AMD EPYC 7642 48-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and llvmpipe 126GB on Ubuntu 19.10 via the Phoronix Test Suite.
EPYC 7642 Processor: AMD EPYC 7642 48-Core @ 2.30GHz (48 Cores / 96 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 129024MB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe 126GB, Audio: AMD Starship/Matisse, Network: 2 x Intel I350
OS: Ubuntu 19.10, Kernel: 5.4.0-999-generic (x86_64) 20191030, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.1 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1024x768
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security 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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig EPYC 7642 3K 6K 9K 12K 15K SE +/- 0.66, N = 2 16270.55 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
HPC Challenge HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL EPYC 7642 20 40 60 80 100 111.53 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
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_all - Data Type: u8s8f32 EPYC 7642 3K 6K 9K 12K 15K SE +/- 11.05, N = 3 12169.4 MIN: 11971.8 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: f32 EPYC 7642 200 400 600 800 1000 SE +/- 4.00, N = 3 794.48 MIN: 766.92 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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: Float + SSE - Size: 2D FFT Size 4096 EPYC 7642 3K 6K 9K 12K 15K SE +/- 75.08, N = 3 15391 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
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: Deconvolution Batch deconv_all - Data Type: f32 EPYC 7642 300 600 900 1200 1500 SE +/- 1.41, N = 3 1532.22 MIN: 1505.24 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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 EPYC 7642 1100 2200 3300 4400 5500 SE +/- 5.58, N = 3 4940.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing EPYC 7642 400 800 1200 1600 2000 SE +/- 18.14, N = 10 2007 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32 EPYC 7642 200 400 600 800 1000 SE +/- 10.65, N = 4 824.63 MIN: 741.05 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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: Float + SSE - Size: 2D FFT Size 2048 EPYC 7642 4K 8K 12K 16K 20K SE +/- 212.99, N = 3 17825 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 70K 140K 210K 280K 350K SE +/- 11506.85, N = 15 328400 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 44.93, N = 15 1283 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 70K 140K 210K 280K 350K SE +/- 12048.18, N = 15 319667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 47.02, N = 15 1249 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 80K 160K 240K 320K 400K SE +/- 18628.36, N = 15 369333 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 72.74, N = 15 1442 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 80K 160K 240K 320K 400K SE +/- 17984.30, N = 15 355333 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 70.23, N = 15 1388 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 70K 140K 210K 280K 350K SE +/- 7895.27, N = 15 304200 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 30.86, N = 15 1189 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 80K 160K 240K 320K 400K SE +/- 16465.22, N = 15 362467 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 64.38, N = 15 1416 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 80K 160K 240K 320K 400K SE +/- 17733.71, N = 15 372867 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 69.13, N = 15 1457 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis EPYC 7642 11 22 33 44 55 SE +/- 0.00, N = 12 47.62 MIN: 43.48 / MAX: 52.63
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 EPYC 7642 11 22 33 44 55 SE +/- 0.41, N = 3 47.34 MIN: 43.82 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 40K 80K 120K 160K 200K SE +/- 2719.18, N = 12 196000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 170 340 510 680 850 SE +/- 10.65, N = 12 766 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write EPYC 7642 10K 20K 30K 40K 50K SE +/- 133.21, N = 3 47269.68 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write EPYC 7642 10K 20K 30K 40K 50K SE +/- 42.98, N = 3 48496.49 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Single Thread - Mode: Read Only EPYC 7642 5K 10K 15K 20K 25K SE +/- 153.60, N = 3 21810.99 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Only EPYC 7642 130K 260K 390K 520K 650K SE +/- 10474.82, N = 3 624614.89 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Gridding EPYC 7642 900 1800 2700 3600 4500 SE +/- 1.84, N = 3 4418.68 1. (CXX) g++ options: -lpthread
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis EPYC 7642 3 6 9 12 15 SE +/- 0.01, N = 12 9.44 MIN: 9.35 / MAX: 9.62
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 EPYC 7642 20 40 60 80 100 SE +/- 0.08, N = 3 103.29 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 14K 28K 42K 56K 70K SE +/- 675.38, N = 9 66356 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 2.54, N = 9 259 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer EPYC 7642 0.936 1.872 2.808 3.744 4.68 SE +/- 0.01, N = 3 4.16 MIN: 4.13 / MAX: 4.18
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 2048 EPYC 7642 1100 2200 3300 4400 5500 SE +/- 25.10, N = 3 5047.4 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer EPYC 7642 1.1475 2.295 3.4425 4.59 5.7375 SE +/- 0.01, N = 5 5.10 MIN: 5.05 / MAX: 5.15
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer EPYC 7642 4 8 12 16 20 SE +/- 0.00, N = 12 14.29 MIN: 13.7 / MAX: 14.49
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen EPYC 7642 110 220 330 440 550 501 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate EPYC 7642 110 220 330 440 550 SE +/- 1.53, N = 3 502 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian EPYC 7642 130 260 390 520 650 587 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced EPYC 7642 160 320 480 640 800 SE +/- 0.58, N = 3 739 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space EPYC 7642 300 600 900 1200 1500 1172 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl EPYC 7642 300 600 900 1200 1500 SE +/- 4.63, N = 3 1574 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SADD EPYC 7642 300K 600K 900K 1200K 1500K SE +/- 24062.10, N = 15 1477511.86 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET EPYC 7642 400K 800K 1200K 1600K 2000K SE +/- 26803.89, N = 15 1706120.78 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPOP EPYC 7642 400K 800K 1200K 1600K 2000K SE +/- 24995.86, N = 15 1823167.52 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs EPYC 7642 0.522 1.044 1.566 2.088 2.61 SE +/- 0.00036, N = 15 2.32007
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Gridding EPYC 7642 1000 2000 3000 4000 5000 SE +/- 0.54, N = 3 4563.85 1. (CXX) g++ options: -lpthread
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 40K 80K 120K 160K 200K SE +/- 2310.84, N = 5 185800 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 160 320 480 640 800 SE +/- 8.91, N = 5 724 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: f32 EPYC 7642 2 4 6 8 10 SE +/- 0.01444, N = 3 7.30358 MIN: 6.9 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: u8s8f32 EPYC 7642 30 60 90 120 150 SE +/- 0.45, N = 3 151.06 MIN: 143.95 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: u8s8f32 EPYC 7642 700 1400 2100 2800 3500 SE +/- 1.33, N = 3 3465.37 MIN: 3453.23 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13b1 ATPase Simulation - 327,506 Atoms EPYC 7642 0.1209 0.2418 0.3627 0.4836 0.6045 SE +/- 0.00100, N = 3 0.53737
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 40K 80K 120K 160K 200K SE +/- 2397.92, N = 4 198500 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 9.68, N = 4 776 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp EPYC 7642 2 4 6 8 10 SE +/- 0.07906, N = 4 6.36774
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_3d - Data Type: f32 EPYC 7642 0.9624 1.9248 2.8872 3.8496 4.812 SE +/- 0.04235, N = 3 4.27741 MIN: 3.91 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Recurrent Neural Network Training - Data Type: f32 EPYC 7642 70 140 210 280 350 SE +/- 0.66, N = 3 304.98 MIN: 299.82 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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: Float + SSE - Size: 2D FFT Size 1024 EPYC 7642 6K 12K 18K 24K 30K SE +/- 286.31, N = 3 29453 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Asian Dragon Obj EPYC 7642 9 18 27 36 45 SE +/- 0.01, N = 3 40.98 MIN: 40.47 / MAX: 41.95
Flexible IO Tester Fio is an advanced disk benchmark that depends upon the kernel's AIO access library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 7.02, N = 3 1097 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 600 1200 1800 2400 3000 SE +/- 0.58, N = 3 2610 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 7.75, N = 3 1103 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 6.36, N = 3 1065 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 40K 80K 120K 160K 200K SE +/- 2333.33, N = 3 200667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 9.17, N = 3 785 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 1.67, N = 3 1086 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 40K 80K 120K 160K 200K SE +/- 577.35, N = 3 205000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 1.76, N = 3 801 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 40K 80K 120K 160K 200K SE +/- 2185.81, N = 3 184667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 160 320 480 640 800 SE +/- 9.28, N = 3 721 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 50K 100K 150K 200K 250K 218000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 852 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 50K 100K 150K 200K 250K SE +/- 666.67, N = 3 217667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 1.67, N = 3 851 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 4.73, N = 3 1097 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 2.08, N = 3 2170 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 2176 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 5.78, N = 3 2170 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 0.58, N = 3 2178 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 4.93, N = 3 1052 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 10.44, N = 3 2001 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 2.73, N = 3 1092 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 1.45, N = 3 2016 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 0.88, N = 3 2021 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 7.67, N = 3 1059 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 5.36, N = 3 1098 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 1.53, N = 3 1101 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 3.48, N = 3 2014 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 600 1200 1800 2400 3000 SE +/- 0.33, N = 3 2612 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 600 1200 1800 2400 3000 2613 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 1.53, N = 3 2253 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 600 1200 1800 2400 3000 2609 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 3.48, N = 3 2241 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 1.86, N = 3 1055 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 3.53, N = 3 2218 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 2.60, N = 3 2344 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 1.20, N = 3 2344 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 4.81, N = 3 2214 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 100K 200K 300K 400K 500K SE +/- 577.35, N = 3 474000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 2.03, N = 3 1852 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 1.76, N = 3 2343 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 200 400 600 800 1000 SE +/- 1.76, N = 3 1051 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 13K 26K 39K 52K 65K SE +/- 503.32, N = 3 62400 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 50 100 150 200 250 SE +/- 2.19, N = 3 244 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 100K 200K 300K 400K 500K SE +/- 333.33, N = 3 477667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 0.88, N = 3 1865 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 90K 180K 270K 360K 450K SE +/- 1452.97, N = 3 399333 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 300 600 900 1200 1500 SE +/- 5.81, N = 3 1560 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 13K 26K 39K 52K 65K SE +/- 208.17, N = 3 59800 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 50 100 150 200 250 SE +/- 0.88, N = 3 234 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory EPYC 7642 500 1000 1500 2000 2500 SE +/- 2.19, N = 3 2345 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 100K 200K 300K 400K 500K SE +/- 1154.70, N = 3 458000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 5.49, N = 3 1789 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 14K 28K 42K 56K 70K SE +/- 1050.40, N = 3 65800 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 4.00, N = 3 257 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 100K 200K 300K 400K 500K SE +/- 6887.99, N = 3 447667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 400 800 1200 1600 2000 SE +/- 26.23, N = 3 1749 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 14K 28K 42K 56K 70K SE +/- 472.58, N = 3 65600 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 1.76, N = 3 256 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 14K 28K 42K 56K 70K SE +/- 606.45, N = 3 65833 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 257 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 16K 32K 48K 64K 80K SE +/- 953.94, N = 3 72900 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 285 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 14K 28K 42K 56K 70K SE +/- 737.11, N = 3 66600 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 2.65, N = 3 260 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 14K 28K 42K 56K 70K SE +/- 940.45, N = 3 65967 