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. march=k8: GCC 4.7.0: Processor: AMD FX-8150 Eight-Core @ 3.60GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: AMD nee ATI RD890, Memory: 16384MB, Disk: 240GB OCZ VERTEX3, Graphics: AMD Radeon HD 6570 512MB, Audio: Realtek ALC889, Monitor: DELL P2210H, Network: Intel 82583V Gigabit Connection OS: Ubuntu 12.04, Kernel: 3.2.0-20-generic (x86_64), Desktop: Unity 5.6.0, Display Server: X Server 1.11.3, Display Driver: radeon 6.14.99, OpenGL: 2.1 Mesa 8.0.2 Gallium 0.4, Compiler: GCC 4.7.0, File-System: ext4, Screen Resolution: 1920x1080 march=k8: LLVM-Clang 3.1 SVN: Processor: AMD FX-8150 Eight-Core @ 3.60GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: AMD nee ATI RD890, Memory: 16384MB, Disk: 240GB OCZ VERTEX3, Graphics: AMD Radeon HD 6570 512MB, Audio: Realtek ALC889, Monitor: DELL P2210H, Network: Intel 82583V Gigabit Connection OS: Ubuntu 12.04, Kernel: 3.2.0-20-generic (x86_64), Desktop: Unity 5.6.0, Display Server: X Server 1.11.3, Display Driver: radeon 6.14.99, OpenGL: 2.1 Mesa 8.0.2 Gallium 0.4, Compiler: Clang 3.1 (SVN 153515) + LLVM 3.1svn, File-System: ext4, Screen Resolution: 1920x1080 march=k8: AMD Open64 4.5.1: Processor: AMD FX-8150 Eight-Core @ 3.60GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: AMD nee ATI RD890, Memory: 16384MB, Disk: 240GB OCZ VERTEX3, Graphics: AMD Radeon HD 6570 512MB, Audio: Realtek ALC889, Monitor: DELL P2210H, Network: Intel 82583V Gigabit Connection OS: Ubuntu 12.04, Kernel: 3.2.0-20-generic (x86_64), Desktop: Unity 5.6.0, Display Server: X Server 1.11.3, Display Driver: radeon 6.14.99, OpenGL: 2.1 Mesa 8.0.2 Gallium 0.4, Compiler: Open64 4.5.1, File-System: ext4, Screen Resolution: 1920x1080 march=bdver1: GCC 4.7.0: Processor: AMD FX-8150 Eight-Core @ 3.60GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: AMD nee ATI RD890, Memory: 16384MB, Disk: 240GB OCZ VERTEX3, Graphics: AMD Radeon HD 6570 512MB, Audio: Realtek ALC889, Monitor: DELL P2210H, Network: Intel 82583V Gigabit Connection OS: Ubuntu 12.04, Kernel: 3.2.0-20-generic (x86_64), Desktop: Unity 5.6.0, Display Server: X Server 1.11.3, Display Driver: radeon 6.14.99, OpenGL: 2.1 Mesa 8.0.2 Gallium 0.4, Compiler: GCC 4.7.0, File-System: ext4, Screen Resolution: 1920x1080 march=bdver1: LLVM-Clang 3.1 SVN: Processor: AMD FX-8150 Eight-Core @ 3.60GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: AMD nee ATI RD890, Memory: 16384MB, Disk: 240GB OCZ VERTEX3, Graphics: AMD Radeon HD 6570 512MB, Audio: Realtek ALC889, Monitor: DELL P2210H, Network: Intel 82583V Gigabit Connection OS: Ubuntu 12.04, Kernel: 3.2.0-20-generic (x86_64), Desktop: Unity 5.6.0, Display Server: X Server 1.11.3, Display Driver: radeon 6.14.99, OpenGL: 2.1 Mesa 8.0.2 Gallium 0.4, Compiler: Clang 3.1 (SVN 153515) + LLVM 3.1svn, File-System: ext4, Screen Resolution: 1920x1080 march=bdver1: AMD Open64 4.5.1: Processor: AMD FX-8150 Eight-Core @ 3.60GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: AMD nee ATI RD890, Memory: 16384MB, Disk: 240GB OCZ VERTEX3, Graphics: AMD Radeon HD 6570 512MB, Audio: Realtek ALC889, Monitor: DELL P2210H, Network: Intel 82583V Gigabit Connection OS: Ubuntu 12.04, Kernel: 3.2.0-20-generic (x86_64), Desktop: Unity 5.6.0, Display Server: X Server 1.11.3, Display Driver: radeon 6.14.99, OpenGL: 2.1 Mesa 8.0.2 Gallium 0.4, Compiler: Open64 4.5.1, File-System: ext4, Screen Resolution: 1920x1080 w510-intel-i7-bulldozer-comparison: Processor: Intel Core i7 820Q @ 1.73GHz (8 Cores), Motherboard: LENOVO 438924U, Chipset: Intel Core DMI, Memory: 8192MB, Disk: 320GB HITACHI HTS72503, Graphics: NVIDIA Quadro FX 880M 1024MB (550/790MHz), Audio: Intel 5 /3400, Network: Intel 82577LM Gigabit Connection + Intel Centrino Ultimate-N 6300 OS: Fedora 17, Kernel: 3.3.2-1.fc17.x86_64 (x86_64), Desktop: GNOME Shell 3.4.0, Display Server: X Server 1.12.0, Display Driver: NVIDIA 295.40, OpenGL: 3.3.0 NVIDIA, Compiler: GCC 4.7.0 20120416, File-System: ext4, Screen Resolution: 3200x1200 GraphicsMagick 1.3.12 Operation: Blur Iterations Per Minute > Higher Is Better march=k8: GCC 4.7.0 ................ 99 |=============================== march=k8: LLVM-Clang 3.1 SVN ....... 70 |====================== march=k8: AMD Open64 4.5.1 ......... 63 |==================== march=bdver1: GCC 4.7.0 ............ 117 |===================================== march=bdver1: LLVM-Clang 3.1 SVN ... 70 |====================== march=bdver1: AMD Open64 4.5.1 ..... 62 |==================== w510-intel-i7-bulldozer-comparison . 77 |======================== GraphicsMagick 1.3.12 Operation: HWB Color Space Iterations Per Minute > Higher Is Better march=k8: GCC 4.7.0 ................ 