Read - 64MB - 4tiobench: Rand Write - 64MB - 4tiobench: Rand Write - 32MB - 16multichase: 1GB Array, 256 Byte Stride, 4 Threadsfftw: Stock - 2D FFT Size 128multichase: 1GB Array, 256 Byte Stride, 2 Threadsiozone: 1MB - 2GB - Write Performancemultichase: 1GB Array, 256 Byte Strideiozone: 64Kb - 2GB - Write Performancemultichase: 256MB Array, 256 Byte Stridemultichase: 4MB Array, 64 Byte Striderodinia: OpenCL Heartwallparboil: OpenCL BFSnpb: LU.Atiobench: Read - 32MB - 8tiobench: Rand Write - 32MB - 8fs-mark: 1000 Files, 1MB Sizetiobench: Rand Write - 32MB - 4clpeak: Integer Compute INTpolybench-c: 3 Matrix Multiplicationstiobench: Read - 32MB - 4ctx-clock: Context Switch Timetiobench: Write - 64MB - 4tachyon: Total Timecomd-cl: Average Atom Update Ratesvt-vp9: 1080p 8-bit YUV To VP9 Video Encodesvt-hevc: 1080p 8-bit YUV To HEVC Video Encodeparboil: OpenCL TPACFparboil: OpenMP CUTCPtscp: AI Chess Performancesystem-libxml2: 3 MBclpeak: Global Memory Bandwidthcloverleaf: Lagrangian-Eulerian Hydrodynamicstiobench: Write - 32MB - 4mbw: Memory Copy, Fixed Block Size - 128 MiBmbw: Memory Copy - 128 MiBaio-stress: Rand Writeiozone: 4Kb - 512MB - Read Performanceclpeak: Single-Precision Floatsystem-libxml2: 2 MBiozone: 1MB - 512MB - Read Performanceiozone: 64Kb - 512MB - Read Performancenpb: FT.Aiozone: 4Kb - 512MB - Write Performanceiozone: 1MB - 512MB - Write Performanceiozone: 64Kb - 512MB - Write Performanceclpeak: Kernel Latencyapache-siege: 1fs-mark: 1000 Files, 1MB Size, No Sync/FSyncsystem-libxml2: 850 KBsystem-libxml2: 1 MBblake2: system-libxml2: 950 KBsystem-libxml2: 600 KBsystem-libxml2: 900 KBsystem-libxml2: 400 KBsystem-libxml2: 800 KBsystem-libxml2: 500 KBsystem-libxml2: 750 KBsystem-libxml2: 700 KBsystem-libxml2: 650 KBsystem-libxml2: 550 KBsystem-libxml2: 450 KBsystem-libxml2: 350 KBsystem-libxml2: 300 KBsystem-libxml2: 250 KBsystem-libxml2: 200 KBsystem-libxml2: 100 KBsystem-libxml2: 150 KBsystem-libxml2: 50 KBsystem-libxml2: 5 KBpts-self-test: Peak Memory Usagepts-self-test: Merge Resultspts-self-test: Info Commandpts-self-test: Render Testpts-self-test: List Suitesbullet: Convex Trimeshbullet: Prim Trimeshbullet: 136 Ragdollsbullet: 1000 Convexbullet: 1000 Stackscimark2: Jacobi Successive Over-Relaxationscimark2: Dense LU Matrix Factorizationscimark2: Sparse Matrix Multiplyscimark2: Fast Fourier Transformluajit: Jacobi Successive Over-Relaxationluajit: Dense LU Matrix Factorizationluajit: Sparse Matrix Multiplyluajit: Fast Fourier Transformluajit: Monte Carlojava-scimark2: Jacobi Successive Over-Relaxationjava-scimark2: Dense LU Matrix Factorizationjava-scimark2: Sparse Matrix Multiplyjava-scimark2: Fast Fourier Transformjava-scimark2: Monte Carlostream: Addstream: Triadstream: Scalecompilebench: Read Compiled Treecompilebench: Initial Createblogbench: WriteO3O2 LTO GRAPHITE LTO GRAPHITE LTO GRAPHITE LTO GRAPHITE993114376962509526412398126081066442312431224388626243696301296604451627922120938682781768.141827672272964221422069911271614401075775741805756091221010.44873813811085079731178372562693072141652289723092111599407864771524010553100864887893398925024883.162461271220.1044845920119534.2864.55571052051723229724928024128430758.965785779734240.898051341180.0009273757.965238815210300312913947.5179622471422998671881547.2534.2611.09232236143.39260941.9511217400226097271872142262823375003.261064037.12204364958398425595941179793212811025.7222421155248125827611314501658901095161841911711933.7215733800689557548910.7732.380.3388911311351345554890.7316938721785637867520754008510511110513627796981126881231721173351544395152986887573348789754771302923081396513455827.3012153875519.6625.6862326828.851666722.067157713804223.667472038422.53789358022.65881617138443847393044.6845.223974012952961067214614695.3896.52606714415773522406764487691575455478750787567898012.227981773309931575311103170030932330843182230616317613147580329023933579505367716.72315850932615.7315.763712201384589.131149121131176889308338167497152713.1310886053189522348353078.0783858737313.3074966313.32378255119669304234273812.6168265123112364960010.68401979868610.64193239888420028810232439824029432515327651861910.476.5210.8011882856.4610.461.702361.951.722.401.721106810.0442259445811.479.47352495969.068.9762265264401110158.57692792996.416.11556221640097157151028685.7724612588573314668271671674099339088415248721612510796.97345865.1667822178971050176.53348107196.47323995968122.8161336122612096.171978720877244517.16112915.5455.03198819092.3526.99249673477080.18360619633611024.70257305324.50119074246964954782239163.8331607297571744.02172833.832.44654470723.38108716180181461738470.361116968.67122667.71122562.608.553.011.31465363131115083978911811622.64163426411841.892.683813581.801.91144941916791451.6320286979016398341393629112965946944121751102124012204.751388925664653603.38337327323223280276266241229190159123109857261501625002.981.4733.120.710.970.822.393.874.502222398226415761654374814085065491603502125589421085579495891952256272956440914959111436174514356412419125381061411712441208386583543469946095358737527823449915981581968.11184217226666382141837010127160441114788178183175616399590.44583793771055079331177372563600949134792322123931111598479814751523210881100910491323591524624883.192461281230.1050503820120334.9065.62559202072823229624827924128230758.865798141534000.896631301170.0009221650.545146715110300316382047.6080172533431778776916446.9534.0410.80235739543.34260641.9611216051146148274603153297923152323.351064037.09191588458733224086561181323152011625.7122501154248121152211304491664963928661841511812133.8215893940288192549250.8032.390.3394411111651217562690.4116921621802737227516053978710410910913474194421126561201719473381345504160980057556348917761601301917031460025436627.2912263854119.7325.7063504527.901658522.087130213722823.487472038522.78793356122.33882940338703839393544.6745.223994012952961058414614695.4296.52605414416205392389764317696274676077782793497811412.187980433274531643309073141430677331143157030418314773114080276824468576145610816.823319401128415.4215.753780031384499.151142171138247246311337947518152613.0310836044151527941337117.9285329061613.3075817013.32396795122468904233641212.6568659125512235000710.69398632871310.63192702923020743410207407734039882497327481922410.556.5110.8511872556.5710.421.692361.951.722.401.721058810.0343693436411.709.55339894679.068.9662109563961111128.55691303006.426.10558451632998177266528615.7323712652530325700972271664110279242402249391614211086.91343005.1267506186531058776.56350104936.47323566007122.6760833124112306.131979064874644217.07113415.5955.44198890242.3826.52255093419178.90361859783616934.63263307394.51113504221982549669234833.8931704300411733.99170863.842.44673672433.40110616179182281731370.131184568.65123867.53122862.128.533.021.304804531164152031006918011612.67164116411831.912.683803571.801.92145247516761451.6320590419034398442633612111769067206119161074119912084.761401925404563553.38329323319218275273261237226189156119107847260491625003.001.4633.060.700.970.832.423.914.58222351742692585165438121411516551160350642553943108557934588245210326835644109498997486059501450512384122611041405612421224378135143252902695882402428021522971282081368.20182527277306392141886495127161442110677489172865616334280.45163813841055080431179372564033269146832329022020111441063771921526310968101918192233597924924983.102461241230.1045051720120031.8965.48542372060023229624927924128430658.895819249032970.898231301180.0009259258.145170215210300318649947.4675172456425269216925746.9533.9711.70259317843.39254641.9511118739886199271531154373324706303.121063937.72219462452604527908331186403240511425.7322731155248119137811304501668716366461741512112233.3315954131088107552750.7832.450.3382011011751346543090.49169728222805378245203240597104110106137301955311263512717228833077449071511000537462450539774401301926121522336465827.1812083818919.7025.8165127826.891658822.077139113768923.657479039022.74803353922.30881763938463854396644.6845.233974012952961007014614695.3996.52608014416183762376762067592973988178707785497894012.228141083402932296318083242331640338883259131189325313216483604823967581675661917.163367701020815.4415.443871371380189.181107071123977275307343267648153317.2211076049517518224333378.1384237852113.3474835713.24396895361869199233539912.6069063125612674959410.68403712920710.63195217932820319914087400464109702682327871906310.426.5410.7811777356.3410.541.692351.951.722.411.731043210.0442283450011.949.74341089999.069.0962241265915136228.57689352936.436.10565691639790577159728375.6524815278592327707473841664111919127429247711613010686.87343465.0867312178761040546.53359102646.46325145997422.6261107125112616.201979147934445817.13118715.5555.28198346592.4127.30247883455880.29366509053624974.75263307474.48150024409922449407237163.7431583298831743.99171103.832.52690872403.55110816142180671732070.181096068.69124368.69122961.758.603.011.31475813135315027946912811642.70162046411861.912.713813591.801.92141370316701451.6220191449604398842723636112368597264143011096123812274.761395625584563583.38331323321218279272264239228189157120108847260501625002.991.5332.850.691.000.842.343.934.1422245913335559516543837140952355116035047255810741085580915892652280270255941093988113126803498298612363125021048406212291227387892943325861195641557627822609917682081568.06184156246366392101896591127160441110757216179775616398700.44743783801095080031178372563414993129872319624096111450172401921524110794101862987805336025125083.082461301220.1050605020120031.7565.15593482057323129524727824128330458.835841866332760.897951251200.0009234550.735249315210200313826047.5474892493432708655880847.0633.6511.25249347243.43263441.9811016375396148281771162064523719083.341064037.72191652048453924467301187133252311325.7122681155248125058911324481662902067261741611912333.6515753904190155560430.8132.450.3389311411551363553090.4616853321905137141516054046910511210513696094933127731241728003325944437148993717496548960763311301925151435245441826.9412083838619.6825.6963636028.131650122.087129613773023.977475538622.66793357322.33881684838463855399044.9245.23396401295296986614614695.4296.52605614416036732395755297584472482778778790237938012.208022533277831360308173145830742328543159330267315003118977104024654579845698517.023281131083715.4715.523654361379459.201138361135286861309343367512156317.0311046030462535609344068.1284992777813.3975474213.26371355068969550233753612.6069248125012544979810.84398950868910.62189083887519946312880400944079652709327161888010.366.5410.7911945856.1510.451.742361.961.732.411.731014210.0443866443011.139.72334088679.069.0262355965863136608.54692452876.436.10553371641689187227528495.7724615292582325668372581674143069468397250931612910766.96344235.0667728182691011736.54344104246.47324515886722.9760580122512476.181968735873045617.07119195.5754.63196451962.4126.28250283458980.37366999220608144.72263306524.51150554417929449284242663.6631733295161704.00171023.842.38670570703.49110116234173171725870.261089368.82120567.70124262.238.693.021.30493013115014951966871611652.65160256401801.952.693793581.801.92141515516841451.6420286839004405140973618112264227182142751083122812354.761388925594593603.38333325323221280274265241229190158121108857260501625003.031.4732.850.770.990.842.313.904.0522235603319858116543750140851155116035010255810821085580355886852111267456141466993113666854496734212391125631061416312291228381914743182188495665172228321323925982582068.12183807266636412082166820128161442111187326186335593363440.46303853801055079531177372562631352143362334523991111607173154781509010936101909388913446025024983.162471281210.1052943720120234.9666.76590902040424031025829225129732258.925794189534080.897581301190.0009341758.185389115210233321333747.5181162510425929195873047.0438.6411.21248184343.23262241.9511116708856250276275162038923831363.341063937.13192713159227224760711189113263411442.9422241150248123086411274471663635479661641711912233.9515683972088755562560.7632.380.3390511611651080549290.6016955722161137952515204012810611010813764394421126561211714353342944779148989447539249771765871328519631417787432928.2212123862819.6925.6863822227.141655622.107121313718323.607474339022.74856354422.60883269338813869393944.6845.233984012952961041814614595.4396.53606814416262132381761237683574446978950795288001712.487935553288231462309993152130796328833166030462316123135879350324490561855523316.96334458988115.7815.633793491395969.171122971138607174307348087425154610.5510736029005532851353098.1984326279613.4275839913.32374175438669210234430312.6368985122912575032110.70408492924110.61192841879620352610175384124099942449326691895511.116.5610.7311674256.4310.471.702381.961.732.411.731120010.0343867418711.409.94333494719.119.0762105163921111348.55694682966.436.11551341638198897016928585.7024412623579320697272051674046748931401250601578410886.97345195.1667727179091028426.59347106356.48323356014123.3960408121712336.201978629932445417.24107965.5755.01194922222.3327.25249653463479.79356059676623514.73256304614.50126244384983749842246103.8031647292941743.97173183.852.43689870383.70109116099173551735469.901150069.11121367.19122661.408.633.001.31470163101814870994866011682.69161536671781.892.733783531.801.91144942317171451.6520390119444397941483638115264216962120901100124312214.771408625684703663.38338333329226285286273245233192161123110877362511625003.021.5833.060.730.960.822.383.864.481564405126385601653372514075045521604506525578101085579585890252175267455940873959113357042522773712142123161065448412201224383119443537221895420372727923526958682382368.06184257227126372091857030130161443109888213192195602405460.461138138111050793311553724633894751321924036236891115987219847315263107981019145869212244125325383.142461281230.1057381920219934.2764.70559362098823930925729124929532158.885854492834120.896951291230.0009241550.535356515110200320786447.5480452473432429168872747.0538.7611.40245384343.44252641.9710616379536199279723156561424130163.311064037.10219324158653323944271197023205311242.9323081155248124142811304501661897057461741711711933.8615923887190411557440.7832.390.3380811411751009563190.2416802121956337824516484025610410910613849696811125071261709233364344011150991157573348960754771301923541461562449528.2012083820119.6325.3563916928.511641622.087096313731323.637455738322.84856360822.55882326538823859397744.7045.323984012952961022514614595.3396.49607514416280432403761107584473912177213783727893512.278175303346231879312063195131066335753205930762319923134082087324332580855289216.833204111009316.3015.513793221383209.171110691129406945305346487672151510.5511226023267531031345998.1982230497213.4473815413.33386965133869277233451212.6068789125312865035710.69397741921510.58192510918620423910409398373929842496322961926911.466.5410.7611872656.8710.421.722301.951.722.401.721052610.0443857422211.239.89345995009.068.8962318865349112488.61686422896.426.10558491626199507261828465.7922912658570321675072961574128029150404249931609411246.99343995.1267887185361044946.58343107836.47321525924422.7060646124212826.181979116929943717.00111405.5754.91196542842.4426.42254323440978.83358759748618554.67248306924.50123404188978749455241213.8231449297801694.00171423.842.44661071803.72112016134183871736470.201161168.97123367.72127861.888.503.001.31481423090514632964885811632.70162916411791.912.723783531.791.91145018417241451.6320390829571410142463614115866597256120751068120112234.761408525824673653.38338332328228284282272244232193161123110867362511625003.041.4733.490.720.970.822.393.904.521565568229155771654382914125125511603509025581203108557792589905270127285684104598998086071497843412102122641040407412301217384023843296206795359109827822098933481682968.22183176527136372101896453130161442111937732195095606431320.46103843811095079431177372564287169134942332823290111439307461821515810459101869990103337224724983.092461231210.1046089920120131.9465.33553522072823931025829125029532158.995792911532920.896631311210.0009212058.185238415210200323858047.5774972486427028723893747.0933.9110.83253027043.59252641.9610817704656148278272175062624953763.261064037.70192306753022324006781193073211711042.9723101155248129435611314481663171228261841712011933.5915763857188875557870.8032.450.3387211211450954544990.4817331221990437781516053995710510910613610795275126351231734833324844608149992857564848491779521305123861444608441728.3212053814019.6725.7564490328.741643422.107133513773223.907469339022.86860356622.71881631738793864396444.6545.223984012952961064214514695.4296.50606114416364852383769737617973818379119788737935212.308084523359232030315593216331319335923229031026322063189574008224696531445264316.91339063948615.4315.543800261384199.161122351117986907304343547474151315.5811026041605539098344658.1583371336013.3075997913.24371125394169427233146012.6069081122312514926410.69403580874310.59188525890119458311990403273979032695322431906111.706.5510.8511912956.1010.431.672341.951.722.401.721041310.0442247431111.289.80344192349.068.9862295663921117318.58688572986.436.10564451628096466863228545.8024915232580322668572111674170109025417254581602511096.88345175.1567630161661006866.61355101996.47321765978523.0361101124712336.191978829886244717.11117955.5354.62195028322.3427.65255523460379.09349229125625864.79266304934.49149714316926647349229223.6631454296991724.00171613.862.44665570463.66108615933177491731970.021075968.79123267.94122662.028.463.021.30475813090314881917904811672.70160756411811.872.693803541.801.92141442916841451.6420487929102404041613649113464987142143521088121512304.821388925744643673.38334328324222281277266245231190159122109867361501625003.031.5633.260.850.990.832.303.914.0515685643318356816543751141151155116035080255812231085580565889252295269256141410990112826614506751512400125121041405212151216376397943304525095577755727822147955682082368.18183416776916382141776458129161420109627907184905593334120.47033843811085080331175372663379126143142315725227111450807361801524711232101909791273644625124483.092461271220.1051014220120031.7465.93570322070924031025829125129532058.995790002332840.897271281170.0008704750.655389015210200318052547.6873992494432519128916346.8733.6711.84253525643.40262841.9610916563336097273920176028124583023.371064037.71193581855457623132641193243180811342.9922971155248129998511314491667748840361641711912233.6115743962589728545070.8032.420.3392511111850696554490.6716904522365937952514353953110211110713764396981126671251738243324844352151982617547749003755631327523871490269447728.3112103842319.7125.6163141628.211651022.097127013680823.397476938022.73849358322.59884880238913862393744.9045.233984012952961017014614695.4396.54605214416154372397763377681271882678453784497864512.218214543356031963315463207631348336873220030952321193209177771924162578255289017.05341106996015.5215.513909041388249.251120241119606961319348207615151915.3810936025710529960354598.3285751156713.3273731213.26360305188569536233855412.6168738120712305049110.70347632912510.62190134915220172113780409874079452715325751881511.486.5510.8111885956.4310.531.712411.961.732.411.731040410.0242247435011.189.84335389289.069.0462131064631112678.56693072906.426.11553861632092917019928395.7724615275579324702973461694141319257414250431606310996.89345415.2167994180181031026.59346103566.47322985951322.1060598123212136.201979055924445216.92121075.5555.19194557982.3926.15255693473679.79363249125610734.69261307914.50150784316935851320235803.7631653297111723.97172473.832.46688171633.66107416135181921721269.921067468.67122268.11120562.708.523.001.30486673133114940947908711632.68161696721841.922.693793541.801.92141442917221451.6420590219503397341713617113667717179144411083120712114.791395625564673663.38333332332225280275265241230189158123109857261501625003.001.4133.300.721.000.842.353.934.1415675639319855816533739140851855116035034255812071085580915891152285270156541331OpenBenchmarking.org

CppPerformanceBenchmarks

CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Random NumbersLTOGRAPHITELTO GRAPHITE2004006008001000SE +/- 0.01, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 2.43, N = 3SE +/- 0.04, N = 39599889899939599899909931. (CXX) g++ options: -march=native -pipe -O2 -ftree-vectorize -std=c++11 -O3

Dbench

Dbench is a benchmark designed by the Samba project as a free alternative to netbench, but dbench contains only file-system calls for testing the disk performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 48LTO GRAPHITELTOGRAPHITE2K4K6K8K10KSE +/- 7.48, N = 3SE +/- 9.69, N = 3SE +/- 165.12, N = 9SE +/- 11.02, N = 3SE +/- 8.21, N = 3SE +/- 6.49, N = 3SE +/- 42.71, N = 3SE +/- 78.56, N = 3114371131211143974811366113351128298081. (CC) gcc options: -lpopt -march=native -pipe

O2O3OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 12LTOLTO GRAPHITEGRAPHITE15003000450060007500SE +/- 6.42, N = 3SE +/- 2.66, N = 3SE +/- 101.37, N = 9SE +/- 6.66, N = 3SE +/- 4.07, N = 3SE +/- 1.30, N = 3SE +/- 5.15, N = 3SE +/- 2.96, N = 3704268546614607169626803617460591. (CC) gcc options: -lpopt -march=native -pipe

Numpy Benchmark

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

O2O3OpenBenchmarking.orgNanoseconds, Fewer Is BetterNumpy BenchmarkLTO GRAPHITEGRAPHITELTO1.1M2.2M3.3M4.4M5.5M49673424978434506751552277374982986501450550952645143564

Dbench

Dbench is a benchmark designed by the Samba project as a free alternative to netbench, but dbench contains only file-system calls for testing the disk performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 256LTOLTO GRAPHITEGRAPHITE3K6K9K12K15KSE +/- 8.74, N = 3SE +/- 52.91, N = 3SE +/- 2.76, N = 3SE +/- 22.21, N = 3SE +/- 9.93, N = 3SE +/- 28.96, N = 3SE +/- 13.24, N = 3SE +/- 19.39, N = 312419123981238412363124001239112142121021. (CC) gcc options: -lpopt -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 128LTO GRAPHITELTOGRAPHITE3K6K9K12K15KSE +/- 5.91, N = 3SE +/- 15.40, N = 3SE +/- 7.14, N = 3SE +/- 232.93, N = 3SE +/- 6.10, N = 3SE +/- 6.92, N = 3SE +/- 5.85, N = 3SE +/- 5.87, N = 312608125381250212261125631251212316122641. (CC) gcc options: -lpopt -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 1LTO GRAPHITELTOGRAPHITE2004006008001000SE +/- 2.60, N = 3SE +/- 2.96, N = 3SE +/- 3.34, N = 3SE +/- 6.70, N = 3SE +/- 1.09, N = 3SE +/- 3.69, N = 3SE +/- 4.84, N = 3SE +/- 0.50, N = 3106610611048104110651061104110401. (CC) gcc options: -lpopt -march=native -pipe

O2O3OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 6LTOLTO GRAPHITEGRAPHITE10002000300040005000SE +/- 5.52, N = 3SE +/- 75.93, N = 3SE +/- 5.44, N = 3SE +/- 7.87, N = 3SE +/- 7.00, N = 3SE +/- 2.26, N = 3SE +/- 14.83, N = 3SE +/- 2.06, N = 3448441634074405244234117406240561. (CC) gcc options: -lpopt -march=native -pipe

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.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Fishy Cat - Compute: CUDALTOLTO GRAPHITEGRAPHITE3006009001200150012151220122912301229124212431244

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Fishy Cat - Compute: OpenCLLTOGRAPHITELTO GRAPHITE3006009001200150012081224122412271216121712241228

BlogBench

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

O3O2OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: ReadLTO GRAPHITELTOGRAPHITE800K1600K2400K3200K4000KSE +/- 5417.42, N = 3SE +/- 75432.58, N = 3SE +/- 19918.02, N = 3SE +/- 24300.12, N = 3SE +/- 33892.32, N = 3SE +/- 35356.74, N = 3SE +/- 21282.43, N = 3SE +/- 40313.06, N = 3388626238789293865835378135138402383831194381914737639791. (CC) gcc options: -march=native -pipe -pthread

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATLTO GRAPHITELTOGRAPHITE90M180M270M360M450MSE +/- 359623.43, N = 3SE +/- 268239.00, N = 3SE +/- 969130.90, N = 3SE +/- 551831.61, N = 3SE +/- 740071.73, N = 3SE +/- 177359.32, N = 3SE +/- 143994.60, N = 3SE +/- 660332.35, N = 34369630124346994604332586114325290264353722184330452504329620674318218841. (CC) gcc options: -march=native -pipe -O3 -lm

O3O2OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: DOUBLELTO GRAPHITEGRAPHITELTO200M400M600M800M1000MSE +/- 949353.12, N = 3SE +/- 1939878.89, N = 3SE +/- 3203089.79, N = 3SE +/- 1986693.57, N = 3SE +/- 1620971.61, N = 3SE +/- 1129622.34, N = 3SE +/- 3024118.72, N = 3SE +/- 296143.00, N = 39660445169588240249564155769535873759566517229557775579542037279535910981. (CC) gcc options: -march=native -pipe -O3 -lm