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 3.51, N = 3 258 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 16K 32K 48K 64K 80K SE +/- 405.52, N = 3 75133 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 1.45, N = 3 294 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 16K 32K 48K 64K 80K SE +/- 731.06, N = 3 73167 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: No - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 2.73, N = 3 286 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 16K 32K 48K 64K 80K SE +/- 1316.98, N = 3 73933 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: POSIX AIO - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory EPYC 7642 60 120 180 240 300 SE +/- 4.98, N = 3 289 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis EPYC 7642 15 30 45 60 75 SE +/- 0.00, N = 12 66.67 MIN: 62.5 / MAX: 71.43
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: Deconvolution Batch deconv_1d - Data Type: u8s8f32 EPYC 7642 300 600 900 1200 1500 SE +/- 2.35, N = 3 1299.20 MIN: 1292.74 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 EPYC 7642 0.5282 1.0564 1.5846 2.1128 2.641 SE +/- 0.03109, N = 3 2.34775 MIN: 2.18 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll EPYC 7642 0.522 1.044 1.566 2.088 2.61 SE +/- 0.00083, N = 6 2.31998
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 EPYC 7642 2K 4K 6K 8K 10K SE +/- 4.09, N = 3 10290.7 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32 EPYC 7642 300 600 900 1200 1500 SE +/- 1.49, N = 3 1232.91 MIN: 1220.48 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis EPYC 7642 8 16 24 32 40 SE +/- 0.14, N = 8 34.34 MIN: 32.26 / MAX: 34.48
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 EPYC 7642 20 40 60 80 100 SE +/- 0.18, N = 3 107.64 MIN: 105.8 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: f32 EPYC 7642 0.5379 1.0758 1.6137 2.1516 2.6895 SE +/- 0.03547, N = 15 2.39045 MIN: 2.2 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: f32 EPYC 7642 0.4135 0.827 1.2405 1.654 2.0675 SE +/- 0.01672, N = 3 1.83770 MIN: 1.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: u8s8f32 EPYC 7642 7 14 21 28 35 SE +/- 0.13, N = 3 31.55 MIN: 28.36 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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: Float + SSE - Size: 1D FFT Size 256 EPYC 7642 6K 12K 18K 24K 30K SE +/- 380.12, N = 15 29273 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Asian Dragon EPYC 7642 10 20 30 40 50 SE +/- 0.02, N = 3 45.75 MIN: 45.17 / MAX: 46.68
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 1024 EPYC 7642 1300 2600 3900 5200 6500 SE +/- 12.82, N = 3 6062.4 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: log2 EPYC 7642 2 4 6 8 10 SE +/- 0.04550, N = 4 7.65921
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding EPYC 7642 1500 3000 4500 6000 7500 SE +/- 0.00, N = 3 7006.74 1. (CXX) g++ options: -lpthread
MKL-DNN DNNL This is a test of the Intel MKL-DNN (DNNL / Deep Neural Network Library) as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 EPYC 7642 500 1000 1500 2000 2500 SE +/- 4.76, N = 3 2159.60 MIN: 2150.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
glibc bench The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more.
Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once EPYC 7642 0.5216 1.0432 1.5648 2.0864 2.608 SE +/- 0.00084, N = 3 2.31818
OSPray Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: Path Tracer EPYC 7642 70 140 210 280 350 SE +/- 0.00, N = 12 333.33 MIN: 166.67 / MAX: 500
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: Float + SSE - Size: 2D FFT Size 512 EPYC 7642 7K 14K 21K 28K 35K SE +/- 140.44, N = 3 32390 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 EPYC 7642 9K 18K 27K 36K 45K SE +/- 173.54, N = 3 44188 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 2048 EPYC 7642 10K 20K 30K 40K 50K SE +/- 79.85, N = 3 46700 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 EPYC 7642 1400 2800 4200 5600 7000 SE +/- 7.21, N = 3 6670.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -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: Float + SSE - Size: 1D FFT Size 1024 EPYC 7642 10K 20K 30K 40K 50K SE +/- 769.92, N = 3 45116 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -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 512 EPYC 7642 1400 2800 4200 5600 7000 SE +/- 3.87, N = 3 6583.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 512 EPYC 7642 8K 16K 24K 32K 40K SE +/- 138.91, N = 3 38691 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 2048 EPYC 7642 1500 3000 4500 6000 7500 SE +/- 9.94, N = 3 6848.