Ryzen 3 3300X Linux 5.9 Kernel Test AMD Ryzen 3 3300X 4-Core testing with a MSI B350M GAMING PRO (MS-7A39) v1.0 (2.NR BIOS) and AMD FirePro V3800 512MB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009165-FI-RYZEN333083&sor&grs .
Ryzen 3 3300X Linux 5.9 Kernel Test Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution v5.8 v5.9 20200911 PLU 1000 PLU 0 PLU 1 PLU 2 AMD Ryzen 3 3300X 4-Core @ 3.80GHz (4 Cores / 8 Threads) MSI B350M GAMING PRO (MS-7A39) v1.0 (2.NR BIOS) AMD Starship/Matisse 8GB 256GB INTEL SSDPEKKW256G7 AMD FirePro V3800 512MB AMD Redwood HDMI Audio VA2431 Realtek RTL8111/8168/8411 Ubuntu 20.04 5.8.0-050800-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 3.3 Mesa 20.0.8 (LLVM 10.0.0) GCC 9.3.0 ext4 1920x1080 5.9.0-050900rc4daily20200911-generic (x86_64) 20200910 5.9.0-rc5-14sep-patch (x86_64) 20200914 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 Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701021 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 STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ryzen 3 3300X Linux 5.9 Kernel Test apache-siege: 100 apache-siege: 250 apache-siege: 200 apache-siege: 50 perf-bench: Memcpy 1MB redis: LPOP hackbench: 4 - Process hackbench: 4 - Thread hackbench: 2 - Thread hackbench: 1 - Thread hackbench: 2 - Process hackbench: 1 - Process hackbench: 8 - Process lczero: Eigen perf-bench: Sched Pipe lczero: BLAS apache-siege: 10 perf-bench: Futex Hash redis: GET apache: Static Web Page Serving pmbench: 4 - 100% Reads nginx: Static Web Page Serving redis: SADD redis: SET mlpack: scikit_linearridgeregression redis: LPUSH perf-bench: Syscall Basic mlpack: scikit_ica pmbench: 2 - 100% Reads pmbench: 1 - 100% Reads pmbench: 4 - 100% Writes mlpack: scikit_qda perf-bench: Epoll Wait pmbench: 2 - 100% Writes pmbench: 4 - 50% pmbench: 8 - 100% Reads mlpack: scikit_svm pmbench: 8 - 50% gromacs: Water Benchmark pmbench: 2 - 80% Reads 20% Writes pmbench: 1 - 100% Writes pmbench: 8 - 80% Reads 20% Writes pmbench: 2 - 50% compress-zstd: 3 pmbench: 4 - 80% Reads 20% Writes pmbench: 1 - 50% pmbench: 8 - 100% Writes pmbench: 1 - 80% Reads 20% Writes namd: ATPase Simulation - 327,506 Atoms perf-bench: Futex Lock-Pi tensorflow-lite: Mobilenet Quant tensorflow-lite: NASNet Mobile tensorflow-lite: Inception V4 tensorflow-lite: SqueezeNet tensorflow-lite: Inception ResNet V2 tensorflow-lite: Mobilenet Float compress-zstd: 19 perf-bench: Memset 1MB v5.8 v5.9 20200911 PLU 1000 PLU 0 PLU 1 PLU 2 55576.32 51025.12 51667.55 59761.09 14.639894 1727281.75 12.913 13.541 7.076 3.881 6.717 3.741 28.311 540 310099 607 52087.10 6909009 2597507.75 40677.80 0.0372 49731.51 2259314.8 2003558.12 3.03 1686391.79 20567530 53.56 0.0356 0.0362 0.0476 66.25 314106 0.0421 0.0769 0.0364 19.48 0.0832 0.557 0.0886 0.0415 0.0964 0.0720 3672.3 0.0930 0.0701 0.0666 0.0871 4.30658 2087 253893 261743 5278087 365455 4779203 246337 21.4 71.975730 20535.60 18859.93 19351.25 25276.27 14.870989 1727688.96 15.739 16.291 8.260 4.490 7.994 4.277 31.943 