Threadripper 2990WX CPU Frequency Scaling Governor Tests

Benchmarks by Michael Larabel.

HTML result view exported from: https://openbenchmarking.org/result/1808204-PTS-THREADRI92&grr&sor.

Threadripper 2990WX CPU Frequency Scaling Governor TestsProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionCPUFreq ConservativeCPUFreq OndemandCPUFreq PerformanceCPUFreq PowersaveCPUFreq SchedutilAMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)ASUS ROG ZENITH EXTREME (1402 BIOS)AMD Family 17h32768MBSamsung SSD 970 EVO 500GBAMD Radeon RX Vega 8192MBRealtek ALC1220ASUS VP28UIntel I211 Gigabit Connection + Qualcomm Atheros QCA6174 802.11ac WirelessUbuntu 18.044.18.0-999-generic (x86_64) 20180818GNOME Shell 3.28.2X Server 1.19.6amdgpu 18.0.14.5 Mesa 18.0.5 (LLVM 6.0.0)GCC 7.3.0ext43840x2160OpenBenchmarking.orgCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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-as=/usr/bin/x86_64-linux-gnu-as --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-ld=/usr/bin/x86_64-linux-gnu-ld --with-multilib-list=m32,m64,mx32 --with-target-system-zlib --with-tune=generic --without-cuda-driver -v Processor Details- CPUFreq Conservative: Scaling Governor: acpi-cpufreq conservative- CPUFreq Ondemand: Scaling Governor: acpi-cpufreq ondemand- CPUFreq Performance: Scaling Governor: acpi-cpufreq performance- CPUFreq Powersave: Scaling Governor: acpi-cpufreq powersave- CPUFreq Schedutil: Scaling Governor: acpi-cpufreq schedutilPython Details- Python 2.7.15rc1 + Python 3.6.5Security Details- __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp Protection

Threadripper 2990WX CPU Frequency Scaling Governor Testshint: DOUBLEradiance: Serialvpxenc: vpxencindigobench: Supercarindigobench: Bedroomblender: Barbershop - CPU-Onlycompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19compress-7zip: Compress Speed Testradiance: SMP Parallelbuild-llvm: Time To Compilebuild-linux-kernel: Time To Compilegraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: HWB Color Spacex265: H.265 Video Encodingpybench: Total For Average Test Timesttsiod-renderer: Phong Rendering With Soft-Shadow Mappingscikit-learn: aircrack-ng: c-ray: Total Time - 4K, 16 Rays Per Pixelm-queens: Time To Solvephpbench: PHP Benchmark Suiteopenssl: RSA 4096-bit Performancesysbench: CPUdarktable: Boat - CPU-onlydarktable: Masskrug - CPU-onlydarktable: Server Room - CPU-onlyx264: H.264 Video Encodingdarktable: Server Rack - CPU-onlyCPUFreq ConservativeCPUFreq OndemandCPUFreq PerformanceCPUFreq PowersaveCPUFreq Schedutil788101913.93791.4915.896.823.13400.12124.7186448255.27221.7531.7124024927311.691585516.0225.805106524.6324.605161045866.3056694.088.815.712.51141.610.15801994967.96772.4615.846.672.94405.19124.6180489242.21230.3431.5724224827111.871582543.0125.745111224.5424.725133205863.6056691.429.015.712.56143.550.14731684229.79773.8216.006.803.04402.36124.8281517244.76214.0730.9624424927512.521579574.5125.765123524.5824.705166365867.2056719.828.645.732.75157.880.16402546158.211474.978.435.582.72552.70179.7468048455.60276.6443.751371341507.603018484.0948.303336336.8638.402677803793.3336594.269.727.403.20103.650.18749844642.13773.7715.966.813.21403.51124.5182186247.20219.7131.7123625027410.761580517.2026.155106624.5924.665126375856.1756624.118.725.862.70132.800.17OpenBenchmarking.org

Hierarchical INTegration

Test: DOUBLE

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: DOUBLECPUFreq OndemandCPUFreq ConservativeCPUFreq SchedutilCPUFreq PerformanceCPUFreq Powersave200M400M600M800M1000MSE +/- 11165311.19, N = 3SE +/- 10845446.00, N = 9SE +/- 1584437.26, N = 3SE +/- 6223379.87, N = 3SE +/- 606823.76, N = 3801994967.96788101913.93749844642.13731684229.79402546158.211. (CC) gcc options: -O3 -march=native -lm