CppPerformanceBenchmarks

CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Math LibraryLTOGRAPHITELTO GRAPHITE60120180240300SE +/- 0.18, N = 3SE +/- 0.50, N = 3SE +/- 0.43, N = 3SE +/- 1.19, N = 3SE +/- 0.05, N = 3SE +/- 0.20, N = 3SE +/- 0.61, N = 3SE +/- 2.60, N = 32782782792802782782792831. (CXX) g++ options: -march=native -pipe -std=c++11 -O3

Tinymembench

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

O2O3OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard MemsetLTOLTO GRAPHITEGRAPHITE5K10K15K20K25KSE +/- 1871.91, N = 3SE +/- 154.87, N = 3SE +/- 556.96, N = 3SE +/- 318.81, N = 3SE +/- 1504.62, N = 3SE +/- 222.91, N = 3SE +/- 109.36, N = 3SE +/- 342.53, N = 323526221472209821323234492260922120215221. (CC) gcc options: -O2 -march=native -pipe -lm

O3O2OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard MemcpyGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 106.07, N = 3SE +/- 63.95, N = 3SE +/- 29.34, N = 3SE +/- 30.81, N = 3SE +/- 20.59, N = 3SE +/- 68.34, N = 3SE +/- 37.35, N = 3SE +/- 55.09, N = 3971293869176915995869556933492591. (CC) gcc options: -O2 -march=native -pipe -lm

Blender

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Pabellon Barcelona - Compute: OpenCLLTOGRAPHITELTO GRAPHITE2004006008001000815820820827816820823825

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Pabellon Barcelona - Compute: CUDAGRAPHITELTO GRAPHITELTO2004006008001000813815817819820823823829

RAR Compression

This test measures the time needed to archive/compress two copies of the Linux 4.13 kernel source tree using RAR/WinRAR compression. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRAR Compression 5.6.1Linux Source Tree Archiving To RARLTOLTO GRAPHITEGRAPHITE1530456075SE +/- 1.86, N = 12SE +/- 1.85, N = 12SE +/- 1.83, N = 12SE +/- 1.86, N = 12SE +/- 1.84, N = 12SE +/- 1.86, N = 12SE +/- 1.83, N = 12SE +/- 1.83, N = 1268.0668.1168.1468.2068.0668.1268.1868.22

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 4096LTOLTO GRAPHITEGRAPHITE4K8K12K16K20KSE +/- 41.63, N = 3SE +/- 277.22, N = 3SE +/- 151.24, N = 3SE +/- 53.25, N = 3SE +/- 144.08, N = 3SE +/- 37.18, N = 3SE +/- 96.78, N = 3SE +/- 9.07, N = 318425183801834118317184211841518276182521. (CC) gcc options: -pthread -march=native -pipe -lm

Blender

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CUDAGRAPHITELTO GRAPHITELTO160320480640800624722722727652677722726

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: OpenCLLTO GRAPHITELTOGRAPHITE160320480640800636666729730663691712713

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SerialLTOGRAPHITELTO GRAPHITE140280420560700637637638641638639639642

LZMA Compression

This test measures the time needed to compress a file using LZMA compression. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterLZMA Compression256MB File CompressionLTO GRAPHITELTOGRAPHITE50100150200250SE +/- 0.60, N = 3SE +/- 0.44, N = 3SE +/- 0.25, N = 3SE +/- 0.17, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 3SE +/- 0.19, N = 32082092102142102142142141. (CXX) g++ options: -march=native -pipe

LLVM Test Suite

This test times how long it takes to run the LLVM Test Suite. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterLLVM Test Suite 6.0.0Time To RunLTOGRAPHITELTO GRAPHITE50100150200250SE +/- 0.27, N = 3SE +/- 0.18, N = 3SE +/- 0.10, N = 3SE +/- 0.29, N = 3SE +/- 0.15, N = 3SE +/- 0.32, N = 3SE +/- 0.19, N = 3SE +/- 0.28, N = 31771851892161831881892201. (CXX) g++ options: -march=native -pipe -O3 -lstdc++

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096LTOLTO GRAPHITEGRAPHITE15003000450060007500SE +/- 38.39, N = 3SE +/- 49.67, N = 3SE +/- 61.19, N = 3SE +/- 11.01, N = 3SE +/- 26.15, N = 3SE +/- 48.78, N = 3SE +/- 42.46, N = 3SE +/- 34.34, N = 3703068206458645370106991659164951. (CC) gcc options: -pthread -march=native -pipe -lm

Phoronix Test Suite Self Test

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Total TimeLTO GRAPHITELTOGRAPHITE306090120150SE +/- 0.30, N = 3SE +/- 0.71, N = 3SE +/- 0.38, N = 3SE +/- 0.54, N = 3SE +/- 0.25, N = 3SE +/- 1.12, N = 3SE +/- 0.62, N = 3SE +/- 0.78, N = 3127127127127128129130130

Scikit-Learn

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1LTOLTO GRAPHITEGRAPHITE4080120160200SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.28, N = 3SE +/- 0.16, N = 3SE +/- 0.19, N = 3160160161161161161161161

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.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-OnlyLTO GRAPHITELTOGRAPHITE100200300400500420442442443440441441442

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 6LTO GRAPHITELTOGRAPHITE2K4K6K8K10KSE +/- 211.54, N = 15SE +/- 145.80, N = 15SE +/- 233.63, N = 15SE +/- 118.00, N = 11SE +/- 211.49, N = 15SE +/- 207.78, N = 15SE +/- 132.25, N = 15SE +/- 239.88, N = 1510757110671107511478109621098811118111931. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 32 - Workers Per Message Thread: 2LTO GRAPHITEGRAPHITELTO2K4K6K8K10KSE +/- 513.56, N = 12SE +/- 398.91, N = 15SE +/- 410.48, N = 15SE +/- 210.62, N = 13SE +/- 391.99, N = 15SE +/- 377.81, N = 15SE +/- 330.48, N = 15SE +/- 321.66, N = 15721674897574817873267732790782131. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 16GRAPHITELTO GRAPHITELTO4K8K12K16K20KSE +/- 599.09, N = 15SE +/- 547.15, N = 15SE +/- 461.30, N = 15SE +/- 577.60, N = 15SE +/- 424.17, N = 15SE +/- 472.69, N = 12SE +/- 320.32, N = 15SE +/- 429.71, N = 1217286179771805718317184901863319219195091. (CC) gcc options: -O2 -lpthread

GNU GMP GMPbench

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

O3O2OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.1.2Total TimeGRAPHITELTOLTO GRAPHITE12002400360048006000561656165616560956065602559355931. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -lm

Apache Siege

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

O3O2OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200LTO GRAPHITEGRAPHITELTO30K60K90K120K150KSE +/- 7609.36, N = 12SE +/- 466.62, N = 8SE +/- 399.98, N = 15SE +/- 70.88, N = 3SE +/- 534.46, N = 7SE +/- 368.77, N = 14SE +/- 404.41, N = 9SE +/- 58.16, N = 3122101399593987033428431324054636344334121. (CC) gcc options: -march=native -pipe -lpthread -ldl -lssl -lcrypto

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkLTOLTO GRAPHITEGRAPHITE0.10580.21160.31740.42320.529SE +/- 0.0005, N = 3SE +/- 0.0019, N = 3SE +/- 0.0003, N = 3SE +/- 0.0018, N = 3SE +/- 0.0009, N = 3SE +/- 0.0008, N = 3SE +/- 0.0003, N = 3SE +/- 0.0011, N = 30.44580.44740.44870.45160.46100.46110.46300.47031. R scripting front-end version 3.6.0 (2019-04-26)

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: CUDALTOLTO GRAPHITEGRAPHITE80160240320400378379381381381384384385

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: OpenCLLTOLTO GRAPHITEGRAPHITE80160240320400377380381384380381381381

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingLTOGRAPHITELTO GRAPHITE20406080100SE +/- 0.89, N = 3SE +/- 1.01, N = 3SE +/- 1.58, N = 5SE +/- 2.03, N = 3SE +/- 0.95, N = 3SE +/- 1.59, N = 5SE +/- 1.54, N = 3SE +/- 1.26, N = 31051051081091051081091101. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteGRAPHITELTO GRAPHITELTO11K22K33K44K55KSE +/- 10.30, N = 3SE +/- 2.79, N = 3SE +/- 1.57, N = 3SE +/- 3.39, N = 3SE +/- 4.66, N = 3SE +/- 2.40, N = 3SE +/- 4.03, N = 3SE +/- 4.97, N = 350804508005079750793508035079550794507931. (CC) gcc options: -lrt

O3O2OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteGRAPHITELTO GRAPHITELTO7K14K21K28K35KSE +/- 0.37, N = 3SE +/- 0.29, N = 3SE +/- 0.84, N = 3SE +/- 0.28, N = 3SE +/- 0.24, N = 3SE +/- 1.21, N = 3SE +/- 1.36, N = 3SE +/- 22.81, N = 331179311783117831177311773117731175311551. (CC) gcc options: -lrt

O2O3OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: ReadGRAPHITELTO GRAPHITELTO8001600240032004000SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.22, N = 3SE +/- 1.15, N = 3SE +/- 0.16, N = 3SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.23, N = 3372637253725372437253725372537251. (CC) gcc options: -lrt

asmFish

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

O2O3OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthGRAPHITELTOLTO GRAPHITE14M28M42M56M70MSE +/- 224301.53, N = 3SE +/- 1212462.43, N = 3SE +/- 524774.43, N = 3SE +/- 83485.52, N = 3SE +/- 183322.24, N = 3SE +/- 522758.71, N = 3SE +/- 34223.87, N = 3SE +/- 859562.02, N = 36428716963389475633791266263135264033269636009496341499362693072

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 8LTOGRAPHITELTO GRAPHITE3K6K9K12K15KSE +/- 21.33, N = 3SE +/- 241.52, N = 15SE +/- 334.44, N = 15SE +/- 560.84, N = 15SE +/- 201.78, N = 5SE +/- 267.24, N = 15SE +/- 488.50, N = 15SE +/- 453.98, N = 1512987134791416514683132191349414314143361. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 6LTO GRAPHITELTOGRAPHITE5K10K15K20K25KSE +/- 305.69, N = 15SE +/- 426.89, N = 15SE +/- 76.92, N = 3SE +/- 354.90, N = 15SE +/- 358.88, N = 3SE +/- 423.93, N = 15SE +/- 442.32, N = 15SE +/- 482.28, N = 1522897231962322123290231572332823345240361. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 32GRAPHITELTO GRAPHITELTO5K10K15K20K25KSE +/- 1012.51, N = 12SE +/- 1071.55, N = 15SE +/- 897.77, N = 15SE +/- 760.86, N = 12SE +/- 808.09, N = 15SE +/- 1154.28, N = 12SE +/- 1206.66, N = 12SE +/- 216.51, N = 322020230922393124096232902368923991252271. (CC) gcc options: -O2 -lpthread

BYTE Unix Benchmark

This is a test of BYTE. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Floating-Point ArithmeticGRAPHITELTOLTO GRAPHITE0.2250.450.6750.91.125111111111. (CC) gcc options: -march=native -pipe -O3

O2O3OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Register ArithmeticGRAPHITELTOLTO GRAPHITE0.2250.450.6750.91.125111111111. (CC) gcc options: -march=native -pipe -O3

O2O3OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Integer ArithmeticGRAPHITELTOLTO GRAPHITE0.2250.450.6750.91.125111111111. (CC) gcc options: -march=native -pipe -O3

O2O3OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2LTO GRAPHITELTOGRAPHITE13M26M39M52M65MSE +/- 535439.20, N = 3SE +/- 177886.75, N = 3SE +/- 245871.68, N = 3SE +/- 197747.51, N = 3SE +/- 114177.08, N = 3SE +/- 266227.30, N = 3SE +/- 77816.46, N = 3SE +/- 128858.07, N = 360717315598721984508073643930746599407865984798145017240441063771. (CC) gcc options: -march=native -pipe

Timed LLVM Compilation

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

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileGRAPHITELTOLTO GRAPHITE100200300400500180182473478192192475477

Fhourstones

This integer benchmark solves positions in the game of Connect-4, as played on a vertical 7x6 board. By default, it uses a 64Mb transposition table with the twobig replacement strategy. Positions are represented as 64-bit bitboards, and the hash function is computed using a single 64-bit modulo operation, giving 64-bit machines a slight edge. The alpha-beta searcher sorts moves dynamically based on the history heuristic. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgKpos / sec, More Is BetterFhourstones 3.1Complex Connect-4 SolvingLTOGRAPHITELTO GRAPHITE3K6K9K12K15KSE +/- 18.55, N = 3SE +/- 12.01, N = 3SE +/- 9.47, N = 3SE +/- 7.46, N = 3SE +/- 1.96, N = 3SE +/- 9.79, N = 3SE +/- 4.02, N = 3SE +/- 19.59, N = 315263152471515815090152631524115240152321. (CC) gcc options: -O3

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 4GRAPHITELTO GRAPHITELTO2K4K6K8K10KSE +/- 138.67, N = 3SE +/- 203.36, N = 15SE +/- 129.39, N = 8SE +/- 176.48, N = 4SE +/- 186.50, N = 15SE +/- 182.39, N = 15SE +/- 196.91, N = 15SE +/- 265.87, N = 1210459107981093611232105531079410881109681. (CC) gcc options: -O2 -lpthread

Minion

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: QuasigroupLTO GRAPHITELTOGRAPHITE20406080100SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.20, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.29, N = 3SE +/- 0.24, N = 3SE +/- 0.19, N = 31001001011011011011011011. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

MBW

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

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 8192 MiBGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 2.43, N = 3SE +/- 0.55, N = 3SE +/- 0.46, N = 3SE +/- 1.86, N = 3SE +/- 3.12, N = 3SE +/- 1.92, N = 3SE +/- 0.47, N = 3SE +/- 1.43, N = 3918191048648862991459097909386991. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiBGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 2.68, N = 3SE +/- 2.07, N = 3SE +/- 1.68, N = 3SE +/- 2.77, N = 3SE +/- 1.24, N = 3SE +/- 112.86, N = 3SE +/- 170.92, N = 3SE +/- 4.03, N = 3922391328789878091279010889186921. (CC) gcc options: -O3 -march=native -pipe

Apache Siege

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

O2O3OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250LTOGRAPHITELTO GRAPHITE30K60K90K120K150KSE +/- 8729.27, N = 12SE +/- 633.35, N = 3SE +/- 310.67, N = 3SE +/- 27.52, N = 3SE +/- 1450.97, N = 15SE +/- 640.08, N = 3SE +/- 590.10, N = 3SE +/- 281.09, N = 3122441364463446033372533603597935915339891. (CC) gcc options: -march=native -pipe -lpthread -ldl -lssl -lcrypto

Blender

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Classroom - Compute: OpenCLLTOGRAPHITELTO GRAPHITE60120180240300246249250251247250251253

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Classroom - Compute: CUDALTO GRAPHITELTOGRAPHITE60120180240300244249249253248248249250

CppPerformanceBenchmarks

CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov VectorGRAPHITELTOLTO GRAPHITE20406080100SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 383.0883.1083.1683.1983.0983.0983.1483.161. (CXX) g++ options: -march=native -pipe -std=c++11 -O3

Blender

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Pabellon Barcelona - Compute: CPU-OnlyLTO GRAPHITELTOGRAPHITE50100150200250246246246246246246246247

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 6GRAPHITELTO GRAPHITELTO306090120150SE +/- 1.00, N = 3SE +/- 1.70, N = 15SE +/- 1.53, N = 3SE +/- 1.45, N = 15SE +/- 1.71, N = 6SE +/- 2.25, N = 41231271281281241271281301. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 4LTO GRAPHITEGRAPHITELTO306090120150SE +/- 1.53, N = 3SE +/- 1.25, N = 15SE +/- 1.00, N = 3SE +/- 2.40, N = 3SE +/- 1.53, N = 15SE +/- 1.33, N = 3SE +/- 1.48, N = 151211211221231221221231231. (CC) gcc options: -O2 -lpthread

Perl Benchmarks

Perl benchmark suite that can be used to compare the relative speed of different versions of perl. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: Pod2htmlLTO GRAPHITEGRAPHITELTO0.02380.04760.07140.09520.119SE +/- 0.00035883, N = 3SE +/- 0.00009383, N = 3SE +/- 0.00015272, N = 3SE +/- 0.00026637, N = 3SE +/- 0.00007060, N = 3SE +/- 0.00025085, N = 3SE +/- 0.00043538, N = 3SE +/- 0.00012571, N = 30.104484590.104505170.105050380.105060500.104608990.105101420.105294370.10573819

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Classroom - Compute: CPU-OnlyLTO GRAPHITELTOGRAPHITE4080120160200201201201201201201201202

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP ParallelLTO GRAPHITELTOGRAPHITE4080120160200195200200203199200201202

CppPerformanceBenchmarks

CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: CtypeGRAPHITELTOLTO GRAPHITE816243240SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.48, N = 15SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.52, N = 1431.7431.9434.2734.9631.7531.8934.2834.901. (CXX) g++ options: -march=native -pipe -O3 -std=c++11

Minion

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: SolitaireLTO GRAPHITELTOGRAPHITE1530456075SE +/- 0.44, N = 3SE +/- 0.92, N = 3SE +/- 1.27, N = 3SE +/- 1.18, N = 3SE +/- 0.74, N = 3SE +/- 1.04, N = 3SE +/- 0.52, N = 3SE +/- 0.88, N = 364.5565.1565.4865.6264.7065.3365.9366.761. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 256MB - Thread Count: 16LTO GRAPHITELTOGRAPHITE13K26K39K52K65KSE +/- 98.77, N = 3SE +/- 1278.46, N = 15SE +/- 1574.97, N = 15SE +/- 1850.70, N = 15SE +/- 113.41, N = 3SE +/- 1376.66, N = 15SE +/- 1570.27, N = 15SE +/- 1666.45, N = 1559348571055592054237590905703255936553521. (CC) gcc options: -O2

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2048LTOGRAPHITELTO GRAPHITE4K8K12K16K20KSE +/- 56.10, N = 3SE +/- 60.10, N = 3SE +/- 71.36, N = 3SE +/- 61.55, N = 3SE +/- 89.34, N = 3SE +/- 45.45, N = 3SE +/- 110.88, N = 3SE +/- 39.48, N = 320988207282070920404207282060020573205171. (CC) gcc options: -pthread -march=native -pipe -lm

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests to stress the system's CPU. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SharpenLTO GRAPHITEGRAPHITELTO501001502002502402402392392322322322311. (CC) gcc options: -fopenmp -march=native -pipe -O3 -pthread -lwebp -lwebpmux -llcms2 -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lgomp -lpthread

O2O3OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: ResizingGRAPHITELTO GRAPHITELTO70140210280350SE +/- 0.33, N = 3SE +/- 0.33, N = 33103103103092972962962951. (CC) gcc options: -fopenmp -march=native -pipe -O3 -pthread -lwebp -lwebpmux -llcms2 -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lgomp -lpthread

O2O3OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: EnhancedGRAPHITELTO GRAPHITELTO601201802403002582582582572492492482471. (CC) gcc options: -fopenmp -march=native -pipe -O3 -pthread -lwebp -lwebpmux -llcms2 -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lgomp -lpthread

O2O3OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SwirlLTO GRAPHITEGRAPHITELTO60120180240300SE +/- 0.33, N = 32922912912912802792792781. (CC) gcc options: -fopenmp -march=native -pipe -O3 -pthread -lwebp -lwebpmux -llcms2 -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lgomp -lpthread

O2O3OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Noise-GaussianLTO GRAPHITEGRAPHITELTO50100150200250SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 32512512502492412412412411. (CC) gcc options: -fopenmp -march=native -pipe -O3 -pthread -lwebp -lwebpmux -llcms2 -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lgomp -lpthread

O2O3OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: RotateLTO GRAPHITEGRAPHITELTO60120180240300SE +/- 0.67, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 32972952952952842842832821. (CC) gcc options: -fopenmp -march=native -pipe -O3 -pthread -lwebp -lwebpmux -llcms2 -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lgomp -lpthread

O2O3OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color SpaceLTO GRAPHITEGRAPHITELTO70140210280350SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 33223213213203073073063041. (CC) gcc options: -fopenmp -march=native -pipe -O3 -pthread -lwebp -lwebpmux -llcms2 -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lgomp -lpthread

CppPerformanceBenchmarks

CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: AtolLTOGRAPHITELTO GRAPHITE1326395265SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 358.8358.8658.8958.9658.8858.9258.9958.991. (CXX) g++ options: -march=native -pipe -std=c++11 -O3

Stockfish

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

O2O3OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total TimeLTOGRAPHITELTO GRAPHITE13M26M39M52M65MSE +/- 163171.06, N = 3SE +/- 442251.22, N = 3SE +/- 419940.18, N = 3SE +/- 317798.82, N = 3SE +/- 335559.98, N = 3SE +/- 544476.89, N = 3SE +/- 207209.46, N = 3SE +/- 112930.23, N = 358544928579418955792911557900023584186635819249057981415578577971. (CXX) g++ options: -m64 -lpthread -march=native -pipe -O3 -fno-exceptions -std=c++11 -pedantic -msse -msse3 -mpopcnt -flto

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.

O3O2OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverLTO GRAPHITELTOGRAPHITE7001400210028003500SE +/- 4.16, N = 3SE +/- 0.83, N = 3SE +/- 9.05, N = 3SE +/- 2.61, N = 3SE +/- 7.40, N = 3SE +/- 0.77, N = 3SE +/- 6.87, N = 3SE +/- 4.47, N = 3342434003297327634123408329232841. (CC) gcc options: -O3 -march=native -pipe -mavx2

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.

O3O2OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsLTOGRAPHITELTO GRAPHITE0.20210.40420.60630.80841.0105SE +/- 0.00086, N = 3SE +/- 0.00087, N = 3SE +/- 0.00122, N = 3SE +/- 0.00118, N = 3SE +/- 0.00098, N = 3SE +/- 0.00128, N = 3SE +/- 0.00068, N = 3SE +/- 0.00042, N = 30.896630.897950.898050.898230.896630.896950.897270.89758

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 8LTOGRAPHITELTO GRAPHITE306090120150SE +/- 1.53, N = 3SE +/- 1.69, N = 7SE +/- 0.67, N = 3SE +/- 1.86, N = 3SE +/- 1.48, N = 15SE +/- 1.66, N = 7SE +/- 2.10, N = 4SE +/- 0.88, N = 31251301301341281291301311. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 2LTOLTO GRAPHITEGRAPHITE306090120150SE +/- 1.20, N = 3SE +/- 2.03, N = 3SE +/- 1.15, N = 3SE +/- 1.86, N = 3SE +/- 1.51, N = 7SE +/- 1.83, N = 15SE +/- 1.60, N = 71171181181201171191211231. (CC) gcc options: -O2 -lpthread

Perl Benchmarks

Perl benchmark suite that can be used to compare the relative speed of different versions of perl. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: InterpreterGRAPHITELTOLTO GRAPHITE0.00020.00040.00060.00080.001SE +/- 0.00000189, N = 3SE +/- 0.00000416, N = 3SE +/- 0.00000106, N = 3SE +/- 0.00000793, N = 3SE +/- 0.00000371, N = 3SE +/- 0.00000210, N = 3SE +/- 0.00000487, N = 3SE +/- 0.00000572, N = 30.000870470.000921200.000924150.000934170.000922160.000923450.000925920.00092737

Timed MrBayes Analysis

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

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.1.2Primate Phylogeny AnalysisLTOLTO GRAPHITEGRAPHITE1326395265SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 350.5350.6558.1858.1850.5450.7357.9658.14

System Libxml2 Parsing

This test measures the time to parse a random XML file with libxml2 via xmllint using the streaming API. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 112 MBLTOGRAPHITELTO GRAPHITE12K24K36K48K60KSE +/- 111.92, N = 3SE +/- 232.90, N = 3SE +/- 329.72, N = 3SE +/- 589.51, N = 3SE +/- 199.91, N = 3SE +/- 478.48, N = 3SE +/- 399.30, N = 3SE +/- 392.00, N = 35146751702523885249352384535655389053891

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Fishy Cat - Compute: CPU-OnlyLTOLTO GRAPHITEGRAPHITE306090120150151152152152151152152152

GNU MPC

GNU MPC is a C library for the arithmetic of complex numbers. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgGlobal Score, More Is BetterGNU MPC 1.1.0Multi-Precision BenchmarkGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 33.33, N = 310300103001030010200102331020010200102001. (CC) gcc options: -lm -march=native -pipe -MT -MD -MP -MF

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 256MB - Thread Count: 32GRAPHITELTO GRAPHITELTO700K1400K2100K2800K3500KSE +/- 32190.17, N = 3SE +/- 24286.71, N = 3SE +/- 39307.38, N = 12SE +/- 44001.81, N = 3SE +/- 38518.43, N = 8SE +/- 10648.00, N = 3SE +/- 51183.08, N = 15SE +/- 55839.58, N = 3323858032133373207864318052531864993163820313826031291391. (CC) gcc options: -O2

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBMGRAPHITELTO GRAPHITELTO1122334455SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 347.4647.5147.5447.6047.5147.5447.5747.681. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2048LTO GRAPHITELTOGRAPHITE2K4K6K8K10KSE +/- 44.86, N = 3SE +/- 52.27, N = 3SE +/- 46.57, N = 3SE +/- 108.40, N = 3SE +/- 8.47, N = 3SE +/- 15.36, N = 3SE +/- 17.16, N = 3SE +/- 39.38, N = 3811680457497739980177962751774891. (CC) gcc options: -pthread -march=native -pipe -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.

