AMD Bulldozer bdver1 GCC 4.7 LLVM 3.1 Open64 Compiler GCC 4.7.0 and LLVM / Clang 3.1 SVN (as of 27 March 2012) and AMD Open64 4.5.1 testing from an AMD FX-8150 Bulldozer Eight-Core (bdver1). Testing of GCC 4.7 and LLVM/Clang 3.1 and AMD Open64 4.5.1 when building the tests with "-march=k8 -O3" CFLAGS/CXXFLAGS and then again when using "-march=native -O3" for tapping the bdver1 compiler optimizations for AMD Bulldozer. Benchmarking for a future article on Phoronix.com. Both compilers were in a release build per the compiler configurations listed on system table. The AMD Open64 release from the AMD-provided x86_64 binary.
HTML result view exported from: https://openbenchmarking.org/result/1204189-BY-1203270SU74&grw&sro .
AMD Bulldozer bdver1 GCC 4.7 LLVM 3.1 Open64 Compiler Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=bdver1: AMD Open64 4.5.1 w510-intel-i7-bulldozer-comparison AMD FX-8150 Eight-Core @ 3.60GHz (8 Cores) ASUS Crosshair V Formula AMD nee ATI RD890 16384MB 240GB OCZ VERTEX3 AMD Radeon HD 6570 512MB Realtek ALC889 DELL P2210H Intel 82583V Gigabit Connection Ubuntu 12.04 3.2.0-20-generic (x86_64) Unity 5.6.0 X Server 1.11.3 radeon 6.14.99 2.1 Mesa 8.0.2 Gallium 0.4 GCC 4.7.0 ext4 1920x1080 Clang 3.1 (SVN 153515) + LLVM 3.1svn Open64 4.5.1 GCC 4.7.0 Clang 3.1 (SVN 153515) + LLVM 3.1svn Open64 4.5.1 Intel Core i7 820Q @ 1.73GHz (8 Cores) LENOVO 438924U Intel Core DMI 8192MB 320GB HITACHI HTS72503 NVIDIA Quadro FX 880M 1024MB (550/790MHz) Intel 5 /3400 Intel 82577LM Gigabit Connection + Intel Centrino Ultimate-N 6300 Fedora 17 3.3.2-1.fc17.x86_64 (x86_64) GNOME Shell 3.4.0 X Server 1.12.0 NVIDIA 295.40 3.3.0 NVIDIA GCC 4.7.0 20120416 3200x1200 OpenBenchmarking.org Compiler Details - march=k8: GCC 4.7.0: --enable-checking=release --enable-languages=c,c++,fortran --enable-lto - march=k8: LLVM-Clang 3.1 SVN: Optimized build; Built Mar 27 2012 (12:06:27); Default target: x86_64-unknown-linux-gnu; Host CPU: bdver1 - march=bdver1: GCC 4.7.0: --enable-checking=release --enable-languages=c,c++,fortran --enable-lto - march=bdver1: LLVM-Clang 3.1 SVN: Optimized build; Built Mar 27 2012 (12:06:27); Default target: x86_64-unknown-linux-gnu; Host CPU: bdver1 - w510-intel-i7-bulldozer-comparison: --build=x86_64-redhat-linux --disable-build-poststage1-with-cxx --disable-build-with-cxx --disable-dssi --disable-libjava-multilib --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-checking=release --enable-gnu-unique-object --enable-initfini-array --enable-java-awt=gtk --enable-java-maintainer-mode --enable-languages=c,c++,objc,obj-c++,java,fortran,ada,go,lto --enable-libgcj-multifile --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-cloog --with-ecj-jar=/usr/share/java/eclipse-ecj.jar --with-java-home=/usr/lib/jvm/java-1.5.0-gcj-1.5.0.0/jre --with-linker-hash-style=gnu --with-ppl --with-tune=generic Processor Details - march=k8: GCC 4.7.0, march=k8: LLVM-Clang 3.1 SVN, march=k8: AMD Open64 4.5.1, march=bdver1: GCC 4.7.0, march=bdver1: LLVM-Clang 3.1 SVN, march=bdver1: AMD Open64 4.5.1: Scaling Governor: ondemand System Details - march=k8: GCC 4.7.0: Compiz was running on this system. - march=k8: LLVM-Clang 3.1 SVN: Compiz was running on this system. - march=k8: AMD Open64 4.5.1: Compiz was running on this system. - march=bdver1: GCC 4.7.0: Compiz was running on this system. - march=bdver1: LLVM-Clang 3.1 SVN: Compiz was running on this system. - march=bdver1: AMD Open64 4.5.1: Compiz was running on this system. - w510-intel-i7-bulldozer-comparison: Firefox was running on this system.
