2 x Intel Xeon Platinum 8280 mitigation benchmarks for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1911170-HU-DEFAULTMI73 Cascade Lake TSX + Mitigations + New ucode - Phoronix Test Suite Cascade Lake TSX + Mitigations + New ucode 2 x Intel Xeon Platinum 8280 mitigation benchmarks for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1911170-HU-DEFAULTMI73&grr&rdt .
Cascade Lake TSX + Mitigations + New ucode Processor Motherboard Chipset Memory Disk Graphics Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads) GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS) Intel Sky Lake-E DMI3 Registers 386048MB 280GB INTEL SSDPED1D280GA llvmpipe 377GB VE228 2 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE Ubuntu 19.10 5.4.0-rc7-12nov-vulns (x86_64) 20191112 GNOME Shell 3.34.1 X Server 1.20.5 modesetting 1.20.5 3.3 Mesa 19.2.1 (LLVM 9.0 256 bits) GCC 9.2.1 20191008 ext4 1920x1080 2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores) OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --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 - Default Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c - No Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c - No Mitigations + Old ucode: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5000021 - Default Mitigations + TSX: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c - Default Mitigations + No HT: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c - Default Mitigations + No HT + TSX: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c Java Details - OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1) Python Details - Python 2.7.17rc1 + Python 3.7.5rc1 Security Details - Default Mitigations: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled - No Mitigations: itlb_multihit: KVM: Vulnerable + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + tsx_async_abort: Mitigation of TSX disabled - No Mitigations + Old ucode: itlb_multihit: KVM: Vulnerable + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled + tsx_async_abort: Vulnerable - Default Mitigations + TSX: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable - Default Mitigations + No HT: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of TSX disabled - Default Mitigations + No HT + TSX: itlb_multihit: KVM: Mitigation of Split huge pages + 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 Enhanced IBRS IBPB: conditional RSB filling + tsx_async_abort: Mitigation of Clear buffers; SMT disabled
Cascade Lake TSX + Mitigations + New ucode build-gcc: Time To Compile rocksdb: Seq Fill mysqlslap: 256 memtier-benchmark: Redis renaissance: Savina Reactors.IO dacapobench: Tradebeans blender: Barbershop - CPU-Only dacapobench: Tradesoap dav1d: Chimera 1080p 10-bit pgbench: Buffer Test - Normal Load - Read Only hackbench: 32 - Process mrbayes: Primate Phylogeny Analysis ospray: XFrog Forest - Path Tracer graphics-magick: Rotate renaissance: Apache Spark Bayes namd: ATPase Simulation - 327,506 Atoms build-linux-kernel: Time To Compile rocksdb: Read While Writing blender: Classroom - CPU-Only ospray: XFrog Forest - SciVis graphics-magick: HWB Color Space renaissance: In-Memory Database Shootout nginx: Static Web Page Serving fio: Rand Read - Linux AIO - Yes - No - 4KB - Default Test Directory fio: Rand Read - Linux AIO - Yes - No - 4KB - Default Test Directory fio: Seq Read - Linux AIO - Yes - No - 4KB - Default Test Directory fio: Seq Read - Linux AIO - Yes - No - 4KB - Default Test Directory sqlite-speedtest: Timed Time - Size 1,000 hackbench: 16 - Process rocksdb: Rand Fill Sync rocksdb: Rand Fill graphics-magick: Sharpen graphics-magick: Noise-Gaussian graphics-magick: Enhanced graphics-magick: Swirl hackbench: 16 - Thread fio: Seq Read - Linux AIO - Yes - No - 2MB - Default Test Directory sqlite: 64 sockperf: Latency Under Load fs-mark: 5000 Files, 1MB Size, 4 Threads apache: Static Web Page Serving hackbench: 8 - Thread gromacs: Water Benchmark build-llvm: Time To Compile sockperf: Throughput java-scimark2: Composite coremark: CoreMark Size 666 - Iterations Per Second fio: Rand Write - Linux AIO - Yes - No - 4KB - Default Test Directory fio: Rand Write - Linux AIO - Yes - No - 4KB - Default Test Directory fio: Rand Write - Linux AIO - Yes - No - 2MB - Default Test Directory mcperf: Get glibc-bench: ffs fio: Seq Write - Linux AIO - Yes - No - 4KB - Default Test Directory fio: Seq Write - Linux AIO - Yes - No - 4KB - Default Test Directory embree: Pathtracer - Asian Dragon Obj glibc-bench: exp gimp: unsharp-mask embree: Pathtracer ISPC - Asian Dragon Obj t-test1: 1 npb: EP.D gimp: auto-levels selenium: PSPDFKit WASM - Firefox pybench: Total For Average Test Times sockperf: Latency Ping Pong glibc-bench: ffsll gimp: rotate compilebench: Compile mcperf: Set hackbench: 8 - Process selenium: Maze Solver - Firefox glibc-bench: pthread_once dacapobench: H2 ospray: Magnetic Reconnection - SciVis dav1d: Summer Nature 4K embree: Pathtracer - Crown phpbench: PHP Benchmark Suite fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size embree: Pathtracer ISPC - Crown gimp: resize t-test1: 2 npb: FT.C n-queens: Elapsed Time dacapobench: Jython tjbench: Decompression Throughput osbench: Create Files osbench: Memory Allocations osbench: Create Processes osbench: Create Threads fs-mark: 1000 Files, 1MB Size npb: EP.C ctx-clock: Context Switch Time ior: Read Test ior: Write Test fs-mark: 1000 Files, 1MB Size, No Sync/FSync compilebench: Read Compiled Tree compilebench: Initial Create Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 903.317 190549 441 4047462.82 27064.810 11886 185.77 7272 66.12 909277.747396 49.760 140.328 6.67 602 3364.959 0.36134 24.959 6335435 98.36 12.05 751 17153.869 31592.00 78900 308 444200 1736 66.097 27.101 165265 190828 541 461 801 1446 28.897 1880 19.807 38.440 1243.6 24718.20 9.372 5.786 113.895 426235 2020.37 1687345.843844 208000 813 897 107000.5 1.67080 216000 845 51.6747 5.60802 29.698 57.9361 18.803 6364.25 23.578 1787 1093 3.956 1.67230 18.430 1685.69 62923.7 7.340 6.6 1.68213 8940 71.43 206.13 45.2129 645204 665.4 53.1467 12.535 8.804 47783.61 3.375 4781 176.591879 14.046368 89.348555 46.190421 20.526250 725.1 6110.45 135 1849.54 1297.33 1804.7 2753.54 579.22 900.539 197249 441 4455789.73 26263.558 12283 185.50 7876 65.84 914647.716544 46.696 140.487 6.67 600 3382.145 0.36167 24.869 6345586 98.13 12.05 730 16974.925 34173.55 77473 303 460000 1797 65.019 26.164 169005 197271 543 481 800 1458 29.447 1914 17.214 39.938 1287.0 25808.38 10.907 5.759 113.985 440031 2023.44 1668803.224037 210667 822 922 116181.7 1.65556 216000 843 51.5274 5.58804 27.745 58.7775 19.241 6555.18 23.276 1678 1091 3.692 1.65581 18.310 1783.97 66321.9 7.297 6.5 1.66339 9093 71.43 203.89 45.5616 646447 776.6 53.1453 12.418 8.984 47770.69 3.339 4770 176.892850 13.719780 89.657625 45.783520 20.319621 740.1 5967.87 134 1975.11 1274.11 1828.7 2828.44 593.91 887.099 199393 446 3942410.03 26188.263 12150 182.00 7665 68.73 901390.609121 50.079 127.166 6.76 606 3286.454 0.36049 24.185 6412323 95.27 12.20 755 16902.210 32865.75 80680 315 454800 1776 63.878 26.742 175248 199879 544 474 809 1454 28.538 1924 17.556 37.693 1252.0 26306.18 10.582 5.783 112.269 448360 2152.56 1870205.527200 210000 820 907 116305.7 1.66029 216000 845 51.9557 5.08538 26.698 58.8285 18.868 6424.36 22.509 1611 1032 3.700 1.66125 17.746 1791.87 65755.6 7.640 6.5 1.67045 8736 71.43 205.38 45.4925 673402 813.4 53.4040 12.061 8.617 46890.67 3.158 4559 181.818865 13.270633 85.631370 44.786135 20.410220 795.9 6099.23 135 1984.95 1412.73 1848.5 2928.31 600.51 941.097 172758 434 3743629.93 28018.320 11956 185.63 7363 66.05 888296.743186 52.741 140.846 6.67 584 3531.929 0.36144 25.535 6221981 98.27 12.05 726 17134.645 29726.12 73767 289 406333 1588 71.598 30.361 158260 172229 540 457 803 1431 32.551 1824 18.709 36.738 1250.2 23639.63 8.591 5.768 117.018 403297 2025.82 1703749.932379 196333 766 876 102237.0 1.80224 202333 790 51.7106 5.72369 30.105 58.7731 19.980 6462.18 24.493 1782 1093 4.184 1.80203 18.938 1761.26 61202.8 6.971 6.7 1.80817 8790 71.43 205.03 45.6398 643614 772.3 53.2048 12.768 9.163 46840.52 3.364 4783 176.233830 14.722453 91.519991 47.218005 21.256606 780.1 6160.50 455 1929.81 1221.78 1722.8 2543.26 553.70 904.607 191878 441 3913100.61 26595.648 11932 185.31 7409 66.08 909226.950543 47.041 140.543 6.67 587 3361.071 0.36480 24.971 6341103 98.24 12.05 769 16939.151 31860.39 75800 296 452667 1769 66.054 27.214 163705 191201 541 467 798 1456 28.965 1930 18.746 36.388 1267.3 25051.76 9.978 5.753 116.031 420154 2018.53 1680764.402269 207333 810 910 107775.5 1.66963 216667 845 51.7701 5.64088 29.600 58.6374 19.225 6646.46 24.317 1772 1093 3.831 1.66994 18.419 1779.60 62276.2 7.480 6.6 1.67938 8912 71.43 204.81 45.7155 644906 613.3 52.6317 12.346 8.585 36833.86 3.310 4843 176.943615 14.028326 90.132555 45.714378 20.667712 730.4 6077.89 135 1979.48 1398.11 1796.3 2754.83 581.72 971.014 174853 440 2519515.57 28941.314 13668 213.07 7179 50.83 694383.862015 47.699 140.180 4.66 574 3353.068 0.42164 28.316 5046027 123.90 8.55 722 17702.101 30724.03 72933 285 399667 1560 71.672 25.214 136358 174872 525 445 790 1263 29.557 1910 20.121 41.813 1204.5 24145.48 14.740 5.794 124.515 406044 2026.30 1250999.816485 196667 768 916 102549.9 1.79641 199333 778 35.0889 5.72415 30.461 38.6987 64.707 6474.74 25.791 1772 1089 4.185 1.79714 19.186 1753.54 60861.1 14.112 6.6 1.80347 7989 55.56 167.53 34.5033 643732 604.9 35.7095 12.513 21.460 47329.24 4.823 4831 176.381758 14.716700 92.037360 40.589968 19.660791 574.6 6558.81 481 1850.50 1142.03 1725.3 2514.16 553.25 OpenBenchmarking.org