O3O2OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansGRAPHITELTO GRAPHITELTO5001000150020002500SE +/- 3.97, N = 4SE +/- 11.51, N = 4SE +/- 15.18, N = 4SE +/- 18.93, N = 4SE +/- 24.50, N = 4SE +/- 15.47, N = 4SE +/- 14.01, N = 4SE +/- 7.08, N = 424562471249325332473248624942510

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: LU.CLTOGRAPHITELTO GRAPHITE9K18K27K36K45KSE +/- 21.73, N = 3SE +/- 49.13, N = 3SE +/- 73.68, N = 3SE +/- 93.42, N = 3SE +/- 42.81, N = 3SE +/- 53.04, N = 3SE +/- 37.43, N = 3SE +/- 132.51, N = 343270431774252642299432514324242702425921. 3.3

MBW

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

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiBGRAPHITELTO GRAPHITELTO2K4K6K8K10KSE +/- 2.74, N = 3SE +/- 155.55, N = 3SE +/- 0.17, N = 3SE +/- 1.58, N = 3SE +/- 32.49, N = 3SE +/- 2.87, N = 3SE +/- 2.62, N = 3SE +/- 1.93, N = 3921687768671865591959168912887231. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiBGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 2.81, N = 3SE +/- 5.01, N = 3SE +/- 3.12, N = 3SE +/- 5.81, N = 3SE +/- 0.19, N = 3SE +/- 2.09, N = 3SE +/- 1.11, N = 3SE +/- 1.17, N = 3925791648815880891638937873087271. (CC) gcc options: -O3 -march=native -pipe

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.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL MyocyteLTOGRAPHITELTO GRAPHITE1122334455SE +/- 0.09, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.35, N = 346.8747.0447.0547.0946.9546.9547.0647.251. (CXX) g++ options: -O2 -lOpenCL

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To CompileGRAPHITELTOLTO GRAPHITE918273645SE +/- 0.48, N = 5SE +/- 0.67, N = 3SE +/- 0.50, N = 5SE +/- 0.55, N = 4SE +/- 0.50, N = 4SE +/- 0.59, N = 3SE +/- 0.63, N = 4SE +/- 0.60, N = 433.6533.9734.0434.2633.6733.9138.6438.76

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterLTOGRAPHITELTO GRAPHITE3691215SE +/- 0.01, N = 3SE +/- 0.16, N = 15SE +/- 0.18, N = 15SE +/- 0.20, N = 15SE +/- 0.01, N = 3SE +/- 0.18, N = 15SE +/- 0.20, N = 15SE +/- 0.19, N = 1510.8011.0911.2511.7010.8311.2111.4011.841. (CXX) g++ options: -O2 -lOpenCL

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 256MB - Thread Count: 16GRAPHITELTO GRAPHITELTO600K1200K1800K2400K3000KSE +/- 17175.69, N = 3SE +/- 24115.47, N = 3SE +/- 59239.72, N = 12SE +/- 53296.44, N = 15SE +/- 37971.60, N = 3SE +/- 32461.38, N = 3SE +/- 41740.39, N = 15SE +/- 39625.19, N = 15259317824934722357395232236125352562530270248184324538431. (CC) gcc options: -O2

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ProcessLTO GRAPHITELTOGRAPHITE1020304050SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 343.2343.4043.4443.5943.3443.3943.3943.431. (CC) gcc options: -lpthread -march=native -pipe

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.

O2O3OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapLTOGRAPHITELTO GRAPHITE6001200180024003000SE +/- 18.82, N = 4SE +/- 41.76, N = 4SE +/- 22.76, N = 16SE +/- 25.66, N = 4SE +/- 17.03, N = 4SE +/- 32.95, N = 7SE +/- 39.00, N = 4SE +/- 15.26, N = 425262526262226282546260626092634

Rust Mandelbrot

This test profile is of the combined time for the serial and parallel Mandelbrot sets written in Rustlang via willi-kappler/mandel-rust. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel MandelbrotLTO GRAPHITEGRAPHITELTO1020304050SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 341.9541.9541.9641.9841.9541.9641.9641.97

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 6 - Workers Per Message Thread: 2LTOGRAPHITELTO GRAPHITE306090120150SE +/- 0.67, N = 3SE +/- 1.73, N = 3SE +/- 1.00, N = 3SE +/- 0.88, N = 3SE +/- 1.11, N = 121061081091111101111121121. (CC) gcc options: -O2 -lpthread

Redis

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

O3O2OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SETGRAPHITELTO GRAPHITELTO400K800K1200K1600K2000KSE +/- 12198.66, N = 3SE +/- 42914.21, N = 15SE +/- 44000.06, N = 15SE +/- 36074.39, N = 15SE +/- 22278.31, N = 3SE +/- 41556.34, N = 15SE +/- 49354.23, N = 12SE +/- 42636.67, N = 14187398817400221637539160511417704651670885165633316379531. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

PostMark

This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction PerformanceLTO GRAPHITELTOGRAPHITE13002600390052006500SE +/- 51.00, N = 3SE +/- 51.00, N = 3SE +/- 51.00, N = 3SE +/- 51.00, N = 3SE +/- 51.00, N = 3625061996148609761996148614860971. (CC) gcc options: -O3

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 32 - Workers Per Message Thread: 32GRAPHITELTO GRAPHITELTO60K120K180K240K300KSE +/- 3563.62, N = 3SE +/- 1564.19, N = 3SE +/- 2238.27, N = 3SE +/- 1806.17, N = 3SE +/- 3876.80, N = 3SE +/- 2995.38, N = 10SE +/- 4827.94, N = 4SE +/- 2665.90, N = 32715312718722746032817712739202762752782722797231. (CC) gcc options: -O2 -lpthread

Redis

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

O2O3OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSHGRAPHITELTO GRAPHITELTO400K800K1200K1600K2000KSE +/- 27901.87, N = 12SE +/- 17642.80, N = 15SE +/- 36228.58, N = 12SE +/- 36092.91, N = 15SE +/- 32251.87, N = 15SE +/- 26391.54, N = 15SE +/- 3926.71, N = 3SE +/- 10444.11, N = 3176028117506261620389156561416206451543733153297914226281. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

O2O3OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GETGRAPHITELTOLTO GRAPHITE500K1000K1500K2000K2500KSE +/- 32280.60, N = 7SE +/- 35503.43, N = 15SE +/- 39645.32, N = 4SE +/- 47452.96, N = 15SE +/- 46039.99, N = 15SE +/- 36001.71, N = 5SE +/- 46590.30, N = 15SE +/- 37031.01, N = 15249537624583022413016238313624706302371908233750023152321. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Sockperf

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

O3O2OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping PongGRAPHITELTO GRAPHITELTO0.75831.51662.27493.03323.7915SE +/- 0.07, N = 25SE +/- 0.03, N = 25SE +/- 0.02, N = 5SE +/- 0.02, N = 5SE +/- 0.04, N = 25SE +/- 0.04, N = 21SE +/- 0.01, N = 5SE +/- 0.02, N = 53.123.263.343.353.263.313.343.371. (CXX) g++ options: --param -march=native -pipe -rdynamic -ldl -lpthread

lzbench

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

O2O3OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: DecompressionGRAPHITELTOLTO GRAPHITE204060801001061061061061061061061061. (CXX) g++ options: -lrt -static -lpthread

O2O3OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: CompressionGRAPHITELTOLTO GRAPHITE918273645SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 340404039404040391. (CXX) g++ options: -lrt -static -lpthread

m-queens

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveLTOLTO GRAPHITEGRAPHITE918273645SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 337.0937.1237.7237.7237.1037.1337.7037.711. (CXX) g++ options: -fopenmp -march=native -pipe -O2

Redis

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

O3O2OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADDGRAPHITELTOLTO GRAPHITE500K1000K1500K2000K2500KSE +/- 6440.58, N = 3SE +/- 38089.22, N = 3SE +/- 51368.48, N = 15SE +/- 44604.29, N = 15SE +/- 16766.14, N = 3SE +/- 58274.33, N = 15SE +/- 52644.10, N = 15SE +/- 53674.02, N = 15219462420436491916520191588421932411935818192713119230671. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

ebizzy

This is a test of ebizzy, a program to generate workloads resembling web server workloads. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3LTO GRAPHITELTOGRAPHITE130K260K390K520K650KSE +/- 6383.63, N = 10SE +/- 4747.42, N = 3SE +/- 8631.83, N = 4SE +/- 7283.08, N = 3SE +/- 5616.97, N = 3SE +/- 2130.51, N = 3SE +/- 6097.02, N = 15SE +/- 9659.20, N = 35922725865335545765302235873325839845260454845391. (CC) gcc options: -pthread -lpthread -march=native -pipe -O3

Redis

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

O3O2OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPOPGRAPHITELTO GRAPHITELTO600K1200K1800K2400K3000KSE +/- 13774.42, N = 3SE +/- 51584.55, N = 3SE +/- 45866.07, N = 3SE +/- 37834.45, N = 15SE +/- 32312.34, N = 15SE +/- 50196.02, N = 15SE +/- 58370.54, N = 15SE +/- 50781.01, N = 15279083325595942446730240865624760712400678239442723132641. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

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.

O2O3OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestLTOGRAPHITELTO GRAPHITE30K60K90K120K150KSE +/- 366.05, N = 3SE +/- 326.76, N = 3SE +/- 269.21, N = 3SE +/- 500.30, N = 3SE +/- 328.13, N = 3SE +/- 108.27, N = 3SE +/- 385.01, N = 3SE +/- 250.71, N = 31197021193241193071189111187131186401181321179791. (CXX) g++ options: -pipe -lpthread

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 6 - Workers Per Message Thread: 16LTOGRAPHITELTO GRAPHITE7K14K21K28K35KSE +/- 594.66, N = 3SE +/- 605.75, N = 3SE +/- 439.67, N = 3SE +/- 570.14, N = 3SE +/- 610.80, N = 3SE +/- 407.01, N = 3SE +/- 449.34, N = 6SE +/- 448.16, N = 531520321283240532523318083205332117326341. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 2LTO GRAPHITEGRAPHITELTO306090120150SE +/- 1.67, N = 3SE +/- 1.65, N = 6SE +/- 2.08, N = 3SE +/- 1.67, N = 3SE +/- 1.93, N = 4SE +/- 1.70, N = 41101131141161101121131141. (CC) gcc options: -O2 -lpthread

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelLTOLTO GRAPHITEGRAPHITE1020304050SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 325.7125.7125.7225.7342.9342.9442.9742.991. (CC) gcc options: -lm -lpthread -O3 -march=native -pipe -O2 -ftree-vectorize

Java SciMark

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

O2O3OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: CompositeGRAPHITELTOLTO GRAPHITE5001000150020002500SE +/- 26.17, N = 4SE +/- 23.90, N = 4SE +/- 27.36, N = 4SE +/- 4.59, N = 4SE +/- 26.00, N = 4SE +/- 31.58, N = 4SE +/- 27.43, N = 4SE +/- 26.78, N = 423102308229722242273226822502242

lzbench

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

O2O3OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: DecompressionGRAPHITELTOLTO GRAPHITE2004006008001000115511551155115011551155115511541. (CXX) g++ options: -lrt -static -lpthread

O2O3OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: CompressionGRAPHITELTOLTO GRAPHITE50100150200250SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 32482482482482482482482481. (CXX) g++ options: -lrt -static -lpthread

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 128MB - Thread Count: 16GRAPHITELTO GRAPHITELTO300K600K900K1200K1500KSE +/- 21930.96, N = 4SE +/- 14690.71, N = 3SE +/- 26025.10, N = 15SE +/- 22684.71, N = 15SE +/- 17982.37, N = 15SE +/- 26485.39, N = 15SE +/- 30751.89, N = 15SE +/- 36089.61, N = 15129998512943561241428123086412582761250589121152211913781. (CC) gcc options: -O2

lzbench

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

O3O2OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: DecompressionGRAPHITELTO GRAPHITELTO2004006008001000SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3113211311130113011311131113011271. (CXX) g++ options: -lrt -static -lpthread

O2O3OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: CompressionLTOGRAPHITELTO GRAPHITE100200300400500SE +/- 1.45, N = 3SE +/- 2.08, N = 3SE +/- 1.00, N = 3SE +/- 2.00, N = 3SE +/- 2.00, N = 3SE +/- 1.53, N = 34504494484474504504494481. (CXX) g++ options: -lrt -static -lpthread

Go Benchmarks

Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: buildLTO GRAPHITELTOGRAPHITE4000M8000M12000M16000M20000MSE +/- 36229303.38, N = 3SE +/- 49239319.31, N = 3SE +/- 46754005.24, N = 3SE +/- 21098888.19, N = 3SE +/- 17799366.27, N = 3SE +/- 76559453.96, N = 3SE +/- 47353765.29, N = 3SE +/- 22727615.08, N = 31658901095116629020672166496392861668716366416618970574166317122821663635479616677488403

lzbench

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

O2O3OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: DecompressionGRAPHITELTOLTO GRAPHITE130260390520650SE +/- 1.67, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 36186176166166186186176171. (CXX) g++ options: -lrt -static -lpthread

O3O2OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: CompressionLTO GRAPHITEGRAPHITELTO90180270360450SE +/- 5.17, N = 3SE +/- 4.37, N = 3SE +/- 5.33, N = 3SE +/- 5.36, N = 3SE +/- 4.84, N = 3SE +/- 4.91, N = 3SE +/- 5.67, N = 3SE +/- 3.51, N = 34194164154154174174174171. (CXX) g++ options: -lrt -static -lpthread

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 4LTO GRAPHITELTOGRAPHITE306090120150SE +/- 0.58, N = 3SE +/- 1.67, N = 6SE +/- 1.67, N = 3SE +/- 2.08, N = 3SE +/- 1.45, N = 3SE +/- 1.86, N = 3SE +/- 1.33, N = 3SE +/- 2.08, N = 31171181191211171191191201. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 6LTO GRAPHITELTOGRAPHITE306090120150SE +/- 2.08, N = 3SE +/- 1.81, N = 5SE +/- 1.97, N = 4SE +/- 1.53, N = 3SE +/- 2.00, N = 3SE +/- 2.03, N = 3SE +/- 2.03, N = 3SE +/- 1.53, N = 31191211221231191191221221. (CC) gcc options: -O2 -lpthread

Gzip Compression

This test measures the time needed to archive/compress two copies of the Linux 4.13 kernel source tree using Gzip compression. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterGzip CompressionLinux Source Tree Archiving To .tar.gzGRAPHITELTO GRAPHITELTO816243240SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 333.3333.6533.7233.8233.5933.6133.8633.95

LuaJIT

This test profile is a collection of Lua scripts/benchmarks run against a locally-built copy of LuaJIT upstream. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: CompositeGRAPHITELTOLTO GRAPHITE30060090012001500SE +/- 0.86, N = 3SE +/- 1.18, N = 3SE +/- 1.31, N = 3SE +/- 1.78, N = 3SE +/- 1.79, N = 3SE +/- 1.06, N = 3SE +/- 1.95, N = 3SE +/- 1.01, N = 3159515891575157315921576157415681. (CC) gcc options: -lm -ldl

Apache Siege

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

O3O2OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 100GRAPHITELTO GRAPHITELTO9K18K27K36K45KSE +/- 462.40, N = 9SE +/- 118.88, N = 3SE +/- 265.72, N = 3SE +/- 365.73, N = 3SE +/- 137.14, N = 3SE +/- 44.77, N = 3SE +/- 344.20, N = 3SE +/- 554.33, N = 441310394023904138006397203962538871385711. (CC) gcc options: -march=native -pipe -lpthread -ldl -lssl -lcrypto

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 32 - Workers Per Message Thread: 8GRAPHITELTOLTO GRAPHITE20K40K60K80K100KSE +/- 170.67, N = 3SE +/- 1115.88, N = 3SE +/- 1480.48, N = 3SE +/- 950.23, N = 3SE +/- 1353.17, N = 5SE +/- 1089.46, N = 3SE +/- 677.31, N = 3SE +/- 1373.31, N = 388107881928955790155887558887589728904111. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 6 - Workers Per Message Thread: 24LTO GRAPHITELTOGRAPHITE12K24K36K48K60KSE +/- 615.35, N = 3SE +/- 364.54, N = 3SE +/- 147.80, N = 3SE +/- 666.47, N = 3SE +/- 762.22, N = 5SE +/- 371.96, N = 3SE +/- 42.67, N = 354507557445578756256548915492555275560431. (CC) gcc options: -O2 -lpthread

Sunflow Rendering System

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

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image SynthesisLTO GRAPHITEGRAPHITELTO0.18230.36460.54690.72920.9115SE +/- 0.01, N = 3SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.00, N = 3SE +/- 0.01, N = 15SE +/- 0.01, N = 15SE +/- 0.01, N = 150.760.780.800.800.770.780.800.81

CppPerformanceBenchmarks

CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov AbstractionLTO GRAPHITELTOGRAPHITE816243240SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 332.3832.3932.4532.4532.3832.3932.4232.451. (CXX) g++ options: -march=native -pipe -std=c++11 -O3

NAMD CUDA

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. This version of the NAMD test profile uses CUDA GPU acceleration. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD CUDA 2.13ATPase Simulation - 327,506 AtomsLTOGRAPHITELTO GRAPHITE0.07640.15280.22920.30560.382SE +/- 0.00063, N = 3SE +/- 0.00152, N = 3SE +/- 0.00066, N = 3SE +/- 0.00090, N = 3SE +/- 0.00054, N = 3SE +/- 0.00081, N = 3SE +/- 0.00077, N = 3SE +/- 0.00077, N = 30.338080.338720.339050.339250.338200.338890.338930.33944

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 6 - Workers Per Message Thread: 4GRAPHITELTOLTO GRAPHITE306090120150SE +/- 1.15, N = 3SE +/- 1.00, N = 3SE +/- 1.53, N = 3SE +/- 0.88, N = 3SE +/- 1.91, N = 4SE +/- 0.67, N = 31101111131141111121141161. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 6 - Workers Per Message Thread: 6LTO GRAPHITEGRAPHITELTO306090120150SE +/- 1.67, N = 3SE +/- 1.45, N = 3SE +/- 1.53, N = 3SE +/- 1.20, N = 3SE +/- 1.45, N = 3SE +/- 1.45, N = 31131151161171141161171181. (CC) gcc options: -O2 -lpthread

Node.js Octane Benchmark

A Node.js version of the JavaScript Octane Benchmark. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgScore, More Is BetterNode.js Octane BenchmarkGRAPHITELTO GRAPHITELTO11K22K33K44K55KSE +/- 74.70, N = 3SE +/- 51.85, N = 3SE +/- 100.73, N = 3SE +/- 131.34, N = 3SE +/- 214.29, N = 3SE +/- 5.78, N = 3SE +/- 119.65, N = 3SE +/- 55.11, N = 351363513465134551217510805100950954506961. Nodejs

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: BT.ALTOLTO GRAPHITEGRAPHITE12002400360048006000SE +/- 17.41, N = 3SE +/- 20.73, N = 3SE +/- 20.16, N = 3SE +/- 28.65, N = 3SE +/- 12.26, N = 3SE +/- 7.36, N = 3SE +/- 41.72, N = 3SE +/- 10.93, N = 3563155445492544956265548553054301. 3.3

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.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: CPU-OnlyLTOGRAPHITELTO GRAPHITE2040608010090.2490.4890.6090.6790.4190.4690.4990.73

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 32 - Workers Per Message Thread: 16LTOLTO GRAPHITEGRAPHITE40K80K120K160K200KSE +/- 743.92, N = 3SE +/- 950.23, N = 3SE +/- 1806.17, N = 3SE +/- 782.09, N = 3SE +/- 853.33, N = 3SE +/- 1288.51, N = 3SE +/- 1458.18, N = 3SE +/- 512.00, N = 31680211690451695571733121685331692161693871697281. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 32 - Workers Per Message Thread: 24LTO GRAPHITELTOGRAPHITE50K100K150K200K250KSE +/- 2048.00, N = 3SE +/- 2960.96, N = 3SE +/- 615.35, N = 3SE +/- 1487.84, N = 3SE +/- 1923.32, N = 3SE +/- 1645.85, N = 3SE +/- 3426.11, N = 3SE +/- 3105.01, N = 32178562180272190512228052195632199042216112236591. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 32 - Workers Per Message Thread: 4LTOGRAPHITELTO GRAPHITE8K16K24K32K40KSE +/- 364.54, N = 3SE +/- 307.67, N = 3SE +/- 112.89, N = 3SE +/- 279.78, N = 3SE +/- 128.00, N = 3SE +/- 128.00, N = 337141372273782437867377813782437952379521. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 32 - Workers Per Message Thread: 6LTO GRAPHITELTOGRAPHITE11K22K33K44K55KSE +/- 492.06, N = 3SE +/- 266.45, N = 3SE +/- 670.56, N = 3SE +/- 195.52, N = 3SE +/- 364.54, N = 3SE +/- 259.53, N = 3SE +/- 322.13, N = 3SE +/- 407.01, N = 351435515205160551648516055160552032520751. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 8LTOGRAPHITELTO GRAPHITE9K18K27K36K45KSE +/- 85.33, N = 3SE +/- 112.89, N = 3SE +/- 195.52, N = 3SE +/- 586.57, N = 3SE +/- 225.77, N = 3SE +/- 298.67, N = 3SE +/- 279.78, N = 3SE +/- 259.53, N = 339531399574012840256397874008540469405971. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 2LTOGRAPHITELTO GRAPHITE20406080100SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.58, N = 31021041051061041041051051. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 4LTOGRAPHITELTO GRAPHITE306090120150SE +/- 1.00, N = 3SE +/- 1.15, N = 3SE +/- 1.00, N = 3SE +/- 1.67, N = 3SE +/- 1.76, N = 3SE +/- 2.19, N = 3SE +/- 1.00, N = 31091101111121091091101111. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 2LTO GRAPHITEGRAPHITELTO20406080100SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 2.00, N = 3SE +/- 1.20, N = 31051051061091061061071081. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 24LTOGRAPHITELTO GRAPHITE30K60K90K120K150KSE +/- 1038.12, N = 3SE +/- 1396.97, N = 3SE +/- 615.35, N = 3SE +/- 1806.17, N = 3SE +/- 1487.84, N = 3SE +/- 1230.69, N = 3SE +/- 1536.00, N = 31347411362771369601373011361071376431376431384961. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 16LTOLTO GRAPHITEGRAPHITE20K40K60K80K100KSE +/- 853.33, N = 3SE +/- 225.77, N = 3SE +/- 559.57, N = 3SE +/- 743.92, N = 3SE +/- 903.08, N = 3SE +/- 938.67, N = 3SE +/- 1194.67, N = 3SE +/- 426.67, N = 394421949339553196981944219527596811969811. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 6 - Workers Per Message Thread: 8LTOGRAPHITELTO GRAPHITE3K6K9K12K15KSE +/- 28.22, N = 3SE +/- 69.95, N = 3SE +/- 128.00, N = 3SE +/- 118.78, N = 3SE +/- 87.31, N = 3SE +/- 73.90, N = 3SE +/- 102.87, N = 3SE +/- 21.33, N = 312507126351265612667126351265612688127731. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 8LTOLTO GRAPHITEGRAPHITE306090120150SE +/- 2.19, N = 3SE +/- 2.08, N = 3SE +/- 1.76, N = 3SE +/- 2.08, N = 3SE +/- 1.00, N = 3SE +/- 2.00, N = 3SE +/- 2.33, N = 31201231241271211231251261. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 32LTOLTO GRAPHITEGRAPHITE40K80K120K160K200KSE +/- 1230.69, N = 3SE +/- 2076.25, N = 3SE +/- 615.35, N = 3SE +/- 886.81, N = 3SE +/- 170.67, N = 3SE +/- 2407.55, N = 3SE +/- 2048.00, N = 3SE +/- 2131.63, N = 31709231714351734831738241719471721171722881728001. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 24GRAPHITELTO GRAPHITELTO7K14K21K28K35KSE +/- 348.75, N = 3SE +/- 364.54, N = 3SE +/- 213.33, N = 3SE +/- 307.67, N = 3SE +/- 459.66, N = 3SE +/- 625.71, N = 3SE +/- 42.67, N = 3SE +/- 237.56, N = 333077332593351533813332483324833429336431. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 16LTOLTO GRAPHITEGRAPHITE10K20K30K40K50KSE +/- 349.24, N = 3SE +/- 73.90, N = 3SE +/- 225.77, N = 3SE +/- 407.01, N = 3SE +/- 592.74, N = 3SE +/- 298.67, N = 3SE +/- 449.52, N = 344011443524460844779443954443744907455041. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 16LTO GRAPHITEGRAPHITELTO4080120160200SE +/- 0.58, N = 3SE +/- 1.45, N = 3SE +/- 0.88, N = 3SE +/- 2.85, N = 3SE +/- 0.88, N = 3SE +/- 0.88, N = 3SE +/- 1.45, N = 31481511521601481491501511. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 32LTOLTO GRAPHITEGRAPHITE20K40K60K80K100KSE +/- 961.66, N = 3SE +/- 903.08, N = 3SE +/- 1239.54, N = 3SE +/- 758.46, N = 3SE +/- 256.00, N = 3SE +/- 890.91, N = 3SE +/- 341.33, N = 3980059868899371100053982619894499115992851. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 24GRAPHITELTO GRAPHITELTO16K32K48K64K80KSE +/- 1065.81, N = 3SE +/- 519.06, N = 3SE +/- 341.33, N = 3SE +/- 814.03, N = 3SE +/- 644.25, N = 3SE +/- 371.96, N = 3SE +/- 443.41, N = 3SE +/- 1048.59, N = 374624749657556375733753927547775648757331. (CC) gcc options: -O2 -lpthread

