linux 55 AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (0601 BIOS) and AMD Radeon VII 16GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2001293-VE-LINUX550867&obr_sgm=y&obr_swl=y&grs&sor .
linux 55 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Linux 5.3 Linux 5.4 Linux 5.5 AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads) ASUS ROG ZENITH II EXTREME (0601 BIOS) AMD Starship/Matisse 64GB 1000GB Force MP600 AMD Radeon VII 16GB (1802/1001MHz) AMD Vega 20 HDMI Audio ASUS MG28U Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.3.0-050300-generic (x86_64) GNOME Shell 3.34.1 X Server 1.20.5 amdgpu 19.1.0 4.5 Mesa 19.2.4 (LLVM 9.0.0) GCC 9.2.1 20191130 ext4 3840x2160 5.4.0-050400-generic (x86_64) 5.5.0-050500-generic (x86_64) OpenBenchmarking.org Compiler Details - --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-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --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-build-config=bootstrap-lto-lean --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 Disk Details - NONE / errors=remount-ro,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 Graphics Details - Linux 5.3, Linux 5.4: GLAMOR Java Details - OpenJDK Runtime Environment (build 11.0.5+10-post-Ubuntu-2ubuntu1) Python Details - Python 2.7.17 + Python 3.7.6 Security Details - Linux 5.3: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling - Linux 5.4: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected - Linux 5.5: 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 STIBP: conditional RSB filling + tsx_async_abort: Not affected
linux 55 stress-ng: System V Message Passing fio: Rand Read - Linux AIO - Yes - No - 2MB - Default Test Directory fio: Rand Read - Linux AIO - Yes - No - 2MB - Default Test Directory ctx-clock: Context Switch Time nginx: Static Web Page Serving sqlite: 8 stress-ng: Forking hackbench: 16 - Process fio: Seq Write - Linux AIO - Yes - No - 2MB - Default Test Directory fio: Seq Write - Linux AIO - Yes - No - 2MB - Default Test Directory osbench: Create Processes hackbench: 16 - Thread osbench: Launch Programs stress-ng: Tsearch stress-ng: Socket Activity osbench: Create Threads xonotic: 3840 x 2160 - Low tinymembench: Standard Memset stress-ng: Memory Copying geexlab: 3840 x 2160 - GL2 AntTweakBar tesseract: 3840 x 2160 sqlite: 1 rodinia: OpenMP CFD Solver svt-av1: Enc Mode 8 - 1080p parboil: OpenMP CUTCP vpxenc: Speed 5 dacapobench: Tradebeans dav1d: Summer Nature 1080p stress-ng: Glibc C String Functions stress-ng: Matrix Math selenium: Kraken - Firefox mbw: Memory Copy - 4096 MiB dav1d: Summer Nature 4K fio: Seq Read - Linux AIO - Yes - No - 2MB - Default Test Directory geexlab: 3840 x 2160 - GL2 Cell Shading fio: Seq Read - Linux AIO - Yes - No - 2MB - Default Test Directory scikit-learn: build-llvm: Time To Compile npb: SP.B tinymembench: Standard Memcpy stress-ng: Semaphores apache: Static Web Page Serving npb: BT.C sqlite-speedtest: Timed Time - Size 1,000 stress-ng: Glibc Qsort Data Sorting xonotic: 3840 x 2160 - Ultra xonotic: 3840 x 2160 - High mlpack: scikit_svm geexlab: 3840 x 2160 - GL2 Hot Tunnel DNA dacapobench: Tradesoap dacapobench: H2 inkscape: SVG Files To PNG npb: EP.C npb: LU.C geexlab: 3840 x 2160 - GL3 Vertex Pool mbw: Memory Copy, Fixed Block Size - 4096 MiB stress-ng: Hsearch selenium: Jetstream 2 - Firefox geexlab: 3840 x 2160 - GL3 Mesh Exploder dav1d: Chimera 1080p 10-bit geexlab: 3840 x 2160 - GL2 Tunnel Beauty xonotic: 3840 x 2160 - Ultimate numpy: build2: Time To Compile selenium: PSPDFKit WASM - Firefox stress-ng: Bsearch dav1d: Chimera 1080p osbench: Memory Allocations npb: MG.C stress-ng: Lsearch build-linux-kernel: Time To Compile dacapobench: Jython selenium: WASM