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 8.2 Time To Compile Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 0.61, N = 3 SE +/- 0.98, N = 3 SE +/- 1.99, N = 3 SE +/- 0.69, N = 3 SE +/- 1.44, N = 3 SE +/- 0.41, N = 3 903.32 900.54 887.10 941.10 904.61 971.01
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 40K 80K 120K 160K 200K SE +/- 302.73, N = 3 SE +/- 294.32, N = 3 SE +/- 182.30, N = 3 SE +/- 84.11, N = 3 SE +/- 207.93, N = 3 SE +/- 486.11, N = 3 190549 197249 199393 172758 191878 174853 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
MariaDB Clients: 256 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.3.8 Clients: 256 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 100 200 300 400 500 SE +/- 0.66, N = 3 SE +/- 0.75, N = 3 SE +/- 0.34, N = 3 SE +/- 1.41, N = 3 SE +/- 0.76, N = 3 SE +/- 0.42, N = 3 441 441 446 434 441 440 1. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
Memtier_benchmark Protocol: Redis OpenBenchmarking.org Ops/sec, More Is Better Memtier_benchmark 1.2.17 Protocol: Redis Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1000K 2000K 3000K 4000K 5000K SE +/- 170934.41, N = 12 SE +/- 2516.82, N = 3 SE +/- 182130.65, N = 12 SE +/- 202059.99, N = 12 SE +/- 172554.23, N = 12 SE +/- 11397.28, N = 3 4047462.82 4455789.73 3942410.03 3743629.93 3913100.61 2519515.57 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Savina Reactors.IO Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 6K 12K 18K 24K 30K SE +/- 403.62, N = 40 SE +/- 370.01, N = 40 SE +/- 368.24, N = 40 SE +/- 446.70, N = 40 SE +/- 317.64, N = 40 SE +/- 470.43, N = 40 27064.81 26263.56 26188.26 28018.32 26595.65 28941.31
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 3K 6K 9K 12K 15K SE +/- 62.94, N = 4 SE +/- 214.58, N = 16 SE +/- 134.88, N = 20 SE +/- 120.94, N = 8 SE +/- 142.95, N = 6 SE +/- 95.67, N = 18 11886 12283 12150 11956 11932 13668
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Barbershop - Compute: CPU-Only Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 50 100 150 200 250 SE +/- 0.25, N = 3 SE +/- 0.28, N = 3 SE +/- 0.07, N = 3 SE +/- 0.16, N = 3 SE +/- 0.32, N = 3 SE +/- 0.02, N = 3 185.77 185.50 182.00 185.63 185.31 213.07
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 2K 4K 6K 8K 10K SE +/- 58.97, N = 20 SE +/- 54.13, N = 4 SE +/- 106.71, N = 4 SE +/- 86.60, N = 20 SE +/- 89.29, N = 16 SE +/- 85.56, N = 5 7272 7876 7665 7363 7409 7179
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p 10-bit Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 15 30 45 60 75 SE +/- 0.11, N = 3 SE +/- 0.40, N = 3 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 66.12 65.84 68.73 66.05 66.08 50.83 MIN: 49.13 / MAX: 104.59 MIN: 49.05 / MAX: 104.44 MIN: 51.32 / MAX: 108.82 MIN: 49.01 / MAX: 104.31 MIN: 49.14 / MAX: 104.39 MIN: 36.44 / MAX: 88.58 1. (CC) gcc options: -pthread
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 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200K 400K 600K 800K 1000K SE +/- 7811.39, N = 3 SE +/- 453.84, N = 3 SE +/- 14964.49, N = 3 SE +/- 2791.38, N = 3 SE +/- 2807.93, N = 3 SE +/- 1046.95, N = 3 909277.75 914647.72 901390.61 888296.74 909226.95 694383.86 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Hackbench Count: 32 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 12 24 36 48 60 SE +/- 0.89, N = 15 SE +/- 0.67, N = 12 SE +/- 0.54, N = 3 SE +/- 1.14, N = 15 SE +/- 1.14, N = 15 SE +/- 0.25, N = 3 49.76 46.70 50.08 52.74 47.04 47.70 1. (CC) gcc options: -lpthread
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 30 60 90 120 150 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 SE +/- 0.31, N = 3 SE +/- 0.25, N = 3 SE +/- 0.30, N = 3 SE +/- 0.40, N = 3 140.33 140.49 127.17 140.85 140.54 140.18 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mrdrnd -mbmi -mbmi2 -madx -mmpx -mabm -O3 -std=c99 -pedantic -lm
OSPray Demo: XFrog Forest - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 2 4 6 8 10 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.01, N = 3 6.67 6.67 6.76 6.67 6.67 4.66 MIN: 5.85 / MAX: 6.76 MIN: 5.85 / MAX: 6.71 MIN: 5.88 / MAX: 6.8 MIN: 5.71 / MAX: 6.76 MIN: 5.88 / MAX: 6.76 MIN: 4.15 / MAX: 4.69
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 130 260 390 520 650 SE +/- 5.92, N = 9 SE +/- 5.35, N = 15 SE +/- 3.51, N = 3 SE +/- 8.97, N = 3 SE +/- 5.84, N = 3 SE +/- 9.54, N = 3 602 600 606 584 587 574 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Apache Spark Bayes Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 800 1600 2400 3200 4000 SE +/- 41.85, N = 40 SE +/- 54.20, N = 32 SE +/- 34.64, N = 32 SE +/- 60.43, N = 40 SE +/- 42.51, N = 40 SE +/- 25.05, N = 40 3364.96 3382.15 3286.45 3531.93 3361.07 3353.07
