AMD Ryzen Threadripper 3960X GCC vs. LLVM Clang compiler benchmarks by Michael Larabel for a future article.
GCC 10.0.0 20191208 Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32768MB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz), Audio: AMD Baffin HDMI/DP, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723
OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: GCC 10.0.0 20191208, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
LLVM Clang 10.0 20191222 OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: Clang 10.0.0, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Notes: Optimized build; Default target: x86_64-unknown-linux-gnu; Host CPU: znver2Disk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
GCC 9.2.1 OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
LLVM Clang 9.0.0 OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: Clang 9.0.0, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Disk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
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.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 300K 600K 900K 1200K 1500K SE +/- 1231.70, N = 5 SE +/- 9469.71, N = 5 SE +/- 1690.40, N = 5 SE +/- 2711.28, N = 5 1345991 1373089 1528248 1487001 1. (CC) gcc options: -O3 -march=native
XZ Compression This test measures the time needed to compress a sample file (an Ubuntu file-system image) using XZ compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 5 10 15 20 25 SE +/- 0.16, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 20.04 19.75 19.69 19.69 1. (CC) gcc options: -pthread -fvisibility=hidden -O3 -march=native
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Ctype GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.30, N = 3 SE +/- 0.01, N = 3 32.31 32.22 29.80 29.09 1. (CXX) g++ options: -O3 -march=native -std=c++11
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Math Library GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 60 120 180 240 300 SE +/- 0.29, N = 3 SE +/- 0.45, N = 3 SE +/- 2.46, N = 3 SE +/- 0.41, N = 3 262.97 269.48 258.40 260.64 1. (CXX) g++ options: -O3 -march=native -std=c++11
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Random Numbers GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 300 600 900 1200 1500 SE +/- 10.04, N = 3 SE +/- 2.69, N = 3 SE +/- 12.43, N = 3 SE +/- 0.16, N = 3 1061.48 1069.48 1282.03 1296.98 1. (CXX) g++ options: -O3 -march=native -std=c++11
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Vector GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 76.26 77.50 66.78 67.11 1. (CXX) g++ options: -O3 -march=native -std=c++11
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Function Objects GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 13.84 14.82 14.76 14.70 1. (CXX) g++ options: -O3 -march=native -std=c++11
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Abstraction GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 28.30 28.52 25.86 26.03 1. (CXX) g++ options: -O3 -march=native -std=c++11
FLAC Audio Encoding This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 2 4 6 8 10 SE +/- 0.006, N = 5 SE +/- 0.007, N = 5 SE +/- 0.003, N = 5 SE +/- 0.005, N = 5 8.042 8.073 7.145 7.192 -fvisibility=hidden -fvisibility=hidden 1. (CXX) g++ options: -O3 -march=native -logg -lm
LAME MP3 Encoding LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 2 4 6 8 10 SE +/- 0.007, N = 3 SE +/- 0.012, N = 3 SE +/- 0.008, N = 3 SE +/- 0.001, N = 6 6.701 6.729 7.788 7.951 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -lncurses 1. (CC) gcc options: -O3 -pipe -march=native -lm
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 2K 4K 6K 8K 10K SE +/- 76.26, N = 3 SE +/- 26.44, N = 3 SE +/- 24.98, N = 3 8135.2 8111.6 7531.2 1. (CC) gcc options: -pthread -O3 -march=native -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 5K 10K 15K 20K 25K SE +/- 239.62, N = 3 SE +/- 309.06, N = 4 SE +/- 404.65, N = 3 20287 24184 23559 1. (CC) gcc options: -pthread -O3 -march=native -lm