Radiance Benchmark

Test: Serial

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SerialCPUFreq OndemandCPUFreq SchedutilCPUFreq PerformanceCPUFreq ConservativeCPUFreq Powersave30060090012001500772.46773.77773.82791.491474.97

VP9 libvpx Encoding

vpxenc

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.7.0vpxencCPUFreq PerformanceCPUFreq SchedutilCPUFreq ConservativeCPUFreq OndemandCPUFreq Powersave48121620SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 316.0015.9615.8915.848.431. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE

IndigoBench

Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: SupercarCPUFreq ConservativeCPUFreq SchedutilCPUFreq PerformanceCPUFreq OndemandCPUFreq Powersave246810SE +/- 0.12, N = 12SE +/- 0.12, N = 12SE +/- 0.12, N = 12SE +/- 0.11, N = 12SE +/- 0.04, N = 36.826.816.806.675.58

IndigoBench

Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: BedroomCPUFreq SchedutilCPUFreq ConservativeCPUFreq PerformanceCPUFreq OndemandCPUFreq Powersave0.72231.44462.16692.88923.6115SE +/- 0.07, N = 12SE +/- 0.07, N = 12SE +/- 0.08, N = 11SE +/- 0.08, N = 12SE +/- 0.04, N = 33.213.133.042.942.72

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-OnlyCPUFreq ConservativeCPUFreq PerformanceCPUFreq SchedutilCPUFreq OndemandCPUFreq Powersave120240360480600400.12402.36403.51405.19552.70

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19CPUFreq SchedutilCPUFreq OndemandCPUFreq ConservativeCPUFreq PerformanceCPUFreq Powersave4080120160200SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.35, N = 3124.51124.61124.71124.82179.741. (CC) gcc options: -O3 -pthread -lz -llzma

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestCPUFreq ConservativeCPUFreq SchedutilCPUFreq PerformanceCPUFreq OndemandCPUFreq Powersave20K40K60K80K100KSE +/- 1206.10, N = 3SE +/- 1295.83, N = 3SE +/- 1842.64, N = 10SE +/- 1199.48, N = 5SE +/- 943.67, N = 386448821868151780489680481. (CXX) g++ options: -pipe -lpthread

Radiance Benchmark

Test: SMP Parallel

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP ParallelCPUFreq OndemandCPUFreq PerformanceCPUFreq SchedutilCPUFreq ConservativeCPUFreq Powersave100200300400500242.21244.76247.20255.27455.60

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileCPUFreq PerformanceCPUFreq SchedutilCPUFreq ConservativeCPUFreq OndemandCPUFreq Powersave60120180240300214.07219.71221.75230.34276.64

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To CompileCPUFreq PerformanceCPUFreq OndemandCPUFreq ConservativeCPUFreq SchedutilCPUFreq Powersave1020304050SE +/- 0.41, N = 6SE +/- 0.39, N = 8SE +/- 0.40, N = 7SE +/- 0.44, N = 6SE +/- 0.58, N = 730.9631.5731.7131.7143.75

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SwirlCPUFreq PerformanceCPUFreq OndemandCPUFreq ConservativeCPUFreq SchedutilCPUFreq Powersave50100150200250SE +/- 1.20, N = 3SE +/- 1.20, N = 3SE +/- 0.67, N = 32442422402361371. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: RotateCPUFreq SchedutilCPUFreq PerformanceCPUFreq ConservativeCPUFreq OndemandCPUFreq Powersave50100150200250SE +/- 0.33, N = 32502492492481341. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color SpaceCPUFreq PerformanceCPUFreq SchedutilCPUFreq ConservativeCPUFreq OndemandCPUFreq Powersave60120180240300SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 32752742732711501. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

x265

H.265 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 2.8H.265 Video EncodingCPUFreq PerformanceCPUFreq OndemandCPUFreq ConservativeCPUFreq SchedutilCPUFreq Powersave3691215SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 312.5211.8711.6910.767.601. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesCPUFreq PerformanceCPUFreq SchedutilCPUFreq OndemandCPUFreq ConservativeCPUFreq Powersave6001200180024003000SE +/- 2.91, N = 3SE +/- 1.86, N = 3SE +/- 2.19, N = 315791580158215853018