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13b1 ATPase Simulation - 327,506 Atoms Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 0.0949 0.1898 0.2847 0.3796 0.4745 SE +/- 0.00025, N = 15 SE +/- 0.00020, N = 15 SE +/- 0.00022, N = 15 SE +/- 0.00025, N = 12 SE +/- 0.00278, N = 10 SE +/- 0.00021, N = 14 0.36134 0.36167 0.36049 0.36144 0.36480 0.42164
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 7 14 21 28 35 SE +/- 0.28, N = 13 SE +/- 0.25, N = 14 SE +/- 0.26, N = 13 SE +/- 0.27, N = 13 SE +/- 0.26, N = 13 SE +/- 0.29, N = 13 24.96 24.87 24.19 25.54 24.97 28.32
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1.4M 2.8M 4.2M 5.6M 7M SE +/- 70382.26, N = 3 SE +/- 33377.10, N = 3 SE +/- 75864.17, N = 5 SE +/- 53165.01, N = 15 SE +/- 57902.26, N = 3 SE +/- 77587.94, N = 3 6335435 6345586 6412323 6221981 6341103 5046027 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Classroom - Compute: CPU-Only Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 30 60 90 120 150 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.23, N = 3 98.36 98.13 95.27 98.27 98.24 123.90
OSPray Demo: XFrog Forest - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 3 6 9 12 15 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 12.05 12.05 12.20 12.05 12.05 8.55 MIN: 10.31 / MAX: 12.2 MIN: 8.93 / MAX: 12.2 MIN: 10.1 / MAX: 12.35 MIN: 9.62 / MAX: 12.2 MIN: 10 / MAX: 12.2 MIN: 7.19 / MAX: 8.62
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 170 340 510 680 850 SE +/- 10.37, N = 4 SE +/- 5.69, N = 3 SE +/- 8.11, N = 3 SE +/- 2.00, N = 3 SE +/- 2.67, N = 3 SE +/- 7.65, N = 8 751 730 755 726 769 722 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: In-Memory Database Shootout Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 4K 8K 12K 16K 20K SE +/- 119.20, N = 8 SE +/- 152.42, N = 8 SE +/- 170.14, N = 8 SE +/- 149.97, N = 11 SE +/- 162.96, N = 9 SE +/- 176.64, N = 9 17153.87 16974.93 16902.21 17134.65 16939.15 17702.10
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 7K 14K 21K 28K 35K SE +/- 428.12, N = 4 SE +/- 273.17, N = 3 SE +/- 95.09, N = 3 SE +/- 360.88, N = 5 SE +/- 323.50, N = 3 SE +/- 74.44, N = 3 31592.00 34173.55 32865.75 29726.12 31860.39 30724.03 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
Flexible IO Tester Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 20K 40K 60K 80K 100K SE +/- 1017.35, N = 4 SE +/- 908.71, N = 15 SE +/- 916.06, N = 15 SE +/- 895.05, N = 3 SE +/- 1266.23, N = 3 SE +/- 895.05, N = 3 78900 77473 80680 73767 75800 72933 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 70 140 210 280 350 SE +/- 3.97, N = 4 SE +/- 3.55, N = 15 SE +/- 3.72, N = 15 SE +/- 2.08, N = 3 SE +/- 4.91, N = 3 SE +/- 3.46, N = 3 308 303 315 289 296 285 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 100K 200K 300K 400K 500K SE +/- 4852.29, N = 15 SE +/- 1527.53, N = 3 SE +/- 4251.83, N = 15 SE +/- 2185.81, N = 3 SE +/- 3382.96, N = 3 SE +/- 333.33, N = 3 444200 460000 454800 406333 452667 399667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 400 800 1200 1600 2000 SE +/- 18.99, N = 15 SE +/- 5.78, N = 3 SE +/- 16.57, N = 15 SE +/- 8.08, N = 3 SE +/- 13.32, N = 3 SE +/- 1.00, N = 3 1736 1797 1776 1588 1769 1560 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 16 32 48 64 80 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 66.10 65.02 63.88 71.60 66.05 71.67 1. (CC) gcc options: -O2 -ldl -lz -lpthread
Hackbench Count: 16 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 7 14 21 28 35 SE +/- 0.42, N = 3 SE +/- 0.22, N = 13 SE +/- 0.28, N = 3 SE +/- 0.35, N = 15 SE +/- 0.20, N = 3 SE +/- 0.05, N = 3 27.10 26.16 26.74 30.36 27.21 25.21 1. (CC) gcc options: -lpthread
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 40K 80K 120K 160K 200K SE +/- 242.56, N = 3 SE +/- 24.04, N = 3 SE +/- 344.06, N = 3 SE +/- 284.36, N = 3 SE +/- 138.90, N = 3 SE +/- 313.12, N = 3 165265 169005 175248 158260 163705 136358 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 40K 80K 120K 160K 200K SE +/- 258.57, N = 3 SE +/- 96.46, N = 3 SE +/- 561.22, N = 3 SE +/- 265.64, N = 3 SE +/- 516.59, N = 3 SE +/- 372.72, N = 3 190828 197271 199879 172229 191201 174872 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 120 240 360 480 600 SE +/- 1.76, N = 3 SE +/- 2.08, N = 3 SE +/- 1.00, N = 3 SE +/- 3.71, N = 3 541 543 544 540 541 525 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 100 200 300 400 500 SE +/- 7.36, N = 3 SE +/- 6.51, N = 3 SE +/- 7.31, N = 3 SE +/- 2.85, N = 3 SE +/- 4.33, N = 3 461 481 474 457 467 445 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 3.48, N = 3 SE +/- 5.70, N = 3 SE +/- 9.00, N = 3 SE +/- 3.48, N = 3 SE +/- 6.33, N = 3 SE +/- 8.84, N = 3 801 800 809 803 798 790 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 300 600 900 1200 1500 SE +/- 10.97, N = 3 SE +/- 11.02, N = 3 SE +/- 8.39, N = 3 SE +/- 7.69, N = 3 SE +/- 9.67, N = 3 SE +/- 13.20, N = 3 1446 1458 1454 1431 1456 1263 1. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread
Hackbench Count: 16 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 8 16 24 32 40 SE +/- 0.35, N = 3 SE +/- 0.30, N = 3 SE +/- 0.16, N = 3 SE +/- 0.41, N = 3 SE +/- 0.28, N = 9 SE +/- 0.26, N = 15 28.90 29.45 28.54 32.55 28.97 29.56 1. (CC) gcc options: -lpthread
Flexible IO Tester Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 400 800 1200 1600 2000 SE +/- 15.95, N = 15 SE +/- 13.91, N = 3 SE +/- 8.33, N = 3 SE +/- 20.39, N = 6 SE +/- 13.45, N = 3 SE +/- 7.88, N = 3 1880 1914 1924 1824 1930 1910 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
SQLite Threads / Copies: 64 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 64 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 5 10 15 20 25 SE +/- 0.26, N = 15 SE +/- 0.21, N = 6 SE +/- 0.20, N = 3 SE +/- 0.18, N = 3 SE +/- 0.21, N = 7 SE +/- 0.37, N = 15 19.81 17.21 17.56 18.71 18.75 20.12 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
Sockperf Test: Latency Under Load OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Under Load Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 10 20 30 40 50 SE +/- 0.57, N = 25 SE +/- 0.20, N = 5 SE +/- 0.57, N = 25 SE +/- 1.49, N = 20 SE +/- 1.56, N = 20 SE +/- 0.09, N = 5 38.44 39.94 37.69 36.74 36.39 41.81 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -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 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 300 600 900 1200 1500 SE +/- 15.37, N = 3 SE +/- 13.49, N = 15 SE +/- 16.57, N = 5 SE +/- 18.14, N = 4 SE +/- 3.13, N = 3 SE +/- 11.96, N = 15 1243.6 1287.0 1252.0 1250.2 1267.3 1204.5 1. (CC) gcc options: -static
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 6K 12K 18K 24K 30K SE +/- 307.51, N = 3 SE +/- 385.40, N = 3 SE +/- 327.13, N = 3 SE +/- 236.82, N = 3 SE +/- 151.50, N = 3 SE +/- 72.28, N = 3 24718.20 25808.38 26306.18 23639.63 25051.76 24145.48 1. (CC) gcc options: -shared -fPIC -O2 -pthread
Hackbench Count: 8 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Thread Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 4 8 12 16 20 SE +/- 0.236, N = 15 SE +/- 0.224, N = 15 SE +/- 0.352, N = 15 SE +/- 0.163, N = 12 SE +/- 0.280, N = 12 SE +/- 0.116, N = 3 9.372 10.907 10.582 8.591 9.978 14.740 1. (CC) gcc options: -lpthread
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2019.4 Water Benchmark Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1.3037 2.6074 3.9111 5.2148 6.5185 SE +/- 0.012, N = 3 SE +/- 0.010, N = 3 SE +/- 0.003, N = 3 SE +/- 0.004, N = 3 SE +/- 0.020, N = 3 SE +/- 0.003, N = 3 5.786 5.759 5.783 5.768 5.753 5.794 1. (CXX) g++ options: -mavx512f -mfma -std=c++11 -O3 -funroll-all-loops -pthread -lrt -lpthread -lm
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 30 60 90 120 150 113.90 113.99 112.27 117.02 116.03 124.52
Sockperf Test: Throughput OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.4 Test: Throughput Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 100K 200K 300K 400K 500K SE +/- 5060.17, N = 6 SE +/- 4862.22, N = 20 SE +/- 3122.93, N = 25 SE +/- 3902.29, N = 5 SE +/- 3219.28, N = 15 SE +/- 3994.07, N = 5 426235 440031 448360 403297 420154 406044 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Java SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Composite Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 500 1000 1500 2000 2500 SE +/- 6.10, N = 4 SE +/- 6.46, N = 4 SE +/- 2.70, N = 4 SE +/- 10.55, N = 4 SE +/- 5.22, N = 4 SE +/- 6.82, N = 4 2020.37 2023.44 2152.56 2025.82 2018.53 2026.30
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 400K 800K 1200K 1600K 2000K SE +/- 14186.81, N = 3 SE +/- 17835.28, N = 3 SE +/- 2418.41, N = 3 SE +/- 12267.15, N = 3 SE +/- 13559.95, N = 3 SE +/- 3755.77, N = 3 1687345.84 1668803.22 1870205.53 1703749.93 1680764.40 1250999.82 1. (CC) gcc options: -O2 -lrt" -lrt
