AMD EPYC 7642 benchmarks by Michael Larabel.
Linux 4.19 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: 4.19.0-041900-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: l1tf: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB IBRS_FW
Linux 4.20 OS: Ubuntu 19.10, Kernel: 4.20.0-042000-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: l1tf: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling
Linux 5.0 OS: Ubuntu 19.10, Kernel: 5.0.0-050000-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: l1tf: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling
Linux 5.1 OS: Ubuntu 19.10, Kernel: 5.1.0-050100-generic (x86_64), 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
Linux 5.2 OS: Ubuntu 19.10, Kernel: 5.2.0-050200-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython 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 __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling
Linux 5.3 OS: Ubuntu 19.10, Kernel: 5.3.0-050300-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython 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
Linux 5.4 Git OS: Ubuntu 19.10, Kernel: 5.4.0-999-generic (x86_64) 20191114, 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security 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 IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing Linux 5.2 Linux 5.4 Git Linux 5.3 Linux 4.19 Linux 4.20 Linux 5.1 Linux 5.0 5M 10M 15M 20M 25M SE +/- 343954.12, N = 3 SE +/- 262185.79, N = 3 SE +/- 152445.45, N = 3 SE +/- 98020.59, N = 3 SE +/- 227361.43, N = 3 SE +/- 210267.26, N = 5 SE +/- 209148.15, N = 3 25562465.64 25342661.18 25071193.85 20076725.52 19207241.83 17724572.05 16341283.72 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
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 GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth Linux 5.2 Linux 5.4 Git Linux 5.1 Linux 5.3 Linux 4.20 Linux 4.19 Linux 5.0 0.3474 0.6948 1.0422 1.3896 1.737 1.54411 1.51968 1.51464 1.49760 1.05889 1.05287 1.04710 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
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: 64 Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.1 Linux 5.0 Linux 5.3 Linux 5.4 Git 11 22 33 44 55 SE +/- 0.24, N = 3 SE +/- 0.25, N = 3 SE +/- 0.26, N = 3 SE +/- 0.29, N = 3 SE +/- 0.21, N = 3 SE +/- 0.18, N = 3 SE +/- 0.17, N = 3 35.45 41.84 46.21 46.67 46.81 48.60 49.63 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.3 Linux 5.0 Linux 5.4 Git Linux 5.1 5K 10K 15K 20K 25K SE +/- 165.26, N = 3 SE +/- 90.99, N = 3 SE +/- 30.89, N = 3 SE +/- 50.67, N = 3 SE +/- 83.21, N = 3 SE +/- 30.87, N = 3 SE +/- 96.60, N = 3 22759.99 21012.98 19306.41 18882.33 18024.67 17813.09 17038.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Sockperf This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.4 Test: Throughput Linux 4.19 Linux 5.2 Linux 5.1 Linux 4.20 Linux 5.0 Linux 5.3 Linux 5.4 Git 130K 260K 390K 520K 650K SE +/- 6466.62, N = 7 SE +/- 3465.01, N = 5 SE +/- 3214.70, N = 25 SE +/- 6800.46, N = 5 SE +/- 3468.09, N = 25 SE +/- 3138.18, N = 5 SE +/- 4204.73, N = 5 613928 530344 518292 513794 511030 501403 463561 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
IOR IOR is a parallel I/O storage benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Write Test Linux 5.4 Git Linux 5.0 Linux 5.2 Linux 5.1 Linux 5.3 Linux 4.19 Linux 4.20 300 600 900 1200 1500 SE +/- 5.16, N = 3 SE +/- 7.01, N = 3 SE +/- 3.19, N = 3 SE +/- 4.56, N = 3 SE +/- 0.49, N = 3 SE +/- 1.31, N = 3 SE +/- 5.07, N = 3 1321.75 1318.48 1284.88 1282.55 1282.16 1066.92 1015.17 MIN: 839.28 / MAX: 1582.43 MIN: 994.58 / MAX: 1526.05 MIN: 985.73 / MAX: 1508.69 MIN: 906.35 / MAX: 1474.65 MIN: 867.51 / MAX: 1481.34 MIN: 746.27 / MAX: 1274.81 MIN: 755.6 / MAX: 1226.07 1. (CC) gcc options: -O2 -lm -pthread -lmpi
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 Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.4 Git 150K 300K 450K 600K 750K SE +/- 2393.16, N = 3 SE +/- 2647.50, N = 3 SE +/- 1791.01, N = 3 SE +/- 1864.77, N = 3 SE +/- 538.18, N = 3 SE +/- 946.01, N = 3 SE +/- 666.98, N = 3 722889.74 721247.82 581740.70 581546.25 577466.97 575463.82 571175.70 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -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: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Linux 5.2 Linux 5.4 Git Linux 5.0 Linux 5.1 Linux 5.3 Linux 4.19 Linux 4.20 14K 28K 42K 56K 70K SE +/- 1020.40, N = 15 SE +/- 827.41, N = 5 SE +/- 666.67, N = 3 SE +/- 493.29, N = 3 SE +/- 903.68, N = 15 SE +/- 348.01, N = 3 SE +/- 674.28, N = 15 63287 61740 61033 60800 60267 57867 50060 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 Linux 5.1 Linux 5.0 Linux 5.2 Linux 5.4 Git Linux 5.3 Linux 4.19 Linux 4.20 500 1000 1500 2000 2500 SE +/- 3.79, N = 3 SE +/- 9.64, N = 3 SE +/- 6.66, N = 3 SE +/- 2.52, N = 3 SE +/- 4.36, N = 3 SE +/- 4.81, N = 3 SE +/- 3.38, N = 3 2304 2297 2295 2255 2240 1915 1825 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 Linux 5.2 Linux 5.4 Git Linux 5.1 Linux 5.0 Linux 5.3 Linux 4.19 Linux 4.20 50 100 150 200 250 SE +/- 3.92, N = 15 SE +/- 3.16, N = 5 SE +/- 1.20, N = 3 SE +/- 2.67, N = 3 SE +/- 3.52, N = 15 SE +/- 1.15, N = 3 SE +/- 2.74, N = 15 247 241 239 238 236 226 196 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
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: 128 Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.0 Linux 5.1 Linux 5.4 Git Linux 5.3 20 40 60 80 100 SE +/- 0.78, N = 3 SE +/- 0.35, N = 3 SE +/- 0.12, N = 3 SE +/- 0.28, N = 3 SE +/- 0.36, N = 3 SE +/- 0.22, N = 3 SE +/- 0.11, N = 3 86.36 89.98 98.48 99.69 99.93 105.44 106.72 1. (CC) gcc options: -O2 -lz -lm -ldl -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 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 Linux 5.1 Linux 5.0 Linux 5.2 Linux 5.4 Git Linux 5.3 Linux 4.20 Linux 4.19 500 1000 1500 2000 2500 SE +/- 4.16, N = 3 SE +/- 8.11, N = 3 SE +/- 9.21, N = 3 SE +/- 3.18, N = 3 SE +/- 4.18, N = 3 SE +/- 25.85, N = 15 SE +/- 7.84, N = 3 2112 2108 2092 1898 1898 1822 1734 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 Linux 5.1 Linux 5.0 Linux 5.2 Linux 5.3 Linux 5.4 Git Linux 4.20 Linux 4.19 120K 240K 360K 480K 600K SE +/- 881.92, N = 3 SE +/- 2333.33, N = 3 SE +/- 2333.33, N = 3 SE +/- 1000.00, N = 3 SE +/- 666.67, N = 3 SE +/- 6631.00, N = 15 SE +/- 2000.00, N = 3 540667 539667 535333 486000 485667 466467 444000 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
Hackbench This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.1 Linux 5.0 Linux 5.3 Linux 5.4 Git 7 14 21 28 35 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.22, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 25.20 26.24 26.34 26.64 26.71 29.88 30.60 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.4 Git 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 13.94 14.32 14.51 14.69 14.75 15.98 16.24 1. (CC) gcc options: -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process Linux 4.19 Linux 4.20 Linux 5.1 Linux 5.2 Linux 5.0 Linux 5.3 Linux 5.4 Git 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 13.30 13.55 13.69 13.76 13.80 15.09 15.28 1. (CC) gcc options: -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 Read Linux 4.19 Linux 4.20 Linux 5.3 Linux 5.0 Linux 5.4 Git Linux 5.1 Linux 5.2 40M 80M 120M 160M 200M SE +/- 1203747.24, N = 3 SE +/- 520913.11, N = 3 SE +/- 57111.29, N = 3 SE +/- 256647.25, N = 3 SE +/- 876467.18, N = 3 SE +/- 931233.21, N = 3 SE +/- 1941434.34, N = 5 186016129 185394718 169222387 167208762 167033565 166608589 163416242 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Classroom - Compute: CPU-Only Linux 4.19 Linux 4.20 Linux 5.1 Linux 5.2 Linux 5.0 Linux 5.4 Git Linux 5.3 30 60 90 120 150 SE +/- 0.08, N = 3 SE +/- 0.56, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.46, N = 3 SE +/- 0.27, N = 3 SE +/- 0.20, N = 3 111.08 112.01 121.64 121.99 122.62 123.12 123.22
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 Sync Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.3 Linux 5.2 Linux 5.4 Git 40K 80K 120K 160K 200K SE +/- 613.59, N = 3 SE +/- 116.64, N = 3 SE +/- 263.50, N = 3 SE +/- 57.74, N = 3 SE +/- 284.11, N = 3 SE +/- 336.19, N = 3 SE +/- 409.63, N = 3 186362 183227 170948 170485 169927 169283 168454 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
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 Linux 4.20 Linux 5.2 Linux 4.19 Linux 5.3 Linux 5.0 Linux 5.1 Linux 5.4 Git 700 1400 2100 2800 3500 SE +/- 5.54, N = 3 SE +/- 23.30, N = 3 SE +/- 30.06, N = 3 SE +/- 21.18, N = 3 SE +/- 32.95, N = 15 SE +/- 24.10, N = 3 SE +/- 22.73, N = 3 3401.94 3378.89 3369.73 3368.84 3316.84 3121.91 3095.72 1. (CC) gcc options: -O3 -mavx2
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: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory Linux 5.0 Linux 4.20 Linux 4.19 Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.4 Git 300 600 900 1200 1500 SE +/- 5.69, N = 3 SE +/- 8.57, N = 3 SE +/- 3.84, N = 3 SE +/- 1.67, N = 3 SE +/- 3.18, N = 3 SE +/- 4.06, N = 3 1195 1192 1190 1176 1169 1105 1088 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 Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.4 Git 300 600 900 1200 1500 SE +/- 1.86, N = 3 SE +/- 3.53, N = 3 SE +/- 3.84, N = 3 SE +/- 0.88, N = 3 SE +/- 1.15, N = 3 SE +/- 2.19, N = 3 SE +/- 2.33, N = 3 1195 1193 1190 1181 1166 1129 1089 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 Linux 5.1 Linux 5.2 Linux 5.0 Linux 4.19 Linux 4.20 Linux 5.3 Linux 5.4 Git 200 400 600 800 1000 SE +/- 3.61, N = 3 SE +/- 2.19, N = 3 SE +/- 2.91, N = 3 SE +/- 10.33, N = 3 SE +/- 4.98, N = 3 SE +/- 5.24, N = 3 SE +/- 2.73, N = 3 1159 1153 1153 1123 1114 1062 1058 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
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 Linux 5.3 Linux 5.4 Git Linux 4.19 Linux 5.0 Linux 4.20 Linux 5.2 Linux 5.1 4K 8K 12K 16K 20K 16539.04 16498.66 16325.46 16274.25 15392.67 15183.78 15140.56 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