imageConvolute - Firefox rodinia: OpenMP LavaMD parboil: OpenMP MRI Gridding stress-ng: CPU Stress selenium: WASM collisionDetection - Firefox npb: CG.C npb: IS.D stress-ng: Crypto hpcg: etlegacy: Renderer2 - 3840 x 2160 geexlab: 3840 x 2160 - GL2 Noise Animation Electric osbench: Create Files deepspeech: CPU stress-ng: Vector Math gromacs: Water Benchmark npb: EP.D npb: FT.C mcperf: Set mcperf: Get stress-ng: Context Switching lammps: Rhodopsin Protein rodinia: OpenMP Streamcluster parboil: OpenMP Stencil fio: Rand Write - Linux AIO - Yes - No - 2MB - Default Test Directory fio: Rand Write - Linux AIO - Yes - No - 2MB - Default Test Directory Linux 5.3 Linux 5.4 Linux 5.5 27028660.05 550 1107 148 36884.43 48.578 85406.51 16.488 944 1896 39.879481 16.494 48.349698 1198.22 22635.01 20.120144 313.0539342 21706.6 8678.04 3086.1 371.0648 14.827 7.545 71.504 0.972292 25.17 4649 728.85 1251087.82 235032.00 726.7 20733.035 329.82 2186 4013.4 1089 8.243 114.667 35513.78 12361.3 3385969.43 35259.93 77305.90 57.435 532.83 382.5492214 427.4533256 11.33 138.0 3304 3839 25.640 2895.90 68200.82 6698.4 12959.327 256772.88 95.072 3999.9 97.04 113.7 301.5073488 427.32 47.448 1301 23217.33 652.03 67.709605 31544.33 527.97 23.161 3926 26.5 7.953 58.004842 11699.74 362.2 11097.13 1485.89 9336.06 10.9919 252.6 2711.2 11.051907 55.86505 89286.22 3.263 2931.14 35301.64 45254.1 75737.9 21391138.40 19.935 14.438 5.648926 944 1895 26068855.67 721 1448 148 44900.87 47.645 85871.35 17.130 1088 2183 38.393338 17.312 45.543512 1184.03 22204.70 19.493898 310.6536908 21696.3 8726.84 3116.6 386.7498 14.790 7.348 71.713 0.972538 24.87 4532 716.25 1272661.50 234076.13 727.3 20946.955 324.99 2169 3960.8 1081 8.177 114.276 35243.86 12159.4 3337412.08 35331.30 76935.05 57.152 525.23 387.9018576 433.3906124 11.35 137.5 3338 3855 25.852 2931.98 68170.59 6622.4 12935.651 256750.10 94.049 3959.5 97.23 113.7 303.9750585 424.59 47.550 1295 23065.81 656.04 67.332268 31374.30 526.12 23.092 3924 26.4 7.978 57.925083 11697.55 361.1 11115.40 1489.52 9327.04 10.9781 253.1 2714.1 11.043271 55.84179 89309.26 3.260 2929.45 35298.01 45874.1 77672.9 20353215.90 19.542 14.461 5.810131 997 2000 19907191.35 718 1443 185 42615.58 41.003 98746.91 14.833 989 1986 35.552979 15.462 44.047038 1092.10 21028.54 18.710295 332.5376383 20279.7 8190.43 3263.6 390.4660 14.288 7.623 69.193 0.939145 24.34 4623 710.54 1281125.10 229825.73 711.9 21174.300 322.98 2142 3932.8 1068 8.097 116.257 34931.15 12255.3 3392567.94 34763.42 76068.50 58.007 531.36 383.3582733 431.1697962 11.20 136.2 3347 3806 25.533 2931.45 67373.27 6632.0 12815.611 259610.85 94.982 3974.9 96.31 112.7 304.0414953 423.93 47.219 1292 23076.47 653.30 67.606926 31491.61 528.96 23.201 3940 26.4 7.948 58.114450 11735.43 361.1 11130.32 1486.17 9346.94 11.0012 252.7 2709.2 11.058753 55.91776 89399.91 3.263 2931.00 35284.02 48632.7 77581.7 19979856.27 19.374 15.089 4.905847 951 1908 OpenBenchmarking.org
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing Linux 5.3 Linux 5.4 Linux 5.5 6M 12M 18M 24M 30M SE +/- 245959.41, N = 15 SE +/- 322879.22, N = 15 SE +/- 67259.08, N = 3 27028660.05 26068855.67 19907191.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Flexible IO Tester Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.4 Linux 5.5 Linux 5.3 160 320 480 640 800 SE +/- 2.40, N = 3 SE +/- 3.21, N = 3 SE +/- 2.65, N = 3 721 718 550 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.4 Linux 5.5 Linux 5.3 300 600 900 1200 1500 SE +/- 4.81, N = 3 SE +/- 6.69, N = 3 SE +/- 5.13, N = 3 1448 1443 1107 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
ctx_clock Context Switch Time OpenBenchmarking.org Clocks, Fewer Is Better ctx_clock Context Switch Time Linux 5.3 Linux 5.4 Linux 5.5 40 80 120 160 200 148 148 185
