LLVM Clang 3.8 Compiler Benchmarks

Intel Xeon E5-2687W v3 LLVM Clang 3.6 / 3.7 / 3.8 SVN C/C++ compiler benchmarks. Tests by Michael Larabel for a future article on Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1602036-GA-LLVMCLANG84&grr&rdt.

LLVM Clang 3.8 Compiler BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionClang 3.8 SVNClang 3.7.0Clang 3.6.0Intel Xeon E5-2687W v3 @ 3.50GHz (20 Cores)MSI X99S SLI PLUS (MS-7885) v1.0Intel Xeon E7 v3/Xeon16384MBPNY CS1211 120GB + 80GB INTEL SSDSCKGW08AMD FirePro V7900 2048MBRealtek ALC892ASUS PB278Intel ConnectionUbuntu 16.044.5.0-040500rc1-generic (x86_64) 20160124Unity 7.4.0X Server 1.17.3radeon 7.6.13.3 Mesa 11.0.8 Gallium 0.4Clang 3.8.0 (SVN 259676) + LLVM 3.8.0ext42560x1440Clang 3.7.0 + LLVM 3.7.0Clang 3.6.0 + LLVM 3.6.0OpenBenchmarking.orgCompiler Details- Clang 3.8 SVN: Optimized build; Built Feb 3 2016 (13:57:10); Default target: x86_64-unknown-linux-gnu; Host CPU: haswell- Clang 3.7.0: Optimized build; Built Feb 3 2016 (14:58:25); Default target: x86_64-unknown-linux-gnu; Host CPU: haswell- Clang 3.6.0: Optimized build; Built Feb 3 2016 (16:12:29); Default target: x86_64-unknown-linux-gnu; Host CPU: core-avx2Processor Details- Scaling Governor: intel_pstate powersave

LLVM Clang 3.8 Compiler Benchmarksapache: Static Web Page Servingredis: SETredis: GETpgbench: Buffer Test - Heavy Contention - Read Writeencode-mp3: WAV To MP3encode-flac: WAV To FLACbullet: 1000 Stackbullet: 3000 Fallbullet: Raytestssmallpt: Global Illumination Renderer; 100 Samplesc-ray: Total Timebuild-php: Time To Compilebuild-apache: Time To Compilehimeno: Poisson Pressure Solvergraphics-magick: Local Adaptive Thresholdingscimark2: Jacobi Successive Over-Relaxationscimark2: Dense LU Matrix Factorizationscimark2: Sparse Matrix Multiplyscimark2: Fast Fourier Transformscimark2: Monte Carloscimark2: Compositehmmer: Pfam Database SearchClang 3.8 SVNClang 3.7.0Clang 3.6.021484.41511943.18552906.125468.8115.367.316.745.693.591313.2216.8122.241268.91801408.074806.982473.60343.69225.301851.5311.2222826.44562350.48625801.985345.6514.727.326.675.873.6615512.8415.7619.841444.58851415.374786.502484.07346.20521.711910.7713.9923551.58577378.53627746.115434.1515.687.386.445.883.5415012.6913.6717.661544.88851473.984862.282414.46362.61536.021929.8715.45OpenBenchmarking.org

Apache Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.7Static Web Page ServingClang 3.8 SVNClang 3.7.0Clang 3.6.05K10K15K20K25KSE +/- 97.80, N = 3SE +/- 180.59, N = 3SE +/- 19.77, N = 321484.4122826.4423551.581. (CC) gcc options: -shared -fPIC -pthread -O3 -march=native

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SETClang 3.8 SVNClang 3.7.0Clang 3.6.0120K240K360K480K600KSE +/- 9097.01, N = 6SE +/- 2717.97, N = 3SE +/- 10638.06, N = 6511943.18562350.48577378.531. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETClang 3.8 SVNClang 3.7.0Clang 3.6.0130K260K390K520K650KSE +/- 5597.88, N = 3SE +/- 2487.14, N = 3SE +/- 10172.04, N = 4552906.12625801.98627746.111. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 9.4.3Scaling: Buffer Test - Test: Heavy Contention - Mode: Read WriteClang 3.8 SVNClang 3.7.0Clang 3.6.012002400360048006000SE +/- 61.06, N = 3SE +/- 127.49, N = 6SE +/- 60.57, N = 35468.815345.655434.15-mthreads-mthreads1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -pthread -pthreads -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3Clang 3.8 SVNClang 3.7.0Clang 3.6.048121620SE +/- 0.09, N = 5SE +/- 0.04, N = 5SE +/- 0.13, N = 515.3614.7215.681. (CC) gcc options: -pipe -O3 -march=native -lm