Timed MrBayes Analysis This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 16 32 48 64 80 SE +/- 0.32, N = 3 SE +/- 0.27, N = 3 SE +/- 0.32, N = 3 SE +/- 0.36, N = 3 69.79 70.33 70.71 64.85 -mabm -mabm 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -O3 -std=c99 -pedantic -march=native -lm
Himeno Benchmark The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 1100 2200 3300 4400 5500 SE +/- 51.56, N = 7 SE +/- 61.37, N = 3 SE +/- 77.03, N = 3 SE +/- 84.96, N = 3 4898.17 4583.35 4866.90 4983.28 1. (CC) gcc options: -O3 -march=native -mavx2
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: f32 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 0.4188 0.8376 1.2564 1.6752 2.094 SE +/- 0.00636, N = 3 SE +/- 0.00269, N = 3 SE +/- 0.00428, N = 3 1.86131 1.73710 1.67315 -fopenmp - MIN: 1.81 -fopenmp - MIN: 1.67 -fopenmp=libomp - MIN: 1.62 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.22.0 Backend: BLAS GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 8 16 24 32 40 SE +/- 0.41, N = 3 SE +/- 0.56, N = 12 SE +/- 0.60, N = 15 29.33 32.76 33.30 1. (CXX) g++ options: -O3 -march=native -lpthread
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 12 24 36 48 60 SE +/- 0.24, N = 3 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 52.47 52.28 51.33 -fopenmp - MIN: 51.43 -fopenmp - MIN: 51.18 -fopenmp=libomp - MIN: 50.48 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.22.0 Backend: Random GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 20K 40K 60K 80K 100K SE +/- 275.83, N = 3 SE +/- 354.64, N = 3 SE +/- 553.66, N = 3 105805.0 105996.0 100236.8 1. (CXX) g++ options: -O3 -march=native -lpthread
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 30 60 90 120 150 SE +/- 1.45, N = 3 SE +/- 1.55, N = 3 SE +/- 0.15, N = 3 124.28 125.01 118.99 -fopenmp - MIN: 122.25 -fopenmp - MIN: 122.48 -fopenmp=libomp - MIN: 118.28 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Recurrent Neural Network Training - Data Type: f32 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 40 80 120 160 200 SE +/- 0.39, N = 3 SE +/- 0.16, N = 3 SE +/- 0.38, N = 3 194.08 194.77 145.85 -fopenmp - MIN: 192.29 -fopenmp - MIN: 192.97 -fopenmp=libomp - MIN: 143.95 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
GROMACS The Gromacs molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2019.4 Water Benchmark GCC 10.0.0 20191208 GCC 9.2.1 0.5661 1.1322 1.6983 2.2644 2.8305 SE +/- 0.005, N = 3 SE +/- 0.001, N = 3 2.515 2.516 1. (CXX) g++ options: -mavx2 -mfma -O3 -march=native -std=c++11 -funroll-all-loops -pthread -lrt -lpthread -lm
Parboil The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP GCC 10.0.0 20191208 GCC 9.2.1 0.283 0.566 0.849 1.132 1.415 SE +/- 0.007993, N = 3 SE +/- 0.002849, N = 3 1.257410 1.257716 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP Stencil GCC 10.0.0 20191208 GCC 9.2.1 2 4 6 8 10 SE +/- 0.036635, N = 3 SE +/- 0.021046, N = 3 7.551706 7.576396 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP MRI Gridding GCC 10.0.0 20191208 GCC 9.2.1 14 28 42 56 70 SE +/- 0.24, N = 3 SE +/- 0.15, N = 3 62.94 49.00 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD GCC 10.0.0 20191208 GCC 9.2.1 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 10.09 10.10 1. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 3 6 9 12 15 SE +/- 0.029, N = 3 SE +/- 0.052, N = 3 SE +/- 0.133, N = 3 9.185 9.151 9.633 -O2 -lOpenCL -O2 -lOpenCL -O3 -fopenmp 1. (CXX) g++ options:
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP Streamcluster GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.54, N = 15 SE +/- 0.06, N = 3 19.07 19.76 18.82 -O2 -lOpenCL -O2 -lOpenCL -O3 -fopenmp 1. (CXX) g++ options:
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding GCC 10.0.0 20191208 GCC 9.2.1 700 1400 2100 2800 3500 SE +/- 13.81, N = 3 SE +/- 2.38, N = 3 3339.33 3376.27 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding GCC 10.0.0 20191208 GCC 9.2.1 1200 2400 3600 4800 6000 SE +/- 34.80, N = 3 SE +/- 37.73, N = 3 5255.51 5509.30 1. (CXX) g++ options: -lpthread
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding GCC 10.0.0 20191208 GCC 9.2.1 900 1800 2700 3600 4500 SE +/- 46.05, N = 3 SE +/- 0.00, N = 3 3716.33 4096.25 1. (CXX) g++ options: -lpthread
