1. Computers
  2. Display Drivers
  3. Graphics Cards
  4. Memory
  5. Motherboards
  6. Processors
  7. Software
  8. Storage
  9. Operating Systems


Facebook RSS Twitter Twitter Google Plus


Phoronix Test Suite

OpenBenchmarking.org

Optimized Binaries Provide Great Benefits For Intel Haswell

Michael Larabel

Published on 15 June 2013
Written by Michael Larabel
Page 1 of 4 - 9 Comments

Utilizing the core-avx2 CPU optimizations offered by the GCC 4.8 compiler can provide real benefits for the Intel Core i7 4770K processor and other new "Haswell" CPUs. For some computational workloads, the new Haswell instruction set extensions can offer tremendous speed-ups compared to what's offered by the previous-generation Ivy Bridge CPUs.

With our source-based benchmarks to date of Haswell, we have been using the -march=native compiler flag that effectively means -march=core-avx2 but we haven't looked specifically at the benefits provided by Haswell CPUs introducing support for AVX2, FMA, BMI, and BMI2. This is also particularly interesting since on the Windows side, most of the benchmarking that happens at the other review sites is done using generic pre-compiled binaries rather than building from source with optimizations for a given architecture.

For those unfamiliar with the GCC x86/x86_64 optimization options, read the online GCC documentation. The new core-avx2 option means "Intel Core CPU with 64-bit extensions, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2, AES, PCLMUL, FSGSBASE, RDRND, FMA, BMI, BMI2 and F16C instruction set support."

The other tested options were Nocona (the old Xeons), Core2 (the original Intel Core CPUs with SSE3 support), Corei7 (Ironlake), Corei7-avx (Sandy Bridge), and Core-avx-i (Ivy Bridge). Again, the GCC documentation explains what instruction sets are offered by each of these different Intel CPU models.

Results in full are on OpenBenchmarking.org in 1306150-PTS-INTELHAS05. The Core i7 4770K Haswell system was running Ubuntu 13.04 with the Linux 3.10 development kernel and GCC 4.8.1 was built from source. The various compiler options were set via the CFLAGS and CXXFLAGS environment variables along with passing -O3 for the most aggressive compiler optimizations.

<< Previous Page
1
Latest Linux Hardware Reviews
  1. The Power Consumption & Efficiency Of Open-Source GPU Drivers
  2. AMD R600g/RadeonSI Performance On Linux 3.16 With Mesa 10.3-devel
  3. Intel Pentium G3258 On Linux
  4. SilverStone Precision PS10
Latest Linux Articles
  1. Nouveau vs. Radeon vs. Intel Tests On Linux 3.16, Mesa 10.3-devel
  2. KVM Benchmarks On Ubuntu 14.10
  3. X.Org Server 1.16 Officially Released With Terrific Features
  4. Ubuntu With Linux 3.16 Smashes OS X 10.9.4 On The MacBook Air
Latest Linux News
  1. Git 2.1 To Further Mainline Windows Support Patches
  2. Debian 8.0 Jessie Is Settling For Linux 3.16
  3. Meson: A Next-Gen Build System Showing Promise
  4. Linux 3.16-rc7 Calms Things Down For The Linux 3.16 Kernel
  5. Open-Source AMD Users Report Hawaii GPU Acceleration Is Working
  6. Linus Torvalds On GCC 4.9: Pure & Utter Crap
  7. Cauldron 2014: GCC & LLVM Will Look To Collaborate More
  8. GCC Receives ACM Programming Languages Software Award
  9. KDE 4.14 Beta 3 Released
  10. A New Video Has Us Real Excited About The New UT For Linux
Latest Forum Discussions
  1. Updated and Optimized Ubuntu Free Graphics Drivers
  2. ASRock AM1H-ITX: One Of The Best AM1 Mini-ITX Motherboards
  3. Debian + radeonsi
  4. Open-source drivers on ATI R7 260X
  5. Table test
  6. How To Setup Radeon DPM On Ubuntu Linux
  7. New build, first Linux PC, what could go wrong? ;)
  8. AMD "Hawaii" Open-Source GPU Acceleration Still Not Working Right