LLVM Clang 3.2 vs. GCC 4.8 - Intel Ivy Bridge

Intel Core i7-3517UE Ivy Bridge quick comparison of LLVM 3.2 SVN and GCC 4.8 SVN as of 17 August 2012 for a quick future article on phoronix.com by Michael Larabel looking at the GCC vs. LLVM/Clang compiler performance on this latest Intel hardware.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1208179-SU-LLVMCLANG08
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 4 Tests
C/C++ Compiler Tests 12 Tests
CPU Massive 14 Tests
Creator Workloads 5 Tests
Cryptography 2 Tests
Encoding 3 Tests
HPC - High Performance Computing 5 Tests
Common Kernel Benchmarks 2 Tests
Multi-Core 6 Tests
Renderers 2 Tests
Scientific Computing 5 Tests
Server 3 Tests
Server CPU Tests 5 Tests
Single-Threaded 3 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
LLVM 3.2 SVN 2012-08-17
August 17 2012
 
GCC 4.8.0 2012-08-17
August 17 2012
 
Invert Hiding All Results Option
 
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 3.2 vs. GCC 4.8 - Intel Ivy BridgeOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7-3517UE @ 2.10GHz (4 Cores)CompuLab Intense-PCIntel 3rd Gen Core DRAM8192MB500GB Hitachi HCC54755Intel 3rd Gen CoreRealtek ALC888VA2431Intel 82579LM Gigabit Connection + Realtek RTL8188CE 802.11b/g/nUbuntu 12.103.6.0-999-generic (x86_64)Unity 2D 6.2.0X Server 1.12.1.902 (1.12.2 RC 2)intel 2.20.32.1 Mesa 8.1-devel (git-6a3ac03)Clang 3.2 (SVN 162102) + LLVM 3.2svnGCC 4.8.0 20120817ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilersFile-SystemScreen ResolutionLLVM Clang 3.2 Vs. GCC 4.8 - Intel Ivy Bridge BenchmarksSystem Logs- LLVM 3.2 SVN 2012-08-17: (Ubuntu 3.0-9)Optimized build; Built Apr 27 2012 (15:29:31); Host: x86_64-pc-linux-gnu; Host CPU: i686 - GCC 4.8.0 2012-08-17: --enable-checking=release --enable-languages=c,c++ --enable-lto- Scaling Governor: ondemand- GCC 4.8.0 2012-08-17: Firefox was running on this system.

LLVM 3.2 SVN 2012-08-17 vs. GCC 4.8.0 2012-08-17 ComparisonPhoronix Test SuiteBaseline+48.2%+48.2%+96.4%+96.4%+144.6%+144.6%+192.8%+192.8%192.9%191.5%23.8%22.4%14.6%9.4%8%6.1%4.6%3.4%2.8%G.I.R.1.SBlowfishP.D.SP.P.AM.S.AWAV To MP3SolitairevpxencBibdC.S.T3.8%Elapsed Time3.5%Graceful3.5%P.P.SQuasigroupS.W.P.S2.2%SmallptJohn The RipperTimed HMMer SearchTimed MrBayes AnalysisTimed MAFFT AlignmentLAME MP3 EncodingMinionVP8 libvpx EncodingMinion7-Zip CompressionCraftyMinionHimeno BenchmarkMinionNGINX BenchmarkLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17

LLVM Clang 3.2 vs. GCC 4.8 - Intel Ivy Bridgeffte: N=64, 1D Complex FFT Routinehmmer: Pfam Database Searchmafft: Multiple Sequence Alignmentmrbayes: Primate Phylogeny Analysisjohn-the-ripper: Blowfishvpxenc: vpxenchimeno: Poisson Pressure Solvercompress-7zip: Compress Speed Testc-ray: Total Timesmallpt: Global Illumination Renderer; 100 Samplescrafty: Elapsed Timeencode-mp3: WAV To MP3ffmpeg: AVI To NTSC VCDminion: Bibdminion: Gracefulminion: Solitaireminion: Quasigroupopenssl: RSA 4096-bit Performancenginx: Static Web Page Servingapache: Static Web Page ServingLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-174174.4832.5715.5832.4072113.941170.53826192.0120599.8520.6413.55160.6691.00154.67209.9470.9023429.5616978.744144.4126.3113.6026.48210214.791210.23795891.8770103.3818.86153.6594.20143.26204.2371.7022927.2916801.78OpenBenchmarking.org

