2 x AMD EPYC 7742 64-Core testing with a AMD DAYTONA_X (RDY1001C BIOS) and llvmpipe 504GB on Ubuntu 19.10 via the Phoronix Test Suite.
Linux 5.6-rc1 Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 19.10, Kernel: 5.6.0-050600rc1-generic (x86_64) 20200209, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.1.0-devel (git-35961b1 2020-02-08 eoan-oibaf-ppa) (LLVM 9.0.1 128 bits), Compiler: GCC 9.2.1 20191008 + LLVM 9.0.0, File-System: ext4, Screen Resolution: 1920x1080
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: 0x830101cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected
Linux 5.5 OS: Ubuntu 19.10, Kernel: 5.5.0-050500-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.1.0-devel (git-35961b1 2020-02-08 eoan-oibaf-ppa) (LLVM 9.0.1 128 bits), Compiler: GCC 9.2.1 20191008 + LLVM 9.0.0, File-System: ext4, Screen Resolution: 1920x1080
EPYC 7742 Linux 5.6 Test OpenBenchmarking.org Phoronix Test Suite 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads) AMD DAYTONA_X (RDY1001C BIOS) AMD Starship/Matisse 504GB 280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFD llvmpipe 504GB VE228 2 x Mellanox MT27710 Ubuntu 19.10 5.6.0-050600rc1-generic (x86_64) 20200209 5.5.0-050500-generic (x86_64) GNOME Shell 3.34.1 X Server 1.20.7 modesetting 1.20.7 3.3 Mesa 20.1.0-devel (git-35961b1 2020-02-08 eoan-oibaf-ppa) (LLVM 9.0.1 128 bits) GCC 9.2.1 20191008 + LLVM 9.0.0 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernels Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution EPYC 7742 Linux 5.6 Test Benchmarks System Logs - --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 -v - NONE / errors=remount-ro,relatime,rw - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x830101c - OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1) - Python 2.7.17 + Python 3.7.5 - 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: conditional RSB filling + tsx_async_abort: Not affected
Linux 5.6-rc1 vs. Linux 5.5 Comparison Phoronix Test Suite Baseline +5.5% +5.5% +11% +11% +16.5% +16.5% +22% +22% 12.4% 6.5% 5.9% 4.6% 4.3% 3.1% 3% 2.9% 2.7% 2.3% 2.3% 2% TCP - Connections/s - 1 22.1% Socket Activity 20.8% Memory Allocations 13.5% TCP - Latency - 1 32 - Process 8.3% Rand Fill Sync Rand Write - Linux AIO - Yes - No - 4KB 6.2% Rand Write - Linux AIO - Yes - No - 4KB 6.1% M.L.U.s.m Rand Read - Linux AIO - Yes - No - 4KB Seq Fill 4.4% Rand Read - Linux AIO - Yes - No - 4KB S.W.P.S 3.5% S.V.M.P Seq Read - Linux AIO - Yes - No - 4KB 3.1% Seq Read - Linux AIO - Yes - No - 4KB 3.1% Launch Programs Create Threads Rand Write - Linux AIO - Yes - No - 2MB 2.8% Rand Write - Linux AIO - Yes - No - 2MB 2.8% Create Processes Semaphores 2.5% 256 A.U.C.T Summer Nature 4K 2.2% SP.B 2% Create Files Ethr Stress-NG OSBench Ethr Hackbench Facebook RocksDB Flexible IO Tester Flexible IO Tester BenchmarkMutex Flexible IO Tester Facebook RocksDB Flexible IO Tester Apache Benchmark Stress-NG Flexible IO Tester Flexible IO Tester OSBench OSBench Flexible IO Tester Flexible IO Tester OSBench Stress-NG MariaDB Renaissance dav1d NAS Parallel Benchmarks OSBench Linux 5.6-rc1 Linux 5.5
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Linux 5.5 Linux 5.6-rc1 300K 600K 900K 1200K 1500K SE +/- 9376.40, N = 3 SE +/- 3867.36, N = 3 1328560.73 1362190.71 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity Linux 5.5 Linux 5.6-rc1 8K 16K 24K 32K 40K SE +/- 113.24, N = 3 SE +/- 233.23, N = 3 29676.91 35841.02 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Linux 5.5 Linux 5.6-rc1 13M 26M 39M 52M 65M SE +/- 620356.30, N = 15 SE +/- 948934.73, N = 15 59872379.34 59771822.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing Linux 5.5 Linux 5.6-rc1 7M 14M 21M 28M 35M SE +/- 347121.49, N = 3 SE +/- 272958.95, N = 3 32195155.01 31227697.91 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Akka Unbalanced Cobwebbed Tree Linux 5.5 Linux 5.6-rc1 10K 20K 30K 40K 50K SE +/- 684.00, N = 40 SE +/- 821.95, N = 40 44035.13 45054.20
