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