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 50K 100K 150K 200K 250K SE +/- 1201.85, N = 3 SE +/- 577.35, N = 3 SE +/- 881.92, N = 3 SE +/- 666.67, N = 3 SE +/- 333.33, N = 3 208000 210667 210000 196333 207333 196667 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 0.67, N = 3 SE +/- 4.04, N = 3 SE +/- 2.33, N = 3 SE +/- 3.93, N = 3 SE +/- 2.52, N = 3 SE +/- 2.19, N = 3 813 822 820 766 810 768 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 7.84, N = 3 SE +/- 3.18, N = 3 SE +/- 13.25, N = 3 SE +/- 4.81, N = 3 SE +/- 12.00, N = 3 SE +/- 4.58, N = 3 897 922 907 876 910 916 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Memcached mcperf Method: Get OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 20K 40K 60K 80K 100K SE +/- 2398.21, N = 12 SE +/- 490.15, N = 3 SE +/- 1036.03, N = 3 SE +/- 2233.11, N = 12 SE +/- 338.52, N = 3 SE +/- 770.74, N = 3 107000.5 116181.7 116305.7 102237.0 107775.5 102549.9 1. (CC) gcc options: -O2 -lm -rdynamic
glibc bench Benchmark: ffs OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 0.4055 0.811 1.2165 1.622 2.0275 SE +/- 0.00018, N = 15 SE +/- 0.00015, N = 3 SE +/- 0.00249, N = 3 SE +/- 0.00044, N = 15 SE +/- 0.00014, N = 15 SE +/- 0.00231, N = 3 1.67080 1.65556 1.66029 1.80224 1.66963 1.79641
Flexible IO Tester Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 50K 100K 150K 200K 250K SE +/- 1000.00, N = 3 SE +/- 2081.67, N = 3 SE +/- 3214.55, N = 3 SE +/- 3480.10, N = 3 SE +/- 3333.33, N = 3 SE +/- 2027.59, N = 3 216000 216000 216000 202333 216667 199333 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Flexible IO Tester Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.16 Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 4.04, N = 3 SE +/- 7.86, N = 3 SE +/- 12.47, N = 3 SE +/- 13.12, N = 3 SE +/- 13.17, N = 3 SE +/- 8.41, N = 3 845 843 845 790 845 778 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Asian Dragon Obj Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 12 24 36 48 60 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 51.67 51.53 51.96 51.71 51.77 35.09 MIN: 50.5 / MAX: 53.23 MIN: 50.41 / MAX: 52.89 MIN: 50.83 / MAX: 53.35 MIN: 50.49 / MAX: 53.01 MIN: 50.5 / MAX: 53.39 MIN: 34.67 / MAX: 35.59
glibc bench Benchmark: exp OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1.2879 2.5758 3.8637 5.1516 6.4395 SE +/- 0.00686, N = 3 SE +/- 0.00203, N = 3 SE +/- 0.00297, N = 3 SE +/- 0.00125, N = 3 SE +/- 0.01620, N = 3 SE +/- 0.00212, N = 3 5.60802 5.58804 5.08538 5.72369 5.64088 5.72415
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: unsharp-mask Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 7 14 21 28 35 SE +/- 0.17, N = 3 SE +/- 0.35, N = 3 SE +/- 0.03, N = 3 SE +/- 0.25, N = 3 SE +/- 0.22, N = 3 SE +/- 0.12, N = 3 29.70 27.75 26.70 30.11 29.60 30.46
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 13 26 39 52 65 SE +/- 0.73, N = 3 SE +/- 0.06, N = 3 SE +/- 0.25, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 57.94 58.78 58.83 58.77 58.64 38.70 MIN: 54.22 / MAX: 60.76 MIN: 56.96 / MAX: 61.09 MIN: 56.05 / MAX: 61.11 MIN: 57.07 / MAX: 60.62 MIN: 56.92 / MAX: 60.63 MIN: 38.16 / MAX: 39.33
t-test1 Threads: 1 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 1 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 14 28 42 56 70 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 18.80 19.24 18.87 19.98 19.23 64.71 1. (CC) gcc options: -pthread
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1400 2800 4200 5600 7000 SE +/- 12.14, N = 3 SE +/- 87.24, N = 4 SE +/- 21.53, N = 3 SE +/- 93.21, N = 4 SE +/- 26.22, N = 3 SE +/- 86.72, N = 4 6364.25 6555.18 6424.36 6462.18 6646.46 6474.74 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: auto-levels Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 6 12 18 24 30 SE +/- 0.29, N = 4 SE +/- 0.24, N = 3 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 SE +/- 0.17, N = 3 23.58 23.28 22.51 24.49 24.32 25.79
Selenium Benchmark: PSPDFKit WASM - Browser: Firefox OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 400 800 1200 1600 2000 SE +/- 11.26, N = 3 SE +/- 7.06, N = 3 SE +/- 9.13, N = 3 SE +/- 8.57, N = 3 SE +/- 6.44, N = 3 SE +/- 20.69, N = 3 1787 1678 1611 1782 1772 1772 1. firefox 70.0.1
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 1.20, N = 3 SE +/- 2.60, N = 3 SE +/- 1.20, N = 3 SE +/- 2.19, N = 3 SE +/- 0.58, N = 3 1093 1091 1032 1093 1093 1089
Sockperf Test: Latency Ping Pong OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Ping Pong Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 0.9416 1.8832 2.8248 3.7664 4.708 SE +/- 0.018, N = 25 SE +/- 0.028, N = 5 SE +/- 0.014, N = 5 SE +/- 0.036, N = 5 SE +/- 0.030, N = 5 SE +/- 0.037, N = 5 3.956 3.692 3.700 4.184 3.831 4.185 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
glibc bench Benchmark: ffsll OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 0.4055 0.811 1.2165 1.622 2.0275 SE +/- 0.00033, N = 13 SE +/- 0.00040, N = 3 SE +/- 0.00250, N = 3 SE +/- 0.00084, N = 3 SE +/- 0.00030, N = 15 SE +/- 0.00179, N = 3 1.67230 1.65581 1.66125 1.80203 1.66994 1.79714
