Cascade Lake TSX + Mitigations + New Microcode

2 x Intel Xeon Platinum 8280 mitigation benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1911242-HU-CASCADEMI26&sor&grt.

Cascade Lake TSX + Mitigations + New MicrocodeProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers386048MB280GB INTEL SSDPED1D280GAllvmpipe 377GBVE2282 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 19.105.4.0-rc7-12nov-vulns (x86_64) 20191112GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.53.3 Mesa 19.2.1 (LLVM 9.0 256 bits)GCC 9.2.1 20191008ext41920x10802 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores)OpenBenchmarking.orgCompiler 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,rwProcessor Details- No Mitigations + Old ucode: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x5000021- No Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Default Mitigations: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Default Mitigations + TSX: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002c- Default Mitigations + TSX + No HT: Scaling Governor: intel_pstate powersave - CPU Microcode: 0x500002cJava Details- OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Details- Python 2.7.17rc1 + Python 3.7.5rc1Security Details- 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 - 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 - 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 - 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 + TSX + 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 Clear buffers; SMT disabled

Cascade Lake TSX + Mitigations + New Microcodeapache: Static Web Page Servingblender: Classroom - CPU-Onlyblender: Barbershop - CPU-Onlycompilebench: Compilecompilebench: Initial Createcompilebench: Read Compiled Treecoremark: CoreMark Size 666 - Iterations Per Secondctx-clock: Context Switch Timedacapobench: H2dacapobench: Jythondacapobench: Tradesoapdacapobench: Tradebeansdav1d: Summer Nature 4Kdav1d: Chimera 1080p 10-bitembree: Pathtracer - Crownembree: Pathtracer ISPC - Crownembree: Pathtracer - Asian Dragon Objembree: Pathtracer ISPC - Asian Dragon Objrocksdb: Rand Fillrocksdb: Seq Fillrocksdb: Rand Fill Syncrocksdb: Read While Writingfio: Rand Read - Linux AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Read - Linux AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Write - Linux AIO - Yes - No - 2MB - Default Test Directoryfio: Rand Write - Linux AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Write - Linux AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Read - Linux AIO - Yes - No - 2MB - Default Test Directoryfio: Seq Read - Linux AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Read - Linux AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Write - Linux AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Write - Linux AIO - Yes - No - 4KB - Default Test Directoryfs-mark: 1000 Files, 1MB Sizefs-mark: 5000 Files, 1MB Size, 4 Threadsfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizefs-mark: 1000 Files, 1MB Size, No Sync/FSyncgimp: resizegimp: rotategimp: auto-levelsgimp: unsharp-maskglibc-bench: expglibc-bench: ffsglibc-bench: ffsllglibc-bench: pthread_oncegraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacegromacs: Water Benchmarkhackbench: 8 - Threadhackbench: 16 - Threadhackbench: 8 - Processhackbench: 16 - Processhackbench: 32 - Processior: Write Testior: Read Testjava-scimark2: Compositetjbench: Decompression Throughputmysqlslap: 256mcperf: Getmcperf: Setmemtier-benchmark: Redisn-queens: Elapsed Timenamd: ATPase Simulation - 327,506 Atomsnpb: EP.Cnpb: EP.Dnpb: FT.Cnginx: Static Web Page Servingosbench: Create Filesosbench: Create Threadsosbench: Create Processesosbench: Memory Allocationsospray: XFrog Forest - SciVisospray: XFrog Forest - Path Tracerospray: Magnetic Reconnection - SciVisphpbench: PHP Benchmark Suitepgbench: Buffer Test - Normal Load - Read Onlypybench: Total For Average Test Timesrenaissance: Apache Spark Bayesrenaissance: Savina Reactors.IOrenaissance: In-Memory Database Shootoutselenium: Maze Solver - Firefoxselenium: PSPDFKit WASM - Firefoxsockperf: Throughputsockperf: Latency Ping Pongsockperf: Latency Under Loadsqlite: 64sqlite-speedtest: Timed Time - Size 1,000t-test1: 1t-test1: 2build-gcc: Time To Compilebuild-linux-kernel: Time To Compilebuild-llvm: Time To Compilemrbayes: Primate Phylogeny AnalysisNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT26306.1895.27182.001791.87600.512928.311870205.52720013587364559766512150205.3868.7345.492553.404051.955758.828519987919939317524864123233158068090782021000019241776454800845216000795.91252.0813.41848.512.06117.74622.50926.6985.085381.660291.661251.6704514546065448094747555.78310.58228.5387.64026.74250.0791412.731984.952152.56181.818865446116305.765755.63942410.033.1580.360496099.236424.3646890.6732865.7513.27063320.41022044.78613585.63137012.206.7671.43673402901390.60912110323286.45426188.26316902.2106.516114483603.70037.69317.55663.87818.8688.617887.09924.185112.269127.16625808.3898.13185.501783.97593.912828.441668803.22403713490934770787612283203.8965.8445.561653.145351.527458.777519727119724916900563455863037747392282221066719141797460000843216000740.11287.0776.61828.712.41818.31023.27627.7455.588041.655561.655811.6633914586005438004817305.75910.90729.4477.29726.16446.6961274.111975.112023.44176.892850441116181.766321.94455789.733.3390.361675967.876555.1847770.6934173.5513.71978020.31962145.78352089.65762512.056.6771.43646447914647.71654410913382.14526263.55816974.9256.516784400313.69239.93817.21465.01919.2418.984900.53924.869113.985140.48724718.2098.36185.771685.69579.222753.541687345.84384413589404781727211886206.1366.1245.212953.146751.674757.936119082819054916526563354353087890089781320800018801736444200845216000725.11243.6665.41804.712.53518.43023.57829.6985.608021.670801.672301.6821314466025418014617515.7869.37228.8977.34027.10149.7601297.331849.542020.37176.591879441107000.562923.74047462.823.3750.361346110.456364.2547783.6131592.0014.04636820.52625046.19042189.34855512.056.6771.43645204909277.74739610933364.95927064.81017153.8696.617874262353.95638.44019.80766.09718.8038.804903.31724.959113.895140.32823639.6398.27185.631761.26553.702543.261703749.93237945587904783736311956205.0366.0545.639853.204851.710658.773117222917275815826062219812897376787676619633318241588406333790202333780.11250.2772.31722.812.76818.93824.49330.1055.723691.802241.802031.8081714315845408034577265.7688.59132.5516.97130.36152.7411221.781929.812025.82176.233830434102237.061202.83743629.933.3640.361446160.506462.1846840.5229726.1214.72245321.25660647.21800591.51999112.056.6771.43643614888296.74318610933531.92928018.32017134.6456.717824032974.18436.73818.70971.59819.9809.163941.09725.535117.018140.84624145.48123.90213.071753.54553.252514.161250999.81648548179894831717913668167.5350.8334.503335.709535.088938.698717487217485313635850460272857293391676819666719101560399667778199333574.61204.5604.91725.312.51319.18625.79130.4615.724151.796411.797141.8034712635745257904457225.79414.74029.55714.11225.21447.6991142.031850.502026.30176.381758440102549.960861.12519515.574.8230.421646558.816474.7447329.2430724.0314.71670019.66079140.58996892.0373608.554.6655.56643732694383.86201510893353.06828941.31417702.1016.617724060444.18541.81320.12171.67264.70721.460971.01428.316124.515140.180OpenBenchmarking.org

Apache Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX6K12K18K24K30KSE +/- 327.13, N = 3SE +/- 385.40, N = 3SE +/- 307.51, N = 3SE +/- 72.28, N = 3SE +/- 236.82, N = 326306.1825808.3824718.2024145.4823639.631. (CC) gcc options: -shared -fPIC -O2 -pthread

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Classroom - Compute: CPU-OnlyNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT306090120150SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.13, N = 3SE +/- 0.23, N = 395.2798.1398.2798.36123.90

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Barbershop - Compute: CPU-OnlyNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT50100150200250SE +/- 0.07, N = 3SE +/- 0.28, N = 3SE +/- 0.16, N = 3SE +/- 0.25, N = 3SE +/- 0.02, N = 3182.00185.50185.63185.77213.07

Compile Bench

Test: Compile

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: CompileNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HTDefault Mitigations400800120016002000SE +/- 2.79, N = 3SE +/- 5.66, N = 3SE +/- 10.84, N = 3SE +/- 8.10, N = 3SE +/- 19.46, N = 61791.871783.971761.261753.541685.69

Compile Bench

Test: Initial Create

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial CreateNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT130260390520650SE +/- 1.08, N = 3SE +/- 4.80, N = 3SE +/- 4.56, N = 3SE +/- 2.41, N = 3SE +/- 1.37, N = 3600.51593.91579.22553.70553.25

Compile Bench

Test: Read Compiled Tree

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled TreeNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT6001200180024003000SE +/- 9.50, N = 3SE +/- 15.64, N = 3SE +/- 9.23, N = 3SE +/- 7.86, N = 3SE +/- 12.13, N = 32928.312828.442753.542543.262514.16

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HT400K800K1200K1600K2000KSE +/- 2418.41, N = 3SE +/- 12267.15, N = 3SE +/- 14186.81, N = 3SE +/- 17835.28, N = 3SE +/- 3755.77, N = 31870205.531703749.931687345.841668803.221250999.821. (CC) gcc options: -O2 -lrt" -lrt

ctx_clock

Context Switch Time

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT100200300400500SE +/- 0.67, N = 3SE +/- 1.33, N = 3SE +/- 0.67, N = 3SE +/- 4.79, N = 8134135135455481

