ltoize

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

HTML result view exported from: https://openbenchmarking.org/result/1910276-HV-LTOIZE49411&sor&grs.

ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDisplay ServerDisplay DriverVulkanCompilerFile-SystemScreen ResolutionO3O2 LTO GRAPHITE LTO GRAPHITE LTO GRAPHITE LTO GRAPHITEIntel 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 10.1ext41920x1080OpenBenchmarking.orgEnvironment Details- 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-vectorizeCompiler Details- --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 Disk Details- NONE / noatime,rwProcessor Details- Scaling Governor: intel_pstate performanceJava Details- OpenJDK Runtime Environment (IcedTea 3.12.0) (Gentoo icedtea-3.12.0)Python Details- Python 3.6.9Security Details- 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

apache-siege: 250apache-siege: 200build-llvm: Time To Compilec-ray: Total Time - 4K, 16 Rays Per Pixelbuild-imagemagick: Time To Compilescimark2: Compositescimark2: Dense LU Matrix Factorizationscimark2: Jacobi Successive Over-Relaxationbyte: Dhrystone 2fftw: Stock - 1D FFT Size 32scimark2: Sparse Matrix Multiplyllvm-test-suite: Time To Runpts-self-test: List Suitesebizzy: npb: FT.Bnpb: FT.Atiobench: Rand Read - 128MB - 4dbench: 48blender: Barbershop - CUDAdbench: 12apache-siege: 10fftw: Float + SSE - 1D FFT Size 32build-linux-kernel: Time To Compilemrbayes: Primate Phylogeny Analysisblender: Barbershop - OpenCLbullet: 1000 Stacktiobench: Rand Read - 256MB - 4dcraw: RAW To PPM Image Conversionfftw: Stock - 1D FFT Size 128pts-self-test: Info Commandtiobench: Write - 32MB - 32fftw: Stock - 2D FFT Size 128dbench: 6tinymembench: Standard Memsetcpp-perf-bench: Ctypefs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizehmmer: Pfam Database Searchfs-mark: 1000 Files, 1MB Sizefftw: Stock - 2D FFT Size 2048tiobench: Read - 128MB - 16tiobench: Rand Read - 256MB - 8ttsiod-renderer: Phong Rendering With Soft-Shadow Mappingfftw: Stock - 2D FFT Size 4096tiobench: Write - 128MB - 8apache-siege: 100fftw: Stock - 2D FFT Size 1024schbench: 2 - 16fftw: Stock - 2D FFT Size 512tiobench: Write - 32MB - 16sockperf: Latency Ping Pongtiobench: Write - 256MB - 4iozone: 4Kb - 8GB - Read Performanceiozone: 1MB - 512MB - Read Performanceiozone: 4Kb - 4GB - Read Performancefftw: Float + SSE - 1D FFT Size 128perl-benchmark: Interpretersockperf: Latency Under Loadosbench: Create Threadstiobench: Write - 64MB - 8schbench: 2 - 8mbw: Memory Copy - 512 MiBmbw: Memory Copy - 128 MiBfftw: Stock - 2D FFT Size 256scimark2: Fast Fourier Transformtiobench: Rand Read - 64MB - 4sunflow: Global Illumination + Image Synthesismbw: Memory Copy - 4096 MiBmbw: Memory Copy - 8192 MiBmbw: Memory Copy - 1024 MiBbullet: 3000 Falltiobench: Rand Write - 64MB - 4mbw: Memory Copy, Fixed Block Size - 8192 MiBmbw: Memory Copy, Fixed Block Size - 4096 MiBiozone: 64Kb - 2GB - Write Performancembw: Memory Copy, Fixed Block Size - 1024 MiBiozone: 64Kb - 4GB - Write Performancetinymembench: Standard Memcpyiozone: 1MB - 8GB - Read Performancefftw: Stock - 1D FFT Size 512tiobench: Rand Write - 32MB - 4mbw: Memory Copy, Fixed Block Size - 512 MiBnpb: LU.Agraphics-magick: HWB Color Spacehackbench: 1 - Threadtiobench: Rand Write - 256MB - 4iozone: 1MB - 4GB - Read Performanceosbench: Create Processesschbench: 4 - 8osbench: Launch Programsfftw: Stock - 1D FFT Size 256t-test1: 1dacapobench: H2schbench: 2 - 6schbench: 6 - 2iozone: 1MB - 2GB - Read Performancerbenchmark: blender: Barbershop - CPU-Onlyiozone: 4Kb - 2GB - Read Performanceschbench: 6 - 4schbench: 4 - 2graphics-magick: Rotatembw: Memory Copy, Fixed Block Size - 128 MiBiozone: 4Kb - 4GB - Write Performancenumpy: bullet: 136 Ragdollstiobench: Rand Read - 32MB - 4iozone: 64Kb - 8GB - Write Performancesystem-libxml2: 500 KBschbench: 2 - 2aobench: 2048 x 2048 - Total Timetiobench: Rand Write - 128MB - 4graphics-magick: Resizingencode-opus: WAV, Opus Encode, Opus Decodegraphics-magick: Swirlctx-clock: Context Switch Timetiobench: Rand Read - 128MB - 8sudokut: Total Timetiobench: Write - 256MB - 16tiobench: Write - 64MB - 32tiobench: Write - 256MB - 8parboil: OpenMP MRI Griddinghackbench: 1 - Processsystem-libxml2: 112 MBtiobench: Write - 64MB - 16iozone: 64Kb - 512MB - Read Performancesystem-libxml2: 750 KBtiobench: Write - 128MB - 32system-libxml2: 400 KBiozone: 4Kb - 8GB - Write Performancetiobench: Write - 32MB - 8himeno: Poisson Pressure Solvertiobench: Write - 64MB - 4graphics-magick: Enhancedschbench: 6 - 6iozone: 4Kb - 2GB - Write Performanceswet: Averagetachyon: Total Timedacapobench: Tradesoapiozone: 4Kb - 512MB - Read Performanceschbench: 4 - 32clomp: Static OMP Speedupbullet: Convex Trimeshgraphics-magick: Noise-Gaussiantiobench: Write - 128MB - 16radiance: SMP Parallelsystem-libxml2: 150 KBsystem-libxml2: 900 KBiozone: 1MB - 8GB - Write Performancesockperf: Throughputschbench: 16 - 2ramspeed: Copy - Floating Pointtiobench: Rand Write - 32MB - 8graphics-magick: Sharpenjava-scimark2: Compositesysbench: CPUschbench: 8 - 2mcperf: Deleteschbench: 32 - 32luajit: Fast Fourier Transformtiobench: Rand Read - 128MB - 32npb: BT.Ablender: Classroom - CUDAsystem-libxml2: 2 MBiozone: 1MB - 512MB - Write Performancesystem-libxml2: 800 KBsystem-libxml2: 250 KBtiobench: Rand Read - 32MB - 8cpp-perf-bench: Rand Numbersschbench: 6 - 16tiobench: Rand Read - 64MB - 32tiobench: Rand Read - 256MB - 32git: Time To Complete Common Git Commandsminion: Solitaireschbench: 4 - 4schbench: 8 - 16system-libxml2: 1 MBsystem-libxml2: 700 KBschbench: 4 - 6system-libxml2: 350 KBramspeed: Average - Integersystem-libxml2: 100 KBiozone: 64Kb - 8GB - Read Performancefs-mark: 5000 Files, 1MB Size, 4 Threadsramspeed: Scale - Integerschbench: 6 - 32blogbench: Readramspeed: Add - Integersystem-libxml2: 3 MBaio-stress: Rand Writeramspeed: Add - Floating Pointramspeed: Average - Floating Pointschbench: 6 - 24system-libxml2: 450 KBfftw: Float + SSE - 2D FFT Size 1024iozone: 4Kb - 512MB - Write Performanceiozone: 1MB - 2GB - Write Performancefftw: Float + SSE - 2D FFT Size 256schbench: 32 - 16ramspeed: Copy - Integerramspeed: Triad - Floating Pointdacapobench: Tradebeanstiobench: Read - 32MB - 32system-libxml2: 650 KBsystem-libxml2: 600 KBphpbench: PHP Benchmark Suitesystem-libxml2: 850 KBtiobench: Rand Read - 32MB - 32ramspeed: Triad - Integerapache-siege: 50iozone: 64Kb - 4GB - Read Performanceluajit: Dense LU Matrix Factorizationramspeed: Scale - Floating Pointunpack-linux: linux-4.15.tar.xztiobench: Write - 128MB - 4fftw: Float + SSE - 1D FFT Size 1024iozone: 64Kb - 2GB - Read Performancecompress-lzma: 256MB File Compressionfftw: Float + SSE - 2D FFT Size 2048blender: Classroom - OpenCLdbench: 128system-libxml2: 300 KBiozone: 1MB - 4GB - Write Performanceschbench: 16 - 24fftw: Float + SSE - 2D FFT Size 512schbench: 8 - 4tscp: AI Chess Performancesystem-libxml2: 950 KBmultichase: 4MB Array, 64 Byte Strideschbench: 16 - 16schbench: 16 - 8schbench: 32 - 24parboil: OpenMP Stencilasmfish: 1024 Hash Memory, 26 Depthcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9tiobench: Write - 256MB - 32dbench: 256schbench: 32 - 8fftw: Float + SSE - 1D FFT Size 4096lzbench: XZ 0 - Compressiontiobench: Rand Write - 64MB - 8postmark: Disk Transaction Performancedbench: 1fftw: Float + SSE - 1D FFT Size 512hackbench: 16 - Threadmcperf: Appendhackbench: 8 - Processbullet: Prim Trimeshmcperf: Replacetiobench: Read - 32MB - 4blender: Fishy Cat - CUDApts-self-test: Total Timetiobench: Rand Write - 256MB - 8npb: LU.Cpolybench-c: 3 Matrix Multiplicationstiobench: Read - 128MB - 4compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19iozone: 64Kb - 512MB - Write Performancemultichase: 1GB Array, 256 Byte Stridesysbench: Memoryschbench: 4 - 24schbench: 32 - 4tiobench: Rand Write - 128MB - 8schbench: 6 - 8multichase: 256MB Array, 256 Byte Stridesystem-libxml2: 550 KBschbench: 8 - 32hackbench: 8 - Threadcompilebench: Read Compiled Treeschbench: 2 - 24pts-self-test: Merge Resultstiobench: Write - 32MB - 4blender: Pabellon Barcelona - CUDAosbench: Memory Allocationsgo-benchmark: httppts-self-test: Render Testmcperf: Setosbench: Create Filestiobench: Read - 64MB - 4comd-cl: Average Atom Update Ratecompress-gzip: Linux Source Tree Archiving To .tar.gzblender: BMW27 - OpenCLblender: BMW27 - CUDAcloverleaf: Lagrangian-Eulerian Hydrodynamicsmcperf: Getcython-bench: espeak: Text-To-Speech Synthesisbullet: 1000 Convexcpp-perf-bench: Math Libraryhackbench: 4 - Threadpybench: Total For Average Test Timesluajit: Compositesvt-hevc: 1080p 8-bit YUV To HEVC Video Encodem-queens: Time To Solveschbench: 16 - 32tiobench: Rand Write - 64MB - 16tiobench: Read - 256MB - 8blender: Fishy Cat - OpenCLfs-mark: 1000 Files, 1MB Size, No Sync/FSyncschbench: 2 - 4apache: Static Web Page Servingcompilebench: Initial Createjava-scimark2: Dense LU Matrix Factorizationfftw: Float + SSE - 1D FFT Size 2048dacapobench: Eclipsenpb: SP.Asvt-av1: 1080p 8-bit YUV To AV1 Video Encodeglibc-bench: tanhschbench: 8 - 24mcperf: Prependmcperf: Addclpeak: Kernel Latencyblender: Pabellon Barcelona - OpenCLhackbench: 16 - Processcompress-7zip: Compress Speed Testtiobench: Read - 32MB - 8blogbench: Writetiobench: Rand Write - 128MB - 32apache-siege: 1system-libxml2: 200 KBx265: H.265 1080p Video Encodingtiobench: Rand Write - 32MB - 32node-octane: encode-flac: WAV To FLAChint: DOUBLEcompilebench: Compilehackbench: 2 - Threadschbench: 32 - 6hackbench: 4 - Processbotan: AES-256 - Decrypttiobench: Rand Write - 128MB - 16perl-benchmark: Pod2htmltiobench: Rand Write - 256MB - 16hint: FLOATstockfish: Total Timerodinia: OpenMP CFD Solverstream: Scalefhourstones: Complex Connect-4 Solvinggnupg: 2GB File Encryptiontiobench: Read - 128MB - 8network-loopback: Time To Transfer 10GB Via Loopbackdacapobench: Jythont-test1: 2fftw: Float + SSE - 2D FFT Size 128rodinia: OpenMP LavaMDclpeak: Single-Precision Floattiobench: Read - 64MB - 32minion: Quasigrouptiobench: Rand Write - 32MB - 16mpcbench: Multi-Precision Benchmarklzbench: Brotli 0 - Compressiontiobench: Read - 256MB - 4fftw: Float + SSE - 2D FFT Size 4096tiobench: Read - 128MB - 32tiobench: Read - 64MB - 8tiobench: Rand Write - 256MB - 32tiobench: Read - 256MB - 32tiobench: Rand Write - 64MB - 32hackbench: 32 - Processbork: File Encryption Timerodinia: OpenCL Myocytesvt-vp9: 1080p 8-bit YUV To VP9 Video Encoderadiance: Serialhackbench: 2 - Processbotan: AES-256 - Encryptparboil: OpenCL BFSencode-wavpack: WAV To WavPackbotan: Twofish - Decryptbotan: CAST-256 - Decryptbotan: CAST-256 - Encryptcpp-perf-bench: Function Objectslzbench: Zstd 1 - Compressionmultichase: 1GB Array, 256 Byte Stride, 2 Threadssmallpt: Global Illumination Renderer; 128 Samplesrodinia: OpenCL Heartwallblender: Fishy Cat - CPU-Onlymultichase: 1GB Array, 256 Byte Stride, 4 Threadsscikit-learn: glibc-bench: sinclpeak: Integer Compute INTgo-benchmark: buildglibc-bench: ffsllglibc-bench: ffsy-cruncher: Calculating 500M Pi Digitsparboil: OpenCL TPACFsample-program: go-benchmark: jsonluajit: Monte Carloblender: BMW27 - CPU-Onlyparboil: OpenMP CUTCPstream: Addglibc-bench: pthread_oncetjbench: Decompression Throughputjava-gradle-perf: Reactorblender: Classroom - CPU-Onlyxsbench: parboil: OpenMP LBMopenssl: RSA 4096-bit Performancelzbench: Zstd 1 - Decompressionlzbench: Libdeflate 1 - Decompressionglibc-bench: sqrtgmpbench: Total Timeblender: Pabellon Barcelona - CPU-Onlygo-benchmark: garbagenamd-cuda: ATPase Simulation - 327,506 Atomsrodinia: OpenCL Particle Filtercrafty: Elapsed Timeluajit: Sparse Matrix Multiplylzbench: Brotli 0 - Decompressionstream: Copyclpeak: Transfer Bandwidth enqueueReadBufferrust-prime: Prime Number Test To 200,000,000stream: Triadcpp-perf-bench: Atolglibc-bench: coscpp-perf-bench: Stepanov Abstractionprimesieve: 1e12 Prime Number Generationjava-scimark2: Sparse Matrix Multiplyparboil: OpenCL LBMnamd: ATPase Simulation - 327,506 Atomsclpeak: Transfer Bandwidth enqueueWriteBuffercpp-perf-bench: Stepanov Vectorbotan: KASUMI - Decryptcachebench: Writerust-mandel: Time To Complete Serial/Parallel Mandelbrotjava-scimark2: Jacobi Successive Over-Relaxationluajit: Jacobi Successive Over-Relaxationcachebench: Readbotan: KASUMI - Encryptcachebench: Read / Modify / Writepts-self-test: Peak Memory Usageclpeak: Global Memory Bandwidthclpeak: Double-Precision Doublesystem-libxml2: 50 KBsystem-libxml2: 5 KBbotan: Blowfish - Decryptbotan: Blowfish - Encryptbotan: Twofish - Encryptbyte: Floating-Point Arithmeticbyte: Register Arithmeticbyte: Integer Arithmeticjava-scimark2: Monte Carloblake2: lzbench: Libdeflate 1 - Compressionlzbench: XZ 0 - Decompressionschbench: 4 - 16schbench: 32 - 2schbench: 2 - 32schbench: 16 - 6schbench: 16 - 4schbench: 8 - 8schbench: 8 - 6compress-rar: Linux Source Tree Archiving To RARredis: SETredis: GETredis: LPUSHredis: SADDredis: LPOPjava-scimark2: Fast Fourier Transformfftw: Float + SSE - 1D FFT Size 256fftw: Float + SSE - 2D FFT Size 64fftw: Float + SSE - 2D FFT Size 32fftw: Float + SSE - 1D FFT Size 64fftw: Stock - 1D FFT Size 4096fftw: Stock - 1D FFT Size 2048fftw: Stock - 1D FFT Size 1024fftw: Stock - 2D FFT Size 64fftw: Stock - 2D FFT Size 32fftw: Stock - 1D FFT Size 64rodinia: OpenMP Streamclusternpb: EP.Ctiobench: Rand Read - 256MB - 16tiobench: Rand Read - 128MB - 16tiobench: Rand Read - 64MB - 16tiobench: Rand Read - 32MB - 16tiobench: Rand Read - 64MB - 8tiobench: Read - 256MB - 16tiobench: Read - 64MB - 16tiobench: Read - 32MB - 16O3O2 LTO GRAPHITE LTO GRAPHITE LTO GRAPHITE LTO GRAPHITE3398912210147725.7213.13230839822222599407861190726412200.715839841258812175401979114377226962547821789734.2657.967294.5080329010.47112911.475731116944232212034.289433.389787962579501396513789699124638006959615296334153.26167455865944458239160.0009273728.8511.472571348772901696495762002880.778671864886863.83181468789881512258884120993866889908891188720465363072.4471510668222.8112326.991071915.73352412711265440.448744042461131102848697107950952642.39105017123627611827.30360612978.072806417545549.473084452361082.355238834869442664022231088299342418424911310878385873731.8926094139487891.700.9724131419550323123152234810533099150832322242422591051149122718725061577352554824811291240280851932399933212879817731291394.7064.55117443953602411191233176161749715273147575477388626231822167939833111031700548911592393311021226249671693873308430932247164401229327749663465409933306163381671673748315755.16174611027072214205172501260810912261362772487211114494193378.5596981400852178565.776269307216.723841239889557556224029757609710664960023.667875012.220.8278980163421243127118828422992.64161258.97122067.71198819093351537867596811268862.601909868815.762729130292.9820281780.18358033.127644817.16161802.6833.723813811.6311311722.6525.683.872796.971215157335837.121721173477032765122425661223875556450216133616667393055.0310.687573378756769154.7582722.53117979313114091468265138897256.4617283513459.1396604451624064.02520756.533844692790.104484591384584369630125785779710.4652256152406.173239910.8028685.543053213.30362967822100173841030041916400182766930431607138042715773458643.398.5747.253816423.8338471.316.5239714614613.3245068.674.503.0115270.3616144.681162165890109511.721.7210.641.809.06234273854990.731