AMD EPYC Rome Compiler Benchmarks

AMD AOCC 2.0, GCC, LLVM Clang compiler benchmarks on EPYC 7742. Tests by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1908089-AS-AMDEPYCRO53
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 2 Tests
Timed Code Compilation 2 Tests
C/C++ Compiler Tests 16 Tests
CPU Massive 19 Tests
Creator Workloads 10 Tests
Encoding 6 Tests
HPC - High Performance Computing 2 Tests
Imaging 2 Tests
Multi-Core 14 Tests
Programmer / Developer System Benchmarks 2 Tests
Renderers 2 Tests
Server 2 Tests
Server CPU Tests 12 Tests
Single-Threaded 4 Tests
Video Encoding 6 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
GCC 9.1.0
August 07 2019
  7 Hours, 44 Minutes
GCC 10.0 Git
August 07 2019
  8 Hours
LLVM Clang 9.0 SVN
August 08 2019
  5 Hours, 9 Minutes
AOCC 2.0
August 08 2019
  5 Hours, 57 Minutes
Invert Hiding All Results Option
  6 Hours, 42 Minutes

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

GCC 9.1.0

Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 6 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: GCC 9.1.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2
Compiler Notes: --disable-multilib --enable-checking=release
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

GCC 10.0 Git

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: GCC 10.0.0 20190804, File-System: ext4, Screen Resolution: 1920x1080

LLVM Clang 9.0 SVN

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: Clang 9.0.0-svn364739-1~exp1+0~20190701101552.184~1.gbp124358, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

AOCC 2.0

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: Clang 8.0.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2
Compiler Notes: Optimized build with assertions; Default target: x86_64-unknown-linux-gnu; Host CPU: znver1
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

AMD EPYC Rome Compiler BenchmarksOpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads)AMD DAYTONA_X (RDY1001C BIOS)AMD Device 1480516096MB280GB INTEL SSDPED1D280GA + 6 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFDASPEEDVE2282 x Mellanox MT27710Ubuntu 19.045.2.0-050200rc7-generic (x86_64) 20190630GNOME Shell 3.32.1X Server 1.20.4modesetting 1.20.4GCC 9.1.0GCC 10.0.0 20190804Clang 9.0.0-svn364739-1~exp1+0~20190701101552.184~1.gbp124358Clang 8.0.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilersFile-SystemScreen ResolutionAMD EPYC Rome Compiler Benchmarks PerformanceSystem Logs- CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2- GCC 9.1.0: --disable-multilib --enable-checking=release- GCC 10.0 Git: --disable-multilib --enable-checking=release- AOCC 2.0: Optimized build with assertions; Default target: x86_64-unknown-linux-gnu; Host CPU: znver1- Scaling Governor: acpi-cpufreq ondemand- Python 2.7.16 + Python 3.7.3- l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0Logarithmic Result OverviewPhoronix Test SuiteTimed PHP CompilationMKL-DNNTimed LLVM CompilationC-RayCoremarkJohn The RipperAOBenchFFTWGraphicsMagickTSCPSciMarkHigh Performance Conjugate GradientCppPerformanceBenchmarksApache Benchmarkx264dav1dx265libjpeg-turbo tjbench