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 Write Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.4 Git 11K 22K 33K 44K 55K SE +/- 85.19, N = 3 SE +/- 96.49, N = 3 SE +/- 146.05, N = 3 SE +/- 121.61, N = 3 SE +/- 58.84, N = 3 SE +/- 89.09, N = 3 SE +/- 76.69, N = 3 51881.21 51279.17 48849.19 48622.86 48370.51 48206.28 47535.22 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -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 Linux 5.4 Git Linux 4.19 Linux 5.1 Linux 5.2 Linux 5.3 Linux 4.20 Linux 5.0 400 800 1200 1600 2000 SE +/- 27.34, N = 3 SE +/- 20.92, N = 7 SE +/- 26.90, N = 4 SE +/- 24.07, N = 15 SE +/- 8.41, N = 3 SE +/- 20.51, N = 12 SE +/- 31.56, N = 3 2044 1959 1954 1944 1920 1903 1890 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Sockperf This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Ping Pong Linux 4.19 Linux 5.0 Linux 5.1 Linux 4.20 Linux 5.3 Linux 5.2 Linux 5.4 Git 1.1513 2.3026 3.4539 4.6052 5.7565 SE +/- 0.026, N = 5 SE +/- 0.038, N = 5 SE +/- 0.020, N = 5 SE +/- 0.013, N = 5 SE +/- 0.028, N = 5 SE +/- 0.025, N = 5 SE +/- 0.021, N = 5 4.759 4.896 4.897 5.003 5.048 5.057 5.117 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
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: HWB Color Space Linux 4.19 Linux 5.0 Linux 5.1 Linux 5.4 Git Linux 5.3 Linux 4.20 Linux 5.2 300 600 900 1200 1500 SE +/- 5.21, N = 3 SE +/- 1.86, N = 3 SE +/- 7.54, N = 3 SE +/- 6.66, N = 3 SE +/- 4.18, N = 3 SE +/- 4.62, N = 3 SE +/- 5.77, N = 3 1295 1260 1238 1227 1222 1219 1214 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
IOR IOR is a parallel I/O storage benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Read Test Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.1 Linux 5.0 Linux 5.3 Linux 5.4 Git 400 800 1200 1600 2000 SE +/- 2.24, N = 3 SE +/- 6.78, N = 3 SE +/- 4.68, N = 3 SE +/- 0.94, N = 3 SE +/- 6.73, N = 3 SE +/- 1.63, N = 3 SE +/- 0.88, N = 3 2065.61 2011.92 1957.96 1956.10 1955.10 1952.87 1942.90 MIN: 1863.84 / MAX: 2197.06 MIN: 1719.74 / MAX: 2160.71 MIN: 1795.71 / MAX: 2112.41 MIN: 1757.21 / MAX: 2106.98 MIN: 1792.3 / MAX: 2070.14 MIN: 1827.41 / MAX: 2057.45 MIN: 1706.45 / MAX: 2063.35 1. (CC) gcc options: -O2 -lm -pthread -lmpi
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: Sequential Fill Linux 4.20 Linux 5.3 Linux 4.19 Linux 5.4 Git Linux 5.0 Linux 5.2 Linux 5.1 80K 160K 240K 320K 400K SE +/- 3989.10, N = 3 SE +/- 4197.90, N = 3 SE +/- 3198.53, N = 3 SE +/- 4438.49, N = 3 SE +/- 3421.21, N = 3 SE +/- 3655.57, N = 3 SE +/- 785.90, N = 3 374265 370037 364865 363578 359923 358055 353535 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Blender Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Barbershop - Compute: CPU-Only Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.1 Linux 5.0 Linux 5.3 Linux 5.4 Git 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.23, N = 3 SE +/- 0.37, N = 3 SE +/- 0.24, N = 3 SE +/- 0.39, N = 3 SE +/- 0.35, N = 3 SE +/- 0.72, N = 3 190.55 191.55 200.09 200.30 200.73 201.29 201.46
ACES DGEMM This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate Linux 5.1 Linux 5.2 Linux 5.3 Linux 4.19 Linux 5.0 Linux 5.4 Git Linux 4.20 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.22, N = 3 SE +/- 0.21, N = 3 SE +/- 0.19, N = 5 SE +/- 0.21, N = 3 14.19 14.09 14.07 14.01 13.99 13.98 13.50 1. (CC) gcc options: -O3 -march=native -fopenmp
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 Linux 4.19 Linux 5.2 Linux 4.20 Linux 5.3 Linux 5.1 Linux 5.4 Git Linux 5.0 11 22 33 44 55 SE +/- 0.60, N = 4 SE +/- 0.60, N = 4 SE +/- 0.48, N = 5 SE +/- 0.27, N = 12 SE +/- 0.24, N = 10 SE +/- 0.00, N = 12 50.00 48.21 48.21 48.10 48.02 47.86 47.62 MIN: 43.48 / MAX: 52.63 MIN: 45.45 / MAX: 52.63 MIN: 43.48 / MAX: 52.63 MIN: 45.45 / MAX: 52.63 MIN: 41.67 / MAX: 52.63 MIN: 43.48 / MAX: 52.63 MIN: 41.67 / MAX: 52.63
ASKAP This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding Linux 5.2 Linux 5.3 Linux 5.4 Git Linux 4.20 Linux 4.19 Linux 5.1 Linux 5.0 1400 2800 4200 5600 7000 SE +/- 51.54, N = 3 SE +/- 51.54, N = 3 SE +/- 38.66, N = 4 SE +/- 0.00, N = 3 SE +/- 30.97, N = 15 SE +/- 54.54, N = 15 SE +/- 33.45, N = 15 6442.51 6390.97 6378.09 6339.43 6175.02 6151.17 6137.47 1. (CXX) g++ options: -lpthread
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 Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.4 Git Linux 5.3 Linux 5.2 60 120 180 240 300 SE +/- 1.01, N = 3 SE +/- 0.70, N = 3 SE +/- 0.63, N = 3 SE +/- 3.01, N = 3 SE +/- 1.61, N = 3 SE +/- 2.70, N = 3 SE +/- 3.02, N = 3 294.90 288.79 286.95 286.69 285.78 283.52 281.27 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -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: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Linux 5.0 Linux 5.1 Linux 4.20 Linux 4.19 Linux 5.2 Linux 5.3 Linux 5.4 Git 50K 100K 150K 200K 250K SE +/- 881.92, N = 3 SE +/- 666.67, N = 3 SE +/- 577.35, N = 3 SE +/- 1201.85, N = 3 SE +/- 333.33, N = 3 SE +/- 333.33, N = 3 227667 226667 226000 226000 225667 220333 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: No - Block Size: 4KB - Disk Target: Default Test Directory Linux 5.0 Linux 5.1 Linux 4.20 Linux 4.19 Linux 5.2 Linux 5.3 Linux 5.4 Git 200 400 600 800 1000 SE +/- 2.96, N = 3 SE +/- 2.52, N = 3 SE +/- 2.65, N = 3 SE +/- 4.04, N = 3 SE +/- 0.67, N = 3 889 887 883 882 881 861 850 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