.91579491.9519719.66201605318947.516067113111552.4056092466226520.3388912.6188161711408618747206.416.475891958.9645.2232.3810.04255822.060.898056.1183.1695.383117841.9516031654372596.525079750014514416229529640111110853.38248106180577574230922289710553141651075768.141740022233750014226282043649255959494235307378254398218619106729326110689715110151023211.09251523223611258276623268315850371220571055367751196359153995947525.7113.03170351742223598479811135026921830.705873321265211916398632111437226174496691865334.0450.546664.5880276810.55113411.465301184541172344934.909883.4010068017576141460025793701023739402946716097834023.35166436669064364234830.0009221627.9011.702631308746903498255852074340.808776910487133.89182289132916412289230123091597246924291809064480453072.4472665700922.6712026.521049315.42339812811267360.445844142211111162829041110851435642.42105877122327311727.29361852967.922796417467609.553114422361052.385146735072062614032181083300340018324811611068532906161.9126064263489171.690.9724132520349319125552794110432745152032322250436931091142172746035161620539562624811171199275841927029593152079804331638204.6365.62118455043552371211193147760751815263114076160386583531570167639843090731414549251562446810741238255091692163311430677253363961226323758170456411027304183379472273812316435.12173616937243214207282461253810712411347412493910914524753298.5394421397872180275.736360094916.823851241988192558454030041614810615000723.487778212.180.8378114164111244127118725431772.67161428.96120867.53198890243381337227600711265662.121899800515.752683130193.0020581978.90356133.067643117.07161792.6833.823773791.6311382422.3325.703.912786.911226158935737.091719473419132748120825401233854156450646083316585393555.4410.697556379349769624.7681522.78118132311644109468659140197256.5717086512179.1595358737523893.99516056.563870691300.105050381384494346994605798141510.4252103152326.133235610.8528615.593073913.30361267506100173131030041516329184216890431704137228713023430043.348.5546.953806383.8438391.306.5139914614613.3244968.654.513.0215170.1316044.671161166496392861.721.7210.631.809.06233641255190.411.92579341.9519719.73201604415147.606054113011542.4056162466210950.3394412.6588294031411618747206.426.475882458.8645.2232.3910.03255322.080.896636.1083.1995.423117741.9616031654372596.525079350014514416229529640111110853.38248106183178178239312322110881134791147868.1116051142315232153297919158842408656943337113967940773192241058411284105889817111121020710.80249723573951211522635045331940378003559205610851224359793342819225.7317.22261259132224441063771500233551880.69526045152781430140371297487276059494071787633.9758.147304.1483604810.42118711.535921096040562152231.899703.559467517581671522336803649524841310899915190534293.12166465868594500237160.0009259226.8911.942631309344960492245952031990.789216918192073.74180679223925712299328126197127275912791289147475813062.5271597707422.6212727.301026415.44341012411169080.451644244091101142849144106850145052.34104054126727211827.18366502968.132796417398819.743074582351052.415170235972642644102181107293329718624911711088423785211.9125464272505391.691.0024132720050321125651822410434029150272322273422831061107072715315231618376543024911231238279841952179893240581410831864994.7565.48121449073582391221203253160764815333216477440378135132591167039883180832423552751572396710961243247881697283388831640245665915228323748357456411191311893432673843837322965.08174624977240214206002491226110812511373012477111014137033318.6095531405972228055.656403326917.163901238488107565693929883619910414959423.657870712.220.8478940162041242127117773425262.70161309.09122768.69198346593307737824599741263561.7518910005315.442702130192.9920181380.29353932.857620617.13161422.7133.333843811.6211239722.3025.813.932806.871208159535937.721722883455832787122425581233818955950476110716588396655.2810.687462478549759294.7682022.74118640313534109369063139567256.3417110513469.1895882402423763.99520326.533846689350.104505171380184325290265819249010.5452280152636.203251410.7828375.553074713.34363667312101173201030041516397182526919931583137689713913434643.398.5746.953816393.8338541.316.5439714614613.2445068.694.483.0115270.1816144.681164166871636641.721.7310.631.809.06233539955190.491.92580911.9519719.70201604951747.466080113011552.4156162466224120.3382012.6088176391409617747906.436.465892658.8945.2332.4510.04255822.070.898236.1083.1095.393117941.9516031654372596.525080450014514416229529640111110853.38248106172867489220202329010968146831106768.20187398824706301543733219462427908331074333373968940046190631007010208104329057136221408711.70268225931781191378651278336770387137542375661953618533603987019225.7117.03251556032223450172401505531981890.774845391529214275398950113126246803492841826933.6550.736364.0577104010.36119191.475821089340622260931.759653.499667489579841435245793659124639041886714892203973.34167441864224430242660.0009234528.1311.132631258730900492945811994630.818655862986893.66173178780880812428875124791766861946887168735493013042.3872275668322.9712426.281042415.47334013011067050.447444144171141132838683107649829862.31101173125427412026.94366992958.122786407248279.723094562361092.415249334471822654072211104287327618024711511018499277781.9526344097489601.740.9924132520050323125053560910532778149512312268438661051138362817715111603673553025011221228280851890839883252380225331382604.7265.15119444373602411231213150060751215633118976331387892931593168440513081731458560431582465410831205250281685333285430742249365863229325754742459414306302673433672583750313605.06170608147070210205732511250210812251369602509311214151553338.6994933404692190515.776341499317.023861236390155553374029516614810484979823.977877812.200.8479380160251229127119458432702.65161299.02123567.70196451963325937141588671277362.231909937115.522674130193.0320281580.37357332.857552917.07162342.6933.653803781.6411352822.3325.693.902786.961208157535837.721728003458932716122725591223838656150106058016501399054.6310.847496579023758444.7682022.66118713311504146669248138897256.1517102513639.2095641557623954.00516056.543846692450.105060501379454332586115841866310.4552111152416.183245110.7928495.573065213.39361867728101172581020041616416184156955031733137730712963442343.438.5447.063796393.8438551.306.5439614614613.2644868.824.513.0215270.2616044.921165166290206721.731.7310.621.809.06233753655190.461.92580351.9619619.68201603046247.546056113211552.4156162466235590.3389312.6088168481408617747556.436.475886858.8345.2332.4510.04255822.080.897956.1083.0895.423117841.9816031654372596.525080050014514416229529640111110853.38248106179777216240962319610794129871107568.0616375392371908162064519165202446730108234406371354009418880986610837101428918136601288011.25270924934721250589636360328113365436593485698550689344603634447842.9410.55196340511564607173151262426382160.735922721262312090408492113667266854498421790938.6458.186634.4879350311.11107961.585791150041632132334.969943.709948116561851417787856682024439720947114896764013.34167432964214187246100.0009341727.1411.402561309324944498375602035260.769195909392413.80173558891873012268796123392597174893186608629470163222.4370169697223.3912127.251063515.78333412811168980.463044243841161142979011108849673422.38102842125728611928.22356053108.192926677444699.943074542381052.335389134769622734092261073296340817825811610918432627961.8926224148497711.700.9625132020251329122953285110632882148702402224438671081122972762755041626213549224911521243285871928419933263479355532133374.7366.76119447793662451221233161262742515463135876587381914731660171739793099931521562561612449011001213249651695573288330796251063921233333758399