AMD EPYC 2019 vs. 2017 Linux Performance AMD EPYC 7601 of Ubuntu 17.04 versus Ubuntu 19.04 for seeing how the performance has evolved since AMD EPYC launch. Benchmarks by Michael Larabel for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1906078-HV-AMDEPYC2019&grr&sor .
AMD EPYC 2019 vs. 2017 Linux Performance Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads) TYAN B8026T70AE24HR (V1.02.B10 BIOS) AMD Device 1450 129024MB 280GB INTEL SSDPE21D280GA LLVMpipe VE228 2 x Broadcom NetXtreme BCM5720 PCIe Ubuntu 17.04 4.10.0-42-generic (x86_64) Unity 7.5.0 X Server 1.19.3 modesetting 1.19.3 3.3 Mesa 17.0.7 Gallium 0.4 (LLVM 4.0 128 bits) GCC 6.3.0 20170406 ext4 1920x1080 AMD 17h ASPEED Ubuntu 19.04 5.0.0-16-generic (x86_64) GNOME Shell 3.32.1 X Server 1.20.4 modesetting 1.20.4 GCC 8.3.0 5.2.0-999-generic (x86_64) 20190603 OpenBenchmarking.org Environment Details - Ubuntu 17.04: LIBGL_ALWAYS_SOFTWARE=1 Compiler Details - Ubuntu 17.04: --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --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-arch-directory=amd64 --with-default-libstdcxx-abi=new --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic -v - Ubuntu 19.04: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - Ubuntu 19.04 + Linux 5.2: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - Ubuntu 19.04 + Linux 5.2 + No Spec: --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: acpi-cpufreq ondemand Java Details - Ubuntu 17.04: OpenJDK Runtime Environment (build 1.8.0_151-8u151-b12-0ubuntu0.17.04.2-b12) - Ubuntu 19.04: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1) - Ubuntu 19.04 + Linux 5.2: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1) - Ubuntu 19.04 + Linux 5.2 + No Spec: OpenJDK Runtime Environment (build 11.0.3+7-Ubuntu-1ubuntu219.04.1) Python Details - Ubuntu 17.04: Python 2.7.13 + Python 3.5.3 - Ubuntu 19.04: Python 2.7.16 + Python 3.7.3 - Ubuntu 19.04 + Linux 5.2: Python 2.7.16 + Python 3.7.3 - Ubuntu 19.04 + Linux 5.2 + No Spec: Python 2.7.16 + Python 3.7.3 Security Details - Ubuntu 19.04: 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 STIBP: disabled RSB filling - Ubuntu 19.04 + Linux 5.2: 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 STIBP: disabled RSB filling - Ubuntu 19.04 + Linux 5.2 + No Spec: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled
AMD EPYC 2019 vs. 2017 Linux Performance numpy: mkl-dnn: Deconvolution Batch deconv_all - f32 hpcg: build-gcc: Time To Compile mysqlslap: 64 mcperf: Set apache: Static Web Page Serving build-linux-kernel: Time To Compile asmfish: 1024 Hash Memory, 26 Depth blender: Barbershop - CPU-Only v-ray: CPU stress-ng: Forking mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 pgbench: Buffer Test - Normal Load - Read Only pgbench: Buffer Test - Normal Load - Read Write stress-ng: Context Switching stockfish: Total Time perl-benchmark: Pod2html mcperf: Get build-llvm: Time To Compile stress-ng: Glibc C String Functions parboil: OpenMP Stencil rodinia: OpenMP Streamcluster himeno: Poisson Pressure Solver perl-benchmark: Interpreter namd: ATPase Simulation - 327,506 Atoms mysqlslap: 1 npb: FT.B stress-ng: Socket Activity pybench: Total For Average Test Times cython-bench: blender: BMW27 - CPU-Only ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping stress-ng: Memory Copying stress-ng: Crypto stress-ng: Semaphores stress-ng: Bsearch stress-ng: Glibc Qsort Data Sorting phpbench: PHP Benchmark Suite povray: Trace Time redis: GET svt-hevc: 1080p 8-bit YUV To HEVC Video Encode npb: EP.C openssl: RSA 4096-bit Performance mafft: Multiple Sequence Alignment rodinia: OpenMP LavaMD scikit-learn: mkl-dnn: Convolution Batch conv_alexnet - f32 rodinia: OpenMP CFD Solver redis: SET svt-av1: 1080p 8-bit YUV To AV1 Video Encode hmmer: Pfam Database Search x264: H.264 Video Encoding npb: FT.A parboil: OpenMP CUTCP ctx-clock: Context