GCC AMD Bulldozer Compiler Tuning

AMD FX-8150 Bulldozer compiler tuning using GCC 4.7.1 with different march options for the test profiles to look at the latest AMD GCC performance. Benchmarking by Michael Larabel 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 1209227-RA-GCCAMDBUL32
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:

C/C++ Compiler Tests 5 Tests
CPU Massive 6 Tests
Creator Workloads 3 Tests
Multi-Core 6 Tests
Renderers 2 Tests
Server CPU Tests 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
march=nocona
September 14 2012
 
march=core2
September 14 2012
 
march=k8
September 14 2012
 
march=k8-sse3
September 15 2012
 
march=barcelona
September 14 2012
 
march=bdver1
September 14 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 AMD Bulldozer Compiler TuningOpenBenchmarking.orgPhoronix Test SuiteAMD FX-8150 Eight-Core @ 3.60GHz (8 Cores)ASUS Crosshair V FormulaAMD ATI RD890 bridge4096MB60GB OCZ VERTEX2NVIDIA GeForce 9600 GSO 512MB (399/399MHz)Realtek ALC889DELL P2210HIntel 82583V Gigabit ConnectionUbuntu 12.103.5.0-14-generic (x86_64)Unity 6.4.0X Server 1.13.0nouveau 1.0.23.0 Mesa 8.1-devel Gallium 0.4GCC 4.7ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionGCC AMD Bulldozer Compiler Tuning BenchmarksSystem Logs- --build=x86_64-linux-gnu --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-arch-32=i686 --with-tune=generic -v - Scaling Governor: ondemand- march=nocona: Compiz was running on this system.- march=core2: Compiz was running on this system.- march=k8: Compiz and Firefox were running on this system.- march=k8-sse3: Compiz was running on this system.- march=barcelona: Compiz was running on this system.- march=bdver1: Compiz and Firefox were running on this system.

march=noconamarch=core2march=k8march=k8-sse3march=barcelonamarch=bdver1Result OverviewPhoronix Test Suite100%124%148%172%C-RayGraphicsMagickSmallptOpen FMM Nero2DGraphicsMagickGraphicsMagickHimeno BenchmarkGraphicsMagickTimed PHP CompilationPostgreSQL pgbenchGraphicsMagickTotal TimeSharpenG.I.R.1.STotal TimeBlurResizingP.P.SL.A.TTime To CompileT.B.T.P.SHWB Color Space

GCC AMD Bulldozer Compiler Tuninggraphics-magick: Blurgraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdinghimeno: Poisson Pressure Solverbuild-php: Time To Compilec-ray: Total Timesmallpt: Global Illumination Renderer; 100 Samplesnero2d: Total Timepgbench: TPC-B Transactions Per Secondmarch=noconamarch=core2march=k8march=k8-sse3march=barcelonamarch=bdver1996512616068654.2731.2036.8433549.432064.40969913915867670.7533.2236.3833531.272039.71976312815167614.8333.0252.8444643.591986.18956212615066678.9732.9852.8244636.992018.341078613915661669.2833.0736.0932534.422037.1111310014415766698.9234.4126.9930561.851916.51OpenBenchmarking.org

