Clear Linux Cascadelake JCC Microcode

Benchmarks for a future article of JCC erratum.

HTML result view exported from: https://openbenchmarking.org/result/1911113-HU-CLEARLINU55.

Clear Linux Cascadelake JCC MicrocodeProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionOld ucodeNew ucodeNew ucode + Assembler2 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 10/25/40/50GbEClear Linux OS 314705.3.8-854.native (x86_64)GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.53.3 Mesa 19.3.0-devel (LLVM 9.0.0 256 bits)GCC 9.2.1 20191101 gcc-9-branch@277702 + Clang 9.0.0 + LLVM 9.0.0ext41920x1080Clear Linux OS 31480GCC 9.2.1 20191103 gcc-9-branch@277748 + Clang 9.0.0 + LLVM 9.0.0OpenBenchmarking.orgEnvironment Details- CFFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,-sort-common -Wl,--enable-new-dtags" FFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -malign-data=abi -fno-semantic-interposition -ftree-vectorize -ftree-loop-vectorize -Wl,--enable-new-dtags" CXXFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake -fvisibility-inlines-hidden -Wl,--enable-new-dtags" MESA_GLSL_CACHE_DISABLE=0 CFLAGS="-g -O3 -feliminate-unused-debug-types -pipe -Wall -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=32 -Wformat -Wformat-security -m64 -fasynchronous-unwind-tables -Wp,-D_REENTRANT -ftree-loop-distribute-patterns -Wl,-z -Wl,now -Wl,-z -Wl,relro -fno-semantic-interposition -ffat-lto-objects -fno-trapping-math -Wl,-sort-common -Wl,--enable-new-dtags -mtune=skylake" THEANO_FLAGS="floatX=float32,openmp=true,gcc.cxxflags="-ftree-vectorize -mavx"" Compiler Details- --build=x86_64-generic-linux --disable-libmpx --disable-libunwind-exceptions --disable-multiarch --disable-vtable-verify --disable-werror --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-clocale=gnu --enable-default-pie --enable-gnu-indirect-function --enable-languages=c,c++,fortran,go --enable-ld=default --enable-libstdcxx-pch --enable-lto --enable-multilib --enable-plugin --enable-shared --enable-threads=posix --exec-prefix=/usr --includedir=/usr/include --target=x86_64-generic-linux --with-arch=westmere --with-gcc-major-version-only --with-glibc-version=2.19 --with-gnu-ld --with-isl --with-ppl=yes --with-tune=haswell Processor Details- Scaling Governor: intel_pstate performanceJava Details- OpenJDK Runtime Environment (build 1.8.0-u232-ga-b00)Python Details- Python 3.7.5Security Details- 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

Clear Linux Cascadelake JCC Microcodenpb: EP.Dnamd: ATPase Simulation - 327,506 Atomsqmcpack: graphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spaceospray: Magnetic Reconnection - SciVisembree: Pathtracer - Asian Dragonembree: Pathtracer ISPC - Asian Dragonrav1e: 1080p To AV1 Video Encodesvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080ptjbench: Decompression Throughputgromacs: Water Benchmarkredis: SETrocksdb: Rand Fillrocksdb: Seq Fillrocksdb: Read While Writingmcperf: Addmcperf: Getmcperf: Setpybench: Total For Average Test Timesapache: Static Web Page Servingphpbench: PHP Benchmark SuiteOld ucodeNew ucodeNew ucode + Assembler6537.220.362033879.815877195878962095664115276.9260.506971.75650.913343.57358.75181.8961755.8591880693.73409287418776619698762995.257144.362591.3102428072.829268916403.290.365803924.615796744848712040663116376.2459.883770.68620.901340.47345.65177.3737085.7901809059.85403069414795587302161271.057139.661768.3108228149.378533336507.450.363803902.315696995828912024643105676.0160.103772.09900.895344.90348.87183.4027605.8451819823.37405800415584573566961713.456098.062221.6103325832.31880797OpenBenchmarking.org

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DOld ucodeNew ucodeNew ucode + Assembler14002800420056007000SE +/- 87.31, N = 4SE +/- 86.47, N = 3SE +/- 93.39, N = 36537.226403.296507.451. (F9X) gfortran options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. 3.2

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsOld ucodeNew ucodeNew ucode + Assembler0.08230.16460.24690.32920.4115SE +/- 0.00033, N = 10SE +/- 0.00299, N = 3SE +/- 0.00094, N = 30.362030.365800.36380

QMCPACK

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.8Old ucodeNew ucodeNew ucode + Assembler80016002400320040003879.83924.63902.31. (CXX) g++ options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -ffast-math -lm

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlOld ucodeNew ucodeNew ucode + Assembler30060090012001500SE +/- 6.17, N = 3SE +/- 12.67, N = 3SE +/- 9.28, N = 31587157915691. (CC) gcc options: -fopenmp -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateOld ucodeNew ucodeNew ucode + Assembler160320480640800SE +/- 6.33, N = 3SE +/- 10.54, N = 3SE +/- 10.73, N = 37196746991. (CC) gcc options: -fopenmp -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenOld ucodeNew ucodeNew ucode + Assembler130260390520650SE +/- 2.03, N = 3SE +/- 1.86, N = 3SE +/- 2.73, N = 35874845821. (CC) gcc options: -fopenmp -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedOld ucodeNew ucodeNew ucode + Assembler2004006008001000SE +/- 1.53, N = 3SE +/- 1.00, N = 3SE +/- 2.60, N = 38968718911. (CC) gcc options: -fopenmp -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingOld ucodeNew ucodeNew ucode + Assembler400800120016002000SE +/- 2.08, N = 3SE +/- 30.93, N = 3SE +/- 33.31, N = 32095204020241. (CC) gcc options: -fopenmp -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -pthread -ltiff -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-GaussianOld ucodeNew ucodeNew ucode + Assembler140280420560700SE +/- 0.33, N = 3SE +/- 8.16, N = 4SE +/- 6.23, N = 36646636431. (CC) gcc options: -fopenmp -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -pthread -ltiff -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 SpaceOld ucodeNew ucodeNew ucode + Assembler30060090012001500SE +/- 9.26, N = 3SE +/- 13.89, N = 15SE +/- 0.67, N = 31152116310561. (CC) gcc options: -fopenmp -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -pthread -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lxml2 -lz -lm -lpthread

OSPray

Demo: Magnetic Reconnection - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisOld ucodeNew ucodeNew ucode + Assembler20406080100SE +/- 0.00, N = 12SE +/- 0.69, N = 8SE +/- 0.92, N = 676.9276.2476.01MIN: 52.63MIN: 52.63 / MAX: 76.92MIN: 55.56 / MAX: 76.92

Embree

Binary: Pathtracer - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian DragonOld ucodeNew ucodeNew ucode + Assembler1428425670SE +/- 0.46, N = 3SE +/- 0.86, N = 4SE +/- 0.69, N = 360.5159.8860.10MIN: 58.32 / MAX: 62.62MIN: 55.58 / MAX: 62.86MIN: 57.24 / MAX: 62.14

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian DragonOld ucodeNew ucodeNew ucode + Assembler1632486480SE +/- 1.20, N = 3SE +/- 0.71, N = 3SE +/- 0.21, N = 371.7670.6972.10MIN: 66.45 / MAX: 74.99MIN: 67.89 / MAX: 74.49MIN: 68.93 / MAX: 74.37

rav1e

1080p To AV1 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.11080p To AV1 Video EncodeOld ucodeNew ucodeNew ucode + Assembler0.20540.41080.61620.82161.027SE +/- 0.002, N = 3SE +/- 0.004, N = 3SE +/- 0.002, N = 30.9130.9010.895