GIMP Test: rotate OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: rotate Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.21, N = 7 18.43 18.31 17.75 18.94 18.42 19.19
Compile Bench Test: Compile OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Compile Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 400 800 1200 1600 2000 SE +/- 19.46, N = 6 SE +/- 5.66, N = 3 SE +/- 2.79, N = 3 SE +/- 10.84, N = 3 SE +/- 10.97, N = 3 SE +/- 8.10, N = 3 1685.69 1783.97 1791.87 1761.26 1779.60 1753.54
Memcached mcperf Method: Set OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 14K 28K 42K 56K 70K SE +/- 461.71, N = 3 SE +/- 454.12, N = 3 SE +/- 395.99, N = 3 SE +/- 290.11, N = 3 SE +/- 169.40, N = 3 SE +/- 185.19, N = 3 62923.7 66321.9 65755.6 61202.8 62276.2 60861.1 1. (CC) gcc options: -O2 -lm -rdynamic
Hackbench Count: 8 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Process Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 4 8 12 16 20 SE +/- 0.096, N = 3 SE +/- 0.091, N = 3 SE +/- 0.131, N = 3 SE +/- 0.120, N = 3 SE +/- 0.115, N = 12 SE +/- 0.142, N = 15 7.340 7.297 7.640 6.971 7.480 14.112 1. (CC) gcc options: -lpthread
Selenium Benchmark: Maze Solver - Browser: Firefox OpenBenchmarking.org Seconds, Fewer Is Better Selenium Benchmark: Maze Solver - Browser: Firefox Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 6.6 6.5 6.5 6.7 6.6 6.6 1. firefox 70.0.1
glibc bench Benchmark: pthread_once OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 0.4068 0.8136 1.2204 1.6272 2.034 SE +/- 0.00032, N = 12 SE +/- 0.00032, N = 4 SE +/- 0.00149, N = 3 SE +/- 0.00094, N = 3 SE +/- 0.00117, N = 9 SE +/- 0.00285, N = 3 1.68213 1.66339 1.67045 1.80817 1.67938 1.80347
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 2K 4K 6K 8K 10K SE +/- 127.99, N = 4 SE +/- 105.37, N = 4 SE +/- 108.34, N = 4 SE +/- 50.28, N = 4 SE +/- 119.00, N = 5 SE +/- 42.18, N = 4 8940 9093 8736 8790 8912 7989
OSPray Demo: Magnetic Reconnection - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 16 32 48 64 80 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 12 SE +/- 0.00, N = 15 71.43 71.43 71.43 71.43 71.43 55.56 MIN: 16.95 / MAX: 76.92 MIN: 18.18 / MAX: 76.92 MIN: 18.52 / MAX: 76.92 MIN: 18.18 / MAX: 76.92 MIN: 17.54 / MAX: 76.92 MIN: 17.86 / MAX: 58.82
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 4K Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 50 100 150 200 250 SE +/- 1.69, N = 3 SE +/- 1.75, N = 3 SE +/- 0.77, N = 3 SE +/- 3.19, N = 3 SE +/- 0.25, N = 3 SE +/- 1.22, N = 3 206.13 203.89 205.38 205.03 204.81 167.53 MIN: 82.9 / MAX: 230.43 MIN: 77.51 / MAX: 229.61 MIN: 81.1 / MAX: 229.85 MIN: 74.4 / MAX: 229.72 MIN: 80.25 / MAX: 228.7 MIN: 96.74 / MAX: 181.56 1. (CC) gcc options: -pthread
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Crown Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 10 20 30 40 50 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.29, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 45.21 45.56 45.49 45.64 45.72 34.50 MIN: 43.83 / MAX: 46.84 MIN: 44.06 / MAX: 47.1 MIN: 43.03 / MAX: 47.49 MIN: 44.18 / MAX: 47.67 MIN: 44.28 / MAX: 47.49 MIN: 33.83 / MAX: 35.24
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 140K 280K 420K 560K 700K SE +/- 649.79, N = 3 SE +/- 157.25, N = 3 SE +/- 875.68, N = 3 SE +/- 1056.10, N = 3 SE +/- 198.66, N = 3 SE +/- 586.46, N = 3 645204 646447 673402 643614 644906 643732
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 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 7.64, N = 3 SE +/- 12.88, N = 15 SE +/- 16.62, N = 12 SE +/- 17.76, N = 12 SE +/- 10.60, N = 3 SE +/- 2.66, N = 3 665.4 776.6 813.4 772.3 613.3 604.9 1. (CC) gcc options: -static
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 12 24 36 48 60 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.20, N = 3 SE +/- 0.07, N = 3 SE +/- 0.64, N = 3 SE +/- 0.12, N = 3 53.15 53.15 53.40 53.20 52.63 35.71 MIN: 51.12 / MAX: 55.69 MIN: 51.22 / MAX: 55.78 MIN: 50.65 / MAX: 56.15 MIN: 51.28 / MAX: 56.01 MIN: 48.49 / MAX: 55.83 MIN: 34.11 / MAX: 36.61
GIMP Test: resize OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: resize Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 3 6 9 12 15 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 12.54 12.42 12.06 12.77 12.35 12.51
t-test1 Threads: 2 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 2 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 5 10 15 20 25 SE +/- 0.045, N = 3 SE +/- 0.080, N = 3 SE +/- 0.020, N = 3 SE +/- 0.013, N = 3 SE +/- 0.128, N = 3 SE +/- 0.101, N = 3 8.804 8.984 8.617 9.163 8.585 21.460 1. (CC) gcc options: -pthread