AMD EPYC Rome Compiler Benchmarksbuild-php: Time To Compilemkl-dnn: Deconvolution Batch deconv_all - f32mkl-dnn: Convolution Batch conv_all - f32build-llvm: Time To Compilec-ray: Total Time - 4K, 16 Rays Per Pixelcoremark: CoreMark Size 666 - Iterations Per Secondjohn-the-ripper: Blowfishscimark2: Fast Fourier Transformscimark2: Sparse Matrix Multiplycpp-perf-bench: Rand Numbersaobench: 2048 x 2048 - Total Timefftw: Stock - 1D FFT Size 4096graphics-magick: Rotategraphics-magick: HWB Color Spacecpp-perf-bench: Stepanov Vectorfftw: Stock - 2D FFT Size 2048cpp-perf-bench: Ctypegraphics-magick: Enhancedfftw: Stock - 2D FFT Size 4096graphics-magick: Swirlgraphics-magick: Noise-Gaussiangraphics-magick: Sharpenfftw: Stock - 1D FFT Size 2048tscp: AI Chess Performancecpp-perf-bench: Stepanov Abstractionscimark2: Jacobi Successive Over-Relaxationscimark2: Compositeapache-siege: 250apache-siege: 200scimark2: Dense LU Matrix Factorizationcpp-perf-bench: Math Librarydav1d: Summer Nature 4Ksvt-vp9: 1080p 8-bit YUV To VP9 Video Encodex264: H.264 Video Encodinglzbench: Zstd 1 - Decompressionscimark2: Monte Carlosvt-av1: 1080p 8-bit YUV To AV1 Video Encodedav1d: Summer Nature 1080px265: H.265 1080p Video Encodingsvt-hevc: 1080p 8-bit YUV To HEVC Video Encodelzbench: Libdeflate 1 - Compressionapache-siege: 100lzbench: XZ 0 - Decompressiontjbench: Decompression Throughputlzbench: Brotli 0 - Compressioncpp-perf-bench: Function Objectssockperf: Throughputlzbench: Zstd 1 - Compressionlzbench: Libdeflate 1 - Decompressioncpp-perf-bench: Atollzbench: Brotli 0 - Decompressionlzbench: XZ 0 - Compressionsockperf: Latency Ping Pongapache: Static Web Page Servinggraphics-magick: Resizingmkl-dnn: Convolution Batch conv_googlenet_v3 - f32mkl-dnn: Convolution Batch conv_alexnet - f32mkl-dnn: Deconvolution Batch deconv_3d - f32mkl-dnn: Deconvolution Batch deconv_1d - f32mkl-dnn: Convolution Batch conv_3d - f32mkl-dnn: IP Batch All - f32mkl-dnn: IP Batch 1D - f32hpcg: sockperf: Latency Under LoadGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.064.6220853637344.8096.295.723868113.71148302203.682741.971599.0736.778808.9320422899.217381.0041.662156327.202182082078946.23107281236.661801.312834.0633869.9332222.728811.17343.4511.52277.45153.31982612.17101.074.7544.54343.2919726315.8087175.1638918.9347757836488074.36446305.3924915.191023194.834136.48588.07818.78387.716593.301585.030.3622.4265.0620708638147.1696.855.823825301.45148542202.712763.501627.9935.338816.7320222697.707288.8039.332136289.302192072078958.53104077536.521800.112828.0132367.3130752.548762.75333.8511.16283.63152.431011610.98100.444.7744.73344.0419426336.6186175.4838619.0148041536287674.32305.3924096.601023342.144171.88500.54955.00440.316961.88946.120.3624.1288.302590.09371.9578.869.193024508.81187652224.523382.931892.4641.758258.3723723485.896627.7736.742155842.732162202098273.10114937033.441655.772880.5633938.1332213.598518.52331.0211.56274.55153.95621.05102.784.8645.37337.7525958.51174.1318.8274.1024594.6611923.3042.492.746.082.6690.6616.760.35230.211917.89370.63146.609.013284059.92187140178.572736.941894.0237.027503.5720520289.736462.3337.811905593.441941951868007.57109368234.101656.182730.138473.11330.4111.14157.18605.884.7745.57175.9618.9474.3824163.3112023.2142.782.735.402.7176.8011.600.33OpenBenchmarking.org

Timed PHP Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To CompileGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 0.28, N = 3SE +/- 0.29, N = 3SE +/- 0.24, N = 3SE +/- 0.53, N = 364.6265.0688.30230.211. (CC) gcc options: -O3 -march=znver2 -pedantic -ldl -lz -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To CompileGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 64.15 / Avg: 64.62 / Max: 65.13Min: 64.71 / Avg: 65.06 / Max: 65.63Min: 87.82 / Avg: 88.3 / Max: 88.59Min: 229.34 / Avg: 230.21 / Max: 231.181. (CC) gcc options: -O3 -march=znver2 -pedantic -ldl -lz -lm

MKL-DNN

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.040K80K120K160K200KSE +/- 2544.01, N = 3SE +/- 3229.16, N = 3SE +/- 22.00, N = 3SE +/- 15.15, N = 3208536.00207086.002590.091917.89-march=native -mtune=native -fopenmp - MIN: 153312-march=native -mtune=native -fopenmp - MIN: 1496981. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_all - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.040K80K120K160K200KMin: 204004 / Avg: 208535.67 / Max: 212805Min: 203092 / Avg: 207085.67 / Max: 213478Min: 2547.69 / Avg: 2590.09 / Max: 2621.49Min: 1892.03 / Avg: 1917.89 / Max: 1944.491. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.08K16K24K32K40KSE +/- 601.47, N = 3SE +/- 509.65, N = 5SE +/- 1.44, N = 3SE +/- 0.50, N = 337344.8038147.16371.95370.63-march=native -mtune=native -fopenmp - MIN: 28450.7-march=native -mtune=native -fopenmp - MIN: 29056.71. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_all - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.07K14K21K28K35KMin: 36532.7 / Avg: 37344.8 / Max: 38519.4Min: 36729.5 / Avg: 38147.16 / Max: 39331.7Min: 369.37 / Avg: 371.95 / Max: 374.36Min: 370.02 / Avg: 370.63 / Max: 371.631. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.030609012015096.2996.8578.86146.60

C-Ray

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

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.03691215SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 35.725.829.199.011. (CC) gcc options: -lm -lpthread -O3 -march=znver2
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.03691215Min: 5.58 / Avg: 5.72 / Max: 5.9Min: 5.68 / Avg: 5.82 / Max: 6Min: 9.15 / Avg: 9.19 / Max: 9.26Min: 8.8 / Avg: 9.01 / Max: 9.241. (CC) gcc options: -lm -lpthread -O3 -march=znver2

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0800K1600K2400K3200K4000KSE +/- 60538.32, N = 3SE +/- 29615.82, N = 3SE +/- 32092.57, N = 3SE +/- 40813.96, N = 33868113.713825301.453024508.813284059.921. (CC) gcc options: -O2 -O3 -march=znver2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0700K1400K2100K2800K3500KMin: 3749267.72 / Avg: 3868113.71 / Max: 3947571.32Min: 3777761.38 / Avg: 3825301.45 / Max: 3879669.62Min: 2960336.12 / Avg: 3024508.81 / Max: 3057690.01Min: 3202936.02 / Avg: 3284059.92 / Max: 3332465.51. (CC) gcc options: -O2 -O3 -march=znver2 -lrt" -lrt