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 128 EPYC 7642 7K 14K 21K 28K 35K SE +/- 198.64, N = 3 32160 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -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: Float + SSE - Size: 2D FFT Size 256 EPYC 7642 7K 14K 21K 28K 35K SE +/- 136.29, N = 3 32004 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 1024 EPYC 7642 1500 3000 4500 6000 7500 SE +/- 0.57, N = 3 7057.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 256 EPYC 7642 1400 2800 4200 5600 7000 SE +/- 13.83, N = 3 6591.2 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 EPYC 7642 2K 4K 6K 8K 10K SE +/- 7.33, N = 3 11648 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 64 EPYC 7642 1600 3200 4800 6400 8000 SE +/- 2.49, N = 3 7292.1 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 512 EPYC 7642 1500 3000 4500 6000 7500 SE +/- 2.95, N = 3 6874.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -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: Float + SSE - Size: 1D FFT Size 64 EPYC 7642 3K 6K 9K 12K 15K SE +/- 46.25, N = 3 16192 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 64 EPYC 7642 2K 4K 6K 8K 10K SE +/- 1.76, N = 3 7948.6 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
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.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p EPYC 7642 60 120 180 240 300 SE +/- 1.79, N = 3 280.66 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -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: Float + SSE - Size: 1D FFT Size 128 EPYC 7642 4K 8K 12K 16K 20K SE +/- 296.75, N = 3 20579 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 64 EPYC 7642 8K 16K 24K 32K 40K SE +/- 39.60, N = 3 36207 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 256 EPYC 7642 1400 2800 4200 5600 7000 SE +/- 4.83, N = 3 6721.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
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.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p EPYC 7642 80 160 240 320 400 SE +/- 2.58, N = 3 366.19 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
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.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p EPYC 7642 80 160 240 320 400 SE +/- 2.45, N = 3 368.51 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -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 128 EPYC 7642 1500 3000 4500 6000 7500 SE +/- 6.33, N = 3 6812.1 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 32 EPYC 7642 7K 14K 21K 28K 35K SE +/- 41.53, N = 3 35001 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 EPYC 7642 2K 4K 6K 8K 10K SE +/- 1.40, N = 3 8611.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 128 EPYC 7642 1400 2800 4200 5600 7000 SE +/- 46.34, N = 3 6451.6 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 32 EPYC 7642 2K 4K 6K 8K 10K SE +/- 7.77, N = 3 8620.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Write Test EPYC 7642 300 600 900 1200 1500 SE +/- 7.99, N = 3 1271.13 MIN: 854.09 / MAX: 1523.23 1. (CC) gcc options: -O2 -lm -pthread -lmpi
HPC Challenge HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Max Ping Pong Bandwidth EPYC 7642 3K 6K 9K 12K 15K 15140.45 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth EPYC 7642 0.3373 0.6746 1.0119 1.3492 1.6865 1.49915 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency EPYC 7642 0.2581 0.5162 0.7743 1.0324 1.2905 1.14712 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access EPYC 7642 0.0412 0.0824 0.1236 0.1648 0.206 0.18317 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad EPYC 7642 0.4789 0.9578 1.4367 1.9156 2.3945 2.12824 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans EPYC 7642 3 6 9 12 15 11.93 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM EPYC 7642 5 10 15 20 25 20.93 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte EPYC 7642 4 8 12 16 20 16.55 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte EPYC 7642 4 8 12 16 20 16.55 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
EPYC 7642 Processor: AMD EPYC 7642 48-Core @ 2.30GHz (48 Cores / 96 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 129024MB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: llvmpipe 126GB, Audio: AMD Starship/Matisse, Network: 2 x Intel I350
OS: Ubuntu 19.10, Kernel: 5.4.0-999-generic (x86_64) 20191030, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 3.3 Mesa 19.2.1 (LLVM 9.0 128 bits), Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 1024x768
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vDisk Notes: NONE / errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandJava Notes: OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security 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 usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling
Testing initiated at 11 November 2019 11:30 by user phoronix.