470404674304623480872053725314625.16174623517038208204042501256311012171376432506011014494233388.6394421401282216115.706263135216.963901239188755551343929294625010615032123.607895012.480.8280017161531229128116742425922.69157849.07122167.19194922223342937952601411265661.401929894415.632674132853.0220382079.79354433.067612317.24160992.7333.953803851.6511386022.6025.683.862836.971212156835337.131714353463432669122825681213862855950656040816556393955.0110.707539279528768354.7782522.74118911310184087368985140867356.4317318510809.1795665172223813.97515206.593881694680.105294371395964318218845794189510.4752175150906.203233510.7328585.573046113.42363867727101173541023341716381183806921031647137183712133451943.238.5547.043786413.8538691.316.5639814614513.3244769.114.503.0015269.9016144.681168166363547961.731.7310.611.809.11234430355290.601.91579581.9619719.69201602900547.516068112711502.4155932476210510.3390512.6388326931407616747436.436.485890258.9245.2332.3810.03255722.100.897586.1183.1695.433117741.9516041653372596.535079550014514416229529640111110853.38248106186337326239912334510936143361111868.121670885238313616203891927131247607181035309374173841218955104189881112009889111341017511.212449248184312308646382223344583793495909055233543861224414054647342.9310.55235456821565598721981234029151850.725865331265812075397741113357227042494551853638.7650.537124.5282087311.46111401.475701161144842352634.279843.729648045580851461562856703022938871950015097484043.31157449566594222241210.0009241528.5111.232481299299957197875772042390.789168914592153.82183878692872712789186128295866945915088589116481423212.4472618675022.7012626.421078316.30345912810666100.461144341881141122959082112452277372.39104494128628212328.20358753098.192916417391219.893054372301102.445356534372562723922281122289341217925711711208223049721.9125264246489601.720.9724932119951328125353103110433462146322392308438571061110692797235121628043563125311581201284861925109593205381753032078644.6764.70117440113652441191233199262767215153134075477383119432059172441013120631951557441612433210681233254321680213357531066247365349232332738154467412802307623464872963829318795.12169618557180209209882531231611012421384962499310914501843388.5096811402562195635.796338947516.833831214290411558494029780619910655035723.637721312.270.8278935162911220130118726432422.70160948.89122367.72196542843364337824592441250761.881939911515.512728130193.0420382378.83360833.497611017.00161342.7233.863813811.6311294022.5525.353.902796.991208159235337.101709233440932296122425821233820156850906064616416397754.9110.697573378372758444.7682322.84119702309054104568789140857356.8717142510099.1795420372724034.00516486.583882686420.105738191383204353722185854492810.4252701152636.183215210.7628465.573069213.44361467887101173641020041716261184256927731449137313709633439943.448.6147.053786373.8438591.316.5439814614513.3345068.974.503.0015170.2016144.701163166189705741.721.7210.581.799.06233451255190.241.91577921.9519719.63202602326747.546075113011552.4056022466231880.3380812.6088232651412617745576.426.475899058.8845.3232.3910.04255822.080.896956.1083.1495.333115541.9716031654372496.495079350014514416229529640111110853.38248106192198213236892403610798132191098868.06163795324130161565614219324123944271203345993869639837192691022510093105269950112481040911.40249624538431241428639169320411379322559365289251338333724313218242.9715.58238656431568439307461497131831890.85530223152321435240358098086526071473491616633.9158.187134.0574008211.70117951.565801075940742209831.949033.669177497531441444608860645324938571923414991254173.26167441764984311229220.0009212028.7411.282661318862910292665681945830.808723869987433.66177499010893712268901123393346907902590488829475813212.4468632668523.0312327.651019915.43344112310866550.461044243161121102958792110949784342.30100686125127712128.32349223108.152916417381839.803044472341092.345238435571422663972221102298329218125811410868337133601.8725264161484911.670.9925032220150324122353909810533592148812392310422471061122352782725111636485544924911341215281861885259893211780845232385804.7965.33120446083672451191223220661747415133189577952384023832290168440403155932163557871592469610881232255521733123359231319248663921231328759979464417010310263435472113751320305.15172625867046210207282471226410912471361072545810914144293348.4695275399572199045.806428716916.913901210288875564454029699614810404926423.907911912.300.8379352160751230130119129427022.70160258.98123067.94195028323324837781597851263562.021909928515.542692130513.0320482979.09356633.267697317.11159332.6933.593813841.6411179822.7125.753.912786.881205157635437.701734833460332243121725741213814056150806110116434396454.6210.697564878873761794.8281622.86119307309034141069081138897356.1017161509549.1695359109823834.00516056.613879688570.104608991384194329620675792911510.4352295151586.193217610.8528545.533049313.30364967630101173191020041716280183176942731454137732713353451743.598.5847.093806373.8638641.306.5539814514613.2444868.794.493.0215270.0216144.651167166317122821.721.7210.591.809.06233146055190.481.92580561.9519719.67201604160547.576061113111552.4056062466229560.3387212.6088163171411618746936.436.475889258.9945.2232.4510.04255822.100.896636.1083.0995.423117741.9616031654372596.505079450014514416229529640111110853.38248106195097732232902332810459134941119368.2217704652495376175062619230672400678122334465371124032719061106429486104139646117311199010.83269525302701294356644903339063380026553525264353941364463341218042.9915.38238756391567450807361507831981770.725545761527514441347632112826776614513201801833.6750.656914.1477771911.48121071.415791067440522214731.749453.669477399578251490269849645824639625892815191254143.37169447767714350235800.0008704728.2111.182611289244950393585582017210.809128909791253.76181929127916312059152121395566961925790879055486673202.4670199702922.1012526.151035615.52335312710968810.470342043161111132959021109950675152.35103102123027511728.31363243108.322916727188269.843194522411082.395389034671792654072251093290328418425811810748575115671.9226284171490031.711.0025132420050332120752996010233560149402402297422471071120242739205181615437554424411361207280851901349903180882145431805254.6965.93119443523662411221233211961761515193209175563376397932200172239733154632076545071582416210831222255691690453368731348249464631230332737312467414131309523482073463739319635.21172610737163214207092511251210912321376432504311114144293338.5296981395312236595.776337912617.053801240089728553864029711609710415049123.397845312.210.8478645161691215129118859432512.68160639.04121168.11194557983324837952595131266762.701899826115.512701132753.0020582379.79358333.307633716.92161352.6933.613813841.6411196022.5925.613.932786.891210157435437.711738243473632575121625561223842356550346059816510393755.1910.707547778449768124.7982022.73119324313314133168738139567256.4317247506969.2595577755723973.97514356.593891693070.105101421388244330452505790002310.5352285152476.203229810.8128395.553079113.32361767994101172121020041716320183416953631653136808712703454143.408.5646.873796383.8338621.306.5539814614613.2644968.674.503.0015269.9216144.901163166774884031.731.7310.621.809.06233855455190.671.92580911.9619719.71201602571047.686052113111552.4155932466213100.3392512.6188488021408616747696.426.475891158.9945.2332.4210.02255822.090.897276.1183.0995.433117541.9616031653372696.545080350014514416229529640111110853.38248106184907907252272315711232143141096268.1816563332458302176028119358182313264120735459360304098718815101709960104049291112671378011.84271525352561299985631416341106390904570325289051885OpenBenchmarking.org

