AMD EPYC 7F72 24-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2009146-FI-EPYC7F72K42 EPYC 7F72 Kernel Testing - Phoronix Test Suite EPYC 7F72 Kernel Testing AMD EPYC 7F72 24-Core testing with a ASRockRack EPYCD8 (P2.10 BIOS) and ASPEED on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009146-FI-EPYC7F72K42&grs&sro .
EPYC 7F72 Kernel Testing Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution Linux 5.9-rc4 Linux 5.9-rc4 + patch Linux 5.8 AMD EPYC 7F72 24-Core @ 3.20GHz (24 Cores / 48 Threads) ASRockRack EPYCD8 (P2.10 BIOS) AMD Starship/Matisse 126GB 3841GB Micron_9300_MTFDHAL3T8TDP + 32GB Flash Disk ASPEED AMD Starship/Matisse VE228 2 x Intel I350 Ubuntu 20.04 5.9.0-rc4-pts (x86_64) 20200910 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 GCC 9.3.0 ext4 1920x1080 5.9.0-rc4-pts-patch (x86_64) 20200911 1024x768 5.8.0-pts (x86_64) OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-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-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: 0x830101c Java Details - OpenJDK Runtime Environment (build 11.0.8+10-post-Ubuntu-0ubuntu120.04) Python Details - Python 3.8.2 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
EPYC 7F72 Kernel Testing apache-siege: 200 apache-siege: 100 hackbench: 4 - Process apache-siege: 50 hackbench: 2 - Process hackbench: 2 - Thread osbench: Create Processes hackbench: 4 - Thread stress-ng: MMAP hackbench: 8 - Process stress-ng: Context Switching stress-ng: Forking pyperformance: python_startup hackbench: 8 - Thread stress-ng: System V Message Passing osbench: Launch Programs stress-ng: MEMFD hackbench: 32 - Process pmbench: 2 - 50% mcperf: Append - 1 pmbench: 4 - 50% osbench: Create Threads mcperf: Add - 16 mcperf: Append - 16 mcperf: Set - 16 mcperf: Prepend - 16 perf-bench: Epoll Wait hackbench: 16 - Process mcperf: Prepend - 1 mcperf: Replace - 16 mcperf: Get - 16 ethr: TCP - Latency - 1 java-gradle-perf: Reactor mcperf: Replace - 1 geekbench: CPU Single Core - Gaussian Blur gmic: Plotting Isosurface Of A 3D Volume, 1000 Times mcperf: Add - 1 cassandra: Writes mcperf: Set - 1 ecp-candle: P1B2 pyperformance: raytrace apache: Static Web Page Serving mcperf: Delete - 1 nginx: Static Web Page Serving hpcg: geekbench: CPU Multi Core aom-av1: Speed 0 Two-Pass aom-av1: Speed 8 Realtime fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size pyperformance: float build-llvm: Time To Compile compilebench: Initial Create blosc: blosclz schbench: 2 - 6 aom-av1: Speed 6 Two-Pass iperf: 5201 - 10 Seconds - TCP - 20 iperf: 5201 - 10 Seconds - UDP - 1000Mbit Objective - 32 rodinia: OpenMP Leukocyte fs-mark: 1000 Files, 1MB Size, No Sync/FSync schbench: 4 - 8 node-octane: aom-av1: Speed 6 Realtime pgbench: Buffer Test - Single Thread - Read Only dacapobench: Tradesoap schbench: 2 - 8 renaissance: In-Memory Database Shootout ethr: TCP - Bandwidth - 16 stress-ng: Socket Activity perf-bench: Sched Pipe pmbench: 8 - 50% numenta-nab: EXPoSE hackbench: 16 - Thread iperf: 5201 - 10 Seconds - TCP - 32 aom-av1: Speed 4 Two-Pass perf-bench: Memset 1MB schbench: 4 - 4 stress-ng: Memory Copying x264: H.264 Video Encoding dacapobench: H2 ethr: TCP - Connections/s - 1 fs-mark: 1000 Files, 1MB Size stress-ng: Malloc renaissance: Akka Unbalanced Cobwebbed Tree compilebench: Compile mcperf: Delete - 16 ethr: TCP - Latency - 16 mysqlslap: 16 ecp-candle: P3B1 mlpack: scikit_ica ai-benchmark: Device Training Score renaissance: Twitter HTTP Requests dacapobench: Tradebeans numenta-nab: Earthgecko Skyline pgbench: Buffer Test - Single Thread - Read Write mcperf: Get - 1 geekbench: CPU Single Core himeno: Poisson Pressure Solver dacapobench: Jython iperf: 5201 - 10 Seconds - TCP - 1 pmbench: 4 - 100% Writes stress-ng: SENDFILE rodinia: OpenMP Streamcluster compress-zstd: 19 osbench: Memory Allocations build-apache: Time To Compile numenta-nab: Bayesian Changepoint ai-benchmark: Device AI Score osbench: Create Files pgbench: Buffer Test - Normal Load - Read Only stress-ng: Semaphores perf-bench: Futex Lock-Pi lczero: Eigen ai-benchmark: Device Inference Score renaissance: Genetic Algorithm Using Jenetics + Futures stress-ng: NUMA yafaray: Total Time For Sample Scene brl-cad: VGR Performance Metric apache-siege: 10 pmbench: 8 - 100% Writes plaidml: No - Inference - VGG19 - CPU svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p mlpack: scikit_linearridgeregression x265: H.265 1080p Video Encoding geekbench: CPU Single Core - Horizon Detection fs-mark: 5000 Files, 1MB Size, 4 Threads renaissance: Apache Spark ALS svt-av1: Enc Mode 8 - 1080p tensorflow-lite: NASNet Mobile pyperformance: regex_compile rawtherapee: Total Benchmark Time build2: Time To Compile pyperformance: pathlib stress-ng: Glibc Qsort Data Sorting mysqlslap: 128 stress-ng: Vector Math mysqlslap: 64 renaissance: Rand Forest mlpack: scikit_qda numenta-nab: Windowed Gaussian numenta-nab: Relative Entropy rsvg: SVG Files To PNG ecp-candle: P3B2 perf-bench: Futex Hash geekbench: CPU Single Core - Face Detection rodinia: OpenMP HotSpot3D build-linux-kernel: Time To Compile sqlite-speedtest: Timed Time - Size 1,000 pyperformance: 2to3 pmbench: 2 - 100% Writes avifenc: 8 ethr: UDP - Bandwidth - 16 pyperformance: crypto_pyaes pyperformance: nbody pyperformance: chaos oidn: Memorial plaidml: No - Inference - IMDB LSTM - CPU ethr: HTTP - Bandwidth - 16 avifenc: 10 rodinia: OpenMP LavaMD avifenc: 0 pyperformance: django_template pgbench: Buffer Test - Normal Load - Read Write geekbench: CPU Multi Core - Gaussian Blur svt-av1: Enc Mode 4 - 1080p avifenc: 2 plaidml: No - Inference - VGG16 - CPU renaissance: Apache Spark PageRank compilebench: Read Compiled Tree geekbench: CPU Multi Core - Face Detection ocrmypdf: Processing 60 Page PDF Document blender: Fishy Cat - CPU-Only gmic: 2D Function Plotting, 1000 Times blender: Pabellon Barcelona - CPU-Only openvkl: vklBenchmark mlpack: scikit_svm plaidml: No - Inference - Mobilenet - CPU hugin: Panorama Photo Assistant + Stitching Time gmic: 3D Elevated Function In Rand Colors, 100 Times plaidml: No - Inference - DenseNet 201 - CPU blender: BMW27 - CPU-Only cp2k: Fayalite-FIST Data coremark: CoreMark Size 666 - Iterations Per Second pybench: Total For Average Test Times renaissance: Scala Dotty svt-vp9: Visual Quality Optimized - Bosphorus 1080p stress-ng: CPU Stress git: Time To Complete Common Git Commands sqlite: 8 mysqlslap: 32 rodinia: OpenMP CFD Solver pmbench: 4 - 100% Reads blender: Classroom - CPU-Only mysqlslap: 512 tensorflow-lite: Inception V4 phpbench: PHP Benchmark Suite tesseract-ocr: Time To OCR 7 Images perf-bench: Syscall Basic pyperformance: pickle_pure_python lczero: BLAS pyperformance: json_loads pyperformance: go tensorflow-lite: SqueezeNet tensorflow-lite: Mobilenet Quant astcenc: Medium pmbench: 1 - 50% astcenc: Thorough blender: Barbershop - CPU-Only compress-zstd: 3 tensorflow-lite: Inception ResNet V2 pmbench: 2 - 100% Reads pmbench: 1 - 100% Reads pmbench: 8 - 100% Reads mysqlslap: 256 perf-bench: Memcpy 1MB plaidml: No - Inference - Inception V3 - CPU stress-ng: Crypto astcenc: Fast pmbench: 1 - 100% Writes stress-ng: Matrix Math plaidml: No - Inference - ResNet 50 - CPU astcenc: Exhaustive openssl: RSA 4096-bit Performance tensorflow-lite: Mobilenet Float keydb: ethr: HTTP - Bandwidth - 1 stress-ng: Atomic geekbench: CPU Multi Core - Horizon Detection neat: namd: ATPase Simulation - 327,506 Atoms plaidml: No - Inference - NASNer Large - CPU iperf: 5201 - 10 Seconds - UDP - 32 iperf: 5201 - 10 Seconds - UDP - 20 iperf: 5201 - 10 Seconds - UDP - 1 iperf: 5201 - 10 Seconds - UDP - 1000Mbit Objective - 20 iperf: 5201 - 10 Seconds - UDP - 100Mbit Objective - 32 iperf: 5201 - 10 Seconds - UDP - 100Mbit Objective - 20 iperf: 5201 - 10 Seconds - UDP - 1000Mbit Objective - 1 iperf: 5201 - 10 Seconds - UDP - 100Mbit Objective - 1 schbench: 4 - 6 schbench: 4 - 2 schbench: 2 - 4 schbench: 2 - 2 apache-siege: 250 apache-siege: 1 cassandra: Reads stress-ng: Glibc C String Functions stress-ng: CPU Cache redis: SET redis: GET redis: LPUSH redis: SADD redis: LPOP hackbench: 1 - Process hackbench: 1 - Thread svt-vp9: VMAF Optimized - Bosphorus 1080p node-express-loadtest: renaissance: Savina Reactors.IO renaissance: Apache Spark Bayes ethr: TCP - Connections/s - 16 Linux 5.9-rc4 Linux 5.9-rc4 + patch Linux 5.8 19552.82 20975.03 9.252 26919.66 5.558 5.951 49.753984 9.550 410.72 15.015 10013372.56 57705.57 8.79 16.520 12519608.14 68.899791 825.00 56.688 0.1200 41729.0 0.1137 22.447109 39677.1 41622.6 39836.5 41932.0 10720 27.214 