This is a step by step procedure on how to run the High Performance Linpack (HPL) benchmark on a Linux cluster using Intel-MPI. This was done on a Linux cluster of 128 nodes running Intel’s Nehalem processor 2.93 MHz with 12GB of RAM on each node.
Intel® Math Kernel Library
Using Intel® MKL with the NAG* libraries
This article describes how to ensure that when using NAG library you are making the best use of the Intel® Math Kernel Library to maximize your performance on Intel® architectures.
Using Intel® MKL with Intel Visual Fortran Compiler Professional Edition
A video provides instructions on using Intel® MKL with Intel Visual Fortran Compiler Professional Edition.
PARDISO new feature ( store and load handle on HDD ) – open discussion
Intel® MKL Team is working on the new functionality in PARDISO and we are considering several versions of interfaces to handle this feature.
Intel® Math Kernel Library (Intel® MKL) for Windows* - Compiling and Linking with Microsoft* Visual C/C++*
|
The following provides hints for linking your program with Intel® MKL from the Microsoft* Visual C/C++*: Intel® MKL 9.0 with Microsoft* Visual C++* .NET 2003 or Microsoft* Visual C++* 2005 |
Compiling and Linking Intel MKL 10.0 using Microsoft* Visual Studio* 2005 or 2008
This page contains instructions for compiling and linking Intel MKL 10.x with Microsoft* Visual Studio* 2005 and 2008.
MKL v.10.0 - error LNK2019: unresolved external symbol __fseeki64 referenced in function _mkl_pds_isendoffile
MKL's Linking error - unresolved external symbol __fseeki64
Intel® MKL versions 10.0 and 10.1
Microsoft Visual Studio.NET 2003
Compatibility libraries (also known as dummy libraries) no more available
Dummy libraries have been removed from Intel® MKL 10.2.
{SC,DZ}GEMM function
Mixed real and complex precision matrix-matrix multiply available from Intel® MKL 10.2 onwards
PARDISO use half the memory now
Reduced memory use by PARDISO for both in-core and out-of-core on all symmetric matrix types
Seiten