Apache Siege

Concurrent Users: 250

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

Apache Siege

Concurrent Users: 200

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

Timed LLVM Compilation

Time To Compile

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

C-Ray

Total Time - 4K, 16 Rays Per Pixel

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

Timed ImageMagick Compilation

Time To Compile

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

SciMark

Computational Test: Composite

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

SciMark

Computational Test: Dense LU Matrix Factorization

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

SciMark

Computational Test: Jacobi Successive Over-Relaxation

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

BYTE Unix Benchmark

Computational Test: Dhrystone 2

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

FFTW

Build: Stock - Size: 1D FFT Size 32

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

SciMark

Computational Test: Sparse Matrix Multiply

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

LLVM Test Suite

Time To Run

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++

Phoronix Test Suite Self Test

Test: List Suites

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

ebizzy

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

NAS Parallel Benchmarks

Test / Class: FT.B

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

NAS Parallel Benchmarks

Test / Class: FT.A

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 128MB - Thread Count: 4

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

Dbench

Client Count: 48

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

Blender

Blend File: Barbershop - Compute: CUDA

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

Dbench

Client Count: 12

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

Apache Siege

Concurrent Users: 10

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

Build: Float + SSE - Size: 1D FFT Size 32

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

Timed Linux Kernel Compilation

Time To Compile

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

Timed MrBayes Analysis

Primate Phylogeny Analysis

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

Blender

Blend File: Barbershop - Compute: OpenCL

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

Bullet Physics Engine

Test: 1000 Stack

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 256MB - Thread Count: 4

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

dcraw

RAW To PPM Image Conversion

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

FFTW

Build: Stock - Size: 1D FFT Size 128

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

Phoronix Test Suite Self Test

Test: Info Command

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

Threaded I/O Tester

Test: Write - Size Per Thread: 32MB - Thread Count: 32

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

FFTW

Build: Stock - Size: 2D FFT Size 128

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

Dbench

Client Count: 6

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

Tinymembench

Standard Memset

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

CppPerformanceBenchmarks

Test: Ctype

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

FS-Mark

Test: 4000 Files, 32 Sub Dirs, 1MB Size

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

Timed HMMer Search

Pfam Database Search

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

FS-Mark

Test: 1000 Files, 1MB Size

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

FFTW

Build: Stock - Size: 2D FFT Size 2048

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

Threaded I/O Tester

Test: Read - Size Per Thread: 128MB - Thread Count: 16

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 256MB - Thread Count: 8

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

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

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++

FFTW

Build: Stock - Size: 2D FFT Size 4096

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

Threaded I/O Tester

Test: Write - Size Per Thread: 128MB - Thread Count: 8

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

Apache Siege

Concurrent Users: 100

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

FFTW

Build: Stock - Size: 2D FFT Size 1024

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

Schbench

Message Threads: 2 - Workers Per Message Thread: 16

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

FFTW

Build: Stock - Size: 2D FFT Size 512

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

Threaded I/O Tester

Test: Write - Size Per Thread: 32MB - Thread Count: 16

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

Sockperf

Test: Latency Ping Pong

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

Threaded I/O Tester

Test: Write - Size Per Thread: 256MB - Thread Count: 4

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

IOzone

Record Size: 4Kb - File Size: 8GB - Disk Test: Read Performance

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

IOzone

Record Size: 1MB - File Size: 512MB - Disk Test: Read Performance

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

IOzone

Record Size: 4Kb - File Size: 4GB - Disk Test: Read Performance

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

FFTW

Build: Float + SSE - Size: 1D FFT Size 128

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

Perl Benchmarks

Test: Interpreter

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

Sockperf

Test: Latency Under Load

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

OSBench

Test: Create Threads

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

Threaded I/O Tester

Test: Write - Size Per Thread: 64MB - Thread Count: 8

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

Schbench

Message Threads: 2 - Workers Per Message Thread: 8

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

MBW

Test: Memory Copy - Array Size: 512 MiB

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

MBW

Test: Memory Copy - Array Size: 128 MiB

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

FFTW

Build: Stock - Size: 2D FFT Size 256

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

SciMark

Computational Test: Fast Fourier Transform

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 64MB - Thread Count: 4

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

Sunflow Rendering System

Global Illumination + Image Synthesis

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

MBW

Test: Memory Copy - Array Size: 4096 MiB

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

MBW

Test: Memory Copy - Array Size: 8192 MiB

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

MBW

Test: Memory Copy - Array Size: 1024 MiB

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

Bullet Physics Engine

Test: 3000 Fall

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

Test: Random Write - Size Per Thread: 64MB - Thread Count: 4

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

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB

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

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB

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

IOzone

Record Size: 64Kb - File Size: 2GB - Disk Test: Write Performance

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

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB

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

IOzone

Record Size: 64Kb - File Size: 4GB - Disk Test: Write Performance

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

Tinymembench

Standard Memcpy

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

IOzone

Record Size: 1MB - File Size: 8GB - Disk Test: Read Performance

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

FFTW

Build: Stock - Size: 1D FFT Size 512

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

Test: Random Write - Size Per Thread: 32MB - Thread Count: 4

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

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB

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

NAS Parallel Benchmarks

Test / Class: LU.A

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

GraphicsMagick

Operation: HWB Color Space

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

Hackbench

Count: 1 - Type: Thread

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 256MB - Thread Count: 4

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

IOzone

Record Size: 1MB - File Size: 4GB - Disk Test: Read Performance

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

OSBench

Test: Create Processes

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

Schbench

Message Threads: 4 - Workers Per Message Thread: 8

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

OSBench

Test: Launch Programs

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

Build: Stock - Size: 1D FFT Size 256

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

t-test1

Threads: 1

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

DaCapo Benchmark

Java Test: H2

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

Schbench

Message Threads: 2 - Workers Per Message Thread: 6

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

Schbench

Message Threads: 6 - Workers Per Message Thread: 2

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

IOzone

Record Size: 1MB - File Size: 2GB - Disk Test: Read Performance

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

R Benchmark

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

Blend File: Barbershop - Compute: CPU-Only

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

IOzone

Record Size: 4Kb - File Size: 2GB - Disk Test: Read Performance

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

Schbench

Message Threads: 6 - Workers Per Message Thread: 4

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

Schbench

Message Threads: 4 - Workers Per Message Thread: 2

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

GraphicsMagick

Operation: Rotate

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

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB

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

IOzone

Record Size: 4Kb - File Size: 4GB - Disk Test: Write Performance

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

Numpy Benchmark

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

Bullet Physics Engine

Test: 136 Ragdolls

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 32MB - Thread Count: 4

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

IOzone

Record Size: 64Kb - File Size: 8GB - Disk Test: Write Performance

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

System Libxml2 Parsing

Filesize: 500 KB

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

Schbench

Message Threads: 2 - Workers Per Message Thread: 2

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

AOBench

Size: 2048 x 2048 - Total Time

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 128MB - Thread Count: 4

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

GraphicsMagick

Operation: Resizing

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

Opus Codec Encoding

WAV, Opus Encode, Opus Decode

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

GraphicsMagick

Operation: Swirl

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

ctx_clock

Context Switch Time

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

Test: Random Read - Size Per Thread: 128MB - Thread Count: 8

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

Sudokut

Total Time

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

Threaded I/O Tester

Test: Write - Size Per Thread: 256MB - Thread Count: 16