Switch Time Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec 9217173 5748 0.73 989 596 34687 19655 41.92 63528003 486 23723 42151 146 374295 34731 13990904 57376331 0.19430801 52387 226 1409567 13.47 20.03 1007 0.00265858 0.91092 10170 1991 22953 1993 38.52 101 427 1802 5822 1485116 16071 361 309890 23.15 1667825 182 461 4576 3.34 30.42 28.62 328 12.30 1155205 36.39 8.25 106 2447 1.87 132 8474464 4681 0.76 997 630 24852 16256 36.96 61934696 504 24577 44974 131 389965 35065 12189090 57736660 0.19089546 50397 201 1640034 9.87 17.51 1006 0.00222401 0.90958 10093 3409 19810 1465 33.08 101 445 3832 5887 1517588 14656 379 393045 22.34 1948133 185 851 4583 3.83 13.06 12.34 300 10.68 1333439 37.04 7.23 108 3237 1.88 132 8456027 4589 0.77 999 624 25180 16429 37.00 61166139 504 24522 46811 129 387941 35079 14724311 57798263 0.19025251 49583 195 1640928 10.13 16.11 1001 0.00227404 0.91657 10274 4804 18624 1468 32.98 101 446 3930 5885 1518407 14621 378 393201 22.34 1713980 183 884 4583 3.91 13.08 12.49 297 10.67 1324367 36.50 7.18 107 4445 1.87 154 8655647 4522 0.81 997 633 27802 16829 36.86 61582238 503 24724 47201 130 393695 35413 16288573 58368046 0.19075409 58305 209 1643759 9.22 17.77 1002 0.00224459 0.90951 11236 4734 19035 1466 32.83 102 446 3943 5879 1495419 14724 382 396305 22.41 1998041 180 923 4590 3.80 12.99 12.48 295 10.76 1347124 36.85 7.19 109 4400 1.93 154 OpenBenchmarking.org
Numpy Benchmark OpenBenchmarking.org Nanoseconds, Fewer Is Better Numpy Benchmark Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 2M 4M 6M 8M 10M 8456027 8474464 8655647 9217173
MKL-DNN Harness: Deconvolution Batch deconv_all - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Deconvolution Batch deconv_all - Data Type: f32 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 1200 2400 3600 4800 6000 SE +/- 40.49, N = 3 SE +/- 51.56, N = 6 SE +/- 8.80, N = 3 SE +/- 81.53, N = 3 4522 4589 4681 5748 MIN: 4367.56 MIN: 4374.56 MIN: 4542.68 MIN: 4893.14 1. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.0 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 0.1823 0.3646 0.5469 0.7292 0.9115 SE +/- 0.02, N = 15 SE +/- 0.01, N = 15 SE +/- 0.02, N = 15 SE +/- 0.01, N = 3 0.81 0.77 0.76 0.73
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 8.2 Time To Compile Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 200 400 600 800 1000 989 997 997 999
MariaDB Clients: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.3.8 Clients: 64 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 140 280 420 560 700 SE +/- 0.93, N = 3 SE +/- 2.03, N = 3 SE +/- 1.57, N = 3 SE +/- 0.83, N = 3 633 630 624 596 -laio -lpcre -laio -lpcre -laio -lpcre 1. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -lnuma -lz -lm -lcrypt -lssl -lcrypto -ldl
Memcached mcperf Method: Set OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 7K 14K 21K 28K 35K SE +/- 298.45, N = 15 SE +/- 834.64, N = 15 SE +/- 1103.57, N = 15 SE +/- 730.39, N = 15 34687 27802 25180 24852 1. (CC) gcc options: -O2 -lm -rdynamic
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 4K 8K 12K 16K 20K SE +/- 47.59, N = 3 SE +/- 342.95, N = 15 SE +/- 212.10, N = 15 SE +/- 233.64, N = 3 19655 16829 16429 16256 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 4.18 Time To Compile Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 10 20 30 40 50 SE +/- 0.28, N = 15 SE +/- 0.32, N = 13 SE +/- 0.28, N = 15 SE +/- 0.35, N = 13 36.86 36.96 37.00 41.92
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 14M 28M 42M 56M 70M SE +/- 638722.99, N = 3 SE +/- 510625.43, N = 3 SE +/- 219141.26, N = 3 SE +/- 195549.26, N = 3 63528003 61934696 61582238 61166139
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: Barbershop - Compute: CPU-Only Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 110 220 330 440 550 486 503 504 504