42450.5 41885.2 60759.6 21.04 333.129 40974.7 72.6 22.984 39749.9 184151 39138.5 40.362 517 28386.73 60717.2 32458.44 17.0454 25743 0.30 32.26 886.9 128 283.240 585.65 9682.3 34 3.52 34617 31821 53.467 2442.3 37 41798 18.69 20409.591238 3677 39 5229.245 157893.77777778 13647.40 281265 0.1156 889.883 30.854 34398 2.26 58.640326 46 12488.10 174.85 4098 12697 898.4 507114594.73 14532.640 1949.98 59868.9 20.94 6316 614.691 61.05 1451 3405.963 5302 81.029 3064.146293 58072.3 1149 4084.742600 4624 37701 0.0590 387421.39 14.364 102.4 104.051272 23.297 28.902 3325 14.884636 403854.026382 3456386.40 230 2114 1874 1800.313 578.19 90.176 305706 20243.63 0.0586 24.00 369.70 1.66 60.67 26.6 1869.8 2108.752 56.681 98874.3 183 50.535 67.813 18.6 369.27 565 199819.54 1256 1980.277 39.42 7.349 14.988 29.475 863.376 4481219 9.60 97.484 38.710 72.165 348 0.0577 5.548 100940.66666667 118 118 120 18.28 654.03 2758.07 5.413 99.148 62.081 51.3 31955.148057 1.30 6.731 37.902 29.67 3683.318 3023.05 231.5 18.877 86.98 187.639 214.42 290.20 24.70 13.57 50.689 96.425 3.13 67.28 533.876 993262.698054 1068 1655.731 285.77 8853.55 54.990 4.619 2849 10.596 0.0446 196.64 467 1315513 573649 28.743 17262967 499 2255 26.2 263 87232.2 58870.8 6.71 0.1007 10.48 284.71 8384.5 1146990 0.0446 0.0446 0.0447 470 9.232573 10.41 6306.14 5.42 0.0543 101892.21 5.75 81.12 6339.1 58012.2 407410.68 900.40 365322.27 689.0 16.283 0.85790 1.1 33.6 21 1.05 19999 3200 2000 1000 100 41 25 29 27 19657.26 6789.89 1008 3436106.84 53.87 1444961.84 1768092.33 1218625.21 1620429.83 1332716.88 3.093 3.894 353.44 8380 15131.102 224.903 47475 19590.51 20384.64 9.122 27677.37 5.600 5.910 53.490798 9.523 403.89 14.623 11280975.34 58452.66 8.62 16.153 12462106.06 67.121188 824.32 54.910 0.1103 43306.4 0.1089 22.776922 40435.2 42918.6 40598.2 42834.2 11440 25.581 42294.7 42390.3 62084.5 19.85 337.867 41621.8 68.6 21.723 39085.7 174367 40095.9 39.086 495 28553.85 60980.7 32866.12 16.5803 25586 0.29 31.60 895.4 124 291.528 587.33 9810.9 34 3.42 35326 30970 54.947 2424.6 37 40728 18.21 20600.042022 3585 39 5214.587 154016.44444444 13905.76 282779 0.1146 876.250 30.529 34280 2.21 59.919849 47 12753.86 171.77 4184 12800 917.2 501004926.05 14690.062 1950.71 60526.0 20.56 6343 622.247 61.97 1478 3444.914 5254 79.637 3103.422078 58812.6 1130 4150.818714 4624 37672 0.0594 391202.84 14.364 100.9 102.550666 23.373 28.636 3362 14.937108 402885.864141 3441381.21 228 2114 1884 1815.121 585.61 89.910 304906 20149.13 0.0579 24.29 367.35 1.67 60.70 26.3 1854.5 2132.302 56.124 98318.6 182 50.422 68.553 18.4 369.43 561 198393.34 1250 1966.522 39.02 7.277 14.842 29.542 871.628 4524020 9.54 96.588 38.988 71.938 346 0.0582 5.554 101621 118 119 119 18.35 650.52 2737.02 5.427 99.010 62.512 51.7 31943.588086 1.29 6.718 37.619 29.45 3666.592 3000.73 232.5 19.015 86.49 187.461 214.17 290.65 24.73 13.53 50.951 95.831 3.15 66.87 536.976 993613.525992 1064 1658.824 284.30 8880.22 55.266 4.639 2846 10.633 0.0447 196.27 467 1310450 575978 28.856 17307552 499 2246 26.3 263 87168.0 58877.5 6.69 0.1009 10.46 285.02 8383.1 1149627 0.0446 0.0445 0.0448 471 9.214093 10.42 6305.67 5.43 0.0544 102008.94 5.76 81.05 6349.1 57955.4 407892.70 901.47 364924.54 689.3 16.281 0.85795 1.1 33.6 21 1.05 19999 3200 2000 1000 100 41 23 34 26 19731.42 6918.14 730 3322250.21 52.17 1505075.70 1750558.62 1231050.56 1612914.46 1278815.50 3.756 4.104 351.74 7652 14681.450 224.167 59438 57546.34 33610.11 6.434 36228.06 4.321 4.670 43.668906 7.925 350.33 13.084 10450619.33 64896.91 7.82 14.762 13824575.94 62.320232 748.43 51.591 0.1101 39856.0 0.1183 21.004677 37421.6 40015.3 37981.5 40102.3 11138 27.265 39907.8 39855.4 58492.5 20.93 318.950 39296.6 72.0 21.913 37569.4 176581 38084.2 40.989 495 29495.14 58784.8 33656.47 16.4450 24851 0.29 31.23 916.0 125 282.636 603.17 9529.0 35 3.50 35608 30959 54.566 2490.7 38 41816 18.32 20934.704705 3617 40 5098.655 157569.11111111 13570.3 276116 0.1129 869.962 30.167 35056 2.26 59.129714 46 12739.56 171.25 4138 12963 900.7 496833797.02 14829.725 1988.91 59368.2 20.96 6438 626.312 62.19 1456 3384.016 5210 80.726 3117.375594 59073.3 1148 4126.670794 4698 37121 0.0599 385334.22 14.581 100.9 102.888981 23.046 29.034 3316 14.733552 408399.064631 3487114.64 227 2087 1860 1823.494 579.32 89.038 301850 20398.99 0.0586 24.21 365.29 1.68 59.99 26.5 1875.5 2117.255 56.057 97790.3 181 50.974 68.009 18.4 365.52 567 200464.43 1263 1959.971 39.40 7.308 14.958 29.255 867.946 4489484 9.51 97.235 38.630 72.589 345 0.0582 5.596 100755.11111111 117 118 119 18.43 648.79 2736.14 5.456 98.369 62.567 51.7 32192.642460 1.29 6.680 37.759 29.57 3656.008 3023.05 233.2 18.949 86.35 186.287 215.71 292.28 24.56 13.48 50.620 95.809 3.13 67.01 537.09 999077.150684 1062 1649.865 285.09 8898.87 55.075 4.616 2860 10.644 0.0445 197.15 469 1310057 575324 28.859 17238058 501 2248 26.3 262 86930.6 58686.1 6.71 0.1010 10.45 284.21 8361.7 1146897 0.0445 0.0446 0.0447 471 9.226524 10.43 6317.76 5.42 0.0544 101825.56 5.76 80.99 6339.1 57927.7 407304.60 900.88 365355.88 688.9 16.277 0.85800 1.1 33.6 21 1.05 19999 3200 2000 1000 100 43 25 30 25 59490.65 7912.29 572 3354956.81 51.95 1600412.63 1996950.61 1353713.40 1817867.40 1420279.27 3.062 3.239 350.31 8608 14187.883 228.292 61266 OpenBenchmarking.org
Apache Siege Concurrent Users: 200 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 200 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12K 24K 36K 48K 60K SE +/- 927.04, N = 13 SE +/- 74.75, N = 3 SE +/- 135.97, N = 3 57546.34 19552.82 19590.51 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Apache Siege Concurrent Users: 100 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 100 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7K 14K 21K 28K 35K SE +/- 84.95, N = 3 SE +/- 289.78, N = 4 SE +/- 22.31, N = 3 33610.11 20975.03 20384.64 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Hackbench Count: 4 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Process Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.034, N = 3 SE +/- 0.011, N = 3 SE +/- 0.041, N = 3 6.434 9.252 9.122 1. (CC) gcc options: -lpthread
Apache Siege Concurrent Users: 50 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 50 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 8K 16K 24K 32K 40K SE +/- 299.97, N = 3 SE +/- 253.47, N = 9 SE +/- 410.23, N = 3 36228.06 26919.66 27677.37 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Hackbench Count: 2 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Process Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1.26 2.52 3.78 5.04 6.3 SE +/- 0.014, N = 3 SE +/- 0.056, N = 3 SE +/- 0.003, N = 3 4.321 5.558 5.600 1. (CC) gcc options: -lpthread
Hackbench Count: 2 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Thread Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1.339 2.678 4.017 5.356 6.695 SE +/- 0.053, N = 3 SE +/- 0.046, N = 3 SE +/- 0.037, N = 3 4.670 5.951 5.910 1. (CC) gcc options: -lpthread
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12 24 36 48 60 SE +/- 0.37, N = 15 SE +/- 0.50, N = 3 SE +/- 0.38, N = 3 43.67 49.75 53.49 1. (CC) gcc options: -lm
Hackbench Count: 4 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Thread Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.040, N = 3 SE +/- 0.130, N = 3 SE +/- 0.083, N = 3 7.925 9.550 9.523 1. (CC) gcc options: -lpthread
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MMAP Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 90 180 270 360 450 SE +/- 0.57, N = 3 SE +/- 1.41, N = 3 SE +/- 0.65, N = 3 350.33 410.72 403.89 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Hackbench Count: 8 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Process Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.17, N = 6 SE +/- 0.04, N = 3 13.08 15.02 14.62 1. (CC) gcc options: -lpthread
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2M 4M 6M 8M 10M SE +/- 83653.88, N = 14 SE +/- 139140.74, N = 3 SE +/- 83253.58, N = 3 10450619.33 10013372.56 11280975.34 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 14K 28K 42K 56K 70K SE +/- 703.73, N = 3 SE +/- 727.53, N = 15 SE +/- 638.47, N = 15 64896.91 57705.57 58452.66 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
PyPerformance Benchmark: python_startup OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: python_startup Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 7.82 8.79 8.62
Hackbench Count: 8 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Thread Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4 8 12 16 20 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 SE +/- 0.16, N = 3 14.76 16.52 16.15 1. (CC) gcc options: -lpthread
