Open64 Bulldozer FX-8150 Compiler Testing the AMD Open64 4.2.5.2 compiler on an AMD FX-8150 eight-core Bulldozer under Ubuntu 11.10 64-bit with a Linux 3.1 kernel snapshot. Testing in stock compiler configuration and then various AMD compiler performance tuning options. Benchmarking managed by Michael Larabel for a future article on Phoronix.com. Stock: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 No Optimizations: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 O1 Local Optimizations: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 O3 Aggressive Optimizations: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 bdver1: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 bdver1 + Ofast: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 Auto-Parallelization: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 Huge Pages: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 Loop Nest Optimizations: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 Multi-Core Scalability: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 LNO Prefetch: Processor: AMD FX-8150 Eight-Core @ 3.61GHz (8 Cores), Motherboard: ASUS Crosshair V Formula, Chipset: ATI RD890 PCI to PCI bridge, Memory: 8192MB, Disk: 60GB OCZ VERTEX2, Graphics: NVIDIA GeForce GTX 460 768MB (675/1800MHz), Audio: Realtek ALC889, Network: Intel 82583V Gigabit Connection OS: Ubuntu 11.10, Kernel: 3.1.0-999-generic (x86_64), Desktop: Unity 4.22.0, Display Server: X Server 1.10.4, Display Driver: NVIDIA 290.03, OpenGL: 4.2.0 NVIDIA 290.03, Compiler: Open64 4.2.5.2, File-System: ext4, Screen Resolution: 1920x1080 Apache Benchmark 2.2.17 Static Web Page Serving Requests Per Second > Higher Is Better Stock ....................... 21522.42 |======================================= No Optimizations ............ 20546.10 |===================================== O1 Local Optimizations ...... 20734.08 |====================================== O3 Aggressive Optimizations . 21130.13 |====================================== bdver1 ...................... 21090.72 |====================================== Auto-Parallelization ........ 8177.35 |=============== Huge Pages .................. 21474.41 |======================================= Loop Nest Optimizations ..... 21328.23 |======================================= Multi-Core Scalability ...... 20860.34 |====================================== LNO Prefetch ................ 21338.56 |======================================= Timed PHP Compilation 5.2.9 Time To Compile Seconds < Lower Is Better Stock ....................... 37.59 |================================ No Optimizations ............ 22.87 |=================== O1 Local Optimizations ...... 29.10 |======================== O3 Aggressive Optimizations . 50.01 |========================================== bdver1 ...................... 36.70 |=============================== Auto-Parallelization ........ 41.81 |=================================== Huge Pages .................. 36.65 |=============================== Loop Nest Optimizations ..... 36.74 |=============================== Multi-Core Scalability ...... 36.61 |=============================== LNO Prefetch ................ 36.76 |=============================== Timed Apache Compilation 2.2.17 Time To Compile Seconds < Lower Is Better Stock ....................... 37.72 |=================================== No Optimizations ............ 21.14 |==================== O1 Local Optimizations ...... 31.33 |============================= O3 Aggressive Optimizations . 44.97 |========================================== bdver1 ...................... 37.29 |=================================== Auto-Parallelization ........ 40.28 |====================================== Huge Pages .................. 37.03 |=================================== Loop Nest Optimizations ..... 37.02 |=================================== Multi-Core Scalability ...... 37.04 |=================================== LNO Prefetch ................ 37.16 |=================================== POV-Ray 3.6.1 Total Time Seconds < Lower Is Better Stock ....................... 905 |==================== No Optimizations ............ 1939 |=========================================== O1 Local Optimizations ...... 1610 |==================================== O3 Aggressive Optimizations . 903 |==================== bdver1 ...................... 681 |=============== Auto-Parallelization ........ 873 |=================== Huge Pages .................. 891 |==================== Loop Nest Optimizations ..... 900 |==================== Multi-Core Scalability ...... 904 |==================== LNO Prefetch ................ 893 |==================== TTSIOD 3D Renderer 2.1v Phong Rendering With Soft-Shadow Mapping FPS > Higher Is Better Stock ....................... 23.65 |========================================= No Optimizations ............ 4.12 |======= O1 Local Optimizations ...... 5.35 |========= O3 Aggressive Optimizations . 24.34 |========================================== bdver1 ...................... 18.53 |================================ Auto-Parallelization ........ 18.09 |=============================== Huge Pages .................. 18.53 |================================ Loop Nest Optimizations ..... 17.40 |============================== Multi-Core Scalability ...... 18.81 |================================ LNO Prefetch ................ 17.96 |=============================== GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding Iterations Per Minute > Higher Is Better Stock ....................... 21 |=========================================== No Optimizations ............ 8 |================ O3 Aggressive Optimizations . 22 |============================================= bdver1 ...................... 22 |============================================= Auto-Parallelization ........ 19 |======================================= Huge Pages .................. 22 |============================================= Loop Nest Optimizations ..... 21 |=========================================== Multi-Core Scalability ...... 22 |============================================= GraphicsMagick 1.3.12 Operation: Resizing Iterations Per Minute > Higher Is Better Stock ....................... 69 |=========================================== No Optimizations ............ 28 |================= O3 Aggressive Optimizations . 73 |============================================= bdver1 ...................... 69 |=========================================== Auto-Parallelization ........ 69 |=========================================== Huge Pages .................. 69 |=========================================== Loop Nest Optimizations ..... 69 |=========================================== Multi-Core Scalability ...... 69 |=========================================== LAME MP3 Encoding 3.98.2 WAV To MP3 Seconds < Lower Is Better Stock ....................... 25.03 |============== No Optimizations ............ 75.08 |========================================== O1 Local Optimizations ...... 46.86 |========================== O3 Aggressive Optimizations . 25.90 |============== bdver1 ...................... 27.68 |=============== Auto-Parallelization ........ 35.51 |==================== Huge Pages .................. 27.64 |=============== Loop Nest Optimizations ..... 27.63 |=============== Multi-Core Scalability ...... 27.67 |=============== LNO Prefetch ................ 20.91 |============ Gcrypt Library 1.4.4 CAMELLIA256-ECB Cipher Microseconds < Lower Is Better Stock ....................... 1990 |======= No Optimizations ............ 11025 |====================================== O1 Local Optimizations ...... 12230 |========================================== O3 Aggressive Optimizations . 1903 |======= bdver1 ...................... 1990 |======= Auto-Parallelization ........ 1930 |======= Huge Pages .................. 1970 |======= Multi-Core Scalability ...... 2013 |======= LNO Prefetch ................ 2003 |=======