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org Ksamples, More Is Better Chaos Group V-RAY 4.10.03 Mode: CPU Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 5K 10K 15K 20K 25K SE +/- 376.98, N = 3 SE +/- 367.58, N = 4 SE +/- 295.67, N = 3 SE +/- 225.70, N = 15 24724 24577 24522 23723
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Forking Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 10K 20K 30K 40K 50K SE +/- 1057.95, N = 12 SE +/- 794.86, N = 15 SE +/- 1356.42, N = 15 SE +/- 980.75, N = 15 47201 46811 44974 42151 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
MKL-DNN Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 17.04 30 60 90 120 150 SE +/- 0.61, N = 3 SE +/- 1.42, N = 3 SE +/- 0.35, N = 3 SE +/- 1.92, N = 3 129 130 131 146 MIN: 123.45 MIN: 122.74 MIN: 125.04 MIN: 128.19 1. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 80K 160K 240K 320K 400K SE +/- 2741.64, N = 3 SE +/- 3325.76, N = 3 SE +/- 1977.63, N = 3 SE +/- 1336.66, N = 3 393695 389965 387941 374295 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 8K 16K 24K 32K 40K SE +/- 18.63, N = 3 SE +/- 60.44, N = 3 SE +/- 64.02, N = 3 SE +/- 67.51, N = 3 35413 35079 35065 34731 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 Ubuntu 19.04 3M 6M 9M 12M 15M SE +/- 551960.44, N = 15 SE +/- 439477.63, N = 15 SE +/- 182035.08, N = 3 SE +/- 139919.46, N = 15 16288573 14724311 13990904 12189090 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 13M 26M 39M 52M 65M SE +/- 357751.74, N = 3 SE +/- 513423.92, N = 3 SE +/- 312086.54, N = 3 SE +/- 579265.86, N = 3 58368046 57798263 57736660 57376331 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
Perl Benchmarks Test: Pod2html OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Pod2html Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 17.04 0.0437 0.0874 0.1311 0.1748 0.2185 SE +/- 0.00042886, N = 3 SE +/- 0.00010418, N = 3 SE +/- 0.00092862, N = 3 SE +/- 0.00059088, N = 3 0.19025251 0.19075409 0.19089546 0.19430801
Memcached mcperf Method: Get OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 12K 24K 36K 48K 60K SE +/- 1129.17, N = 15 SE +/- 676.97, N = 3 SE +/- 1936.69, N = 15 SE +/- 288.03, N = 3 58305 52387 50397 49583 1. (CC) gcc options: -O2 -lm -rdynamic
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 50 100 150 200 250 195 201 209 226
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Glibc C String Functions Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 400K 800K 1200K 1600K 2000K SE +/- 25241.53, N = 15 SE +/- 23620.75, N = 4 SE +/- 23170.19, N = 4 SE +/- 3278.74, N = 3 1643759 1640928 1640034 1409567 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Parboil Test: OpenMP Stencil OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP Stencil Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 3 6 9 12 15 SE +/- 0.24, N = 15 SE +/- 0.45, N = 15 SE +/- 0.53, N = 15 SE +/- 0.61, N = 15 9.22 9.87 10.13 13.47 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP Streamcluster Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.53, N = 15 SE +/- 0.42, N = 12 SE +/- 0.65, N = 12 16.11 17.51 17.77 20.03 1. (CXX) g++ options: -O2 -lOpenCL
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 200 400 600 800 1000 SE +/- 2.88, N = 3 SE +/- 4.47, N = 3 SE +/- 2.56, N = 3 SE +/- 0.47, N = 3 1007 1006 1002 1001 1. (CC) gcc options: -O3 -mavx2
Perl Benchmarks Test: Interpreter OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Interpreter Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 0.0006 0.0012 0.0018 0.0024 0.003 SE +/- 0.00002062, N = 3 SE +/- 0.00001889, N = 3 SE +/- 0.00000780, N = 3 SE +/- 0.00000080, N = 3 0.00222401 0.00224459 0.00227404 0.00265858
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13b1 ATPase Simulation - 327,506 Atoms Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 0.2062 0.4124 0.6186 0.8248 1.031 SE +/- 0.00060, N = 3 SE +/- 0.00156, N = 3 SE +/- 0.00024, N = 3 SE +/- 0.00548, N = 3 0.90951 0.90958 0.91092 0.91657