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving Linux 5.4 Linux 5.5 Linux 5.3 10K 20K 30K 40K 50K SE +/- 165.19, N = 3 SE +/- 495.02, N = 3 SE +/- 29.56, N = 3 44900.87 42615.58 36884.43 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
SQLite Threads / Copies: 8 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 8 Linux 5.5 Linux 5.4 Linux 5.3 11 22 33 44 55 SE +/- 0.40, N = 3 SE +/- 0.37, N = 3 SE +/- 0.46, N = 3 41.00 47.65 48.58 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Forking Linux 5.5 Linux 5.4 Linux 5.3 20K 40K 60K 80K 100K SE +/- 247.16, N = 3 SE +/- 123.55, N = 3 SE +/- 525.16, N = 3 98746.91 85871.35 85406.51 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Hackbench Count: 16 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process Linux 5.5 Linux 5.3 Linux 5.4 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.19, N = 3 14.83 16.49 17.13 1. (CC) gcc options: -lpthread
Flexible IO Tester Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.4 Linux 5.5 Linux 5.3 200 400 600 800 1000 SE +/- 17.62, N = 3 SE +/- 11.58, N = 14 SE +/- 16.50, N = 3 1088 989 944 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.4 Linux 5.5 Linux 5.3 500 1000 1500 2000 2500 SE +/- 34.66, N = 3 SE +/- 23.16, N = 14 SE +/- 32.54, N = 3 2183 1986 1896 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Linux 5.5 Linux 5.4 Linux 5.3 9 18 27 36 45 SE +/- 0.53, N = 3 SE +/- 0.50, N = 3 SE +/- 0.61, N = 3 35.55 38.39 39.88 1. (CC) gcc options: -lm
Hackbench Count: 16 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread Linux 5.5 Linux 5.3 Linux 5.4 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.16, N = 3 15.46 16.49 17.31 1. (CC) gcc options: -lpthread
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs Linux 5.5 Linux 5.4 Linux 5.3 11 22 33 44 55 SE +/- 0.28, N = 3 SE +/- 0.07, N = 3 SE +/- 0.28, N = 3 44.05 45.54 48.35 1. (CC) gcc options: -lm
Stress-NG Test: Tsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Tsearch Linux 5.3 Linux 5.4 Linux 5.5 300 600 900 1200 1500 SE +/- 1.13, N = 3 SE +/- 12.91, N = 3 SE +/- 6.40, N = 3 1198.22 1184.03 1092.10 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity Linux 5.3 Linux 5.4 Linux 5.5 5K 10K 15K 20K 25K SE +/- 43.01, N = 3 SE +/- 83.92, N = 3 SE +/- 161.64, N = 3 22635.01 22204.70 21028.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Linux 5.5 Linux 5.4 Linux 5.3 5 10 15 20 25 SE +/- 0.16, N = 3 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 18.71 19.49 20.12 1. (CC) gcc options: -lm
Xonotic Resolution: 3840 x 2160 - Effects Quality: Low OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: Low Linux 5.5 Linux 5.3 Linux 5.4 70 140 210 280 350 SE +/- 4.59, N = 15 SE +/- 3.63, N = 6 SE +/- 3.32, N = 3 332.54 313.05 310.65 MIN: 125 / MAX: 1157 MIN: 123 / MAX: 1121 MIN: 128 / MAX: 1088
Tinymembench Standard Memset OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset Linux 5.3 Linux 5.4 Linux 5.5 5K 10K 15K 20K 25K SE +/- 164.06, N = 3 SE +/- 163.62, N = 3 SE +/- 84.40, N = 3 21706.6 21696.3 20279.7 1. (CC) gcc options: -O2 -lm
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Memory Copying Linux 5.4 Linux 5.3 Linux 5.5 2K 4K 6K 8K 10K SE +/- 78.24, N = 3 SE +/- 55.47, N = 3 SE +/- 83.56, N = 3 8726.84 8678.04 8190.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
GeeXLab Resolution: 3840 x 2160 - Test: GL2 AntTweakBar OpenBenchmarking.org FPS, More Is Better GeeXLab 0.28.0 Resolution: 3840 x 2160 - Test: GL2 AntTweakBar Linux 5.5 Linux 5.4 Linux 5.3 700 1400 2100 2800 3500 SE +/- 3.34, N = 3 SE +/- 45.96, N = 3 SE +/- 24.19, N = 3 3263.6 3116.6 3086.1