O2O3OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 4 - Workers Per Message Thread: 32GRAPHITELTO GRAPHITELTO11K22K33K44K55KSE +/- 601.89, N = 3SE +/- 338.66, N = 3SE +/- 492.06, N = 3SE +/- 153.84, N = 3SE +/- 85.33, N = 3SE +/- 298.67, N = 3SE +/- 256.00, N = 3SE +/- 619.77, N = 348491489604900349771487894891748960505391. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 6 - Workers Per Message Thread: 32LTO GRAPHITELTOGRAPHITE20K40K60K80K100KSE +/- 451.54, N = 3SE +/- 532.91, N = 3SE +/- 698.48, N = 3SE +/- 391.05, N = 3SE +/- 1257.04, N = 3SE +/- 1230.69, N = 3SE +/- 1257.04, N = 3SE +/- 256.00, N = 375477761607633177440754777556376587779521. (CC) gcc options: -O2 -lpthread

O3O2OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 2 - Workers Per Message Thread: 24LTOGRAPHITELTO GRAPHITE3K6K9K12K15KSE +/- 10.67, N = 3SE +/- 10.67, N = 3SE +/- 10.67, N = 3SE +/- 10.67, N = 3SE +/- 10.67, N = 3SE +/- 42.67, N = 3SE +/- 174.62, N = 3SE +/- 245.33, N = 313019130191301913029130191305113275132851. (CC) gcc options: -O2 -lpthread

SciMark

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

O3O2OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeGRAPHITELTOLTO GRAPHITE6001200180024003000SE +/- 1.89, N = 3SE +/- 1.24, N = 3SE +/- 1.19, N = 3SE +/- 1.04, N = 3SE +/- 4.91, N = 3SE +/- 2.70, N = 3SE +/- 3.27, N = 3SE +/- 1.23, N = 3261225152308170323872386235419631. (CC) gcc options: -march=native -pipe -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 256MB - Thread Count: 8GRAPHITELTOLTO GRAPHITE300K600K900K1200K1500KSE +/- 5273.10, N = 3SE +/- 14761.95, N = 3SE +/- 14264.61, N = 15SE +/- 23910.80, N = 15SE +/- 18776.70, N = 7SE +/- 8402.42, N = 3SE +/- 15121.50, N = 3SE +/- 24802.99, N = 15152233614600251435245139651314902691461562144460814177871. (CC) gcc options: -O2

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 8GB - Disk Test: Read PerformanceGRAPHITELTO GRAPHITELTO10002000300040005000SE +/- 75.24, N = 3SE +/- 78.39, N = 4SE +/- 76.69, N = 4SE +/- 5.01, N = 3SE +/- 76.07, N = 4SE +/- 7.01, N = 3SE +/- 44.75, N = 15SE +/- 8.55, N = 3465845584418436644954477441743291. (CC) gcc options: -O3

AOBench

AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeGRAPHITELTOLTO GRAPHITE714212835SE +/- 0.12, N = 3SE +/- 0.37, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 326.9427.1827.2927.3028.2028.2228.3128.321. (CC) gcc options: -lm -O3 -march=native -pipe -O2 -ftree-vectorize

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.

O2O3OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesGRAPHITELTOLTO GRAPHITE30060090012001500SE +/- 1.15, N = 3SE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 2.03, N = 3SE +/- 0.67, N = 3SE +/- 1.00, N = 312051208121012121208120812151226

Apache Benchmark

This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingLTO GRAPHITELTOGRAPHITE8K16K24K32K40KSE +/- 149.61, N = 3SE +/- 91.18, N = 3SE +/- 35.61, N = 3SE +/- 76.05, N = 3SE +/- 53.26, N = 3SE +/- 44.34, N = 3SE +/- 74.05, N = 3SE +/- 46.17, N = 338755385413838638189386283842338201381401. (CC) gcc options: -shared -fPIC -pthread -march=native

Java Gradle Build

This test runs Java software project builds using the Gradle build system. It is intended to give developers an idea as to the build performance for development activities and build servers. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterJava Gradle Build 1.0Gradle Build: ReactorLTOLTO GRAPHITEGRAPHITE510152025SE +/- 0.04, N = 4SE +/- 0.05, N = 4SE +/- 0.05, N = 4SE +/- 0.02, N = 4SE +/- 0.04, N = 4SE +/- 0.04, N = 4SE +/- 0.03, N = 4SE +/- 0.03, N = 419.6319.6719.6919.7119.6619.6819.7019.73

eSpeak Speech Engine

This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak Speech Engine 1.48.04Text-To-Speech SynthesisLTOLTO GRAPHITEGRAPHITE612182430SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.25, N = 3SE +/- 0.23, N = 3SE +/- 0.22, N = 3SE +/- 0.20, N = 3SE +/- 0.20, N = 3SE +/- 0.26, N = 325.3525.6125.6825.7525.6825.6925.7025.811. (CXX) g++ options: -lstdc++

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 64MB - Thread Count: 16GRAPHITELTOLTO GRAPHITE140K280K420K560K700KSE +/- 11753.75, N = 15SE +/- 12258.57, N = 15SE +/- 12846.91, N = 15SE +/- 16476.15, N = 15SE +/- 10224.24, N = 15SE +/- 12516.07, N = 15SE +/- 11524.05, N = 15SE +/- 11328.85, N = 156512786363606350456232686449036391696382226314161. (CC) gcc options: -O2

Sockperf

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

O3O2OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under LoadGRAPHITELTO GRAPHITELTO714212835SE +/- 1.22, N = 20SE +/- 0.30, N = 5SE +/- 0.22, N = 5SE +/- 0.37, N = 7SE +/- 0.85, N = 20SE +/- 0.20, N = 5SE +/- 0.22, N = 5SE +/- 0.43, N = 526.8927.9028.1328.8527.1428.2128.5128.741. (CXX) g++ options: --param -march=native -pipe -rdynamic -ldl -lpthread

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.

O2O3OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: EclipseLTOGRAPHITELTO GRAPHITE4K8K12K16K20KSE +/- 36.12, N = 4SE +/- 53.73, N = 4SE +/- 59.66, N = 4SE +/- 40.31, N = 4SE +/- 26.40, N = 4SE +/- 52.12, N = 4SE +/- 17.58, N = 4SE +/- 59.57, N = 41641616434165101655616501165851658816667

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenCL LBMLTO GRAPHITEGRAPHITELTO510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 322.0622.0722.0822.0822.0822.0922.1022.101. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 256MB - Thread Count: 32LTO GRAPHITEGRAPHITELTO15K30K45K60K75KSE +/- 76.10, N = 3SE +/- 205.11, N = 3SE +/- 81.64, N = 3SE +/- 154.89, N = 3SE +/- 123.76, N = 3SE +/- 143.72, N = 3SE +/- 134.02, N = 3SE +/- 80.05, N = 371577713917130271296713357127071213709631. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 256MB - Thread Count: 32LTO GRAPHITEGRAPHITELTO30K60K90K120K150KSE +/- 264.56, N = 3SE +/- 449.68, N = 3SE +/- 757.15, N = 3SE +/- 902.54, N = 3SE +/- 303.53, N = 3SE +/- 413.24, N = 3SE +/- 627.93, N = 3SE +/- 122.13, N = 31380421377301376891372281377321373131371831368081. (CC) gcc options: -O2

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ThreadLTOLTO GRAPHITEGRAPHITE612182430SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.16, N = 3SE +/- 0.24, N = 3SE +/- 0.17, N = 3SE +/- 0.21, N = 3SE +/- 0.31, N = 323.3923.6023.6323.9023.4823.6523.6623.971. (CC) gcc options: -lpthread -march=native -pipe

Stream

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

O3O2OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: CopyGRAPHITELTO GRAPHITELTO16K32K48K64K80KSE +/- 22.04, N = 5SE +/- 11.76, N = 5SE +/- 33.32, N = 5SE +/- 22.42, N = 5SE +/- 31.05, N = 5SE +/- 58.51, N = 5SE +/- 36.79, N = 5SE +/- 25.15, N = 574790747557472074720747697474374693745571. (CC) gcc options: -march=native -pipe -O3 -fopenmp

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 256MB - Thread Count: 32GRAPHITELTO GRAPHITELTO80160240320400SE +/- 1.12, N = 3SE +/- 2.30, N = 3SE +/- 1.40, N = 3SE +/- 3.87, N = 3SE +/- 1.80, N = 3SE +/- 6.19, N = 3SE +/- 0.59, N = 3SE +/- 3.06, N = 33903903833803903863853841. (CC) gcc options: -O2

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ProcessLTO GRAPHITEGRAPHITELTO510152025SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.03, N = 3SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.15, N = 322.5322.6622.7422.7822.7322.7422.8422.861. (CC) gcc options: -lpthread -march=native -pipe -O2 -ftree-vectorize

TTSIOD 3D Renderer

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

O2O3OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingGRAPHITELTOLTO GRAPHITE2004006008001000SE +/- 1.62, N = 3SE +/- 6.07, N = 3SE +/- 1.61, N = 3SE +/- 6.23, N = 3SE +/- 3.44, N = 3SE +/- 1.25, N = 3SE +/- 6.40, N = 3SE +/- 9.50, N = 38608568568498037937937891. (CXX) g++ options: -march=native -pipe -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lpthread -fopenmp -fwhole-program -lstdc++

Go Benchmarks

Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: httpGRAPHITELTO GRAPHITELTO8001600240032004000SE +/- 19.46, N = 3SE +/- 29.02, N = 3SE +/- 1.45, N = 3SE +/- 13.61, N = 3SE +/- 5.61, N = 3SE +/- 25.13, N = 3SE +/- 18.36, N = 3SE +/- 13.05, N = 335393561357335803544356635833608

Cython benchmark

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCython benchmark 0.27GRAPHITELTOLTO GRAPHITE510152025SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 322.3022.3322.3322.6522.5522.5922.6022.71

Crafty

This is a performance test of Crafty, an advanced open-source chess engine. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed TimeLTO GRAPHITELTOGRAPHITE2M4M6M8M10MSE +/- 11858.51, N = 3SE +/- 9502.97, N = 3SE +/- 11085.94, N = 3SE +/- 6818.47, N = 3SE +/- 21898.78, N = 3SE +/- 8579.23, N = 3SE +/- 7504.06, N = 3SE +/- 11653.10, N = 3884880288326938823265881631788294038817639881684888161711. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

Botan

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

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: AES-256 - DecryptLTOLTO GRAPHITEGRAPHITE8001600240032004000SE +/- 2.83, N = 3SE +/- 4.34, N = 3SE +/- 7.03, N = 3SE +/- 2.53, N = 3SE +/- 1.27, N = 3SE +/- 1.71, N = 3SE +/- 3.75, N = 3SE +/- 2.87, N = 3389138823881387938703846384638441. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: AES-256 - EncryptLTO GRAPHITEGRAPHITELTO8001600240032004000SE +/- 1.47, N = 3SE +/- 1.54, N = 3SE +/- 1.42, N = 3SE +/- 1.22, N = 3SE +/- 0.41, N = 3SE +/- 3.02, N = 3SE +/- 4.46, N = 3SE +/- 0.68, N = 3386938643862385938553854384738391. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: SP.ALTOGRAPHITELTO GRAPHITE9001800270036004500SE +/- 46.73, N = 3SE +/- 22.51, N = 3SE +/- 24.81, N = 3SE +/- 22.50, N = 3SE +/- 40.41, N = 3SE +/- 20.07, N = 3SE +/- 8.41, N = 3SE +/- 38.26, N = 3399039663935393039773964393939371. 3.3

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.

O2O3OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinGRAPHITELTOLTO GRAPHITE1020304050SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.21, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 344.6544.6844.7044.9044.6744.6844.6844.92

O3O2OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cosLTO GRAPHITELTOGRAPHITE1020304050SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 345.2245.2245.2345.2345.2245.2345.2345.32

Botan

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

O3O2OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Twofish - DecryptLTOGRAPHITELTO GRAPHITE90180270360450SE +/- 0.06, N = 3SE +/- 0.20, N = 3SE +/- 0.01, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 33993973973963983983983981. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Twofish - EncryptGRAPHITELTOLTO GRAPHITE90180270360450SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 34014014014014014014014011. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Blowfish - DecryptGRAPHITELTOLTO GRAPHITE60120180240300SE +/- 0.19, N = 3SE +/- 0.06, N = 3SE +/- 0.21, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.35, N = 3SE +/- 0.01, N = 32952952952952952952952951. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: Blowfish - EncryptGRAPHITELTOLTO GRAPHITE60120180240300SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 32962962962962962962962961. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 4096LTO GRAPHITEGRAPHITELTO2K4K6K8K10KSE +/- 242.50, N = 15SE +/- 195.10, N = 15SE +/- 166.28, N = 3SE +/- 260.33, N = 15SE +/- 90.42, N = 3SE +/- 244.22, N = 15SE +/- 270.70, N = 15SE +/- 253.60, N = 151067210584100709866106421041810225101701. (CC) gcc options: -pthread -march=native -pipe -lm

Botan

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

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: CAST-256 - DecryptLTOLTO GRAPHITEGRAPHITE306090120150SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.60, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 31461461461451461461461461. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: CAST-256 - EncryptGRAPHITELTOLTO GRAPHITE306090120150SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 31461461451451461461461461. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: KASUMI - DecryptLTO GRAPHITEGRAPHITELTO20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 395.4395.4395.4295.3395.4295.4295.3995.381. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

O2O3OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.8.0Test: KASUMI - EncryptLTO GRAPHITEGRAPHITELTO20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 396.5496.5396.5096.4996.5296.5296.5296.521. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenSSL

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

O3O2OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceGRAPHITELTOLTO GRAPHITE13002600390052006500SE +/- 1.62, N = 3SE +/- 9.05, N = 3SE +/- 6.80, N = 3SE +/- 0.99, N = 3SE +/- 7.57, N = 3SE +/- 2.74, N = 3SE +/- 9.33, N = 3SE +/- 7.41, N = 3608060676056605460756068606160521. (CC) gcc options: -pthread -m64 -march=native -pipe -lssl -lcrypto -ldl

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Double-Precision DoubleGRAPHITELTOLTO GRAPHITE306090120150SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 31441441441441441441441441. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lOpenCL

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 128MB - Thread Count: 32GRAPHITELTOLTO GRAPHITE400K800K1200K1600K2000KSE +/- 6294.27, N = 3SE +/- 15081.27, N = 3SE +/- 11761.89, N = 3SE +/- 27135.03, N = 4SE +/- 7641.91, N = 3SE +/- 14392.39, N = 3SE +/- 27774.86, N = 3SE +/- 20329.70, N = 15163648516280431626213161543716205391618376160367315773521. (CC) gcc options: -O2

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileLTO GRAPHITELTOGRAPHITE5001000150020002500SE +/- 0.00, N = 3SE +/- 2.79, N = 3SE +/- 4.84, N = 3SE +/- 29.99, N = 3SE +/- 11.18, N = 3SE +/- 12.62, N = 3SE +/- 2.80, N = 3SE +/- 9.68, N = 324062395238923762403239723832381

Memcached mcperf

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

O2O3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: SetGRAPHITELTO GRAPHITELTO16K32K48K64K80KSE +/- 271.78, N = 3SE +/- 382.34, N = 3SE +/- 234.87, N = 3SE +/- 202.88, N = 3SE +/- 189.27, N = 3SE +/- 501.40, N = 3SE +/- 417.62, N = 3SE +/- 267.06, N = 376973763377612376110764487643176206755291. (CC) gcc options: -march=native -pipe -lm -rdynamic

O3O2OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: AddLTOLTO GRAPHITEGRAPHITE16K32K48K64K80KSE +/- 270.14, N = 3SE +/- 809.20, N = 3SE +/- 339.42, N = 3SE +/- 28.57, N = 3SE +/- 145.84, N = 3SE +/- 187.94, N = 3SE +/- 347.01, N = 3SE +/- 198.78, N = 376962769157592975844768357681276179758441. (CC) gcc options: -march=native -pipe -lm -rdynamic

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 128MB - Thread Count: 8LTO GRAPHITELTOGRAPHITE160K320K480K640K800KSE +/- 10934.32, N = 3SE +/- 10287.78, N = 15SE +/- 12591.18, N = 4SE +/- 12413.45, N = 15SE +/- 6191.70, N = 3SE +/- 10320.72, N = 15SE +/- 9543.92, N = 15SE +/- 14248.28, N = 37545547467607398817248277444697391217381837188261. (CC) gcc options: -O2

Memcached mcperf

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

O2O3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: AppendGRAPHITELTO GRAPHITELTO20K40K60K80K100KSE +/- 197.87, N = 3SE +/- 1047.00, N = 3SE +/- 406.38, N = 3SE +/- 481.97, N = 3SE +/- 300.12, N = 3SE +/- 248.84, N = 3SE +/- 152.54, N = 3SE +/- 180.97, N = 379119789507845377213787787875078707777821. (CC) gcc options: -march=native -pipe -lm -rdynamic

O2O3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: PrependLTO GRAPHITELTOGRAPHITE20K40K60K80K100KSE +/- 604.44, N = 3SE +/- 737.81, N = 3SE +/- 730.29, N = 3SE +/- 477.37, N = 3SE +/- 97.01, N = 3SE +/- 671.62, N = 3SE +/- 417.94, N = 3SE +/- 283.44, N = 379528788737844978372793497902378756785491. (CC) gcc options: -march=native -pipe -lm -rdynamic

O2O3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: ReplaceLTO GRAPHITEGRAPHITELTO20K40K60K80K100KSE +/- 563.61, N = 3SE +/- 642.36, N = 3SE +/- 287.02, N = 3SE +/- 212.11, N = 3SE +/- 385.17, N = 3SE +/- 258.88, N = 3SE +/- 249.10, N = 3SE +/- 297.20, N = 380017793527893578645793807898078940781141. (CC) gcc options: -march=native -pipe -lm -rdynamic

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ProcessLTOLTO GRAPHITEGRAPHITE3691215SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.22, N = 1512.1812.2012.2212.2212.2112.2712.3012.481. (CC) gcc options: -lpthread -march=native -pipe -O2 -ftree-vectorize

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 64MB - Thread Count: 32LTOGRAPHITELTO GRAPHITE200K400K600K800K1000KSE +/- 10849.39, N = 3SE +/- 8610.55, N = 3SE +/- 9767.94, N = 15SE +/- 11379.65, N = 15SE +/- 11576.21, N = 3SE +/- 8941.82, N = 9SE +/- 8131.18, N = 15SE +/- 2639.63, N = 38214548175308084527935558141088022537981777980431. (CC) gcc options: -O2

RAMspeed SMP

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

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating PointGRAPHITELTOLTO GRAPHITE7K14K21K28K35K34029330993277832745335923356033462328821. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating PointGRAPHITELTOLTO GRAPHITE7K14K21K28K35K32296316433157531360320303196331879314621. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating PointGRAPHITELTOLTO GRAPHITE7K14K21K28K35K31808311103090730817315593154631206309991. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating PointGRAPHITELTOLTO GRAPHITE7K14K21K28K35K32423317003145831414321633207631951315211. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating PointGRAPHITELTOLTO GRAPHITE7K14K21K28K35K31640309323074230677313483131931066307961. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerGRAPHITELTOLTO GRAPHITE7K14K21K28K35K33888331143308432854336873359233575328831. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerGRAPHITELTOLTO GRAPHITE7K14K21K28K35K32591318223159331570322903220032059316601. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: IntegerGRAPHITELTOLTO GRAPHITE7K14K21K28K35K31189306163041830267310263095230762304621. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerGRAPHITELTOLTO GRAPHITE7K14K21K28K35K32531317613150031477322063211931992316121. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerGRAPHITELTO GRAPHITELTO7K14K21K28K35K32164314753118931140320913189531358313401. (CC) gcc options: -O3 -march=native -pipe

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 256MB - Thread Count: 4GRAPHITELTOLTO GRAPHITE200K400K600K800K1000KSE +/- 7388.33, N = 3SE +/- 7801.18, N = 3SE +/- 4500.72, N = 3SE +/- 15609.75, N = 15SE +/- 15504.31, N = 3SE +/- 8295.96, N = 11SE +/- 7777.06, N = 12SE +/- 14259.77, N = 38360488032908027687710408208737935037777197400821. (CC) gcc options: -O2

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 1024GRAPHITELTO GRAPHITELTO5K10K15K20K25KSE +/- 226.59, N = 3SE +/- 43.68, N = 3SE +/- 280.15, N = 3SE +/- 400.40, N = 3SE +/- 33.41, N = 3SE +/- 74.75, N = 3SE +/- 155.11, N = 3SE +/- 338.06, N = 324696244902433224162246542446823967239331. (CC) gcc options: -pthread -march=native -pipe -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 128MB - Thread Count: 16GRAPHITELTOLTO GRAPHITE12K24K36K48K60KSE +/- 135.97, N = 3SE +/- 19.43, N = 3SE +/- 81.84, N = 3SE +/- 367.36, N = 3SE +/- 200.09, N = 3SE +/- 103.19, N = 3SE +/- 1271.52, N = 15SE +/- 1777.12, N = 1558167579845795057614580855782556185531441. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 64MB - Thread Count: 16GRAPHITELTOLTO GRAPHITE12K24K36K48K60KSE +/- 83.63, N = 3SE +/- 154.78, N = 3SE +/- 234.51, N = 3SE +/- 1453.76, N = 15SE +/- 1124.24, N = 12SE +/- 1623.64, N = 15SE +/- 1580.42, N = 15SE +/- 1574.63, N = 1556985566195610853677552335289252890526431. (CC) gcc options: -O2

XZ Compression

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9LTO GRAPHITELTOGRAPHITE48121620SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 316.7216.8217.0217.1616.8316.9116.9617.051. (CC) gcc options: -pthread -fvisibility=hidden -march=native -pipe

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 32MB - Thread Count: 16GRAPHITELTO GRAPHITELTO70K140K210K280K350KSE +/- 5093.99, N = 15SE +/- 12738.48, N = 12SE +/- 5089.98, N = 15SE +/- 6744.06, N = 15SE +/- 7607.10, N = 15SE +/- 7551.52, N = 15SE +/- 6970.34, N = 15SE +/- 7389.89, N = 153411063390633344583204113367703319403281133158501. (CC) gcc options: -O2

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2048LTOGRAPHITELTO GRAPHITE2K4K6K8K10KSE +/- 162.08, N = 3SE +/- 14.47, N = 3SE +/- 235.96, N = 15SE +/- 390.04, N = 12SE +/- 245.30, N = 15SE +/- 203.40, N = 15SE +/- 281.26, N = 15SE +/- 278.07, N = 151128410837102089326100939960988194861. (CC) gcc options: -pthread -march=native -pipe -lm

t-test1

This is a test of t-test1 for basic memory allocator benchmarks. Note this test profile is currently very basic and the overall time does include the warmup time of the custom t-test1 compilation. Improvements welcome. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1LTOGRAPHITELTO GRAPHITE48121620SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.18, N = 315.4215.4415.4715.7315.4315.5215.7816.301. (CC) gcc options: -pthread -march=native -pipe

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ThreadGRAPHITELTOLTO GRAPHITE48121620SE +/- 0.16, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 315.4415.5215.7515.7615.5115.5115.5415.631. (CC) gcc options: -lpthread -march=native -pipe

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 64MB - Thread Count: 8GRAPHITELTO GRAPHITELTO80K160K240K320K400KSE +/- 7177.12, N = 3SE +/- 8294.11, N = 15SE +/- 3838.15, N = 11SE +/- 6150.11, N = 15SE +/- 5195.20, N = 3SE +/- 5494.13, N = 15SE +/- 6425.45, N = 15SE +/- 8701.27, N = 153909043800263793493793223871373780033712203654361. (CC) gcc options: -O2