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3M 6M 9M 12M 15M SE +/- 177055.98, N = 3 SE +/- 76200.04, N = 3 SE +/- 181040.40, N = 4 13824575.94 12519608.14 12462106.06 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 15 30 45 60 75 SE +/- 0.75, N = 3 SE +/- 0.35, N = 3 SE +/- 0.25, N = 3 62.32 68.90 67.12 1. (CC) gcc options: -lm
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 0.64, N = 3 SE +/- 0.77, N = 3 SE +/- 0.73, N = 3 748.43 825.00 824.32 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Hackbench Count: 32 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13 26 39 52 65 SE +/- 0.63, N = 3 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 51.59 56.69 54.91 1. (CC) gcc options: -lpthread
pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 50% OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 50% Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.027 0.054 0.081 0.108 0.135 SE +/- 0.0015, N = 4 SE +/- 0.0001, N = 3 SE +/- 0.0017, N = 3 0.1101 0.1200 0.1103 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Memcached mcperf Method: Append - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Append - Connections: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 650.04, N = 3 SE +/- 362.05, N = 15 SE +/- 148.93, N = 3 39856.0 41729.0 43306.4 1. (CC) gcc options: -O2 -lm -rdynamic
pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 50% OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 50% Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0266 0.0532 0.0798 0.1064 0.133 SE +/- 0.0006, N = 3 SE +/- 0.0010, N = 3 SE +/- 0.0006, N = 3 0.1183 0.1137 0.1089 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 SE +/- 0.30, N = 4 SE +/- 0.12, N = 3 SE +/- 0.20, N = 3 21.00 22.45 22.78 1. (CC) gcc options: -lm
Memcached mcperf Method: Add - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Add - Connections: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 182.57, N = 3 SE +/- 127.76, N = 3 SE +/- 190.91, N = 3 37421.6 39677.1 40435.2 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Append - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Append - Connections: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 135.05, N = 3 SE +/- 117.77, N = 3 SE +/- 384.41, N = 3 40015.3 41622.6 42918.6 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Set - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Set - Connections: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 201.66, N = 3 SE +/- 40.38, N = 3 SE +/- 45.06, N = 3 37981.5 39836.5 40598.2 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Prepend - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Prepend - Connections: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 66.44, N = 3 SE +/- 41.21, N = 3 SE +/- 188.96, N = 3 40102.3 41932.0 42834.2 1. (CC) gcc options: -O2 -lm -rdynamic
perf-bench Benchmark: Epoll Wait OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Epoll Wait Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2K 4K 6K 8K 10K SE +/- 92.15, N = 3 SE +/- 146.72, N = 4 SE +/- 72.55, N = 3 11138 10720 11440 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
Hackbench Count: 16 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.32, N = 15 SE +/- 0.28, N = 3 27.27 27.21 25.58 1. (CC) gcc options: -lpthread
Memcached mcperf Method: Prepend - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Prepend - Connections: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 394.48, N = 15 SE +/- 633.01, N = 4 SE +/- 378.71, N = 15 39907.8 42450.5 42294.7 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Replace - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Replace - Connections: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 208.77, N = 3 SE +/- 129.28, N = 3 SE +/- 125.69, N = 3 39855.4 41885.2 42390.3 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Get - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Get - Connections: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13K 26K 39K 52K 65K SE +/- 299.89, N = 3 SE +/- 492.13, N = 3 SE +/- 1045.09, N = 3 58492.5 60759.6 62084.5 1. (CC) gcc options: -O2 -lm -rdynamic
Ethr Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1 OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.21, N = 3 SE +/- 0.18, N = 3 20.93 21.04 19.85 MIN: 9.43 / MAX: 27.34 MIN: 9.51 / MAX: 25.7 MIN: 9.26 / MAX: 24.99
Java Gradle Build Gradle Build: Reactor OpenBenchmarking.org Seconds, Fewer Is Better Java Gradle Build Gradle Build: Reactor Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 70 140 210 280 350 SE +/- 4.35, N = 4 SE +/- 5.33, N = 9 SE +/- 5.46, N = 9 318.95 333.13 337.87
Memcached mcperf Method: Replace - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Replace - Connections: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 347.73, N = 15 SE +/- 560.74, N = 4 SE +/- 651.19, N = 3 39296.6 40974.7 41621.8 1. (CC) gcc options: -O2 -lm -rdynamic
Geekbench Test: CPU Single Core - Gaussian Blur OpenBenchmarking.org Mpixels/sec, More Is Better Geekbench 5 Test: CPU Single Core - Gaussian Blur Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 16 32 48 64 80 SE +/- 0.15, N = 3 SE +/- 0.38, N = 3 SE +/- 1.85, N = 3 72.0 72.6 68.6
G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 21.91 22.98 21.72 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
Memcached mcperf Method: Add - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Add - Connections: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 373.15, N = 15 SE +/- 342.85, N = 11 SE +/- 519.15, N = 3 37569.4 39749.9 39085.7 1. (CC) gcc options: -O2 -lm -rdynamic
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Writes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 40K 80K 120K 160K 200K SE +/- 1589.70, N = 3 SE +/- 2545.69, N = 3 SE +/- 1825.19, N = 3 176581 184151 174367
Memcached mcperf Method: Set - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Set - Connections: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 472.77, N = 3 SE +/- 373.15, N = 3 SE +/- 431.42, N = 3 38084.2 39138.5 40095.9 1. (CC) gcc options: -O2 -lm -rdynamic
ECP-CANDLE Benchmark: P1B2 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.3 Benchmark: P1B2 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9 18 27 36 45 40.99 40.36 39.09
PyPerformance Benchmark: raytrace OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: raytrace Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 110 220 330 440 550 SE +/- 0.33, N = 3 SE +/- 1.00, N = 3 495 517 495
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6K 12K 18K 24K 30K SE +/- 222.22, N = 3 SE +/- 30.81, N = 3 SE +/- 56.84, N = 3 29495.14 28386.73 28553.85 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Memcached mcperf Method: Delete - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Delete - Connections: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13K 26K 39K 52K 65K SE +/- 733.36, N = 15 SE +/- 661.72, N = 15 SE +/- 639.33, N = 15 58784.8 60717.2 60980.7 1. (CC) gcc options: -O2 -lm -rdynamic
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7K 14K 21K 28K 35K SE +/- 538.68, N = 3 SE +/- 304.93, N = 3 SE +/- 241.38, N = 3 33656.47 32458.44 32866.12 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4 8 12 16 20 SE +/- 0.17, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 16.45 17.05 16.58 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
Geekbench Test: CPU Multi Core OpenBenchmarking.org Score, More Is Better Geekbench 5 Test: CPU Multi Core Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6K 12K 18K 24K 30K SE +/- 163.22, N = 3 SE +/- 59.41, N = 3 SE +/- 16.84, N = 3 24851 25743 25586
AOM AV1 Encoder Mode: Speed 0 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0675 0.135 0.2025 0.27 0.3375 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.29 0.30 0.29 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 8 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 8 Realtime Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7 14 21 28 35 SE +/- 0.32, N = 3 SE +/- 0.20, N = 3 SE +/- 0.25, N = 3 31.23 32.26 31.60 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
FS-Mark Test: 4000 Files, 32 Sub Dirs, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 7.53, N = 13 SE +/- 2.74, N = 3 SE +/- 6.61, N = 3 916.0 886.9 895.4 1. (CC) gcc options: -static
PyPerformance Benchmark: float OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 30 60 90 120 150 SE +/- 0.33, N = 3 125 128 124