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

Threaded I/O Tester

Test: Write - Size Per Thread: 64MB - Thread Count: 32

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

Threaded I/O Tester

Test: Write - Size Per Thread: 256MB - Thread Count: 8

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

Parboil

Test: OpenMP MRI Gridding

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

Hackbench

Count: 1 - Type: Process

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

System Libxml2 Parsing

Filesize: 112 MB

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

Threaded I/O Tester

Test: Write - Size Per Thread: 64MB - Thread Count: 16

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

IOzone

Record Size: 64Kb - File Size: 512MB - Disk Test: Read Performance

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

System Libxml2 Parsing

Filesize: 750 KB

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

Threaded I/O Tester

Test: Write - Size Per Thread: 128MB - Thread Count: 32

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

System Libxml2 Parsing

Filesize: 400 KB

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

IOzone

Record Size: 4Kb - File Size: 8GB - Disk Test: Write Performance

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

Threaded I/O Tester

Test: Write - Size Per Thread: 32MB - Thread Count: 8

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

Himeno Benchmark

Poisson Pressure Solver

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

Threaded I/O Tester

Test: Write - Size Per Thread: 64MB - Thread Count: 4

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

GraphicsMagick

Operation: Enhanced

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

Schbench

Message Threads: 6 - Workers Per Message Thread: 6

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

IOzone

Record Size: 4Kb - File Size: 2GB - Disk Test: Write Performance

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

Swet

Average

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

Tachyon

Total Time

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

DaCapo Benchmark

Java Test: Tradesoap

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

IOzone

Record Size: 4Kb - File Size: 512MB - Disk Test: Read Performance

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

Schbench

Message Threads: 4 - Workers Per Message Thread: 32

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

CLOMP

Static OMP Speedup

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

Bullet Physics Engine

Test: Convex Trimesh

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

GraphicsMagick

Operation: Noise-Gaussian

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

Threaded I/O Tester

Test: Write - Size Per Thread: 128MB - Thread Count: 16

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

Radiance Benchmark

Test: SMP Parallel

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

System Libxml2 Parsing

Filesize: 150 KB

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

System Libxml2 Parsing

Filesize: 900 KB

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

IOzone

Record Size: 1MB - File Size: 8GB - Disk Test: Write Performance

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

Sockperf

Test: Throughput

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

Schbench

Message Threads: 16 - Workers Per Message Thread: 2

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

RAMspeed SMP

Type: Copy - Benchmark: Floating Point

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 32MB - Thread Count: 8

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

GraphicsMagick

Operation: Sharpen

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

Java SciMark

Computational Test: Composite

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

Sysbench

Test: CPU

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

Schbench

Message Threads: 8 - Workers Per Message Thread: 2

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

Memcached mcperf

Method: Delete

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

Schbench

Message Threads: 32 - Workers Per Message Thread: 32

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

LuaJIT

Test: Fast Fourier Transform

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 128MB - Thread Count: 32

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

NAS Parallel Benchmarks

Test / Class: BT.A

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

Blend File: Classroom - Compute: CUDA

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

System Libxml2 Parsing

Filesize: 2 MB

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

Record Size: 1MB - File Size: 512MB - Disk Test: Write Performance

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

System Libxml2 Parsing

Filesize: 800 KB

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

System Libxml2 Parsing

Filesize: 250 KB

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 32MB - Thread Count: 8

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

CppPerformanceBenchmarks

Test: Random Numbers

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

Schbench

Message Threads: 6 - Workers Per Message Thread: 16

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 64MB - Thread Count: 32

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 256MB - Thread Count: 32

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

Git

Time To Complete Common Git Commands

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

Minion

Benchmark: Solitaire

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

Schbench

Message Threads: 4 - Workers Per Message Thread: 4

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

Schbench

Message Threads: 8 - Workers Per Message Thread: 16

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

System Libxml2 Parsing

Filesize: 1 MB

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

System Libxml2 Parsing

Filesize: 700 KB

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

Schbench

Message Threads: 4 - Workers Per Message Thread: 6

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

System Libxml2 Parsing

Filesize: 350 KB

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

RAMspeed SMP

Type: Average - Benchmark: Integer

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

System Libxml2 Parsing

Filesize: 100 KB

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

IOzone

Record Size: 64Kb - File Size: 8GB - Disk Test: Read Performance

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

Test: 5000 Files, 1MB Size, 4 Threads

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

RAMspeed SMP

Type: Scale - Benchmark: Integer

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

Schbench

Message Threads: 6 - Workers Per Message Thread: 32

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

BlogBench

Test: Read

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

RAMspeed SMP

Type: Add - Benchmark: Integer

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

System Libxml2 Parsing

Filesize: 3 MB

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

AIO-Stress

Test: Random Write

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

RAMspeed SMP

Type: Add - Benchmark: Floating Point

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

RAMspeed SMP

Type: Average - Benchmark: Floating Point

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

Schbench

Message Threads: 6 - Workers Per Message Thread: 24

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

System Libxml2 Parsing

Filesize: 450 KB

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

FFTW

Build: Float + SSE - Size: 2D FFT Size 1024

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

IOzone

Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance

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

IOzone

Record Size: 1MB - File Size: 2GB - Disk Test: Write Performance

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

FFTW

Build: Float + SSE - Size: 2D FFT Size 256

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

Schbench

Message Threads: 32 - Workers Per Message Thread: 16

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

RAMspeed SMP

Type: Copy - Benchmark: Integer

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

RAMspeed SMP

Type: Triad - Benchmark: Floating Point

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

DaCapo Benchmark

Java Test: Tradebeans

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

Threaded I/O Tester

Test: Read - Size Per Thread: 32MB - Thread Count: 32

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

System Libxml2 Parsing

Filesize: 650 KB

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

System Libxml2 Parsing

Filesize: 600 KB

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

PHPBench

PHP Benchmark Suite

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

System Libxml2 Parsing

Filesize: 850 KB

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 32MB - Thread Count: 32

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

RAMspeed SMP

Type: Triad - Benchmark: Integer

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

Apache Siege

Concurrent Users: 50

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

Record Size: 64Kb - File Size: 4GB - Disk Test: Read Performance

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

LuaJIT

Test: Dense LU Matrix Factorization

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

RAMspeed SMP

Type: Scale - Benchmark: Floating Point

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

Unpacking The Linux Kernel

linux-4.15.tar.xz

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

Test: Write - Size Per Thread: 128MB - Thread Count: 4

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

FFTW

Build: Float + SSE - Size: 1D FFT Size 1024

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

IOzone

Record Size: 64Kb - File Size: 2GB - Disk Test: Read Performance

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

LZMA Compression

256MB File Compression

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

FFTW

Build: Float + SSE - Size: 2D FFT Size 2048

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

Blender

Blend File: Classroom - Compute: OpenCL

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

Dbench

Client Count: 128

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

System Libxml2 Parsing

Filesize: 300 KB

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

IOzone

Record Size: 1MB - File Size: 4GB - Disk Test: Write Performance

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

Schbench

Message Threads: 16 - Workers Per Message Thread: 24

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

FFTW

Build: Float + SSE - Size: 2D FFT Size 512

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

Schbench

Message Threads: 8 - Workers Per Message Thread: 4

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

TSCP

AI Chess Performance

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

Filesize: 950 KB

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

Multichase Pointer Chaser

Test: 4MB Array, 64 Byte Stride

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

Schbench

Message Threads: 16 - Workers Per Message Thread: 16

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

Schbench

Message Threads: 16 - Workers Per Message Thread: 8

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

Schbench

Message Threads: 32 - Workers Per Message Thread: 24

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

Parboil

Test: OpenMP Stencil

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

asmFish

1024 Hash Memory, 26 Depth

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

XZ Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9