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 256MB - Thread Count: 16LTO GRAPHITELTOGRAPHITE30K60K90K120K150KSE +/- 845.01, N = 3SE +/- 641.02, N = 3SE +/- 590.79, N = 3SE +/- 437.24, N = 3SE +/- 643.71, N = 3SE +/- 331.84, N = 3SE +/- 937.15, N = 3SE +/- 442.37, N = 31395961388241384191383201384581384491380181379451. (CC) gcc options: -O2

FLAC Audio Encoding

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACLTO GRAPHITELTOGRAPHITE3691215SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 59.139.159.189.209.169.179.179.251. (CXX) g++ options: -march=native -pipe -fvisibility=hidden -logg -lm

Memcached mcperf

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

O3O2OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: DeleteLTO GRAPHITELTOGRAPHITE20K40K60K80K100KSE +/- 214.88, N = 3SE +/- 479.41, N = 3SE +/- 266.31, N = 3SE +/- 1059.73, N = 3SE +/- 273.03, N = 3SE +/- 357.66, N = 3SE +/- 785.71, N = 3SE +/- 314.11, N = 31149121142171138361107071122971122351120241110691. (CC) gcc options: -march=native -pipe -lm -rdynamic

O2O3OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: GetLTO GRAPHITELTOGRAPHITE20K40K60K80K100KSE +/- 233.79, N = 3SE +/- 328.44, N = 3SE +/- 895.94, N = 3SE +/- 756.08, N = 3SE +/- 1243.20, N = 3SE +/- 176.25, N = 3SE +/- 710.69, N = 3SE +/- 696.74, N = 31138601129401119601117981138241135281131171123971. (CC) gcc options: -march=native -pipe -lm -rdynamic

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 8GB - Disk Test: Read PerformanceGRAPHITELTOLTO GRAPHITE16003200480064008000SE +/- 1.50, N = 3SE +/- 3.89, N = 3SE +/- 14.47, N = 3SE +/- 8.52, N = 3SE +/- 12.53, N = 3SE +/- 99.36, N = 3SE +/- 8.97, N = 3SE +/- 2.65, N = 3727572466889686171746961694569071. (CC) gcc options: -O3

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 256MB - Thread Count: 16LTOLTO GRAPHITEGRAPHITE70140210280350SE +/- 1.21, N = 3SE +/- 5.69, N = 3SE +/- 2.43, N = 3SE +/- 5.12, N = 3SE +/- 2.28, N = 3SE +/- 3.14, N = 3SE +/- 1.98, N = 3SE +/- 0.54, N = 33193073053043113093083071. (CC) gcc options: -O2

Apache Siege

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

O2O3OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 50LTO GRAPHITELTOGRAPHITE7K14K21K28K35KSE +/- 148.69, N = 3SE +/- 314.91, N = 3SE +/- 309.42, N = 3SE +/- 479.40, N = 3SE +/- 245.85, N = 3SE +/- 386.76, N = 3SE +/- 151.94, N = 3SE +/- 212.62, N = 334820348083464834354343363432633816337941. (CC) gcc options: -march=native -pipe -O3 -lpthread -ldl -lssl -lcrypto

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 8GB - Disk Test: Read PerformanceLTOGRAPHITELTO GRAPHITE16003200480064008000SE +/- 49.79, N = 3SE +/- 29.20, N = 3SE +/- 22.91, N = 3SE +/- 11.76, N = 3SE +/- 21.38, N = 3SE +/- 34.52, N = 3SE +/- 30.82, N = 3SE +/- 49.45, N = 3767276157474742576487518751274971. (CC) gcc options: -O3

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 ThreadsLTO GRAPHITEGRAPHITELTO30060090012001500SE +/- 3.01, N = 3SE +/- 4.89, N = 3SE +/- 1.39, N = 3SE +/- 5.66, N = 3SE +/- 5.00, N = 3SE +/- 9.40, N = 2SE +/- 12.20, N = 3SE +/- 5.79, N = 3156315331527152615461519151515131. (CC) gcc options: -static

Timed ImageMagick Compilation

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

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileLTO GRAPHITELTOGRAPHITE48121620SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 310.5510.5515.3815.5813.0313.1317.0317.22

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 8GB - Disk Test: Write PerformanceLTOGRAPHITELTO GRAPHITE2004006008001000SE +/- 1.29, N = 3SE +/- 0.14, N = 3SE +/- 5.06, N = 3SE +/- 2.60, N = 3SE +/- 4.38, N = 3SE +/- 3.13, N = 3SE +/- 6.26, N = 3SE +/- 13.33, N = 3112211021093107311071104108810831. (CC) gcc options: -O3

Xsbench

XSBench is a mini-app representing a key computational kernel of the Monte Carlo neutronics application OpenMC. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgLookups/s, More Is BetterXsbench 2017-07-06LTO GRAPHITEGRAPHITELTO1.3M2.6M3.9M5.2M6.5MSE +/- 2087.75, N = 3SE +/- 4253.63, N = 3SE +/- 3099.86, N = 3SE +/- 2732.01, N = 3SE +/- 2711.20, N = 3SE +/- 4067.06, N = 3SE +/- 31414.50, N = 3SE +/- 13313.57, N = 3605318960495176044151603046260416056029005602571060232671. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm

Sockperf

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

O2O3OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: ThroughputGRAPHITELTO GRAPHITELTO120K240K360K480K600KSE +/- 5296.28, N = 5SE +/- 5657.41, N = 5SE +/- 2569.74, N = 5SE +/- 6878.12, N = 5SE +/- 1934.24, N = 5SE +/- 3175.67, N = 5SE +/- 5461.64, N = 5SE +/- 7472.89, N = 55390985328515310315299605356095279415223485182241. (CXX) g++ options: --param -march=native -pipe -rdynamic -ldl -lpthread

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 256LTO GRAPHITELTOGRAPHITE8K16K24K32K40KSE +/- 570.36, N = 15SE +/- 686.03, N = 3SE +/- 659.06, N = 15SE +/- 536.99, N = 15SE +/- 860.85, N = 15SE +/- 584.22, N = 15SE +/- 67.22, N = 3SE +/- 369.66, N = 335459353093459934465353073440633711333371. (CC) gcc options: -pthread -march=native -pipe -O3 -lm

Opus Codec Encoding

Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus and then to decode the generated Opus file. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.0.1WAV, Opus Encode, Opus DecodeLTOLTO GRAPHITEGRAPHITE246810SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 57.928.078.128.138.158.198.198.321. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -fPIE -pie -logg -lopus -lm

Swet

Swet is a synthetic CPU/RAM benchmark, includes multi-processor test cases. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgOperations Per Second, More Is BetterSwet 1.5.16AverageLTOLTO GRAPHITEGRAPHITE200M400M600M800M1000MSE +/- 7333312.01, N = 3SE +/- 3864697.02, N = 3SE +/- 12426900.31, N = 3SE +/- 8781499.21, N = 3SE +/- 6065226.54, N = 3SE +/- 9725702.11, N = 3SE +/- 9382367.29, N = 3SE +/- 8667900.17, N = 38575115678432627968337133608223049728532906168499277788423785218385873731. (CC) gcc options: -lm -lpthread -lcurses -lrt

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDLTO GRAPHITELTOGRAPHITE3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 313.3013.3013.3413.3913.3013.3213.4213.441. (CXX) g++ options: -O2 -lOpenCL

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.

O2O3OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteGRAPHITELTO GRAPHITELTO160K320K480K640K800KSE +/- 591.64, N = 3SE +/- 1052.30, N = 3SE +/- 41.28, N = 3SE +/- 1183.61, N = 3SE +/- 402.40, N = 3SE +/- 4161.96, N = 3SE +/- 525.67, N = 3SE +/- 1711.07, N = 3759979758399738154737312758170754742749663748357

CppPerformanceBenchmarks

CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Function ObjectsGRAPHITELTO GRAPHITELTO3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 313.2413.2613.3213.3213.2413.2613.3213.331. (CXX) g++ options: -march=native -pipe -O2 -ftree-vectorize -std=c++11 -O3

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 64GRAPHITELTOLTO GRAPHITE9K18K27K36K45KSE +/- 25.10, N = 3SE +/- 570.27, N = 12SE +/- 587.53, N = 15SE +/- 874.72, N = 15SE +/- 676.98, N = 15SE +/- 742.73, N = 15SE +/- 855.41, N = 15SE +/- 797.17, N = 1539689396793782537135386963741737112360301. (CC) gcc options: -pthread -march=native -pipe -O2 -ftree-vectorize -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 32MB - Thread Count: 16LTO GRAPHITEGRAPHITELTO12K24K36K48K60KSE +/- 438.11, N = 3SE +/- 263.41, N = 3SE +/- 1413.44, N = 15SE +/- 1561.99, N = 15SE +/- 1068.14, N = 12SE +/- 1441.47, N = 15SE +/- 1607.65, N = 15SE +/- 1627.34, N = 1554386539415188551338536185122451196506891. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 128MB - Thread Count: 32GRAPHITELTO GRAPHITELTO15K30K45K60K75KSE +/- 181.06, N = 3SE +/- 212.48, N = 3SE +/- 58.89, N = 3SE +/- 254.78, N = 3SE +/- 195.90, N = 3SE +/- 289.07, N = 3SE +/- 284.72, N = 3SE +/- 199.44, N = 369550693046919968904695366942769277692101. (CC) gcc options: -O2

Go Benchmarks

Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: jsonGRAPHITELTOLTO GRAPHITE500K1000K1500K2000K2500KSE +/- 463.46, N = 3SE +/- 5459.73, N = 3SE +/- 7314.22, N = 3SE +/- 299.89, N = 3SE +/- 3802.89, N = 3SE +/- 662.06, N = 3SE +/- 4657.90, N = 3SE +/- 3267.29, N = 323314602334512233855423443032335399233641223375362342738

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL Particle FilterGRAPHITELTOLTO GRAPHITE3691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 312.6012.6012.6112.6512.6012.6012.6112.631. (CXX) g++ options: -O2 -lOpenCL

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 128MB - Thread Count: 32GRAPHITELTO GRAPHITELTO15K30K45K60K75KSE +/- 278.46, N = 3SE +/- 375.31, N = 3SE +/- 85.93, N = 3SE +/- 128.80, N = 3SE +/- 160.16, N = 3SE +/- 293.38, N = 3SE +/- 353.68, N = 3SE +/- 228.80, N = 369248690636865968265690816898568789687381. (CC) gcc options: -O2

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 8GB - Disk Test: Write PerformanceGRAPHITELTOLTO GRAPHITE30060090012001500SE +/- 0.79, N = 3SE +/- 2.64, N = 3SE +/- 0.95, N = 3SE +/- 0.41, N = 3SE +/- 4.39, N = 3SE +/- 2.09, N = 3SE +/- 14.87, N = 3SE +/- 10.75, N = 3125612551250123112531229122312071. (CC) gcc options: -O3

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 8GB - Disk Test: Write PerformanceLTOGRAPHITELTO GRAPHITE30060090012001500SE +/- 2.01, N = 3SE +/- 9.96, N = 3SE +/- 3.75, N = 3SE +/- 6.09, N = 3SE +/- 3.18, N = 3SE +/- 4.02, N = 3SE +/- 8.50, N = 3SE +/- 3.62, N = 3128612571251123012671254123612231. (CC) gcc options: -O3

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 512LTOLTO GRAPHITEGRAPHITE11K22K33K44K55KSE +/- 658.27, N = 15SE +/- 841.58, N = 3SE +/- 929.65, N = 3SE +/- 991.39, N = 3SE +/- 579.02, N = 3SE +/- 697.74, N = 15SE +/- 458.91, N = 15SE +/- 507.47, N = 1150491503575032149264500074979849600495941. (CC) gcc options: -pthread -march=native -pipe -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.

O3O2OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanhLTO GRAPHITEGRAPHITELTO3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.14, N = 7SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 310.6810.6810.6910.8410.6910.6910.7010.70

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 128MB - Thread Count: 4LTO GRAPHITEGRAPHITELTO90K180K270K360K450KSE +/- 4273.23, N = 3SE +/- 5194.21, N = 15SE +/- 6644.14, N = 15SE +/- 7010.78, N = 3SE +/- 5248.76, N = 3SE +/- 5594.88, N = 12SE +/- 4305.07, N = 3SE +/- 7556.40, N = 34084924035803977413476324037124019793989503986321. (CC) gcc options: -O2

MBW

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

O2O3OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 1024 MiBLTO GRAPHITELTOGRAPHITE2K4K6K8K10KSE +/- 0.59, N = 3SE +/- 0.64, N = 3SE +/- 2.29, N = 3SE +/- 0.72, N = 3SE +/- 2.54, N = 3SE +/- 2.87, N = 3SE +/- 1.60, N = 3SE +/- 0.86, N = 3924192159125874392078713868986861. (CC) gcc options: -O3 -march=native -pipe

Y-Cruncher

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

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.7Calculating 500M Pi DigitsLTOGRAPHITELTO GRAPHITE3691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 310.5810.5910.6110.6210.6210.6310.6310.64

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 32MB - Thread Count: 8GRAPHITELTO GRAPHITELTO40K80K120K160K200KSE +/- 2097.67, N = 3SE +/- 2819.60, N = 15SE +/- 3648.75, N = 15SE +/- 3723.49, N = 15SE +/- 2795.74, N = 5SE +/- 2028.18, N = 15SE +/- 2172.30, N = 15SE +/- 2917.80, N = 151952171932391927021890831928411925101901341885251. (CC) gcc options: -O2

MBW

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

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiBGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 2.67, N = 3SE +/- 2.21, N = 3SE +/- 2.10, N = 3SE +/- 1.90, N = 3SE +/- 3.40, N = 3SE +/- 1.63, N = 3SE +/- 0.48, N = 3SE +/- 3.01, N = 3932892308884887591869152890187961. (CC) gcc options: -O3 -march=native -pipe

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 64MB - Thread Count: 4LTOLTO GRAPHITEGRAPHITE40K80K120K160K200KSE +/- 3972.80, N = 15SE +/- 2678.68, N = 13SE +/- 3001.51, N = 15SE +/- 2631.54, N = 15SE +/- 3051.99, N = 3SE +/- 2904.43, N = 3SE +/- 3050.72, N = 3SE +/- 2809.10, N = 152074342031992002881994632042392035262017211945831. (CC) gcc options: -O2

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 64GRAPHITELTOLTO GRAPHITE3K6K9K12K15KSE +/- 8.74, N = 3SE +/- 510.16, N = 15SE +/- 227.38, N = 15SE +/- 300.19, N = 15SE +/- 32.87, N = 3SE +/- 630.65, N = 15SE +/- 195.21, N = 15SE +/- 217.77, N = 1514087128801023210207137801199010409101751. (CC) gcc options: -pthread -march=native -pipe -lm

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 32LTO GRAPHITELTOGRAPHITE9K18K27K36K45KSE +/- 430.35, N = 3SE +/- 693.88, N = 15SE +/- 619.65, N = 15SE +/- 615.72, N = 15SE +/- 718.14, N = 15SE +/- 771.02, N = 15SE +/- 629.27, N = 15SE +/- 241.99, N = 343982407734009440046409874032739837384121. (CC) gcc options: -pthread -march=native -pipe -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 128MB - Thread Count: 32GRAPHITELTO GRAPHITELTO90180270360450SE +/- 3.78, N = 3SE +/- 2.98, N = 3SE +/- 2.68, N = 3SE +/- 1.31, N = 3SE +/- 6.09, N = 3SE +/- 1.67, N = 3SE +/- 3.54, N = 3SE +/- 4.94, N = 34104074034024094073973921. (CC) gcc options: -O2

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB SizeLTO GRAPHITELTOGRAPHITE2004006008001000SE +/- 0.25, N = 3SE +/- 4.83, N = 3SE +/- 12.29, N = 15SE +/- 1.20, N = 3SE +/- 0.19, N = 3SE +/- 15.55, N = 3SE +/- 10.58, N = 15SE +/- 11.80, N = 159949849459039889709659431. (CC) gcc options: -static

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: EP.CGRAPHITELTO GRAPHITELTO6001200180024003000SE +/- 8.95, N = 3SE +/- 11.67, N = 3SE +/- 41.25, N = 15SE +/- 41.34, N = 15SE +/- 16.80, N = 3SE +/- 35.23, N = 3SE +/- 65.01, N = 15SE +/- 46.16, N = 15271526952496244927092682251524971. 3.3

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 256MB - Thread Count: 8GRAPHITELTO GRAPHITELTO7K14K21K28K35KSE +/- 26.56, N = 3SE +/- 64.53, N = 3SE +/- 20.68, N = 3SE +/- 89.99, N = 3SE +/- 65.47, N = 3SE +/- 36.07, N = 3SE +/- 48.84, N = 3SE +/- 37.46, N = 332787327653274832716326693257532296322431. (CC) gcc options: -O2

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 64LTOGRAPHITELTO GRAPHITE4K8K12K16K20KSE +/- 505.45, N = 15SE +/- 450.15, N = 15SE +/- 403.51, N = 15SE +/- 307.79, N = 4SE +/- 604.04, N = 15SE +/- 484.52, N = 15SE +/- 610.20, N = 12SE +/- 322.28, N = 319269190611895518815192241906318880186191. (CC) gcc options: -pthread -march=native -pipe -lm

dcraw

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image ConversionGRAPHITELTO GRAPHITELTO3691215SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 310.3610.4210.4710.5511.1111.4611.4811.701. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -lm

WavPack Audio Encoding

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.1WAV To WavPackLTOLTO GRAPHITEGRAPHITE246810SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 56.516.526.546.546.546.556.556.561. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -lm

Loopback TCP Network Performance

This test measures the loopback network adapter performance using a micro-benchmark to measure the TCP performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterLoopback TCP Network PerformanceTime To Transfer 10GB Via LoopbackLTO GRAPHITELTOGRAPHITE3691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 310.7310.7610.8110.8510.7810.7910.8010.85

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 256MB - Thread Count: 8GRAPHITELTO GRAPHITELTO30K60K90K120K150KSE +/- 311.86, N = 3SE +/- 503.64, N = 3SE +/- 929.83, N = 3SE +/- 956.22, N = 3SE +/- 593.97, N = 3SE +/- 299.93, N = 3SE +/- 306.40, N = 3SE +/- 2231.84, N = 31194581188281187251177731191291188591187261167421. (CC) gcc options: -O2

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.

O2O3OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video EncodingLTOLTO GRAPHITEGRAPHITE1326395265SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.15, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 356.8756.4356.4356.1056.5756.4656.3456.151. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lpthread -lrt -ldl -lnuma

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverLTOGRAPHITELTO GRAPHITE3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.17, N = 310.4210.4510.4610.5410.4210.4310.4710.531. (CXX) g++ options: -O2 -lOpenCL

CLOMP

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

O3O2OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP SpeedupLTOLTO GRAPHITEGRAPHITE0.39150.7831.17451.5661.9575SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 51.741.701.691.691.721.711.701.671. (CC) gcc options: --openmp -O3 -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 256MB - Thread Count: 8LTO GRAPHITELTOGRAPHITE50100150200250SE +/- 1.21, N = 3SE +/- 2.62, N = 3SE +/- 2.53, N = 3SE +/- 1.04, N = 3SE +/- 2.10, N = 3SE +/- 2.91, N = 3SE +/- 1.25, N = 3SE +/- 3.54, N = 42412382342302362362362351. (CC) gcc options: -O2

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.

O3O2OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceLTO GRAPHITELTOGRAPHITE0.4410.8821.3231.7642.205SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.951.951.951.961.951.951.961.96

O3O2OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsllLTO GRAPHITELTOGRAPHITE0.38930.77861.16791.55721.9465SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.721.721.721.731.721.721.731.73

O3O2OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtLTO GRAPHITELTOGRAPHITE0.54231.08461.62692.16922.7115SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.402.402.412.412.402.402.412.41

O3O2OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsLTO GRAPHITELTOGRAPHITE0.38930.77861.16791.55721.9465SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.721.721.731.731.721.721.731.73

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1024LTO GRAPHITELTOGRAPHITE2K4K6K8K10KSE +/- 37.81, N = 3SE +/- 262.72, N = 15SE +/- 15.86, N = 3SE +/- 6.51, N = 3SE +/- 78.04, N = 3SE +/- 225.24, N = 15SE +/- 19.65, N = 3SE +/- 169.10, N = 1511200105261041310404110681058810432101421. (CC) gcc options: -pthread -march=native -pipe -lm

Primesieve

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

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number GenerationLTOLTO GRAPHITEGRAPHITE3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 310.0210.0310.0410.0410.0310.0410.0410.041. (CXX) g++ options: -march=native -pipe -O3 -lpthread

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPULTO GRAPHITELTOGRAPHITE9K18K27K36K45KSE +/- 1.46, N = 3SE +/- 1.97, N = 3SE +/- 4.97, N = 3SE +/- 5.60, N = 3SE +/- 2.72, N = 3SE +/- 5.61, N = 3SE +/- 7.30, N = 3SE +/- 7.45, N = 343867438574224742247438664369342283422591. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=native -pipe -rdynamic -ldl -laio -lm

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 4GB - Disk Test: Read PerformanceGRAPHITELTO GRAPHITELTO10002000300040005000SE +/- 71.09, N = 3SE +/- 1.60, N = 3SE +/- 68.10, N = 4SE +/- 66.88, N = 4SE +/- 77.48, N = 3SE +/- 65.48, N = 4SE +/- 75.57, N = 3SE +/- 4.01, N = 3450044584430436443504311422241871. (CC) gcc options: -O3

OSBench

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

O3O2OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ThreadsLTOGRAPHITELTO GRAPHITE3691215SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.26, N = 15SE +/- 0.30, N = 15SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 311.1311.4711.7011.9411.1811.2311.2811.401. (CC) gcc options: -march=native -pipe -lm

Sudokut

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterSudokut 0.4Total TimeLTO GRAPHITELTOGRAPHITE3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 39.479.559.729.749.809.849.899.94

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.

O2O3OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2LTO GRAPHITELTOGRAPHITE8001600240032004000SE +/- 24.86, N = 4SE +/- 8.29, N = 4SE +/- 33.59, N = 4SE +/- 58.55, N = 4SE +/- 28.78, N = 4SE +/- 48.42, N = 4SE +/- 50.27, N = 4SE +/- 48.55, N = 433343353344134593340339834103524

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1024LTO GRAPHITELTOGRAPHITE2K4K6K8K10KSE +/- 105.26, N = 3SE +/- 76.42, N = 3SE +/- 14.45, N = 3SE +/- 132.68, N = 3SE +/- 44.07, N = 3SE +/- 8.53, N = 3SE +/- 39.42, N = 3SE +/- 16.08, N = 3959694678999886795009471923489281. (CC) gcc options: -pthread -march=native -pipe -lm

Sample Pi Program

A simple C++ program that calculates Pi to 8,765,4321 digits using the Leibniz formula. This test can be used for showcasing how to write a basic test profile. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterSample Pi ProgramLTO GRAPHITELTOGRAPHITE3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 39.069.069.069.069.069.069.069.11

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.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19LTOLTO GRAPHITEGRAPHITE3691215SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 38.898.989.049.078.968.979.029.091. (CC) gcc options: -march=native -pipe -pthread -lz -llzma

Go Benchmarks

Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: garbageLTO GRAPHITELTOGRAPHITE130K260K390K520K650KSE +/- 1777.30, N = 3SE +/- 973.67, N = 3SE +/- 1190.29, N = 3SE +/- 1315.90, N = 3SE +/- 733.55, N = 3SE +/- 1544.80, N = 3SE +/- 1517.44, N = 3SE +/- 987.83, N = 3621051621310622956623188621095622412622652623559

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 32MB - Thread Count: 32GRAPHITELTOLTO GRAPHITE14K28K42K56K70KSE +/- 152.97, N = 3SE +/- 52.81, N = 3SE +/- 981.22, N = 5SE +/- 663.99, N = 3SE +/- 264.92, N = 3SE +/- 733.11, N = 9SE +/- 1101.74, N = 12SE +/- 1076.52, N = 1565915658636440163961653496463163921639211. (CC) gcc options: -O2

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 32GRAPHITELTOLTO GRAPHITE3K6K9K12K15KSE +/- 613.50, N = 15SE +/- 621.38, N = 15SE +/- 28.84, N = 3SE +/- 43.26, N = 3SE +/- 436.96, N = 15SE +/- 17.85, N = 3SE +/- 21.50, N = 3SE +/- 81.26, N = 313660136221111211015117311126711248111341. (CC) gcc options: -pthread -march=native -pipe -lm

Bork File Encrypter

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBork File Encrypter 1.4File Encryption TimeLTOLTO GRAPHITEGRAPHITE246810SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 38.548.558.578.578.558.568.588.61

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 128MB - Thread Count: 16LTO GRAPHITELTOGRAPHITE15K30K45K60K75KSE +/- 461.97, N = 3SE +/- 143.75, N = 3SE +/- 162.24, N = 3SE +/- 255.57, N = 3SE +/- 129.21, N = 3SE +/- 258.22, N = 3SE +/- 408.21, N = 3SE +/- 194.23, N = 369468693076885768642692796924569130689351. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 32MB - Thread Count: 8LTOLTO GRAPHITEGRAPHITE70140210280350SE +/- 2.88, N = 15SE +/- 1.17, N = 3SE +/- 4.00, N = 15SE +/- 3.08, N = 15SE +/- 3.71, N = 15SE +/- 3.63, N = 15SE +/- 3.77, N = 15SE +/- 3.44, N = 153002992932872982962902891. (CC) gcc options: -O2

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueReadBufferGRAPHITELTO GRAPHITELTO246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 36.436.436.426.426.436.436.426.411. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lOpenCL

O2O3OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Transfer Bandwidth enqueueWriteBufferLTO GRAPHITEGRAPHITELTO246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 36.116.116.106.106.116.106.106.101. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lOpenCL

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 4096GRAPHITELTOLTO GRAPHITE12K24K36K48K60KSE +/- 31.19, N = 3SE +/- 635.46, N = 3SE +/- 310.91, N = 3SE +/- 1026.94, N = 3SE +/- 694.07, N = 3SE +/- 629.85, N = 3SE +/- 603.41, N = 3SE +/- 604.79, N = 356569558455562255337564455584955386551341. (CC) gcc options: -pthread -march=native -pipe -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 256MB - Thread Count: 4LTO GRAPHITEGRAPHITELTO4K8K12K16K20KSE +/- 14.13, N = 3SE +/- 12.42, N = 3SE +/- 18.71, N = 3SE +/- 21.18, N = 3SE +/- 23.68, N = 3SE +/- 22.91, N = 3SE +/- 15.80, N = 3SE +/- 13.50, N = 316416164001639716329163811632016280162611. (CC) gcc options: -O2

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 64LTOLTO GRAPHITEGRAPHITE2K4K6K8K10KSE +/- 231.71, N = 15SE +/- 217.22, N = 15SE +/- 251.97, N = 15SE +/- 14.69, N = 3SE +/- 212.32, N = 12SE +/- 51.23, N = 3SE +/- 124.91, N = 5SE +/- 173.76, N = 3995098899646929198179715905789181. (CC) gcc options: -pthread -march=native -pipe -O3 -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 256MB - Thread Count: 4LTOGRAPHITELTO GRAPHITE16K32K48K64K80KSE +/- 407.46, N = 3SE +/- 396.38, N = 3SE +/- 359.99, N = 3SE +/- 642.35, N = 3SE +/- 325.29, N = 3SE +/- 1193.86, N = 3SE +/- 338.21, N = 3SE +/- 742.31, N = 372665722757159771510726187019970169686321. (CC) gcc options: -O2

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.