MariaDB Clients: 1 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.3.8 Clients: 1 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 Ubuntu 19.04 2K 4K 6K 8K 10K SE +/- 0.00, N = 3 SE +/- 144.76, N = 15 SE +/- 69.42, N = 3 SE +/- 104.49, N = 7 11236 10274 10170 10093 -laio -lpcre -laio -lpcre -laio -lpcre 1. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -lnuma -lz -lm -lcrypt -lssl -lcrypto -ldl
NAS Parallel Benchmarks Test / Class: FT.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: FT.B Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 17.04 1000 2000 3000 4000 5000 SE +/- 12.41, N = 3 SE +/- 14.86, N = 3 SE +/- 4.71, N = 3 SE +/- 73.99, N = 15 4804 4734 3409 1991 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 2.0.2
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 5K 10K 15K 20K 25K SE +/- 53.20, N = 3 SE +/- 205.06, N = 3 SE +/- 227.87, N = 6 SE +/- 227.34, N = 5 22953 19810 19035 18624 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 400 800 1200 1600 2000 SE +/- 2.52, N = 3 SE +/- 2.19, N = 3 SE +/- 7.09, N = 3 SE +/- 1.33, N = 3 1465 1466 1468 1993
Cython benchmark OpenBenchmarking.org Seconds, Fewer Is Better Cython benchmark 0.27 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.33, N = 3 SE +/- 0.20, N = 3 32.83 32.98 33.08 38.52
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.79a Blend File: BMW27 - Compute: CPU-Only Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec 20 40 60 80 100 101 101 101 102
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 100 200 300 400 500 SE +/- 1.57, N = 3 SE +/- 0.98, N = 3 SE +/- 2.03, N = 3 SE +/- 1.65, N = 3 446 446 445 427 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Memory Copying Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 800 1600 2400 3200 4000 SE +/- 55.55, N = 4 SE +/- 15.48, N = 3 SE +/- 18.35, N = 3 SE +/- 2.15, N = 3 3943 3930 3832 1802 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Crypto Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 1300 2600 3900 5200 6500 SE +/- 41.17, N = 3 SE +/- 39.66, N = 3 SE +/- 44.50, N = 3 SE +/- 35.92, N = 3 5887 5885 5879 5822 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 300K 600K 900K 1200K 1500K SE +/- 3813.97, N = 3 SE +/- 8820.67, N = 3 SE +/- 5908.58, N = 3 SE +/- 8902.99, N = 3 1518407 1517588 1495419 1485116 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Bsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Bsearch Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 3K 6K 9K 12K 15K SE +/- 124.05, N = 3 SE +/- 212.01, N = 3 SE +/- 148.05, N = 3 SE +/- 91.88, N = 3 16071 14724 14656 14621 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Glibc Qsort Data Sorting Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 80 160 240 320 400 SE +/- 3.60, N = 3 SE +/- 3.86, N = 3 SE +/- 3.22, N = 3 SE +/- 1.69, N = 3 382 379 378 361 -laio -laio -laio 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 80K 160K 240K 320K 400K SE +/- 1521.00, N = 3 SE +/- 202.51, N = 3 SE +/- 130.46, N = 3 SE +/- 501.22, N = 3 396305 393201 393045 309890
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 6 12 18 24 30 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 22.34 22.34 22.41 23.15 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: GET Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 400K 800K 1200K 1600K 2000K SE +/- 26538.58, N = 3 SE +/- 8872.20, N = 3 SE +/- 22708.15, N = 4 SE +/- 27915.23, N = 15 1998041 1948133 1713980 1667825 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
SVT-HEVC 1080p 8-bit YUV To HEVC Video Encode OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 2019-02-03 1080p 8-bit YUV To HEVC Video Encode Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 + No Spec 40 80 120 160 200 SE +/- 3.81, N = 15 SE +/- 3.45, N = 15 SE +/- 5.63, N = 15 SE +/- 2.93, N = 15 185 183 182 180 1. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native -pie -rdynamic -lpthread -lrt