585 308723 586 51381.04 6819664 2589745.97 39057.92 0.0367 49009.48 2283390.67 2017980.08 3.02 1729279.45 20461613 53.23 0.0357 0.0357 0.0474 65.72 311872 0.0427 0.0757 0.0366 19.41 0.0835 0.559 0.0884 0.0414 0.0958 0.0714 3647.6 0.0933 0.0703 0.0669 0.0869 4.31479 2093 253497 261550 5277283 365419 4781233 246310 21.4 71.534860 55218.33 50800.33 51384.81 58916.51 14.206472 1716491.17 15.783 16.425 8.494 4.533 7.968 4.357 32.072 592 308960 600 53381.12 6643738 2627465.58 40399.46 0.0360 49929.25 2311856.75 2032930.33 3.05 1721275.54 20227854 53.60 0.0358 0.0357 0.0479 66.05 308469 0.0420 0.0762 0.0365 19.42 0.0831 0.553 0.0877 0.0416 0.0956 0.0718 3677.5 0.0930 0.0698 0.0668 0.0867 4.30735 2094 253167 261851 5278293 365490 4778383 246311 21.4 62.875238 20605.73 18965.58 19445.04 25132.30 10.232930 2616808.88 15.849 16.503 8.371 4.618 7.989 4.353 32.327 578 297848 613 53764.48 6654765 2653604.72 40331.94 0.0366 50408.12 2322249.92 2057945.33 3.05 1688431.17 20312035 54.29 0.0359 0.0357 0.0470 66.59 310003 0.0420 0.0762 0.0365 19.42 0.0832 0.554 0.0879 0.0414 0.0955 0.0720 3662.3 0.0927 0.0700 0.0666 0.0866 4.29760 2094 253848 261877 5277027 365407 4779490 246197 21.4 38.408277 55813.97 50648.94 51339.59 58731.91 11.439383 1712165.71 15.800 16.437 8.364 4.572 7.976 4.316 32.278 582 303736 583 52729.33 6630089 2698028.42 39952.92 0.0361 50455.93 2304963.42 2031390.00 3.07 1704564.25 20068513 54.51 0.0357 0.0355 0.0477 66.76 310153 0.0421 0.0758 0.0367 19.58 0.0825 0.553 0.0881 0.0418 0.0958 0.0719 3651.6 0.0933 0.0701 0.0669 0.0867 4.30369 2092 253369 262267 5278900 365567 4778727 246290 21.4 24.875640 55453.61 50710.41 51904.05 58985.69 9.595183 1724583.50 15.594 16.197 8.375 4.632 7.895 4.308 31.736 596 315039 611 53097.68 6623342 2664860.92 40056.77 0.0363 50015.86 2319589.5 2045029.75 3.10 1715991.04 20245884 53.55 0.0352 0.0358 0.0476 65.52 309684 0.0421 0.0762 0.0369 19.65 0.0833 0.555 0.0879 0.0416 0.0959 0.0719 3661.6 0.0926 0.0700 0.0670 0.0868 4.31505 2094 253580 261854 5282723 365694 4780107 246280 21.4 17.280933 OpenBenchmarking.org
Apache Siege Concurrent Users: 100 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 100 PLU 1 v5.8 PLU 2 PLU 1000 PLU 0 v5.9 20200911 12K 24K 36K 48K 60K SE +/- 20.76, N = 3 SE +/- 72.11, N = 3 SE +/- 143.88, N = 3 SE +/- 76.83, N = 3 SE +/- 241.21, N = 3 SE +/- 325.43, N = 3 55813.97 55576.32 55453.61 55218.33 20605.73 20535.60 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Apache Siege Concurrent Users: 250 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 250 v5.8 PLU 1000 PLU 2 PLU 1 PLU 0 v5.9 20200911 11K 22K 33K 44K 55K SE +/- 177.92, N = 3 SE +/- 166.25, N = 3 SE +/- 108.80, N = 3 SE +/- 127.44, N = 3 SE +/- 165.33, N = 12 SE +/- 119.08, N = 3 51025.12 50800.33 50710.41 50648.94 18965.58 18859.93 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Apache Siege Concurrent Users: 200 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 200 PLU 2 v5.8 PLU 1000 PLU 1 PLU 0 v5.9 20200911 11K 22K 33K 44K 55K SE +/- 155.41, N = 3 SE +/- 183.80, N = 3 SE +/- 212.52, N = 3 SE +/- 112.79, N = 3 SE +/- 70.48, N = 3 SE +/- 116.90, N = 3 51904.05 51667.55 51384.81 51339.59 19445.04 19351.25 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Apache Siege Concurrent Users: 50 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 50 v5.8 PLU 2 PLU 1000 PLU 1 v5.9 20200911 PLU 0 13K 26K 39K 52K 65K SE +/- 63.03, N = 3 SE +/- 83.54, N = 3 SE +/- 129.09, N = 3 SE +/- 121.82, N = 3 SE +/- 344.51, N = 4 SE +/- 340.55, N = 15 59761.09 58985.69 58916.51 58731.91 25276.27 25132.30 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
perf-bench Benchmark: Memcpy 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memcpy 1MB v5.9 20200911 v5.8 PLU 1000 PLU 1 PLU 0 PLU 2 4 8 12 16 20 SE +/- 0.111915, N = 15 SE +/- 0.133016, N = 3 SE +/- 0.043464, N = 3 SE +/- 0.307225, N = 15 SE +/- 0.123563, N = 3 SE +/- 0.123849, N = 15 14.870989 14.639894 14.206472 11.439383 10.232930 9.595183 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -lnuma
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPOP PLU 0 v5.9 20200911 v5.8 PLU 2 PLU 1000 PLU 1 600K 1200K 1800K 2400K 3000K SE +/- 154833.24, N = 12 SE +/- 22111.28, N = 3 SE +/- 12015.87, N = 3 SE +/- 19704.01, N = 3 SE +/- 14479.31, N = 3 SE +/- 26455.36, N = 3 2616808.88 1727688.96 1727281.75 1724583.50 1716491.17 1712165.71 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Hackbench Count: 4 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Process v5.8 PLU 2 v5.9 20200911 PLU 1000 PLU 1 PLU 0 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 12.91 15.59 15.74 15.78 15.80 15.85 1. (CC) gcc options: -lpthread
Hackbench Count: 4 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Thread v5.8 PLU 2 v5.9 20200911 PLU 1000 PLU 1 PLU 0 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 13.54 16.20 16.29 16.43 16.44 16.50 1. (CC) gcc options: -lpthread
Hackbench Count: 2 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Thread v5.8 v5.9 20200911 PLU 1 PLU 0 PLU 2 PLU 1000 2 4 6 8 10 SE +/- 0.017, N = 3 SE +/- 0.021, N = 3 SE +/- 0.016, N = 3 SE +/- 0.008, N = 3 SE +/- 0.088, N = 8 SE +/- 0.112, N = 4 7.076 8.260 8.364 8.371 8.375 8.494 1. (CC) gcc options: -lpthread
Hackbench Count: 1 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Thread v5.8 v5.9 20200911 PLU 1000 PLU 1 PLU 0 PLU 2 1.0422 2.0844 3.1266 4.1688 5.211 SE +/- 0.008, N = 3 SE +/- 0.037, N = 3 SE +/- 0.013, N = 3 SE +/- 0.027, N = 3 SE +/- 0.057, N = 3 SE +/- 0.080, N = 14 3.881 4.490 4.533 4.572 4.618 4.632 1. (CC) gcc options: -lpthread
Hackbench Count: 2 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Process v5.8 PLU 2 PLU 1000 PLU 1 PLU 0 v5.9 20200911 2 4 6 8 10 SE +/- 0.019, N = 3 SE +/- 0.007, N = 3 SE +/- 0.005, N = 3 SE +/- 0.014, N = 3 SE +/- 0.020, N = 3 SE +/- 0.015, N = 3 6.717 7.895 7.968 7.976 7.989 7.994 1. (CC) gcc options: -lpthread