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 5.0Test: N=64, 1D Complex FFT RoutineLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-179001800270036004500SE +/- 5.07, N = 3SE +/- 25.56, N = 34174.484144.411. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_f90 -lmpi_f77 -lmpi -lopen-rte -lopen-pal -ldl -lnsl -lutil -lm
OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 5.0Test: N=64, 1D Complex FFT RoutineLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-177001400210028003500Min: 4165.93 / Avg: 4174.48 / Max: 4183.46Min: 4093.36 / Avg: 4144.41 / Max: 4172.311. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_f90 -lmpi_f77 -lmpi -lopen-rte -lopen-pal -ldl -lnsl -lutil -lm

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 SearchLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17816243240SE +/- 0.01, N = 3SE +/- 0.03, N = 332.5726.311. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17714212835Min: 32.54 / Avg: 32.57 / Max: 32.59Min: 26.27 / Avg: 26.31 / Max: 26.361. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm

Timed MAFFT Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence AlignmentLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1748121620SE +/- 0.29, N = 6SE +/- 0.24, N = 615.5813.601. (CC) gcc options: -O3 -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence AlignmentLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1748121620Min: 15.03 / Avg: 15.58 / Max: 16.5Min: 13.01 / Avg: 13.6 / Max: 14.271. (CC) gcc options: -O3 -lm -lpthread

Timed MrBayes Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.1.2Primate Phylogeny AnalysisLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17816243240SE +/- 0.02, N = 3SE +/- 0.04, N = 332.4026.48
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.1.2Primate Phylogeny AnalysisLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17714212835Min: 32.37 / Avg: 32.4 / Max: 32.43Min: 26.43 / Avg: 26.48 / Max: 26.57

John The Ripper

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.7.9Test: BlowfishLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-175001000150020002500SE +/- 0.58, N = 3SE +/- 0.00, N = 372121021. (CC) gcc options: -fopenmp -lcrypt
OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.7.9Test: BlowfishLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17400800120016002000Min: 720 / Avg: 721 / Max: 722Min: 2102 / Avg: 2102 / Max: 21021. (CC) gcc options: -fopenmp -lcrypt

VP8 libvpx Encoding

OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 0.9.7-p1vpxencLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1748121620SE +/- 0.15, N = 3SE +/- 0.11, N = 313.9414.791. (CC) gcc options: -m64 -lvpx -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 0.9.7-p1vpxencLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1748121620Min: 13.69 / Avg: 13.94 / Max: 14.21Min: 14.59 / Avg: 14.79 / Max: 14.951. (CC) gcc options: -m64 -lvpx -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 SolverLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1730060090012001500SE +/- 3.44, N = 3SE +/- 1.93, N = 31170.531210.231. (CC) gcc options: -O3 -march=native
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-172004006008001000Min: 1166.38 / Avg: 1170.53 / Max: 1177.36Min: 1206.4 / Avg: 1210.23 / Max: 1212.451. (CC) gcc options: -O3 -march=native

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 9.20.1Compress Speed TestLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-172K4K6K8K10KSE +/- 37.65, N = 3SE +/- 29.33, N = 3826179581. (CXX) g++ options: -pipe -lpthread
OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 9.20.1Compress Speed TestLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1714002800420056007000Min: 8199 / Avg: 8261 / Max: 8329Min: 7911 / Avg: 7958.33 / Max: 80121. (CXX) g++ options: -pipe -lpthread

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 TimeLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1720406080100SE +/- 0.10, N = 3SE +/- 0.16, N = 392.0191.871. (CC) gcc options: -lm -lpthread -O3 -march=native
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1720406080100Min: 91.9 / Avg: 92.01 / Max: 92.21Min: 91.63 / Avg: 91.87 / Max: 92.181. (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 SamplesLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-174080120160200SE +/- 0.67, N = 3SE +/- 0.33, N = 3205701. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 SamplesLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-174080120160200Min: 204 / Avg: 205.33 / Max: 206Min: 70 / Avg: 70.33 / Max: 711. (CXX) g++ options: -fopenmp -O3 -march=native

