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/1205219-BY-1203270SU71 .
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 gcc42 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 AMD Opteron 6282 SE @ 2.60GHz (64 Cores) iXsystems AX4424-848A 1234567890 524288MB 10924GB FreeBSD 9.0-RELEASE (x86_64) GCC 4.2.1 20070831 + Clang 3.0 (SVN 142614) + LLVM 3.0 zfs 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 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, 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: Compiz was running on this system.
AMD Bulldozer bdver1 GCC 4.7 LLVM 3.1 Open64 Compiler graphics-magick: Blur graphics-magick: HWB Color Space graphics-magick: Local Adaptive Thresholding graphics-magick: Resizing graphics-magick: Sharpen byte: Dhrystone 2 himeno: Poisson Pressure Solver hmmer: Pfam Database Search c-ray: Total Time compress-lzma: 256MB File Compression 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 gcc42 99 156 68 130 64 20658131.60 533.49 16.57 52.73 152.31 70 106 26 83 28 611.13 18.64 44.78 160.40 63 91 25 71 28 14617671.60 399.49 15.94 56.16 160.53 117 159 67 148 102 19688800.73 596.68 17.29 26.92 152.39 70 106 26 83 28 425.86 18.66 44.71 159.67 62 87 22 72 35 15085911.93 420.44 16.05 44.31 162.12 13136704.77 193.91 21.34 9.86 306.55 OpenBenchmarking.org
GraphicsMagick Operation: Blur march=k8 march=bdver1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Blur GCC 4.7.0 LLVM-Clang 3.1 SVN AMD Open64 4.5.1 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 99 70 63 117 70 62 1. (CC) gcc options: -O3 -march=bdver1 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space march=k8 march=bdver1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: HWB Color Space GCC 4.7.0 LLVM-Clang 3.1 SVN AMD Open64 4.5.1 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 156 106 91 159 106 87 1. (CC) gcc options: -O3 -march=bdver1 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Local Adaptive Thresholding march=k8 march=bdver1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding GCC 4.7.0 LLVM-Clang 3.1 SVN AMD Open64 4.5.1 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 68 26 25 67 26 22 1. (CC) gcc options: -O3 -march=bdver1 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Resizing march=k8 march=bdver1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Resizing GCC 4.7.0 LLVM-Clang 3.1 SVN AMD Open64 4.5.1 30 60 90 120 150 SE +/- 0.58, 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 = 3 130 83 71 148 83 72 1. (CC) gcc options: -O3 -march=bdver1 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Sharpen march=k8 march=bdver1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Sharpen GCC 4.7.0 LLVM-Clang 3.1 SVN AMD Open64 4.5.1 20 40 60 80 100 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 +/- 0.00, N = 3 64 28 28 102 28 35 1. (CC) gcc options: -O3 -march=bdver1 -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 march=k8: GCC 4.7.0 march=k8: AMD Open64 4.5.1 march=bdver1: GCC 4.7.0 march=bdver1: AMD Open64 4.5.1 gcc42 4M 8M 12M 16M 20M SE +/- 126249.38, N = 3 SE +/- 87271.25, N = 3 SE +/- 110793.57, N = 3 SE +/- 94748.16, N = 3 SE +/- 11422.50, N = 3 20658131.60 14617671.60 19688800.73 15085911.93 13136704.77 -march=k8 -march=k8 -march=bdver1 -march=bdver1 1. (CC) gcc options: -O3
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver 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 gcc42 130 260 390 520 650 SE +/- 5.01, N = 3 SE +/- 0.53, N = 3 SE +/- 6.76, N = 4 SE +/- 2.62, N = 3 SE +/- 1.61, N = 3 SE +/- 0.21, N = 3 SE +/- 0.65, N = 3 533.49 611.13 399.49 596.68 425.86 420.44 193.91 -march=k8 -march=k8 -march=k8 -march=bdver1 -march=bdver1 -march=bdver1 1. (CC) gcc options: -O3
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search 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 gcc42 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 16.57 18.64 15.94 17.29 18.66 16.05 21.34 -march=k8 -march=k8 -march=k8 -march=bdver1 -march=bdver1 -march=bdver1 1. (CC) gcc options: -O3 -pthread -lhmmer -lsquid -lm
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time 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 gcc42 13 26 39 52 65 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 4 52.73 44.78 56.16 26.92 44.71 44.31 9.86 -march=k8 -march=k8 -march=k8 -march=bdver1 -march=bdver1 -march=bdver1 1. (CC) gcc options: -lm -lpthread -O3
LZMA Compression 256MB File Compression OpenBenchmarking.org Seconds, Fewer Is Better LZMA Compression 256MB File Compression 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 gcc42 70 140 210 280 350 SE +/- 0.25, N = 3 SE +/- 0.09, N = 3 SE +/- 0.29, N = 3 SE +/- 0.69, N = 3 SE +/- 0.23, N = 3 SE +/- 0.25, N = 3 SE +/- 0.55, N = 3 152.31 160.40 160.53 152.39 159.67 162.12 306.55 -march=k8 -march=k8 -march=k8 -march=bdver1 -march=bdver1 -march=bdver1 1. (CC) gcc options: -O3
Phoronix Test Suite v10.8.4