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Firefox Linux 4.20 Linux 5.1 Linux 5.4 Git Linux 5.2 Linux 5.3 Linux 4.19 Linux 5.0 6K 12K 18K 24K 30K SE +/- 193.22, N = 3 SE +/- 116.89, N = 3 SE +/- 142.82, N = 3 SE +/- 275.73, N = 7 SE +/- 331.11, N = 3 SE +/- 346.00, N = 3 SE +/- 355.39, N = 3 26129 26118 25869 25739 25630 25339 25006 1. firefox 70.0.1
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 usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency Linux 5.2 Linux 4.19 Linux 5.0 Linux 5.1 Linux 5.4 Git Linux 4.20 Linux 5.3 0.2607 0.5214 0.7821 1.0428 1.3035 1.10960 1.13436 1.13548 1.13674 1.14714 1.15245 1.15864 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
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 Linux 5.3 Linux 4.20 Linux 5.4 Git Linux 5.1 Linux 5.0 Linux 5.2 Linux 4.19 80K 160K 240K 320K 400K SE +/- 2504.78, N = 3 SE +/- 265.67, N = 3 SE +/- 3369.74, N = 3 SE +/- 3149.20, N = 3 SE +/- 2260.59, N = 3 SE +/- 3274.37, N = 3 SE +/- 4127.34, N = 15 356507 356242 351130 350102 346493 344395 341457 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Apache Benchmark This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Linux 5.2 Linux 4.20 Linux 4.19 Linux 5.4 Git Linux 5.1 Linux 5.0 Linux 5.3 6K 12K 18K 24K 30K SE +/- 112.59, N = 3 SE +/- 230.93, N = 3 SE +/- 61.73, N = 3 SE +/- 163.62, N = 3 SE +/- 78.31, N = 3 SE +/- 182.72, N = 3 SE +/- 12.14, N = 3 26791.01 26722.02 26677.41 26068.79 26047.28 25995.77 25689.25 1. (CC) gcc options: -shared -fPIC -O2 -pthread
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: Read While Writing Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.4 Git Linux 5.3 Linux 5.1 Linux 5.2 1.5M 3M 4.5M 6M 7.5M SE +/- 20358.98, N = 3 SE +/- 23548.23, N = 3 SE +/- 71047.20, N = 3 SE +/- 35505.31, N = 3 SE +/- 47412.86, N = 3 SE +/- 23444.70, N = 3 SE +/- 45736.83, N = 3 6960064 6950399 6780873 6748932 6707642 6690902 6675991 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -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: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Linux 5.1 Linux 5.0 Linux 4.20 Linux 5.2 Linux 4.19 Linux 5.4 Git Linux 5.3 50K 100K 150K 200K 250K SE +/- 1201.85, N = 3 SE +/- 333.33, N = 3 SE +/- 881.92, N = 3 SE +/- 577.35, N = 3 SE +/- 2723.36, N = 4 212333 212333 211000 210333 210000 207000 204500 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 Linux 5.1 Linux 5.0 Linux 4.20 Linux 4.19 Linux 5.2 Linux 5.4 Git Linux 5.3 200 400 600 800 1000 SE +/- 5.03, N = 3 SE +/- 1.76, N = 3 SE +/- 3.28, N = 3 SE +/- 2.33, N = 3 SE +/- 2.96, N = 3 SE +/- 1.76, N = 3 SE +/- 10.72, N = 4 829 829 824 822 821 810 799 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
Timed HMMer Search This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search Linux 5.2 Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.3 Linux 5.1 Linux 5.4 Git 2 4 6 8 10 SE +/- 0.053, N = 3 SE +/- 0.021, N = 3 SE +/- 0.068, N = 6 SE +/- 0.082, N = 3 SE +/- 0.065, N = 3 SE +/- 0.056, N = 3 SE +/- 0.081, N = 3 6.069 6.105 6.220 6.239 6.255 6.262 6.285 1. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -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: Swirl Linux 4.19 Linux 5.1 Linux 5.0 Linux 5.3 Linux 4.20 Linux 5.4 Git Linux 5.2 300 600 900 1200 1500 SE +/- 1.15, N = 3 SE +/- 1.00, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 SE +/- 1.20, N = 3 SE +/- 1.67, N = 3 1627 1604 1604 1598 1595 1587 1572 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
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 GFLOP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte Linux 4.19 Linux 5.2 Linux 5.3 Linux 5.0 Linux 4.20 Linux 5.4 Git Linux 5.1 4 8 12 16 20 17.33 17.17 17.06 17.05 16.96 16.92 16.76 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 Linux 4.19 Linux 5.2 Linux 5.3 Linux 5.0 Linux 4.20 Linux 5.4 Git Linux 5.1 4 8 12 16 20 17.33 17.17 17.06 17.05 16.96 16.92 16.76 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 Linux 5.0 Linux 5.3 Linux 4.20 Linux 5.4 Git Linux 4.19 Linux 5.1 Linux 5.2 5 10 15 20 25 21.62 21.50 21.46 21.39 21.23 21.10 20.99 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
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: Noise-Gaussian Linux 4.20 Linux 4.19 Linux 5.4 Git Linux 5.0 Linux 5.2 Linux 5.1 Linux 5.3 130 260 390 520 650 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 SE +/- 2.40, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 605 605 594 594 593 589 588 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 Linux 4.19 Linux 5.3 Linux 5.1 Linux 5.0 Linux 5.4 Git Linux 4.20 Linux 5.2 110 220 330 440 550 SE +/- 1.20, N = 3 SE +/- 2.52, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 1.20, N = 3 SE +/- 0.67, N = 3 524 522 515 515 514 513 510 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Linux 5.2 Linux 5.4 Git Linux 5.1 Linux 5.0 Linux 4.20 Linux 4.19 Linux 5.3 110K 220K 330K 440K 550K SE +/- 3938.22, N = 3 SE +/- 1838.24, N = 3 SE +/- 691.47, N = 3 SE +/- 1155.33, N = 3 SE +/- 723.60, N = 3 SE +/- 1320.55, N = 3 SE +/- 677.46, N = 3 507537 502586 501792 500688 499151 498271 494186
