Intel Core i7 GCC Icelake Compiler Testing Intel Core i7-1065G7 GCC compiler tuning benchmarks by Michael Larabel for a future article. -O3 -march=skylake: Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: Dell 06CDVY (1.0.9 BIOS), Chipset: Intel Device 34ef, Memory: 16384MB, Disk: KBG40ZPZ512G NVMe TOSHIBA 512GB, Graphics: Intel Iris Plus 3GB (1100MHz), Audio: Realtek ALC289, Network: Intel Device 34f0 OS: Clear Linux OS 31340, Kernel: 5.3.6-850.native (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.6 Mesa 19.3.0-devel, Vulkan: 1.1.102, Compiler: GCC 9.2.1 20191017 gcc-9-branch@277087 + Clang 9.0.0 + LLVM 9.0.0, File-System: ext4, Screen Resolution: 1920x1200 -O3 -march=skylake-avx512: Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: Dell 06CDVY (1.0.9 BIOS), Chipset: Intel Device 34ef, Memory: 16384MB, Disk: KBG40ZPZ512G NVMe TOSHIBA 512GB, Graphics: Intel Iris Plus 3GB (1100MHz), Audio: Realtek ALC289, Network: Intel Device 34f0 OS: Clear Linux OS 31340, Kernel: 5.3.6-850.native (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.6 Mesa 19.3.0-devel, Vulkan: 1.1.102, Compiler: GCC 9.2.1 20191017 gcc-9-branch@277087 + Clang 9.0.0 + LLVM 9.0.0, File-System: ext4, Screen Resolution: 1920x1200 -O3 -march=icelake-client: Processor: Intel Core i7-1065G7 @ 3.90GHz (4 Cores / 8 Threads), Motherboard: Dell 06CDVY (1.0.9 BIOS), Chipset: Intel Device 34ef, Memory: 16384MB, Disk: KBG40ZPZ512G NVMe TOSHIBA 512GB, Graphics: Intel Iris Plus 3GB (1100MHz), Audio: Realtek ALC289, Network: Intel Device 34f0 OS: Clear Linux OS 31340, Kernel: 5.3.6-850.native (x86_64), Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.6 Mesa 19.3.0-devel, Vulkan: 1.1.102, Compiler: GCC 9.2.1 20191017 gcc-9-branch@277087 + Clang 9.0.0 + LLVM 9.0.0, File-System: ext4, Screen Resolution: 1920x1200 miniFE 2.2 Problem Size: Small CG Mflops > Higher Is Better -O3 -march=skylake ........ 3961.75 |========================================== -O3 -march=skylake-avx512 . 3973.09 |========================================== -O3 -march=icelake-client . 3963.16 |========================================== FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 Mflops > Higher Is Better -O3 -march=skylake ........ 18850 |========================================= -O3 -march=skylake-avx512 . 20116 |=========================================== -O3 -march=icelake-client . 20431 |============================================ FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 Mflops > Higher Is Better -O3 -march=skylake ........ 66442 |============================================ -O3 -march=skylake-avx512 . 66497 |============================================ -O3 -march=icelake-client . 65942 |============================================ FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 Mflops > Higher Is Better -O3 -march=skylake ........ 19297 |============================================ -O3 -march=skylake-avx512 . 18515 |========================================== -O3 -march=icelake-client . 19077 |=========================================== Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Seconds < Lower Is Better -O3 -march=skylake ........ 138.31 |========================================== -O3 -march=skylake-avx512 . 141.75 |=========================================== -O3 -march=icelake-client . 141.39 |=========================================== QMCPACK 3.8 Total Execution Time - Seconds < Lower Is Better -O3 -march=skylake ........ 488.62 |=========================================== -O3 -march=skylake-avx512 . 482.29 |========================================== -O3 -march=icelake-client . 476.93 |========================================== Timed HMMer Search 2.3.2 Pfam Database Search Seconds < Lower Is Better -O3 -march=skylake ........ 5.92 |========================================= -O3 -march=skylake-avx512 . 6.50 |============================================= -O3 -march=icelake-client . 6.41 |============================================ Timed MAFFT Alignment 7.392 Multiple Sequence Alignment Seconds < Lower Is Better -O3 -march=skylake ........ 4.37 |=========================================== -O3 -march=skylake-avx512 . 4.62 |============================================= -O3 -march=icelake-client . 4.46 |=========================================== SciMark 2.0 Computational Test: Composite Mflops > Higher Is Better -O3 -march=skylake ........ 2636.43 |========================================= -O3 -march=skylake-avx512 . 2702.45 |========================================== -O3 -march=icelake-client . 2661.03 |========================================= SciMark 2.0 Computational Test: Monte Carlo Mflops > Higher Is Better -O3 -march=skylake ........ 909.89 |========================================= -O3 -march=skylake-avx512 . 924.95 |========================================== -O3 -march=icelake-client . 