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pOld ucodeNew ucodeNew ucode + Assembler70140210280350SE +/- 2.73, N = 14SE +/- 1.16, N = 3SE +/- 3.42, N = 9343.57340.47344.901. (CC) gcc options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pOld ucodeNew ucodeNew ucode + Assembler80160240320400SE +/- 2.60, N = 3SE +/- 4.06, N = 3SE +/- 2.37, N = 3358.75345.65348.871. (CC) gcc options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

libjpeg-turbo tjbench

Test: Decompression Throughput

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression ThroughputOld ucodeNew ucodeNew ucode + Assembler4080120160200SE +/- 0.32, N = 3SE +/- 0.39, N = 3SE +/- 0.10, N = 3181.90177.37183.401. (CC) gcc options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -rdynamic

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2019.4Water BenchmarkOld ucodeNew ucodeNew ucode + Assembler1.31832.63663.95495.27326.5915SE +/- 0.026, N = 3SE +/- 0.020, N = 3SE +/- 0.004, N = 35.8595.7905.8451. (CXX) g++ options: -mavx512f -mfma -pthread -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -std=c++11 -funroll-all-loops -lrt -lpthread -lm

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETOld ucodeNew ucodeNew ucode + Assembler400K800K1200K1600K2000KSE +/- 19430.82, N = 8SE +/- 35782.39, N = 15SE +/- 23886.38, N = 151880693.731809059.851819823.371. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake

Facebook RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random FillOld ucodeNew ucodeNew ucode + Assembler90K180K270K360K450KSE +/- 1592.77, N = 3SE +/- 2131.05, N = 3SE +/- 2049.92, N = 34092874030694058001. (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 FillOld ucodeNew ucodeNew ucode + Assembler90K180K270K360K450KSE +/- 550.05, N = 3SE +/- 365.04, N = 3SE +/- 438.89, N = 34187764147954155841. (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 WritingOld ucodeNew ucodeNew ucode + Assembler1.3M2.6M3.9M5.2M6.5MSE +/- 64642.57, N = 15SE +/- 103250.30, N = 15SE +/- 78853.34, N = 46196987587302157356691. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Memcached mcperf

Method: Add

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: AddOld ucodeNew ucodeNew ucode + Assembler13K26K39K52K65KSE +/- 137.80, N = 3SE +/- 933.56, N = 12SE +/- 262.38, N = 362995.261271.061713.41. (CC) gcc options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -lm -rdynamic

Memcached mcperf

Method: Get

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: GetOld ucodeNew ucodeNew ucode + Assembler12K24K36K48K60KSE +/- 599.69, N = 3SE +/- 525.50, N = 15SE +/- 772.61, N = 357144.357139.656098.01. (CC) gcc options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -lm -rdynamic

Memcached mcperf

Method: Set

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: SetOld ucodeNew ucodeNew ucode + Assembler13K26K39K52K65KSE +/- 52.60, N = 3SE +/- 66.58, N = 3SE +/- 210.63, N = 362591.361768.362221.61. (CC) gcc options: -O3 -pipe -fexceptions -fstack-protector -m64 -ffat-lto-objects -fno-trapping-math -mtune=skylake -lm -rdynamic

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesOld ucodeNew ucodeNew ucode + Assembler2004006008001000SE +/- 3.06, N = 3SE +/- 3.61, N = 3SE +/- 1.86, N = 3102410821033

Apache Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingOld ucodeNew ucodeNew ucode + Assembler6K12K18K24K30KSE +/- 340.14, N = 3SE +/- 120.77, N = 3SE +/- 359.87, N = 328072.8228149.3725832.311. (CC) gcc options: -shared -fPIC -pthread -O3 -fstack-protector -m64 -mtune=skylake

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteOld ucodeNew ucodeNew ucode + Assembler200K400K600K800K1000KSE +/- 718.51, N = 3SE +/- 309.51, N = 3SE +/- 1348.44, N = 3926891853333880797

Phoronix Test Suite v10.8.4