O3O2OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonGRAPHITELTOLTO GRAPHITE6001200180024003000SE +/- 6.76, N = 4SE +/- 4.27, N = 4SE +/- 18.78, N = 4SE +/- 20.26, N = 4SE +/- 3.09, N = 4SE +/- 6.38, N = 4SE +/- 10.65, N = 4SE +/- 6.31, N = 428372849286128682839284628542858

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.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilGRAPHITELTO GRAPHITELTO1.3052.613.9155.226.525SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 5SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 35.655.735.775.775.705.775.795.801. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 128MB - Thread Count: 8GRAPHITELTO GRAPHITELTO50100150200250SE +/- 3.45, N = 3SE +/- 1.85, N = 3SE +/- 2.25, N = 14SE +/- 2.41, N = 3SE +/- 2.20, N = 3SE +/- 4.29, N = 3SE +/- 4.26, N = 4SE +/- 4.31, N = 32492462442292482462462371. (CC) gcc options: -O2

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: FT.BGRAPHITELTOLTO GRAPHITE3K6K9K12K15KSE +/- 18.65, N = 3SE +/- 7.00, N = 3SE +/- 23.06, N = 3SE +/- 22.95, N = 3SE +/- 11.86, N = 3SE +/- 4.94, N = 3SE +/- 28.38, N = 3SE +/- 16.91, N = 315292152781265212588152751523212658126231. 3.3

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 32MB - Thread Count: 32GRAPHITELTO GRAPHITELTO130260390520650SE +/- 10.17, N = 3SE +/- 1.74, N = 3SE +/- 7.56, N = 15SE +/- 8.89, N = 3SE +/- 7.68, N = 15SE +/- 6.48, N = 3SE +/- 7.32, N = 15SE +/- 7.82, N = 65925825735305805795795701. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 128MB - Thread Count: 16GRAPHITELTOLTO GRAPHITE70140210280350SE +/- 5.22, N = 3SE +/- 4.88, N = 3SE +/- 2.64, N = 3SE +/- 5.96, N = 3SE +/- 2.77, N = 3SE +/- 3.40, N = 3SE +/- 3.98, N = 3SE +/- 0.29, N = 33273253253143243223213201. (CC) gcc options: -O2

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 4GB - Disk Test: Read PerformanceGRAPHITELTOLTO GRAPHITE15003000450060007500SE +/- 13.19, N = 3SE +/- 15.29, N = 3SE +/- 13.25, N = 3SE +/- 18.69, N = 3SE +/- 20.61, N = 3SE +/- 23.79, N = 3SE +/- 8.93, N = 3SE +/- 9.55, N = 3707470096683668270296972675066851. (CC) gcc options: -O3

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 4GB - Disk Test: Read PerformanceGRAPHITELTOLTO GRAPHITE16003200480064008000SE +/- 52.15, N = 3SE +/- 20.22, N = 3SE +/- 46.53, N = 3SE +/- 27.45, N = 3SE +/- 29.48, N = 3SE +/- 43.15, N = 3SE +/- 12.23, N = 3SE +/- 46.75, N = 3738472587227716773467296721172051. (CC) gcc options: -O3

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 256MB - Thread Count: 4GRAPHITELTO GRAPHITELTO4080120160200SE +/- 0.58, N = 3SE +/- 0.19, N = 3SE +/- 0.69, N = 3SE +/- 1.37, N = 3SE +/- 0.68, N = 3SE +/- 1.38, N = 3SE +/- 0.72, N = 3SE +/- 0.11, N = 31691671671571671671661661. (CC) gcc options: -O2

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 32MB - Thread Count: 32GRAPHITELTOLTO GRAPHITE90K180K270K360K450KSE +/- 1803.53, N = 3SE +/- 5941.91, N = 3SE +/- 6218.02, N = 12SE +/- 5868.48, N = 15SE +/- 1460.80, N = 3SE +/- 3395.46, N = 3SE +/- 619.63, N = 3SE +/- 3509.18, N = 34170104141314128024046744143064111914110274099331. (CC) gcc options: -O2

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 512LTOGRAPHITELTO GRAPHITE2K4K6K8K10KSE +/- 140.95, N = 3SE +/- 135.31, N = 3SE +/- 14.02, N = 3SE +/- 136.36, N = 5SE +/- 111.95, N = 15SE +/- 140.08, N = 5SE +/- 145.97, N = 15SE +/- 45.61, N = 3946892429127908892579150902589311. (CC) gcc options: -pthread -march=native -pipe -O2 -ftree-vectorize -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 32MB - Thread Count: 16GRAPHITELTO GRAPHITELTO90180270360450SE +/- 5.22, N = 15SE +/- 3.49, N = 3SE +/- 5.60, N = 6SE +/- 1.50, N = 3SE +/- 6.24, N = 15SE +/- 5.13, N = 15SE +/- 4.83, N = 15SE +/- 4.49, N = 34294154023974174144044011. (CC) gcc options: -O2

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 512GRAPHITELTO GRAPHITELTO5K10K15K20K25KSE +/- 86.85, N = 3SE +/- 73.63, N = 3SE +/- 72.59, N = 3SE +/- 147.79, N = 3SE +/- 103.49, N = 3SE +/- 140.33, N = 3SE +/- 137.69, N = 3SE +/- 85.43, N = 325458250602504324993250932493924872247711. (CC) gcc options: -pthread -march=native -pipe -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 128MB - Thread Count: 4LTOGRAPHITELTO GRAPHITE3K6K9K12K15KSE +/- 15.25, N = 3SE +/- 47.01, N = 3SE +/- 46.86, N = 3SE +/- 29.58, N = 3SE +/- 42.85, N = 3SE +/- 23.35, N = 3SE +/- 37.69, N = 3SE +/- 333.71, N = 1216142161301612916125160941606316025157841. (CC) gcc options: -O2

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 4GB - Disk Test: Write PerformanceLTOGRAPHITELTO GRAPHITE2004006008001000SE +/- 5.59, N = 3SE +/- 5.99, N = 3SE +/- 5.65, N = 3SE +/- 4.49, N = 3SE +/- 4.80, N = 3SE +/- 2.37, N = 3SE +/- 17.39, N = 3SE +/- 10.88, N = 3112411091099108811081079107610681. (CC) gcc options: -O3

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: ThreadGRAPHITELTOLTO GRAPHITE246810SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 36.876.916.966.976.886.896.976.991. (CC) gcc options: -lpthread -march=native -pipe

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 64MB - Thread Count: 32LTO GRAPHITEGRAPHITELTO7K14K21K28K35KSE +/- 120.83, N = 3SE +/- 129.73, N = 3SE +/- 55.67, N = 3SE +/- 42.40, N = 3SE +/- 135.58, N = 3SE +/- 93.42, N = 3SE +/- 86.05, N = 3SE +/- 209.66, N = 334586344233434634300345413451934517343991. (CC) gcc options: -O2

Unpacking The Linux Kernel

This test measures how long it takes to extract the .tar.xz Linux kernel package. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking The Linux Kernellinux-4.15.tar.xzGRAPHITELTOLTO GRAPHITE1.17232.34463.51694.68925.8615SE +/- 0.01, N = 4SE +/- 0.02, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.01, N = 4SE +/- 0.00, N = 45.065.085.125.165.125.155.165.21

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 64MB - Thread Count: 32LTOLTO GRAPHITEGRAPHITE15K30K45K60K75KSE +/- 107.37, N = 3SE +/- 9.22, N = 3SE +/- 97.03, N = 3SE +/- 135.37, N = 3SE +/- 212.57, N = 3SE +/- 116.46, N = 3SE +/- 190.12, N = 3SE +/- 721.73, N = 367994678876772767630678226772867506673121. (CC) gcc options: -O2

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 32LTOLTO GRAPHITEGRAPHITE4K8K12K16K20KSE +/- 228.25, N = 8SE +/- 267.46, N = 5SE +/- 161.91, N = 3SE +/- 253.18, N = 15SE +/- 177.14, N = 13SE +/- 0.33, N = 3SE +/- 258.83, N = 3SE +/- 399.05, N = 1518653182691789717876185361801817909161661. (CC) gcc options: -pthread -march=native -pipe -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Read - Size Per Thread: 32MB - Thread Count: 4LTOLTO GRAPHITEGRAPHITE20K40K60K80K100KSE +/- 482.93, N = 3SE +/- 1600.37, N = 15SE +/- 955.72, N = 3SE +/- 1669.29, N = 15SE +/- 1292.44, N = 3SE +/- 885.20, N = 3SE +/- 1737.85, N = 3SE +/- 1839.13, N = 151058771050171040541011731044941031021028421006861. (CC) gcc options: -O2

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: ProcessLTO GRAPHITEGRAPHITELTO246810SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 36.536.536.546.566.586.596.596.611. (CC) gcc options: -lpthread -march=native -pipe -O2 -ftree-vectorize

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 64MB - Thread Count: 16GRAPHITELTOLTO GRAPHITE80160240320400SE +/- 0.49, N = 3SE +/- 5.75, N = 3SE +/- 4.49, N = 7SE +/- 6.46, N = 3SE +/- 6.96, N = 3SE +/- 4.27, N = 8SE +/- 2.59, N = 3SE +/- 3.86, N = 93593503483443553473463431. (CC) gcc options: -O2

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 256LTOLTO GRAPHITEGRAPHITE2K4K6K8K10KSE +/- 182.26, N = 3SE +/- 107.20, N = 11SE +/- 70.86, N = 3SE +/- 68.39, N = 3SE +/- 65.70, N = 3SE +/- 105.30, N = 15SE +/- 24.58, N = 3SE +/- 30.69, N = 310783106351035610199107191049310424102641. (CC) gcc options: -pthread -march=native -pipe -lm

Rust Prime Benchmark

Based on petehunt/rust-benchmark, this is a prime number benchmark that is multi-threaded and written in Rustlang. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,000GRAPHITELTO GRAPHITELTO246810SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.466.476.476.476.476.476.476.48

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 128MB - Thread Count: 8GRAPHITELTO GRAPHITELTO7K14K21K28K35KSE +/- 56.18, N = 3SE +/- 30.81, N = 3SE +/- 67.51, N = 3SE +/- 81.93, N = 3SE +/- 26.02, N = 3SE +/- 89.43, N = 3SE +/- 38.42, N = 3SE +/- 11.08, N = 332514324513239932356323353229832176321521. (CC) gcc options: -O2

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 128MB - Thread Count: 8LTO GRAPHITELTOGRAPHITE13K26K39K52K65KSE +/- 52.53, N = 3SE +/- 576.21, N = 3SE +/- 415.38, N = 3SE +/- 240.58, N = 3SE +/- 608.00, N = 3SE +/- 250.53, N = 3SE +/- 234.56, N = 3SE +/- 404.18, N = 360141597855951359244600715997459681588671. (CC) gcc options: -O2

OSBench

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

O2O3OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ProcessesGRAPHITELTOLTO GRAPHITE612182430SE +/- 0.31, N = 3SE +/- 0.25, N = 3SE +/- 0.25, N = 3SE +/- 0.31, N = 6SE +/- 0.12, N = 3SE +/- 0.18, N = 3SE +/- 0.12, N = 3SE +/- 0.31, N = 622.1022.7023.0323.3922.6222.6722.8122.971. (CC) gcc options: -march=native -pipe -lm

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 2048LTO GRAPHITEGRAPHITELTO13K26K39K52K65KSE +/- 491.80, N = 3SE +/- 370.02, N = 3SE +/- 184.32, N = 3SE +/- 369.84, N = 3SE +/- 400.03, N = 3SE +/- 859.84, N = 3SE +/- 357.29, N = 3SE +/- 90.01, N = 361336611076083360580611016064660598604081. (CC) gcc options: -pthread -march=native -pipe -lm

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 4GB - Disk Test: Write PerformanceGRAPHITELTOLTO GRAPHITE30060090012001500SE +/- 2.82, N = 3SE +/- 1.30, N = 3SE +/- 0.50, N = 3SE +/- 3.79, N = 3SE +/- 1.17, N = 3SE +/- 0.60, N = 3SE +/- 1.16, N = 3SE +/- 4.53, N = 3125112411226122512471242123212171. (CC) gcc options: -O3

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 4GB - Disk Test: Write PerformanceLTOGRAPHITELTO GRAPHITE30060090012001500SE +/- 0.63, N = 3SE +/- 3.01, N = 3SE +/- 3.11, N = 3SE +/- 5.39, N = 3SE +/- 5.09, N = 3SE +/- 0.85, N = 3SE +/- 2.38, N = 3SE +/- 4.85, N = 3128212331233121312611247123012091. (CC) gcc options: -O3

GnuPG

This test times how long it takes to encrypt a file using GnuPG. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterGnuPG 1.4.222GB File EncryptionLTOLTO GRAPHITEGRAPHITE246810SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 36.136.176.186.206.186.196.206.201. (CC) gcc options: -march=native -pipe -MT -MD -MP -MF

libjpeg-turbo tjbench

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

O2O3OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.3Test: Decompression ThroughputGRAPHITELTOLTO GRAPHITE4080120160200SE +/- 0.69, N = 3SE +/- 0.53, N = 3SE +/- 0.27, N = 3SE +/- 0.37, N = 3SE +/- 0.06, N = 3SE +/- 0.59, N = 3SE +/- 0.17, N = 3SE +/- 0.14, N = 31971971971971971971971961. (CC) gcc options: -march=native -pipe -O3 -lm

MBW

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

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 512 MiBGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 5.34, N = 3SE +/- 5.00, N = 3SE +/- 3.31, N = 3SE +/- 1.76, N = 3SE +/- 2.66, N = 3SE +/- 3.52, N = 3SE +/- 3.46, N = 3SE +/- 2.95, N = 3914790648735872091169055882986291. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 512 MiBGRAPHITELTO GRAPHITELTO2K4K6K8K10KSE +/- 3.15, N = 3SE +/- 2.36, N = 3SE +/- 0.66, N = 3SE +/- 1.83, N = 3SE +/- 1.64, N = 3SE +/- 1.18, N = 3SE +/- 1.10, N = 3SE +/- 2.68, N = 3934487728746873093249299924488621. (CC) gcc options: -O3 -march=native -pipe

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 64MB - Thread Count: 32GRAPHITELTO GRAPHITELTO100200300400500SE +/- 3.25, N = 3SE +/- 3.24, N = 3SE +/- 2.74, N = 3SE +/- 6.22, N = 3SE +/- 5.66, N = 3SE +/- 3.54, N = 3SE +/- 8.80, N = 3SE +/- 2.26, N = 34584564454424544524474371. (CC) gcc options: -O2

OSBench

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

O2O3OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create FilesLTOGRAPHITELTO GRAPHITE48121620SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 316.9217.0017.1117.2417.0717.0717.1317.161. (CC) gcc options: -march=native -pipe -lm

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 128GRAPHITELTOLTO GRAPHITE3K6K9K12K15KSE +/- 11.55, N = 3SE +/- 54.60, N = 3SE +/- 303.17, N = 15SE +/- 242.90, N = 15SE +/- 53.80, N = 3SE +/- 62.81, N = 3SE +/- 8.39, N = 3SE +/- 51.35, N = 312107117951114010796119191187111341112911. (CC) gcc options: -pthread -march=native -pipe -lm

t-test1

This is a test of t-test1 for basic memory allocator benchmarks. Note this test profile is currently very basic and the overall time does include the warmup time of the custom t-test1 compilation. Improvements welcome. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2GRAPHITELTO GRAPHITELTO1.25782.51563.77345.03126.289SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 35.535.555.575.575.545.555.575.591. (CC) gcc options: -pthread -march=native -pipe

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.

O3O2OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.51080p 8-bit YUV To AV1 Video EncodeLTOGRAPHITELTO GRAPHITE1224364860SE +/- 0.11, N = 3SE +/- 0.19, N = 3SE +/- 0.37, N = 3SE +/- 0.20, N = 3SE +/- 0.13, N = 3SE +/- 0.19, N = 3SE +/- 0.26, N = 3SE +/- 0.14, N = 355.4455.2855.0354.6355.1955.0154.9154.621. (CXX) g++ options: -march=native -pipe -O3 -pie -lpthread -lm

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: MemoryLTOLTO GRAPHITEGRAPHITE4M8M12M16M20MSE +/- 22770.05, N = 3SE +/- 41886.85, N = 3SE +/- 83986.00, N = 3SE +/- 73779.96, N = 3SE +/- 101995.88, N = 3SE +/- 157893.08, N = 3SE +/- 143605.27, N = 3SE +/- 9190.64, N = 319889024198819091983465919645196196542841950283219492222194557981. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=native -pipe -O2 -ftree-vectorize -rdynamic -ldl -laio -lm

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: ProcessLTO GRAPHITEGRAPHITELTO0.5491.0981.6472.1962.745SE +/- 0.02, N = 3SE +/- 0.03, N = 6SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 5SE +/- 0.04, N = 3SE +/- 0.02, N = 15SE +/- 0.03, N = 152.332.342.392.442.352.382.412.411. (CC) gcc options: -lpthread -march=native -pipe

OSBench

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

O2O3OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch ProgramsLTOLTO GRAPHITEGRAPHITE714212835SE +/- 0.28, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 3SE +/- 0.47, N = 4SE +/- 0.09, N = 3SE +/- 0.16, N = 3SE +/- 0.32, N = 3SE +/- 0.52, N = 326.1526.4227.2527.6526.2826.5226.9927.301. (CC) gcc options: -march=native -pipe -lm

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 256GRAPHITELTOLTO GRAPHITE5K10K15K20K25KSE +/- 426.61, N = 4SE +/- 457.54, N = 3SE +/- 325.62, N = 3SE +/- 37.99, N = 3SE +/- 379.42, N = 5SE +/- 413.09, N = 3SE +/- 241.98, N = 3SE +/- 122.88, N = 325569255522543224965255092502824967247881. (CC) gcc options: -pthread -march=native -pipe -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 64MB - Thread Count: 16LTO GRAPHITEGRAPHITELTO7K14K21K28K35KSE +/- 38.69, N = 3SE +/- 194.64, N = 3SE +/- 141.63, N = 3SE +/- 130.87, N = 3SE +/- 223.47, N = 3SE +/- 206.08, N = 3SE +/- 88.63, N = 3SE +/- 146.36, N = 334770345893455834191347363463434603344091. (CC) gcc options: -O2

OSBench

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

O2O3OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory AllocationsLTOGRAPHITELTO GRAPHITE20406080100SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 378.8379.0979.7979.7978.9080.1880.2980.371. (CC) gcc options: -march=native -pipe -O3 -lm

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 128MB - Thread Count: 4GRAPHITELTOLTO GRAPHITE8K16K24K32K40KSE +/- 158.04, N = 3SE +/- 207.85, N = 3SE +/- 133.16, N = 3SE +/- 120.38, N = 3SE +/- 285.26, N = 3SE +/- 332.92, N = 3SE +/- 425.19, N = 3SE +/- 266.65, N = 336699366503618536061363243587535605349221. (CC) gcc options: -O2

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 512LTOLTO GRAPHITEGRAPHITE2K4K6K8K10KSE +/- 16.55, N = 3SE +/- 87.50, N = 3SE +/- 12.83, N = 3SE +/- 23.85, N = 3SE +/- 26.16, N = 3SE +/- 35.93, N = 3SE +/- 17.94, N = 3SE +/- 21.71, N = 3978396339220905397489676912591251. (CC) gcc options: -pthread -march=native -pipe -lm

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 1024GRAPHITELTO GRAPHITELTO13K26K39K52K65KSE +/- 756.06, N = 3SE +/- 1234.15, N = 3SE +/- 559.09, N = 3SE +/- 799.30, N = 3SE +/- 168.77, N = 3SE +/- 516.25, N = 3SE +/- 256.22, N = 3SE +/- 141.80, N = 362586623516185561073624976169361102608141. (CC) gcc options: -pthread -march=native -pipe -O3 -lm

Git

This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsLTOLTO GRAPHITEGRAPHITE1.07782.15563.23344.31125.389SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 34.634.704.724.754.674.694.734.791. git version 2.22.1

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 64MB - Thread Count: 8GRAPHITELTOLTO GRAPHITE60120180240300SE +/- 1.74, N = 3SE +/- 1.60, N = 3SE +/- 1.02, N = 3SE +/- 3.76, N = 4SE +/- 3.46, N = 3SE +/- 2.41, N = 15SE +/- 4.54, N = 3SE +/- 2.86, N = 32662612562482632632632571. (CC) gcc options: -O2

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 128GRAPHITELTOLTO GRAPHITE7K14K21K28K35KSE +/- 41.26, N = 3SE +/- 40.95, N = 3SE +/- 192.65, N = 3SE +/- 246.61, N = 3SE +/- 112.40, N = 3SE +/- 28.34, N = 3SE +/- 115.50, N = 3SE +/- 131.93, N = 330791306923049330461307473073930652305321. (CC) gcc options: -pthread -march=native -pipe -lm

Smallpt

Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesGRAPHITELTO GRAPHITELTO1.01482.02963.04444.05925.074SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.484.504.514.514.494.504.504.501. (CXX) g++ options: -fopenmp -O3 -march=native -pipe

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 32GRAPHITELTO GRAPHITELTO3K6K9K12K15KSE +/- 13.50, N = 3SE +/- 54.34, N = 3SE +/- 82.50, N = 3SE +/- 167.49, N = 3SE +/- 105.73, N = 3SE +/- 90.50, N = 3SE +/- 101.00, N = 3SE +/- 410.00, N = 1215078149711262412340150551500211907113501. (CC) gcc options: -pthread -march=native -pipe -lm

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 2GB - Disk Test: Read PerformanceGRAPHITELTO GRAPHITELTO9001800270036004500SE +/- 2.15, N = 3SE +/- 65.11, N = 3SE +/- 65.68, N = 3SE +/- 72.23, N = 3SE +/- 62.83, N = 3SE +/- 69.63, N = 3SE +/- 3.80, N = 3SE +/- 75.27, N = 3441744094246422143844316431641881. (CC) gcc options: -O3

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 256LTO GRAPHITELTOGRAPHITE2K4K6K8K10KSE +/- 61.05, N = 3SE +/- 25.33, N = 3SE +/- 34.09, N = 3SE +/- 49.25, N = 3SE +/- 16.20, N = 3SE +/- 82.87, N = 3SE +/- 76.82, N = 3SE +/- 18.04, N = 3983797879358926698259649929492241. (CC) gcc options: -pthread -march=native -pipe -lm