John The Ripper

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

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.040K80K120K160K200KSE +/- 794.73, N = 3SE +/- 760.59, N = 3SE +/- 2145.04, N = 3SE +/- 858.63, N = 31483021485421876521871401. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: BlowfishGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.030K60K90K120K150KMin: 146715 / Avg: 148302 / Max: 149172Min: 147483 / Avg: 148541.67 / Max: 150017Min: 185164 / Avg: 187652.33 / Max: 191923Min: 185472 / Avg: 187140.33 / Max: 1883271. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

SciMark

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

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 0.91, N = 3SE +/- 0.44, N = 3SE +/- 0.10, N = 3SE +/- 0.38, N = 3203.68202.71224.52178.571. (CC) gcc options: -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 202.24 / Avg: 203.68 / Max: 205.36Min: 202.17 / Avg: 202.71 / Max: 203.58Min: 224.42 / Avg: 224.52 / Max: 224.71Min: 178.12 / Avg: 178.57 / Max: 179.331. (CC) gcc options: -O3 -march=znver2 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.07001400210028003500SE +/- 69.70, N = 3SE +/- 15.27, N = 3SE +/- 47.14, N = 3SE +/- 14.78, N = 32741.972763.503382.932736.941. (CC) gcc options: -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.06001200180024003000Min: 2624.77 / Avg: 2741.97 / Max: 2865.94Min: 2733.31 / Avg: 2763.5 / Max: 2782.59Min: 3291.5 / Avg: 3382.93 / Max: 3448.6Min: 2709.71 / Avg: 2736.94 / Max: 2760.51. (CC) gcc options: -O3 -march=znver2 -lm

CppPerformanceBenchmarks

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Random NumbersGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0400800120016002000SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.26, N = 31599.071627.991892.461894.021. (CXX) g++ options: -O3 -march=znver2 -std=c++11
OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Random NumbersGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.030060090012001500Min: 1599 / Avg: 1599.07 / Max: 1599.19Min: 1627.77 / Avg: 1627.99 / Max: 1628.19Min: 1892.42 / Avg: 1892.46 / Max: 1892.5Min: 1893.61 / Avg: 1894.02 / Max: 1894.491. (CXX) g++ options: -O3 -march=znver2 -std=c++11

AOBench

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

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.01020304050SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 336.7735.3341.7537.021. (CC) gcc options: -lm -O3 -march=znver2
OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0918273645Min: 36.75 / Avg: 36.77 / Max: 36.78Min: 35.32 / Avg: 35.33 / Max: 35.34Min: 41.74 / Avg: 41.75 / Max: 41.77Min: 36.98 / Avg: 37.02 / Max: 37.111. (CC) gcc options: -lm -O3 -march=znver2

FFTW

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

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 4096GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.02K4K6K8K10KSE +/- 10.91, N = 3SE +/- 4.55, N = 3SE +/- 12.43, N = 3SE +/- 113.30, N = 38808.938816.738258.377503.571. (CC) gcc options: -pthread -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 4096GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.015003000450060007500Min: 8788.2 / Avg: 8808.93 / Max: 8825.2Min: 8811.6 / Avg: 8816.73 / Max: 8825.8Min: 8234.4 / Avg: 8258.37 / Max: 8276.1Min: 7277.6 / Avg: 7503.57 / Max: 7631.11. (CC) gcc options: -pthread -O3 -march=znver2 -lm

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: RotateGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 1.15, N = 3204202237205-ldl-ldl-lomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: RotateGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 235 / Avg: 237 / Max: 2391. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color SpaceGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 0.33, N = 3SE +/- 2.65, N = 3228226234202-ldl-ldl-lomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color SpaceGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 226 / Avg: 226.33 / Max: 227Min: 229 / Avg: 234 / Max: 2381. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

CppPerformanceBenchmarks

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov VectorGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.020406080100SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.35, N = 399.2197.7085.8989.731. (CXX) g++ options: -O3 -march=znver2 -std=c++11
OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov VectorGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.020406080100Min: 99.19 / Avg: 99.21 / Max: 99.24Min: 97.6 / Avg: 97.7 / Max: 97.77Min: 85.78 / Avg: 85.89 / Max: 86.1Min: 89.14 / Avg: 89.73 / Max: 90.351. (CXX) g++ options: -O3 -march=znver2 -std=c++11

FFTW

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

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2048GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.016003200480064008000SE +/- 15.60, N = 3SE +/- 74.47, N = 3SE +/- 50.06, N = 3SE +/- 19.37, N = 37381.007288.806627.776462.331. (CC) gcc options: -pthread -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2048GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.013002600390052006500Min: 7359.4 / Avg: 7381 / Max: 7411.3Min: 7149 / Avg: 7288.8 / Max: 7403.2Min: 6558.8 / Avg: 6627.77 / Max: 6725.1Min: 6428.7 / Avg: 6462.33 / Max: 6495.81. (CC) gcc options: -pthread -O3 -march=znver2 -lm