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Default Mitigations + TSX + No HTNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsNo Mitigations2K4K6K8K10KSE +/- 42.18, N = 4SE +/- 108.34, N = 4SE +/- 50.28, N = 4SE +/- 127.99, N = 4SE +/- 105.37, N = 479898736879089409093

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT10002000300040005000SE +/- 23.08, N = 4SE +/- 14.09, N = 4SE +/- 13.96, N = 4SE +/- 29.70, N = 4SE +/- 31.58, N = 445594770478147834831

DaCapo Benchmark

Java Test: Tradesoap

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapDefault Mitigations + TSX + No HTDefault MitigationsDefault Mitigations + TSXNo Mitigations + Old ucodeNo Mitigations2K4K6K8K10KSE +/- 85.56, N = 5SE +/- 58.97, N = 20SE +/- 86.60, N = 20SE +/- 106.71, N = 4SE +/- 54.13, N = 471797272736376657876

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansDefault MitigationsDefault Mitigations + TSXNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSX + No HT3K6K9K12K15KSE +/- 62.94, N = 4SE +/- 120.94, N = 8SE +/- 134.88, N = 20SE +/- 214.58, N = 16SE +/- 95.67, N = 181188611956121501228313668

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 4KDefault MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSXNo MitigationsDefault Mitigations + TSX + No HT50100150200250SE +/- 1.69, N = 3SE +/- 0.77, N = 3SE +/- 3.19, N = 3SE +/- 1.75, N = 3SE +/- 1.22, N = 3206.13205.38205.03203.89167.53MIN: 82.9 / MAX: 230.43MIN: 81.1 / MAX: 229.85MIN: 74.4 / MAX: 229.72MIN: 77.51 / MAX: 229.61MIN: 96.74 / MAX: 181.561. (CC) gcc options: -pthread

dav1d

Video Input: Chimera 1080p 10-bit

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Chimera 1080p 10-bitNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXNo MitigationsDefault Mitigations + TSX + No HT1530456075SE +/- 0.16, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.40, N = 3SE +/- 0.05, N = 368.7366.1266.0565.8450.83MIN: 51.32 / MAX: 108.82MIN: 49.13 / MAX: 104.59MIN: 49.01 / MAX: 104.31MIN: 49.05 / MAX: 104.44MIN: 36.44 / MAX: 88.581. (CC) gcc options: -pthread

Embree

Binary: Pathtracer - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: CrownDefault Mitigations + TSXNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX + No HT1020304050SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.29, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 345.6445.5645.4945.2134.50MIN: 44.18 / MAX: 47.67MIN: 44.06 / MAX: 47.1MIN: 43.03 / MAX: 47.49MIN: 43.83 / MAX: 46.84MIN: 33.83 / MAX: 35.24

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: CrownNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HT1224364860SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 353.4053.2053.1553.1535.71MIN: 50.65 / MAX: 56.15MIN: 51.28 / MAX: 56.01MIN: 51.12 / MAX: 55.69MIN: 51.22 / MAX: 55.78MIN: 34.11 / MAX: 36.61

Embree

Binary: Pathtracer - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon ObjNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HT1224364860SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 351.9651.7151.6751.5335.09MIN: 50.83 / MAX: 53.35MIN: 50.49 / MAX: 53.01MIN: 50.5 / MAX: 53.23MIN: 50.41 / MAX: 52.89MIN: 34.67 / MAX: 35.59

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT1326395265SE +/- 0.25, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.73, N = 3SE +/- 0.03, N = 358.8358.7858.7757.9438.70MIN: 56.05 / MAX: 61.11MIN: 56.96 / MAX: 61.09MIN: 57.07 / MAX: 60.62MIN: 54.22 / MAX: 60.76MIN: 38.16 / MAX: 39.33

Facebook RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX40K80K120K160K200KSE +/- 561.22, N = 3SE +/- 96.46, N = 3SE +/- 258.57, N = 3SE +/- 372.72, N = 3SE +/- 265.64, N = 31998791972711908281748721722291. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX40K80K120K160K200KSE +/- 182.30, N = 3SE +/- 294.32, N = 3SE +/- 302.73, N = 3SE +/- 486.11, N = 3SE +/- 84.11, N = 31993931972491905491748531727581. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill SyncNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT40K80K120K160K200KSE +/- 344.06, N = 3SE +/- 24.04, N = 3SE +/- 242.56, N = 3SE +/- 284.36, N = 3SE +/- 313.12, N = 31752481690051652651582601363581. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT1.4M2.8M4.2M5.6M7MSE +/- 75864.17, N = 5SE +/- 33377.10, N = 3SE +/- 70382.26, N = 3SE +/- 53165.01, N = 15SE +/- 77587.94, N = 3641232363455866335435622198150460271. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Flexible IO Tester

Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.16Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT70140210280350SE +/- 3.72, N = 15SE +/- 3.97, N = 4SE +/- 3.55, N = 15SE +/- 2.08, N = 3SE +/- 3.46, N = 33153083032892851. (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.orgIOPS, More Is BetterFlexible IO Tester 3.16Type: Random Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT20K40K60K80K100KSE +/- 916.06, N = 15SE +/- 1017.35, N = 4SE +/- 908.71, N = 15SE +/- 895.05, N = 3SE +/- 895.05, N = 380680789007747373767729331. (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.orgMB/s, More Is BetterFlexible IO Tester 3.16Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryNo MitigationsDefault Mitigations + TSX + No HTNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX2004006008001000SE +/- 3.18, N = 3SE +/- 4.58, N = 3SE +/- 13.25, N = 3SE +/- 7.84, N = 3SE +/- 4.81, N = 39229169078978761. (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.orgMB/s, More Is BetterFlexible IO Tester 3.16Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX2004006008001000SE +/- 4.04, N = 3SE +/- 2.33, N = 3SE +/- 0.67, N = 3SE +/- 2.19, N = 3SE +/- 3.93, N = 38228208137687661. (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.orgIOPS, More Is BetterFlexible IO Tester 3.16Type: Random Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX50K100K150K200K250KSE +/- 1201.85, N = 3SE +/- 577.35, N = 3SE +/- 333.33, N = 3SE +/- 881.92, N = 32106672100002080001966671963331. (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: 2MB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.16Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 2MB - Disk Target: Default Test DirectoryNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSX + No HTDefault MitigationsDefault Mitigations + TSX400800120016002000SE +/- 8.33, N = 3SE +/- 13.91, N = 3SE +/- 7.88, N = 3SE +/- 15.95, N = 15SE +/- 20.39, N = 6192419141910188018241. (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.orgMB/s, More Is BetterFlexible IO Tester 3.16Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT400800120016002000SE +/- 5.78, N = 3SE +/- 16.57, N = 15SE +/- 18.99, N = 15SE +/- 8.08, N = 3SE +/- 1.00, N = 3179717761736158815601. (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.orgIOPS, More Is BetterFlexible IO Tester 3.16Type: Sequential Read - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT100K200K300K400K500KSE +/- 1527.53, N = 3SE +/- 4251.83, N = 15SE +/- 4852.29, N = 15SE +/- 2185.81, N = 3SE +/- 333.33, N = 34600004548004442004063333996671. (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.orgMB/s, More Is BetterFlexible IO Tester 3.16Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryDefault MitigationsNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT2004006008001000SE +/- 4.04, N = 3SE +/- 12.47, N = 3SE +/- 7.86, N = 3SE +/- 13.12, N = 3SE +/- 8.41, N = 38458458437907781. (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.orgIOPS, More Is BetterFlexible IO Tester 3.16Type: Sequential Write - IO Engine: Linux AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test DirectoryDefault MitigationsNo MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSXDefault Mitigations + TSX + No HT50K100K150K200K250KSE +/- 1000.00, N = 3SE +/- 2081.67, N = 3SE +/- 3214.55, N = 3SE +/- 3480.10, N = 3SE +/- 2027.59, N = 32160002160002160002023331993331. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lnuma -libverbs -lrt -laio -lz -lm -lpthread -ldl

FS-Mark

Test: 1000 Files, 1MB Size

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB SizeNo Mitigations + Old ucodeDefault Mitigations + TSXNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HT2004006008001000SE +/- 7.81, N = 15SE +/- 7.88, N = 15SE +/- 11.20, N = 3SE +/- 9.77, N = 15SE +/- 8.98, N = 3795.9780.1740.1725.1574.61. (CC) gcc options: -static

FS-Mark

Test: 5000 Files, 1MB Size, 4 Threads

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 ThreadsNo MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT30060090012001500SE +/- 13.49, N = 15SE +/- 16.57, N = 5SE +/- 18.14, N = 4SE +/- 15.37, N = 3SE +/- 11.96, N = 151287.01252.01250.21243.61204.51. (CC) gcc options: -static

FS-Mark

Test: 4000 Files, 32 Sub Dirs, 1MB Size

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB SizeNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT2004006008001000SE +/- 16.62, N = 12SE +/- 12.88, N = 15SE +/- 17.76, N = 12SE +/- 7.64, N = 3SE +/- 2.66, N = 3813.4776.6772.3665.4604.91. (CC) gcc options: -static

FS-Mark

Test: 1000 Files, 1MB Size, No Sync/FSync

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSyncNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX400800120016002000SE +/- 4.78, N = 3SE +/- 5.19, N = 3SE +/- 2.87, N = 3SE +/- 3.13, N = 3SE +/- 6.79, N = 31848.51828.71804.71725.31722.81. (CC) gcc options: -static

GIMP

Test: resize

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: resizeNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSX + No HTDefault MitigationsDefault Mitigations + TSX3691215SE +/- 0.13, N = 3SE +/- 0.18, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.10, N = 312.0612.4212.5112.5412.77

GIMP

Test: rotate

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: rotateNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT510152025SE +/- 0.01, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.21, N = 717.7518.3118.4318.9419.19

GIMP

Test: auto-levels

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: auto-levelsNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT612182430SE +/- 0.17, N = 3SE +/- 0.24, N = 3SE +/- 0.29, N = 4SE +/- 0.23, N = 3SE +/- 0.17, N = 322.5123.2823.5824.4925.79

GIMP

Test: unsharp-mask

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: unsharp-maskNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT714212835SE +/- 0.03, N = 3SE +/- 0.35, N = 3SE +/- 0.17, N = 3SE +/- 0.25, N = 3SE +/- 0.12, N = 326.7027.7529.7030.1130.46

glibc bench

Benchmark: exp

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: expNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT1.28792.57583.86375.15166.4395SE +/- 0.00297, N = 3SE +/- 0.00203, N = 3SE +/- 0.00686, N = 3SE +/- 0.00125, N = 3SE +/- 0.00212, N = 35.085385.588045.608025.723695.72415

glibc bench

Benchmark: ffs

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX0.40550.8111.21651.6222.0275SE +/- 0.00015, N = 3SE +/- 0.00249, N = 3SE +/- 0.00018, N = 15SE +/- 0.00231, N = 3SE +/- 0.00044, N = 151.655561.660291.670801.796411.80224

glibc bench

Benchmark: ffsll

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsllNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX0.40550.8111.21651.6222.0275SE +/- 0.00040, N = 3SE +/- 0.00250, N = 3SE +/- 0.00033, N = 13SE +/- 0.00179, N = 3SE +/- 0.00084, N = 31.655811.661251.672301.797141.80203

glibc bench

Benchmark: pthread_once

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX0.40680.81361.22041.62722.034SE +/- 0.00032, N = 4SE +/- 0.00149, N = 3SE +/- 0.00032, N = 12SE +/- 0.00285, N = 3SE +/- 0.00094, N = 31.663391.670451.682131.803471.80817

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT30060090012001500SE +/- 11.02, N = 3SE +/- 8.39, N = 3SE +/- 10.97, N = 3SE +/- 7.69, N = 3SE +/- 13.20, N = 3145814541446143112631. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT130260390520650SE +/- 3.51, N = 3SE +/- 5.92, N = 9SE +/- 5.35, N = 15SE +/- 8.97, N = 3SE +/- 9.54, N = 36066026005845741. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT120240360480600SE +/- 1.00, N = 3SE +/- 2.08, N = 3SE +/- 1.76, N = 3SE +/- 3.71, N = 35445435415405251. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HT2004006008001000SE +/- 9.00, N = 3SE +/- 3.48, N = 3SE +/- 3.48, N = 3SE +/- 5.70, N = 3SE +/- 8.84, N = 38098038018007901. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT100200300400500SE +/- 6.51, N = 3SE +/- 7.31, N = 3SE +/- 7.36, N = 3SE +/- 2.85, N = 3SE +/- 4.33, N = 34814744614574451. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color SpaceNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT160320480640800SE +/- 8.11, N = 3SE +/- 10.37, N = 4SE +/- 5.69, N = 3SE +/- 2.00, N = 3SE +/- 7.65, N = 87557517307267221. (CC) gcc options: -fopenmp -O2 -pthread -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2019.4Water BenchmarkDefault Mitigations + TSX + No HTDefault MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSXNo Mitigations1.30372.60743.91115.21486.5185SE +/- 0.003, N = 3SE +/- 0.012, N = 3SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.010, N = 35.7945.7865.7835.7685.7591. (CXX) g++ options: -mavx512f -mfma -std=c++11 -O3 -funroll-all-loops -pthread -lrt -lpthread -lm

Hackbench

Count: 8 - Type: Thread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ThreadDefault Mitigations + TSXDefault MitigationsNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSX + No HT48121620SE +/- 0.163, N = 12SE +/- 0.236, N = 15SE +/- 0.352, N = 15SE +/- 0.224, N = 15SE +/- 0.116, N = 38.5919.37210.58210.90714.7401. (CC) gcc options: -lpthread

Hackbench

Count: 16 - Type: Thread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ThreadNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX816243240SE +/- 0.16, N = 3SE +/- 0.35, N = 3SE +/- 0.30, N = 3SE +/- 0.26, N = 15SE +/- 0.41, N = 328.5428.9029.4529.5632.551. (CC) gcc options: -lpthread