Apache Siege

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

O3O2OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 10LTO GRAPHITELTOGRAPHITE12K24K36K48K60KSE +/- 1018.25, N = 3SE +/- 573.84, N = 15SE +/- 611.16, N = 8SE +/- 602.01, N = 8SE +/- 814.60, N = 4SE +/- 682.09, N = 6SE +/- 750.12, N = 5SE +/- 846.31, N = 354782496694940749284513204984249455473491. (CC) gcc options: -march=native -pipe -lpthread -ldl -lssl -lcrypto

FFTW

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

O2O3OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 128LTO GRAPHITELTOGRAPHITE5K10K15K20K25KSE +/- 210.05, N = 3SE +/- 303.98, N = 3SE +/- 237.83, N = 15SE +/- 431.74, N = 3SE +/- 167.05, N = 3SE +/- 210.54, N = 3SE +/- 238.52, N = 3SE +/- 155.97, N = 324610241212358022922242662391623716234831. (CC) gcc options: -pthread -march=native -pipe -lm

Bullet Physics Engine

This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 FallGRAPHITELTO GRAPHITELTO0.87531.75062.62593.50124.3765SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.663.743.833.893.663.763.803.821. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lglut -lGL -lGLU

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 64MB - Thread Count: 8LTOLTO GRAPHITEGRAPHITE7K14K21K28K35KSE +/- 68.11, N = 3SE +/- 69.53, N = 3SE +/- 86.37, N = 3SE +/- 36.10, N = 3SE +/- 46.33, N = 3SE +/- 32.68, N = 3SE +/- 44.13, N = 3SE +/- 168.01, N = 331733317043160731583316533164731454314491. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 64MB - Thread Count: 8LTOGRAPHITELTO GRAPHITE6K12K18K24K30KSE +/- 200.46, N = 3SE +/- 109.13, N = 3SE +/- 246.03, N = 3SE +/- 159.52, N = 3SE +/- 67.37, N = 3SE +/- 192.25, N = 3SE +/- 221.71, N = 3SE +/- 144.54, N = 330041298832975729516297802971129699292941. (CC) gcc options: -O2

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 128MB - Thread Count: 4LTO GRAPHITEGRAPHITELTO4080120160200SE +/- 0.57, N = 3SE +/- 0.54, N = 3SE +/- 0.06, N = 3SE +/- 0.50, N = 3SE +/- 0.57, N = 3SE +/- 1.08, N = 3SE +/- 0.60, N = 3SE +/- 0.72, N = 31741721721691741741731701. (CC) gcc options: -O2

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: ThreadLTO GRAPHITELTOGRAPHITE0.90451.8092.71353.6184.5225SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.973.974.004.003.993.994.004.021. (CC) gcc options: -lpthread -march=native -pipe

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 32MB - Thread Count: 32LTO GRAPHITEGRAPHITELTO4K8K12K16K20KSE +/- 160.11, N = 3SE +/- 13.35, N = 3SE +/- 60.46, N = 3SE +/- 95.66, N = 3SE +/- 63.88, N = 3SE +/- 67.45, N = 3SE +/- 74.75, N = 3SE +/- 47.99, N = 317318172471716117142172831711017102170861. (CC) gcc options: -O2

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: ProcessLTO GRAPHITEGRAPHITELTO0.86851.7372.60553.4744.3425SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.833.833.843.843.833.843.853.861. (CC) gcc options: -lpthread -march=native -pipe

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: ThreadLTO GRAPHITELTOGRAPHITE0.5671.1341.7012.2682.835SE +/- 0.01, N = 3SE +/- 0.04, N = 4SE +/- 0.03, N = 10SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 7SE +/- 0.04, N = 42.382.442.442.522.432.442.442.461. (CC) gcc options: -lpthread -march=native -pipe

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 2GB - Disk Test: Read PerformanceGRAPHITELTO GRAPHITELTO15003000450060007500SE +/- 17.09, N = 3SE +/- 124.99, N = 3SE +/- 133.98, N = 3SE +/- 13.56, N = 3SE +/- 5.13, N = 3SE +/- 11.20, N = 3SE +/- 120.56, N = 3SE +/- 28.33, N = 3690867366705654468986881665566101. (CC) gcc options: -O3

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 2GB - Disk Test: Read PerformanceLTOGRAPHITELTO GRAPHITE16003200480064008000SE +/- 38.21, N = 3SE +/- 58.15, N = 3SE +/- 25.86, N = 3SE +/- 50.82, N = 3SE +/- 39.04, N = 3SE +/- 18.21, N = 3SE +/- 12.03, N = 3SE +/- 32.27, N = 3724372407072707071807163704670381. (CC) gcc options: -O3

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchLTO GRAPHITELTOGRAPHITE0.8371.6742.5113.3484.185SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 33.383.403.493.553.663.663.703.721. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -pthread -lhmmer -lsquid -lm

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 2GB - Disk Test: Write PerformanceLTOGRAPHITELTO GRAPHITE2004006008001000SE +/- 5.53, N = 3SE +/- 5.85, N = 3SE +/- 17.84, N = 3SE +/- 15.10, N = 3SE +/- 6.67, N = 3SE +/- 6.16, N = 3SE +/- 14.31, N = 3SE +/- 4.76, N = 3112010911086107411081106110110871. (CC) gcc options: -O3

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 64MB - Thread Count: 4LTO GRAPHITELTOGRAPHITE3K6K9K12K15KSE +/- 38.13, N = 3SE +/- 66.41, N = 3SE +/- 61.86, N = 3SE +/- 67.01, N = 3SE +/- 58.24, N = 3SE +/- 27.58, N = 3SE +/- 63.39, N = 3SE +/- 93.28, N = 316234161801617916142161351613416099159331. (CC) gcc options: -O2

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 64MB - Thread Count: 4LTOLTO GRAPHITEGRAPHITE4K8K12K16K20KSE +/- 39.90, N = 3SE +/- 40.20, N = 3SE +/- 172.91, N = 3SE +/- 139.23, N = 3SE +/- 93.73, N = 3SE +/- 75.04, N = 3SE +/- 162.23, N = 3SE +/- 149.25, N = 318387181921774917355182281814618067173171. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 32MB - Thread Count: 16LTO GRAPHITELTOGRAPHITE4K8K12K16K20KSE +/- 93.24, N = 3SE +/- 121.45, N = 3SE +/- 130.95, N = 3SE +/- 29.99, N = 3SE +/- 81.29, N = 3SE +/- 136.59, N = 3SE +/- 43.52, N = 3SE +/- 56.02, N = 317384173201731317258173641735417319172121. (CC) gcc options: -O2

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stride, 4 ThreadsLTO GRAPHITEGRAPHITELTO1632486480SE +/- 0.21, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 0.26, N = 3SE +/- 0.03, N = 3SE +/- 0.22, N = 3SE +/- 0.39, N = 369.9069.9270.0270.2070.1370.1870.2670.361. (CC) gcc options: -O2 -static -pthread -lrt

FFTW

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

O3O2OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 128LTOLTO GRAPHITEGRAPHITE3K6K9K12K15KSE +/- 58.35, N = 3SE +/- 188.43, N = 3SE +/- 21.99, N = 3SE +/- 56.16, N = 3SE +/- 55.60, N = 3SE +/- 88.42, N = 3SE +/- 108.31, N = 3SE +/- 158.29, N = 311845111691096010893116111150010759106741. (CC) gcc options: -pthread -march=native -pipe -lm

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stride, 2 ThreadsLTOLTO GRAPHITEGRAPHITE1530456075SE +/- 0.27, N = 3SE +/- 0.21, N = 3SE +/- 0.17, N = 3SE +/- 0.06, N = 3SE +/- 0.48, N = 3SE +/- 0.24, N = 3SE +/- 0.23, N = 3SE +/- 0.10, N = 368.6568.6768.6968.8268.6768.7968.9769.111. (CC) gcc options: -O2 -static -pthread -lrt

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 2GB - Disk Test: Write PerformanceGRAPHITELTOLTO GRAPHITE30060090012001500SE +/- 6.58, N = 3SE +/- 1.90, N = 3SE +/- 0.67, N = 3SE +/- 0.53, N = 3SE +/- 1.24, N = 3SE +/- 6.54, N = 3SE +/- 5.23, N = 3SE +/- 2.49, N = 3124312381226120512331232122212131. (CC) gcc options: -O3

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte StrideLTO GRAPHITELTOGRAPHITE1530456075SE +/- 0.07, N = 3SE +/- 0.45, N = 3SE +/- 0.23, N = 3SE +/- 0.03, N = 3SE +/- 0.41, N = 3SE +/- 0.33, N = 3SE +/- 0.37, N = 3SE +/- 0.18, N = 367.1967.7267.9468.1167.5367.7067.7168.691. (CC) gcc options: -O2 -static -pthread -lrt

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 2GB - Disk Test: Write PerformanceLTOGRAPHITELTO GRAPHITE30060090012001500SE +/- 0.45, N = 3SE +/- 2.53, N = 3SE +/- 9.28, N = 3SE +/- 6.48, N = 3SE +/- 2.01, N = 3SE +/- 6.31, N = 3SE +/- 4.53, N = 3SE +/- 2.63, N = 3127812261226120512421229122812251. (CC) gcc options: -O3

Multichase Pointer Chaser

This is a benchmark of Google's multichase pointer chaser program. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 256MB Array, 256 Byte StrideLTO GRAPHITEGRAPHITELTO1428425670SE +/- 0.36, N = 3SE +/- 0.23, N = 3SE +/- 0.51, N = 3SE +/- 0.48, N = 3SE +/- 0.35, N = 3SE +/- 0.51, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 361.4061.8862.0262.7061.7562.1262.2362.601. (CC) gcc options: -O2 -static -pthread -lrt

O2O3OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 4MB Array, 64 Byte StrideGRAPHITELTOLTO GRAPHITE246810SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 38.468.508.528.638.538.558.608.691. (CC) gcc options: -O2 -static -pthread -lrt

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.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenCL HeartwallLTO GRAPHITELTOGRAPHITE0.67951.3592.03852.7183.3975SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.003.003.003.023.013.013.023.021. (CXX) g++ options: -O2 -lOpenCL

Parboil

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

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenCL BFSLTOGRAPHITELTO GRAPHITE0.29480.58960.88441.17921.474SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.301.301.311.311.301.301.311.311. (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. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: LU.ALTOGRAPHITELTO GRAPHITE11K22K33K44K55KSE +/- 72.47, N = 3SE +/- 404.10, N = 3SE +/- 213.04, N = 3SE +/- 189.37, N = 3SE +/- 187.72, N = 3SE +/- 225.23, N = 3SE +/- 68.38, N = 3SE +/- 89.77, N = 349301480454758146536486674814247581470161. 3.3

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 32MB - Thread Count: 8GRAPHITELTO GRAPHITELTO7K14K21K28K35KSE +/- 184.15, N = 3SE +/- 253.18, N = 3SE +/- 72.28, N = 3SE +/- 311.21, N = 3SE +/- 131.59, N = 3SE +/- 48.94, N = 3SE +/- 350.13, N = 3SE +/- 156.65, N = 331353313113116431150313313101830905309031. (CC) gcc options: -O2

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 32MB - Thread Count: 8LTOLTO GRAPHITEGRAPHITE3K6K9K12K15KSE +/- 44.99, N = 3SE +/- 151.80, N = 3SE +/- 113.98, N = 3SE +/- 84.08, N = 3SE +/- 105.09, N = 3SE +/- 104.48, N = 3SE +/- 169.24, N = 3SE +/- 130.08, N = 315203150831502714951149401488114870146321. (CC) gcc options: -O2

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB SizeLTOLTO GRAPHITEGRAPHITE2004006008001000SE +/- 0.85, N = 3SE +/- 4.66, N = 3SE +/- 11.43, N = 15SE +/- 11.69, N = 15SE +/- 2.44, N = 3SE +/- 2.53, N = 3SE +/- 11.67, N = 15SE +/- 0.59, N = 310069789669469949649479171. (CC) gcc options: -static

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Random Write - Size Per Thread: 32MB - Thread Count: 4LTOGRAPHITELTO GRAPHITE2K4K6K8K10KSE +/- 33.56, N = 3SE +/- 73.66, N = 3SE +/- 68.23, N = 3SE +/- 61.61, N = 3SE +/- 70.15, N = 3SE +/- 67.00, N = 3SE +/- 143.99, N = 4SE +/- 42.52, N = 3918091289118871690879048885886601. (CC) gcc options: -O2

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgGIOPS, More Is BetterclpeakOpenCL Test: Integer Compute INTLTO GRAPHITEGRAPHITELTO30060090012001500SE +/- 0.36, N = 3SE +/- 1.01, N = 3SE +/- 0.13, N = 3SE +/- 0.61, N = 3SE +/- 1.76, N = 3SE +/- 1.80, N = 3SE +/- 0.40, N = 3SE +/- 0.62, N = 3116811671163116311651164116211611. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lOpenCL

PolyBench-C

PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: 3 Matrix MultiplicationsLTO GRAPHITELTOGRAPHITE0.60751.2151.82252.433.0375SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 32.642.652.672.702.682.692.702.701. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -O3

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Read - Size Per Thread: 32MB - Thread Count: 4LTOLTO GRAPHITEGRAPHITE4K8K12K16K20KSE +/- 43.97, N = 3SE +/- 110.01, N = 3SE +/- 67.60, N = 3SE +/- 178.36, N = 3SE +/- 95.52, N = 3SE +/- 152.30, N = 3SE +/- 65.69, N = 3SE +/- 52.33, N = 316411163421620416025162911616916153160751. (CC) gcc options: -O2

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.

O3O2OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeLTO GRAPHITELTOGRAPHITE150300450600750SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.76, N = 36406416416416416416676721. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 64MB - Thread Count: 4GRAPHITELTO GRAPHITELTO4080120160200SE +/- 2.85, N = 3SE +/- 2.01, N = 3SE +/- 1.07, N = 3SE +/- 1.33, N = 3SE +/- 2.08, N = 3SE +/- 2.91, N = 3SE +/- 2.98, N = 3SE +/- 0.98, N = 31861841831801841811791781. (CC) gcc options: -O2

Tachyon

This is a test of the threaded Tachyon, a parallel ray-tracing system. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total TimeGRAPHITELTO GRAPHITELTO0.43880.87761.31641.75522.194SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 4SE +/- 0.02, N = 3SE +/- 0.03, N = 71.871.891.911.921.891.911.911.951. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

CoMD OpenCL

CoMD benchmark in OpenCL via GPUOpen. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgus/atom/task, More Is BetterCoMD OpenCL 2017-07-06Average Atom Update RateLTO GRAPHITELTOGRAPHITE0.61431.22861.84292.45723.0715SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 32.732.722.692.692.712.692.682.681. (CC) gcc options: -std=c99 -O5 -lm -lOpenCL

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video EncodeGRAPHITELTO GRAPHITELTO80160240320400SE +/- 6.33, N = 3SE +/- 6.13, N = 4SE +/- 7.20, N = 3SE +/- 6.59, N = 3SE +/- 6.12, N = 3SE +/- 5.69, N = 4SE +/- 7.33, N = 3SE +/- 6.51, N = 33813813803793803793783781. (CC) gcc options: -march=native -pipe -O2 -fPIE -fPIC -flto -fvisibility=hidden -mavx -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

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

O3O2OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video EncodeGRAPHITELTO GRAPHITELTO80160240320400SE +/- 4.13, N = 3SE +/- 5.77, N = 3SE +/- 3.91, N = 3SE +/- 3.33, N = 3SE +/- 2.03, N = 3SE +/- 2.90, N = 3SE +/- 4.20, N = 3SE +/- 3.67, N = 33593583583573543543533531. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -fPIE -fPIC -flto -fvisibility=hidden -pie -rdynamic -lpthread -lrt

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.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenCL TPACFLTOLTO GRAPHITEGRAPHITE0.4050.811.2151.622.025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.791.801.801.801.801.801.801.801. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPLTO GRAPHITELTOGRAPHITE0.4320.8641.2961.7282.16SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.911.921.921.921.911.911.921.921. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

TSCP

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

O3O2OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceLTOLTO GRAPHITEGRAPHITE300K600K900K1200K1500KSE +/- 765.00, N = 5SE +/- 1206.25, N = 5SE +/- 726.00, N = 5SE +/- 889.16, N = 5SE +/- 1427.82, N = 5SE +/- 1705.90, N = 5SE +/- 889.16, N = 5SE +/- 889.16, N = 5145247514494191415155141370314501841449423141442914144291. (CC) gcc options: -march=native -pipe -O3

System Libxml2 Parsing

This test measures the time to parse a random XML file with libxml2 via xmllint using the streaming API. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 3 MBGRAPHITELTOLTO GRAPHITE400800120016002000SE +/- 15.67, N = 3SE +/- 20.67, N = 3SE +/- 8.76, N = 3SE +/- 3.18, N = 3SE +/- 2.91, N = 3SE +/- 24.13, N = 3SE +/- 18.89, N = 316701676167916841684171717221724

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgGBPS, More Is BetterclpeakOpenCL Test: Global Memory BandwidthGRAPHITELTOLTO GRAPHITE306090120150SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31451451451451451451451451. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lOpenCL

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm8192.in input file. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsGRAPHITELTO GRAPHITELTO0.37130.74261.11391.48521.8565SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 31.621.631.631.641.631.641.641.651. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Threaded I/O Tester

Tiotester (Threaded I/O Tester) benchmarks the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 32MB - Thread Count: 4LTOGRAPHITELTO GRAPHITE4080120160200SE +/- 1.18, N = 3SE +/- 0.87, N = 3SE +/- 0.46, N = 3SE +/- 1.23, N = 3SE +/- 1.16, N = 3SE +/- 1.31, N = 3SE +/- 1.13, N = 3SE +/- 3.57, N = 32052042032032052022022011. (CC) gcc options: -O2

MBW

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

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 128 MiBGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 5.03, N = 3SE +/- 7.04, N = 3SE +/- 3.02, N = 3SE +/- 5.17, N = 3SE +/- 0.83, N = 3SE +/- 9.51, N = 3SE +/- 6.80, N = 3SE +/- 6.68, N = 3914490418697868390829021901187921. (CC) gcc options: -O3 -march=native -pipe

O3O2OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 128 MiBGRAPHITELTOLTO GRAPHITE2K4K6K8K10KSE +/- 7.69, N = 3SE +/- 7.10, N = 3SE +/- 7.66, N = 3SE +/- 7.97, N = 3SE +/- 6.02, N = 3SE +/- 5.45, N = 3SE +/- 159.15, N = 3SE +/- 4.35, N = 3960490349016900495719503944491021. (CC) gcc options: -O3 -march=native -pipe

AIO-Stress

AIO-Stress is an a-synchronous I/O benchmark created by SuSE. Current this profile uses a 2048MB test file and a 64KB record size. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMB/s, More Is BetterAIO-Stress 0.21Test: Random WriteLTOGRAPHITELTO GRAPHITE9001800270036004500SE +/- 5.89, N = 3SE +/- 4.44, N = 3SE +/- 7.99, N = 3SE +/- 7.74, N = 3SE +/- 7.20, N = 3SE +/- 2.68, N = 3SE +/- 4.81, N = 3SE +/- 7.35, N = 3410140403979397340513988398439831. (CC) gcc options: -pthread -laio

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 512MB - Disk Test: Read PerformanceGRAPHITELTOLTO GRAPHITE9001800270036004500SE +/- 61.71, N = 3SE +/- 61.11, N = 3SE +/- 68.23, N = 3SE +/- 14.45, N = 3SE +/- 17.59, N = 3SE +/- 63.91, N = 3SE +/- 48.64, N = 3SE +/- 28.49, N = 3427242634139409742464171416141481. (CC) gcc options: -O3

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgGFLOPS, More Is BetterclpeakOpenCL Test: Single-Precision FloatGRAPHITELTO GRAPHITELTO8001600240032004000SE +/- 8.24, N = 3SE +/- 12.71, N = 3SE +/- 2.06, N = 3SE +/- 6.14, N = 3SE +/- 12.20, N = 3SE +/- 13.35, N = 3SE +/- 1.69, N = 3SE +/- 4.18, N = 3364936383617361436363629361836121. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lOpenCL

System Libxml2 Parsing

This test measures the time to parse a random XML file with libxml2 via xmllint using the streaming API. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 2 MBLTOGRAPHITELTO GRAPHITE2004006008001000SE +/- 2.60, N = 3SE +/- 0.33, N = 3SE +/- 9.35, N = 3SE +/- 5.17, N = 3SE +/- 10.00, N = 3SE +/- 10.09, N = 311171122112311291134113611521158

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 512MB - Disk Test: Read PerformanceLTOGRAPHITELTO GRAPHITE15003000450060007500SE +/- 34.72, N = 3SE +/- 34.05, N = 3SE +/- 3.43, N = 3SE +/- 62.67, N = 3SE +/- 5.83, N = 3SE +/- 17.92, N = 3SE +/- 52.86, N = 3SE +/- 46.93, N = 3690668596594642267716659649864211. (CC) gcc options: -O3

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 512MB - Disk Test: Read PerformanceGRAPHITELTOLTO GRAPHITE16003200480064008000SE +/- 30.79, N = 3SE +/- 12.50, N = 3SE +/- 15.81, N = 3SE +/- 92.48, N = 3SE +/- 7.00, N = 3SE +/- 15.17, N = 3SE +/- 22.95, N = 3SE +/- 101.13, N = 3726472067182694472567179714269621. (CC) gcc options: -O3

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3.1Test / Class: FT.AGRAPHITELTO GRAPHITELTO3K6K9K12K15KSE +/- 3.22, N = 3SE +/- 75.72, N = 3SE +/- 83.26, N = 3SE +/- 86.79, N = 3SE +/- 116.83, N = 3SE +/- 106.53, N = 3SE +/- 16.67, N = 3SE +/- 195.31, N = 314441143521209012075143011427512175119161. 3.3

IOzone

The IOzone benchmark tests the hard disk drive / file-system performance. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 512MB - Disk Test: Write PerformanceLTO GRAPHITEGRAPHITELTO2004006008001000SE +/- 12.52, N = 3SE +/- 4.00, N = 3SE +/- 9.43, N = 3SE +/- 5.86, N = 3SE +/- 2.87, N = 3SE +/- 2.14, N = 3SE +/- 4.35, N = 3SE +/- 4.35, N = 3110210961083107411001088108310681. (CC) gcc options: -O3

O2O3OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 512MB - Disk Test: Write PerformanceLTO GRAPHITEGRAPHITELTO30060090012001500SE +/- 6.64, N = 3SE +/- 6.15, N = 3SE +/- 4.77, N = 3SE +/- 7.74, N = 3SE +/- 10.84, N = 3SE +/- 3.53, N = 3SE +/- 3.57, N = 3SE +/- 6.14, N = 3124312151207120112401238122811991. (CC) gcc options: -O3

O3O2OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 512MB - Disk Test: Write PerformanceGRAPHITELTOLTO GRAPHITE30060090012001500SE +/- 4.40, N = 3SE +/- 8.21, N = 3SE +/- 8.97, N = 3SE +/- 9.91, N = 3SE +/- 2.62, N = 3SE +/- 1.63, N = 3SE +/- 4.23, N = 3SE +/- 3.29, N = 3123512271220120812301223122112111. (CC) gcc options: -O3

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgus, Fewer Is BetterclpeakOpenCL Test: Kernel LatencyLTO GRAPHITELTOGRAPHITE1.08452.1693.25354.3385.4225SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.754.764.764.764.764.774.794.821. (CXX) g++ options: -march=native -pipe -O2 -ftree-vectorize -O3 -rdynamic -lOpenCL

Apache Siege

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

O2O3OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 1LTO GRAPHITELTOGRAPHITE3K6K9K12K15KSE +/- 114.56, N = 3SE +/- 0.00, N = 3SE +/- 128.63, N = 3SE +/- 0.00, N = 3SE +/- 65.21, N = 3SE +/- 128.63, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 314086140851395613889140191395613889138891. (CC) gcc options: -march=native -pipe -lpthread -ldl -lssl -lcrypto

FS-Mark

FS_Mark is designed to test a system's file-system performance. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSyncLTOGRAPHITELTO GRAPHITE6001200180024003000SE +/- 2.07, N = 3SE +/- 1.11, N = 3SE +/- 1.97, N = 3SE +/- 3.24, N = 3SE +/- 0.89, N = 3SE +/- 1.81, N = 3SE +/- 1.05, N = 3SE +/- 0.78, N = 3258225742568255625662559255825401. (CC) gcc options: -static

System Libxml2 Parsing

This test measures the time to parse a random XML file with libxml2 via xmllint using the streaming API. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 850 KBLTOGRAPHITELTO GRAPHITE100200300400500SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 4.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 7.02, N = 3SE +/- 0.88, N = 3456456459465464467467470

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 1 MBLTOGRAPHITELTO GRAPHITE80160240320400SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 5.84, N = 4SE +/- 6.03, N = 3355358360360365366366367

BLAKE2

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

O3O2OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 20170307LTO GRAPHITELTOGRAPHITE0.76051.5212.28153.0423.8025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.383.383.383.383.383.383.383.381. (CC) gcc options: -O3 -march=native -lcrypto -lz

