GCC 4.9 Snapshot Compiler Flag Tests GCC 4.9 compiler optimization tests of an Intel Core i7 Haswell CPU and applying different CFLAGS/CXXFLAGS to look at impact of core-avx2 CPU optimizations and other x86_64 -march= options. Benchmarks by Michael Larabel. Core-AVX2: Processor: Intel Core i7-4900MQ @ 2.80GHz (8 Cores), Motherboard: System76 Gazelle Professional, Chipset: Intel Xeon E3-1200 v3/4th, Memory: 8192MB, Disk: 120GB INTEL SSDSC2CW12, Graphics: Intel 4th Gen Core IGP (1300MHz), Audio: Intel Haswell HDMI, Network: Realtek RTL8111/8168/8411 + Intel Centrino Advanced-N 6235 OS: Ubuntu 13.10, Kernel: 3.11.0-4-generic (x86_64), Desktop: Unity 7.1.0, Display Server: X Server 1.14.2.901 (1.14.3 RC 1), Display Driver: intel 2.21.14, OpenGL: 3.1 Mesa 9.2.0, Compiler: GCC 4.9.0 20130731, File-System: ext4, Screen Resolution: 1920x1080 Core-AVX-I: Processor: Intel Core i7-4900MQ @ 2.80GHz (8 Cores), Motherboard: System76 Gazelle Professional, Chipset: Intel Xeon E3-1200 v3/4th, Memory: 8192MB, Disk: 120GB INTEL SSDSC2CW12, Graphics: Intel 4th Gen Core IGP (1300MHz), Audio: Intel Haswell HDMI, Network: Realtek RTL8111/8168/8411 + Intel Centrino Advanced-N 6235 OS: Ubuntu 13.10, Kernel: 3.11.0-4-generic (x86_64), Desktop: Unity 7.1.0, Display Server: X Server 1.14.2.901 (1.14.3 RC 1), Display Driver: intel 2.21.14, OpenGL: 3.1 Mesa 9.2.0, Compiler: GCC 4.9.0 20130731, File-System: ext4, Screen Resolution: 1920x1080 Corei7-AVX: Processor: Intel Core i7-4900MQ @ 2.80GHz (8 Cores), Motherboard: System76 Gazelle Professional, Chipset: Intel Xeon E3-1200 v3/4th, Memory: 8192MB, Disk: 120GB INTEL SSDSC2CW12, Graphics: Intel 4th Gen Core IGP (1300MHz), Audio: Intel Haswell HDMI, Network: Realtek RTL8111/8168/8411 + Intel Centrino Advanced-N 6235 OS: Ubuntu 13.10, Kernel: 3.11.0-4-generic (x86_64), Desktop: Unity 7.1.0, Display Server: X Server 1.14.2.901 (1.14.3 RC 1), Display Driver: intel 2.21.14, OpenGL: 3.1 Mesa 9.2.0, Compiler: GCC 4.9.0 20130731, File-System: ext4, Screen Resolution: 1920x1080 Corei7: Processor: Intel Core i7-4900MQ @ 2.80GHz (8 Cores), Motherboard: System76 Gazelle Professional, Chipset: Intel Xeon E3-1200 v3/4th, Memory: 8192MB, Disk: 120GB INTEL SSDSC2CW12, Graphics: Intel 4th Gen Core IGP (1300MHz), Audio: Intel Haswell HDMI, Network: Realtek RTL8111/8168/8411 + Intel Centrino Advanced-N 6235 OS: Ubuntu 13.10, Kernel: 3.11.0-4-generic (x86_64), Desktop: Unity 7.1.0, Display Server: X Server 1.14.2.901 (1.14.3 RC 1), Display Driver: intel 2.21.14, OpenGL: 3.1 Mesa 9.2.0, Compiler: GCC 4.9.0 20130731, File-System: ext4, Screen Resolution: 1920x1080 Core2: Processor: Intel Core i7-4900MQ @ 2.80GHz (8 Cores), Motherboard: System76 Gazelle Professional, Chipset: Intel Xeon E3-1200 v3/4th, Memory: 8192MB, Disk: 120GB INTEL SSDSC2CW12, Graphics: Intel 4th Gen Core IGP (1300MHz), Audio: Intel Haswell HDMI, Network: Realtek RTL8111/8168/8411 + Intel Centrino Advanced-N 6235 OS: Ubuntu 13.10, Kernel: 3.11.0-4-generic (x86_64), Desktop: Unity 7.1.0, Display Server: X Server 1.14.2.901 (1.14.3 RC 1), Display Driver: intel 2.21.14, OpenGL: 3.1 Mesa 9.2.0, Compiler: GCC 4.9.0 20130731, File-System: ext4, Screen Resolution: 1920x1080 Nocona: Processor: Intel Core i7-4900MQ @ 2.80GHz (8 Cores), Motherboard: System76 Gazelle Professional, Chipset: Intel Xeon E3-1200 v3/4th, Memory: 8192MB, Disk: 120GB INTEL SSDSC2CW12, Graphics: Intel 4th Gen Core IGP (1300MHz), Audio: Intel Haswell HDMI, Network: Realtek RTL8111/8168/8411 + Intel Centrino Advanced-N 6235 OS: Ubuntu 13.10, Kernel: 3.11.0-4-generic (x86_64), Desktop: Unity 7.1.0, Display Server: X Server 1.14.2.901 (1.14.3 RC 1), Display Driver: intel 2.21.14, OpenGL: 3.1 Mesa 9.2.0, Compiler: GCC 4.9.0 20130731, File-System: ext4, Screen Resolution: 1920x1080 SciMark 2.0 Computational Test: Monte Carlo Mflops > Higher Is Better Core-AVX2 .. 595.70 |================================================= Core-AVX-I . 595.28 |================================================= Corei7-AVX . 594.05 |================================================= Corei7 ..... 596.52 |================================================== Core2 ...... 595.70 |================================================= Nocona ..... 698.37 |========================================================== SciMark 2.0 Computational Test: Fast Fourier Transform Mflops > Higher Is Better Core-AVX2 .. 335.89 |========================================================== Core-AVX-I . 329.12 |========================================================= Corei7-AVX . 315.45 |====================================================== Corei7 ..... 316.62 |======================================================= Core2 ...... 319.57 |======================================================= Nocona ..... 318.08 |======================================================= SciMark 2.0 Computational Test: Sparse Matrix Multiply Mflops > Higher Is Better Core-AVX2 .. 2332.25 |======================================================== Core-AVX-I . 2184.67 |==================================================== Corei7-AVX . 2322.34 |======================================================= Corei7 ..... 2388.35 |========================================================= Core2 ...... 