Clang znver1 Scheduler Model Tests

AMD Ryzen 7 1700 Eight-Core testing with the new Zen znver1 scheduler model. Tests by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1707198-TR-CLANGZNVE46&grr&rdt.

ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay DriverCompilerFile-SystemScreen ResolutionClang 4.0Clang SVN -O3 -march=znver1 -O3 -march=x86-64 -O3 -march=x86-64 -O3 -march=znver1AMD Ryzen 7 1700 Eight-Core @ 3.00GHz (16 Cores)MSI B350 TOMAHAWK (MS-7A34) v1.0AMD Device 145016384MB120GB Samsung SSD 840HIS AMD Radeon HD 7750/8740 / R7 250E 1024MBAMD Cape Verde/PitcairnRealtek RTL8111/8168/8411Ubuntu 17.044.12.0-999-generic (x86_64) 20170622Unity 7.5.0modesetting 1.19.3Clang 4.0.0-1ubuntu1ext41024x768Clang 6.0.0 (SVN 308494)OpenBenchmarking.orgProcessor Details- Scaling Governor: acpi-cpufreq ondemandCompiler Details- Clang SVN: -O3 -march=x86-64, Clang SVN: -O3 -march=znver1: Optimized build; Default target: x86_64-unknown-linux-gnu; Host CPU: znver1

apache: Static Web Page Servinghint: FLOATredis: SETredis: GETredis: LPOPpgbench: Buffer Test - Heavy Contention - Read Writepgbench: Buffer Test - Single Thread - Read Writepgbench: Buffer Test - Normal Load - Read Writetjbench: Decompression Throughputtachyon: Total Timeencode-wavpack: WAV To WavPackencode-mp3: WAV To MP3encode-flac: WAV To FLACbullet: Convex Trimeshbullet: Prim Trimeshbullet: 136 Ragdollsbullet: 1000 Convexbullet: 1000 Stackbullet: 3000 Fallbullet: Raytestsstockfish: Total Timec-ray: Total Timeebizzy: himeno: Poisson Pressure Solvergraphics-magick: Local Adaptive Thresholdinggraphics-magick: HWB Color Spacegraphics-magick: Resizinggraphics-magick: Sharpengraphics-magick: Blurx264: H.264 Video Encodingtscp: AI Chess Performancescimark2: Jacobi Successive Over-Relaxationscimark2: Dense LU Matrix Factorizationscimark2: Sparse Matrix Multiplyscimark2: Fast Fourier Transformscimark2: Monte Carloscimark2: Compositefftw: Float + SSE - 2D FFT Size 4096Clang 4.0Clang SVN -O3 -march=znver1 -O3 -march=x86-64 -O3 -march=x86-64 -O3 -march=znver126808.65301686748.921400655.091896426.081908429.462061.89226.211938.55166.395.256.4410.745.721.170.992.934.695.144.532.79367114.624068021115.3613414813560101252.7310199641677.135792.782616.81135.84651.732174.861307227221.41301996595.091415121.331900142.801890860.672021.12226.161899.66163.715.236.509.626.771.190.992.974.895.334.622.85370414.724082781114.0313316313257105252.2110547301675.635534.542654.48134.39623.662124.541297526994.80301795000.851385134.041953368.381968693.381938.93226.041865.09161.785.296.529.756.771.201.002.964.845.274.622.86371013.684085091110.92133173137136252.3311033311675.035572.722623.75133.36642.552129.481369027700.93300351844.051413713.291973143.291960971.501875.27224.891813.34165.305.296.4510.925.691.160.992.934.645.104.532.78367013.623829601022.65136178139140252.5210963031679.215692.832597.54134.24657.962152.3613398OpenBenchmarking.org

Apache Benchmark

Static Web Page Serving

Clang 4.0Clang SVNOpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.7Static Web Page Serving-O3 -march=znver1-O3 -march=x86-646K12K18K24K30KSE +/- 228.50, N = 3SE +/- 320.32, N = 3SE +/- 179.13, N = 3SE +/- 44.40, N = 326808.6527221.4126994.8027700.931. (CC) gcc options: -shared -fPIC -pthread -O3

Hierarchical INTegration

Test: FLOAT

Clang 4.0Clang SVNOpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOAT-O3 -march=znver1-O3 -march=x86-6460M120M180M240M300MSE +/- 359206.87, N = 3SE +/- 176504.67, N = 3SE +/- 120507.74, N = 3SE +/- 20484.23, N = 3301686748.92301996595.09301795000.85300351844.051. (CC) gcc options: -O3 -lm

Redis

Test: SET

Clang 4.0Clang SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SET-O3 -march=znver1-O3 -march=x86-64300K600K900K1200K1500KSE +/- 8135.91, N = 3SE +/- 4364.72, N = 3SE +/- 8018.20, N = 3SE +/- 23768.12, N = 61400655.091415121.331385134.041413713.291. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl

Redis

Test: GET

Clang 4.0Clang SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GET-O3 -march=znver1-O3 -march=x86-64400K800K1200K1600K2000KSE +/- 9354.06, N = 3SE +/- 29446.39, N = 5SE +/- 15420.28, N = 3SE +/- 27406.80, N = 31896426.081900142.801953368.381973143.291. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl

Redis

Test: LPOP

Clang 4.0Clang SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPOP-O3 -march=znver1-O3 -march=x86-64400K800K1200K1600K2000KSE +/- 5577.00, N = 3SE +/- 21807.56, N = 3SE +/- 13701.81, N = 3SE +/- 13594.16, N = 31908429.461890860.671968693.381960971.501. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl

PostgreSQL pgbench

Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write

Clang 4.0Clang SVNOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 9.6.3Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write-O3 -march=znver1-O3 -march=x86-64400800120016002000SE +/- 36.47, N = 6SE +/- 7.18, N = 3SE +/- 30.24, N = 3SE +/- 30.52, N = 42061.892021.121938.931875.271. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -fpic -shared

PostgreSQL pgbench

Scaling: Buffer Test - Test: Single Thread - Mode: Read Write

Clang 4.0Clang SVNOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 9.6.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Write-O3 -march=znver1-O3 -march=x86-6450100150200250SE +/- 0.63, N = 3SE +/- 0.18, N = 3SE +/- 0.39, N = 3SE +/- 1.25, N = 3226.21226.16226.04224.891. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -fpic -shared

PostgreSQL pgbench

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

Clang 4.0Clang SVNOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 9.6.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Write-O3 -march=znver1-O3 -march=x86-64400800120016002000SE +/- 30.13, N = 3SE +/- 33.75, N = 6SE +/- 47.88, N = 6SE +/- 52.04, N = 61938.551899.661865.091813.341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -fpic -shared

libjpeg-turbo tjbench

Test: Decompression Throughput

Clang 4.0Clang SVNOpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.1Test: Decompression Throughput-O3 -march=znver1-O3 -march=x86-644080120160200SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.07, N = 3166.39163.71161.78165.301. (CC) gcc options: -O3 -lm

Tachyon

Total Time

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total Time-O3 -march=znver1-O3 -march=x86-641.19032.38063.57094.76125.9515SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 35.255.235.295.291. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

WavPack Audio Encoding

WAV To WavPack

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.1WAV To WavPack-O3 -march=znver1-O3 -march=x86-64246810SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 56.446.506.526.451. (CC) gcc options: -O3 -lm

LAME MP3 Encoding

WAV To MP3

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3-O3 -march=znver1-O3 -march=x86-643691215SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 510.749.629.7510.921. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm

FLAC Audio Encoding

WAV To FLAC

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.1WAV To FLAC-O3 -march=znver1-O3 -march=x86-64246810SE +/- 0.06, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 55.726.776.775.691. (CXX) g++ options: -O3 -logg -lm

Bullet Physics Engine

Test: Convex Trimesh

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex Trimesh-O3 -march=znver1-O3 -march=x86-640.270.540.811.081.35SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.171.191.201.161. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Prim Trimesh

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim Trimesh-O3 -march=znver1-O3 -march=x86-640.2250.450.6750.91.125SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.990.991.000.991. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 136 Ragdolls

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 Ragdolls-O3 -march=znver1-O3 -march=x86-640.66831.33662.00492.67323.3415SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.932.972.962.931. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Convex

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Convex-O3 -march=znver1-O3 -march=x86-641.10032.20063.30094.40125.5015SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.694.894.844.641. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Stack

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Stack-O3 -march=znver1-O3 -march=x86-641.19932.39863.59794.79725.9965SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.145.335.275.101. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 3000 Fall

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 Fall-O3 -march=znver1-O3 -march=x86-641.03952.0793.11854.1585.1975SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.534.624.624.531. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Raytests

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Raytests-O3 -march=znver1-O3 -march=x86-640.64351.2871.93052.5743.2175SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.792.852.862.781. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Stockfish

Total Time

Clang 4.0Clang SVNOpenBenchmarking.orgms, Fewer Is BetterStockfish 2014-11-26Total Time-O3 -march=znver1-O3 -march=x86-648001600240032004000SE +/- 12.02, N = 3SE +/- 2.96, N = 3SE +/- 1.76, N = 3SE +/- 5.03, N = 336713704371036701. (CXX) g++ options: -lpthread -O3 -fno-exceptions -fno-rtti -ansi -pedantic -msse -msse3 -mpopcnt

C-Ray

Total Time

Clang 4.0Clang SVNOpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time-O3 -march=znver1-O3 -march=x86-6448121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 314.6214.7213.6813.621. (CC) gcc options: -lm -lpthread -O3

ebizzy

Clang 4.0Clang SVNOpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3-O3 -march=znver1-O3 -march=x86-6490K180K270K360K450KSE +/- 4344.35, N = 3SE +/- 6544.76, N = 4SE +/- 4432.38, N = 3SE +/- 5536.66, N = 64068024082784085093829601. (CC) gcc options: -pthread -lpthread -O3

Himeno Benchmark

Poisson Pressure Solver

Clang 4.0Clang SVNOpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-O3 -march=znver1-O3 -march=x86-642004006008001000SE +/- 6.87, N = 3SE +/- 0.52, N = 3SE +/- 1.19, N = 3SE +/- 5.42, N = 31115.361114.031110.921022.651. (CC) gcc options: -O3 -mavx2

GraphicsMagick

Operation: Local Adaptive Thresholding

Clang 4.0Clang SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Local Adaptive Thresholding-O3 -march=znver1-O3 -march=x86-643060901201501341331331361. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

GraphicsMagick

Operation: HWB Color Space

Clang 4.0Clang SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: HWB Color Space-O3 -march=znver1-O3 -march=x86-644080120160200SE +/- 0.33, N = 31481631731781. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Resizing-O3 -march=znver1-O3 -march=x86-64306090120150SE +/- 0.33, N = 3135132-march=znver1-march=x86-641. (CC) gcc options: -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

Clang 4.0Clang SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Sharpen-O3 -march=znver1-O3 -march=x86-64306090120150SE +/- 0.33, N = 360571371391. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

GraphicsMagick

Operation: Blur

Clang 4.0Clang SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Blur-O3 -march=znver1-O3 -march=x86-643060901201501011051361401. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

x264

H.264 Video Encoding

Clang 4.0Clang SVNOpenBenchmarking.orgFrames Per Second, More Is Betterx264 2017-05-19H.264 Video Encoding-O3 -march=znver1-O3 -march=x86-6460120180240300SE +/- 1.15, N = 5SE +/- 0.72, N = 5SE +/- 0.34, N = 5SE +/- 0.68, N = 5252.73252.21252.33252.521. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fomit-frame-pointer -fno-tree-vectorize

TSCP

AI Chess Performance

Clang 4.0Clang SVNOpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performance-O3 -march=znver1-O3 -march=x86-64200K400K600K800K1000KSE +/- 1196.29, N = 5SE +/- 987.82, N = 5SE +/- 1625.76, N = 5SE +/- 1629.46, N = 510199641054730110333110963031. (CC) gcc options: -O3

SciMark

Computational Test: Jacobi Successive Over-Relaxation

Clang 4.0Clang SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxation-O3 -march=znver1-O3 -march=x86-64400800120016002000SE +/- 0.75, N = 4SE +/- 0.35, N = 4SE +/- 0.35, N = 4SE +/- 0.50, N = 41677.131675.631675.031679.211. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Dense LU Matrix Factorization

Clang 4.0Clang SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorization-O3 -march=znver1-O3 -march=x86-6412002400360048006000SE +/- 36.57, N = 4SE +/- 49.61, N = 4SE +/- 14.40, N = 4SE +/- 16.27, N = 45792.785534.545572.725692.831. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Sparse Matrix Multiply

Clang 4.0Clang SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiply-O3 -march=znver1-O3 -march=x86-646001200180024003000SE +/- 3.22, N = 4SE +/- 3.12, N = 4SE +/- 4.33, N = 4SE +/- 5.05, N = 42616.812654.482623.752597.541. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Fast Fourier Transform

Clang 4.0Clang SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform-O3 -march=znver1-O3 -march=x86-64306090120150SE +/- 0.22, N = 4SE +/- 0.28, N = 4SE +/- 0.55, N = 4SE +/- 0.63, N = 4135.84134.39133.36134.241. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Monte Carlo

Clang 4.0Clang SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlo-O3 -march=znver1-O3 -march=x86-64140280420560700SE +/- 0.07, N = 4SE +/- 0.39, N = 4SE +/- 0.08, N = 4SE +/- 0.67, N = 4651.73623.66642.55657.961. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Composite

Clang 4.0Clang SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Composite-O3 -march=znver1-O3 -march=x86-645001000150020002500SE +/- 6.84, N = 4SE +/- 10.27, N = 4SE +/- 2.34, N = 4SE +/- 2.54, N = 42174.862124.542129.482152.361. (CC) gcc options: -O3 -lm

FFTW

Build: Float + SSE - Size: 2D FFT Size 4096

Clang 4.0Clang SVNOpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.4Build: Float + SSE - Size: 2D FFT Size 4096-O3 -march=znver1-O3 -march=x86-643K6K9K12K15KSE +/- 75.88, N = 5SE +/- 25.06, N = 5SE +/- 12.52, N = 5SE +/- 55.71, N = 5130721297513690133981. (CC) gcc options: -O3 -lm

Phoronix Test Suite v10.8.5