Hackbench Count: 1 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Process v5.8 v5.9 20200911 PLU 2 PLU 1 PLU 0 PLU 1000 0.9803 1.9606 2.9409 3.9212 4.9015 SE +/- 0.018, N = 3 SE +/- 0.010, N = 3 SE +/- 0.014, N = 3 SE +/- 0.009, N = 3 SE +/- 0.026, N = 3 SE +/- 0.034, N = 3 3.741 4.277 4.308 4.316 4.353 4.357 1. (CC) gcc options: -lpthread
Hackbench Count: 8 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Process v5.8 PLU 2 v5.9 20200911 PLU 1000 PLU 1 PLU 0 8 16 24 32 40 SE +/- 0.70, N = 15 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.19, N = 3 SE +/- 0.07, N = 3 28.31 31.74 31.94 32.07 32.28 32.33 1. (CC) gcc options: -lpthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen PLU 2 PLU 1000 v5.9 20200911 PLU 1 PLU 0 v5.8 130 260 390 520 650 SE +/- 11.02, N = 9 SE +/- 9.49, N = 9 SE +/- 3.48, N = 3 SE +/- 10.39, N = 9 SE +/- 18.14, N = 6 SE +/- 5.81, N = 3 596 592 585 582 578 540 1. (CXX) g++ options: -flto -pthread
perf-bench Benchmark: Sched Pipe OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Sched Pipe PLU 2 v5.8 PLU 1000 v5.9 20200911 PLU 1 PLU 0 70K 140K 210K 280K 350K SE +/- 3769.88, N = 6 SE +/- 4341.87, N = 3 SE +/- 3148.67, N = 8 SE +/- 2989.50, N = 3 SE +/- 3681.08, N = 15 SE +/- 3886.58, N = 3 315039 310099 308960 308723 303736 297848 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -lnuma
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS PLU 0 PLU 2 v5.8 PLU 1000 v5.9 20200911 PLU 1 130 260 390 520 650 SE +/- 6.59, N = 9 SE +/- 12.11, N = 9 SE +/- 9.07, N = 3 SE +/- 6.88, N = 9 SE +/- 8.12, N = 4 SE +/- 7.21, N = 9 613 611 607 600 586 583 1. (CXX) g++ options: -flto -pthread
Apache Siege Concurrent Users: 10 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 10 PLU 0 PLU 1000 PLU 2 PLU 1 v5.8 v5.9 20200911 12K 24K 36K 48K 60K SE +/- 166.89, N = 3 SE +/- 94.82, N = 3 SE +/- 93.81, N = 3 SE +/- 373.31, N = 3 SE +/- 313.27, N = 3 SE +/- 536.62, N = 3 53764.48 53381.12 53097.68 52729.33 52087.10 51381.04 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
perf-bench Benchmark: Futex Hash OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Hash v5.8 v5.9 20200911 PLU 0 PLU 1000 PLU 1 PLU 2 1.5M 3M 4.5M 6M 7.5M SE +/- 870.57, N = 3 SE +/- 4819.80, N = 3 SE +/- 10075.41, N = 3 SE +/- 12119.02, N = 3 SE +/- 15464.71, N = 3 SE +/- 6855.16, N = 3 6909009 6819664 6654765 6643738 6630089 6623342 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -lnuma
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET PLU 1 PLU 2 PLU 0 PLU 1000 v5.8 v5.9 20200911 600K 1200K 1800K 2400K 3000K SE +/- 15824.27, N = 3 SE +/- 27467.89, N = 3 SE +/- 27095.85, N = 8 SE +/- 25399.97, N = 3 SE +/- 11686.12, N = 3 SE +/- 19974.18, N = 15 2698028.42 2664860.92 2653604.72 2627465.58 2597507.75 2589745.97 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving v5.8 PLU 1000 PLU 0 PLU 2 PLU 1 v5.9 20200911 9K 18K 27K 36K 45K SE +/- 40.16, N = 3 SE +/- 74.14, N = 3 SE +/- 46.21, N = 3 SE +/- 71.32, N = 3 SE +/- 19.00, N = 3 SE +/- 239.92, N = 3 40677.80 40399.46 40331.94 40056.77 39952.92 39057.92 1. (CC) gcc options: -shared -fPIC -O2 -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 PLU 1000 PLU 1 PLU 2 PLU 0 v5.9 20200911 v5.8 0.0084 0.0168 0.0252 0.0336 0.042 SE +/- 0.0004, N = 3 SE +/- 0.0005, N = 12 SE +/- 0.0003, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0005, N = 4 0.0360 0.0361 0.0363 0.0366 0.0367 0.0372 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving PLU 1 PLU 0 PLU 2 PLU 1000 v5.8 v5.9 20200911 11K 22K 33K 44K 55K SE +/- 229.83, N = 3 SE +/- 180.15, N = 3 SE +/- 123.92, N = 3 SE +/- 70.83, N = 3 SE +/- 142.20, N = 3 SE +/- 121.07, N = 3 50455.93 50408.12 50015.86 49929.25 49731.51 49009.48 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SADD PLU 0 PLU 2 PLU 1000 PLU 1 v5.9 20200911 v5.8 500K 1000K 1500K 2000K 2500K SE +/- 17609.76, N = 3 SE +/- 37481.24, N = 3 SE +/- 26454.23, N = 3 SE +/- 30671.05, N = 3 SE +/- 18060.80, N = 3 SE +/- 17723.96, N = 3 2322249.92 2319589.50 2311856.75 2304963.42 2283390.67 2259314.80 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET PLU 0 PLU 2 PLU 1000 PLU 1 v5.9 20200911 v5.8 400K 800K 1200K 1600K 2000K SE +/- 18515.67, N = 3 SE +/- 6405.07, N = 3 SE +/- 20446.81, N = 3 SE +/- 15741.55, N = 3 SE +/- 22366.98, N = 3 SE +/- 20729.23, N = 8 2057945.33 2045029.75 2032930.33 2031390.00 2017980.08 2003558.12 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Mlpack Benchmark Benchmark: scikit_linearridgeregression OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression v5.9 20200911 v5.8 PLU 1000 PLU 0 PLU 1 PLU 2 0.6975 1.395 2.0925 2.79 3.4875 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 3.02 3.03 3.05 3.05 3.07 3.10
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPUSH v5.9 20200911 PLU 1000 PLU 2 PLU 1 PLU 0 v5.8 400K 800K 1200K 1600K 2000K SE +/- 12207.65, N = 3 SE +/- 9500.08, N = 3 SE +/- 24855.23, N = 3 SE +/- 28768.71, N = 3 SE +/- 12715.27, N = 3 SE +/- 6567.70, N = 3 1729279.45 1721275.54 1715991.04 1704564.25 1688431.17 1686391.79 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
perf-bench Benchmark: Syscall Basic OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Syscall Basic v5.8 v5.9 20200911 PLU 0 PLU 2 PLU 1000 PLU 1 4M 8M 12M 16M 20M SE +/- 64647.21, N = 3 SE +/- 20860.95, N = 3 SE +/- 38198.32, N = 3 SE +/- 34443.55, N = 3 SE +/- 41716.73, N = 3 SE +/- 142718.16, N = 3 20567530 20461613 20312035 20245884 20227854 20068513 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -lnuma
Mlpack Benchmark Benchmark: scikit_ica OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_ica v5.9 20200911 PLU 2 v5.8 PLU 1000 PLU 0 PLU 1 12 24 36 48 60 SE +/- 0.71, N = 4 SE +/- 0.14, N = 3 SE +/- 0.49, N = 3 SE +/- 0.79, N = 3 SE +/- 0.16, N = 3 SE +/- 0.61, N = 3 53.23 53.55 53.56 53.60 54.29 54.51