2379.68 |========================================================= Nocona ..... 2346.98 |======================================================== SciMark 2.0 Computational Test: Dense LU Matrix Factorization Mflops > Higher Is Better Core-AVX2 .. 2783.23 |======================================================== Core-AVX-I . 2794.16 |======================================================== Corei7-AVX . 2786.85 |======================================================== Corei7 ..... 2842.55 |========================================================= Core2 ...... 2853.98 |========================================================= Nocona ..... 2589.06 |==================================================== SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Mflops > Higher Is Better Core-AVX2 .. 1142.92 |========================================================= Core-AVX-I . 1142.92 |========================================================= Corei7-AVX . 1142.92 |========================================================= Corei7 ..... 1140.79 |========================================================= Core2 ...... 1140.79 |========================================================= Nocona ..... 1140.79 |========================================================= TTSIOD 3D Renderer 2.2z Phong Rendering With Soft-Shadow Mapping FPS > Higher Is Better Core-AVX2 .. 133.95 |==================================================== Core-AVX-I . 133.36 |==================================================== Corei7-AVX . 132.85 |=================================================== Corei7 ..... 150.07 |========================================================== Core2 ...... 146.09 |======================================================== Nocona ..... 144.87 |======================================================== x264 2013-06-08 H.264 Video Encoding Frames Per Second > Higher Is Better Core-AVX2 .. 162.96 |========================================================== Core-AVX-I . 163.77 |========================================================== Corei7-AVX . 162.86 |========================================================== Corei7 ..... 162.76 |========================================================== Core2 ...... 162.10 |========================================================= Nocona ..... 162.14 |========================================================= GraphicsMagick 1.3.16 Operation: Blur Iterations Per Minute > Higher Is Better Core-AVX2 .. 149 |============================================================= Core-AVX-I . 149 |============================================================= Corei7-AVX . 149 |============================================================= Corei7 ..... 149 |============================================================= Core2 ...... 149 |============================================================= Nocona ..... 148 |============================================================= GraphicsMagick 1.3.16 Operation: Sharpen Iterations Per Minute > Higher Is Better Core-AVX2 .. 126 |============================================================= Core-AVX-I . 116 |======================================================== Corei7-AVX . 116 |======================================================== Corei7 ..... 116 |======================================================== Core2 ...... 116 |======================================================== Nocona ..... 115 |======================================================== GraphicsMagick 1.3.16 Operation: Resizing Iterations Per Minute > Higher Is Better Core-AVX2 .. 180 |============================================================= Core-AVX-I . 176 |============================================================ Corei7-AVX . 176 |============================================================ Corei7 ..... 175 |=========================================================== Core2 ...... 176 |============================================================ Nocona ..... 172 |========================================================== GraphicsMagick 1.3.16 Operation: HWB Color Space Iterations Per Minute > Higher Is Better Core-AVX2 .. 200 |============================================================= Core-AVX-I . 201 |============================================================= Corei7-AVX . 201 |============================================================= Corei7 ..... 200 |============================================================= Core2 ...... 201 |============================================================= Nocona ..... 198 |============================================================ GraphicsMagick 1.3.16 Operation: Local Adaptive Thresholding Iterations Per Minute > Higher Is Better Core-AVX2 .. 116 |============================================================= Core-AVX-I . 116 |============================================================= Corei7-AVX . 116 |============================================================= Corei7 ..... 115 |============================================================ Core2 ...... 115 |============================================================ Nocona ..... 114 |============================================================ Himeno Benchmark 3.0 Poisson Pressure Solver MFLOPS > Higher Is Better Core-AVX2 .. 