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 10K 20K 30K 40K 50K SE +/- 261.30, N = 3 SE +/- 205.01, N = 3 SE +/- 654.85, N = 3 SE +/- 678.25, N = 3 SE +/- 465.64, N = 3 SE +/- 430.85, N = 3 47783.61 47770.69 46890.67 46840.52 36833.86 47329.24 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1.0852 2.1704 3.2556 4.3408 5.426 SE +/- 0.042, N = 3 SE +/- 0.009, N = 3 SE +/- 0.049, N = 15 SE +/- 0.027, N = 3 SE +/- 0.033, N = 3 SE +/- 0.040, N = 15 3.375 3.339 3.158 3.364 3.310 4.823 1. (CC) gcc options: -static -fopenmp -O3 -march=native
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1000 2000 3000 4000 5000 SE +/- 13.96, N = 4 SE +/- 14.09, N = 4 SE +/- 23.08, N = 4 SE +/- 29.70, N = 4 SE +/- 47.39, N = 4 SE +/- 31.58, N = 4 4781 4770 4559 4783 4843 4831
libjpeg-turbo tjbench Test: Decompression Throughput OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 2.0.2 Test: Decompression Throughput Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 40 80 120 160 200 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 SE +/- 0.61, N = 3 SE +/- 0.54, N = 3 SE +/- 0.16, N = 3 SE +/- 0.24, N = 3 176.59 176.89 181.82 176.23 176.94 176.38 1. (CC) gcc options: -O3 -rdynamic
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 14.05 13.72 13.27 14.72 14.03 14.72 1. (CC) gcc options: -lm
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 20 40 60 80 100 SE +/- 0.27, N = 3 SE +/- 0.07, N = 3 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 89.35 89.66 85.63 91.52 90.13 92.04 1. (CC) gcc options: -lm
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 11 22 33 44 55 SE +/- 0.56, N = 3 SE +/- 0.15, N = 3 SE +/- 0.28, N = 3 SE +/- 0.33, N = 3 SE +/- 0.32, N = 3 SE +/- 0.11, N = 3 46.19 45.78 44.79 47.22 45.71 40.59 1. (CC) gcc options: -lm
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.24, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.17, N = 3 20.53 20.32 20.41 21.26 20.67 19.66 1. (CC) gcc options: -lm
FS-Mark Test: 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 200 400 600 800 1000 SE +/- 9.77, N = 15 SE +/- 11.20, N = 3 SE +/- 7.81, N = 15 SE +/- 7.88, N = 15 SE +/- 6.82, N = 3 SE +/- 8.98, N = 3 725.1 740.1 795.9 780.1 730.4 574.6 1. (CC) gcc options: -static
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 1400 2800 4200 5600 7000 SE +/- 44.02, N = 3 SE +/- 16.32, N = 3 SE +/- 79.78, N = 5 SE +/- 47.84, N = 3 SE +/- 38.96, N = 3 SE +/- 104.45, N = 3 6110.45 5967.87 6099.23 6160.50 6077.89 6558.81 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
ctx_clock Context Switch Time OpenBenchmarking.org Clocks, Fewer Is Better ctx_clock Context Switch Time Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 100 200 300 400 500 SE +/- 1.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.33, N = 3 SE +/- 4.79, N = 8 135 134 135 455 135 481
IOR Read Test OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Read Test Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 400 800 1200 1600 2000 SE +/- 12.24, N = 3 SE +/- 23.04, N = 15 SE +/- 2.64, N = 3 SE +/- 20.13, N = 3 SE +/- 3.28, N = 3 SE +/- 19.36, N = 15 1849.54 1975.11 1984.95 1929.81 1979.48 1850.50 MIN: 1576.82 / MAX: 2125.1 MIN: 1512.99 / MAX: 2311.65 MIN: 1475.97 / MAX: 2157.41 MIN: 1255.72 / MAX: 2137.28 MIN: 1591.39 / MAX: 2150.22 MIN: 806.81 / MAX: 2294.23 1. (CC) gcc options: -O2 -lm -pthread -lmpi
IOR Write Test OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Write Test Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 300 600 900 1200 1500 SE +/- 15.41, N = 3 SE +/- 29.66, N = 15 SE +/- 2.97, N = 3 SE +/- 17.74, N = 3 SE +/- 8.02, N = 3 SE +/- 11.81, N = 15 1297.33 1274.11 1412.73 1221.78 1398.11 1142.03 MIN: 633.28 / MAX: 1724.03 MIN: 646.56 / MAX: 1856.98 MIN: 764.99 / MAX: 1787.94 MIN: 748.72 / MAX: 1723.13 MIN: 739.85 / MAX: 1771.77 MIN: 284.66 / MAX: 1569.45 1. (CC) gcc options: -O2 -lm -pthread -lmpi
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 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 400 800 1200 1600 2000 SE +/- 2.87, N = 3 SE +/- 5.19, N = 3 SE +/- 4.78, N = 3 SE +/- 6.79, N = 3 SE +/- 6.66, N = 3 SE +/- 3.13, N = 3 1804.7 1828.7 1848.5 1722.8 1796.3 1725.3 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 Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 600 1200 1800 2400 3000 SE +/- 9.23, N = 3 SE +/- 15.64, N = 3 SE +/- 9.50, N = 3 SE +/- 7.86, N = 3 SE +/- 25.39, N = 3 SE +/- 12.13, N = 3 2753.54 2828.44 2928.31 2543.26 2754.83 2514.16
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Default Mitigations No Mitigations No Mitigations + Old ucode Default Mitigations + TSX Default Mitigations + No HT Default Mitigations + No HT + TSX 130 260 390 520 650 SE +/- 4.56, N = 3 SE +/- 4.80, N = 3 SE +/- 1.08, N = 3 SE +/- 2.41, N = 3 SE +/- 3.52, N = 3 SE +/- 1.37, N = 3 579.22 593.91 600.51 553.70 581.72 553.25
Phoronix Test Suite v10.8.4