System Libxml2 Parsing

This test measures the time to parse a random XML file with libxml2 via xmllint using the streaming API. Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 950 KBLTOGRAPHITELTO GRAPHITE70140210280350SE +/- 0.67, N = 3SE +/- 4.04, N = 3SE +/- 1.20, N = 3329331333337333334338338

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 600 KBLTOGRAPHITELTO GRAPHITE70140210280350SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 1.86, N = 3SE +/- 6.33, N = 3SE +/- 0.58, N = 3323323325327328332332333

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 900 KBLTOGRAPHITELTO GRAPHITE70140210280350SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 6.17, N = 3319321323323324328329332

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 400 KBLTOGRAPHITELTO GRAPHITE50100150200250SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 2.66, N = 8SE +/- 3.36, N = 5218218221223222225226228

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 800 KBLTOGRAPHITELTO GRAPHITE60120180240300SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3275279280280280281284285

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 500 KBGRAPHITELTOLTO GRAPHITE60120180240300SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 1.67, N = 3SE +/- 5.17, N = 3272273274276275277282286

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 750 KBLTOGRAPHITELTO GRAPHITE60120180240300SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 1.53, N = 3SE +/- 2.19, N = 3261264265266265266272273

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 700 KBLTOGRAPHITELTO GRAPHITE50100150200250SE +/- 0.33, N = 3SE +/- 1.33, N = 3SE +/- 0.33, N = 3SE +/- 3.67, N = 5237239241241241244245245

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 650 KBLTOGRAPHITELTO GRAPHITE50100150200250SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 1.20, N = 3SE +/- 0.33, N = 3226228229229230231232233

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 550 KBLTOGRAPHITELTO GRAPHITE4080120160200SE +/- 3.00, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3189189190190189190192193

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 450 KBLTOGRAPHITELTO GRAPHITE4080120160200SE +/- 0.33, N = 3SE +/- 0.67, N = 3156157158159158159161161

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 350 KBLTOGRAPHITELTO GRAPHITE306090120150SE +/- 1.86, N = 3SE +/- 0.33, N = 3SE +/- 1.67, N = 3119120121123122123123123

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 300 KBLTOGRAPHITELTO GRAPHITE20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3107108108109109109110110

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 250 KBLTOGRAPHITELTO GRAPHITE20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 38484858585868687

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 200 KBLTO GRAPHITELTOGRAPHITE1632486480SE +/- 0.33, N = 3SE +/- 1.00, N = 37272727272737373

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 100 KBLTOGRAPHITELTO GRAPHITE1428425670SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 36060606161616262

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 150 KBLTOLTO GRAPHITEGRAPHITE12243648604950505050505151

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 50 KBLTO GRAPHITELTOGRAPHITE481216201616161616161616

O3O2OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 5 KBLTO GRAPHITELTOGRAPHITE0.450.91.351.82.2522222222

Phoronix Test Suite Self Test

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

O3O2OpenBenchmarking.orgMB, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Peak Memory UsageLTO GRAPHITELTOGRAPHITE110220330440550SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2500500500500500500500500

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Merge ResultsLTO GRAPHITEGRAPHITELTO0.6841.3682.0522.7363.42SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.02, N = 2SE +/- 0.04, N = 2SE +/- 0.00, N = 2SE +/- 0.01, N = 2SE +/- 0.00, N = 2SE +/- 0.02, N = 22.982.993.003.033.003.023.033.04

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Info CommandLTOLTO GRAPHITEGRAPHITE0.35550.7111.06651.4221.7775SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.09, N = 2SE +/- 0.10, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.07, N = 21.411.471.561.581.461.471.471.53

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: Render TestGRAPHITELTOLTO GRAPHITE816243240SE +/- 0.06, N = 2SE +/- 0.29, N = 2SE +/- 0.03, N = 2SE +/- 0.01, N = 2SE +/- 0.11, N = 2SE +/- 0.37, N = 2SE +/- 0.12, N = 2SE +/- 0.11, N = 232.8532.8533.0633.1233.0633.2633.3033.49

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterPhoronix Test Suite Self Test 1.0Test: List SuitesGRAPHITELTOLTO GRAPHITE0.19130.38260.57390.76520.9565SE +/- 0.00, N = 2SE +/- 0.00, N = 2SE +/- 0.02, N = 2SE +/- 0.02, N = 2SE +/- 0.02, N = 2SE +/- 0.01, N = 2SE +/- 0.00, N = 2SE +/- 0.15, N = 20.690.700.710.770.720.720.730.85

Bullet Physics Engine

This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex TrimeshLTO GRAPHITELTOGRAPHITE0.2250.450.6750.91.125SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.960.970.991.000.970.970.991.001. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lglut -lGL -lGLU

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim TrimeshLTO GRAPHITELTOGRAPHITE0.1890.3780.5670.7560.945SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.820.830.840.840.820.820.830.841. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lglut -lGL -lGLU

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 RagdollsGRAPHITELTO GRAPHITELTO0.54451.0891.63352.1782.7225SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 32.302.352.382.392.312.342.392.421. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lglut -lGL -lGLU

O2O3OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 ConvexLTO GRAPHITELTOGRAPHITE0.88431.76862.65293.53724.4215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.863.903.913.933.873.903.913.931. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lglut -lGL -lGLU

O3O2OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 StackGRAPHITELTO GRAPHITELTO1.03052.0613.09154.1225.1525SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.054.144.504.584.054.144.484.521. (CXX) g++ options: -march=native -pipe -O3 -rdynamic -lglut -lGL -lGLU

SciMark

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

O3O2OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationGRAPHITELTOLTO GRAPHITE5001000150020002500SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.03, N = 3222422232223222215681567156515641. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -lm

O3O2OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationGRAPHITELTOLTO GRAPHITE13002600390052006500SE +/- 10.69, N = 3SE +/- 4.56, N = 3SE +/- 5.38, N = 3SE +/- 0.37, N = 3SE +/- 3.43, N = 3SE +/- 0.35, N = 3SE +/- 1.30, N = 3SE +/- 0.10, N = 3591356035174398256825643563940511. (CC) gcc options: -march=native -pipe -lm

O3O2OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyGRAPHITELTOLTO GRAPHITE7001400210028003500SE +/- 5.30, N = 3SE +/- 4.42, N = 3SE +/- 1.77, N = 3SE +/- 2.27, N = 3SE +/- 6.31, N = 3SE +/- 5.13, N = 3SE +/- 3.43, N = 3SE +/- 3.65, N = 3335531982692264131983183291526381. (CC) gcc options: -march=native -pipe -lm

O3O2OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformGRAPHITELTOLTO GRAPHITE130260390520650SE +/- 0.82, N = 3SE +/- 2.76, N = 3SE +/- 2.00, N = 3SE +/- 8.27, N = 3SE +/- 16.56, N = 3SE +/- 8.66, N = 3SE +/- 2.71, N = 3SE +/- 29.31, N = 35955855815765775685605581. (CC) gcc options: -march=native -pipe -O2 -ftree-vectorize -lm

LuaJIT

This test profile is a collection of Lua scripts/benchmarks run against a locally-built copy of LuaJIT upstream. Learn more via the OpenBenchmarking.org test page.

O2O3OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Jacobi Successive Over-RelaxationGRAPHITELTOLTO GRAPHITE400800120016002000SE +/- 0.34, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 3SE +/- 0.27, N = 3SE +/- 0.47, N = 3SE +/- 0.16, N = 3SE +/- 0.59, N = 3SE +/- 0.06, N = 3165416541653165316541654165416541. (CC) gcc options: -lm -ldl

O3O2OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Dense LU Matrix FactorizationGRAPHITELTOLTO GRAPHITE8001600240032004000SE +/- 3.17, N = 3SE +/- 11.69, N = 3SE +/- 5.59, N = 3SE +/- 4.43, N = 3SE +/- 3.90, N = 3SE +/- 6.12, N = 3SE +/- 10.97, N = 3SE +/- 8.35, N = 3383738123750374838293751373937251. (CC) gcc options: -lm -ldl

O2O3OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Sparse Matrix MultiplyLTOGRAPHITELTO GRAPHITE30060090012001500SE +/- 2.04, N = 3SE +/- 0.97, N = 3SE +/- 2.17, N = 3SE +/- 2.14, N = 3SE +/- 1.27, N = 3SE +/- 1.20, N = 3SE +/- 1.44, N = 3SE +/- 2.59, N = 3141214111408140714111409140814081. (CC) gcc options: -lm -ldl

O3O2OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Fast Fourier TransformGRAPHITELTOLTO GRAPHITE110220330440550SE +/- 4.65, N = 3SE +/- 8.27, N = 3SE +/- 0.30, N = 3SE +/- 6.26, N = 3SE +/- 1.01, N = 3SE +/- 11.73, N = 3SE +/- 7.57, N = 3SE +/- 4.52, N = 35235165115065185125115041. (CC) gcc options: -lm -ldl

O2O3OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte CarloLTO GRAPHITEGRAPHITELTO120240360480600SE +/- 0.79, N = 3SE +/- 0.27, N = 3SE +/- 0.38, N = 3SE +/- 0.38, N = 3SE +/- 0.35, N = 3SE +/- 0.46, N = 3SE +/- 0.26, N = 3SE +/- 0.36, N = 35525515515515515515515491. (CC) gcc options: -lm -ldl

Java SciMark

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

O2O3OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Jacobi Successive Over-RelaxationLTO GRAPHITEGRAPHITELTO30060090012001500SE +/- 0.84, N = 4SE +/- 0.17, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 416041603160316031603160316031603

O2O3OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Dense LU Matrix FactorizationLTOGRAPHITELTO GRAPHITE11002200330044005500SE +/- 21.41, N = 4SE +/- 15.54, N = 4SE +/- 23.10, N = 4SE +/- 6.19, N = 4SE +/- 27.01, N = 4SE +/- 30.02, N = 4SE +/- 23.69, N = 4SE +/- 7.74, N = 450905080506550345064504750215010

O2O3OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Sparse Matrix MultiplyGRAPHITELTOLTO GRAPHITE5001000150020002500SE +/- 0.60, N = 4SE +/- 0.51, N = 4SE +/- 0.00, N = 4SE +/- 0.31, N = 4SE +/- 0.36, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 3.63, N = 425582558255825572558255825582553

O2O3OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Fast Fourier TransformGRAPHITELTOLTO GRAPHITE30060090012001500SE +/- 139.03, N = 4SE +/- 131.09, N = 4SE +/- 129.30, N = 4SE +/- 2.54, N = 4SE +/- 158.10, N = 4SE +/- 149.55, N = 4SE +/- 128.60, N = 4SE +/- 130.31, N = 412231207120381010821074943942

O2O3OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Monte CarloGRAPHITELTOLTO GRAPHITE2004006008001000SE +/- 0.08, N = 4SE +/- 0.00, N = 4SE +/- 0.00, N = 4SE +/- 0.14, N = 4SE +/- 0.08, N = 4SE +/- 0.07, N = 4SE +/- 0.07, N = 4SE +/- 0.26, N = 410851085108510851085108510851085

Stream

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

O2O3OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: AddGRAPHITELTO GRAPHITELTO12K24K36K48K60KSE +/- 7.58, N = 5SE +/- 3.93, N = 5SE +/- 2.97, N = 5SE +/- 14.85, N = 5SE +/- 3.16, N = 5SE +/- 3.23, N = 5SE +/- 4.10, N = 5SE +/- 3.64, N = 558091580565795857792580915803557949579341. (CC) gcc options: -march=native -pipe -O3 -fopenmp

O2O3OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: TriadLTOGRAPHITELTO GRAPHITE13K26K39K52K65KSE +/- 11.46, N = 5SE +/- 7.62, N = 5SE +/- 6.98, N = 5SE +/- 8.21, N = 5SE +/- 7.23, N = 5SE +/- 6.72, N = 5SE +/- 11.12, N = 5SE +/- 7.11, N = 558990589115890258892589265891958868588241. (CC) gcc options: -march=native -pipe -O3 -fopenmp

O2O3OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: ScaleLTOGRAPHITELTO GRAPHITE11K22K33K44K55KSE +/- 19.76, N = 5SE +/- 11.15, N = 5SE +/- 16.88, N = 5SE +/- 11.26, N = 5SE +/- 10.25, N = 5SE +/- 8.18, N = 5SE +/- 6.12, N = 5SE +/- 8.32, N = 552701522955228552175522805225652111521031. (CC) gcc options: -march=native -pipe -O3 -fopenmp

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

O3O2OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeLTO GRAPHITELTOGRAPHITE6001200180024003000SE +/- 9.50, N = 3SE +/- 35.54, N = 3SE +/- 0.00, N = 3SE +/- 8.94, N = 3SE +/- 24.09, N = 3SE +/- 23.66, N = 3SE +/- 8.94, N = 3SE +/- 17.63, N = 327292702268326742728270126922674

O2O3OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateLTOLTO GRAPHITEGRAPHITE120240360480600SE +/- 2.39, N = 3SE +/- 2.51, N = 3SE +/- 3.41, N = 3SE +/- 3.71, N = 3SE +/- 2.37, N = 3SE +/- 2.96, N = 3SE +/- 1.71, N = 3SE +/- 2.15, N = 3568565561559564564561559

BlogBench

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

O3O2OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: WriteGRAPHITELTOLTO GRAPHITE9K18K27K36K45KSE +/- 144.80, N = 3SE +/- 745.12, N = 3SE +/- 217.73, N = 3SE +/- 91.62, N = 3SE +/- 289.89, N = 3SE +/- 258.32, N = 3SE +/- 152.69, N = 3SE +/- 601.54, N = 341466410944109340914414104133141045408731. (CC) gcc options: -march=native -pipe -pthread

478 Results Shown

CppPerformanceBenchmarks
Dbench:
  48
  12
Numpy Benchmark
Dbench:
  256
  128
  1
  6
Blender:
  Fishy Cat - CUDA
  Fishy Cat - OpenCL
BlogBench
Hierarchical INTegration:
  FLOAT
  DOUBLE
CppPerformanceBenchmarks
Tinymembench:
  Standard Memset
  Standard Memcpy
Blender:
  Pabellon Barcelona - OpenCL
  Pabellon Barcelona - CUDA
RAR Compression
FFTW
Blender:
  Barbershop - CUDA
  Barbershop - OpenCL
Radiance Benchmark
LZMA Compression
LLVM Test Suite
FFTW
Phoronix Test Suite Self Test
Scikit-Learn
Blender
Schbench:
  8 - 6
  32 - 2
  4 - 16
GNU GMP GMPbench
Apache Siege
R Benchmark
Blender:
  BMW27 - CUDA
  BMW27 - OpenCL
Parboil
CacheBench:
  Read / Modify / Write
  Write
  Read
asmFish
Schbench:
  8 - 8
  16 - 6
  2 - 32
BYTE Unix Benchmark:
  Floating-Point Arithmetic
  Register Arithmetic
  Integer Arithmetic
  Dhrystone 2
Timed LLVM Compilation
Fhourstones
Schbench
Minion
MBW:
  Memory Copy - 8192 MiB
  Memory Copy, Fixed Block Size - 8192 MiB
Apache Siege
Blender:
  Classroom - OpenCL
  Classroom - CUDA
CppPerformanceBenchmarks
Blender
Schbench:
  2 - 6
  2 - 4
Perl Benchmarks
Blender
Radiance Benchmark
CppPerformanceBenchmarks
Minion
Threaded I/O Tester
FFTW
GraphicsMagick:
  Sharpen
  Resizing
  Enhanced
  Swirl
  Noise-Gaussian
  Rotate
  HWB Color Space
CppPerformanceBenchmarks
Stockfish
Himeno Benchmark
NAMD
Schbench:
  2 - 8
  2 - 2
Perl Benchmarks
Timed MrBayes Analysis
System Libxml2 Parsing
Blender
GNU MPC
Threaded I/O Tester
Parboil
FFTW
DaCapo Benchmark
NAS Parallel Benchmarks
MBW:
  Memory Copy - 4096 MiB
  Memory Copy, Fixed Block Size - 4096 MiB
Rodinia
Timed Linux Kernel Compilation
Rodinia
Threaded I/O Tester
Hackbench
DaCapo Benchmark
Rust Mandelbrot
Schbench
Redis
PostMark
Schbench
Redis:
  LPUSH
  GET
Sockperf
lzbench:
  XZ 0 - Decompression
  XZ 0 - Compression
m-queens
Redis
ebizzy
Redis
7-Zip Compression
Schbench:
  6 - 16
  4 - 2
C-Ray
Java SciMark
lzbench:
  Libdeflate 1 - Decompression
  Libdeflate 1 - Compression
Threaded I/O Tester
lzbench:
  Zstd 1 - Decompression
  Zstd 1 - Compression
Go Benchmarks
lzbench:
  Brotli 0 - Decompression
  Brotli 0 - Compression
Schbench:
  4 - 4
  4 - 6
Gzip Compression
LuaJIT
Apache Siege
Schbench:
  32 - 8
  6 - 24
Sunflow Rendering System
CppPerformanceBenchmarks
NAMD CUDA
Schbench:
  6 - 4
  6 - 6
Node.js Octane Benchmark
NAS Parallel Benchmarks
Blender
Schbench:
  32 - 16
  32 - 24
  32 - 4
  32 - 6
  16 - 8
  16 - 2
  8 - 4
  8 - 2
  16 - 24
  16 - 16
  6 - 8
  4 - 8
  16 - 32
  4 - 24
  8 - 16
  2 - 16
  8 - 32
  8 - 24
  4 - 32
  6 - 32
  2 - 24
SciMark
Threaded I/O Tester
IOzone
AOBench
PyBench
Apache Benchmark
Java Gradle Build
eSpeak Speech Engine
Threaded I/O Tester
Sockperf
DaCapo Benchmark
Parboil
Threaded I/O Tester:
  Read - 256MB - 32
  Rand Write - 256MB - 32
Hackbench
Stream
Threaded I/O Tester
Hackbench
TTSIOD 3D Renderer
Go Benchmarks
Cython benchmark
Crafty
Botan:
  AES-256 - Decrypt
  AES-256 - Encrypt
NAS Parallel Benchmarks
glibc bench:
  sin
  cos
Botan:
  Twofish - Decrypt
  Twofish - Encrypt
  Blowfish - Decrypt
  Blowfish - Encrypt
FFTW
Botan:
  CAST-256 - Decrypt
  CAST-256 - Encrypt
  KASUMI - Decrypt
  KASUMI - Encrypt
OpenSSL
clpeak
Threaded I/O Tester
Compile Bench
Memcached mcperf:
  Set
  Add
Threaded I/O Tester
Memcached mcperf:
  Append
  Prepend
  Replace
Hackbench
Threaded I/O Tester
RAMspeed SMP:
  Copy - Floating Point
  Scale - Floating Point
  Add - Floating Point
  Average - Floating Point
  Triad - Floating Point
  Copy - Integer
  Add - Integer
  Triad - Integer
  Average - Integer
  Scale - Integer
Threaded I/O Tester
FFTW
Threaded I/O Tester:
  Read - 128MB - 16
  Read - 64MB - 16
XZ Compression
Threaded I/O Tester
FFTW
t-test1
Hackbench
Threaded I/O Tester:
  Rand Read - 64MB - 8
  Rand Write - 256MB - 16
FLAC Audio Encoding
Memcached mcperf:
  Delete
  Get
IOzone
Threaded I/O Tester
Apache Siege
IOzone
FS-Mark
Timed ImageMagick Compilation
IOzone
Xsbench
Sockperf
FFTW
Opus Codec Encoding
Swet
Rodinia
PHPBench
CppPerformanceBenchmarks
FFTW
Threaded I/O Tester:
  Read - 32MB - 16
  Read - 128MB - 32
Go Benchmarks
Rodinia
Threaded I/O Tester
IOzone:
  1MB - 8GB - Write Performance
  64Kb - 8GB - Write Performance
FFTW
glibc bench
Threaded I/O Tester
MBW
Y-Cruncher
Threaded I/O Tester
MBW
Threaded I/O Tester
FFTW:
  Stock - 1D FFT Size 64
  Float + SSE - 2D FFT Size 32
Threaded I/O Tester
FS-Mark
NAS Parallel Benchmarks
Threaded I/O Tester
FFTW
dcraw
WavPack Audio Encoding
Loopback TCP Network Performance
Threaded I/O Tester
x265
Rodinia
CLOMP
Threaded I/O Tester
glibc bench:
  pthread_once
  ffsll
  sqrt
  ffs
FFTW
Primesieve
Sysbench
IOzone
OSBench
Sudokut
DaCapo Benchmark
FFTW
Sample Pi Program
Zstd Compression
Go Benchmarks
Threaded I/O Tester
FFTW
Bork File Encrypter
Threaded I/O Tester:
  Rand Write - 128MB - 16
  Write - 32MB - 8
clpeak:
  Transfer Bandwidth enqueueReadBuffer
  Transfer Bandwidth enqueueWriteBuffer
FFTW
Threaded I/O Tester
FFTW
Threaded I/O Tester
DaCapo Benchmark
Parboil
Threaded I/O Tester
NAS Parallel Benchmarks
Threaded I/O Tester:
  Write - 32MB - 32
  Write - 128MB - 16
IOzone:
  1MB - 4GB - Read Performance
  64Kb - 4GB - Read Performance
Threaded I/O Tester:
  Write - 256MB - 4
  Rand Read - 32MB - 32
FFTW
Threaded I/O Tester
FFTW
Threaded I/O Tester
IOzone
Hackbench
Threaded I/O Tester
Unpacking The Linux Kernel
Threaded I/O Tester
FFTW
Threaded I/O Tester
Hackbench
Threaded I/O Tester
FFTW
Rust Prime Benchmark
Threaded I/O Tester:
  Read - 128MB - 8
  Rand Write - 128MB - 8
OSBench
FFTW
IOzone:
  1MB - 4GB - Write Performance
  64Kb - 4GB - Write Performance
GnuPG
libjpeg-turbo tjbench
MBW:
  Memory Copy, Fixed Block Size - 512 MiB
  Memory Copy - 512 MiB
Threaded I/O Tester
OSBench
FFTW
t-test1
SVT-AV1
Sysbench
Hackbench
OSBench
FFTW
Threaded I/O Tester
OSBench
Threaded I/O Tester
FFTW:
  Stock - 2D FFT Size 512
  Float + SSE - 1D FFT Size 1024
Git
Threaded I/O Tester
FFTW
Smallpt
FFTW
IOzone
FFTW
Apache Siege
FFTW
Bullet Physics Engine
Threaded I/O Tester:
  Read - 64MB - 8
  Rand Write - 64MB - 8
  Write - 128MB - 4
Hackbench
Threaded I/O Tester
Hackbench:
  2 - Process
  1 - Thread
IOzone:
  1MB - 2GB - Read Performance
  64Kb - 2GB - Read Performance
Timed HMMer Search
IOzone
Threaded I/O Tester:
  Read - 64MB - 4
  Rand Write - 64MB - 4
  Rand Write - 32MB - 16
Multichase Pointer Chaser
FFTW
Multichase Pointer Chaser
IOzone
Multichase Pointer Chaser
IOzone
Multichase Pointer Chaser:
  256MB Array, 256 Byte Stride
  4MB Array, 64 Byte Stride
Rodinia
Parboil
NAS Parallel Benchmarks
Threaded I/O Tester:
  Read - 32MB - 8
  Rand Write - 32MB - 8
FS-Mark
Threaded I/O Tester
clpeak
PolyBench-C
Threaded I/O Tester
ctx_clock
Threaded I/O Tester
Tachyon
CoMD OpenCL
SVT-VP9
SVT-HEVC
Parboil:
  OpenCL TPACF
  OpenMP CUTCP
TSCP
System Libxml2 Parsing
clpeak
CloverLeaf
Threaded I/O Tester
MBW:
  Memory Copy, Fixed Block Size - 128 MiB
  Memory Copy - 128 MiB
AIO-Stress
IOzone
clpeak
System Libxml2 Parsing
IOzone:
  1MB - 512MB - Read Performance
  64Kb - 512MB - Read Performance
NAS Parallel Benchmarks
IOzone:
  4Kb - 512MB - Write Performance
  1MB - 512MB - Write Performance
  64Kb - 512MB - Write Performance
clpeak
Apache Siege
FS-Mark
System Libxml2 Parsing:
  850 KB
  1 MB
BLAKE2
System Libxml2 Parsing:
  950 KB
  600 KB
  900 KB
  400 KB
  800 KB
  500 KB
  750 KB
  700 KB
  650 KB
  550 KB
  450 KB
  350 KB
  300 KB
  250 KB
  200 KB
  100 KB
  150 KB
  50 KB
  5 KB
Phoronix Test Suite Self Test:
  Peak Memory Usage
  Merge Results
  Info Command
  Render Test
  List Suites
Bullet Physics Engine:
  Convex Trimesh
  Prim Trimesh
  136 Ragdolls
  1000 Convex
  1000 Stack
SciMark:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
LuaJIT:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
  Monte Carlo
Java SciMark:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
  Monte Carlo
Stream:
  Add
  Triad
  Scale
Compile Bench:
  Read Compiled Tree
  Initial Create
BlogBench