Threadripper 2990WX Thread Scaling

AMD Ryzen Threadripper 2990WX 32-Core testing with different core/thread counts. Benchmarks by Michael Larabel for a future article on Phoronix.

HTML result view exported from: https://openbenchmarking.org/result/1808163-RA-TR2SCALIN95&sro&grw.

Threadripper 2990WX Thread ScalingProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution1 Thread2 Threads4 Threads8 Threads16 Threads32 Threads64 ThreadsAMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (1 Core)ASUS ROG ZENITH EXTREME (0064 BIOS)AMD Family 17h32768MBSamsung SSD 970 EVO 500GBAMD Radeon RX Vega 8192MBRealtek ALC1220DELL P2415QIntel I211 Gigabit Connection + Qualcomm Atheros QCA6174 802.11ac WirelessUbuntu 18.044.18.0-999-generic (x86_64) 20180805GNOME Shell 3.28.2X Server 1.19.6amdgpu 18.0.14.5 Mesa 18.0.5 (LLVM 6.0.0)GCC 7.3.0ext43840x2160AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (2 Cores)AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (4 Cores)AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (8 Cores)AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (16 Cores)AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores)AMD Radeon RX Vega 8064MBAMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)AMD Radeon RX Vega 8192MBOpenBenchmarking.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- Scaling Governor: acpi-cpufreq ondemandGraphics Details- GLAMORSecurity Details- __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp Protection

Threadripper 2990WX Thread Scalingnpb: EP.Cstockfish: Total Timejohn-the-ripper: Blowfishasmfish: 1024 Hash Memory, 26 Depthm-queens: Time To Solvebuild-linux-kernel: Time To Compilesysbench: CPUc-ray: Total Time - 4K, 16 Rays Per Pixelv-ray: CPUblender: Barbershop - CPU-Onlypovray: Trace Timeindigobench: Bedroomindigobench: Supercaropenssl: RSA 4096-bit Performanceebizzy: 1 Thread2 Threads4 Threads8 Threads16 Threads32 Threads64 Threads42.08234176416602589854892.50625.132065.06655.74761.83538.040.110.25212.679099684.13464735133065153369447.21320.884136.77327.35381.55267.950.230.51422.73177694160.75896390660369672981235.56171.227880.26172.28204.043276.02141.320.430.97811.33343462313.3216545321881118055501121.7892.0315350.9388.31108.601801.1873.360.781.741582.67671058594.5029758991148103295562365.3054.3029095.4346.5960.26982.1639.181.433.163002.2711452951092.6553378671309115905866336.3435.2553346.1925.5635.90553.2422.512.575.675514.6015554722160.7566760558446827672805724.7931.7256727.7824.6330.75402.2517.383.076.565869.631367717OpenBenchmarking.org

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: EP.C1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads5001000150020002500SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.29, N = 3SE +/- 0.17, N = 3SE +/- 0.02, N = 3SE +/- 1.71, N = 3SE +/- 0.09, N = 342.08594.5084.131092.65160.752160.75313.321. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 2.1.1

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads14M28M42M56M70MSE +/- 2751.54, N = 3SE +/- 86990.41, N = 3SE +/- 21923.77, N = 3SE +/- 217995.10, N = 3SE +/- 71881.58, N = 3SE +/- 651663.27, N = 3SE +/- 86158.77, N = 3234176429758991464735153378671896390666760558165453211. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Blowfish1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads10K20K30K40K50KSE +/- 18.33, N = 3SE +/- 14.17, N = 3SE +/- 14.73, N = 3SE +/- 565.26, N = 3SE +/- 74.63, N = 3SE +/- 245.29, N = 3SE +/- 372.22, N = 616601481033063091160364468288111. (CC) gcc options: -lssl -lcrypto -fopenmp -pthread -lm -lz -ldl -lcrypt -lbz2

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2017-09-191024 Hash Memory, 26 Depth1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads16M32M48M64M80MSE +/- 619.33, N = 3SE +/- 313307.04, N = 3SE +/- 44526.21, N = 3SE +/- 116017.90, N = 3SE +/- 67053.30, N = 3SE +/- 298662.02, N = 3SE +/- 133076.25, N = 325898543295562351533695905866396729817672805718055501

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.1Time To Solve1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads2004006008001000SE +/- 0.27, N = 3SE +/- 0.02, N = 3SE +/- 0.22, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3892.5065.30447.2136.34235.5624.79121.781. (CXX) g++ options: -fopenmp -O2 -march=native

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To Compile1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads130260390520650SE +/- 0.88, N = 3SE +/- 0.87, N = 3SE +/- 0.79, N = 3SE +/- 0.47, N = 6SE +/- 0.92, N = 3SE +/- 0.43, N = 6SE +/- 0.98, N = 3625.1354.30320.8835.25171.2231.7292.03

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPU1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads12K24K36K48K60KSE +/- 0.87, N = 3SE +/- 8.26, N = 3SE +/- 0.73, N = 3SE +/- 32.79, N = 3SE +/- 1.58, N = 3SE +/- 65.28, N = 3SE +/- 5.20, N = 32065.0629095.434136.7753346.197880.2656727.7815350.931. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads140280420560700SE +/- 0.65, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.06, N = 3SE +/- 0.29, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3655.7446.59327.3525.56172.2824.6388.311. (CC) gcc options: -lm -lpthread -O3

Chaos Group V-RAY

Mode: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterChaos Group V-RAY 1.1.0Mode: CPU1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads160320480640800SE +/- 1.89, N = 3SE +/- 0.16, N = 3SE +/- 1.08, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.34, N = 3761.8360.26381.5535.90204.0430.75108.60

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-Only16 Threads32 Threads4 Threads64 Threads8 Threads7001400210028003500982.16553.243276.02402.251801.18

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads120240360480600SE +/- 0.57, N = 3SE +/- 0.02, N = 3SE +/- 0.46, N = 3SE +/- 0.15, N = 3SE +/- 0.63, N = 3SE +/- 0.05, N = 3SE +/- 0.43, N = 3538.0439.18267.9522.51141.3217.3873.361. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

IndigoBench

Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Bedroom1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads0.69081.38162.07242.76323.454SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.12, N = 6SE +/- 0.00, N = 30.111.430.232.570.433.070.78

IndigoBench

Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Supercar1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.20, N = 6SE +/- 0.00, N = 30.253.160.515.670.976.561.74

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.0fRSA 4096-bit Performance1 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads13002600390052006500SE +/- 0.09, N = 3SE +/- 0.23, N = 3SE +/- 3.02, N = 3SE +/- 2.44, N = 3SE +/- 0.24, N = 3SE +/- 1.87, N = 3SE +/- 0.38, N = 3212.673002.27422.735514.60811.335869.631582.671. (CC) gcc options: -O3 -pthread -m64 -lssl -lcrypto -ldl

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.31 Thread16 Threads2 Threads32 Threads4 Threads64 Threads8 Threads300K600K900K1200K1500KSE +/- 250.34, N = 3SE +/- 1118.92, N = 3SE +/- 3326.82, N = 3SE +/- 22021.37, N = 6SE +/- 282.86, N = 3SE +/- 24098.90, N = 6SE +/- 738.51, N = 3909961145295177694155547234346213677176710581. (CC) gcc options: -pthread -lpthread -O3 -march=native

Phoronix Test Suite v10.8.4