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

Test: Write - Size Per Thread: 256MB - Thread Count: 32

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

Dbench

Client Count: 256

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

Schbench

Message Threads: 32 - Workers Per Message Thread: 8

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

FFTW

Build: Float + SSE - Size: 1D FFT Size 4096

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

lzbench

Test: XZ 0 - Process: Compression

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 64MB - Thread Count: 8

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

PostMark

Disk Transaction Performance

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

Dbench

Client Count: 1

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

FFTW

Build: Float + SSE - Size: 1D FFT Size 512

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

Hackbench

Count: 16 - Type: Thread

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

Memcached mcperf

Method: Append

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

Hackbench

Count: 8 - Type: Process

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

Bullet Physics Engine

Test: Prim Trimesh

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

Memcached mcperf

Method: Replace

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

Threaded I/O Tester

Test: Read - Size Per Thread: 32MB - Thread Count: 4

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

Blender

Blend File: Fishy Cat - Compute: CUDA

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

Phoronix Test Suite Self Test

Test: Total Time

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 256MB - Thread Count: 8

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

NAS Parallel Benchmarks

Test / Class: LU.C

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

PolyBench-C

Test: 3 Matrix Multiplications

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

Test: Read - Size Per Thread: 128MB - Thread Count: 4

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

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

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

IOzone

Record Size: 64Kb - File Size: 512MB - Disk Test: Write Performance

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

Multichase Pointer Chaser

Test: 1GB Array, 256 Byte Stride

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

Sysbench

Test: Memory

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

Schbench

Message Threads: 4 - Workers Per Message Thread: 24

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

Schbench

Message Threads: 32 - Workers Per Message Thread: 4

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 128MB - Thread Count: 8

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

Schbench

Message Threads: 6 - Workers Per Message Thread: 8

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

Multichase Pointer Chaser

Test: 256MB Array, 256 Byte Stride

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

System Libxml2 Parsing

Filesize: 550 KB

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

Schbench

Message Threads: 8 - Workers Per Message Thread: 32

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

Hackbench

Count: 8 - Type: Thread

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

Compile Bench

Test: Read Compiled Tree

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

Schbench

Message Threads: 2 - Workers Per Message Thread: 24

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

Phoronix Test Suite Self Test

Test: Merge Results

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

Threaded I/O Tester

Test: Write - Size Per Thread: 32MB - Thread Count: 4

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

Blender

Blend File: Pabellon Barcelona - Compute: CUDA

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

OSBench

Test: Memory Allocations

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

Go Benchmarks

Test: http

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

Phoronix Test Suite Self Test

Test: Render Test

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

Memcached mcperf

Method: Set

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

OSBench

Test: Create Files

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

Threaded I/O Tester

Test: Read - Size Per Thread: 64MB - Thread Count: 4

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

CoMD OpenCL

Average Atom Update Rate

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

Gzip Compression

Linux Source Tree Archiving To .tar.gz

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

Blender

Blend File: BMW27 - Compute: OpenCL

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

Blender

Blend File: BMW27 - Compute: CUDA

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

CloverLeaf

Lagrangian-Eulerian Hydrodynamics

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

Memcached mcperf

Method: Get

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

Cython benchmark

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

eSpeak Speech Engine

Text-To-Speech Synthesis

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++

Bullet Physics Engine

Test: 1000 Convex

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

CppPerformanceBenchmarks

Test: Math Library

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

Hackbench

Count: 4 - Type: Thread

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

PyBench

Total For Average Test Times

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

LuaJIT

Test: Composite

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

SVT-HEVC

1080p 8-bit YUV To HEVC Video Encode

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

m-queens

Time To Solve

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

Schbench

Message Threads: 16 - Workers Per Message Thread: 32

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 64MB - Thread Count: 16

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

Threaded I/O Tester

Test: Read - Size Per Thread: 256MB - Thread Count: 8

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

Blender

Blend File: Fishy Cat - Compute: OpenCL

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

FS-Mark

Test: 1000 Files, 1MB Size, No Sync/FSync

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

Schbench

Message Threads: 2 - Workers Per Message Thread: 4

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

Apache Benchmark

Static Web Page Serving

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

Compile Bench

Test: Initial Create

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

Java SciMark

Computational Test: Dense LU Matrix Factorization

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

FFTW

Build: Float + SSE - Size: 1D FFT Size 2048

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

DaCapo Benchmark

Java Test: Eclipse

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

NAS Parallel Benchmarks

Test / Class: SP.A

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

SVT-AV1

1080p 8-bit YUV To AV1 Video Encode

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

glibc bench

Benchmark: tanh

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

Schbench

Message Threads: 8 - Workers Per Message Thread: 24

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

Memcached mcperf

Method: Prepend

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

Memcached mcperf

Method: Add

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

clpeak

OpenCL Test: Kernel Latency

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

Blender

Blend File: Pabellon Barcelona - Compute: OpenCL

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

Hackbench

Count: 16 - Type: Process

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

7-Zip Compression

Compress Speed Test

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

Threaded I/O Tester

Test: Read - Size Per Thread: 32MB - Thread Count: 8

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

BlogBench

Test: Write

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 128MB - Thread Count: 32

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

Apache Siege

Concurrent Users: 1

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

System Libxml2 Parsing

Filesize: 200 KB

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

x265

H.265 1080p Video Encoding

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 32MB - Thread Count: 32

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

Node.js Octane Benchmark

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

FLAC Audio Encoding

WAV To FLAC

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

Hierarchical INTegration

Test: DOUBLE

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

Compile Bench

Test: Compile

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

Hackbench

Count: 2 - Type: Thread

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

Schbench

Message Threads: 32 - Workers Per Message Thread: 6

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

Hackbench

Count: 4 - Type: Process

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

Botan

Test: AES-256 - Decrypt

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 128MB - Thread Count: 16

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

Perl Benchmarks

Test: Pod2html

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 256MB - Thread Count: 16

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

Hierarchical INTegration

Test: FLOAT

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

Stockfish

Total Time

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

Rodinia

Test: OpenMP CFD Solver

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

Stream

Type: Scale

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

Fhourstones

Complex Connect-4 Solving

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

GnuPG

2GB File Encryption

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

Threaded I/O Tester

Test: Read - Size Per Thread: 128MB - Thread Count: 8

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

Loopback TCP Network Performance

Time To Transfer 10GB Via Loopback

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

DaCapo Benchmark

Java Test: Jython

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

t-test1

Threads: 2

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

FFTW

Build: Float + SSE - Size: 2D FFT Size 128

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

Rodinia

Test: OpenMP LavaMD

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

clpeak

OpenCL Test: Single-Precision Float

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

Threaded I/O Tester

Test: Read - Size Per Thread: 64MB - Thread Count: 32

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

Minion

Benchmark: Quasigroup

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 32MB - Thread Count: 16

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

GNU MPC

Multi-Precision Benchmark

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

lzbench

Test: Brotli 0 - Process: Compression

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

Threaded I/O Tester

Test: Read - Size Per Thread: 256MB - Thread Count: 4

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

Build: Float + SSE - Size: 2D FFT Size 4096

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

Threaded I/O Tester

Test: Read - Size Per Thread: 128MB - Thread Count: 32

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

Threaded I/O Tester

Test: Read - Size Per Thread: 64MB - Thread Count: 8

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 256MB - Thread Count: 32

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