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: cos Linux 5.5 Linux 5.6-rc1 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 53.83 53.84
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs Linux 5.5 Linux 5.6-rc1 0.5065 1.013 1.5195 2.026 2.5325 SE +/- 0.00022, N = 15 SE +/- 0.00018, N = 12 2.25095 2.25030
OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Linux 5.5 Linux 5.6-rc1 0.5062 1.0124 1.5186 2.0248 2.531 SE +/- 0.00029, N = 12 SE +/- 0.00019, N = 15 2.24975 2.24987
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 Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory Linux 5.5 Linux 5.6-rc1 200 400 600 800 1000 SE +/- 9.21, N = 3 SE +/- 1.67, N = 3 979 989 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: 2MB - Disk Target: Default Test Directory Linux 5.5 Linux 5.6-rc1 110 220 330 440 550 SE +/- 4.70, N = 3 SE +/- 1.00, N = 3 486 491 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 5.5 Linux 5.6-rc1 50 100 150 200 250 SE +/- 3.54, N = 15 SE +/- 5.28, N = 15 219 210 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 Linux 5.5 Linux 5.6-rc1 12K 24K 36K 48K 60K SE +/- 906.74, N = 15 SE +/- 1353.07, N = 15 56047 53607 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 Linux 5.5 Linux 5.6-rc1 200 400 600 800 1000 SE +/- 4.37, N = 3 SE +/- 11.50, N = 3 1065 1095 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: 2MB - Disk Target: Default Test Directory Linux 5.5 Linux 5.6-rc1 120 240 360 480 600 SE +/- 2.08, N = 3 SE +/- 6.00, N = 3 529 544 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 5.5 Linux 5.6-rc1 160 320 480 640 800 SE +/- 9.00, N = 3 SE +/- 11.36, N = 15 689 732 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 Linux 5.5 Linux 5.6-rc1 40K 80K 120K 160K 200K SE +/- 2333.33, N = 3 SE +/- 2933.98, N = 15 176667 187467 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 5.5 Linux 5.6-rc1 500 1000 1500 2000 2500 SE +/- 3.18, N = 3 SE +/- 1.33, N = 3 2172 2181 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: 2MB - Disk Target: Default Test Directory Linux 5.5 Linux 5.6-rc1 200 400 600 800 1000 SE +/- 1.67, N = 3 SE +/- 0.67, N = 3 1082 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 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 5.5 Linux 5.6-rc1 400 800 1200 1600 2000 SE +/- 26.82, N = 3 SE +/- 10.69, N = 3 1819 1875 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 5.5 Linux 5.6-rc1 100K 200K 300K 400K 500K SE +/- 6887.99, N = 3 SE +/- 2516.61, N = 3 465667 480000 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 5.5 Linux 5.6-rc1 200 400 600 800 1000 SE +/- 8.50, N = 3 SE +/- 5.29, N = 3 1086 1072 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: 2MB - Disk Target: Default Test Directory Linux 5.5 Linux 5.6-rc1 120 240 360 480 600 SE +/- 4.33, N = 3 SE +/- 2.65, N = 3 539 532 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 5.5 Linux 5.6-rc1 200 400 600 800 1000 SE +/- 11.29, N = 15 SE +/- 7.46, N = 12 829 839 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 Linux 5.5 Linux 5.6-rc1 50K 100K 150K 200K 250K SE +/- 2901.89, N = 15 SE +/- 1874.20, N = 12 212200 214833 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
DeepSpeech Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU Linux 5.5 Linux 5.6-rc1 20 40 60 80 100 SE +/- 2.46, N = 12 SE +/- 2.60, N = 12 107.83 108.78
