Threadripper 2 Memory Benchmarks

Benchmarks by Michael Larabel.

HTML result view exported from: https://openbenchmarking.org/result/1810310-PTS-THREADRI99&grt.

Threadripper 2 Memory BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen Resolution4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)ASUS ROG ZENITH EXTREME (1501 BIOS)AMD Family 17h32768MBSamsung SSD 970 EVO 500GBAMD Radeon RX Vega 8GBRealtek ALC1220ASUS VP28UIntel I211 Gigabit Connection + Qualcomm Atheros QCA6174 802.11ac WirelessUbuntu 18.044.19.0-041900-generic (x86_64)GNOME Shell 3.28.3X Server 1.19.6amdgpu 18.1.994.5 Mesa 18.3.0-devel- padoka PPA (LLVM 8.0.0)1.1.86GCC 7.3.0ext43840x216016384MBOpenBenchmarking.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-default-libstdcxx-abi=new --with-gcc-major-version-only --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- GLAMORPython Details- Python 2.7.15rc1 + Python 3.6.6Security Details- __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp

Threadripper 2 Memory Benchmarkscompress-7zip: Compress Speed Testblender: Barbershop - CPU-Onlybrl-cad: VGR Performance Metricdarktable: Boat - CPU-onlydarktable: Masskrug - CPU-onlyetlegacy: Renderer2 - 3840 x 2160indigobench: Bedroomm-queens: Time To Solvembw: Memory Copy, Fixed Block Size - 4096 MiBnamd: ATPase Simulation - 327,506 Atomsnode-express-loadtest: opencv-bench: osbench: Memory Allocationsparboil: OpenMP LBMparboil: OpenMP Stencilparboil: OpenMP MRI Griddingpgbench: Buffer Test - Normal Load - Read Onlypgbench: Buffer Test - Normal Load - Read Writeramspeed: Copy - Integerramspeed: Triad - Integerrodinia: OpenMP Streamclusterstream: Copystream: Triadstream: Addsysbench: Memorytensorflow: Cifar10tesseract: 3840 x 2160tesseract-ocr: Time To OCR 7 Imagesbuild-linux-kernel: Time To Compilebuild-llvm: Time To Compilettsiod-renderer: Phong Rendering With Soft-Shadow Mapping4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200824734102939329.086.071872.9521.3983600.75906751789.5770.7386.7814.9127645217716764350743402527.33577534056940853725354447.9927631.6534.91235530773984092873428.995.651832.9521.1475420.75265734188.0072.7293.7816.1327743924116730326553059128.58560793928439661696528448.6526831.9435.03224522804594102892099.656.051822.8521.1671510.75566740089.2474.6188.9017.0728142273216397275472719132.33526513729937710650371850.9826332.3235.802264874288245729013518.197.231791.7821.3279371.14460741786.7770.65164.4023.6327133079113281258132493034.87269661876318745733961568.4626131.5166.41504OpenBenchmarking.org

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320020K40K60K80K100KSE +/- 1312.92, N = 12SE +/- 847.29, N = 3SE +/- 1379.64, N = 3SE +/- 77.72, N = 3824737739880459428821. (CXX) g++ options: -pipe -lpthread

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-Only4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200100200300400500410409410457

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.28.0VGR Performance Metric4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320060K120K180K240K300K2939322873422892092901351. (CXX) g++ options: -std=c++98 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lX11 -lXext -lXrender -lpthread -ldl -lm

Darktable

Test: Boat - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Boat - Acceleration: CPU-only4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320048121620SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 39.088.999.6518.19

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.2Test: Masskrug - Acceleration: CPU-only4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200246810SE +/- 0.06, N = 3SE +/- 0.08, N = 5SE +/- 0.07, N = 12SE +/- 0.10, N = 66.075.656.057.23

ET: Legacy

Renderer: Renderer2 - Resolution: 3840 x 2160

OpenBenchmarking.orgFrames Per Second, More Is BetterET: Legacy 2.75Renderer: Renderer2 - Resolution: 3840 x 21604 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32004080120160200SE +/- 2.01, N = 10SE +/- 3.41, N = 3SE +/- 2.18, N = 12SE +/- 0.56, N = 3187183182179

IndigoBench

Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Bedroom4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32000.66381.32761.99142.65523.319SE +/- 0.09, N = 12SE +/- 0.06, N = 12SE +/- 0.07, N = 12SE +/- 0.00, N = 32.952.952.851.78

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200510152025SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 321.3921.1421.1621.321. (CXX) g++ options: -fopenmp -O2 -march=native

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32002K4K6K8K10KSE +/- 18.19, N = 3SE +/- 122.58, N = 3SE +/- 80.49, N = 3SE +/- 110.11, N = 383607542715179371. (CC) gcc options: -O3 -march=native

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 Atoms4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32000.25750.5150.77251.031.2875SE +/- 0.00102, N = 3SE +/- 0.00096, N = 3SE +/- 0.00192, N = 3SE +/- 0.00149, N = 30.759060.752650.755661.14460

Node.js Express HTTP Load Test

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load Test4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320016003200480064008000SE +/- 118.94, N = 3SE +/- 70.18, N = 3SE +/- 24.88, N = 3SE +/- 40.67, N = 375177341740074171. Nodejs v8.10.0

OpenCV Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenCV Benchmark 3.3.04 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320020406080100SE +/- 0.40, N = 3SE +/- 0.44, N = 3SE +/- 0.25, N = 3SE +/- 1.43, N = 389.5788.0089.2486.771. (CXX) g++ options: -std=c++11 -rdynamic

OSBench

Test: Memory Allocations

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320020406080100SE +/- 0.36, N = 3SE +/- 0.15, N = 3SE +/- 0.07, N = 3SE +/- 0.39, N = 370.7372.7274.6170.651. (CC) gcc options: -lm

Parboil

Test: OpenMP LBM

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBM4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32004080120160200SE +/- 1.42, N = 12SE +/- 2.25, N = 12SE +/- 0.69, N = 3SE +/- 0.07, N = 386.7893.7888.90164.401. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Parboil

Test: OpenMP Stencil

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP Stencil4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200612182430SE +/- 0.26, N = 12SE +/- 0.55, N = 12SE +/- 0.63, N = 12SE +/- 0.34, N = 514.9116.1317.0723.631. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Parboil

Test: OpenMP MRI Gridding

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI Gridding4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320060120180240300SE +/- 0.73, N = 3SE +/- 1.36, N = 3SE +/- 0.56, N = 3SE +/- 0.62, N = 32762772812711. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Only4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200100K200K300K400K500KSE +/- 5273.97, N = 3SE +/- 1559.95, N = 3SE +/- 4070.76, N = 3SE +/- 499.51, N = 34521774392414227323307911. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Write4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32004K8K12K16K20KSE +/- 132.18, N = 3SE +/- 171.53, N = 3SE +/- 221.88, N = 3SE +/- 26.44, N = 3167641673016397132811. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integer4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32008K16K24K32K40K350743265527547258131. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Triad - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Integer4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32007K14K21K28K35K340253059127191249301. (CC) gcc options: -O3 -march=native

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP Streamcluster4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200816243240SE +/- 0.68, N = 12SE +/- 0.90, N = 12SE +/- 1.08, N = 12SE +/- 0.48, N = 627.3328.5832.3334.871. (CXX) g++ options: -O2 -lOpenCL

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320012K24K36K48K60KSE +/- 750.61, N = 5SE +/- 522.81, N = 5SE +/- 706.13, N = 6SE +/- 105.10, N = 5577535607952651269661. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triad4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32009K18K27K36K45KSE +/- 238.14, N = 5SE +/- 160.12, N = 5SE +/- 123.22, N = 5SE +/- 87.25, N = 5405693928437299187631. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32009K18K27K36K45KSE +/- 152.36, N = 5SE +/- 137.63, N = 5SE +/- 464.88, N = 5SE +/- 82.49, N = 5408533966137710187451. (CC) gcc options: -O3 -march=native -fopenmp

Sysbench

Test: Memory

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: Memory4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32001.6M3.2M4.8M6.4M8MSE +/- 2500.67, N = 3SE +/- 3873.16, N = 3SE +/- 8009.55, N = 3SE +/- 3200.47, N = 372535446965284650371873396151. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm

Tensorflow

Build: Cifar10

OpenBenchmarking.orgSeconds, Fewer Is BetterTensorflow 2017-02-03Build: Cifar104 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32001530456075SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 347.9948.6550.9868.46

Tesseract

Resolution: 3840 x 2160

OpenBenchmarking.orgFrames Per Second, More Is BetterTesseract 2014-05-12Resolution: 3840 x 21604 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-320060120180240300SE +/- 0.91, N = 3SE +/- 2.80, N = 3SE +/- 1.97, N = 3SE +/- 2.36, N = 3276268263261

Tesseract OCR

Time To OCR 7 Images

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.0.0-beta.1Time To OCR 7 Images4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200816243240SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 331.6531.9432.3231.51

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To Compile4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-32001530456075SE +/- 0.49, N = 6SE +/- 0.41, N = 8SE +/- 0.51, N = 6SE +/- 0.99, N = 334.9135.0335.8066.41

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To Compile4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-266650100150200250235224226

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow Mapping4 x 8GB DDR4-32004 x 8GB DDR4-29334 x 8GB DDR4-26662 x 8GB DDR4-3200110220330440550SE +/- 7.49, N = 6SE +/- 3.82, N = 3SE +/- 4.83, N = 3SE +/- 7.48, N = 35305224875041. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

Phoronix Test Suite v10.8.5