Intel Software Network articles Feed http://software.intel.com/en-us/articles/dpd-general/type/performance-and-optimization/ en-us Vectorization Toolkit small_vec_banner.png

The following toolkit gives you 6 Steps to Increase Performance Through Vectorization in Your Application. Click on the bolded items to get more details on how to perform each step.

Want more context? 
   View the webinar       Read a white paper       Try some Sample code      Get some help   

---------------------------------------------------------------------------------------------------------------------

The 6-Step Process for Vectorizing your Application

1. Measure Baseline Release Build Performance

2. Determine Hotspots Using Intel® VTune™ Amplifier XE

3. Determine Loop Candidates Using Intel Compiler Vectorization Report

4. Get Advice Using the Intel Compiler GAP Report and Toolkit Resources

5. Implement GAP Advice, Other Suggestions

6. Repeat!
    (As needed until performance achieved or no good candidates left)

]]> http://software.intel.com/en-us/articles/vectorization-toolkit/ Tue, 07 Feb 2012 00:00:00 -0800 http://software.intel.com/en-us/articles/vectorization-toolkit/#comments http://software.intel.com/en-us/articles/vectorization-toolkit/ Software Products General Intel® C++ Compiler for Linux* Knowledge Base Intel® C++ Compiler for Mac OS X* Knowledge Base Intel® C++ Compiler for Windows* Knowledge Base Intel® Visual Fortran Compiler for Windows* Knowledge Base Intel® VTune™ Amplifier XE Knowledge Base Processor and Compiler Compatibility in Intel MKL

System Requirements

Please refer to the Intel® Software Products System Requirements in Intel® Math Kernel Library (Intel® MKL) release notes to find detailed or version-specific information about processor compatibility, compiler compatibility, and operating system requirements.

Processor Compatibility

Using the Intel MKL on Intel Processors
Intel MKL is optimized for the latest features and capabilities of Intel® processors (IA-32 and Intel® 64) supporting Intel® Streaming SIMD Extensions as well as Intel® Advanced Vector Extensions (Intel® AVX). The library automatically selects processor-optimized code at run time designed to provide optimal performance for that specific Intel processor.

Using the Intel MKL on non-Intel Processors
Intel MKL will run code that provides performance competitive with similar math libraries on AMD* processors using a variety of techniques which may include use of Streaming SIMD Extensions (SSE), SSE-2, and SSE-3 instruction sets and other architecture features compatible with Intel processors.

Compiler Compatibility

Refer the part of "Supported C/C++ and Fortran compilers" from Intel MKL release notes for more details.  In addtion, the Intel MKL Link Line Advisor can be particularly helpful for finding the right libraries to link.

Optimization Notice

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804

]]> http://software.intel.com/en-us/articles/intel-math-kernel-library-intel-mkl-processor-and-compiler-compatibility/ Sun, 09 Nov 2008 00:00:00 -0800 http://software.intel.com/en-us/articles/intel-math-kernel-library-intel-mkl-processor-and-compiler-compatibility/#comments http://software.intel.com/en-us/articles/intel-math-kernel-library-intel-mkl-processor-and-compiler-compatibility/ Software Products General Intel® Math Kernel Library Knowledge Base