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Linux 5.5 Linux 5.6-rc1 50K 100K 150K 200K 250K SE +/- 2048.15, N = 12 SE +/- 802.80, N = 3 237066.33 240386.00 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Linux 5.5 Linux 5.6-rc1 10K 20K 30K 40K 50K SE +/- 656.19, N = 3 SE +/- 581.12, N = 5 46157.89 46867.46 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Linux 5.5 Linux 5.6-rc1 2K 4K 6K 8K 10K SE +/- 8.53, N = 3 SE +/- 2.40, N = 3 8439.85 8468.86 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Linux 5.5 Linux 5.6-rc1 20K 40K 60K 80K 100K SE +/- 966.23, N = 3 SE +/- 1476.64, N = 4 104921.38 105219.91 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Linux 5.5 Linux 5.6-rc1 900 1800 2700 3600 4500 SE +/- 45.81, N = 7 SE +/- 50.98, N = 3 4126.20 4198.16 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Linux 5.5 Linux 5.6-rc1 50K 100K 150K 200K 250K SE +/- 232.77, N = 3 SE +/- 1320.67, N = 3 228590.28 225159.18 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Linux 5.5 Linux 5.6-rc1 20K 40K 60K 80K 100K SE +/- 537.01, N = 3 SE +/- 233.62, N = 3 98949.52 99287.24 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Linux 5.5 Linux 5.6-rc1 30K 60K 90K 120K 150K SE +/- 1165.79, N = 15 SE +/- 1081.73, N = 15 117108.10 119473.65 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
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 5.5 Linux 5.6-rc1 0.0593 0.1186 0.1779 0.2372 0.2965 SE +/- 0.00094, N = 3 SE +/- 0.00304, N = 3 0.26327 0.26338
OSBench OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files Linux 5.5 Linux 5.6-rc1 4 8 12 16 20 SE +/- 0.14, N = 3 SE +/- 0.05, N = 3 17.04 17.38 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Linux 5.5 Linux 5.6-rc1 16 32 48 64 80 SE +/- 0.91, N = 4 SE +/- 0.89, N = 5 69.87 71.89 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs Linux 5.5 Linux 5.6-rc1 20 40 60 80 100 SE +/- 0.41, N = 3 SE +/- 0.76, N = 3 102.88 105.99 1. (CC) gcc options: -lm
OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Linux 5.5 Linux 5.6-rc1 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.24, N = 3 91.81 94.28 1. (CC) gcc options: -lm
OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Linux 5.5 Linux 5.6-rc1 40 80 120 160 200 SE +/- 0.81, N = 3 SE +/- 0.79, N = 3 170.15 149.94 1. (CC) gcc options: -lm
PostMark This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance Linux 5.5 Linux 5.6-rc1 1300 2600 3900 5200 6500 SE +/- 46.33, N = 3 SE +/- 46.33, N = 3 5906 5859 1. (CC) gcc options: -O3
Ethr Ethr is a cross-platform Golang-written network performance measurement tool developed by Microsoft that is capable of testing multiple protocols and different measurements. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1 Linux 5.5 Linux 5.6-rc1 7 14 21 28 35 SE +/- 0.24, N = 15 SE +/- 0.90, N = 15 25.01 28.10 MIN: 8.31 / MAX: 62.81 MIN: 8.28 / MAX: 45.66
OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1 Linux 5.5 Linux 5.6-rc1 140 280 420 560 700 SE +/- 9.47, N = 15 SE +/- 11.26, N = 15 637.36 626.23 MIN: 564.48 / MAX: 710.27 MIN: 549.76 / MAX: 704.26
OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1 Linux 5.5 Linux 5.6-rc1 2K 4K 6K 8K 10K SE +/- 697.37, N = 12 SE +/- 100.66, N = 3 8117 9910
iPerf iPerf is a network bandwidth throughput testing software. This test profile is used for automated testing of an iperf client and requires you have access to an iperf server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 30 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 20 Linux 5.5 Linux 5.6-rc1 4K 8K 12K 16K 20K SE +/- 0.33, N = 3 20000 20000 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 30 Seconds - Test: TCP - Parallel: 20 Linux 5.5 Linux 5.6-rc1 8K 16K 24K 32K 40K SE +/- 128.09, N = 3 SE +/- 440.29, N = 4 35179 34712 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 30 Seconds - Test: UDP - Parallel: 20 Linux 5.5 Linux 5.6-rc1 5 10 15 20 25 21 21 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Semaphore Release And Acquire Linux 5.5 Linux 5.6-rc1 4 8 12 16 20 14 14 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 4K Linux 5.5 Linux 5.6-rc1 70 140 210 280 350 SE +/- 0.46, N = 3 SE +/- 3.90, N = 4 296.18 302.60 MIN: 50.47 / MAX: 392.4 MIN: 52.16 / MAX: 412.11 1. (CC) gcc options: -pthread
OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p 10-bit Linux 5.5 Linux 5.6-rc1 30 60 90 120 150 SE +/- 0.31, N = 3 SE +/- 0.27, N = 3 121.21 121.57 MIN: 86.33 / MAX: 179.2 MIN: 86.39 / MAX: 178.93 1. (CC) gcc options: -pthread
SVT-AV1 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p Linux 5.5 Linux 5.6-rc1 20 40 60 80 100 SE +/- 0.86, N = 3 SE +/- 0.63, N = 3 86.11 85.03 1. (CXX) g++ options: -fPIE -fPIC -pie
OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.81 Blend File: Barbershop - Compute: CPU-Only Linux 5.5 Linux 5.6-rc1 20 40 60 80 100 SE +/- 0.53, N = 3 SE +/- 0.40, N = 3 94.90 95.46
NGINX Benchmark This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving Linux 5.5 Linux 5.6-rc1 5K 10K 15K 20K 25K SE +/- 243.39, N = 3 SE +/- 356.83, N = 3 24246.07 23968.01 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
Apache Benchmark This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Linux 5.5 Linux 5.6-rc1 5K 10K 15K 20K 25K SE +/- 33.77, N = 3 SE +/- 173.09, N = 3 22037.86 22813.99 1. (CC) gcc options: -shared -fPIC -O2 -pthread
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 5.5 Linux 5.6-rc1 110K 220K 330K 440K 550K SE +/- 357.13, N = 3 SE +/- 4780.46, N = 3 515483 524586
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 5.5 Linux 5.6-rc1 50K 100K 150K 200K 250K SE +/- 525.43, N = 3 SE +/- 486.88, N = 3 239513 250024 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync Linux 5.5 Linux 5.6-rc1 40K 80K 120K 160K 200K SE +/- 917.41, N = 3 SE +/- 1559.78, N = 3 176611 165783 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing Linux 5.5 Linux 5.6-rc1 3M 6M 9M 12M 15M SE +/- 88274.43, N = 3 SE +/- 174233.87, N = 4 11720180 11714144 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Linux 5.5 Linux 5.6-rc1 3K 6K 9K 12K 15K SE +/- 572.57, N = 9 SE +/- 625.53, N = 9 13854.53 13830.13 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
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 5.5 Linux 5.6-rc1 300 600 900 1200 1500 SE +/- 3.38, N = 3 1200 1203
Linux 5.6-rc1 Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 19.10, Kernel: 5.6.0-050600rc1-generic (x86_64) 20200209, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.1.0-devel (git-35961b1 2020-02-08 eoan-oibaf-ppa) (LLVM 9.0.1 128 bits), Compiler: GCC 9.2.1 20191008 + LLVM 9.0.0, File-System: ext4, Screen Resolution: 1920x1080
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: 0x830101cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 10 February 2020 11:34 by user phoronix.
Linux 5.5 Processor: 2 x AMD EPYC 7742 64-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RDY1001C BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 280GB INTEL SSDPE21D280GA + 256GB Micron_1100_MTFD, Graphics: llvmpipe 504GB, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 19.10, Kernel: 5.5.0-050500-generic (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.7, Display Driver: modesetting 1.20.7, OpenGL: 3.3 Mesa 20.1.0-devel (git-35961b1 2020-02-08 eoan-oibaf-ppa) (LLVM 9.0.1 128 bits), Compiler: GCC 9.2.1 20191008 + LLVM 9.0.0, File-System: ext4, Screen Resolution: 1920x1080
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: 0x830101cJava Notes: OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 10 February 2020 20:28 by user phoronix.