1770.48 |====================================================== Core-AVX-I . 1868.47 |========================================================= Corei7-AVX . 1803.82 |======================================================= Corei7 ..... 1746.95 |===================================================== Core2 ...... 1747.23 |===================================================== Nocona ..... 1695.27 |==================================================== C-Ray 1.1 Total Time Seconds < Lower Is Better Core-AVX2 .. 19.71 |============================================ Core-AVX-I . 26.38 |========================================================== Corei7-AVX . 26.40 |========================================================== Corei7 ..... 26.52 |=========================================================== Core2 ...... 26.53 |=========================================================== Nocona ..... 26.66 |=========================================================== Primesieve 4.2 1e12 Prime Number Generation Seconds < Lower Is Better Core-AVX2 .. 93.19 |=========================================================== Core-AVX-I . 93.17 |=========================================================== Corei7-AVX . 93.15 |=========================================================== Corei7 ..... 93.14 |=========================================================== Core2 ...... 93.15 |=========================================================== Nocona ..... 93.31 |=========================================================== Smallpt 1.0 Global Illumination Renderer; 100 Samples Seconds < Lower Is Better Core-AVX2 .. 29 |============================================================ Core-AVX-I . 29 |============================================================ Corei7-AVX . 29 |============================================================ Corei7 ..... 30 |============================================================== Core2 ...... 30 |============================================================== Nocona ..... 30 |============================================================== FLAC Audio Encoding 1.3.0 WAV To FLAC Seconds < Lower Is Better Core-AVX2 .. 5.31 |========================================================= Core-AVX-I . 5.59 |============================================================ Corei7-AVX . 5.59 |============================================================ Corei7 ..... 5.09 |======================================================= Core2 ...... 5.21 |======================================================== Nocona ..... 5.29 |========================================================= LAME MP3 Encoding 3.99.3 WAV To MP3 Seconds < Lower Is Better Core-AVX2 .. 14.30 |=========================================================== Core-AVX-I . 14.08 |========================================================== Corei7-AVX . 14.07 |========================================================== Corei7 ..... 12.57 |==================================================== Core2 ...... 12.88 |===================================================== Nocona ..... 12.64 |==================================================== Ogg Encoding 1.3.0 WAV To Ogg Seconds < Lower Is Better Core-AVX2 .. 7.06 |============================================================ Core-AVX-I . 7.06 |============================================================ Corei7-AVX . 7.06 |============================================================ Corei7 ..... 7.08 |============================================================ Core2 ...... 7.06 |============================================================ Nocona ..... 7.07 |============================================================ FFmpeg 2.0 H.264 HD To NTSC DV Seconds < Lower Is Better Core-AVX2 .. 13.17 |========================================================== Core-AVX-I . 13.31 |========================================================== Corei7-AVX . 13.37 |========================================================== Corei7 ..... 13.50 |=========================================================== Core2 ...... 13.33 |========================================================== Nocona ..... 13.30 |========================================================== N-Queens 1.0 Elapsed Time Seconds < Lower Is Better Core-AVX2 .. 42.54 |======================================================= Core-AVX-I . 44.51 |========================================================= Corei7-AVX . 44.50 |========================================================= Corei7 ..... 44.54 |========================================================= Core2 ...... 44.51 |========================================================= Nocona ..... 45.76 |=========================================================== Apache Benchmark 2.4.3 Static Web Page Serving Requests Per Second > Higher Is Better Core-AVX2 .. 31291.52 |======================================================== Core-AVX-I . 31007.19 |======================================================= Corei7-AVX . 30875.41 |======================================================= Corei7 ..... 30666.53 |======================================================= Core2 ...... 31064.17 |======================================================== Nocona ..... 29830.02 |=====================================================