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 10.0 Time To Compile Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 60 120 180 240 300 SE +/- 0.81, N = 3 SE +/- 3.09, N = 3 SE +/- 4.59, N = 3 282.64 283.24 291.53
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 130 260 390 520 650 SE +/- 3.10, N = 3 SE +/- 2.19, N = 3 SE +/- 2.92, N = 3 603.17 585.65 587.33
C-Blosc Compressor: blosclz OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.0 Beta 5 Compressor: blosclz Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2K 4K 6K 8K 10K SE +/- 136.70, N = 3 SE +/- 167.64, N = 3 SE +/- 109.39, N = 3 9529.0 9682.3 9810.9
Schbench Message Threads: 2 - Workers Per Message Thread: 6 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 2 - Workers Per Message Thread: 6 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 8 16 24 32 40 SE +/- 0.46, N = 15 35 34 34 1. (CC) gcc options: -O2 -lpthread
AOM AV1 Encoder Mode: Speed 6 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.792 1.584 2.376 3.168 3.96 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.50 3.52 3.42 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 20 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 20 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 8K 16K 24K 32K 40K SE +/- 159.38, N = 3 SE +/- 505.96, N = 4 SE +/- 88.72, N = 3 35608 34617 35326
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 32 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 32 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7K 14K 21K 28K 35K SE +/- 227.51, N = 3 SE +/- 80.71, N = 3 SE +/- 83.70, N = 3 30959 31821 30970
Rodinia Test: OpenMP Leukocyte OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Leukocyte Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12 24 36 48 60 SE +/- 0.38, N = 3 SE +/- 0.70, N = 3 SE +/- 0.17, N = 3 54.57 53.47 54.95 1. (CXX) g++ options: -O2 -lOpenCL
FS-Mark Test: 1000 Files, 1MB Size, No Sync/FSync OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size, No Sync/FSync Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 500 1000 1500 2000 2500 SE +/- 3.80, N = 3 SE +/- 12.61, N = 3 SE +/- 13.74, N = 3 2490.7 2442.3 2424.6 1. (CC) gcc options: -static
Schbench Message Threads: 4 - Workers Per Message Thread: 8 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 4 - Workers Per Message Thread: 8 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9 18 27 36 45 SE +/- 0.50, N = 4 SE +/- 0.34, N = 10 SE +/- 0.52, N = 12 38 37 37 1. (CC) gcc options: -O2 -lpthread
Node.js Octane Benchmark OpenBenchmarking.org Score, More Is Better Node.js Octane Benchmark Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9K 18K 27K 36K 45K SE +/- 51.52, N = 3 SE +/- 97.84, N = 3 SE +/- 142.03, N = 3 41816 41798 40728 1. Nodejs
v10.19.0
AOM AV1 Encoder Mode: Speed 6 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Realtime Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 18.32 18.69 18.21 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
PostgreSQL pgbench Scaling: Buffer Test - Test: Single Thread - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Single Thread - Mode: Read Only Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4K 8K 12K 16K 20K SE +/- 244.73, N = 3 SE +/- 61.10, N = 3 SE +/- 317.87, N = 3 20934.70 20409.59 20600.04 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 800 1600 2400 3200 4000 SE +/- 36.61, N = 4 SE +/- 28.76, N = 4 SE +/- 11.21, N = 4 3617 3677 3585
Schbench Message Threads: 2 - Workers Per Message Thread: 8 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 2 - Workers Per Message Thread: 8 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9 18 27 36 45 SE +/- 0.53, N = 15 SE +/- 0.67, N = 3 40 39 39 1. (CC) gcc options: -O2 -lpthread
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: In-Memory Database Shootout Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1100 2200 3300 4400 5500 SE +/- 42.42, N = 25 SE +/- 42.32, N = 25 SE +/- 56.62, N = 5 5098.66 5229.25 5214.59
Ethr Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 16 OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Bandwidth - Threads: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 30K 60K 90K 120K 150K SE +/- 1299.83, N = 3 SE +/- 681.49, N = 3 SE +/- 1299.86, N = 3 157569.11 157893.78 154016.44 MIN: 149340 / MAX: 165470 MIN: 153130 / MAX: 163030 MIN: 147370 / MAX: 161610
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3K 6K 9K 12K 15K SE +/- 23.38, N = 3 SE +/- 22.48, N = 3 SE +/- 27.32, N = 3 13570.30 13647.40 13905.76 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
perf-bench Benchmark: Sched Pipe OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 60K 120K 180K 240K 300K SE +/- 1191.59, N = 3 SE +/- 101.60, N = 3 SE +/- 625.59, N = 3 276116 281265 282779 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 50% OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 50% Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.026 0.052 0.078 0.104 0.13 SE +/- 0.0004, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0001, N = 3 0.1129 0.1156 0.1146 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Numenta Anomaly Benchmark Detector: EXPoSE OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: EXPoSE Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 10.83, N = 3 SE +/- 11.93, N = 4 SE +/- 8.43, N = 3 869.96 889.88 876.25
Hackbench Count: 16 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.29, N = 13 SE +/- 0.17, N = 3 30.17 30.85 30.53 1. (CC) gcc options: -lpthread
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 32 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 32 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 8K 16K 24K 32K 40K SE +/- 302.11, N = 3 SE +/- 500.64, N = 3 SE +/- 221.49, N = 3 35056 34398 34280
AOM AV1 Encoder Mode: Speed 4 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.5085 1.017 1.5255 2.034 2.5425 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.26 2.26 2.21 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
perf-bench Benchmark: Memset 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13 26 39 52 65 SE +/- 0.55, N = 15 SE +/- 0.97, N = 3 SE +/- 0.58, N = 9 59.13 58.64 59.92 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
Schbench Message Threads: 4 - Workers Per Message Thread: 4 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 4 - Workers Per Message Thread: 4 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 11 22 33 44 55 SE +/- 0.42, N = 15 46 46 47 1. (CC) gcc options: -O2 -lpthread
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3K 6K 9K 12K 15K SE +/- 51.45, N = 3 SE +/- 37.14, N = 3 SE +/- 135.22, N = 3 12739.56 12488.10 12753.86 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 40 80 120 160 200 SE +/- 2.23, N = 3 SE +/- 2.31, N = 3 SE +/- 2.78, N = 3 171.25 174.85 171.77 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 900 1800 2700 3600 4500 SE +/- 50.79, N = 5 SE +/- 36.52, N = 4 SE +/- 21.51, N = 4 4138 4098 4184
Ethr Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1 OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3K 6K 9K 12K 15K SE +/- 184.78, N = 3 SE +/- 142.09, N = 7 SE +/- 164.42, N = 3 12963 12697 12800
FS-Mark Test: 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 3.81, N = 3 SE +/- 11.44, N = 3 SE +/- 10.71, N = 3 900.7 898.4 917.2 1. (CC) gcc options: -static
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 110M 220M 330M 440M 550M SE +/- 2318709.71, N = 3 SE +/- 8156468.21, N = 3 SE +/- 6830608.46, N = 4 496833797.02 507114594.73 501004926.05 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Akka Unbalanced Cobwebbed Tree Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3K 6K 9K 12K 15K SE +/- 66.42, N = 5 SE +/- 123.71, N = 5 SE +/- 121.92, N = 13 14829.73 14532.64 14690.06
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400 800 1200 1600 2000 SE +/- 22.26, N = 6 SE +/- 20.22, N = 8 SE +/- 6.60, N = 3 1988.91 1949.98 1950.71
Memcached mcperf Method: Delete - Connections: 16 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Delete - Connections: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13K 26K 39K 52K 65K SE +/- 656.67, N = 3 SE +/- 280.02, N = 3 SE +/- 567.29, N = 3 59368.2 59868.9 60526.0 1. (CC) gcc options: -O2 -lm -rdynamic
Ethr Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 16 OpenBenchmarking.org Microseconds, Fewer Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Latency - Threads: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.24, N = 3 SE +/- 0.23, N = 3 20.96 20.94 20.56 MIN: 9.43 / MAX: 27.14 MIN: 9.25 / MAX: 26.59 MIN: 9.09 / MAX: 25.01
