Compiler Optimizations For AMD Steamroller/Kaveri Compiler benchmarks by Michael Larabel for a future article on Phoronix.com k8: Processor: AMD A10-7800 Radeon R7 12 Compute Cores 4C+8G @ 3.50GHz (4 Cores), Motherboard: ASUS A88X-PRO, Chipset: AMD Family 15h, Memory: 7168MB, Disk: 64GB OCZ AGILITY, Graphics: ASUS AMD Radeon R7 200 1024MB, Audio: AMD Kaveri HDMI/DP, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 14.04, Kernel: 3.16.0-031600-generic (x86_64), Desktop: Unity 7.2.2, Display Server: X Server 1.15.1, Display Driver: radeon 7.4.99, OpenGL: 3.3 Mesa 10.3.0-devel (git-b1843a2 2014-08-10 trusty-oibaf-ppa+gallium-nine) Gallium 0.4, Compiler: GCC 4.10.0 20140810, File-System: ext4, Screen Resolution: 2560x1600 k8-sse3: Processor: AMD A10-7800 Radeon R7 12 Compute Cores 4C+8G @ 3.50GHz (4 Cores), Motherboard: ASUS A88X-PRO, Chipset: AMD Family 15h, Memory: 7168MB, Disk: 64GB OCZ AGILITY, Graphics: ASUS AMD Radeon R7 200 1024MB, Audio: AMD Kaveri HDMI/DP, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 14.04, Kernel: 3.16.0-031600-generic (x86_64), Desktop: Unity 7.2.2, Display Server: X Server 1.15.1, Display Driver: radeon 7.4.99, OpenGL: 3.3 Mesa 10.3.0-devel (git-b1843a2 2014-08-10 trusty-oibaf-ppa+gallium-nine) Gallium 0.4, Compiler: GCC 4.10.0 20140810, File-System: ext4, Screen Resolution: 2560x1600 barcelona: Processor: AMD A10-7800 Radeon R7 12 Compute Cores 4C+8G @ 3.50GHz (4 Cores), Motherboard: ASUS A88X-PRO, Chipset: AMD Family 15h, Memory: 7168MB, Disk: 64GB OCZ AGILITY, Graphics: ASUS AMD Radeon R7 200 1024MB, Audio: AMD Kaveri HDMI/DP, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 14.04, Kernel: 3.16.0-031600-generic (x86_64), Desktop: Unity 7.2.2, Display Server: X Server 1.15.1, Display Driver: radeon 7.4.99, OpenGL: 3.3 Mesa 10.3.0-devel (git-b1843a2 2014-08-10 trusty-oibaf-ppa+gallium-nine) Gallium 0.4, Compiler: GCC 4.10.0 20140810, File-System: ext4, Screen Resolution: 2560x1600 bdver1: Processor: AMD A10-7800 Radeon R7 12 Compute Cores 4C+8G @ 3.50GHz (4 Cores), Motherboard: ASUS A88X-PRO, Chipset: AMD Family 15h, Memory: 7168MB, Disk: 64GB OCZ AGILITY, Graphics: ASUS AMD Radeon R7 200 1024MB, Audio: AMD Kaveri HDMI/DP, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 14.04, Kernel: 3.16.0-031600-generic (x86_64), Desktop: Unity 7.2.2, Display Server: X Server 1.15.1, Display Driver: radeon 7.4.99, OpenGL: 3.3 Mesa 10.3.0-devel (git-b1843a2 2014-08-10 trusty-oibaf-ppa+gallium-nine) Gallium 0.4, Compiler: GCC 4.10.0 20140810, File-System: ext4, Screen Resolution: 2560x1600 bdver2: Processor: AMD A10-7800 Radeon R7 12 Compute Cores 4C+8G @ 3.50GHz (4 Cores), Motherboard: ASUS A88X-PRO, Chipset: AMD Family 15h, Memory: 7168MB, Disk: 64GB OCZ AGILITY, Graphics: ASUS AMD Radeon R7 200 1024MB, Audio: AMD Kaveri HDMI/DP, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 14.04, Kernel: 3.16.0-031600-generic (x86_64), Desktop: Unity 7.2.2, Display Server: X Server 1.15.1, Display Driver: radeon 7.4.99, OpenGL: 3.3 Mesa 10.3.0-devel (git-b1843a2 2014-08-10 trusty-oibaf-ppa+gallium-nine) Gallium 0.4, Compiler: GCC 4.10.0 20140810, File-System: ext4, Screen Resolution: 2560x1600 bdver3: Processor: AMD A10-7800 Radeon R7 12 Compute Cores 4C+8G @ 3.50GHz (4 Cores), Motherboard: ASUS A88X-PRO, Chipset: AMD Family 15h, Memory: 7168MB, Disk: 64GB OCZ AGILITY, Graphics: ASUS AMD Radeon R7 200 1024MB, Audio: AMD Kaveri HDMI/DP, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 14.04, Kernel: 3.16.0-031600-generic (x86_64), Desktop: Unity 7.2.2, Display Server: X Server 1.15.1, Display Driver: radeon 7.4.99, OpenGL: 3.3 Mesa 10.3.0-devel (git-b1843a2 2014-08-10 trusty-oibaf-ppa+gallium-nine) Gallium 0.4, Compiler: GCC 4.10.0 20140810, File-System: ext4, Screen Resolution: 2560x1600 bdver3 + flto: Processor: AMD A10-7800 Radeon R7 12 Compute Cores 4C+8G @ 3.50GHz (4 Cores), Motherboard: ASUS A88X-PRO, Chipset: AMD Family 15h, Memory: 7168MB, Disk: 64GB OCZ AGILITY, Graphics: ASUS AMD Radeon R7 200 1024MB, Audio: AMD Kaveri HDMI/DP, Monitor: SyncMaster, Network: Realtek RTL8111/8168/8411 OS: Ubuntu 14.04, Kernel: 3.16.0-031600-generic (x86_64), Desktop: Unity 7.2.2, Display Server: X Server 1.15.1, Display Driver: radeon 7.4.99, OpenGL: 3.3 Mesa 10.3.0-devel (git-b1843a2 2014-08-10 trusty-oibaf-ppa+gallium-nine) Gallium 0.4, Compiler: GCC 4.10.0 20140810, File-System: ext4, Screen Resolution: 2560x1600 GraphicsMagick 1.3.19 Operation: Blur Iterations Per Minute > Higher Is Better k8 ............ 77 |============================================= k8-sse3 ....... 92 |===================================================== barcelona ..... 91 |===================================================== bdver1 ........ 100 |========================================================== bdver2 ........ 100 |========================================================== bdver3 ........ 100 |========================================================== bdver3 + flto . 100 |========================================================== GraphicsMagick 1.3.19 Operation: Sharpen Iterations Per Minute > Higher Is Better k8 ............ 42 |==================================== k8-sse3 ....... 42 |==================================== barcelona ..... 58 |================================================== bdver1 ........ 68 |=========================================================== bdver2 ........ 67 |========================================================== bdver3 ........ 67 |========================================================== bdver3 + flto . 67 |========================================================== GraphicsMagick 1.3.19 Operation: Resizing Iterations Per Minute > Higher Is Better k8 ............ 