CppPerformanceBenchmarks

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: CtypeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.01020304050SE +/- 0.12, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 341.6639.3336.7437.811. (CXX) g++ options: -O3 -march=znver2 -std=c++11
OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: CtypeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0918273645Min: 41.54 / Avg: 41.66 / Max: 41.9Min: 39.33 / Avg: 39.33 / Max: 39.34Min: 36.73 / Avg: 36.74 / Max: 36.74Min: 37.81 / Avg: 37.81 / Max: 37.821. (CXX) g++ options: -O3 -march=znver2 -std=c++11

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: EnhancedGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 0.33, N = 3215213215190-ldl-ldl-lomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: EnhancedGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 215 / Avg: 215.33 / Max: 2161. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

FFTW

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

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.014002800420056007000SE +/- 32.75, N = 3SE +/- 67.18, N = 3SE +/- 41.90, N = 3SE +/- 48.86, N = 126327.206289.305842.735593.441. (CC) gcc options: -pthread -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.011002200330044005500Min: 6283.1 / Avg: 6327.2 / Max: 6391.2Min: 6197 / Avg: 6289.3 / Max: 6420Min: 5760.9 / Avg: 5842.73 / Max: 5899.3Min: 5216.6 / Avg: 5593.44 / Max: 5723.11. (CC) gcc options: -pthread -O3 -march=znver2 -lm

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SwirlGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 0.33, N = 3SE +/- 0.33, N = 3218219216194-ldl-ldl-lomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SwirlGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 218 / Avg: 218.33 / Max: 219Min: 216 / Avg: 216.33 / Max: 2171. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Noise-GaussianGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 0.88, N = 3208207220195-ldl-ldl-lomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Noise-GaussianGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 218 / Avg: 219.67 / Max: 2211. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SharpenGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.050100150200250SE +/- 0.67, N = 3SE +/- 1.00, N = 3207207209186-ldl-ldl-lomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SharpenGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200Min: 208 / Avg: 208.67 / Max: 210Min: 184 / Avg: 186 / Max: 1871. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

FFTW

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

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2048GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.02K4K6K8K10KSE +/- 35.41, N = 3SE +/- 20.56, N = 3SE +/- 7.45, N = 3SE +/- 3.56, N = 38946.238958.538273.108007.571. (CC) gcc options: -pthread -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2048GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.016003200480064008000Min: 8901.3 / Avg: 8946.23 / Max: 9016.1Min: 8917.8 / Avg: 8958.53 / Max: 8983.8Min: 8258.3 / Avg: 8273.1 / Max: 8282Min: 8001.6 / Avg: 8007.57 / Max: 8013.91. (CC) gcc options: -pthread -O3 -march=znver2 -lm

TSCP

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

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0200K400K600K800K1000KSE +/- 1412.87, N = 5SE +/- 393.00, N = 5SE +/- 479.00, N = 5SE +/- 532.27, N = 510728121040775114937010936821. (CC) gcc options: -O3 -march=znver2 -march=native
OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0200K400K600K800K1000KMin: 1067399 / Avg: 1072812 / Max: 1075738Min: 1039203 / Avg: 1040775 / Max: 1041168Min: 1147454 / Avg: 1149370 / Max: 1149849Min: 1092813 / Avg: 1093682.2 / Max: 10949861. (CC) gcc options: -O3 -march=znver2 -march=native

CppPerformanceBenchmarks

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov AbstractionGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 336.6636.5233.4434.101. (CXX) g++ options: -O3 -march=znver2 -std=c++11
OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov AbstractionGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0816243240Min: 36.63 / Avg: 36.66 / Max: 36.68Min: 36.51 / Avg: 36.52 / Max: 36.54Min: 33.43 / Avg: 33.44 / Max: 33.45Min: 34.08 / Avg: 34.1 / Max: 34.111. (CXX) g++ options: -O3 -march=znver2 -std=c++11

SciMark

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

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0400800120016002000SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 0.16, N = 3SE +/- 0.43, N = 31801.311800.111655.771656.181. (CC) gcc options: -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.030060090012001500Min: 1801.1 / Avg: 1801.31 / Max: 1801.45Min: 1799.97 / Avg: 1800.11 / Max: 1800.38Min: 1655.46 / Avg: 1655.77 / Max: 1655.93Min: 1655.33 / Avg: 1656.18 / Max: 1656.651. (CC) gcc options: -O3 -march=znver2 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.06001200180024003000SE +/- 10.94, N = 3SE +/- 4.68, N = 3SE +/- 9.28, N = 3SE +/- 4.27, N = 32834.062828.012880.562730.131. (CC) gcc options: -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.05001000150020002500Min: 2814.44 / Avg: 2834.06 / Max: 2852.27Min: 2820.36 / Avg: 2828.01 / Max: 2836.52Min: 2862.09 / Avg: 2880.56 / Max: 2891.47Min: 2721.65 / Avg: 2730.13 / Max: 2735.151. (CC) gcc options: -O3 -march=znver2 -lm

