GCC 4.7 LLVM Clang 3.1 Compiler Performance

Compiler performance benchmarks using GCC 4.6.3, GCC 4.7.0, LLVM Clang 3.0, and LLVM Clang 3.1 SVN from 23 March. Testing for a future article on Phoronix.com. Using an Intel Core i7 3960X Sandy Bridge Extreme Edition clocked at 4.5GHz with 12 threads (six physical + HT).

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1203235-SU-GCC47LLVM92
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:

Bioinformatics 2 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 6 Tests
Creator Workloads 6 Tests
Encoding 3 Tests
HPC - High Performance Computing 2 Tests
Multi-Core 6 Tests
Renderers 2 Tests
Scientific Computing 2 Tests
Server CPU Tests 2 Tests
Single-Threaded 2 Tests
Video Encoding 2 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
GCC 4.6.3
March 23 2012
 
GCC 4.7.0
March 23 2012
 
LLVM-Clang 3.0
March 23 2012
 
LLVM-Clang 3.1 SVN
March 23 2012
 
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):


GCC 4.7 LLVM Clang 3.1 Compiler PerformanceOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-3960X @ 3.20GHz (12 Cores)Intel DX79SIIntel Sandy DMI216384MB240GB OCZ VERTEX3AMD Radeon HD 7900 3072MB (900/1375MHz)Realtek ALC892DELL P2210HIntel 82579LM Gigabit ConnectionUbuntu 12.043.2.0-18-generic (x86_64)Unity 5.6.0X Server 1.11.3fglrx 8.95.3 Catalyst 12.24.2.11554GCC 4.6.3GCC 4.7.0Clang 3.0 + LLVM 3.0Clang 3.1 (SVN 153339) + LLVM 3.1svnext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilersFile-SystemScreen ResolutionGCC 4.7 LLVM Clang 3.1 Compiler Performance BenchmarksSystem Logs- GCC 4.6.3: --enable-checking=release --enable-languages=c,c++- GCC 4.7.0: --enable-checking=release --enable-languages=c,c++- LLVM-Clang 3.0: Optimized build; Built Mar 23 2012 (11:30:39); Host: x86_64-unknown-linux-gnu; Host CPU: corei7-avx - LLVM-Clang 3.1 SVN: Optimized build; Built Mar 23 2012 (08:53:34); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7-avx - Compiz was running on this system.

GCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVNLogarithmic Result OverviewPhoronix Test SuiteSmallptGraphicsMagickC-RayTimed HMMer SearchVP8 libvpx EncodingLZMA CompressionHimeno BenchmarkFFmpegOgg Encoding

GCC 4.7 LLVM Clang 3.1 Compiler Performancevpxenc: vpxencgraphics-magick: Blurgraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdinggraphics-magick: Resizinggraphics-magick: Sharpenbyte: Dhrystone 2himeno: Poisson Pressure Solverhmmer: Pfam Database Searchc-ray: Total Timecompress-lzma: 256MB File Compressionencode-ogg: WAV To Oggffmpeg: AVI To NTSC VCDnero2d: Total Timesmallpt: Global Illumination Renderer; 100 SamplesGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN23.86123162851519821842507.831270.059.1734.01155.299.4612.42557.092023.28123163851529821265475.601322.569.2225.92154.979.4412.32543.942021.46721002166201275.1710.6135.38163.409.4612.3916222.006510025862921549720.131280.0310.3432.40160.869.4912.17546.24176OpenBenchmarking.org

VP8 libvpx Encoding

OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 0.9.7-p1vpxencGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN612182430SE +/- 0.17, N = 3SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 323.8623.2821.4622.001. (CC) gcc options: -m64 -lvpx -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 0.9.7-p1vpxencGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN612182430Min: 23.55 / Avg: 23.86 / Max: 24.15Min: 23.07 / Avg: 23.28 / Max: 23.62Min: 21.37 / Avg: 21.46 / Max: 21.55Min: 21.7 / Avg: 22 / Max: 22.171. (CC) gcc options: -m64 -lvpx -lm -lpthread

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: BlurGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN306090120150SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 31231237265-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-ljpeg-ljpeg1. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: BlurGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN20406080100Min: 123 / Avg: 123 / Max: 123Min: 123 / Avg: 123.33 / Max: 124Min: 72 / Avg: 72.33 / Max: 73Min: 65 / Avg: 65 / Max: 651. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: HWB Color SpaceGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN4080120160200SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3162163100100-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-ljpeg-ljpeg1. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: HWB Color SpaceGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN306090120150Min: 162 / Avg: 162 / Max: 162Min: 163 / Avg: 163 / Max: 163Min: 100 / Avg: 100 / Max: 100Min: 100 / Avg: 100 / Max: 1001. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Local Adaptive ThresholdingGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 385852125-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-ljpeg-ljpeg1. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Local Adaptive ThresholdingGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN1632486480Min: 85 / Avg: 85 / Max: 85Min: 85 / Avg: 85 / Max: 85Min: 21 / Avg: 21 / Max: 21Min: 25 / Avg: 25 / Max: 251. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: ResizingGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31511526686-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-ljpeg-ljpeg1. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: ResizingGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN306090120150Min: 151 / Avg: 151 / Max: 151Min: 152 / Avg: 152 / Max: 152Min: 66 / Avg: 66 / Max: 66Min: 86 / Avg: 86 / Max: 861. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: SharpenGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 398982029-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-std=gnu99 -fopenmp -ltiff -lfreetype -lrt-ljpeg-ljpeg1. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: SharpenGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN20406080100Min: 98 / Avg: 98 / Max: 98Min: 98 / Avg: 98 / Max: 98Min: 20 / Avg: 20 / Max: 20Min: 29 / Avg: 29 / Max: 291. (CC) gcc options: -O3 -march=corei7-avx -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread

BYTE Unix Benchmark

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2GCC 4.6.3GCC 4.7.0LLVM-Clang 3.1 SVN5M10M15M20M25MSE +/- 15381.71, N = 3SE +/- 12258.65, N = 3SE +/- 13587.80, N = 321842507.8321265475.6021549720.13-march=corei7-avx-march=corei7-avx1. (CC) gcc options: -O3
OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2GCC 4.6.3GCC 4.7.0LLVM-Clang 3.1 SVN4M8M12M16M20MMin: 21818010.9 / Avg: 21842507.83 / Max: 21870872Min: 21240976.8 / Avg: 21265475.6 / Max: 21278549.9Min: 21522648 / Avg: 21549720.13 / Max: 21565307.91. (CC) gcc options: -O3

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 SolverGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN30060090012001500SE +/- 4.37, N = 3SE +/- 1.59, N = 3SE +/- 3.11, N = 3SE +/- 0.67, N = 31270.051322.561275.171280.031. (CC) gcc options: -O3 -march=corei7-avx
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN2004006008001000Min: 1261.45 / Avg: 1270.05 / Max: 1275.67Min: 1320.64 / Avg: 1322.56 / Max: 1325.72Min: 1269.01 / Avg: 1275.17 / Max: 1279.03Min: 1278.78 / Avg: 1280.03 / Max: 1281.071. (CC) gcc options: -O3 -march=corei7-avx

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 SearchGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN3691215SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 39.179.2210.6110.341. (CC) gcc options: -O3 -march=corei7-avx -pthread -lhmmer -lsquid -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN3691215Min: 9.12 / Avg: 9.17 / Max: 9.26Min: 9.18 / Avg: 9.22 / Max: 9.29Min: 10.52 / Avg: 10.61 / Max: 10.66Min: 10.31 / Avg: 10.34 / Max: 10.391. (CC) gcc options: -O3 -march=corei7-avx -pthread -lhmmer -lsquid -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 TimeGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN816243240SE +/- 0.32, N = 3SE +/- 0.13, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 334.0125.9235.3832.401. (CC) gcc options: -lm -lpthread -O3 -march=corei7-avx
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN816243240Min: 33.63 / Avg: 34.01 / Max: 34.64Min: 25.67 / Avg: 25.92 / Max: 26.09Min: 35.12 / Avg: 35.38 / Max: 35.52Min: 32.33 / Avg: 32.4 / Max: 32.51. (CC) gcc options: -lm -lpthread -O3 -march=corei7-avx

LZMA Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterLZMA Compression256MB File CompressionGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN4080120160200SE +/- 0.19, N = 3SE +/- 0.21, N = 3SE +/- 0.74, N = 3SE +/- 0.33, N = 3155.29154.97163.40160.861. (CC) gcc options: -O3 -march=corei7-avx
OpenBenchmarking.orgSeconds, Fewer Is BetterLZMA Compression256MB File CompressionGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN306090120150Min: 154.91 / Avg: 155.29 / Max: 155.51Min: 154.76 / Avg: 154.97 / Max: 155.39Min: 162.32 / Avg: 163.4 / Max: 164.81Min: 160.4 / Avg: 160.86 / Max: 161.51. (CC) gcc options: -O3 -march=corei7-avx

Ogg Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.0WAV To OggGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN3691215SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 59.469.449.469.49-lvorbis-lvorbis1. (CC) gcc options: -O2 -ffast-math -fsigned-char -O3 -march=corei7-avx -lm -logg
OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.0WAV To OggGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN3691215Min: 9.42 / Avg: 9.46 / Max: 9.48Min: 9.43 / Avg: 9.44 / Max: 9.47Min: 9.44 / Avg: 9.46 / Max: 9.48Min: 9.45 / Avg: 9.49 / Max: 9.551. (CC) gcc options: -O2 -ffast-math -fsigned-char -O3 -march=corei7-avx -lm -logg

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 0.10AVI To NTSC VCDGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN3691215SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 312.4212.3212.3912.171. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lasound -lSDL -lm -pthread -lbz2
OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 0.10AVI To NTSC VCDGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN48121620Min: 12.33 / Avg: 12.42 / Max: 12.47Min: 12.3 / Avg: 12.32 / Max: 12.33Min: 12.37 / Avg: 12.39 / Max: 12.42Min: 12.11 / Avg: 12.17 / Max: 12.221. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lasound -lSDL -lm -pthread -lbz2

Open FMM Nero2D

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen FMM Nero2D 2.0.2Total TimeGCC 4.6.3GCC 4.7.0LLVM-Clang 3.1 SVN120240360480600557.09543.94546.24-O3 -march=corei7-avx-O3 -march=corei7-avx-O2 -lquadmath1. (CXX) g++ options: -lfftw3 -llapack -lblas -lgfortran -lm

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 SamplesGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN4080120160200SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 320201621761. (CXX) g++ options: -fopenmp -O3 -march=corei7-avx
OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 SamplesGCC 4.6.3GCC 4.7.0LLVM-Clang 3.0LLVM-Clang 3.1 SVN306090120150Min: 20 / Avg: 20.33 / Max: 21Min: 20 / Avg: 20.33 / Max: 21Min: 161 / Avg: 161.67 / Max: 162Min: 176 / Avg: 176 / Max: 1761. (CXX) g++ options: -fopenmp -O3 -march=corei7-avx