Tesseract Resolution: 3840 x 2160 OpenBenchmarking.org Frames Per Second, More Is Better Tesseract 2014-05-12 Resolution: 3840 x 2160 Linux 5.5 Linux 5.4 Linux 5.3 80 160 240 320 400 SE +/- 5.38, N = 3 SE +/- 3.49, N = 3 SE +/- 3.02, N = 15 390.47 386.75 371.06
SQLite Threads / Copies: 1 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 1 Linux 5.5 Linux 5.4 Linux 5.3 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 14.29 14.79 14.83 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver Linux 5.4 Linux 5.3 Linux 5.5 2 4 6 8 10 SE +/- 0.054, N = 3 SE +/- 0.035, N = 3 SE +/- 0.036, N = 3 7.348 7.545 7.623 1. (CXX) g++ options: -O2 -lOpenCL
SVT-AV1 Encoder Mode: Enc Mode 8 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p Linux 5.4 Linux 5.3 Linux 5.5 16 32 48 64 80 SE +/- 0.24, N = 3 SE +/- 0.11, N = 3 SE +/- 0.34, N = 3 71.71 71.50 69.19 1. (CXX) g++ options: -fPIE -fPIC -pie
Parboil Test: OpenMP CUTCP OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP Linux 5.5 Linux 5.3 Linux 5.4 0.2188 0.4376 0.6564 0.8752 1.094 SE +/- 0.002927, N = 3 SE +/- 0.008969, N = 3 SE +/- 0.010003, N = 3 0.939145 0.972292 0.972538 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
VP9 libvpx Encoding Speed: Speed 5 OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 5 Linux 5.3 Linux 5.4 Linux 5.5 6 12 18 24 30 SE +/- 0.19, N = 3 SE +/- 0.13, N = 3 SE +/- 0.24, N = 3 25.17 24.87 24.34 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Linux 5.4 Linux 5.5 Linux 5.3 1000 2000 3000 4000 5000 SE +/- 13.93, N = 4 SE +/- 25.16, N = 4 SE +/- 53.75, N = 4 4532 4623 4649
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 1080p Linux 5.3 Linux 5.4 Linux 5.5 160 320 480 640 800 SE +/- 2.35, N = 3 SE +/- 1.92, N = 3 SE +/- 1.76, N = 3 728.85 716.25 710.54 MIN: 479.08 / MAX: 810.36 MIN: 416.78 / MAX: 791.53 MIN: 430.69 / MAX: 786.42 1. (CC) gcc options: -pthread
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 Linux 5.5 Linux 5.4 Linux 5.3 300K 600K 900K 1200K 1500K SE +/- 11020.63, N = 3 SE +/- 5721.14, N = 3 SE +/- 17000.64, N = 12 1281125.10 1272661.50 1251087.82 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Matrix Math Linux 5.3 Linux 5.4 Linux 5.5 50K 100K 150K 200K 250K SE +/- 2704.39, N = 3 SE +/- 1854.67, N = 3 SE +/- 326.24, N = 3 235032.00 234076.13 229825.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Selenium Benchmark: Kraken - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Firefox Linux 5.5 Linux 5.3 Linux 5.4 160 320 480 640 800 SE +/- 3.03, N = 3 SE +/- 3.86, N = 3 SE +/- 0.90, N = 3 711.9 726.7 727.3 1. firefox 71.0
MBW Test: Memory Copy - Array Size: 4096 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 4096 MiB Linux 5.5 Linux 5.4 Linux 5.3 5K 10K 15K 20K 25K SE +/- 268.15, N = 3 SE +/- 56.13, N = 3 SE +/- 238.50, N = 3 21174.30 20946.96 20733.04 1. (CC) gcc options: -O3 -march=native
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 4K Linux 5.3 Linux 5.4 Linux 5.5 70 140 210 280 350 SE +/- 1.14, N = 3 SE +/- 0.36, N = 3 SE +/- 0.93, N = 3 329.82 324.99 322.98 MIN: 211.72 / MAX: 351.11 MIN: 191.45 / MAX: 346.86 MIN: 188.1 / MAX: 345.26 1. (CC) gcc options: -pthread
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.3 Linux 5.4 Linux 5.5 500 1000 1500 2000 2500 SE +/- 4.00, N = 3 SE +/- 3.84, N = 3 SE +/- 13.08, N = 3 2186 2169 2142 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
GeeXLab Resolution: 3840 x 2160 - Test: GL2 Cell Shading OpenBenchmarking.org FPS, More Is Better GeeXLab 0.28.0 Resolution: 3840 x 2160 - Test: GL2 Cell Shading Linux 5.3 Linux 5.4 Linux 5.5 900 1800 2700 3600 4500 SE +/- 28.32, N = 3 SE +/- 12.59, N = 3 SE +/- 15.70, N = 3 4013.4 3960.8 3932.8
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.3 Linux 5.4 Linux 5.5 200 400 600 800 1000 SE +/- 2.00, N = 3 SE +/- 2.08, N = 3 SE +/- 6.39, N = 3 1089 1081 1068 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Scikit-Learn OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.22.1 Linux 5.5 Linux 5.4 Linux 5.3 2 4 6 8 10 SE +/- 0.016, N = 3 SE +/- 0.040, N = 3 SE +/- 0.049, N = 3 8.097 8.177 8.243
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile Linux 5.4 Linux 5.3 Linux 5.5 30 60 90 120 150 114.28 114.67 116.26
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Linux 5.3 Linux 5.4 Linux 5.5 8K 16K 24K 32K 40K SE +/- 339.67, N = 3 SE +/- 224.28, N = 3 SE +/- 231.03, N = 3 35513.78 35243.86 34931.15 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
Tinymembench Standard Memcpy OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy Linux 5.3 Linux 5.5 Linux 5.4 3K 6K 9K 12K 15K SE +/- 20.52, N = 3 SE +/- 4.01, N = 3 SE +/- 188.16, N = 3 12361.3 12255.3 12159.4 1. (CC) gcc options: -O2 -lm
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Linux 5.5 Linux 5.3 Linux 5.4 700K 1400K 2100K 2800K 3500K SE +/- 10332.47, N = 3 SE +/- 8760.38, N = 3 SE +/- 41291.98, N = 3 3392567.94 3385969.43 3337412.08 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Linux 5.4 Linux 5.3 Linux 5.5 8K 16K 24K 32K 40K SE +/- 32.39, N = 3 SE +/- 99.87, N = 3 SE +/- 85.63, N = 3 35331.30 35259.93 34763.42 1. (CC) gcc options: -shared -fPIC -O2 -pthread
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Linux 5.3 Linux 5.4 Linux 5.5 17K 34K 51K 68K 85K SE +/- 172.46, N = 3 SE +/- 747.97, N = 3 SE +/- 875.28, N = 3 77305.90 76935.05 76068.50 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Linux 5.4 Linux 5.3 Linux 5.5 13 26 39 52 65 SE +/- 0.27, N = 3 SE +/- 0.15, N = 3 SE +/- 0.15, N = 3 57.15 57.44 58.01 1. (CC) gcc options: -O2 -ldl -lz -lpthread
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 Linux 5.3 Linux 5.5 Linux 5.4 120 240 360 480 600 SE +/- 2.09, N = 3 SE +/- 5.01, N = 3 SE +/- 4.34, N = 12 532.83 531.36 525.23 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Xonotic Resolution: 3840 x 2160 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: Ultra Linux 5.4 Linux 5.5 Linux 5.3 80 160 240 320 400 SE +/- 0.36, N = 3 SE +/- 2.25, N = 3 SE +/- 1.36, N = 3 387.90 383.36 382.55 MIN: 230 / MAX: 822 MIN: 159 / MAX: 807 MIN: 234 / MAX: 794
Xonotic Resolution: 3840 x 2160 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: High Linux 5.4 Linux 5.5 Linux 5.3 90 180 270 360 450 SE +/- 0.37, N = 3 SE +/- 1.98, N = 3 SE +/- 2.99, N = 3 433.39 431.17 427.45 MIN: 267 / MAX: 931 MIN: 241 / MAX: 919 MIN: 268 / MAX: 929
Mlpack Benchmark Benchmark: scikit_svm OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_svm Linux 5.5 Linux 5.3 Linux 5.4 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 11.20 11.33 11.35
GeeXLab Resolution: 3840 x 2160 - Test: GL2 Hot Tunnel DNA OpenBenchmarking.org FPS, More Is Better GeeXLab 0.28.0 Resolution: 3840 x 2160 - Test: GL2 Hot Tunnel DNA Linux 5.3 Linux 5.4 Linux 5.5 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 138.0 137.5 136.2
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap Linux 5.3 Linux 5.4 Linux 5.5 700 1400 2100 2800 3500 SE +/- 38.94, N = 20 SE +/- 42.95, N = 20 SE +/- 35.22, N = 20 3304 3338 3347
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Linux 5.5 Linux 5.3 Linux 5.4 800 1600 2400 3200 4000 SE +/- 50.85, N = 5 SE +/- 10.37, N = 4 SE +/- 36.86, N = 4 3806 3839 3855
Inkscape Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better Inkscape Operation: SVG Files To PNG Linux 5.5 Linux 5.3 Linux 5.4 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 25.53 25.64 25.85 1. Inkscape 0.92.4 (5da689c313, 2019-01-14)
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Linux 5.4 Linux 5.5 Linux 5.3 600 1200 1800 2400 3000 SE +/- 7.72, N = 3 SE +/- 23.72, N = 3 SE +/- 49.49, N = 3 2931.98 2931.45 2895.90 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Linux 5.3 Linux 5.4 Linux 5.5 15K 30K 45K 60K 75K SE +/- 38.09, N = 3 SE +/- 59.76, N = 3 SE +/- 285.31, N = 3 68200.82 68170.59 67373.27 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
GeeXLab Resolution: 3840 x 2160 - Test: GL3 Vertex Pool OpenBenchmarking.org FPS, More Is Better GeeXLab 0.28.0 Resolution: 3840 x 2160 - Test: GL3 Vertex Pool Linux 5.3 Linux 5.5 Linux 5.4 1400 2800 4200 5600 7000 SE +/- 5.57, N = 3 SE +/- 15.44, N = 3 SE +/- 13.66, N = 3 6698.4 6632.0 6622.4
MBW Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB Linux 5.3 Linux 5.4 Linux 5.5 3K 6K 9K 12K 15K SE +/- 5.30, N = 3 SE +/- 4.43, N = 3 SE +/- 2.36, N = 3 12959.33 12935.65 12815.61 1. (CC) gcc options: -O3 -march=native
Stress-NG Test: Hsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Hsearch Linux 5.5 Linux 5.3 Linux 5.4 60K 120K 180K 240K 300K SE +/- 421.36, N = 3 SE +/- 192.95, N = 3 SE +/- 363.80, N = 3 259610.85 256772.88 256750.10 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Selenium Benchmark: Jetstream 2 - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Firefox Linux 5.3 Linux 5.5 Linux 5.4 20 40 60 80 100 SE +/- 0.85, N = 3 SE +/- 0.82, N = 3 SE +/- 0.26, N = 3 95.07 94.98 94.05 1. firefox 71.0
GeeXLab Resolution: 3840 x 2160 - Test: GL3 Mesh Exploder OpenBenchmarking.org FPS, More Is Better GeeXLab 0.28.0 Resolution: 3840 x 2160 - Test: GL3 Mesh Exploder Linux 5.3 Linux 5.5 Linux 5.4 900 1800 2700 3600 4500 SE +/- 20.46, N = 3 SE +/- 9.81, N = 3 SE +/- 9.49, N = 3 3999.9 3974.9 3959.5
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p 10-bit Linux 5.4 Linux 5.3 Linux 5.5 20 40 60 80 100 SE +/- 0.26, N = 3 SE +/- 0.35, N = 3 SE +/- 0.08, N = 3 97.23 97.04 96.31 MIN: 61.72 / MAX: 181.03 MIN: 61.56 / MAX: 185.22 MIN: 60.94 / MAX: 180.84 1. (CC) gcc options: -pthread
GeeXLab Resolution: 3840 x 2160 - Test: GL2 Tunnel Beauty OpenBenchmarking.org FPS, More Is Better GeeXLab 0.28.0 Resolution: 3840 x 2160 - Test: GL2 Tunnel Beauty Linux 5.4 Linux 5.3 Linux 5.5 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.19, N = 3 SE +/- 0.03, N = 3 113.7 113.7 112.7
Xonotic Resolution: 3840 x 2160 - Effects Quality: Ultimate OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 3840 x 2160 - Effects Quality: Ultimate Linux 5.5 Linux 5.4 Linux 5.3 70 140 210 280 350 SE +/- 1.16, N = 3 SE +/- 0.33, N = 3 SE +/- 1.05, N = 3 304.04 303.98 301.51 MIN: 50 / MAX: 670 MIN: 54 / MAX: 673 MIN: 53 / MAX: 665
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark Linux 5.3 Linux 5.4 Linux 5.5 90 180 270 360 450 SE +/- 0.82, N = 3 SE +/- 0.82, N = 3 SE +/- 1.06, N = 3 427.32 424.59 423.93
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.12 Time To Compile Linux 5.5 Linux 5.3 Linux 5.4 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 47.22 47.45 47.55
Selenium Benchmark: PSPDFKit WASM - Browser: Firefox OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox Linux 5.5 Linux 5.4 Linux 5.3 300 600 900 1200 1500 SE +/- 5.57, N = 3 SE +/- 5.04, N = 3 SE +/- 5.61, N = 3 1292 1295 1301 1. firefox 71.0
Stress-NG Test: Bsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Bsearch Linux 5.3 Linux 5.5 Linux 5.4 5K 10K 15K 20K 25K SE +/- 30.19, N = 3 SE +/- 19.02, N = 3 SE +/- 80.27, N = 3 23217.33 23076.47 23065.81 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p Linux 5.4 Linux 5.5 Linux 5.3 140 280 420 560 700 SE +/- 1.67, N = 3 SE +/- 1.03, N = 3 SE +/- 1.65, N = 3 656.04 653.30 652.03 MIN: 471.38 / MAX: 815.07 MIN: 458.52 / MAX: 814.08 MIN: 459.77 / MAX: 808.77 1. (CC) gcc options: -pthread
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Linux 5.4 Linux 5.5 Linux 5.3 15 30 45 60 75 SE +/- 0.41, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 67.33 67.61 67.71 1. (CC) gcc options: -lm
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Linux 5.3 Linux 5.5 Linux 5.4 7K 14K 21K 28K 35K SE +/- 5.83, N = 3 SE +/- 33.31, N = 3 SE +/- 99.68, N = 3 31544.33 31491.61 31374.30 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
Stress-NG Test: Lsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Lsearch Linux 5.5 Linux 5.3 Linux 5.4 110 220 330 440 550 SE +/- 0.09, N = 3 SE +/- 0.56, N = 3 SE +/- 1.95, N = 3 528.96 527.97 526.12 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Linux 5.4 Linux 5.3 Linux 5.5 6 12 18 24 30 SE +/- 0.28, N = 6 SE +/- 0.31, N = 5 SE +/- 0.27, N = 6 23.09 23.16 23.20
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Linux 5.4 Linux 5.3 Linux 5.5 800 1600 2400 3200 4000 SE +/- 5.20, N = 4 SE +/- 7.84, N = 4 SE +/- 10.90, N = 4 3924 3926 3940
Selenium Benchmark: WASM imageConvolute - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Firefox Linux 5.4 Linux 5.5 Linux 5.3 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 26.4 26.4 26.5 1. firefox 71.0
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD Linux 5.5 Linux 5.3 Linux 5.4 2 4 6 8 10 SE +/- 0.018, N = 3 SE +/- 0.011, N = 3 SE +/- 0.030, N = 3 7.948 7.953 7.978 1. (CXX) g++ options: -O2 -lOpenCL
Parboil Test: OpenMP MRI Gridding OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP MRI Gridding Linux 5.4 Linux 5.3 Linux 5.5 13 26 39 52 65 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 57.93 58.00 58.11 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: CPU Stress Linux 5.5 Linux 5.3 Linux 5.4 3K 6K 9K 12K 15K SE +/- 20.85, N = 3 SE +/- 11.40, N = 3 SE +/- 14.58, N = 3 11735.43 11699.74 11697.55 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
Selenium Benchmark: WASM collisionDetection - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Firefox Linux 5.4 Linux 5.5 Linux 5.3 80 160 240 320 400 SE +/- 0.32, N = 3 SE +/- 0.69, N = 3 SE +/- 0.38, N = 3 361.1 361.1 362.2 1. firefox 71.0
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Linux 5.5 Linux 5.4 Linux 5.3 2K 4K 6K 8K 10K SE +/- 26.90, N = 3 SE +/- 32.40, N = 3 SE +/- 17.31, N = 3 11130.32 11115.40 11097.13 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Linux 5.4 Linux 5.5 Linux 5.3 300 600 900 1200 1500 SE +/- 3.91, N = 3 SE +/- 9.29, N = 3 SE +/- 3.46, N = 3 1489.52 1486.17 1485.89 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Crypto Linux 5.5 Linux 5.3 Linux 5.4 2K 4K 6K 8K 10K SE +/- 19.97, N = 3 SE +/- 16.58, N = 3 SE +/- 16.43, N = 3 9346.94 9336.06 9327.04 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Linux 5.5 Linux 5.3 Linux 5.4 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 11.00 10.99 10.98 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
ET: Legacy Renderer: Renderer2 - Resolution: 3840 x 2160 OpenBenchmarking.org Frames Per Second, More Is Better ET: Legacy 2.75 Renderer: Renderer2 - Resolution: 3840 x 2160 Linux 5.4 Linux 5.5 Linux 5.3 60 120 180 240 300 SE +/- 1.55, N = 3 SE +/- 1.33, N = 3 SE +/- 4.15, N = 3 253.1 252.7 252.6
GeeXLab Resolution: 3840 x 2160 - Test: GL2 Noise Animation Electric OpenBenchmarking.org FPS, More Is Better GeeXLab 0.28.0 Resolution: 3840 x 2160 - Test: GL2 Noise Animation Electric Linux 5.4 Linux 5.3 Linux 5.5 600 1200 1800 2400 3000 SE +/- 0.73, N = 3 SE +/- 2.11, N = 3 SE +/- 2.33, N = 3 2714.1 2711.2 2709.2
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files Linux 5.4 Linux 5.3 Linux 5.5 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 11.04 11.05 11.06 1. (CC) gcc options: -lm
DeepSpeech Acceleration: CPU OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU Linux 5.4 Linux 5.3 Linux 5.5 13 26 39 52 65 SE +/- 0.24, N = 3 SE +/- 0.21, N = 3 SE +/- 0.09, N = 3 55.84 55.87 55.92
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Vector Math Linux 5.5 Linux 5.4 Linux 5.3 20K 40K 60K 80K 100K SE +/- 84.44, N = 3 SE +/- 62.11, N = 3 SE +/- 63.82, N = 3 89399.91 89309.26 89286.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2019.4 Water Benchmark Linux 5.5 Linux 5.3 Linux 5.4 0.7342 1.4684 2.2026 2.9368 3.671 SE +/- 0.005, N = 3 SE +/- 0.003, N = 3 SE +/- 0.002, N = 8 3.263 3.263 3.260 1. (CXX) g++ options: -mavx2 -mfma -pthread -std=c++11 -O3 -funroll-all-loops -lrt -lpthread -lm
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Linux 5.3 Linux 5.5 Linux 5.4 600 1200 1800 2400 3000 SE +/- 3.58, N = 3 SE +/- 3.36, N = 3 SE +/- 4.19, N = 3 2931.14 2931.00 2929.45 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Linux 5.3 Linux 5.4 Linux 5.5 8K 16K 24K 32K 40K SE +/- 2.40, N = 3 SE +/- 1.59, N = 3 SE +/- 8.39, N = 3 35301.64 35298.01 35284.02 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 4.0.2
Memcached mcperf Method: Set OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set Linux 5.5 Linux 5.4 Linux 5.3 10K 20K 30K 40K 50K SE +/- 1115.18, N = 15 SE +/- 477.52, N = 3 SE +/- 474.56, N = 3 48632.7 45874.1 45254.1 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Get OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get Linux 5.4 Linux 5.5 Linux 5.3 17K 34K 51K 68K 85K SE +/- 1435.47, N = 12 SE +/- 1040.05, N = 5 SE +/- 864.68, N = 3 77672.9 77581.7 75737.9 1. (CC) gcc options: -O2 -lm -rdynamic
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Linux 5.3 Linux 5.4 Linux 5.5 5M 10M 15M 20M 25M SE +/- 526330.06, N = 15 SE +/- 743503.73, N = 12 SE +/- 187594.59, N = 3 21391138.40 20353215.90 19979856.27 1. (CC) gcc options: -O2 -std=gnu99 -lm -lbsd -lz -lcrypt -lrt -lpthread -laio -lc
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 9Jan2020 Model: Rhodopsin Protein Linux 5.3 Linux 5.4 Linux 5.5 5 10 15 20 25 SE +/- 0.30, N = 15 SE +/- 0.45, N = 15 SE +/- 0.39, N = 15 19.94 19.54 19.37 1. (CXX) g++ options: -O3 -rdynamic -lfftw3 -lm
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP Streamcluster Linux 5.3 Linux 5.4 Linux 5.5 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.26, N = 15 14.44 14.46 15.09 1. (CXX) g++ options: -O2 -lOpenCL
Parboil Test: OpenMP Stencil OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP Stencil Linux 5.5 Linux 5.3 Linux 5.4 1.3073 2.6146 3.9219 5.2292 6.5365 SE +/- 0.042856, N = 15 SE +/- 0.174107, N = 12 SE +/- 0.114543, N = 15 4.905847 5.648926 5.810131 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.4 Linux 5.5 Linux 5.3 200 400 600 800 1000 SE +/- 4.63, N = 3 SE +/- 18.10, N = 12 SE +/- 10.31, N = 15 997 951 944 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory 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 5.4 Linux 5.5 Linux 5.3 400 800 1200 1600 2000 SE +/- 9.26, N = 3 SE +/- 36.17, N = 12 SE +/- 20.57, N = 15 2000 1908 1895 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Geometric Mean Of All Test Results Result Composite - linux 55 OpenBenchmarking.org Geometric Mean, More Is Better Geometric Mean Of All Test Results Result Composite - linux 55 Linux 5.4 Linux 5.5 Linux 5.3 70 140 210 280 350 304.58 303.90 301.22
Number Of First Place Finishes Wins - 97 Tests Linux 5.4 31 [32.0%] Linux 5.3 33 [34.0%] Linux 5.5 33 [34.0%] Number Of First Place Finishes Wins - 97 Tests OpenBenchmarking.org
Number Of Last Place Finishes Losses - 97 Tests Linux 5.4 26 [26.8%] Linux 5.3 34 [35.1%] Linux 5.5 37 [38.1%] Number Of Last Place Finishes Losses - 97 Tests OpenBenchmarking.org
Phoronix Test Suite v10.8.5