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 PLU 2 v5.8 v5.9 20200911 PLU 1 PLU 1000 PLU 0 0.0081 0.0162 0.0243 0.0324 0.0405 SE +/- 0.0005, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0002, N = 3 0.0352 0.0356 0.0357 0.0357 0.0358 0.0359 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 PLU 1 v5.9 20200911 PLU 1000 PLU 0 PLU 2 v5.8 0.0081 0.0162 0.0243 0.0324 0.0405 SE +/- 0.0002, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0004, N = 3 0.0355 0.0357 0.0357 0.0357 0.0358 0.0362 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 PLU 0 v5.9 20200911 v5.8 PLU 2 PLU 1 PLU 1000 0.0108 0.0216 0.0324 0.0432 0.054 SE +/- 0.0002, N = 3 SE +/- 0.0005, N = 3 SE +/- 0.0004, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0001, N = 3 0.0470 0.0474 0.0476 0.0476 0.0477 0.0479 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Mlpack Benchmark Benchmark: scikit_qda OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_qda PLU 2 v5.9 20200911 PLU 1000 v5.8 PLU 0 PLU 1 15 30 45 60 75 SE +/- 0.50, N = 3 SE +/- 0.73, N = 3 SE +/- 0.55, N = 15 SE +/- 0.70, N = 3 SE +/- 0.91, N = 15 SE +/- 1.04, N = 3 65.52 65.72 66.05 66.25 66.59 66.76
perf-bench Benchmark: Epoll Wait OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Epoll Wait v5.8 v5.9 20200911 PLU 1 PLU 0 PLU 2 PLU 1000 70K 140K 210K 280K 350K SE +/- 626.16, N = 3 SE +/- 748.58, N = 3 SE +/- 346.44, N = 3 SE +/- 900.43, N = 3 SE +/- 502.49, N = 3 SE +/- 336.92, N = 3 314106 311872 310153 310003 309684 308469 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -lnuma
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 PLU 1000 PLU 0 v5.8 PLU 1 PLU 2 v5.9 20200911 0.0096 0.0192 0.0288 0.0384 0.048 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0006, N = 3 0.0420 0.0420 0.0421 0.0421 0.0421 0.0427 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
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% v5.9 20200911 PLU 1 PLU 1000 PLU 0 PLU 2 v5.8 0.0173 0.0346 0.0519 0.0692 0.0865 SE +/- 0.0008, N = 8 SE +/- 0.0004, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0002, N = 3 0.0757 0.0758 0.0762 0.0762 0.0762 0.0769 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 v5.8 PLU 1000 PLU 0 v5.9 20200911 PLU 1 PLU 2 0.0083 0.0166 0.0249 0.0332 0.0415 SE +/- 0.0003, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0003, N = 3 0.0364 0.0365 0.0365 0.0366 0.0367 0.0369 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Mlpack Benchmark Benchmark: scikit_svm OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_svm v5.9 20200911 PLU 1000 PLU 0 v5.8 PLU 1 PLU 2 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 19.41 19.42 19.42 19.48 19.58 19.65
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% PLU 1 PLU 1000 v5.8 PLU 0 PLU 2 v5.9 20200911 0.0188 0.0376 0.0564 0.0752 0.094 SE +/- 0.0003, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0007, N = 3 0.0825 0.0831 0.0832 0.0832 0.0833 0.0835 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.1 Water Benchmark v5.9 20200911 v5.8 PLU 2 PLU 0 PLU 1 PLU 1000 0.1258 0.2516 0.3774 0.5032 0.629 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.002, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.559 0.557 0.555 0.554 0.553 0.553 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 80% Reads 20% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 