MariaDB Clients: 16 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1400 2800 4200 5600 7000 SE +/- 13.79, N = 3 SE +/- 13.27, N = 3 SE +/- 13.44, N = 3 6438 6316 6343 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
ECP-CANDLE Benchmark: P3B1 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.3 Benchmark: P3B1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 140 280 420 560 700 626.31 614.69 622.25
Mlpack Benchmark Benchmark: scikit_ica OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_ica Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 14 28 42 56 70 SE +/- 0.32, N = 3 SE +/- 0.32, N = 3 SE +/- 0.43, N = 3 62.19 61.05 61.97
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 300 600 900 1200 1500 1456 1451 1478
Renaissance Test: Twitter HTTP Requests OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Twitter HTTP Requests Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 700 1400 2100 2800 3500 SE +/- 17.46, N = 5 SE +/- 29.45, N = 5 SE +/- 19.19, N = 5 3384.02 3405.96 3444.91
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1100 2200 3300 4400 5500 SE +/- 38.95, N = 4 SE +/- 18.92, N = 4 SE +/- 13.60, N = 4 5210 5302 5254
Numenta Anomaly Benchmark Detector: Earthgecko Skyline OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.46, N = 3 SE +/- 0.16, N = 3 SE +/- 0.41, N = 3 80.73 81.03 79.64
PostgreSQL pgbench Scaling: Buffer Test - Test: Single Thread - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Single Thread - Mode: Read Write Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 700 1400 2100 2800 3500 SE +/- 16.49, N = 3 SE +/- 22.86, N = 3 SE +/- 27.44, N = 3 3117.38 3064.15 3103.42 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Memcached mcperf Method: Get - Connections: 1 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.6.0 Method: Get - Connections: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13K 26K 39K 52K 65K SE +/- 634.23, N = 15 SE +/- 550.61, N = 3 SE +/- 340.87, N = 3 59073.3 58072.3 58812.6 1. (CC) gcc options: -O2 -lm -rdynamic
Geekbench Test: CPU Single Core OpenBenchmarking.org Score, More Is Better Geekbench 5 Test: CPU Single Core Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 0.58, N = 3 SE +/- 2.08, N = 3 SE +/- 2.85, N = 3 1148 1149 1130
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 900 1800 2700 3600 4500 SE +/- 54.03, N = 3 SE +/- 8.08, N = 3 SE +/- 57.39, N = 3 4126.67 4084.74 4150.82 1. (CC) gcc options: -O3 -mavx2
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1000 2000 3000 4000 5000 SE +/- 20.14, N = 4 SE +/- 8.24, N = 4 SE +/- 9.23, N = 4 4698 4624 4624
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 1 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 8K 16K 24K 32K 40K SE +/- 322.08, N = 3 SE +/- 403.01, N = 3 SE +/- 421.94, N = 3 37121 37701 37672
pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Writes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0135 0.027 0.0405 0.054 0.0675 SE +/- 0.0000, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 0.0599 0.0590 0.0594 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 80K 160K 240K 320K 400K SE +/- 432.99, N = 3 SE +/- 1479.69, N = 3 SE +/- 1577.06, N = 3 385334.22 387421.39 391202.84 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP Streamcluster Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 14.58 14.36 14.36 1. (CXX) g++ options: -O2 -lOpenCL
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.35, N = 3 SE +/- 0.12, N = 3 100.9 102.4 100.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 102.89 104.05 102.55 1. (CC) gcc options: -lm
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 23.05 23.30 23.37
Numenta Anomaly Benchmark Detector: Bayesian Changepoint OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7 14 21 28 35 SE +/- 0.23, N = 3 SE +/- 0.35, N = 3 SE +/- 0.24, N = 3 29.03 28.90 28.64
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 700 1400 2100 2800 3500 3316 3325 3362
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 14.73 14.88 14.94 1. (CC) gcc options: -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 90K 180K 270K 360K 450K SE +/- 136.76, N = 3 SE +/- 993.29, N = 3 SE +/- 591.63, N = 3 408399.06 403854.03 402885.86 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 700K 1400K 2100K 2800K 3500K SE +/- 7301.99, N = 3 SE +/- 16327.08, N = 3 SE +/- 7309.65, N = 3 3487114.64 3456386.40 3441381.21 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
perf-bench Benchmark: Futex Lock-Pi OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Lock-Pi Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 50 100 150 200 250 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 227 230 228 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 500 1000 1500 2000 2500 SE +/- 31.24, N = 4 SE +/- 26.31, N = 3 SE +/- 20.88, N = 3 2087 2114 2114 1. (CXX) g++ options: -flto -pthread
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400 800 1200 1600 2000 1860 1874 1884
Renaissance Test: Genetic Algorithm Using Jenetics + Futures OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Genetic Algorithm Using Jenetics + Futures Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400 800 1200 1600 2000 SE +/- 19.79, N = 5 SE +/- 20.78, N = 5 SE +/- 17.01, N = 10 1823.49 1800.31 1815.12
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 130 260 390 520 650 SE +/- 3.25, N = 3 SE +/- 3.08, N = 3 SE +/- 0.60, N = 3 579.32 578.19 585.61 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.69, N = 3 SE +/- 0.89, N = 3 SE +/- 0.63, N = 3 89.04 90.18 89.91 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 70K 140K 210K 280K 350K 301850 305706 304906 1. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm
Apache Siege Concurrent Users: 10 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 10 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4K 8K 12K 16K 20K SE +/- 220.02, N = 3 SE +/- 85.07, N = 3 SE +/- 118.21, N = 3 20398.99 20243.63 20149.13 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Writes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0132 0.0264 0.0396 0.0528 0.066 SE +/- 0.0001, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0001, N = 3 0.0586 0.0586 0.0579 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG19 - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.15, N = 3 SE +/- 0.21, N = 3 SE +/- 0.11, N = 3 24.21 24.00 24.29
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 80 160 240 320 400 SE +/- 2.40, N = 3 SE +/- 1.50, N = 3 SE +/- 1.20, N = 3 365.29 369.70 367.35 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Mlpack Benchmark Benchmark: scikit_linearridgeregression OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.378 0.756 1.134 1.512 1.89 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.68 1.66 1.67
x265 H.265 1080p Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x265 3.1.2 H.265 1080p Video Encoding Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 14 28 42 56 70 SE +/- 0.12, N = 3 SE +/- 0.29, N = 3 SE +/- 0.16, N = 3 59.99 60.67 60.70 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Geekbench Test: CPU Single Core - Horizon Detection OpenBenchmarking.org Gpixels/sec, More Is Better Geekbench 5 Test: CPU Single Core - Horizon Detection Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 26.5 26.6 26.3
FS-Mark Test: 5000 Files, 1MB Size, 4 Threads OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400 800 1200 1600 2000 SE +/- 3.48, N = 3 SE +/- 8.13, N = 3 SE +/- 0.44, N = 3 1875.5 1869.8 1854.5 1. (CC) gcc options: -static
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark ALS Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 500 1000 1500 2000 2500 SE +/- 13.96, N = 25 SE +/- 13.10, N = 5 SE +/- 16.24, N = 25 2117.26 2108.75 2132.30
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 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13 26 39 52 65 SE +/- 0.26, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 56.06 56.68 56.12 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20K 40K 60K 80K 100K SE +/- 201.80, N = 3 SE +/- 813.90, N = 15 SE +/- 325.26, N = 3 97790.3 98874.3 98318.6
PyPerformance Benchmark: regex_compile OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 181 183 182
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12 24 36 48 60 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 50.97 50.54 50.42 1. RawTherapee, version 5.8, command line.