Crafty

OpenBenchmarking.orgSeconds, Fewer Is BetterCrafty 23.4Elapsed TimeLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1720406080100SE +/- 0.06, N = 3SE +/- 0.02, N = 399.85103.381. (CC) gcc options: -lstdc++ -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterCrafty 23.4Elapsed TimeLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1720406080100Min: 99.73 / Avg: 99.85 / Max: 99.94Min: 103.35 / Avg: 103.38 / Max: 103.411. (CC) gcc options: -lstdc++ -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 MP3LLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17510152025SE +/- 0.02, N = 5SE +/- 0.01, N = 520.6418.86
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3LLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17510152025Min: 20.59 / Avg: 20.64 / Max: 20.69Min: 18.82 / Avg: 18.86 / Max: 18.9

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 0.10AVI To NTSC VCDLLVM 3.2 SVN 2012-08-173691215SE +/- 0.01, N = 313.551. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lasound -lSDL -lm -pthread -lbz2

Minion

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: BibdLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-174080120160200SE +/- 0.24, N = 3SE +/- 0.36, N = 3160.66153.65-mdynamic-no-pic -lz -lbz21. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt
OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: BibdLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17306090120150Min: 160.28 / Avg: 160.66 / Max: 161.11Min: 153.23 / Avg: 153.65 / Max: 154.361. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: GracefulLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1720406080100SE +/- 0.16, N = 3SE +/- 0.12, N = 391.0094.20-mdynamic-no-pic -lz -lbz21. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt
OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: GracefulLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1720406080100Min: 90.69 / Avg: 91 / Max: 91.23Min: 93.96 / Avg: 94.2 / Max: 94.351. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: SolitaireLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17306090120150SE +/- 0.64, N = 3SE +/- 0.14, N = 3154.67143.26-mdynamic-no-pic -lz -lbz21. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt
OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: SolitaireLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-17306090120150Min: 153.69 / Avg: 154.67 / Max: 155.86Min: 143.05 / Avg: 143.26 / Max: 143.541. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: QuasigroupLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-1750100150200250SE +/- 0.17, N = 3SE +/- 0.03, N = 3209.94204.23-mdynamic-no-pic -lz -lbz21. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt
OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 0.12Benchmark: QuasigroupLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-174080120160200Min: 209.6 / Avg: 209.94 / Max: 210.19Min: 204.19 / Avg: 204.23 / Max: 204.31. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt

OpenSSL

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.0eRSA 4096-bit PerformanceLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-171632486480SE +/- 0.50, N = 4SE +/- 0.07, N = 470.9071.701. (CC) gcc options: -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.0eRSA 4096-bit PerformanceLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-171428425670Min: 69.4 / Avg: 70.9 / Max: 71.5Min: 71.5 / Avg: 71.7 / Max: 71.81. (CC) gcc options: -m64 -O3 -lssl -lcrypto -ldl

NGINX Benchmark

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.0.11Static Web Page ServingLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-175K10K15K20K25KSE +/- 429.23, N = 3SE +/- 214.40, N = 323429.5622927.291. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz
OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.0.11Static Web Page ServingLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-174K8K12K16K20KMin: 22948.76 / Avg: 23429.56 / Max: 24285.86Min: 22528.33 / Avg: 22927.29 / Max: 23262.91. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz

Apache Benchmark

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.2.21Static Web Page ServingLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-174K8K12K16K20KSE +/- 77.92, N = 3SE +/- 111.57, N = 316978.7416801.781. (CC) gcc options: -pthread -O3 -march=native -lm -lexpat -lrt -lcrypt -lpthread -ldl
OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.2.21Static Web Page ServingLLVM 3.2 SVN 2012-08-17GCC 4.8.0 2012-08-173K6K9K12K15KMin: 16867.24 / Avg: 16978.74 / Max: 17128.77Min: 16626.85 / Avg: 16801.78 / Max: 17009.221. (CC) gcc options: -pthread -O3 -march=native -lm -lexpat -lrt -lcrypt -lpthread -ldl