AMD FX-8150 Bulldozer bdver1 GCC 4.7 Tuning

Using GCC 4.7.0 on an AMD FX-8150 Bulldozer eight-core CPU from an ASUS motherboard running a near final Ubuntu 12.04 LTS x86_64 with the Linux 3.2 kernel. Testing of vanilla GCC 4.7..0 and running some open-source computational tests when using CFLAGS/CXXFLAGS of -O3 and then varying -march= flags. The march= GCC 4.7 options tested for the AMD Bulldozer FX-8150 were k8, k8-sse3, barcelona, btver1, and bdver1 (optimal). Testing for a future article on Phoronix.com by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1203277-SU-BDVER1TUN05
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 3 Tests
CPU Massive 3 Tests
Creator Workloads 2 Tests
Multi-Core 2 Tests
Server CPU Tests 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
march=k8
March 27 2012
 
march=k8-sse3
March 27 2012
 
march=btver1
March 27 2012
 
march=barcelona
March 27 2012
 
march=bdver1
March 27 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):


AMD FX-8150 Bulldozer bdver1 GCC 4.7 TuningOpenBenchmarking.orgPhoronix Test SuiteAMD FX-8150 Eight-Core @ 3.60GHz (8 Cores)ASUS Crosshair V FormulaAMD nee ATI RD89016384MB240GB OCZ VERTEX3AMD Radeon HD 6570 512MBRealtek ALC889DELL P2210HIntel 82583V Gigabit ConnectionUbuntu 12.043.2.0-20-generic (x86_64)Unity 5.6.0X Server 1.11.3radeon 6.14.992.1 Mesa 8.0.2 Gallium 0.4GCC 4.7.0ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionAMD FX-8150 Bulldozer Bdver1 GCC 4.7 Tuning BenchmarksSystem Logs- --enable-checking=release --enable-languages=c,c++,fortran --enable-lto- Scaling Governor: ondemand- Compiz was running on this system.

march=k8march=k8-sse3march=btver1march=barcelonamarch=bdver1Result OverviewPhoronix Test Suite100%124%148%172%196%C-RayGraphicsMagickHimeno BenchmarkGraphicsMagickGraphicsMagickTotal TimeSharpenP.P.SBlurResizing

AMD FX-8150 Bulldozer bdver1 GCC 4.7 Tuninggraphics-magick: Blurgraphics-magick: Resizinggraphics-magick: Sharpenhimeno: Poisson Pressure Solverc-ray: Total Timemarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver19913064533.4952.739512964651.4452.759813065661.7647.3010714088662.4036.00117148102596.6826.92OpenBenchmarking.org

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Blurmarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver1306090120150SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3999598107117-march=k8-march=k8-sse3-march=btver1-march=barcelona-march=bdver11. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lrt -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Blurmarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver120406080100Min: 98 / Avg: 98.67 / Max: 99Min: 94 / Avg: 94.67 / Max: 95Min: 98 / Avg: 98 / Max: 98Min: 106 / Avg: 106.67 / Max: 107Min: 117 / Avg: 117 / Max: 1171. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lrt -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Resizingmarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver1306090120150SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3130129130140148-march=k8-march=k8-sse3-march=btver1-march=barcelona-march=bdver11. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lrt -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Resizingmarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver1306090120150Min: 129 / Avg: 130 / Max: 131Min: 129 / Avg: 129.33 / Max: 130Min: 130 / Avg: 130.33 / Max: 131Min: 140 / Avg: 140 / Max: 140Min: 148 / Avg: 148 / Max: 1481. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lrt -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Sharpenmarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver120406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 364646588102-march=k8-march=k8-sse3-march=btver1-march=barcelona-march=bdver11. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lrt -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.12Operation: Sharpenmarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver120406080100Min: 64 / Avg: 64 / Max: 64Min: 64 / Avg: 64 / Max: 64Min: 65 / Avg: 65 / Max: 65Min: 88 / Avg: 88 / Max: 88Min: 102 / Avg: 102 / Max: 1021. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lrt -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=k8march=k8-sse3march=btver1march=barcelonamarch=bdver1140280420560700SE +/- 5.01, N = 3SE +/- 0.51, N = 3SE +/- 0.37, N = 3SE +/- 0.83, N = 3SE +/- 2.62, N = 3533.49651.44661.76662.40596.68-march=k8-march=k8-sse3-march=btver1-march=barcelona-march=bdver11. (CC) gcc options: -O3
OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solvermarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver1120240360480600Min: 524.98 / Avg: 533.49 / Max: 542.32Min: 650.68 / Avg: 651.44 / Max: 652.41Min: 661.21 / Avg: 661.76 / Max: 662.47Min: 661.14 / Avg: 662.4 / Max: 663.97Min: 593.88 / Avg: 596.68 / Max: 601.921. (CC) gcc options: -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.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Timemarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver11224364860SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 352.7352.7547.3036.0026.92-march=k8-march=k8-sse3-march=btver1-march=barcelona-march=bdver11. (CC) gcc options: -lm -lpthread -O3
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Timemarch=k8march=k8-sse3march=btver1march=barcelonamarch=bdver11122334455Min: 52.71 / Avg: 52.73 / Max: 52.76Min: 52.75 / Avg: 52.75 / Max: 52.76Min: 47.28 / Avg: 47.3 / Max: 47.34Min: 35.97 / Avg: 36 / Max: 36.04Min: 26.9 / Avg: 26.92 / Max: 26.951. (CC) gcc options: -lm -lpthread -O3