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 Linux 5.1 Linux 5.0 Linux 4.19 Linux 5.2 Linux 5.3 Linux 5.4 Git Linux 4.20 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 SE +/- 0.27, N = 3 SE +/- 1.25, N = 5 SE +/- 1.18, N = 7 SE +/- 1.40, N = 4 103.00 103.05 103.21 103.93 104.20 105.13 105.65 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
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 8192 MiB Linux 4.19 Linux 5.3 Linux 5.2 Linux 4.20 Linux 5.1 Linux 5.4 Git Linux 5.0 3K 6K 9K 12K 15K SE +/- 29.67, N = 3 SE +/- 28.68, N = 3 SE +/- 67.14, N = 3 SE +/- 94.18, N = 3 SE +/- 12.55, N = 3 SE +/- 95.59, N = 3 SE +/- 30.47, N = 3 15539.42 15303.24 15242.41 15177.67 15172.93 15163.31 15152.88 1. (CC) gcc options: -O3 -march=native
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 Linux 5.2 Linux 5.3 Linux 5.4 Git Linux 5.1 Linux 5.0 Linux 4.19 Linux 4.20 30 60 90 120 150 113.29 112.62 111.88 111.74 111.34 111.06 110.96 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Selenium Benchmark: Maze Solver - Browser: Firefox Linux 4.19 Linux 4.20 Linux 5.1 Linux 5.3 Linux 5.4 Git Linux 5.0 Linux 5.2 1.17 2.34 3.51 4.68 5.85 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 5.1 5.1 5.1 5.1 5.1 5.2 5.2 1. firefox 70.0.1
OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Firefox Linux 5.4 Git Linux 4.20 Linux 5.2 Linux 5.3 Linux 5.0 Linux 5.1 Linux 4.19 15 30 45 60 75 SE +/- 0.09, N = 3 SE +/- 0.23, N = 3 SE +/- 0.10, N = 3 SE +/- 0.42, N = 3 SE +/- 0.20, N = 3 SE +/- 0.38, N = 3 SE +/- 0.29, N = 3 68.76 68.70 68.60 68.40 68.23 67.70 67.50 1. firefox 70.0.1
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.0.0 Scene: Memorial Linux 5.3 Linux 5.2 Linux 4.20 Linux 5.0 Linux 4.19 Linux 5.1 Linux 5.4 Git 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 20.30 20.18 20.17 20.14 20.14 20.11 19.94
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: Volumetric Caustic Linux 4.19 Linux 4.20 Linux 5.3 Linux 5.4 Git Linux 5.1 Linux 5.0 Linux 5.2 0.9959 1.9918 2.9877 3.9836 4.9795 SE +/- 0.00533, N = 3 SE +/- 0.00236, N = 3 SE +/- 0.00552, N = 3 SE +/- 0.00336, N = 3 SE +/- 0.00480, N = 3 SE +/- 0.00264, N = 3 SE +/- 0.00242, N = 3 4.34999 4.35547 4.41098 4.41290 4.41802 4.42436 4.42605 1. (CXX) g++ options: -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 -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
IndigoBench This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Supercar Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.3 Linux 5.1 Linux 5.4 Git Linux 5.0 3 6 9 12 15 SE +/- 0.001, N = 3 SE +/- 0.008, N = 3 SE +/- 0.004, N = 3 SE +/- 0.011, N = 3 SE +/- 0.006, N = 3 SE +/- 0.016, N = 3 SE +/- 0.008, N = 3 9.058 8.988 8.942 8.941 8.940 8.918 8.907
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Firefox Linux 4.19 Linux 5.1 Linux 5.3 Linux 5.2 Linux 5.0 Linux 4.20 Linux 5.4 Git 14 28 42 56 70 SE +/- 0.52, N = 3 SE +/- 0.54, N = 3 SE +/- 0.35, N = 3 SE +/- 0.53, N = 3 SE +/- 0.50, N = 3 SE +/- 0.27, N = 3 SE +/- 0.35, N = 3 61.0 60.7 60.4 60.4 60.4 60.3 60.0 1. firefox 70.0.1
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Linux 5.2 Linux 4.19 Linux 5.4 Git Linux 5.3 Linux 5.1 Linux 5.0 Linux 4.20 500K 1000K 1500K 2000K 2500K SE +/- 8921.76, N = 3 SE +/- 7905.15, N = 3 SE +/- 4316.45, N = 3 SE +/- 4441.04, N = 3 SE +/- 3613.61, N = 3 SE +/- 2743.71, N = 3 SE +/- 8227.87, N = 3 2273593.72 2259261.88 2248510.32 2247022.41 2244518.99 2238135.10 2236833.96 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Timed GCC Compilation This test times how long it takes to build the GNU Compiler Collection (GCC). Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 8.2 Time To Compile Linux 4.19 Linux 5.1 Linux 4.20 Linux 5.0 Linux 5.2 Linux 5.4 Git Linux 5.3 160 320 480 640 800 SE +/- 0.36, N = 3 SE +/- 0.41, N = 3 SE +/- 0.39, N = 3 SE +/- 0.22, N = 3 SE +/- 0.17, N = 3 SE +/- 0.14, N = 3 SE +/- 0.22, N = 3 741.53 742.49 743.02 745.08 745.58 751.65 752.48
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 Linux 4.19 Linux 5.1 Linux 5.0 Linux 5.3 Linux 4.20 Linux 5.4 Git Linux 5.2 110 220 330 440 550 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 505 502 502 501 501 499 498 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 Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.3 Linux 5.1 Linux 5.4 Git Linux 5.2 160 320 480 640 800 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 751 744 743 742 742 741 741 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
IndigoBench This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Bedroom Linux 4.19 Linux 4.20 Linux 5.4 Git Linux 5.3 Linux 5.0 Linux 5.1 Linux 5.2 1.1909 2.3818 3.5727 4.7636 5.9545 SE +/- 0.011, N = 3 SE +/- 0.001, N = 3 SE +/- 0.005, N = 3 SE +/- 0.007, N = 3 SE +/- 0.007, N = 3 SE +/- 0.012, N = 3 SE +/- 0.006, N = 3 5.293 5.287 5.256 5.254 5.248 5.242 5.224
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox Linux 5.3 Linux 5.1 Linux 5.2 Linux 5.4 Git Linux 5.0 Linux 4.19 Linux 4.20 400 800 1200 1600 2000 SE +/- 2.73, N = 3 SE +/- 8.08, N = 3 SE +/- 13.32, N = 3 SE +/- 3.79, N = 3 SE +/- 4.10, N = 3 SE +/- 1.53, N = 3 SE +/- 7.31, N = 3 1779 1782 1782 1783 1790 1791 1802 1. firefox 70.0.1
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 GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access Linux 5.4 Git Linux 4.19 Linux 5.1 Linux 4.20 Linux 5.3 Linux 5.2 Linux 5.0 0.0413 0.0826 0.1239 0.1652 0.2065 0.18353 0.18297 0.18223 0.18209 0.18204 0.18198 0.18141 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
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 Linux 5.0 Linux 4.19 Linux 4.20 Linux 5.3 Linux 5.1 Linux 5.4 Git Linux 5.2 20 40 60 80 100 SE +/- 0.24, N = 3 SE +/- 0.13, N = 3 SE +/- 0.34, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.19, N = 3 77.27 77.41 77.57 77.68 77.90 78.08 78.16 1. (CC) gcc options: -O2 -ldl -lz -lpthread
Selenium This test profile uses the Selenium WebDriver for running various browser benchmarks in different available web browsers. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream - Browser: Firefox Linux 5.3 Linux 5.1 Linux 5.2 Linux 4.20 Linux 5.4 Git Linux 4.19 Linux 5.0 30 60 90 120 150 SE +/- 0.27, N = 3 SE +/- 0.42, N = 3 SE +/- 0.83, N = 3 SE +/- 0.52, N = 3 SE +/- 0.38, N = 3 SE +/- 0.21, N = 3 SE +/- 0.35, N = 3 156.81 156.26 155.96 155.87 155.80 155.61 155.27 1. firefox 70.0.1
ASKAP This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding Linux 5.1 Linux 5.4 Git Linux 5.2 Linux 5.3 Linux 4.19 Linux 5.0 Linux 4.20 1300 2600 3900 5200 6500 SE +/- 17.03, N = 3 SE +/- 7.57, N = 3 SE +/- 16.08, N = 3 SE +/- 6.40, N = 3 SE +/- 6.43, N = 3 SE +/- 19.82, N = 3 SE +/- 16.25, N = 3 5980.58 5959.12 5954.56 5949.87 5934.21 5932.50 5926.03 1. (CXX) g++ options: -lpthread
N-Queens This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time Linux 5.0 Linux 4.20 Linux 4.19 Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.4 Git 0.7441 1.4882 2.2323 2.9764 3.7205 SE +/- 0.001, N = 3 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 SE +/- 0.012, N = 3 SE +/- 0.001, N = 3 3.279 3.281 3.287 3.287 3.288 3.303 3.307 1. (CC) gcc options: -static -fopenmp -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 Linux 5.0 Linux 4.20 Linux 5.2 Linux 5.4 Git Linux 5.3 Linux 5.1 Linux 4.19 2 4 6 8 10 SE +/- 0.05302, N = 3 SE +/- 0.01474, N = 3 SE +/- 0.00317, N = 3 SE +/- 0.06839, N = 3 SE +/- 0.05385, N = 3 SE +/- 0.04443, N = 3 SE +/- 0.01935, N = 3 8.57427 8.58423 8.59725 8.59755 8.60613 8.64465 8.64569 1. (CXX) g++ options: -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 -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
Tinymembench This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset Linux 5.1 Linux 5.0 Linux 5.2 Linux 4.20 Linux 5.4 Git Linux 4.19 Linux 5.3 3K 6K 9K 12K 15K SE +/- 12.40, N = 3 SE +/- 41.10, N = 3 SE +/- 44.50, N = 3 SE +/- 27.92, N = 3 SE +/- 46.36, N = 3 SE +/- 52.75, N = 3 SE +/- 36.01, N = 3 14887.3 14868.3 14862.1 14842.2 14840.1 14826.8 14768.7 1. (CC) gcc options: -O2 -lm
MBW This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB Linux 5.0 Linux 5.3 Linux 5.1 Linux 5.2 Linux 4.19 Linux 4.20 Linux 5.4 Git 2K 4K 6K 8K 10K SE +/- 0.97, N = 3 SE +/- 14.95, N = 3 SE +/- 11.40, N = 3 SE +/- 13.87, N = 3 SE +/- 19.26, N = 3 SE +/- 45.84, N = 3 SE +/- 7.48, N = 3 9054.34 9053.93 9037.68 9017.88 9014.72 8986.49 8982.90 1. (CC) gcc options: -O3 -march=native
Tinymembench This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy Linux 5.2 Linux 4.19 Linux 5.4 Git Linux 5.3 Linux 4.20 Linux 5.0 Linux 5.1 2K 4K 6K 8K 10K SE +/- 20.55, N = 3 SE +/- 23.62, N = 3 SE +/- 13.42, N = 3 SE +/- 20.15, N = 3 SE +/- 8.20, N = 3 SE +/- 35.71, N = 3 SE +/- 104.05, N = 3 8828.0 8821.8 8819.6 8815.0 8807.1 8793.5 8759.6 1. (CC) gcc options: -O2 -lm
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 GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans Linux 4.19 Linux 5.1 Linux 5.3 Linux 5.2 Linux 4.20 Linux 5.0 Linux 5.4 Git 3 6 9 12 15 11.89 11.88 11.88 11.87 11.86 11.85 11.81 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
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 Linux 4.20 Linux 4.19 Linux 5.4 Git Linux 5.2 Linux 5.1 Linux 5.0 Linux 5.3 0.9428 1.8856 2.8284 3.7712 4.714 SE +/- 0.00, N = 12 SE +/- 0.01, N = 3 SE +/- 0.00, N = 5 SE +/- 0.01, N = 3 SE +/- 0.00, N = 6 SE +/- 0.00, N = 4 SE +/- 0.00, N = 5 4.19 4.19 4.17 4.17 4.17 4.17 4.16 MIN: 4.15 / MAX: 4.22 MIN: 4.17 / MAX: 4.22 MIN: 4.13 / MAX: 4.2 MIN: 4.15 / MAX: 4.2 MIN: 4.13 / MAX: 4.2 MIN: 4.15 / MAX: 4.2 MIN: 4.12 / MAX: 4.18
ASKAP This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Gridding Linux 5.4 Git Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.0 Linux 4.19 Linux 4.20 900 1800 2700 3600 4500 SE +/- 11.09, N = 3 SE +/- 10.52, N = 3 SE +/- 20.74, N = 3 SE +/- 11.49, N = 3 SE +/- 5.29, N = 3 SE +/- 2.20, N = 3 SE +/- 3.31, N = 3 4426.90 4421.28 4416.33 4405.54 4404.98 4400.42 4395.88 1. (CXX) g++ options: -lpthread
rav1e Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.1 1080p To AV1 Video Encode Linux 4.19 Linux 5.0 Linux 5.3 Linux 5.4 Git Linux 5.2 Linux 4.20 Linux 5.1 0.2356 0.4712 0.7068 0.9424 1.178 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 SE +/- 0.004, N = 3 1.047 1.044 1.043 1.041 1.041 1.041 1.040
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Linux 4.19 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.2 Linux 5.3 Linux 5.4 Git 300 600 900 1200 1500 SE +/- 2.65, N = 3 SE +/- 2.52, N = 3 SE +/- 2.73, N = 3 SE +/- 2.33, N = 3 SE +/- 1.20, N = 3 SE +/- 2.85, N = 3 SE +/- 3.53, N = 3 1255 1257 1257 1257 1257 1263 1263
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 Linux 4.19 Linux 5.0 Linux 5.3 Linux 5.4 Git Linux 5.1 Linux 5.2 Linux 4.20 4K 8K 12K 16K 20K SE +/- 7.08, N = 3 SE +/- 9.54, N = 3 SE +/- 27.14, N = 3 SE +/- 7.47, N = 3 SE +/- 6.97, N = 3 SE +/- 3.58, N = 3 SE +/- 11.04, N = 3 19405.5 19363.9 19352.2 19348.1 19345.7 19328.0 19292.1 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
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 Linux 5.3 Linux 4.20 Linux 5.2 Linux 5.4 Git Linux 5.0 Linux 4.19 Linux 5.1 0.9191 1.8382 2.7573 3.6764 4.5955 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 SE +/- 0.012, N = 3 4.085 4.076 4.075 4.072 4.070 4.068 4.063 1. (CXX) g++ options: -mavx2 -mfma -std=c++11 -O3 -funroll-all-loops -pthread -lrt -lpthread -lm
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Crown Linux 4.20 Linux 4.19 Linux 5.2 Linux 5.0 Linux 5.3 Linux 5.1 Linux 5.4 Git 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 41.51 41.43 41.36 41.34 41.33 41.33 41.30 MIN: 40.68 / MAX: 42.81 MIN: 40.6 / MAX: 42.87 MIN: 40.52 / MAX: 42.75 MIN: 40.53 / MAX: 42.71 MIN: 40.56 / MAX: 42.85 MIN: 40.5 / MAX: 42.74 MIN: 40.47 / MAX: 42.67
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: Water Caustic Linux 5.0 Linux 5.2 Linux 4.20 Linux 5.3 Linux 5.4 Git Linux 4.19 Linux 5.1 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 22.68 22.69 22.70 22.71 22.74 22.78 22.79 1. (CXX) g++ options: -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 -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
Stream This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale Linux 5.0 Linux 5.1 Linux 5.2 Linux 4.20 Linux 5.4 Git Linux 5.3 Linux 4.19 20K 40K 60K 80K 100K SE +/- 15.69, N = 5 SE +/- 36.52, N = 5 SE +/- 48.27, N = 5 SE +/- 37.97, N = 5 SE +/- 31.34, N = 5 SE +/- 81.93, N = 5 SE +/- 32.48, N = 5 89272.3 89240.1 89227.8 89185.5 89161.8 89060.3 88889.0 1. (CC) gcc options: -O3 -march=native -fopenmp
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown Linux 4.19 Linux 4.20 Linux 5.2 Linux 5.0 Linux 5.1 Linux 5.3 Linux 5.4 Git 9 18 27 36 45 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 39.71 39.68 39.62 39.58 39.57 39.55 39.54 MIN: 38.93 / MAX: 41.18 MIN: 38.83 / MAX: 41.37 MIN: 38.78 / MAX: 40.9 MIN: 38.76 / MAX: 40.98 MIN: 38.77 / MAX: 40.8 MIN: 38.73 / MAX: 41.04 MIN: 38.74 / MAX: 40.92
ASKAP This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Degridding Linux 5.4 Git Linux 5.3 Linux 5.1 Linux 5.2 Linux 4.20 Linux 4.19 Linux 5.0 1300 2600 3900 5200 6500 SE +/- 1.75, N = 3 SE +/- 3.03, N = 3 SE +/- 2.02, N = 3 SE +/- 4.62, N = 3 SE +/- 2.02, N = 3 SE +/- 1.74, N = 3 SE +/- 1.74, N = 3 6225.18 6219.12 6217.10 6216.10 6215.09 6210.05 6204.02 1. (CXX) g++ options: -lpthread
Stream This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy Linux 5.0 Linux 4.20 Linux 5.1 Linux 5.4 Git Linux 5.2 Linux 4.19 Linux 5.3 20K 40K 60K 80K 100K SE +/- 31.48, N = 5 SE +/- 21.18, N = 5 SE +/- 56.88, N = 5 SE +/- 49.14, N = 5 SE +/- 21.78, N = 5 SE +/- 14.25, N = 5 SE +/- 21.75, N = 5 91074.4 91014.3 90996.4 90978.2 90943.3 90792.5 90776.5 1. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add Linux 5.0 Linux 4.20 Linux 5.1 Linux 5.4 Git Linux 5.2 Linux 5.3 Linux 4.19 20K 40K 60K 80K 100K SE +/- 23.62, N = 5 SE +/- 39.51, N = 5 SE +/- 39.91, N = 5 SE +/- 51.38, N = 5 SE +/- 41.68, N = 5 SE +/- 14.77, N = 5 SE +/- 33.52, N = 5 98287.9 98259.7 98248.6 98129.1 98121.8 98003.5 97973.8 1. (CC) gcc options: -O3 -march=native -fopenmp
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 Linux 4.19 Linux 5.2 Linux 4.20 Linux 5.0 Linux 5.1 Linux 5.4 Git Linux 5.3 0.1213 0.2426 0.3639 0.4852 0.6065 SE +/- 0.00051, N = 6 SE +/- 0.00087, N = 3 SE +/- 0.00078, N = 3 SE +/- 0.00031, N = 12 SE +/- 0.00088, N = 3 SE +/- 0.00030, N = 12 SE +/- 0.00103, N = 5 0.53744 0.53778 0.53787 0.53803 0.53803 0.53895 0.53901
Stream This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad Linux 5.0 Linux 4.20 Linux 5.2 Linux 5.1 Linux 5.3 Linux 4.19 Linux 5.4 Git 20K 40K 60K 80K 100K SE +/- 31.55, N = 5 SE +/- 47.96, N = 5 SE +/- 23.61, N = 5 SE +/- 58.16, N = 5 SE +/- 43.24, N = 5 SE +/- 38.49, N = 5 SE +/- 45.99, N = 5 99503.3 99463.5 99459.6 99440.1 99328.6 99293.5 99260.8 1. (CC) gcc options: -O3 -march=native -fopenmp
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 Linux 4.20 Linux 4.19 Linux 5.4 Git Linux 5.2 Linux 5.1 Linux 5.0 Linux 5.3 2K 4K 6K 8K 10K SE +/- 2.67, N = 3 SE +/- 4.74, N = 3 SE +/- 1.57, N = 3 SE +/- 4.02, N = 3 SE +/- 4.54, N = 3 SE +/- 5.47, N = 3 SE +/- 7.50, N = 3 10303.5 10301.9 10298.5 10296.4 10291.6 10286.2 10285.1 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
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 GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad Linux 5.1 Linux 5.4 Git Linux 5.3 Linux 5.0 Linux 5.2 Linux 4.19 Linux 4.20 0.4791 0.9582 1.4373 1.9164 2.3955 2.12919 2.12817 2.12775 2.12696 2.12624 2.12613 2.12610 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. OpenBLAS + Open MPI 3.1.3
ASKAP This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Gridding Linux 5.4 Git Linux 5.3 Linux 4.20 Linux 5.1 Linux 5.2 Linux 5.0 Linux 4.19 1000 2000 3000 4000 5000 SE +/- 0.54, N = 3 SE +/- 0.54, N = 3 SE +/- 1.09, N = 3 SE +/- 1.88, N = 3 SE +/- 1.43, N = 3 SE +/- 0.54, N = 3 SE +/- 0.94, N = 3 4565.48 4562.22 4561.67 4561.13 4560.59 4560.04 4559.50 1. (CXX) g++ options: -lpthread
Stress-NG Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Linux 4.19 Linux 4.20 Linux 5.1 Linux 5.0 Linux 5.3 Linux 5.2 Linux 5.4 Git 5M 10M 15M 20M 25M SE +/- 130458.22, N = 3 SE +/- 418176.79, N = 15 SE +/- 443870.92, N = 15 SE +/- 103131.63, N = 3 SE +/- 290872.94, N = 15 SE +/- 289598.04, N = 3 SE +/- 311219.56, N = 15 25591992.41 22418126.51 19657674.70 18691055.36 17871355.69 17684847.92 16748269.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
ASKAP This is a CUDA benchmark of ATNF's ASKAP Benchmark with currently using the tConvolveCuda sub-test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding Linux 5.1 Linux 5.4 Git Linux 4.19 Linux 5.0 Linux 5.3 Linux 4.20 Linux 5.2 1500 3000 4500 6000 7500 SE +/- 192.10, N = 15 SE +/- 88.55, N = 4 SE +/- 146.03, N = 15 SE +/- 154.86, N = 15 SE +/- 59.89, N = 3 SE +/- 59.89, N = 3 SE +/- 56.89, N = 3 7222.86 7056.51 7019.46 7011.16 6886.97 6886.97 6770.19 1. (CXX) g++ options: -lpthread
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: Non-Exponential Linux 4.20 Linux 5.2 Linux 4.19 Linux 5.3 Linux 5.4 Git Linux 5.1 Linux 5.0 0.7613 1.5226 2.2839 3.0452 3.8065 SE +/- 0.01143, N = 3 SE +/- 0.10732, N = 15 SE +/- 0.10050, N = 15 SE +/- 0.10013, N = 15 SE +/- 0.07330, N = 15 SE +/- 0.01223, N = 3 SE +/- 0.03256, N = 3 2.53678 2.93166 3.08623 3.08744 3.27692 3.35999 3.38365 1. (CXX) g++ options: -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 -fstrict-aliasing -O3 -rdynamic -ljpeg -lpthread -ldl
Sockperf This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Under Load Linux 4.19 Linux 5.0 Linux 4.20 Linux 5.1 Linux 5.4 Git Linux 5.3 Linux 5.2 5 10 15 20 25 SE +/- 0.50, N = 25 SE +/- 0.51, N = 25 SE +/- 0.73, N = 25 SE +/- 0.60, N = 25 SE +/- 0.42, N = 25 SE +/- 0.56, N = 25 SE +/- 0.75, N = 20 18.95 19.39 19.55 20.68 21.51 21.68 21.93 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Linux 4.19 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: 4.19.0-041900-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: l1tf: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB IBRS_FW
Testing initiated at 14 November 2019 14:07 by user phoronix.
Linux 4.20 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: 4.20.0-042000-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: l1tf: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling
Testing initiated at 14 November 2019 21:33 by user phoronix.
Linux 5.0 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: 5.0.0-050000-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: l1tf: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling
Testing initiated at 15 November 2019 06:38 by user phoronix.
Linux 5.1 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: 5.1.0-050100-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security Notes: l1tf: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling
Testing initiated at 15 November 2019 14:16 by user phoronix.
Linux 5.2 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: 5.2.0-050200-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython 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 __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling
Testing initiated at 16 November 2019 06:44 by user phoronix.
Linux 5.3 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: 5.3.0-050300-generic (x86_64), 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 ondemand - CPU Microcode: 0x830101cPython 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 17 November 2019 07:26 by user phoronix.
Linux 5.4 Git 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) 20191114, 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 ondemand - CPU Microcode: 0x830101cPython Notes: Python 2.7.17rc1 + Python 3.7.5rc1Security 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 IBRS_FW STIBP: always-on RSB filling + tsx_async_abort: Not affected
Testing initiated at 16 November 2019 15:18 by user phoronix.