2 - Read-Write Ratio: 80% Reads 20% Writes PLU 1000 PLU 0 PLU 2 PLU 1 v5.9 20200911 v5.8 0.0199 0.0398 0.0597 0.0796 0.0995 SE +/- 0.0000, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0004, N = 3 0.0877 0.0879 0.0879 0.0881 0.0884 0.0886 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 v5.9 20200911 PLU 0 v5.8 PLU 1000 PLU 2 PLU 1 0.0094 0.0188 0.0282 0.0376 0.047 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0003, N = 3 0.0414 0.0414 0.0415 0.0416 0.0416 0.0418 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 80% Reads 20% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 8 - Read-Write Ratio: 80% Reads 20% Writes PLU 0 PLU 1000 v5.9 20200911 PLU 1 PLU 2 v5.8 0.0217 0.0434 0.0651 0.0868 0.1085 SE +/- 0.0002, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 0.0955 0.0956 0.0958 0.0958 0.0959 0.0964 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
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% v5.9 20200911 PLU 1000 PLU 1 PLU 2 v5.8 PLU 0 0.0162 0.0324 0.0486 0.0648 0.081 SE +/- 0.0005, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 0.0714 0.0718 0.0719 0.0719 0.0720 0.0720 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 PLU 1000 v5.8 PLU 0 PLU 2 PLU 1 v5.9 20200911 800 1600 2400 3200 4000 SE +/- 4.11, N = 3 SE +/- 12.59, N = 3 SE +/- 10.43, N = 3 SE +/- 9.67, N = 3 SE +/- 7.05, N = 3 SE +/- 21.59, N = 3 3677.5 3672.3 3662.3 3661.6 3651.6 3647.6 1. (CC) gcc options: -O3 -pthread -lz
pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 80% Reads 20% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 4 - Read-Write Ratio: 80% Reads 20% Writes PLU 2 PLU 0 v5.8 PLU 1000 v5.9 20200911 PLU 1 0.021 0.042 0.063 0.084 0.105 SE +/- 0.0001, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0004, N = 3 SE +/- 0.0010, N = 3 SE +/- 0.0004, N = 3 0.0926 0.0927 0.0930 0.0930 0.0933 0.0933 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% PLU 1000 PLU 0 PLU 2 v5.8 PLU 1 v5.9 20200911 0.0158 0.0316 0.0474 0.0632 0.079 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 0.0698 0.0700 0.0700 0.0701 0.0701 0.0703 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 v5.8 PLU 0 PLU 1000 v5.9 20200911 PLU 1 PLU 2 0.0151 0.0302 0.0453 0.0604 0.0755 SE +/- 0.0006, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0001, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0000, N = 3 0.0666 0.0666 0.0668 0.0669 0.0669 0.0670 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 80% Reads 20% Writes OpenBenchmarking.org us - Average Page Latency, Fewer Is Better pmbench Concurrent Worker Threads: 1 - Read-Write Ratio: 80% Reads 20% Writes PLU 0 PLU 1000 PLU 1 PLU 2 v5.9 20200911 v5.8 0.0196 0.0392 0.0588 0.0784 0.098 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0001, N = 3 0.0866 0.0867 0.0867 0.0868 0.0869 0.0871 1. (CC) gcc options: -lm -luuid -lxml2 -m64 -pthread