Hackbench

Count: 8 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ProcessDefault Mitigations + TSXNo MitigationsDefault MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSX + No HT48121620SE +/- 0.120, N = 3SE +/- 0.091, N = 3SE +/- 0.096, N = 3SE +/- 0.131, N = 3SE +/- 0.142, N = 156.9717.2977.3407.64014.1121. (CC) gcc options: -lpthread

Hackbench

Count: 16 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ProcessDefault Mitigations + TSX + No HTNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX714212835SE +/- 0.05, N = 3SE +/- 0.22, N = 13SE +/- 0.28, N = 3SE +/- 0.42, N = 3SE +/- 0.35, N = 1525.2126.1626.7427.1030.361. (CC) gcc options: -lpthread

Hackbench

Count: 32 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ProcessNo MitigationsDefault Mitigations + TSX + No HTDefault MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSX1224364860SE +/- 0.67, N = 12SE +/- 0.25, N = 3SE +/- 0.89, N = 15SE +/- 0.54, N = 3SE +/- 1.14, N = 1546.7047.7049.7650.0852.741. (CC) gcc options: -lpthread

IOR

Write Test

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Write TestNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT30060090012001500SE +/- 2.97, N = 3SE +/- 15.41, N = 3SE +/- 29.66, N = 15SE +/- 17.74, N = 3SE +/- 11.81, N = 151412.731297.331274.111221.781142.03MIN: 764.99 / MAX: 1787.94MIN: 633.28 / MAX: 1724.03MIN: 646.56 / MAX: 1856.98MIN: 748.72 / MAX: 1723.13MIN: 284.66 / MAX: 1569.451. (CC) gcc options: -O2 -lm -pthread -lmpi

IOR

Read Test

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read TestNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HTDefault Mitigations400800120016002000SE +/- 2.64, N = 3SE +/- 23.04, N = 15SE +/- 20.13, N = 3SE +/- 19.36, N = 15SE +/- 12.24, N = 31984.951975.111929.811850.501849.54MIN: 1475.97 / MAX: 2157.41MIN: 1512.99 / MAX: 2311.65MIN: 1255.72 / MAX: 2137.28MIN: 806.81 / MAX: 2294.23MIN: 1576.82 / MAX: 2125.11. (CC) gcc options: -O2 -lm -pthread -lmpi

Java SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: CompositeNo Mitigations + Old ucodeDefault Mitigations + TSX + No HTDefault Mitigations + TSXNo MitigationsDefault Mitigations5001000150020002500SE +/- 2.70, N = 4SE +/- 6.82, N = 4SE +/- 10.55, N = 4SE +/- 6.46, N = 4SE +/- 6.10, N = 42152.562026.302025.822023.442020.37

libjpeg-turbo tjbench

Test: Decompression Throughput

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression ThroughputNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX4080120160200SE +/- 0.61, N = 3SE +/- 0.03, N = 3SE +/- 0.24, N = 3SE +/- 0.24, N = 3SE +/- 0.54, N = 3181.82176.89176.59176.38176.231. (CC) gcc options: -O3 -rdynamic

MariaDB

Clients: 256

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 256No Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX100200300400500SE +/- 0.34, N = 3SE +/- 0.66, N = 3SE +/- 0.75, N = 3SE +/- 0.42, N = 3SE +/- 1.41, N = 34464414414404341. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

Memcached mcperf

Method: Get

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: GetNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX20K40K60K80K100KSE +/- 1036.03, N = 3SE +/- 490.15, N = 3SE +/- 2398.21, N = 12SE +/- 770.74, N = 3SE +/- 2233.11, N = 12116305.7116181.7107000.5102549.9102237.01. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Set

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: SetNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT14K28K42K56K70KSE +/- 454.12, N = 3SE +/- 395.99, N = 3SE +/- 461.71, N = 3SE +/- 290.11, N = 3SE +/- 185.19, N = 366321.965755.662923.761202.860861.11. (CC) gcc options: -O2 -lm -rdynamic

Memtier_benchmark

Protocol: Redis

OpenBenchmarking.orgOps/sec, More Is BetterMemtier_benchmark 1.2.17Protocol: RedisNo MitigationsDefault MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSXDefault Mitigations + TSX + No HT1000K2000K3000K4000K5000KSE +/- 2516.82, N = 3SE +/- 170934.41, N = 12SE +/- 182130.65, N = 12SE +/- 202059.99, N = 12SE +/- 11397.28, N = 34455789.734047462.823942410.033743629.932519515.571. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

N-Queens

Elapsed Time

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed TimeNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT1.08522.17043.25564.34085.426SE +/- 0.049, N = 15SE +/- 0.009, N = 3SE +/- 0.027, N = 3SE +/- 0.042, N = 3SE +/- 0.040, N = 153.1583.3393.3643.3754.8231. (CC) gcc options: -static -fopenmp -O3 -march=native