Apache Siege

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

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN7K14K21K28K35KSE +/- 479.50, N = 15SE +/- 480.75, N = 15SE +/- 377.42, N = 1533869.9332367.3133938.131. (CC) gcc options: -O3 -march=znver2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN6K12K18K24K30KMin: 28872.99 / Avg: 33869.93 / Max: 36273.94Min: 27651.12 / Avg: 32367.31 / Max: 34170.37Min: 30937.86 / Avg: 33938.13 / Max: 36221.391. (CC) gcc options: -O3 -march=znver2 -lpthread -ldl -lssl -lcrypto

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN7K14K21K28K35KSE +/- 261.42, N = 15SE +/- 170.01, N = 3SE +/- 428.68, N = 332222.7230752.5432213.591. (CC) gcc options: -O3 -march=znver2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN6K12K18K24K30KMin: 29274.16 / Avg: 32222.72 / Max: 32828.66Min: 30412.58 / Avg: 30752.54 / Max: 30928.49Min: 31601.95 / Avg: 32213.59 / Max: 33039.731. (CC) gcc options: -O3 -march=znver2 -lpthread -ldl -lssl -lcrypto

SciMark

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

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.02K4K6K8K10KSE +/- 15.96, N = 3SE +/- 28.43, N = 3SE +/- 6.82, N = 3SE +/- 10.49, N = 38811.178762.758518.528473.111. (CC) gcc options: -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.015003000450060007500Min: 8779.42 / Avg: 8811.17 / Max: 8829.81Min: 8705.95 / Avg: 8762.75 / Max: 8793.37Min: 8507.26 / Avg: 8518.52 / Max: 8530.83Min: 8457.73 / Avg: 8473.11 / Max: 8493.161. (CC) gcc options: -O3 -march=znver2 -lm

CppPerformanceBenchmarks

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Math LibraryGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.070140210280350SE +/- 0.46, N = 3SE +/- 0.12, N = 3SE +/- 0.43, N = 3SE +/- 0.31, N = 3343.45333.85331.02330.411. (CXX) g++ options: -O3 -march=znver2 -std=c++11
OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Math LibraryGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.060120180240300Min: 342.91 / Avg: 343.45 / Max: 344.37Min: 333.63 / Avg: 333.85 / Max: 334.03Min: 330.17 / Avg: 331.02 / Max: 331.54Min: 329.89 / Avg: 330.41 / Max: 330.961. (CXX) g++ options: -O3 -march=znver2 -std=c++11

dav1d

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

OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 4KGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.03691215SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.19, N = 3SE +/- 0.07, N = 311.5211.1611.5611.141. (CC) gcc options: -O3 -march=znver2 -pthread
OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 4KGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.03691215Min: 11.29 / Avg: 11.52 / Max: 11.81Min: 11.09 / Avg: 11.16 / Max: 11.21Min: 11.24 / Avg: 11.56 / Max: 11.89Min: 11 / Avg: 11.14 / Max: 11.251. (CC) gcc options: -O3 -march=znver2 -pthread

SVT-VP9

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video EncodeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN60120180240300SE +/- 4.48, N = 3SE +/- 3.30, N = 15SE +/- 3.16, N = 3277.45283.63274.55-fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx-fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx1. (CC) gcc options: -O3 -march=znver2 -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video EncodeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN50100150200250Min: 272.73 / Avg: 277.45 / Max: 286.4Min: 265.96 / Avg: 283.63 / Max: 309.12Min: 268.82 / Avg: 274.55 / Max: 279.721. (CC) gcc options: -O3 -march=znver2 -pie -rdynamic -lpthread -lrt -lm

x264

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video EncodingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0306090120150SE +/- 0.91, N = 3SE +/- 0.41, N = 3SE +/- 0.48, N = 3SE +/- 2.65, N = 3153.31152.43153.95157.18-mstack-alignment=64-mstack-alignment=641. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -march=znver2 -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video EncodingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0306090120150Min: 151.49 / Avg: 153.31 / Max: 154.38Min: 151.61 / Avg: 152.43 / Max: 152.88Min: 153.23 / Avg: 153.95 / Max: 154.86Min: 153.44 / Avg: 157.18 / Max: 162.31. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -march=znver2 -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

lzbench

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

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: DecompressionGCC 9.1.0GCC 10.0 Git200400600800100098210111. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

SciMark

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

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0130260390520650SE +/- 0.53, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 3612.17610.98621.05605.881. (CC) gcc options: -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0110220330440550Min: 611.11 / Avg: 612.17 / Max: 612.74Min: 610.9 / Avg: 610.98 / Max: 611.08Min: 620.85 / Avg: 621.05 / Max: 621.15Min: 605.64 / Avg: 605.88 / Max: 606.021. (CC) gcc options: -O3 -march=znver2 -lm