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms PLU 0 PLU 1 v5.8 PLU 1000 v5.9 20200911 PLU 2 0.9709 1.9418 2.9127 3.8836 4.8545 SE +/- 0.00115, N = 3 SE +/- 0.00165, N = 3 SE +/- 0.00129, N = 3 SE +/- 0.00234, N = 3 SE +/- 0.00080, N = 3 SE +/- 0.00196, N = 3 4.29760 4.30369 4.30658 4.30735 4.31479 4.31505
perf-bench Benchmark: Futex Lock-Pi OpenBenchmarking.org ops/sec, More Is Better perf-bench Benchmark: Futex Lock-Pi PLU 2 PLU 0 PLU 1000 v5.9 20200911 PLU 1 v5.8 400 800 1200 1600 2000 SE +/- 1.00, N = 3 SE +/- 1.15, N = 3 SE +/- 0.33, N = 3 SE +/- 1.20, N = 3 SE +/- 1.20, N = 3 2094 2094 2094 2093 2092 2087 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -lnuma
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant PLU 1000 PLU 1 v5.9 20200911 PLU 2 PLU 0 v5.8 50K 100K 150K 200K 250K SE +/- 140.75, N = 3 SE +/- 56.15, N = 3 SE +/- 18.02, N = 3 SE +/- 243.95, N = 3 SE +/- 367.38, N = 3 SE +/- 182.72, N = 3 253167 253369 253497 253580 253848 253893
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile v5.9 20200911 v5.8 PLU 1000 PLU 2 PLU 0 PLU 1 60K 120K 180K 240K 300K SE +/- 142.26, N = 3 SE +/- 35.04, N = 3 SE +/- 92.25, N = 3 SE +/- 96.27, N = 3 SE +/- 98.73, N = 3 SE +/- 288.01, N = 3 261550 261743 261851 261854 261877 262267
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 PLU 0 v5.9 20200911 v5.8 PLU 1000 PLU 1 PLU 2 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 693.43, N = 3 SE +/- 176.10, N = 3 SE +/- 309.32, N = 3 SE +/- 588.34, N = 3 SE +/- 897.46, N = 3 SE +/- 2206.21, N = 3 5277027 5277283 5278087 5278293 5278900 5282723
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet PLU 0 v5.9 20200911 v5.8 PLU 1000 PLU 1 PLU 2 80K 160K 240K 320K 400K SE +/- 156.35, N = 3 SE +/- 90.15, N = 3 SE +/- 128.88, N = 3 SE +/- 74.81, N = 3 SE +/- 41.49, N = 3 SE +/- 164.29, N = 3 365407 365419 365455 365490 365567 365694
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 PLU 1000 PLU 1 v5.8 PLU 0 PLU 2 v5.9 20200911 1000K 2000K 3000K 4000K 5000K SE +/- 431.75, N = 3 SE +/- 564.10, N = 3 SE +/- 263.59, N = 3 SE +/- 621.64, N = 3 SE +/- 949.92, N = 3 SE +/- 1644.56, N = 3 4778383 4778727 4779203 4779490 4780107 4781233
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float PLU 0 PLU 2 PLU 1 v5.9 20200911 PLU 1000 v5.8 50K 100K 150K 200K 250K SE +/- 24.48, N = 3 SE +/- 20.78, N = 3 SE +/- 54.31, N = 3 SE +/- 23.64, N = 3 SE +/- 29.02, N = 3 SE +/- 26.12, N = 3 246197 246280 246290 246310 246311 246337
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 PLU 2 PLU 1 PLU 0 PLU 1000 v5.9 20200911 v5.8 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 21.4 21.4 21.4 21.4 21.4 21.4 1. (CC) gcc options: -O3 -pthread -lz
perf-bench Benchmark: Memset 1MB OpenBenchmarking.org GB/sec, More Is Better perf-bench Benchmark: Memset 1MB v5.8 v5.9 20200911 PLU 1000 PLU 0 PLU 1 PLU 2 16 32 48 64 80 SE +/- 0.64, N = 15 SE +/- 0.39, N = 3 SE +/- 6.58, N = 12 SE +/- 5.48, N = 15 SE +/- 1.24, N = 12 SE +/- 0.36, N = 15 71.98 71.53 62.88 38.41 24.88 17.28 1. (CC) gcc options: -O6 -ggdb3 -funwind-tables -std=gnu99 -Xlinker -lpthread -lrt -lm -ldl -lelf -lcrypto -lz -lnuma
Phoronix Test Suite v10.8.5