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.12 Time To Compile Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 15 30 45 60 75 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 68.01 67.81 68.55
PyPerformance Benchmark: pathlib OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 18.4 18.6 18.4
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 80 160 240 320 400 SE +/- 1.76, N = 3 SE +/- 1.24, N = 3 SE +/- 0.91, N = 3 365.52 369.27 369.43 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
MariaDB Clients: 128 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 128 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 120 240 360 480 600 SE +/- 0.28, N = 3 SE +/- 0.43, N = 3 SE +/- 0.48, N = 3 567 565 561 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 40K 80K 120K 160K 200K SE +/- 272.80, N = 3 SE +/- 46.71, N = 3 SE +/- 693.74, N = 3 200464.43 199819.54 198393.34 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
MariaDB Clients: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 64 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 300 600 900 1200 1500 SE +/- 1.60, N = 3 SE +/- 1.39, N = 3 SE +/- 0.90, N = 3 1263 1256 1250 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Random Forest Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400 800 1200 1600 2000 SE +/- 9.85, N = 5 SE +/- 20.68, N = 8 SE +/- 11.99, N = 24 1959.97 1980.28 1966.52
Mlpack Benchmark Benchmark: scikit_qda OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_qda Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9 18 27 36 45 SE +/- 0.15, N = 3 SE +/- 0.29, N = 3 SE +/- 0.29, N = 3 39.40 39.42 39.02
Numenta Anomaly Benchmark Detector: Windowed Gaussian OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2 4 6 8 10 SE +/- 0.058, N = 3 SE +/- 0.017, N = 3 SE +/- 0.036, N = 3 7.308 7.349 7.277
Numenta Anomaly Benchmark Detector: Relative Entropy OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 14.96 14.99 14.84
librsvg Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better librsvg Operation: SVG Files To PNG Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 29.26 29.48 29.54 1. rsvg-convert version 2.48.7
ECP-CANDLE Benchmark: P3B2 OpenBenchmarking.org Seconds, Fewer Is Better ECP-CANDLE 0.3 Benchmark: P3B2 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 867.95 863.38 871.63
perf-bench Benchmark: Futex Hash OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1000K 2000K 3000K 4000K 5000K SE +/- 12029.79, N = 3 SE +/- 31420.68, N = 3 SE +/- 7982.38, N = 3 4489484 4481219 4524020 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
Geekbench Test: CPU Single Core - Face Detection OpenBenchmarking.org images/sec, More Is Better Geekbench 5 Test: CPU Single Core - Face Detection Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 9.51 9.60 9.54
Rodinia Test: OpenMP HotSpot3D OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP HotSpot3D Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.63, N = 3 SE +/- 0.20, N = 3 SE +/- 0.67, N = 3 97.24 97.48 96.59 1. (CXX) g++ options: -O2 -lOpenCL
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9 18 27 36 45 SE +/- 0.59, N = 3 SE +/- 0.58, N = 3 SE +/- 0.60, N = 3 38.63 38.71 38.99
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 16 32 48 64 80 SE +/- 0.30, N = 3 SE +/- 0.58, N = 3 SE +/- 0.53, N = 3 72.59 72.17 71.94 1. (CC) gcc options: -O2 -ldl -lz -lpthread
PyPerformance Benchmark: 2to3 OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: 2to3 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 80 160 240 320 400 345 348 346
pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Writes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0131 0.0262 0.0393 0.0524 0.0655 SE +/- 0.0002, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 0.0582 0.0577 0.0582 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
libavif avifenc Encoder Speed: 8 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 8 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1.2591 2.5182 3.7773 5.0364 6.2955 SE +/- 0.021, N = 3 SE +/- 0.014, N = 3 SE +/- 0.013, N = 3 5.596 5.548 5.554 1. (CXX) g++ options: -O3 -fPIC
Ethr Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16 OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: UDP - Test: Bandwidth - Threads: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20K 40K 60K 80K 100K SE +/- 247.15, N = 3 SE +/- 381.35, N = 3 SE +/- 168.23, N = 3 100755.11 100940.67 101621.00 MIN: 99490 / MAX: 102530 MIN: 99560 / MAX: 102240 MIN: 100670 / MAX: 102740
PyPerformance Benchmark: crypto_pyaes OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 30 60 90 120 150 117 118 118
PyPerformance Benchmark: nbody OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: nbody Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 30 60 90 120 150 SE +/- 0.33, N = 3 118 118 119
PyPerformance Benchmark: chaos OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: chaos Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 30 60 90 120 150 119 120 119
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.2.0 Scene: Memorial Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.21, N = 3 SE +/- 0.13, N = 3 18.43 18.28 18.35
PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: IMDB LSTM - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 140 280 420 560 700 SE +/- 1.83, N = 3 SE +/- 2.66, N = 3 SE +/- 3.34, N = 3 648.79 654.03 650.52
Ethr Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 16 OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 600 1200 1800 2400 3000 SE +/- 6.73, N = 3 SE +/- 14.09, N = 3 SE +/- 14.94, N = 3 2736.14 2758.07 2737.02 MIN: 2660 / MAX: 2850 MIN: 2640 / MAX: 2840 MIN: 2650 / MAX: 2840
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 10 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1.2276 2.4552 3.6828 4.9104 6.138 SE +/- 0.021, N = 3 SE +/- 0.015, N = 3 SE +/- 0.015, N = 3 5.456 5.413 5.427 1. (CXX) g++ options: -O3 -fPIC
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 1.48, N = 3 SE +/- 1.72, N = 3 SE +/- 1.12, N = 3 98.37 99.15 99.01 1. (CXX) g++ options: -O2 -lOpenCL
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 0 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 14 28 42 56 70 SE +/- 0.17, N = 3 SE +/- 0.13, N = 3 SE +/- 0.25, N = 3 62.57 62.08 62.51 1. (CXX) g++ options: -O3 -fPIC
PyPerformance Benchmark: django_template OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12 24 36 48 60 SE +/- 0.10, N = 3 SE +/- 0.26, N = 3 SE +/- 0.19, N = 3 51.7 51.3 51.7
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7K 14K 21K 28K 35K SE +/- 126.41, N = 3 SE +/- 140.24, N = 3 SE +/- 71.81, N = 3 32192.64 31955.15 31943.59 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Geekbench Test: CPU Multi Core - Gaussian Blur OpenBenchmarking.org Mpixels/sec, More Is Better Geekbench 5 Test: CPU Multi Core - Gaussian Blur Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.2925 0.585 0.8775 1.17 1.4625 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.29 1.30 1.29
SVT-AV1 Encoder Mode: Enc Mode 4 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2 4 6 8 10 SE +/- 0.021, N = 3 SE +/- 0.061, N = 3 SE +/- 0.025, N = 3 6.680 6.731 6.718 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 2 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.28, N = 3 SE +/- 0.10, N = 3 37.76 37.90 37.62 1. (CXX) g++ options: -O3 -fPIC
PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7 14 21 28 35 SE +/- 0.25, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 29.57 29.67 29.45
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark PageRank Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 800 1600 2400 3200 4000 SE +/- 39.49, N = 21 SE +/- 31.40, N = 25 SE +/- 39.23, N = 25 3656.01 3683.32 3666.59
Compile Bench Test: Read Compiled Tree OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Read Compiled Tree Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 600 1200 1800 2400 3000 SE +/- 10.79, N = 3 SE +/- 10.79, N = 3 SE +/- 10.44, N = 3 3023.05 3023.05 3000.73
Geekbench Test: CPU Multi Core - Face Detection OpenBenchmarking.org images/sec, More Is Better Geekbench 5 Test: CPU Multi Core - Face Detection Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 50 100 150 200 250 SE +/- 0.84, N = 3 SE +/- 1.46, N = 3 SE +/- 1.93, N = 3 233.2 231.5 232.5
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 18.95 18.88 19.02
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: CPU-Only Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.29, N = 3 SE +/- 0.16, N = 3 86.35 86.98 86.49
G'MIC Test: 2D Function Plotting, 1000 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 2D Function Plotting, 1000 Times Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 40 80 120 160 200 SE +/- 1.89, N = 3 SE +/- 1.10, N = 3 SE +/- 1.76, N = 3 186.29 187.64 187.46 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Pabellon Barcelona - Compute: CPU-Only Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 50 100 150 200 250 SE +/- 0.89, N = 3 SE +/- 0.50, N = 3 SE +/- 0.46, N = 3 215.71 214.42 214.17
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 60 120 180 240 300 SE +/- 0.51, N = 3 SE +/- 0.85, N = 3 SE +/- 0.61, N = 3 292.28 290.20 290.65 MIN: 1 / MAX: 1031 MIN: 1 / MAX: 1034 MIN: 1 / MAX: 1033
