AMD Trinity bdver2 Piledriver Compiler Tuning AMD A10-5800K Trinity APU testing when trying out different compiler tuning flags from the GNU Compiler Collection (GCC) with different CPU micro-architecture targets. Benchmarked configurations from the AMD A10-5800K include -march=k8, -march=k8-sse3, -march=barcelona, -march=bdver1, and -march=bdver2. -march=bdver2 is the native target for the A10-5800K as a Bulldozer 2 / Piledriver product. Benchmarking for a future article on Phoronix.com.
HTML result view exported from: https://openbenchmarking.org/result/1210153-RA-AMDTRINIT61&grw&sor&rro .
AMD Trinity bdver2 Piledriver Compiler Tuning Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution k8 k8-sse3 barcelona bdver1 bdver2 AMD A10-5800K APU @ 3.80GHz (4 Cores) MSI A85XA-G65 (MS-7793) v1.0 AMD Family 15h 8192MB 60GB OCZ VERTEX2 AMD Radeon HD 7660D 512MB ATI R6xx HDMI DELL P2210H Realtek RTL8111/8168B Ubuntu 12.10 3.5.0-15-generic (x86_64) Unity 6.6.0 X Server 1.13.0 radeon 6.99.99 2.1 Mesa 9.0-devel Gallium 0.4 GCC 4.7 ext4 1920x1080 OpenBenchmarking.org Compiler Details - --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 Processor Details - Scaling Governor: ondemand System Details - Compiz was running on this system.
AMD Trinity bdver2 Piledriver Compiler Tuning encode-opus: WAV, Opus Encode, Opus Decode himeno: Poisson Pressure Solver build-php: Time To Compile nero2d: Total Time graphics-magick: Blur graphics-magick: Sharpen graphics-magick: Resizing graphics-magick: HWB Color Space graphics-magick: Local Adaptive Thresholding c-ray: Total Time smallpt: Global Illumination Renderer; 100 Samples k8 k8-sse3 barcelona bdver1 bdver2 13.45 699.55 53.02 657.99 65 41 103 132 72 104.07 83 13.41 681.50 53.00 654.78 68 41 103 132 72 104.11 83 13.55 687.97 52.94 540.59 81 69 117 143 70 70.03 61 12.82 708.32 55.49 519.77 96 76 126 141 67 52.22 56 12.98 678.33 55.55 521.41 100 77 125 142 68 52.42 56 OpenBenchmarking.org
Opus Codec Encoding WAV, Opus Encode, Opus Decode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.0.1 WAV, Opus Encode, Opus Decode barcelona k8 k8-sse3 bdver2 bdver1 3 6 9 12 15 SE +/- 0.05, N = 5 SE +/- 0.02, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.03, N = 5 13.55 13.45 13.41 12.98 12.82 -march=barcelona -march=k8 -march=k8-sse3 -march=bdver2 -march=bdver1 1. (CC) gcc options: -std=gnu99 -O3 -fPIE -pie -logg -lm -lopus
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver bdver2 k8-sse3 barcelona k8 bdver1 150 300 450 600 750 SE +/- 3.04, N = 3 SE +/- 1.44, N = 3 SE +/- 1.79, N = 3 SE +/- 0.41, N = 3 SE +/- 0.88, N = 3 678.33 681.50 687.97 699.55 708.32 -march=bdver2 -march=k8-sse3 -march=barcelona -march=k8 -march=bdver1 1. (CC) gcc options: -O3
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 5.2.9 Time To Compile bdver2 bdver1 k8 k8-sse3 barcelona 12 24 36 48 60 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 55.55 55.49 53.02 53.00 52.94 -march=bdver2 -march=bdver1 -march=k8 -march=k8-sse3 -march=barcelona 1. (CC) gcc options: -O3 -pedantic -ldl -lz -lm
Open FMM Nero2D Total Time OpenBenchmarking.org Seconds, Fewer Is Better Open FMM Nero2D 2.0.2 Total Time k8 k8-sse3 barcelona bdver2 bdver1 140 280 420 560 700 657.99 654.78 540.59 521.41 519.77 -march=k8 -march=k8-sse3 -march=barcelona -march=bdver2 -march=bdver1 1. (CXX) g++ options: -O3 -lfftw3 -llapack -lblas -lgfortran -lquadmath -lm
GraphicsMagick Operation: Blur OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Blur k8 k8-sse3 barcelona bdver1 bdver2 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 65 68 81 96 100 -march=k8 -march=k8-sse3 -march=barcelona -march=bdver1 -march=bdver2 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Sharpen k8 k8-sse3 barcelona bdver1 bdver2 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 41 41 69 76 77 -march=k8 -march=k8-sse3 -march=barcelona -march=bdver1 -march=bdver2 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Resizing k8 k8-sse3 barcelona bdver2 bdver1 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 103 103 117 125 126 -march=k8 -march=k8-sse3 -march=barcelona -march=bdver2 -march=bdver1 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: HWB Color Space k8 k8-sse3 bdver1 bdver2 barcelona 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 132 132 141 142 143 -march=k8 -march=k8-sse3 -march=bdver1 -march=bdver2 -march=barcelona 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Local Adaptive Thresholding bdver1 bdver2 barcelona k8 k8-sse3 16 32 48 64 80 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 67 68 70 72 72 -march=bdver1 -march=bdver2 -march=barcelona -march=k8 -march=k8-sse3 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time k8-sse3 k8 barcelona bdver2 bdver1 20 40 60 80 100 SE +/- 0.25, N = 3 SE +/- 0.23, N = 3 SE +/- 0.15, N = 3 SE +/- 0.23, N = 3 SE +/- 0.20, N = 3 104.11 104.07 70.03 52.42 52.22 -march=k8-sse3 -march=k8 -march=barcelona -march=bdver2 -march=bdver1 1. (CC) gcc options: -lm -lpthread -O3
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples k8-sse3 k8 barcelona bdver2 bdver1 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 83 83 61 56 56 -march=k8-sse3 -march=k8 -march=barcelona -march=bdver2 -march=bdver1 1. (CXX) g++ options: -fopenmp -O3
Phoronix Test Suite v10.8.5