QMCPACK QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.8 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 500 1000 1500 2000 2500 1878.1 1893.6 2262.8 -finline-limit=1000 -funroll-all-loops -finline-limit=1000 -funroll-all-loops 1. (CXX) g++ options: -O3 -march=native -fopenmp -fomit-frame-pointer -fstrict-aliasing -ffast-math -lm
miniFE MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 2K 4K 6K 8K 10K SE +/- 4.74, N = 3 SE +/- 9.20, N = 3 SE +/- 3.20, N = 3 7767.98 7777.50 8037.33 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
Stockfish This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 20M 40M 60M 80M 100M SE +/- 1221575.84, N = 3 SE +/- 74252.03, N = 3 SE +/- 194228.81, N = 3 80909082 76737462 81336054 1. (CXX) g++ options: -m64 -lpthread -O3 -march=native -fno-exceptions -std=c++11 -pedantic -msse -msse3 -mpopcnt -flto
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.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 13K 26K 39K 52K 65K SE +/- 170.74, N = 3 SE +/- 184.04, N = 3 SE +/- 3.28, N = 3 SE +/- 246.24, N = 3 41784 41482 1932 60586 -fopenmp -fopenmp -fopenmp 1. (CC) gcc options: -m64 -lssl -lcrypto -lgmp -pthread -lm -lz -ldl -lcrypt
Zstd Compression This test measures the time needed to compress a sample file (an Ubuntu file-system image) using Zstd compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 3 6 9 12 15 SE +/- 0.089, N = 3 SE +/- 0.125, N = 3 SE +/- 0.033, N = 3 SE +/- 0.100, N = 3 10.052 10.040 10.107 9.817 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
AOM AV1 This is a simple test of the AOMedia AV1 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2019-09-16 AV1 Video Encoding GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 0.0338 0.0676 0.1014 0.1352 0.169 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.15 0.14 0.15 0.15 1. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Summer Nature 4K GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 23.89 23.74 21.17 23.94 1. (CXX) g++ options: -O3 -march=native -lpthread
OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Summer Nature 1080p GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.22, N = 3 77.92 77.11 70.28 78.57 1. (CXX) g++ options: -O3 -march=native -lpthread
OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Chimera 1080p 10-bit GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 21.93 22.01 23.11 24.19 1. (CXX) g++ options: -O3 -march=native -lpthread
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.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.30, N = 3 SE +/- 0.45, N = 15 SE +/- 0.01, N = 3 27.39 28.62 31.75 31.59 1. (CC) gcc options: -lm -O3 -march=native
Tungsten Renderer Tungsten is a C++ physically based renderer that makes use of Intel's Embree ray tracing library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 3 6 9 12 15 SE +/- 0.03984, N = 3 SE +/- 0.02093, N = 3 SE +/- 0.01435, N = 3 SE +/- 0.01343, N = 3 9.44960 9.70952 8.72625 8.70024 -fstrict-aliasing -fstrict-aliasing 1. (CXX) g++ options: -O3 -march=native -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -rdynamic -ljpeg -lpthread -ldl
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 18.22 19.20 19.16 19.35 -fstrict-aliasing -fstrict-aliasing 1. (CXX) g++ options: -O3 -march=native -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -rdynamic -ljpeg -lpthread -ldl
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 0.9158 1.8316 2.7474 3.6632 4.579 SE +/- 0.01371, N = 3 SE +/- 0.01280, N = 3 SE +/- 0.01369, N = 3 SE +/- 0.00501, N = 3 3.36927 3.37419 4.05176 4.07043 -fstrict-aliasing -fstrict-aliasing 1. (CXX) g++ options: -O3 -march=native -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -rdynamic -ljpeg -lpthread -ldl
OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Volumetric Caustic GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 0.9178 1.8356 2.7534 3.6712 4.589 SE +/- 0.04581, N = 3 SE +/- 0.03613, N = 3 SE +/- 0.00780, N = 3 SE +/- 0.00668, N = 3 3.96697 4.07902 3.72488 3.68186 -fstrict-aliasing -fstrict-aliasing 1. (CXX) g++ options: -O3 -march=native -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -rdynamic -ljpeg -lpthread -ldl
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format using a sample 1080p video. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.1 vpxenc VP9 1080p Video Encode GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 50 100 150 200 250 SE +/- 1.29, N = 3 SE +/- 1.49, N = 3 SE +/- 1.73, N = 15 SE +/- 1.20, N = 3 195.63 197.37 207.68 207.78 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=c++11
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.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 40 80 120 160 200 SE +/- 2.04, N = 8 SE +/- 0.53, N = 3 SE +/- 0.76, N = 3 SE +/- 1.58, N = 12 199.22 197.93 196.10 198.29 -mstack-alignment=64 -mstack-alignment=64 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -march=native -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 130 260 390 520 650 SE +/- 4.43, N = 3 SE +/- 2.39, N = 3 SE +/- 1.62, N = 3 SE +/- 2.49, N = 3 612.94 587.24 625.11 623.05 MIN: 452.17 / MAX: 769.81 MIN: 439.81 / MAX: 722.49 MIN: 468.04 / MAX: 781 MIN: 475.37 / MAX: 782.95 1. (CC) gcc options: -O3 -march=native -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 4K GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 60 120 180 240 300 SE +/- 0.64, N = 3 SE +/- 1.13, N = 3 SE +/- 0.34, N = 3 SE +/- 0.37, N = 3 289.29 285.28 291.76 288.60 MIN: 172.47 / MAX: 306.73 MIN: 168.88 / MAX: 304.29 MIN: 174.15 / MAX: 309.6 MIN: 170.73 / MAX: 306.52 1. (CC) gcc options: -O3 -march=native -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 1080p GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 150 300 450 600 750 SE +/- 0.42, N = 3 SE +/- 1.97, N = 3 SE +/- 2.78, N = 3 SE +/- 1.73, N = 3 676.37 667.33 685.40 674.39 MIN: 396.97 / MAX: 738.73 MIN: 387.89 / MAX: 728.98 MIN: 400.43 / MAX: 750.08 MIN: 376.28 / MAX: 738.32 1. (CC) gcc options: -O3 -march=native -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p 10-bit GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.24, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 94.47 99.72 74.45 73.36 MIN: 56.43 / MAX: 192.99 MIN: 60.51 / MAX: 199.48 MIN: 45.96 / MAX: 154.32 MIN: 45.63 / MAX: 149.13 1. (CC) gcc options: -O3 -march=native -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.org Frames Per Second, More Is Better x265 3.1.2 H.265 1080p Video Encoding GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 15 30 45 60 75 SE +/- 0.29, N = 3 SE +/- 0.10, N = 3 SE +/- 0.39, N = 3 SE +/- 0.07, N = 3 65.74 64.69 67.11 66.27 1. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma
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.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 7 14 21 28 35 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 19.13 19.16 30.84 30.97 1. (CC) gcc options: -lm -lpthread -O3 -march=native
TTSIOD 3D Renderer A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 9.0.0 200 400 600 800 1000 SE +/- 1.33, N = 3 SE +/- 2.99, N = 3 SE +/- 0.09, N = 3 961.97 935.12 69.85 1. (CXX) g++ options: -O3 -march=native -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
Smallpt Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples GCC 10.0.0 20191208 GCC 9.2.1 1.0744 2.1488 3.2232 4.2976 5.372 SE +/- 0.107, N = 15 SE +/- 0.006, N = 3 4.775 3.492 1. (CXX) g++ options: -fopenmp -O3 -march=native
NGINX Benchmark This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 9K 18K 27K 36K 45K SE +/- 490.20, N = 3 SE +/- 457.53, N = 3 SE +/- 238.62, N = 3 SE +/- 326.86, N = 3 43035.46 43426.72 43580.60 43783.30 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
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.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 7K 14K 21K 28K 35K SE +/- 54.98, N = 3 SE +/- 27.04, N = 3 SE +/- 71.82, N = 3 SE +/- 32.67, N = 3 34157.76 34228.50 34327.90 34144.39 1. (CC) gcc options: -shared -fPIC -pthread -O3 -march=native
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 1500 3000 4500 6000 7500 SE +/- 20.75, N = 3 SE +/- 21.05, N = 3 SE +/- 21.60, N = 3 SE +/- 29.40, N = 3 7173.7 7178.8 5189.1 7191.6 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -lssl -lcrypto -ldl
SQLite This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 1 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 14.24 14.25 14.25 14.20 1. (CC) gcc options: -O3 -march=native -lz -lm -ldl -lpthread
Facebook RocksDB This is a benchmark of Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill GCC 10.0.0 20191208 GCC 9.2.1 200K 400K 600K 800K 1000K SE +/- 13468.75, N = 3 SE +/- 4040.85, N = 3 930897 1023335 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read GCC 10.0.0 20191208 GCC 9.2.1 30M 60M 90M 120M 150M SE +/- 467553.12, N = 3 SE +/- 234281.58, N = 3 145368967 142287766 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill GCC 10.0.0 20191208 GCC 9.2.1 200K 400K 600K 800K 1000K SE +/- 4276.33, N = 3 SE +/- 10427.62, N = 3 1024733 1083649 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync GCC 10.0.0 20191208 GCC 9.2.1 5K 10K 15K 20K 25K SE +/- 40.43, N = 3 SE +/- 29.29, N = 3 24277 24368 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing GCC 10.0.0 20191208 GCC 9.2.1 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 38218.40, N = 15 SE +/- 73789.66, N = 4 4945916 4950890 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
SQLite Speedtest This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 13 26 39 52 65 SE +/- 0.10, N = 3 SE +/- 0.46, N = 3 SE +/- 0.13, N = 3 SE +/- 0.44, N = 3 57.12 56.17 59.91 58.33 1. (CC) gcc options: -O3 -march=native -ldl -lz -lpthread
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 140K 280K 420K 560K 700K SE +/- 876.37, N = 3 SE +/- 1703.60, N = 3 SE +/- 1018.99, N = 3 SE +/- 2145.94, N = 3 673644.96 654500.68 668836.61 675821.10 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write GCC 10.0.0 20191208 GCC 9.2.1 LLVM Clang 10.0 20191222 LLVM Clang 9.0.0 7K 14K 21K 28K 35K SE +/- 2238.03, N = 12 SE +/- 77.46, N = 3 SE +/- 1738.68, N = 15 SE +/- 127.72, N = 3 15513.44 30910.99 14868.68 31491.38 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
GCC 10.0.0 20191208 Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32768MB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz), Audio: AMD Baffin HDMI/DP, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723
OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: GCC 10.0.0 20191208, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 22 December 2019 11:57 by user pts.
LLVM Clang 10.0 20191222 Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32768MB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz), Audio: AMD Baffin HDMI/DP, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723
OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: Clang 10.0.0, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Notes: Optimized build; Default target: x86_64-unknown-linux-gnu; Host CPU: znver2Disk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 22 December 2019 19:11 by user pts.
GCC 9.2.1 Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32768MB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz), Audio: AMD Baffin HDMI/DP, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723
OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 23 December 2019 05:52 by user pts.
LLVM Clang 9.0.0 Processor: AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads), Motherboard: MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS), Chipset: AMD Starship/Matisse, Memory: 32768MB, Disk: 1000GB Sabrent Rocket 4.0 1TB, Graphics: Gigabyte AMD Radeon 540/540X/550/550X / RX 540X/550/550X 2GB (1206/1750MHz), Audio: AMD Baffin HDMI/DP, Monitor: ASUS VP28U, Network: Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723
OS: Ubuntu 19.10, Kernel: 5.4.0-nvme-hwmon (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.1 (LLVM 9.0.0), Compiler: Clang 9.0.0, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"Disk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Python Notes: Python 2.7.17rc1 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 23 December 2019 13:02 by user pts.