Mlpack Benchmark Benchmark: scikit_svm OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_svm Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 24.56 24.70 24.73
PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Mobilenet - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 13.48 13.57 13.53
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 11 22 33 44 55 SE +/- 0.35, N = 3 SE +/- 0.08, N = 3 SE +/- 0.22, N = 3 50.62 50.69 50.95
G'MIC Test: 3D Elevated Function In Random Colors, 100 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 3D Elevated Function In Random Colors, 100 Times Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 95.81 96.43 95.83 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: DenseNet 201 - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.7088 1.4176 2.1264 2.8352 3.544 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.13 3.13 3.15
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: CPU-Only Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 15 30 45 60 75 SE +/- 0.30, N = 3 SE +/- 0.40, N = 3 SE +/- 0.06, N = 3 67.01 67.28 66.87
CP2K Molecular Dynamics Fayalite-FIST Data OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 6.1 Fayalite-FIST Data Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 120 240 360 480 600 537.09 533.88 536.98
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200K 400K 600K 800K 1000K SE +/- 1904.47, N = 3 SE +/- 646.60, N = 3 SE +/- 2354.81, N = 3 999077.15 993262.70 993613.53 1. (CC) gcc options: -O2 -lrt" -lrt
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 1.33, N = 3 SE +/- 0.67, N = 3 1062 1068 1064
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Scala Dotty Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400 800 1200 1600 2000 SE +/- 3.92, N = 5 SE +/- 8.56, N = 5 SE +/- 4.48, N = 5 1649.87 1655.73 1658.82
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 60 120 180 240 300 SE +/- 2.84, N = 3 SE +/- 1.50, N = 3 SE +/- 2.07, N = 3 285.09 285.77 284.30 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2K 4K 6K 8K 10K SE +/- 5.81, N = 3 SE +/- 9.65, N = 3 SE +/- 12.97, N = 3 8898.87 8853.55 8880.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Git Time To Complete Common Git Commands OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12 24 36 48 60 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 55.08 54.99 55.27 1. git version 2.25.1
SQLite Threads / Copies: 8 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 8 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1.0438 2.0876 3.1314 4.1752 5.219 SE +/- 0.007, N = 3 SE +/- 0.006, N = 3 SE +/- 0.013, N = 3 4.616 4.619 4.639 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
MariaDB Clients: 32 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 32 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 600 1200 1800 2400 3000 SE +/- 2.73, N = 3 SE +/- 4.69, N = 3 SE +/- 2.70, N = 3 2860 2849 2846 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP CFD Solver Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 10.64 10.60 10.63 1. (CXX) g++ options: -O2 -lOpenCL
pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Reads OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 100% Reads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0101 0.0202 0.0303 0.0404 0.0505 SE +/- 0.0000, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 0.0445 0.0446 0.0447 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Classroom - Compute: CPU-Only Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 40 80 120 160 200 SE +/- 0.38, N = 3 SE +/- 0.43, N = 3 SE +/- 0.36, N = 3 197.15 196.64 196.27
MariaDB Clients: 512 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 512 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 100 200 300 400 500 SE +/- 0.29, N = 3 SE +/- 0.79, N = 3 SE +/- 0.83, N = 3 469 467 467 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 300K 600K 900K 1200K 1500K SE +/- 2207.16, N = 3 SE +/- 3706.10, N = 3 SE +/- 927.70, N = 3 1310057 1315513 1310450
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 120K 240K 360K 480K 600K SE +/- 1790.21, N = 3 SE +/- 1018.50, N = 3 SE +/- 1065.12, N = 3 575324 573649 575978
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.1.1 Time To OCR 7 Images Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 7 14 21 28 35 SE +/- 0.19, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 28.86 28.74 28.86
perf-bench Benchmark: Syscall Basic OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4M 8M 12M 16M 20M SE +/- 10970.47, N = 3 SE +/- 34882.47, N = 3 SE +/- 12427.16, N = 3 17238058 17262967 17307552 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
PyPerformance Benchmark: pickle_pure_python OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pickle_pure_python Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 110 220 330 440 550 SE +/- 1.00, N = 3 SE +/- 1.20, N = 3 501 499 499
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 500 1000 1500 2000 2500 SE +/- 16.05, N = 3 SE +/- 24.90, N = 3 SE +/- 29.54, N = 3 2248 2255 2246 1. (CXX) g++ options: -flto -pthread
PyPerformance Benchmark: json_loads OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: json_loads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 26.3 26.2 26.3
PyPerformance Benchmark: go OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: go Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 60 120 180 240 300 262 263 263
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20K 40K 60K 80K 100K SE +/- 91.50, N = 3 SE +/- 123.22, N = 3 SE +/- 182.64, N = 3 86930.6 87232.2 87168.0
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13K 26K 39K 52K 65K SE +/- 130.06, N = 3 SE +/- 162.01, N = 3 SE +/- 240.60, N = 3 58686.1 58870.8 58877.5
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 6.71 6.71 6.69 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 50% OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 50% Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0227 0.0454 0.0681 0.0908 0.1135 SE +/- 0.0002, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 0.1010 0.1007 0.1009 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 10.45 10.48 10.46 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: CPU-Only Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 60 120 180 240 300 SE +/- 0.46, N = 3 SE +/- 0.47, N = 3 SE +/- 0.15, N = 3 284.21 284.71 285.02
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2K 4K 6K 8K 10K SE +/- 49.48, N = 3 SE +/- 12.19, N = 3 SE +/- 54.65, N = 3 8361.7 8384.5 8383.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200K 400K 600K 800K 1000K SE +/- 1754.01, N = 3 SE +/- 2220.12, N = 3 SE +/- 1962.09, N = 3 1146897 1146990 1149627
pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Reads OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 100% Reads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.01 0.02 0.03 0.04 0.05 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 0.0445 0.0446 0.0446 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Reads OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Reads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.01 0.02 0.03 0.04 0.05 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0000, N = 3 0.0446 0.0446 0.0445 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Reads OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 100% Reads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0101 0.0202 0.0303 0.0404 0.0505 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0001, N = 3 0.0447 0.0447 0.0448 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
MariaDB Clients: 256 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.5.2 Clients: 256 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 100 200 300 400 500 SE +/- 0.26, N = 3 SE +/- 0.27, N = 3 SE +/- 0.75, N = 3 471 470 471 1. (CXX) g++ options: -pie -fPIC -fstack-protector -O2 -lpthread -llzma -lbz2 -lsnappy -laio -lnuma -lpcre2-8 -lcrypt -lz -lm -lssl -lcrypto -ldl
perf-bench Benchmark: Memcpy 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memcpy 1MB Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.074362, N = 15 SE +/- 0.130104, N = 3 SE +/- 0.086709, N = 9 9.226524 9.232573 9.214093 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lslang -lz -llzma -lnuma
PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: Inception V3 - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 10.43 10.41 10.42
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1400 2800 4200 5600 7000 SE +/- 5.80, N = 3 SE +/- 6.01, N = 3 SE +/- 8.19, N = 3 6317.76 6306.14 6305.67 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
ASTC Encoder Preset: Fast OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1.2218 2.4436 3.6654 4.8872 6.109 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 5.42 5.42 5.43 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 100% Writes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.0122 0.0244 0.0366 0.0488 0.061 SE +/- 0.0000, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0000, N = 3 0.0544 0.0543 0.0544 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20K 40K 60K 80K 100K SE +/- 133.87, N = 3 SE +/- 628.54, N = 3 SE +/- 1435.26, N = 3 101825.56 101892.21 102008.94 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1.296 2.592 3.888 5.184 6.48 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 5.76 5.75 5.76