Threaded I/O Tester

Test: Read - Size Per Thread: 256MB - Thread Count: 32

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

Threaded I/O Tester

Test: Random Write - Size Per Thread: 64MB - Thread Count: 32

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

Hackbench

Count: 32 - Type: Process

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

Bork File Encrypter

File Encryption Time

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

Rodinia

Test: OpenCL Myocyte

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

SVT-VP9

1080p 8-bit YUV To VP9 Video Encode

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

Radiance Benchmark

Test: Serial

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

Hackbench

Count: 2 - Type: Process

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

Botan

Test: AES-256 - Encrypt

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

Parboil

Test: OpenCL BFS

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

WavPack Audio Encoding

WAV To WavPack

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

Botan

Test: Twofish - Decrypt

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

Botan

Test: CAST-256 - Decrypt

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

Botan

Test: CAST-256 - Encrypt

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

CppPerformanceBenchmarks

Test: Function Objects

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

lzbench

Test: Zstd 1 - Process: Compression

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

Multichase Pointer Chaser

Test: 1GB Array, 256 Byte Stride, 2 Threads

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

Smallpt

Global Illumination Renderer; 128 Samples

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

Rodinia

Test: OpenCL Heartwall

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

Blender

Blend File: Fishy Cat - Compute: CPU-Only

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

Multichase Pointer Chaser

Test: 1GB Array, 256 Byte Stride, 4 Threads

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

Scikit-Learn

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

glibc bench

Benchmark: sin

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

clpeak

OpenCL Test: Integer Compute INT

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

Go Benchmarks

Test: build

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

glibc bench

Benchmark: ffsll

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

glibc bench

Benchmark: ffs

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

Y-Cruncher

Calculating 500M Pi Digits

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

Parboil

Test: OpenCL TPACF

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

Sample Pi Program

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

Go Benchmarks

Test: json

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

LuaJIT

Test: Monte Carlo

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

Blender

Blend File: BMW27 - Compute: CPU-Only

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

Parboil

Test: OpenMP CUTCP

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

Stream

Type: Add

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

glibc bench

Benchmark: pthread_once

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

libjpeg-turbo tjbench

Test: Decompression Throughput

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

Java Gradle Build

Gradle Build: Reactor

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

Blender

Blend File: Classroom - Compute: CPU-Only

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

Xsbench

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

Parboil

Test: OpenMP LBM

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

OpenSSL

RSA 4096-bit Performance

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

lzbench

Test: Zstd 1 - Process: Decompression

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

lzbench

Test: Libdeflate 1 - Process: Decompression

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

glibc bench

Benchmark: sqrt

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

GNU GMP GMPbench

Total Time

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

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

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

Go Benchmarks

Test: garbage

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

NAMD CUDA

ATPase Simulation - 327,506 Atoms

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

Rodinia

Test: OpenCL Particle Filter

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

Crafty

Elapsed Time

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

LuaJIT

Test: Sparse Matrix Multiply

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

lzbench

Test: Brotli 0 - Process: Decompression

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

Stream

Type: Copy

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

clpeak

OpenCL Test: Transfer Bandwidth enqueueReadBuffer

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

Rust Prime Benchmark

Prime Number Test To 200,000,000

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

Stream

Type: Triad

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

CppPerformanceBenchmarks

Test: Atol

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

glibc bench

Benchmark: cos

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

CppPerformanceBenchmarks

Test: Stepanov Abstraction

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

Primesieve

1e12 Prime Number Generation

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

Java SciMark

Computational Test: Sparse Matrix Multiply

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

Parboil

Test: OpenCL LBM

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

NAMD

ATPase Simulation - 327,506 Atoms

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

clpeak

OpenCL Test: Transfer Bandwidth enqueueWriteBuffer

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

CppPerformanceBenchmarks

Test: Stepanov Vector

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

Botan

Test: KASUMI - Decrypt

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

CacheBench

Test: Write

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

Rust Mandelbrot

Time To Complete Serial/Parallel Mandelbrot

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

Java SciMark

Computational Test: Jacobi Successive Over-Relaxation

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

LuaJIT

Test: Jacobi Successive Over-Relaxation

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

CacheBench

Test: Read

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

Botan

Test: KASUMI - Encrypt

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

CacheBench

Test: Read / Modify / Write

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

Phoronix Test Suite Self Test

Test: Peak Memory Usage

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

clpeak

OpenCL Test: Global Memory Bandwidth

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

clpeak

OpenCL Test: Double-Precision Double

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

System Libxml2 Parsing

Filesize: 50 KB

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

System Libxml2 Parsing

Filesize: 5 KB

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

Botan

Test: Blowfish - Decrypt

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

Botan

Test: Blowfish - Encrypt

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

Botan

Test: Twofish - Encrypt

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

BYTE Unix Benchmark

Computational Test: Floating-Point Arithmetic

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

BYTE Unix Benchmark

Computational Test: Register Arithmetic

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

BYTE Unix Benchmark

Computational Test: Integer Arithmetic

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

Java SciMark

Computational Test: Monte Carlo

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

BLAKE2

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

lzbench

Test: Libdeflate 1 - Process: Compression

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

lzbench

Test: XZ 0 - Process: Decompression

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

Schbench

Message Threads: 4 - Workers Per Message Thread: 16

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

Schbench

Message Threads: 32 - Workers Per Message Thread: 2

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

Schbench

Message Threads: 2 - Workers Per Message Thread: 32

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

Schbench

Message Threads: 16 - Workers Per Message Thread: 6

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

Schbench

Message Threads: 16 - Workers Per Message Thread: 4

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

Schbench

Message Threads: 8 - Workers Per Message Thread: 8

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

Schbench

Message Threads: 8 - Workers Per Message Thread: 6

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

RAR Compression

Linux Source Tree Archiving To RAR

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

Redis

Test: SET

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

Redis

Test: GET

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

Redis

Test: LPUSH

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

Redis

Test: SADD

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

Redis

Test: LPOP

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

Java SciMark

Computational Test: Fast Fourier Transform

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

FFTW

Build: Float + SSE - Size: 1D FFT Size 256

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

FFTW

Build: Float + SSE - Size: 2D FFT Size 64

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

FFTW

Build: Float + SSE - Size: 2D FFT Size 32

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

FFTW

Build: Float + SSE - Size: 1D FFT Size 64

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

FFTW

Build: Stock - Size: 1D FFT Size 4096

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

FFTW

Build: Stock - Size: 1D FFT Size 2048

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

FFTW

Build: Stock - Size: 1D FFT Size 1024

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

FFTW

Build: Stock - Size: 2D FFT Size 64

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

FFTW

Build: Stock - Size: 2D FFT Size 32

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

FFTW

Build: Stock - Size: 1D FFT Size 64

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

Rodinia

Test: OpenMP Streamcluster

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

NAS Parallel Benchmarks

Test / Class: EP.C

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

Test: Random Read - Size Per Thread: 256MB - Thread Count: 16

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 128MB - Thread Count: 16

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 64MB - Thread Count: 16

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 32MB - Thread Count: 16

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

Threaded I/O Tester

Test: Random Read - Size Per Thread: 64MB - Thread Count: 8

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

Threaded I/O Tester

Test: Read - Size Per Thread: 256MB - Thread Count: 16

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

Threaded I/O Tester

Test: Read - Size Per Thread: 64MB - Thread Count: 16

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

Threaded I/O Tester

Test: Read - Size Per Thread: 32MB - Thread Count: 16

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


Phoronix Test Suite v10.8.5