102 |================================================ k8-sse3 ....... 102 |================================================ barcelona ..... 119 |======================================================== bdver1 ........ 124 |========================================================== bdver2 ........ 124 |========================================================== bdver3 ........ 124 |========================================================== bdver3 + flto . 124 |========================================================== GraphicsMagick 1.3.19 Operation: HWB Color Space Iterations Per Minute > Higher Is Better k8 ............ 129 |======================================================= k8-sse3 ....... 129 |======================================================= barcelona ..... 137 |========================================================== bdver1 ........ 137 |========================================================== bdver2 ........ 137 |========================================================== bdver3 ........ 137 |========================================================== bdver3 + flto . 137 |========================================================== GraphicsMagick 1.3.19 Operation: Local Adaptive Thresholding Iterations Per Minute > Higher Is Better k8 ............ 77 |======================================================= k8-sse3 ....... 76 |======================================================= barcelona ..... 77 |======================================================= bdver1 ........ 81 |========================================================== bdver2 ........ 81 |========================================================== bdver3 ........ 81 |========================================================== bdver3 + flto . 82 |=========================================================== Himeno Benchmark 3.0 Poisson Pressure Solver MFLOPS > Higher Is Better k8 ............ 870.33 |====================================================== k8-sse3 ....... 869.53 |====================================================== barcelona ..... 871.17 |====================================================== bdver1 ........ 883.06 |======================================================= bdver2 ........ 872.22 |====================================================== bdver3 ........ 882.11 |======================================================= bdver3 + flto . 880.95 |======================================================= Timed Apache Compilation 2.4.7 Time To Compile Seconds < Lower Is Better k8 ............ 61.06 |=================================== k8-sse3 ....... 61.07 |=================================== barcelona ..... 61.07 |=================================== bdver1 ........ 61.29 |=================================== bdver2 ........ 61.71 |==================================== bdver3 ........ 61.40 |==================================== bdver3 + flto . 96.69 |======================================================== Timed PHP Compilation 5.2.9 Time To Compile Seconds < Lower Is Better k8 ............ 58.09 |================= k8-sse3 ....... 58.12 |================= barcelona ..... 58.15 |================= bdver1 ........ 60.55 |================== bdver2 ........ 60.57 |================== bdver3 ........ 20.23 |====== bdver3 + flto . 184.15 |======================================================= C-Ray 1.1 Total Time Seconds < Lower Is Better k8 ............ 96.89 |======================================================== k8-sse3 ....... 96.93 |======================================================== barcelona ..... 65.57 |====================================== bdver1 ........ 47.43 |=========================== bdver2 ........ 47.32 |=========================== bdver3 ........ 47.31 |=========================== bdver3 + flto . 47.41 |=========================== FLAC Audio Encoding 1.3.0 WAV To FLAC Seconds < Lower Is Better k8 ............ 6.74 |===================================================== k8-sse3 ....... 6.74 |===================================================== barcelona ..... 7.22 |========================================================= bdver1 ........ 5.28 |========================================== bdver2 ........ 5.52 |============================================ bdver3 ........ 5.59 |============================================ bdver3 + flto . 5.37 |========================================== LAME MP3 Encoding 3.99.3 WAV To MP3 Seconds < Lower Is Better k8 ............ 20.85 |==================================================== k8-sse3 ....... 20.61 |==================================================== barcelona ..... 22.28 |======================================================== bdver1 ........ 19.63 |================================================= bdver2 ........ 19.60 |================================================= bdver3 ........ 19.61 |================================================= bdver3 + flto . 19.67 |================================================= FFmpeg 2.1.1 H.264 HD To NTSC DV Seconds < Lower Is Better k8 ............ 21.73 |======================================================= k8-sse3 ....... 21.78 |======================================================== barcelona ..... 21.77 |======================================================== bdver1 ........ 21.95 |======================================================== bdver2 ........ 21.69 |======================================================= bdver3 ........ 21.60 |======================================================= bdver3 + flto . 21.65 |=======================================================