SVT-AV1

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.51080p 8-bit YUV To AV1 Video EncodeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN20406080100SE +/- 1.25, N = 5SE +/- 0.16, N = 3SE +/- 0.32, N = 3101.07100.44102.781. (CXX) g++ options: -O3 -march=znver2 -pie -lpthread -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.51080p 8-bit YUV To AV1 Video EncodeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN20406080100Min: 96.57 / Avg: 101.07 / Max: 103.73Min: 100.15 / Avg: 100.44 / Max: 100.71Min: 102.41 / Avg: 102.78 / Max: 103.411. (CXX) g++ options: -O3 -march=znver2 -pie -lpthread -lm

dav1d

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

OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 1080pGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.01.09352.1873.28054.3745.4675SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 34.754.774.864.771. (CC) gcc options: -O3 -march=znver2 -pthread
OpenBenchmarking.orgSeconds, Fewer Is Betterdav1d 0.3Video Input: Summer Nature 1080pGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0246810Min: 4.71 / Avg: 4.75 / Max: 4.82Min: 4.74 / Avg: 4.77 / Max: 4.83Min: 4.86 / Avg: 4.86 / Max: 4.87Min: 4.72 / Avg: 4.77 / Max: 4.841. (CC) gcc options: -O3 -march=znver2 -pthread

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video EncodingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.01020304050SE +/- 0.11, N = 3SE +/- 0.21, N = 3SE +/- 0.15, N = 3SE +/- 0.15, N = 344.5444.7345.3745.571. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video EncodingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0918273645Min: 44.32 / Avg: 44.54 / Max: 44.66Min: 44.49 / Avg: 44.73 / Max: 45.15Min: 45.07 / Avg: 45.37 / Max: 45.57Min: 45.41 / Avg: 45.57 / Max: 45.871. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread -lrt -ldl -lnuma

SVT-HEVC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video EncodeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN70140210280350SE +/- 4.37, N = 3SE +/- 3.15, N = 10SE +/- 4.13, N = 3343.29344.04337.75-fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native-fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native1. (CC) gcc options: -O3 -march=znver2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video EncodeGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN60120180240300Min: 334.63 / Avg: 343.29 / Max: 348.63Min: 330.4 / Avg: 344.04 / Max: 357.57Min: 329.67 / Avg: 337.75 / Max: 343.251. (CC) gcc options: -O3 -march=znver2 -pie -rdynamic -lpthread -lrt

lzbench

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

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: CompressionGCC 9.1.0GCC 10.0 Git4080120160200SE +/- 0.58, N = 31971941. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: CompressionGCC 9.1.0GCC 10.0 Git4080120160200Min: 193 / Avg: 194 / Max: 1951. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Apache Siege

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

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 100GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN6K12K18K24K30KSE +/- 10.57, N = 3SE +/- 17.44, N = 3SE +/- 332.76, N = 426315.8026336.6125958.511. (CC) gcc options: -O3 -march=znver2 -lpthread -ldl -lssl -lcrypto
OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 100GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVN5K10K15K20K25KMin: 26295.03 / Avg: 26315.8 / Max: 26329.65Min: 26301.95 / Avg: 26336.61 / Max: 26357.41Min: 24962.55 / Avg: 25958.51 / Max: 26343.521. (CC) gcc options: -O3 -march=znver2 -lpthread -ldl -lssl -lcrypto

lzbench

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

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: DecompressionGCC 9.1.0GCC 10.0 Git20406080100SE +/- 0.33, N = 387861. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: DecompressionGCC 9.1.0GCC 10.0 Git1632486480Min: 86 / Avg: 86.67 / Max: 871. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

libjpeg-turbo tjbench

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

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression ThroughputGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04080120160200SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3175.16175.48174.13175.961. (CC) gcc options: -O3 -march=znver2 -rdynamic
OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression ThroughputGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0306090120150Min: 175.11 / Avg: 175.16 / Max: 175.18Min: 175.43 / Avg: 175.48 / Max: 175.55Min: 173.97 / Avg: 174.13 / Max: 174.46Min: 175.92 / Avg: 175.96 / Max: 1761. (CC) gcc options: -O3 -march=znver2 -rdynamic

lzbench

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

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: CompressionGCC 9.1.0GCC 10.0 Git80160240320400SE +/- 1.00, N = 3SE +/- 2.33, N = 33893851. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: CompressionGCC 9.1.0GCC 10.0 Git70140210280350Min: 387 / Avg: 389 / Max: 390Min: 380 / Avg: 384.67 / Max: 3871. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

CppPerformanceBenchmarks

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Function ObjectsGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0510152025SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 318.9319.0118.8218.941. (CXX) g++ options: -O3 -march=znver2 -std=c++11
OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Function ObjectsGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0510152025Min: 18.9 / Avg: 18.93 / Max: 18.95Min: 18.85 / Avg: 19.01 / Max: 19.1Min: 18.68 / Avg: 18.82 / Max: 18.95Min: 18.91 / Avg: 18.94 / Max: 191. (CXX) g++ options: -O3 -march=znver2 -std=c++11