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Blurmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona306090120150SE +/- 1.15, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.67, N = 310711396979599-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Blurmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona20406080100Min: 105 / Avg: 107 / Max: 109Min: 112 / Avg: 112.67 / Max: 113Min: 96 / Avg: 96 / Max: 96Min: 97 / Avg: 97.33 / Max: 98Min: 94 / Avg: 95 / Max: 96Min: 98 / Avg: 98.67 / Max: 1001. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Sharpenmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona20406080100SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 38610099636265-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Sharpenmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona20406080100Min: 86 / Avg: 86.33 / Max: 87Min: 99 / Avg: 99.67 / Max: 100Min: 98 / Avg: 98.67 / Max: 99Min: 63 / Avg: 63 / Max: 63Min: 62 / Avg: 62.33 / Max: 63Min: 64 / Avg: 64.67 / Max: 651. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Resizingmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona306090120150SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3139144139128126126-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Resizingmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona306090120150Min: 138 / Avg: 138.67 / Max: 139Min: 143 / Avg: 143.67 / Max: 144Min: 138 / Avg: 138.67 / Max: 139Min: 127 / Avg: 127.67 / Max: 128Min: 125 / Avg: 125.67 / Max: 126Min: 126 / Avg: 126.33 / Max: 1271. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: HWB Color Spacemarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona4080120160200SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.20, N = 3156157158151150160-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: HWB Color Spacemarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona306090120150Min: 155 / Avg: 155.67 / Max: 157Min: 156 / Avg: 156.67 / Max: 157Min: 158 / Avg: 158.33 / Max: 159Min: 151 / Avg: 151.33 / Max: 152Min: 150 / Avg: 150.33 / Max: 151Min: 158 / Avg: 160.33 / Max: 1621. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Local Adaptive Thresholdingmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona1530456075SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3616667676668-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Local Adaptive Thresholdingmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona1326395265Min: 61 / Avg: 61 / Max: 61Min: 66 / Avg: 66 / Max: 66Min: 67 / Avg: 67 / Max: 67Min: 67 / Avg: 67 / Max: 67Min: 66 / Avg: 66 / Max: 66Min: 68 / Avg: 68.33 / Max: 691. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lz -lm -lgomp -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 Solvermarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona150300450600750SE +/- 6.64, N = 3SE +/- 8.36, N = 3SE +/- 8.14, N = 3SE +/- 0.75, N = 3SE +/- 7.84, N = 3SE +/- 5.51, N = 3669.28698.92670.75614.83678.97654.27-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -O3
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solvermarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona120240360480600Min: 657.55 / Avg: 669.28 / Max: 680.54Min: 689.67 / Avg: 698.92 / Max: 715.61Min: 654.51 / Avg: 670.75 / Max: 679.92Min: 613.52 / Avg: 614.83 / Max: 616.1Min: 663.35 / Avg: 678.97 / Max: 687.9Min: 646.91 / Avg: 654.27 / Max: 665.051. (CC) gcc options: -O3

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To Compilemarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona816243240SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 333.0734.4133.2233.0232.9831.20-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -O3 -pedantic -ldl -lz -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To Compilemarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona714212835Min: 32.98 / Avg: 33.07 / Max: 33.14Min: 34.36 / Avg: 34.41 / Max: 34.46Min: 33.12 / Avg: 33.22 / Max: 33.28Min: 32.95 / Avg: 33.02 / Max: 33.14Min: 32.87 / Avg: 32.98 / Max: 33.15Min: 31.17 / Avg: 31.2 / Max: 31.221. (CC) gcc options: -O3 -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 Timemarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona1224364860SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 336.0926.9936.3852.8452.8236.84-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Timemarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona1122334455Min: 36.08 / Avg: 36.09 / Max: 36.09Min: 26.97 / Avg: 26.99 / Max: 27Min: 36.36 / Avg: 36.38 / Max: 36.39Min: 52.79 / Avg: 52.84 / Max: 52.89Min: 52.8 / Avg: 52.82 / Max: 52.86Min: 36.82 / Avg: 36.84 / Max: 36.871. (CC) gcc options: -lm -lpthread -O3

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 Samplesmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona1020304050SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3323033444433-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CXX) g++ options: -fopenmp -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 Samplesmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona918273645Min: 32 / Avg: 32 / Max: 32Min: 29 / Avg: 29.67 / Max: 30Min: 33 / Avg: 33 / Max: 33Min: 44 / Avg: 44 / Max: 44Min: 44 / Avg: 44 / Max: 44Min: 33 / Avg: 33 / Max: 331. (CXX) g++ options: -fopenmp -O3

Open FMM Nero2D

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen FMM Nero2D 2.0.2Total Timemarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona140280420560700534.42561.85531.27643.59636.99549.43-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CXX) g++ options: -O3 -lfftw3 -llapack -lblas -lgfortran -lquadmath -lm

PostgreSQL pgbench

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 8.4.11TPC-B Transactions Per Secondmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona400800120016002000SE +/- 1.46, N = 3SE +/- 33.50, N = 6SE +/- 33.91, N = 3SE +/- 40.09, N = 6SE +/- 8.45, N = 3SE +/- 18.47, N = 32037.111916.512039.711986.182018.342064.40-march=barcelona-march=bdver1-march=core2-march=k8-march=k8-sse3-march=nocona1. (CC) gcc options: -O3 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 8.4.11TPC-B Transactions Per Secondmarch=barcelonamarch=bdver1march=core2march=k8march=k8-sse3march=nocona400800120016002000Min: 2034.27 / Avg: 2037.11 / Max: 2039.14Min: 1770.31 / Avg: 1916.51 / Max: 2001.94Min: 1983.26 / Avg: 2039.71 / Max: 2100.48Min: 1881.69 / Avg: 1986.18 / Max: 2113.16Min: 2009.74 / Avg: 2018.34 / Max: 2035.24Min: 2030.9 / Avg: 2064.4 / Max: 2094.651. (CC) gcc options: -O3 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm