LLVM Clang 3.4 Compiler Optimization Levels

Benchmarking LLVM/Clang compiler optimization levels for a future article on phoronix.com.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1307304-SO-CLANGLEVE44
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

Audio Encoding 2 Tests
Bioinformatics 2 Tests
Timed Code Compilation 2 Tests
C/C++ Compiler Tests 9 Tests
CPU Massive 7 Tests
Creator Workloads 5 Tests
Encoding 2 Tests
HPC - High Performance Computing 2 Tests
Multi-Core 6 Tests
Programmer / Developer System Benchmarks 2 Tests
Renderers 2 Tests
Scientific Computing 2 Tests
Server CPU Tests 3 Tests
Single-Threaded 3 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
-O0
July 29 2013
 
-O1
July 29 2013
 
-O2
July 29 2013
 
-Os
July 29 2013
 
-O3
July 28 2013
 
-Ofast
July 29 2013
 
Invert Hiding All Results Option
 

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


LLVM Clang 3.4 Compiler Optimization LevelsOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7 720Q @ 1.60GHz (8 Cores)LENOVO 4318CTOIntel Core DMI4096MB160GB INTEL SSDSA2M160NVIDIA Quadro FX 880M 1024MB (405/324MHz)Conexant CX20585Intel 82577LM Gigabit Connection + Intel Centrino Ultimate-N 6300Ubuntu 13.103.11.0-031100rc2-generic (x86_64)Xfce 4.10X Server 1.14.2nouveau 1.0.83.0 Mesa 9.1.4 Gallium 0.4Clang 3.4 (SVN 187338) + LLVM 3.4svnext41600x900ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionLLVM Clang 3.4 Compiler Optimization Levels PerformanceSystem Logs- Optimized build; Built Jul 28 2013 (21:43:17); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7 - Scaling Governor: acpi-cpufreq ondemand

-O0-O1-O2-Os-O3-OfastLogarithmic Result OverviewPhoronix Test SuiteHimeno BenchmarkFLAC Audio EncodingTimed HMMer SearchN-QueensLAME MP3 EncodingGraphicsMagickTimed ImageMagick CompilationSmallptC-RayTimed PHP CompilationSciMark

LLVM Clang 3.4 Compiler Optimization Levelshmmer: Pfam Database Searchscimark2: Fast Fourier Transformgraphics-magick: Blurgraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdinghimeno: Poisson Pressure Solverbuild-imagemagick: Time To Compilebuild-php: Time To Compilec-ray: Total Timesmallpt: Global Illumination Renderer; 100 Samplesencode-flac: WAV To FLACencode-mp3: WAV To MP3n-queens: Elapsed Time-O0-O1-O2-Os-O3-Ofast89.33189.30221024368127.9523.1418.55208.5377044.1267.471083.8830.89189.1053356681311105.3657.3731.28100.1141011.2623.55386.2127.31189.7253366680321129.5665.3035.51103.772929.0022.72343.1828.68190.1452366679301102.6863.3333.44104.7232011.1623.04331.7227.33173.5753366680321055.0865.8841.9775.982938.8622.64345.3827.10188.0653366797311128.5066.5542.1593.632758.8522.00343.65OpenBenchmarking.org

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database Search-O0-O1-O2-Os-O3-Ofast20406080100SE +/- 0.46, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 389.3330.8927.3128.6827.3327.10-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -march=native -pthread -lhmmer -lsquid -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database Search-O0-O1-O2-Os-O3-Ofast20406080100Min: 88.51 / Avg: 89.33 / Max: 90.11Min: 30.84 / Avg: 30.89 / Max: 30.94Min: 27.21 / Avg: 27.31 / Max: 27.38Min: 28.58 / Avg: 28.68 / Max: 28.79Min: 27.29 / Avg: 27.33 / Max: 27.35Min: 27.04 / Avg: 27.1 / Max: 27.161. (CC) gcc options: -march=native -pthread -lhmmer -lsquid -lm

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform-O0-O1-O2-Os-O3-Ofast4080120160200SE +/- 0.00, N = 4SE +/- 0.52, N = 4SE +/- 0.24, N = 4SE +/- 0.00, N = 4SE +/- 0.61, N = 4SE +/- 0.41, N = 4189.30189.10189.72190.14173.57188.06-O0-O1-O2-Os-O3-Ofast1. (CXX) g++ options: -march=native
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform-O0-O1-O2-Os-O3-Ofast306090120150Min: 189.3 / Avg: 189.3 / Max: 189.3Min: 187.64 / Avg: 189.1 / Max: 190.14Min: 189.3 / Avg: 189.72 / Max: 190.14Min: 190.14 / Avg: 190.14 / Max: 190.14Min: 172.51 / Avg: 173.57 / Max: 175.34Min: 186.82 / Avg: 188.06 / Max: 188.471. (CXX) g++ options: -march=native

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Blur-O0-O1-O2-Os-O3-Ofast1224364860SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3225353525353-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Blur-O0-O1-O2-Os-O3-Ofast1122334455Min: 21 / Avg: 21.67 / Max: 22Min: 53 / Avg: 53 / Max: 53Min: 53 / Avg: 53 / Max: 53Min: 52 / Avg: 52 / Max: 52Min: 53 / Avg: 53 / Max: 53Min: 53 / Avg: 53 / Max: 531. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Sharpen-O0-O1-O2-Os-O3-Ofast816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3103536363636-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Sharpen-O0-O1-O2-Os-O3-Ofast816243240Min: 10 / Avg: 10 / Max: 10Min: 35 / Avg: 35 / Max: 35Min: 36 / Avg: 36 / Max: 36Min: 36 / Avg: 36 / Max: 36Min: 36 / Avg: 36 / Max: 36Min: 36 / Avg: 36 / Max: 361. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Resizing-O0-O1-O2-Os-O3-Ofast1530456075SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3246666666667-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Resizing-O0-O1-O2-Os-O3-Ofast1326395265Min: 24 / Avg: 24 / Max: 24Min: 66 / Avg: 66 / Max: 66Min: 66 / Avg: 66 / Max: 66Min: 66 / Avg: 66 / Max: 66Min: 66 / Avg: 66 / Max: 66Min: 66 / Avg: 66.67 / Max: 671. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color Space-O0-O1-O2-Os-O3-Ofast20406080100SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3368180798097-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color Space-O0-O1-O2-Os-O3-Ofast20406080100Min: 36 / Avg: 36.33 / Max: 37Min: 81 / Avg: 81 / Max: 81Min: 80 / Avg: 80 / Max: 80Min: 79 / Avg: 79 / Max: 79Min: 80 / Avg: 80 / Max: 80Min: 97 / Avg: 97 / Max: 971. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive Thresholding-O0-O1-O2-Os-O3-Ofast714212835SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 383132303231-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive Thresholding-O0-O1-O2-Os-O3-Ofast714212835Min: 8 / Avg: 8 / Max: 8Min: 31 / Avg: 31 / Max: 31Min: 32 / Avg: 32 / Max: 32Min: 30 / Avg: 30 / Max: 30Min: 32 / Avg: 32 / Max: 32Min: 31 / Avg: 31 / Max: 311. (CC) gcc options: -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-O0-O1-O2-Os-O3-Ofast2004006008001000SE +/- 0.03, N = 3SE +/- 0.14, N = 3SE +/- 0.39, N = 3SE +/- 0.03, N = 3SE +/- 5.78, N = 3SE +/- 0.36, N = 3127.951105.361129.561102.681055.081128.50-O0-O1-O2-Os-Ofast1. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-O0-O1-O2-Os-O3-Ofast2004006008001000Min: 127.9 / Avg: 127.95 / Max: 128.01Min: 1105.12 / Avg: 1105.36 / Max: 1105.58Min: 1128.82 / Avg: 1129.56 / Max: 1130.14Min: 1102.65 / Avg: 1102.68 / Max: 1102.75Min: 1043.87 / Avg: 1055.08 / Max: 1063.14Min: 1127.8 / Avg: 1128.5 / Max: 11291. (CC) gcc options: -O3 -march=native

Timed ImageMagick Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.8.1-10Time To Compile-O0-O1-O2-Os-O3-Ofast1530456075SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.22, N = 3SE +/- 0.14, N = 3SE +/- 0.18, N = 3SE +/- 0.12, N = 323.1457.3765.3063.3365.8866.55
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.8.1-10Time To Compile-O0-O1-O2-Os-O3-Ofast1326395265Min: 23.1 / Avg: 23.14 / Max: 23.21Min: 57.16 / Avg: 57.37 / Max: 57.51Min: 64.91 / Avg: 65.3 / Max: 65.68Min: 63.06 / Avg: 63.33 / Max: 63.55Min: 65.53 / Avg: 65.88 / Max: 66.15Min: 66.32 / Avg: 66.55 / Max: 66.69