944.22 |=========================================== SciMark 2.0 Computational Test: Fast Fourier Transform Mflops > Higher Is Better -O3 -march=skylake ........ 418.95 |=========================================== -O3 -march=skylake-avx512 . 420.70 |=========================================== -O3 -march=icelake-client . 416.91 |=========================================== SciMark 2.0 Computational Test: Sparse Matrix Multiply Mflops > Higher Is Better -O3 -march=skylake ........ 2804.38 |========================================== -O3 -march=skylake-avx512 . 2746.41 |========================================= -O3 -march=icelake-client . 2760.02 |========================================= SciMark 2.0 Computational Test: Dense LU Matrix Factorization Mflops > Higher Is Better -O3 -march=skylake ........ 7064.02 |======================================== -O3 -march=skylake-avx512 . 7464.72 |========================================== -O3 -march=icelake-client . 7398.03 |========================================== SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Mflops > Higher Is Better -O3 -march=skylake ........ 1984.93 |========================================== -O3 -march=skylake-avx512 . 1983.55 |========================================== -O3 -march=icelake-client . 1985.64 |========================================== GraphicsMagick 1.3.33 Operation: Swirl Iterations Per Minute > Higher Is Better -O3 -march=skylake ........ 182 |============================================== -O3 -march=skylake-avx512 . 173 |============================================ -O3 -march=icelake-client . 178 |============================================= GraphicsMagick 1.3.33 Operation: Rotate Iterations Per Minute > Higher Is Better -O3 -march=skylake ........ 1082 |============================================= -O3 -march=skylake-avx512 . 1042 |=========================================== -O3 -march=icelake-client . 1045 |=========================================== GraphicsMagick 1.3.33 Operation: Sharpen Iterations Per Minute > Higher Is Better -O3 -march=skylake ........ 56 |=============================================== -O3 -march=skylake-avx512 . 49 |========================================= -O3 -march=icelake-client . 49 |========================================= GraphicsMagick 1.3.33 Operation: Enhanced Iterations Per Minute > Higher Is Better -O3 -march=skylake ........ 73 |=============================================== -O3 -march=skylake-avx512 . 66 |========================================== -O3 -march=icelake-client . 66 |========================================== GraphicsMagick 1.3.33 Operation: Resizing Iterations Per Minute > Higher Is Better -O3 -march=skylake ........ 307 |============================================== -O3 -march=skylake-avx512 . 282 |========================================== -O3 -march=icelake-client . 281 |========================================== GraphicsMagick 1.3.33 Operation: Noise-Gaussian Iterations Per Minute > Higher Is Better -O3 -march=skylake ........ 83 |=============================================== -O3 -march=skylake-avx512 . 74 |========================================== -O3 -march=icelake-client . 74 |========================================== GraphicsMagick 1.3.33 Operation: HWB Color Space Iterations Per Minute > Higher Is Better -O3 -march=skylake ........ 619 |============================================== -O3 -march=skylake-avx512 . 603 |============================================= -O3 -march=icelake-client . 600 |============================================= dav1d 0.5.0 Video Input: Chimera 1080p FPS > Higher Is Better -O3 -march=skylake ........ 272.24 |=========================================== -O3 -march=skylake-avx512 . 255.22 |======================================== -O3 -march=icelake-client . 256.32 |======================================== dav1d 0.5.0 Video Input: Summer Nature 1080p FPS > Higher Is Better -O3 -march=skylake ........ 256.98 |=========================================== -O3 -march=skylake-avx512 . 243.83 |========================================= -O3 -march=icelake-client . 248.91 |========================================== SVT-HEVC 1.4.1 1080p 8-bit YUV To HEVC Video Encode Frames Per Second > Higher Is Better -O3 -march=skylake ........ 14.45 |============================================ -O3 -march=skylake-avx512 . 13.16 |======================================== -O3 -march=icelake-client . 13.27 |======================================== SVT-VP9 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better -O3 -march=skylake ........ 73.34 |============================================ -O3 -march=skylake-avx512 . 71.05 |=========================================== -O3 -march=icelake-client . 72.30 |=========================================== SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better -O3 -march=skylake ........ 73.35 |============================================ -O3 -march=skylake-avx512 . 70.37 |========================================== -O3 -march=icelake-client . 71.48 |=========================================== SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Frames Per Second > Higher Is Better -O3 -march=skylake ........ 53.72 |============================================ -O3 -march=skylake-avx512 . 52.87 |=========================================== -O3 -march=icelake-client . 53.50 |============================================ ACES DGEMM 1.0 Sustained Floating-Point Rate GFLOP/s > Higher Is Better -O3 -march=skylake ........ 1.03 |============================================= -O3 -march=skylake-avx512 . 1.01 |============================================ -O3 -march=icelake-client . 1.01 |============================================ Himeno Benchmark 3.0 Poisson Pressure Solver MFLOPS > Higher Is Better -O3 -march=skylake ........ 4037.97 |========================================== -O3 -march=skylake-avx512 . 4013.23 |========================================== -O3 -march=icelake-client . 3999.93 |========================================== C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Seconds < Lower Is Better -O3 -march=skylake ........ 188.30 |======================================== -O3 -march=skylake-avx512 . 203.08 |=========================================== -O3 -march=icelake-client . 201.58 |=========================================== Smallpt 1.0 Global Illumination Renderer; 128 Samples Seconds < Lower Is Better -O3 -march=skylake ........ 32.12 |======================================== -O3 -march=skylake-avx512 . 35.33 |============================================ -O3 -march=icelake-client . 35.10 |============================================ AOBench Size: 2048 x 2048 - Total Time Seconds < Lower Is Better -O3 -march=skylake ........ 27.72 |============================================ -O3 -march=skylake-avx512 . 26.98 |=========================================== -O3 -march=icelake-client . 27.08 |=========================================== Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 Seconds < Lower Is Better -O3 -march=skylake ........ 37.26 |=========================================== -O3 -march=skylake-avx512 . 38.45 |============================================ -O3 -march=icelake-client . 38.46 |============================================ OpenSSL 1.1.1 RSA 4096-bit Performance Signs Per Second > Higher Is Better -O3 -march=skylake ........ 842.50 |=========================================== -O3 -march=skylake-avx512 . 816.19 |========================================== -O3 -march=icelake-client . 823.83 |========================================== ASKAP 2018-11-10 Test: tConvolve MT - Gridding Million Grid Points Per Second > Higher Is Better -O3 -march=skylake ........ 1165.70 |========================================== -O3 -march=skylake-avx512 . 1156.48 |========================================== -O3 -march=icelake-client . 1168.61 |========================================== ASKAP 2018-11-10 Test: tConvolve MT - Degridding Million Grid Points Per Second > Higher Is Better -O3 -march=skylake ........ 970.38 |=========================================== -O3 -march=skylake-avx512 . 968.08 |=========================================== -O3 -march=icelake-client . 971.54 |=========================================== ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding Million Grid Points Per Second > Higher Is Better -O3 -march=skylake ........ 1196.17 |========================================== -O3 -march=skylake-avx512 . 1179.93 |========================================= -O3 -march=icelake-client . 1169.76 |========================================= ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding Million Grid Points Per Second > Higher Is Better -O3 -march=skylake ........ 1570.37 |========================================= -O3 -march=skylake-avx512 . 1589.14 |========================================== -O3 -march=icelake-client . 1605.95 |========================================== SQLite Speedtest 3.30 Timed Time - Size 1,000 Seconds < Lower Is Better -O3 -march=skylake ........ 56.51 |============================================ -O3 -march=skylake-avx512 . 56.45 |============================================ -O3 -march=icelake-client . 56.16 |============================================ Redis 5.0.5 Test: GET Requests Per Second > Higher Is Better -O3 -march=skylake ........ 3062487.88 |====================================== -O3 -march=skylake-avx512 . 3125565.17 |======================================= -O3 -march=icelake-client . 3136507.88 |======================================= Redis 5.0.5 Test: SET Requests Per Second > Higher Is Better -O3 -march=skylake ........ 2111347.87 |======================================= -O3 -march=skylake-avx512 . 2077912.88 |====================================== -O3 -march=icelake-client . 2127678.92 |=======================================