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: EP.C Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 200 400 600 800 1000 SE +/- 9.42, N = 15 SE +/- 10.60, N = 3 SE +/- 8.51, N = 3 SE +/- 0.36, N = 3 923 884 851 461 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 2.0.2
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 1000 2000 3000 4000 5000 SE +/- 13.83, N = 3 SE +/- 20.77, N = 3 SE +/- 15.82, N = 3 SE +/- 22.11, N = 3 4590 4583 4583 4576 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Timed MAFFT Alignment Multiple Sequence Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.392 Multiple Sequence Alignment Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 0.8798 1.7596 2.6394 3.5192 4.399 SE +/- 0.09, N = 15 SE +/- 0.08, N = 15 SE +/- 0.06, N = 15 SE +/- 0.07, N = 15 3.34 3.80 3.83 3.91 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 12.99 13.06 13.08 30.42 1. (CXX) g++ options: -O2 -lOpenCL
Scikit-Learn OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.17.1 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 12.34 12.48 12.49 28.62
MKL-DNN Harness: Convolution Batch conv_alexnet - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Convolution Batch conv_alexnet - Data Type: f32 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 17.04 70 140 210 280 350 SE +/- 2.64, N = 3 SE +/- 0.98, N = 3 SE +/- 4.35, N = 3 SE +/- 4.17, N = 3 295 297 300 328 MIN: 286.08 MIN: 287.79 MIN: 284.28 MIN: 288.84 1. (CXX) g++ options: -std=c++11 -march=native -mtune=native -fPIC -fopenmp -O3 -pie -lmklml_intel -ldl
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 17.04 3 6 9 12 15 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 10.67 10.68 10.76 12.30 1. (CXX) g++ options: -O2 -lOpenCL
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SET Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 300K 600K 900K 1200K 1500K SE +/- 3677.04, N = 3 SE +/- 8370.99, N = 3 SE +/- 17246.16, N = 3 SE +/- 3873.52, N = 3 1347124 1333439 1324367 1155205 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
SVT-AV1 1080p 8-bit YUV To AV1 Video Encode OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.5 1080p 8-bit YUV To AV1 Video Encode Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 9 18 27 36 45 SE +/- 0.31, N = 3 SE +/- 0.42, N = 3 SE +/- 0.37, N = 3 SE +/- 0.18, N = 3 37.04 36.85 36.50 36.39 1. (CXX) g++ options: -O3 -pie -lpthread -lm
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 17.04 2 4 6 8 10 SE +/- 0.10, N = 4 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 7.18 7.19 7.23 8.25 1. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 17.04 20 40 60 80 100 SE +/- 0.74, N = 3 SE +/- 0.16, N = 3 SE +/- 0.24, N = 3 SE +/- 0.59, N = 3 109 108 107 106 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
NAS Parallel Benchmarks Test / Class: FT.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3.1 Test / Class: FT.A Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec Ubuntu 19.04 Ubuntu 17.04 1000 2000 3000 4000 5000 SE +/- 6.86, N = 3 SE +/- 7.97, N = 3 SE +/- 8.03, N = 3 SE +/- 120.27, N = 12 4445 4400 3237 2447 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 2.0.2
Parboil Test: OpenMP CUTCP OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP Ubuntu 17.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 + No Spec 0.4343 0.8686 1.3029 1.7372 2.1715 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 4 SE +/- 0.03, N = 3 1.87 1.87 1.88 1.93 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
ctx_clock Context Switch Time OpenBenchmarking.org Clocks, Fewer Is Better ctx_clock Context Switch Time Ubuntu 17.04 Ubuntu 19.04 Ubuntu 19.04 + Linux 5.2 Ubuntu 19.04 + Linux 5.2 + No Spec 30 60 90 120 150 132 132 154 154
Phoronix Test Suite v10.8.5