LLVM 3.2 Clang Intel Linux Compiler

Intel Core i7-3960X Sandy Bridge Extreme Edition computer running Ubuntu 12.10 and comparing builds of LLVM/Clang 3.1 and LLVM/Clang 3.2 SVN. LLVM and Clang both times were built in release mode of --disable-assertions and --enable-optimized. Compiler flags passed to tests included -O3 and then each -march=nocona and -march=corei7-avx to see if there's any x86_64 compiler tuning optimizations when using corei7-avx for Intel Sandy Bridge CPUs. Benchmarking 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 1210095-RA-LLVM32CLA70
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Comparison
Transpose Comparison

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
nocona: LLVM-Clang 3.1
October 09 2012
 
corei7-avx: LLVM-Clang 3.1
October 09 2012
 
nocona: LLVM-Clang 3.2 SVN
October 08 2012
 
corei7-avx: LLVM-Clang 3.2 SVN
October 08 2012
 
Invert Behavior (Only Show Selected Data)
 

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 3.2 Clang Intel Linux CompilerOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-3960X @ 3.30GHz (12 Cores)Intel DX79SIIntel Xeon E5/Core8192MB64GB OCZ VERTEXAMD Radeon HD 4650 512MBRealtek ALC892DELL S2409WIntel 82579LM Gigabit ConnectionUbuntu 12.103.6.0-030600-generic (x86_64)Unity 6.8.0X Server 1.13.0radeon 6.99.993.0 Mesa 9.0-devel Gallium 0.4Clang 3.2 (SVN 165433) + LLVM 3.2svnClang 3.1 + LLVM 3.1ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilersFile-SystemScreen ResolutionLLVM 3.2 Clang Intel Linux Compiler BenchmarksSystem Logs- Scaling Governor: ondemand- Compiz was running on this system.- nocona: LLVM-Clang 3.1, corei7-avx: LLVM-Clang 3.1: Optimized build; Built Oct 9 2012 (06:32:52); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7-avx

apache: Static Web Page Servingc-ray: Total Timeencode-flac: WAV To FLACgraphics-magick: Blurgraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdinghimeno: Poisson Pressure Solverpgbench: TPC-B Transactions Per Secondsmallpt: Global Illumination Renderer; 100 Sampleshmmer: Pfam Database Searchbuild-php: Time To Compilecorei7-avxnoconacorei7-avx LLVM-Clang 3.2 SVN LLVM-Clang 3.2 SVN LLVM-Clang 3.1 LLVM-Clang 3.116277.2520.996.36823189124451545.92377.9815215.3715.6916835.2421.626.407853107123481561.02370.4215715.4515.4716863.3226.346.418753104121451575.76366.3614715.4120.5716850.8726.306.418752104121491582.01360.5114615.4220.57OpenBenchmarking.org

Apache Benchmark

corei7-avxnoconaOpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.3Static Web Page ServingLLVM-Clang 3.1LLVM-Clang 3.2 SVN4K8K12K16K20KSE +/- 43.37, N = 3SE +/- 299.58, N = 3SE +/- 71.80, N = 3SE +/- 26.63, N = 316850.8716277.2516863.3216835.241. (CC) gcc options: -shared -fPIC -pthread -O3

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.

corei7-avxnoconaOpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeLLVM-Clang 3.1LLVM-Clang 3.2 SVN612182430SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 326.3020.9926.3421.621. (CC) gcc options: -lm -lpthread -O3

FLAC Audio Encoding

corei7-avxnoconaOpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.2.1WAV To FLACLLVM-Clang 3.1LLVM-Clang 3.2 SVN246810SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.01, N = 56.416.366.416.401. (CXX) g++ options: -O3 -logg -lm

GraphicsMagick

corei7-avxnoconaOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: BlurLLVM-Clang 3.1LLVM-Clang 3.2 SVN20406080100SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3878287781. (CC) gcc options: -O3 -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread

corei7-avxnoconaOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: SharpenLLVM-Clang 3.1LLVM-Clang 3.2 SVN1224364860SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3523153531. (CC) gcc options: -O3 -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread

corei7-avxnoconaOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: ResizingLLVM-Clang 3.1LLVM-Clang 3.2 SVN20406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3104891041071. (CC) gcc options: -O3 -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread

corei7-avxnoconaOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color SpaceLLVM-Clang 3.1LLVM-Clang 3.2 SVN306090120150SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31211241211231. (CC) gcc options: -O3 -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread

corei7-avxnoconaOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive ThresholdingLLVM-Clang 3.1LLVM-Clang 3.2 SVN1122334455SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3494545481. (CC) gcc options: -O3 -pthread -lXext -lSM -lICE -lX11 -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.

corei7-avxnoconaOpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverLLVM-Clang 3.1LLVM-Clang 3.2 SVN30060090012001500SE +/- 2.49, N = 3SE +/- 3.54, N = 3SE +/- 1.69, N = 3SE +/- 2.19, N = 31582.011545.921575.761561.021. (CC) gcc options: -O3

PostgreSQL pgbench

corei7-avxnoconaOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 8.4.11TPC-B Transactions Per SecondLLVM-Clang 3.1LLVM-Clang 3.2 SVN80160240320400SE +/- 4.65, N = 3SE +/- 0.65, N = 3SE +/- 6.05, N = 3SE +/- 6.91, N = 3360.51377.98366.36370.421. (CC) gcc options: -O3 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -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.

corei7-avxnoconaOpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 SamplesLLVM-Clang 3.1LLVM-Clang 3.2 SVN306090120150SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 31461521471571. (CXX) g++ options: -fopenmp -O3

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.

corei7-avxnoconaOpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchLLVM-Clang 3.1LLVM-Clang 3.2 SVN48121620SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 315.4215.3715.4115.451. (CC) gcc options: -O3 -pthread -lhmmer -lsquid -lm

Timed PHP Compilation

corei7-avxnoconaOpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To CompileLLVM-Clang 3.1LLVM-Clang 3.2 SVN510152025SE +/- 0.06, N = 3SE +/- 0.22, N = 6SE +/- 0.06, N = 3SE +/- 0.04, N = 320.5715.6920.5715.471. (CC) gcc options: -O3 -pedantic -ldl -lpthread -lz -lm