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXNo MitigationsDefault Mitigations + TSX + No HT0.09490.18980.28470.37960.4745SE +/- 0.00022, N = 15SE +/- 0.00025, N = 15SE +/- 0.00025, N = 12SE +/- 0.00020, N = 15SE +/- 0.00021, N = 140.360490.361340.361440.361670.42164

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CDefault Mitigations + TSX + No HTDefault Mitigations + TSXDefault MitigationsNo Mitigations + Old ucodeNo Mitigations14002800420056007000SE +/- 104.45, N = 3SE +/- 47.84, N = 3SE +/- 44.02, N = 3SE +/- 79.78, N = 5SE +/- 16.32, N = 36558.816160.506110.456099.235967.871. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DNo MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSXNo Mitigations + Old ucodeDefault Mitigations14002800420056007000SE +/- 87.24, N = 4SE +/- 86.72, N = 4SE +/- 93.21, N = 4SE +/- 21.53, N = 3SE +/- 12.14, N = 36555.186474.746462.186424.366364.251. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HTNo Mitigations + Old ucodeDefault Mitigations + TSX10K20K30K40K50KSE +/- 261.30, N = 3SE +/- 205.01, N = 3SE +/- 430.85, N = 3SE +/- 654.85, N = 3SE +/- 678.25, N = 347783.6147770.6947329.2446890.6746840.521. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NGINX Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page ServingNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX7K14K21K28K35KSE +/- 273.17, N = 3SE +/- 95.09, N = 3SE +/- 428.12, N = 4SE +/- 74.44, N = 3SE +/- 360.88, N = 534173.5532865.7531592.0030724.0329726.121. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

OSBench

Test: Create Files

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create FilesNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX48121620SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 313.2713.7214.0514.7214.721. (CC) gcc options: -lm

OSBench

Test: Create Threads

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ThreadsDefault Mitigations + TSX + No HTNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSX510152025SE +/- 0.17, N = 3SE +/- 0.02, N = 3SE +/- 0.24, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 319.6620.3220.4120.5321.261. (CC) gcc options: -lm

OSBench

Test: Create Processes

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ProcessesDefault Mitigations + TSX + No HTNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX1122334455SE +/- 0.11, N = 3SE +/- 0.28, N = 3SE +/- 0.15, N = 3SE +/- 0.56, N = 3SE +/- 0.33, N = 340.5944.7945.7846.1947.221. (CC) gcc options: -lm

OSBench

Test: Memory Allocations

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory AllocationsNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT20406080100SE +/- 0.23, N = 3SE +/- 0.27, N = 3SE +/- 0.07, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 385.6389.3589.6691.5292.041. (CC) gcc options: -lm

OSPray

Demo: XFrog Forest - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HT3691215SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 1212.2012.0512.0512.058.55MIN: 10.1 / MAX: 12.35MIN: 9.62 / MAX: 12.2MIN: 10.31 / MAX: 12.2MIN: 8.93 / MAX: 12.2MIN: 7.19 / MAX: 8.62

OSPray

Demo: XFrog Forest - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HT246810SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.01, N = 36.766.676.676.674.66MIN: 5.88 / MAX: 6.8MIN: 5.71 / MAX: 6.76MIN: 5.85 / MAX: 6.76MIN: 5.85 / MAX: 6.71MIN: 4.15 / MAX: 4.69

OSPray

Demo: Magnetic Reconnection - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisDefault Mitigations + TSXDefault MitigationsNo MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSX + No HT1632486480SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 1571.4371.4371.4371.4355.56MIN: 18.18 / MAX: 76.92MIN: 16.95 / MAX: 76.92MIN: 18.18 / MAX: 76.92MIN: 18.52 / MAX: 76.92MIN: 17.86 / MAX: 58.82

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX140K280K420K560K700KSE +/- 875.68, N = 3SE +/- 157.25, N = 3SE +/- 649.79, N = 3SE +/- 586.46, N = 3SE +/- 1056.10, N = 3673402646447645204643732643614

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyNo MitigationsDefault MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSXDefault Mitigations + TSX + No HT200K400K600K800K1000KSE +/- 453.84, N = 3SE +/- 7811.39, N = 3SE +/- 14964.49, N = 3SE +/- 2791.38, N = 3SE +/- 1046.95, N = 3914647.72909277.75901390.61888296.74694383.861. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesNo Mitigations + Old ucodeDefault Mitigations + TSX + No HTNo MitigationsDefault MitigationsDefault Mitigations + TSX2004006008001000SE +/- 2.60, N = 3SE +/- 0.58, N = 3SE +/- 1.20, N = 3SE +/- 1.20, N = 310321089109110931093

Renaissance

Test: Apache Spark Bayes

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark BayesNo Mitigations + Old ucodeDefault Mitigations + TSX + No HTDefault MitigationsNo MitigationsDefault Mitigations + TSX8001600240032004000SE +/- 34.64, N = 32SE +/- 25.05, N = 40SE +/- 41.85, N = 40SE +/- 54.20, N = 32SE +/- 60.43, N = 403286.453353.073364.963382.153531.93

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Savina Reactors.IONo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT6K12K18K24K30KSE +/- 368.24, N = 40SE +/- 370.01, N = 40SE +/- 403.62, N = 40SE +/- 446.70, N = 40SE +/- 470.43, N = 4026188.2626263.5627064.8128018.3228941.31

Renaissance

Test: In-Memory Database Shootout

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: In-Memory Database ShootoutNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT4K8K12K16K20KSE +/- 170.14, N = 8SE +/- 152.42, N = 8SE +/- 149.97, N = 11SE +/- 119.20, N = 8SE +/- 176.64, N = 916902.2116974.9317134.6517153.8717702.10

Selenium

Benchmark: Maze Solver - Browser: Firefox

OpenBenchmarking.orgSeconds, Fewer Is BetterSeleniumBenchmark: Maze Solver - Browser: FirefoxNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX246810SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 36.56.56.66.66.71. firefox 70.0.1

Selenium

Benchmark: PSPDFKit WASM - Browser: Firefox

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: FirefoxNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSXDefault Mitigations400800120016002000SE +/- 9.13, N = 3SE +/- 7.06, N = 3SE +/- 20.69, N = 3SE +/- 8.57, N = 3SE +/- 11.26, N = 3161116781772178217871. firefox 70.0.1

Sockperf

Test: Throughput

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: ThroughputNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSX + No HTDefault Mitigations + TSX100K200K300K400K500KSE +/- 3122.93, N = 25SE +/- 4862.22, N = 20SE +/- 5060.17, N = 6SE +/- 3994.07, N = 5SE +/- 3902.29, N = 54483604400314262354060444032971. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

Sockperf

Test: Latency Ping Pong

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping PongNo MitigationsNo Mitigations + Old ucodeDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT0.94161.88322.82483.76644.708SE +/- 0.028, N = 5SE +/- 0.014, N = 5SE +/- 0.018, N = 25SE +/- 0.036, N = 5SE +/- 0.037, N = 53.6923.7003.9564.1844.1851. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

Sockperf

Test: Latency Under Load

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under LoadDefault Mitigations + TSXNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSX + No HT1020304050SE +/- 1.49, N = 20SE +/- 0.57, N = 25SE +/- 0.57, N = 25SE +/- 0.20, N = 5SE +/- 0.09, N = 536.7437.6938.4439.9441.811. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

SQLite

Threads / Copies: 64

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 64No MitigationsNo Mitigations + Old ucodeDefault Mitigations + TSXDefault MitigationsDefault Mitigations + TSX + No HT510152025SE +/- 0.21, N = 6SE +/- 0.20, N = 3SE +/- 0.18, N = 3SE +/- 0.26, N = 15SE +/- 0.37, N = 1517.2117.5618.7119.8120.121. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000No Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT1632486480SE +/- 0.16, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 363.8865.0266.1071.6071.671. (CC) gcc options: -O2 -ldl -lz -lpthread

t-test1

Threads: 1

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1Default MitigationsNo Mitigations + Old ucodeNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT1428425670SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 318.8018.8719.2419.9864.711. (CC) gcc options: -pthread

t-test1

Threads: 2

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2No Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT510152025SE +/- 0.020, N = 3SE +/- 0.045, N = 3SE +/- 0.080, N = 3SE +/- 0.013, N = 3SE +/- 0.101, N = 38.6178.8048.9849.16321.4601. (CC) gcc options: -pthread

Timed GCC Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To CompileNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT2004006008001000SE +/- 1.99, N = 3SE +/- 0.98, N = 3SE +/- 0.61, N = 3SE +/- 0.69, N = 3SE +/- 0.41, N = 3887.10900.54903.32941.10971.01

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileNo Mitigations + Old ucodeNo MitigationsDefault MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT714212835SE +/- 0.26, N = 13SE +/- 0.25, N = 14SE +/- 0.28, N = 13SE +/- 0.27, N = 13SE +/- 0.29, N = 1324.1924.8724.9625.5428.32

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileNo Mitigations + Old ucodeDefault MitigationsNo MitigationsDefault Mitigations + TSXDefault Mitigations + TSX + No HT306090120150112.27113.90113.99117.02124.52

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisNo Mitigations + Old ucodeDefault Mitigations + TSX + No HTDefault MitigationsNo MitigationsDefault Mitigations + TSX306090120150SE +/- 0.31, N = 3SE +/- 0.40, N = 3SE +/- 0.30, N = 3SE +/- 0.26, N = 3SE +/- 0.25, N = 3127.17140.18140.33140.49140.851. (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

Phoronix Test Suite v10.8.5