Sockperf

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

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: ThroughputGCC 9.1.0GCC 10.0 Git100K200K300K400K500KSE +/- 3521.00, N = 25SE +/- 4088.70, N = 54775784804151. (CXX) g++ options: --param -O3 -march=znver2 -rdynamic -ldl -lpthread
OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: ThroughputGCC 9.1.0GCC 10.0 Git80K160K240K320K400KMin: 405929 / Avg: 477578 / Max: 494290Min: 468782 / Avg: 480415 / Max: 4903311. (CXX) g++ options: --param -O3 -march=znver2 -rdynamic -ldl -lpthread

lzbench

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

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: CompressionGCC 9.1.0GCC 10.0 Git80160240320400SE +/- 0.33, N = 3SE +/- 1.20, N = 33643621. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: CompressionGCC 9.1.0GCC 10.0 Git70140210280350Min: 364 / Avg: 364.33 / Max: 365Min: 360 / Avg: 361.67 / Max: 3641. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: DecompressionGCC 9.1.0GCC 10.0 Git2004006008001000SE +/- 4.67, N = 3SE +/- 7.84, N = 38808761. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: DecompressionGCC 9.1.0GCC 10.0 Git150300450600750Min: 875 / Avg: 879.67 / Max: 889Min: 868 / Avg: 876.33 / Max: 8921. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

CppPerformanceBenchmarks

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

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: AtolGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.020406080100SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.28, N = 374.3674.3274.1074.381. (CXX) g++ options: -O3 -march=znver2 -std=c++11
OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: AtolGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.01428425670Min: 74.03 / Avg: 74.36 / Max: 74.79Min: 74.19 / Avg: 74.32 / Max: 74.57Min: 74 / Avg: 74.1 / Max: 74.21Min: 74.03 / Avg: 74.38 / Max: 74.931. (CXX) g++ options: -O3 -march=znver2 -std=c++11

lzbench

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

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: DecompressionGCC 9.1.0100200300400500SE +/- 0.33, N = 34461. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: CompressionGCC 9.1.0GCC 10.0 Git71421283530301. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Sockperf

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

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping PongGCC 9.1.0GCC 10.0 Git1.21282.42563.63844.85126.064SE +/- 0.02, N = 5SE +/- 0.05, N = 55.395.391. (CXX) g++ options: --param -O3 -march=znver2 -rdynamic -ldl -lpthread
OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping PongGCC 9.1.0GCC 10.0 Git246810Min: 5.33 / Avg: 5.39 / Max: 5.42Min: 5.3 / Avg: 5.39 / Max: 5.571. (CXX) g++ options: --param -O3 -march=znver2 -rdynamic -ldl -lpthread

Apache Benchmark

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

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.05K10K15K20K25KSE +/- 435.79, N = 15SE +/- 497.81, N = 15SE +/- 400.39, N = 15SE +/- 395.53, N = 1524915.1924096.6024594.6624163.311. (CC) gcc options: -shared -fPIC -pthread -O3 -march=znver2
OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.04K8K12K16K20KMin: 20620.01 / Avg: 24915.19 / Max: 26260.37Min: 20278.5 / Avg: 24096.6 / Max: 25578.52Min: 20194.39 / Avg: 24594.66 / Max: 25582.79Min: 21109.49 / Avg: 24163.31 / Max: 255211. (CC) gcc options: -shared -fPIC -pthread -O3 -march=znver2

GraphicsMagick

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

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: ResizingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0306090120150SE +/- 0.58, N = 3SE +/- 1.53, N = 3SE +/- 2.59, N = 12102102119120-ldl-ldl-lomp-lomp1. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: ResizingGCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.020406080100Min: 101 / Avg: 102 / Max: 103Min: 99 / Avg: 102 / Max: 104Min: 106 / Avg: 118.75 / Max: 1391. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