AMD Bulldozer bdver1 GCC 4.7 LLVM 3.1 Open64 Compiler compress-lzma: 256MB File Compression hmmer: Pfam Database Search himeno: Poisson Pressure Solver graphics-magick: Blur graphics-magick: HWB Color Space graphics-magick: Local Adaptive Thresholding graphics-magick: Resizing graphics-magick: Sharpen c-ray: Total Time byte: Dhrystone 2 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=bdver1: AMD Open64 4.5.1 w510-intel-i7-bulldozer-comparison 152.31 16.57 533.49 99 156 68 130 64 52.73 20658131.60 160.40 18.64 611.13 70 106 26 83 28 44.78 160.53 15.94 399.49 63 91 25 71 28 56.16 14617671.60 152.39 17.29 596.68 117 159 67 148 102 26.92 19688800.73 159.67 18.66 425.86 70 106 26 83 28 44.71 162.12 16.05 420.44 62 87 22 72 35 44.31 15085911.93 153.26 26.46 1110.97 77 112 42 88 42 74.16 18151277.53 OpenBenchmarking.org
LZMA Compression 256MB File Compression OpenBenchmarking.org Seconds, Fewer Is Better LZMA Compression 256MB File Compression march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 40 80 120 160 200 SE +/- 0.25, N = 3 SE +/- 0.69, N = 3 SE +/- 0.23, N = 3 SE +/- 0.29, N = 3 SE +/- 0.25, N = 3 SE +/- 0.09, N = 3 SE +/- 0.72, N = 3 162.12 152.39 159.67 160.53 152.31 160.40 153.26 -O3 -march=bdver1 -O3 -march=bdver1 -O3 -march=bdver1 -O3 -march=k8 -O3 -march=k8 -O3 -march=k8 -O2 1. (CC) gcc options:
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.26, N = 3 16.05 17.29 18.66 15.94 16.57 18.64 26.46 -O3 -march=bdver1 -O3 -march=bdver1 -O3 -march=bdver1 -O3 -march=k8 -O3 -march=k8 -O3 -march=k8 -O2 1. (CC) gcc options: -pthread -lhmmer -lsquid -lm
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 200 400 600 800 1000 SE +/- 0.21, N = 3 SE +/- 2.62, N = 3 SE +/- 1.61, N = 3 SE +/- 6.76, N = 4 SE +/- 5.01, N = 3 SE +/- 0.53, N = 3 SE +/- 10.79, N = 3 420.44 596.68 425.86 399.49 533.49 611.13 1110.97 -march=bdver1 -march=bdver1 -march=bdver1 -march=k8 -march=k8 -march=k8 1. (CC) gcc options: -O3
GraphicsMagick Operation: Blur OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Blur march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 62 117 70 63 99 70 77 -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -lrt -O3 -march=bdver1 -ljpeg -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -lrt -O3 -march=k8 -ljpeg -std=gnu99 -fopenmp -O2 -lfreetype -ljpeg -lxml2 -lgomp 1. (CC) gcc options: -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: HWB Color Space march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.88, N = 3 87 159 106 91 156 106 112 -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -lrt -O3 -march=bdver1 -ljpeg -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -lrt -O3 -march=k8 -ljpeg -std=gnu99 -fopenmp -O2 -lfreetype -ljpeg -lxml2 -lgomp 1. (CC) gcc options: -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 15 30 45 60 75 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 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 22 67 26 25 68 26 42 -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -lrt -O3 -march=bdver1 -ljpeg -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -lrt -O3 -march=k8 -ljpeg -std=gnu99 -fopenmp -O2 -lfreetype -ljpeg -lxml2 -lgomp 1. (CC) gcc options: -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Resizing march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 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 +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 1.53, N = 3 72 148 83 71 130 83 88 -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -lrt -O3 -march=bdver1 -ljpeg -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -lrt -O3 -march=k8 -ljpeg -std=gnu99 -fopenmp -O2 -lfreetype -ljpeg -lxml2 -lgomp 1. (CC) gcc options: -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Sharpen march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 35 102 28 28 64 28 42 -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=bdver1 -ltiff -lfreetype -lrt -O3 -march=bdver1 -ljpeg -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -std=gnu99 -fopenmp -O3 -march=k8 -ltiff -lfreetype -lrt -O3 -march=k8 -ljpeg -std=gnu99 -fopenmp -O2 -lfreetype -ljpeg -lxml2 -lgomp 1. (CC) gcc options: -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: LLVM-Clang 3.1 SVN march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 march=k8: LLVM-Clang 3.1 SVN w510-intel-i7-bulldozer-comparison 16 32 48 64 80 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.42, N = 3 44.31 26.92 44.71 56.16 52.73 44.78 74.16 -march=bdver1 -march=bdver1 -march=bdver1 -march=k8 -march=k8 -march=k8 1. (CC) gcc options: -lm -lpthread -O3
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 march=bdver1: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=k8: AMD Open64 4.5.1 march=k8: GCC 4.7.0 w510-intel-i7-bulldozer-comparison 4M 8M 12M 16M 20M SE +/- 94748.16, N = 3 SE +/- 110793.57, N = 3 SE +/- 87271.25, N = 3 SE +/- 126249.38, N = 3 SE +/- 212037.14, N = 3 15085911.93 19688800.73 14617671.60 20658131.60 18151277.53 -O3 -march=bdver1 -O3 -march=bdver1 -O3 -march=k8 -O3 -march=k8 1. (CC) gcc options:
Phoronix Test Suite v10.8.4