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.1WAV To FLACClang 3.8 SVNClang 3.7.0Clang 3.6.0246810SE +/- 0.03, N = 5SE +/- 0.06, N = 5SE +/- 0.04, N = 57.317.327.381. (CXX) g++ options: -O3 -march=native -logg -lm

Bullet Physics Engine

Test: 1000 Stack

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 StackClang 3.8 SVNClang 3.7.0Clang 3.6.0246810SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.18, N = 36.746.676.441. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 3000 Fall

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 FallClang 3.8 SVNClang 3.7.0Clang 3.6.01.3232.6463.9695.2926.615SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 35.695.875.881. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Raytests

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: RaytestsClang 3.8 SVNClang 3.7.0Clang 3.6.00.82351.6472.47053.2944.1175SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 63.593.663.541. (CXX) g++ options: -O3 -march=native -rdynamic -lglut -lGL -lGLU

Smallpt

Global Illumination Renderer; 100 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 SamplesClang 3.8 SVNClang 3.7.0Clang 3.6.0306090120150SE +/- 0.20, N = 5SE +/- 0.00, N = 3SE +/- 0.67, N = 3131551501. (CXX) g++ options: -fopenmp -O3 -march=native

C-Ray

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeClang 3.8 SVNClang 3.7.0Clang 3.6.03691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 313.2212.8412.691. (CC) gcc options: -lm -lpthread -O3 -march=native

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To CompileClang 3.8 SVNClang 3.7.0Clang 3.6.048121620SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 316.8115.7613.671. (CC) gcc options: -O3 -march=native -pedantic -ldl -lz -lm

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.7Time To CompileClang 3.8 SVNClang 3.7.0Clang 3.6.0510152025SE +/- 0.14, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 322.2419.8417.66

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverClang 3.8 SVNClang 3.7.0Clang 3.6.030060090012001500SE +/- 5.06, N = 3SE +/- 4.48, N = 3SE +/- 9.11, N = 31268.911444.581544.881. (CC) gcc options: -O3 -march=native -mavx2

GraphicsMagick

Operation: Local Adaptive Thresholding

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Local Adaptive ThresholdingClang 3.8 SVNClang 3.7.0Clang 3.6.020406080100SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3808585-fopenmp -lgomp1. (CC) gcc options: -O3 -march=native -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread

SciMark

Computational Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationClang 3.8 SVNClang 3.7.0Clang 3.6.030060090012001500SE +/- 7.91, N = 4SE +/- 19.56, N = 4SE +/- 27.88, N = 41408.071415.371473.981. (CXX) g++ options: -O3 -march=native

SciMark

Computational Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationClang 3.8 SVNClang 3.7.0Clang 3.6.010002000300040005000SE +/- 25.29, N = 4SE +/- 12.15, N = 4SE +/- 24.09, N = 44806.984786.504862.281. (CXX) g++ options: -O3 -march=native

SciMark

Computational Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyClang 3.8 SVNClang 3.7.0Clang 3.6.05001000150020002500SE +/- 10.38, N = 4SE +/- 5.81, N = 4SE +/- 41.89, N = 42473.602484.072414.461. (CXX) g++ options: -O3 -march=native

SciMark

Computational Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformClang 3.8 SVNClang 3.7.0Clang 3.6.080160240320400SE +/- 0.59, N = 4SE +/- 1.06, N = 4SE +/- 0.82, N = 4343.69346.20362.611. (CXX) g++ options: -O3 -march=native

SciMark

Computational Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloClang 3.8 SVNClang 3.7.0Clang 3.6.0120240360480600SE +/- 1.45, N = 4SE +/- 5.57, N = 4SE +/- 11.74, N = 4225.30521.71536.021. (CXX) g++ options: -O3 -march=native

SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeClang 3.8 SVNClang 3.7.0Clang 3.6.0400800120016002000SE +/- 5.96, N = 4SE +/- 6.01, N = 4SE +/- 9.91, N = 41851.531910.771929.871. (CXX) g++ options: -O3 -march=native

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchClang 3.8 SVNClang 3.7.0Clang 3.6.048121620SE +/- 0.28, N = 6SE +/- 0.25, N = 3SE +/- 0.29, N = 611.2213.9915.451. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm

Phoronix Test Suite v10.8.5