156 |==================================== march=k8: LLVM-Clang 3.1 SVN ....... 106 |========================= march=k8: AMD Open64 4.5.1 ......... 91 |===================== march=bdver1: GCC 4.7.0 ............ 159 |===================================== march=bdver1: LLVM-Clang 3.1 SVN ... 106 |========================= march=bdver1: AMD Open64 4.5.1 ..... 87 |==================== w510-intel-i7-bulldozer-comparison . 112 |========================== GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding Iterations Per Minute > Higher Is Better march=k8: GCC 4.7.0 ................ 68 |====================================== march=k8: LLVM-Clang 3.1 SVN ....... 26 |=============== march=k8: AMD Open64 4.5.1 ......... 25 |============== march=bdver1: GCC 4.7.0 ............ 67 |===================================== march=bdver1: LLVM-Clang 3.1 SVN ... 26 |=============== march=bdver1: AMD Open64 4.5.1 ..... 22 |============ w510-intel-i7-bulldozer-comparison . 42 |======================= GraphicsMagick 1.3.12 Operation: Resizing Iterations Per Minute > Higher Is Better march=k8: GCC 4.7.0 ................ 130 |================================= march=k8: LLVM-Clang 3.1 SVN ....... 83 |===================== march=k8: AMD Open64 4.5.1 ......... 71 |================== march=bdver1: GCC 4.7.0 ............ 148 |===================================== march=bdver1: LLVM-Clang 3.1 SVN ... 83 |===================== march=bdver1: AMD Open64 4.5.1 ..... 72 |================== w510-intel-i7-bulldozer-comparison . 88 |====================== GraphicsMagick 1.3.12 Operation: Sharpen Iterations Per Minute > Higher Is Better march=k8: GCC 4.7.0 ................ 64 |======================= march=k8: LLVM-Clang 3.1 SVN ....... 28 |========== march=k8: AMD Open64 4.5.1 ......... 28 |========== march=bdver1: GCC 4.7.0 ............ 102 |===================================== march=bdver1: LLVM-Clang 3.1 SVN ... 28 |========== march=bdver1: AMD Open64 4.5.1 ..... 35 |============= w510-intel-i7-bulldozer-comparison . 42 |=============== BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 LPS > Higher Is Better march=k8: GCC 4.7.0 ................ 20658131.60 |============================= march=k8: AMD Open64 4.5.1 ......... 14617671.60 |===================== march=bdver1: GCC 4.7.0 ............ 19688800.73 |============================ march=bdver1: AMD Open64 4.5.1 ..... 15085911.93 |===================== w510-intel-i7-bulldozer-comparison . 18151277.53 |========================= Himeno Benchmark 3.0 Poisson Pressure Solver MFLOPS > Higher Is Better march=k8: GCC 4.7.0 ................ 533.49 |================ march=k8: LLVM-Clang 3.1 SVN ....... 611.13 |================== march=k8: AMD Open64 4.5.1 ......... 399.49 |============ march=bdver1: GCC 4.7.0 ............ 596.68 |================== march=bdver1: LLVM-Clang 3.1 SVN ... 425.86 |============= march=bdver1: AMD Open64 4.5.1 ..... 420.44 |============ w510-intel-i7-bulldozer-comparison . 1110.97 |================================= Timed HMMer Search 2.3.2 Pfam Database Search Seconds < Lower Is Better march=k8: GCC 4.7.0 ................ 16.57 |====================== march=k8: LLVM-Clang 3.1 SVN ....... 18.64 |========================= march=k8: AMD Open64 4.5.1 ......... 15.94 |===================== march=bdver1: GCC 4.7.0 ............ 17.29 |======================= march=bdver1: LLVM-Clang 3.1 SVN ... 18.66 |========================= march=bdver1: AMD Open64 4.5.1 ..... 16.05 |===================== w510-intel-i7-bulldozer-comparison . 26.46 |=================================== C-Ray 1.1 Total Time Seconds < Lower Is Better march=k8: GCC 4.7.0 ................ 52.73 |========================= march=k8: LLVM-Clang 3.1 SVN ....... 44.78 |===================== march=k8: AMD Open64 4.5.1 ......... 56.16 |=========================== march=bdver1: GCC 4.7.0 ............ 26.92 |============= march=bdver1: LLVM-Clang 3.1 SVN ... 44.71 |===================== march=bdver1: AMD Open64 4.5.1 ..... 44.31 |===================== w510-intel-i7-bulldozer-comparison . 74.16 |=================================== LZMA Compression 256MB File Compression Seconds < Lower Is Better march=k8: GCC 4.7.0 ................ 152.31 |================================ march=k8: LLVM-Clang 3.1 SVN ....... 160.40 |================================== march=k8: AMD Open64 4.5.1 ......... 160.53 |================================== march=bdver1: GCC 4.7.0 ............ 152.39 |================================ march=bdver1: LLVM-Clang 3.1 SVN ... 159.67 |================================= march=bdver1: AMD Open64 4.5.1 ..... 162.12 |================================== w510-intel-i7-bulldozer-comparison . 153.26 |================================