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 80.99 81.12 81.05 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 1400 2800 4200 5600 7000 SE +/- 3.84, N = 3 SE +/- 4.91, N = 3 SE +/- 3.46, N = 3 6339.1 6339.1 6349.1 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12K 24K 36K 48K 60K SE +/- 166.77, N = 3 SE +/- 116.29, N = 3 SE +/- 165.53, N = 3 57927.7 58012.2 57955.4
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 5.3.1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 90K 180K 270K 360K 450K SE +/- 2172.59, N = 3 SE +/- 1167.53, N = 3 SE +/- 2298.43, N = 3 407304.60 407410.68 407892.70 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
Ethr Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1 OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 2.18, N = 3 SE +/- 1.96, N = 3 SE +/- 1.52, N = 3 900.88 900.40 901.47 MIN: 866.56 / MAX: 942.98 MIN: 867.33 / MAX: 946.18 MIN: 869.12 / MAX: 943.49
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 80K 160K 240K 320K 400K SE +/- 1680.39, N = 3 SE +/- 807.54, N = 3 SE +/- 1112.08, N = 3 365355.88 365322.27 364924.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Geekbench Test: CPU Multi Core - Horizon Detection OpenBenchmarking.org Gpixels/sec, More Is Better Geekbench 5 Test: CPU Multi Core - Horizon Detection Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 150 300 450 600 750 SE +/- 1.03, N = 3 SE +/- 0.41, N = 3 SE +/- 0.64, N = 3 688.9 689.0 689.3
Nebular Empirical Analysis Tool OpenBenchmarking.org Seconds, Fewer Is Better Nebular Empirical Analysis Tool 2020-02-29 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 16.28 16.28 16.28 1. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.1931 0.3862 0.5793 0.7724 0.9655 SE +/- 0.00110, N = 3 SE +/- 0.00077, N = 3 SE +/- 0.00058, N = 3 0.85800 0.85790 0.85795
PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: NASNer Large - Device: CPU Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.2475 0.495 0.7425 0.99 1.2375 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.1 1.1 1.1
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 32 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 32 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 33.6 33.6 33.6
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 20 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 20 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 5 10 15 20 25 21 21 21
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 1 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.2363 0.4726 0.7089 0.9452 1.1815 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.05 1.05 1.05
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 20 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 20 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 4K 8K 12K 16K 20K 19999 19999 19999
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 32 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 32 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 700 1400 2100 2800 3500 3200 3200 3200
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 20 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 20 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400 800 1200 1600 2000 2000 2000 2000
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 1 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 1000Mbit Objective - Parallel: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 1000 1000 1000
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 1 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - 100Mbit Objective - Parallel: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 20 40 60 80 100 100 100 100
Schbench Message Threads: 4 - Workers Per Message Thread: 6 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 4 - Workers Per Message Thread: 6 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 10 20 30 40 50 SE +/- 0.33, N = 3 SE +/- 0.79, N = 15 43 41 41 1. (CC) gcc options: -O2 -lpthread
Schbench Message Threads: 4 - Workers Per Message Thread: 2 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 4 - Workers Per Message Thread: 2 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.79, N = 12 25 25 23 1. (CC) gcc options: -O2 -lpthread
Schbench Message Threads: 2 - Workers Per Message Thread: 4 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 2 - Workers Per Message Thread: 4 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 8 16 24 32 40 SE +/- 0.32, N = 15 SE +/- 1.85, N = 12 30 29 34 1. (CC) gcc options: -O2 -lpthread
Schbench Message Threads: 2 - Workers Per Message Thread: 2 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 2 - Workers Per Message Thread: 2 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 6 12 18 24 30 SE +/- 0.69, N = 12 SE +/- 2.00, N = 12 SE +/- 1.12, N = 15 25 27 26 1. (CC) gcc options: -O2 -lpthread
Apache Siege Concurrent Users: 250 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 250 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13K 26K 39K 52K 65K SE +/- 1678.24, N = 15 SE +/- 28.55, N = 3 SE +/- 53.05, N = 3 59490.65 19657.26 19731.42 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Apache Siege Concurrent Users: 1 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 1 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2K 4K 6K 8K 10K SE +/- 160.13, N = 15 SE +/- 93.15, N = 3 SE +/- 78.44, N = 15 7912.29 6789.89 6918.14 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Apache Cassandra Test: Reads OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Reads Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 200 400 600 800 1000 SE +/- 5.84, N = 3 SE +/- 26.90, N = 11 SE +/- 18.94, N = 9 572 1008 730
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 700K 1400K 2100K 2800K 3500K SE +/- 63869.43, N = 12 SE +/- 22183.62, N = 3 SE +/- 60257.48, N = 12 3354956.81 3436106.84 3322250.21 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 12 24 36 48 60 SE +/- 0.84, N = 15 SE +/- 0.87, N = 3 SE +/- 0.88, N = 15 51.95 53.87 52.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lcrypt -lrt -lz -ldl -lpthread -lc
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 300K 600K 900K 1200K 1500K SE +/- 36931.54, N = 15 SE +/- 19194.77, N = 14 SE +/- 30809.40, N = 15 1600412.63 1444961.84 1505075.70 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400K 800K 1200K 1600K 2000K SE +/- 50914.96, N = 15 SE +/- 15363.36, N = 3 SE +/- 15317.57, N = 3 1996950.61 1768092.33 1750558.62 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPUSH Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 300K 600K 900K 1200K 1500K SE +/- 25884.34, N = 12 SE +/- 7930.62, N = 3 SE +/- 16412.71, N = 4 1353713.40 1218625.21 1231050.56 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SADD Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 400K 800K 1200K 1600K 2000K SE +/- 51091.22, N = 15 SE +/- 24124.88, N = 14 SE +/- 3003.92, N = 3 1817867.40 1620429.83 1612914.46 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPOP Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 300K 600K 900K 1200K 1500K SE +/- 34105.93, N = 12 SE +/- 25786.36, N = 15 SE +/- 5247.17, N = 3 1420279.27 1332716.88 1278815.50 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Hackbench Count: 1 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Process Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.8451 1.6902 2.5353 3.3804 4.2255 SE +/- 0.050, N = 15 SE +/- 0.117, N = 15 SE +/- 0.045, N = 3 3.062 3.093 3.756 1. (CC) gcc options: -lpthread
Hackbench Count: 1 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Thread Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 0.9234 1.8468 2.7702 3.6936 4.617 SE +/- 0.078, N = 15 SE +/- 0.073, N = 15 SE +/- 0.033, N = 3 3.239 3.894 4.104 1. (CC) gcc options: -lpthread
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 80 160 240 320 400 SE +/- 12.22, N = 12 SE +/- 12.24, N = 12 SE +/- 12.02, N = 12 350.31 353.44 351.74 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Node.js Express HTTP Load Test OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 2K 4K 6K 8K 10K SE +/- 96.52, N = 15 SE +/- 102.14, N = 15 SE +/- 119.60, N = 15 8608 8380 7652 1. Nodejs
v10.19.0
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Savina Reactors.IO Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 3K 6K 9K 12K 15K SE +/- 173.05, N = 20 SE +/- 596.06, N = 15 SE +/- 190.98, N = 20 14187.88 15131.10 14681.45
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark Bayes Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 50 100 150 200 250 SE +/- 13.04, N = 25 SE +/- 13.03, N = 25 SE +/- 12.82, N = 25 228.29 224.90 224.17
Ethr Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 16 OpenBenchmarking.org Connections/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: TCP - Test: Connections/s - Threads: 16 Linux 5.8 Linux 5.9-rc4 Linux 5.9-rc4 + patch 13K 26K 39K 52K 65K SE +/- 7966.56, N = 12 SE +/- 6240.16, N = 15 SE +/- 7420.61, N = 12 61266 47475 59438
Phoronix Test Suite v10.8.4