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To Compile-O0-O1-O2-Os-O3-Ofast1020304050SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 318.5531.2835.5133.4441.9742.15-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -march=native -pedantic -ldl -lz -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To Compile-O0-O1-O2-Os-O3-Ofast918273645Min: 18.53 / Avg: 18.55 / Max: 18.58Min: 31.24 / Avg: 31.28 / Max: 31.29Min: 35.4 / Avg: 35.51 / Max: 35.65Min: 33.42 / Avg: 33.44 / Max: 33.45Min: 41.81 / Avg: 41.97 / Max: 42.16Min: 42.08 / Avg: 42.15 / Max: 42.191. (CC) gcc options: -march=native -pedantic -ldl -lz -lm

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time-O0-O1-O2-Os-O3-Ofast50100150200250SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3208.53100.11103.77104.7275.9893.63-O0-O1-O2-Os-Ofast1. (CC) gcc options: -lm -lpthread -O3 -march=native
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time-O0-O1-O2-Os-O3-Ofast4080120160200Min: 208.42 / Avg: 208.53 / Max: 208.65Min: 100.1 / Avg: 100.11 / Max: 100.13Min: 103.72 / Avg: 103.77 / Max: 103.79Min: 104.65 / Avg: 104.72 / Max: 104.81Min: 75.93 / Avg: 75.98 / Max: 76.05Min: 93.59 / Avg: 93.63 / Max: 93.691. (CC) gcc options: -lm -lpthread -O3 -march=native

Smallpt

Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 Samples-O0-O1-O2-Os-O3-Ofast170340510680850SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 1.67, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3770410292320293275-O0-O1-O2-Os-O3-Ofast1. (CXX) g++ options: -fopenmp -march=native
OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 Samples-O0-O1-O2-Os-O3-Ofast140280420560700Min: 769 / Avg: 770 / Max: 771Min: 410 / Avg: 410.33 / Max: 411Min: 290 / Avg: 291.67 / Max: 293Min: 317 / Avg: 320.33 / Max: 322Min: 292 / Avg: 293 / Max: 294Min: 274 / Avg: 274.67 / Max: 2751. (CXX) g++ options: -fopenmp -march=native

FLAC Audio Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.0WAV To FLAC-O0-O1-O2-Os-O3-Ofast1020304050SE +/- 0.02, N = 5SE +/- 0.05, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 544.1211.269.0011.168.868.85-O0-O1-O2-Os-O3-Ofast1. (CXX) g++ options: -march=native -fvisibility=hidden -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.0WAV To FLAC-O0-O1-O2-Os-O3-Ofast918273645Min: 44.06 / Avg: 44.12 / Max: 44.17Min: 11.08 / Avg: 11.26 / Max: 11.41Min: 8.97 / Avg: 9 / Max: 9.03Min: 11.14 / Avg: 11.16 / Max: 11.17Min: 8.85 / Avg: 8.86 / Max: 8.88Min: 8.83 / Avg: 8.85 / Max: 8.871. (CXX) g++ options: -march=native -fvisibility=hidden -logg -lm

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3-O0-O1-O2-Os-O3-Ofast1530456075SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 567.4723.5522.7223.0422.6422.00-O0-O1-O2-Os-O3-Ofast1. (CC) gcc options: -pipe -march=native -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3-O0-O1-O2-Os-O3-Ofast1326395265Min: 67.41 / Avg: 67.47 / Max: 67.52Min: 23.51 / Avg: 23.55 / Max: 23.58Min: 22.7 / Avg: 22.72 / Max: 22.74Min: 23.01 / Avg: 23.04 / Max: 23.09Min: 22.6 / Avg: 22.64 / Max: 22.71Min: 21.98 / Avg: 22 / Max: 22.021. (CC) gcc options: -pipe -march=native -lm

N-Queens

This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed Time-O0-O1-O2-Os-O3-Ofast2004006008001000SE +/- 0.13, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3SE +/- 0.89, N = 3SE +/- 0.04, N = 31083.88386.21343.18331.72345.38343.65-O0-O1-O2-Os-Ofast1. (CC) gcc options: -static -fopenmp -O3 -march=native
OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed Time-O0-O1-O2-Os-O3-Ofast2004006008001000Min: 1083.73 / Avg: 1083.88 / Max: 1084.13Min: 386.2 / Avg: 386.21 / Max: 386.22Min: 343.13 / Avg: 343.18 / Max: 343.22Min: 331.48 / Avg: 331.72 / Max: 331.91Min: 343.77 / Avg: 345.38 / Max: 346.84Min: 343.59 / Avg: 343.65 / Max: 343.711. (CC) gcc options: -static -fopenmp -O3 -march=native