MKL-DNN

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

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.07001400210028003500SE +/- 173.73, N = 12SE +/- 108.79, N = 12SE +/- 0.11, N = 3SE +/- 0.27, N = 63194.833342.1423.3023.21-march=native -mtune=native -fopenmp - MIN: 1649.04-march=native -mtune=native -fopenmp - MIN: 1649.031. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.06001200180024003000Min: 2557.51 / Avg: 3194.83 / Max: 4410.94Min: 2602.39 / Avg: 3342.14 / Max: 3899.21Min: 23.08 / Avg: 23.3 / Max: 23.47Min: 21.97 / Avg: 23.21 / Max: 23.711. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.09001800270036004500SE +/- 56.84, N = 15SE +/- 66.32, N = 15SE +/- 0.28, N = 3SE +/- 0.09, N = 34136.484171.8842.4942.78-march=native -mtune=native -fopenmp - MIN: 3325.34-march=native -mtune=native -fopenmp - MIN: 3313.31. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_alexnet - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.07001400210028003500Min: 3745.55 / Avg: 4136.48 / Max: 4434.27Min: 3678.35 / Avg: 4171.88 / Max: 4612.97Min: 41.94 / Avg: 42.49 / Max: 42.89Min: 42.62 / Avg: 42.78 / Max: 42.921. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0130260390520650SE +/- 105.31, N = 12SE +/- 48.77, N = 15SE +/- 0.02, N = 3SE +/- 0.00, N = 3588.07500.542.742.73-march=native -mtune=native -fopenmp - MIN: 189.7-march=native -mtune=native -fopenmp - MIN: 192.521. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_3d - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0100200300400500Min: 277.83 / Avg: 588.07 / Max: 1208.54Min: 236.45 / Avg: 500.54 / Max: 811.51Min: 2.72 / Avg: 2.74 / Max: 2.79Min: 2.72 / Avg: 2.73 / Max: 2.731. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.02004006008001000SE +/- 138.13, N = 12SE +/- 140.61, N = 15SE +/- 0.11, N = 12SE +/- 0.07, N = 6818.78955.006.085.40-march=native -mtune=native -fopenmp - MIN: 286.61-march=native -mtune=native -fopenmp - MIN: 287.251. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Deconvolution Batch deconv_1d - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.02004006008001000Min: 382.19 / Avg: 818.78 / Max: 1800.16Min: 427.16 / Avg: 955 / Max: 1867.49Min: 5.6 / Avg: 6.08 / Max: 6.7Min: 5.23 / Avg: 5.4 / Max: 5.631. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.0100200300400500SE +/- 57.38, N = 15SE +/- 108.49, N = 12SE +/- 0.02, N = 3SE +/- 0.03, N = 15387.71440.312.662.71-march=native -mtune=native -fopenmp - MIN: 159.05-march=native -mtune=native -fopenmp - MIN: 157.551. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: Convolution Batch conv_3d - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.080160240320400Min: 255.97 / Avg: 387.71 / Max: 926.52Min: 258.32 / Avg: 440.31 / Max: 1541.91Min: 2.62 / Avg: 2.66 / Max: 2.69Min: 2.45 / Avg: 2.71 / Max: 2.851. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.015003000450060007500SE +/- 192.76, N = 15SE +/- 320.05, N = 12SE +/- 1.29, N = 4SE +/- 1.10, N = 36593.306961.8890.6676.80-march=native -mtune=native -fopenmp - MIN: 3178.05-march=native -mtune=native -fopenmp - MIN: 3291.221. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch All - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.012002400360048006000Min: 5577.27 / Avg: 6593.3 / Max: 7776.85Min: 5765.67 / Avg: 6961.88 / Max: 9630.25Min: 87.43 / Avg: 90.66 / Max: 93.41Min: 75.55 / Avg: 76.8 / Max: 791. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.030060090012001500SE +/- 218.86, N = 12SE +/- 119.82, N = 15SE +/- 0.25, N = 3SE +/- 0.25, N = 151585.03946.1216.7611.60-march=native -mtune=native -fopenmp - MIN: 283.94-march=native -mtune=native -fopenmp - MIN: 276.31. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl
OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: f32GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.030060090012001500Min: 497.98 / Avg: 1585.03 / Max: 3625.48Min: 454.43 / Avg: 946.12 / Max: 1829.53Min: 16.45 / Avg: 16.76 / Max: 17.26Min: 9.94 / Avg: 11.6 / Max: 13.411. (CXX) g++ options: -O3 -march=znver2 -std=c++11 -fPIC -pie -lmklml_intel -ldl

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.0GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.00.0810.1620.2430.3240.405SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 12SE +/- 0.01, N = 120.360.360.350.33
OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.0GCC 9.1.0GCC 10.0 GitLLVM Clang 9.0 SVNAOCC 2.012345Min: 0.36 / Avg: 0.36 / Max: 0.36Min: 0.35 / Avg: 0.36 / Max: 0.36Min: 0.32 / Avg: 0.35 / Max: 0.37Min: 0.3 / Avg: 0.33 / Max: 0.36

Sockperf

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

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under LoadGCC 9.1.0GCC 10.0 Git612182430SE +/- 0.86, N = 25SE +/- 0.50, N = 2022.4224.121. (CXX) g++ options: --param -O3 -march=znver2 -rdynamic -ldl -lpthread
OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under LoadGCC 9.1.0GCC 10.0 Git612182430Min: 6.66 / Avg: 22.42 / Max: 27.16Min: 18.5 / Avg: 24.12 / Max: 30.171. (CXX) g++ options: --param -O3 -march=znver2 -rdynamic -ldl -lpthread

GCC 9.1.0

Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 6 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: GCC 9.1.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2
Compiler Notes: --disable-multilib --enable-checking=release
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 7 August 2019 09:14 by user phoronix.

GCC 10.0 Git

Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 6 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: GCC 10.0.0 20190804, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2
Compiler Notes: --disable-multilib --enable-checking=release
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 7 August 2019 18:15 by user phoronix.

LLVM Clang 9.0 SVN

Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 6 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: Clang 9.0.0-svn364739-1~exp1+0~20190701101552.184~1.gbp124358, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 8 August 2019 05:38 by user phoronix.

AOCC 2.0

Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Device 1480, Memory: 516096MB, Disk: 280GB INTEL SSDPED1D280GA + 6 x 3841GB Micron_9300_MTFDHAL3T8TDP + 256GB Micron_1100_MTFD, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710

OS: Ubuntu 19.04, Kernel: 5.2.0-050200rc7-generic (x86_64) 20190630, Desktop: GNOME Shell 3.32.1, Display Server: X Server 1.20.4, Display Driver: modesetting 1.20.4, Compiler: Clang 8.0.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2
Compiler Notes: Optimized build with assertions; Default target: x86_64-unknown-linux-gnu; Host CPU: znver1
Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Python Notes: Python 2.7.16 + Python 3.7.3
Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling

Testing initiated at 8 August 2019 14:11 by user phoronix.