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingCPUFreq PerformanceCPUFreq OndemandCPUFreq SchedutilCPUFreq ConservativeCPUFreq Powersave120240360480600SE +/- 9.57, N = 4SE +/- 10.56, N = 3SE +/- 8.75, N = 3SE +/- 6.24, N = 3SE +/- 4.21, N = 3574.51543.01517.20516.02484.091. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1CPUFreq OndemandCPUFreq PerformanceCPUFreq ConservativeCPUFreq SchedutilCPUFreq Powersave1122334455SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 325.7425.7625.8026.1548.30

Aircrack-ng

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.3CPUFreq PerformanceCPUFreq OndemandCPUFreq SchedutilCPUFreq ConservativeCPUFreq Powersave11K22K33K44K55KSE +/- 126.60, N = 3SE +/- 81.03, N = 3SE +/- 99.93, N = 3SE +/- 24.34, N = 3SE +/- 31.33, N = 351235511125106651065333631. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -lpthread -lcrypto -lz -ldl -lm -pthread

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelCPUFreq OndemandCPUFreq PerformanceCPUFreq SchedutilCPUFreq ConservativeCPUFreq Powersave816243240SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 324.5424.5824.5924.6336.861. (CC) gcc options: -lm -lpthread -O3

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.1Time To SolveCPUFreq ConservativeCPUFreq SchedutilCPUFreq PerformanceCPUFreq OndemandCPUFreq Powersave918273645SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 324.6024.6624.7024.7238.401. (CXX) g++ options: -fopenmp -O2 -march=native

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteCPUFreq PerformanceCPUFreq ConservativeCPUFreq OndemandCPUFreq SchedutilCPUFreq Powersave110K220K330K440K550KSE +/- 2222.72, N = 3SE +/- 2871.15, N = 3SE +/- 1378.21, N = 3SE +/- 4791.26, N = 3SE +/- 552.36, N = 3516636516104513320512637267780

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.0fRSA 4096-bit PerformanceCPUFreq PerformanceCPUFreq ConservativeCPUFreq OndemandCPUFreq SchedutilCPUFreq Powersave13002600390052006500SE +/- 5.62, N = 3SE +/- 1.97, N = 3SE +/- 5.93, N = 3SE +/- 7.69, N = 3SE +/- 3.20, N = 35867.205866.305863.605856.173793.331. (CC) gcc options: -O3 -pthread -m64 -lssl -lcrypto -ldl

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPUCPUFreq PerformanceCPUFreq ConservativeCPUFreq OndemandCPUFreq SchedutilCPUFreq Powersave12K24K36K48K60KSE +/- 23.68, N = 3SE +/- 61.08, N = 3SE +/- 116.65, N = 3SE +/- 86.20, N = 3SE +/- 22.29, N = 356719.8256694.0856691.4256624.1136594.261. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm

Darktable

Test: Boat - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Boat - Acceleration: CPU-onlyCPUFreq PerformanceCPUFreq SchedutilCPUFreq ConservativeCPUFreq OndemandCPUFreq Powersave3691215SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.08, N = 38.648.728.819.019.72

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Masskrug - Acceleration: CPU-onlyCPUFreq ConservativeCPUFreq OndemandCPUFreq PerformanceCPUFreq SchedutilCPUFreq Powersave246810SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 4SE +/- 0.10, N = 3SE +/- 0.09, N = 35.715.715.735.867.40

Darktable

Test: Server Room - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Server Room - Acceleration: CPU-onlyCPUFreq ConservativeCPUFreq OndemandCPUFreq SchedutilCPUFreq PerformanceCPUFreq Powersave0.721.442.162.883.6SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 9SE +/- 0.04, N = 3SE +/- 0.05, N = 42.512.562.702.753.20

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-07-28H.264 Video EncodingCPUFreq PerformanceCPUFreq OndemandCPUFreq ConservativeCPUFreq SchedutilCPUFreq Powersave306090120150SE +/- 1.68, N = 3SE +/- 1.45, N = 3SE +/- 2.09, N = 5SE +/- 2.59, N = 3SE +/- 1.98, N = 3157.88143.55141.61132.80103.651. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

Darktable

Test: Server Rack - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Server Rack - Acceleration: CPU-onlyCPUFreq OndemandCPUFreq ConservativeCPUFreq PerformanceCPUFreq SchedutilCPUFreq Powersave0.04050.0810.12150.1620.2025SE +/- 0.00, N = 6SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 9SE +/- 0.00, N = 30.140.150.160.170.18

Phoronix Test Suite v10.8.4