Extreme eigenvalue problem
Hello,I read this article on a FEAST add-on that automatically estimates an eigenvalue search interval and a subspace size when the user is only interested in the lowest or highest k eigenvalues of a...
View ArticleMake publicly available the mkl-devel conda package
First, I'd like to congratulate Intel on the awesome initiatives to (1) make MKL freely available through the Community Licensing, (2) develop the super fast Intel Distribution for Python and (3) make...
View ArticleLink Issue with mkl_scalapack
my code(test.cpp) is this:#include <vector> #include "mkl_scalapack.h"void main(){ int N = 1000; std::vector<int> key(N); std::vector<double> value(N); for (int i = 0; i...
View ArticleCMAKE and FindMKL or FindLAPACK (Intel® Parallel Studio XE 2016, Windows)
Are there any CMAKE experts on this Forum? If so do you have a version of findMKL or findLAPACK that works for me on modern Intel Fortran/Windows I have not tested them in Linux but suspect they...
View ArticleCan pardiso use the windows virtual memory?
Hi,I know about the OOC functionality, but if I just want to use the in-core option (iparm(60) = 0), how can I make sure pardiso uses virtual memory (windows 7)? In a large solve with 6 million...
View Articlenonlinear optimization (?trnlspbc_solve)
Hi everyone,I am wondering whether I can use the routine ?trnlspbc_solve to tackle a multivariate, nonlinear regression problem with linear constraints.Cheers,Michele
View ArticleClik here to view.
Delete data fitting task seems to fail clearing internal memory
Hi,I have observed that deleting an interpolation task by dfDeleteTask doesn't affect the number of allocated buffers (using mkl_mem_stat). Is this an expected behaviour? According to the manual of...
View ArticleWhere is mathimf.h when using MS C++?
#include <stdio.h> #include <Mkl.h> #include <Math.h> //#include <Mathimf.h> // cannot open int main() { printf("Bessel J0(5)\t%1.19f\n", j0(5.0)); // testing MKL...
View ArticleVIsual studio 2015 integration weird issue
I installed visual studio 2013 ultimate, then intel parallel studio 2017 cluster edition (exclusively for the MKL) and the latter was integrated in visual studio 2013 (access, through visual studio...
View ArticleImportance of size of lwork array when passed to ?getri
Just a FYI for MKL users, as this caught me....I was profiling and noticed that calls to zgetri was not scaling as the # of threads increased. Also Intel Amplifier showed that that OMP threads apart...
View ArticleMKL mkl_?csrcoo conversion problem
Hi I am using MKL c++ version to solve for pardiso. My input is a sparse matrix in the coordinate format and I am planning to convert it to CSR format to use the pardiso command with mkl_?csrcoo. The...
View ArticleFGMRES for pentadiagonal matrix
Hello,I am new to Fortran intel MKL. I am trying to use the FGMRES with ILUT preconditioner for solving the Penta diagonal matrix (A*x=b.) resulting from discretization of 3D convection-diffusion...
View ArticleFEAST 3.0 and estimates of the search subspace M0
Hi,the last version 3.0 of the FEAST solver includes stochastic estimates for the number of eigenvalues inside of the search interval.This feature will be very useful to estimate a value for the search...
View ArticleInstallation issues with Parallel Studio XE 2017
Hi All,I couldn't find a proper forum to post issues during installation, so I am posting it here. I am trying to install Intel Parallel Studio XE 2017 on OpenSUSE LEAP 42.1. The installation script...
View Articleusing dlasrt2 with integer keys
Hi, I've been using dlasrt2 with the APIvoid dlasrt2 (char *id , MKL_INT *n , double *d , MKL_INT *key , MKL_INT *info ); however i wonder if we can link directly to fortran counterpart to have int...
View ArticleClik here to view.
slasrt2 performance
Hi I have a question regarding the performance of the slasrt2 function. I'm using vtune and am seeing the following results, which shows that my code is not getting the FPU peak or anywhere near that....
View ArticleUse of gather and scatter when it's not supported
Hi there!I am a MSc student in HPC, and I am currently working with Quantum Espresso, in order to improve their performance in a cluster environment.Recently I generated the call graph of the...
View ArticleCompile error fftw3 wrapper using Fortran 2017 on Mac OS 10.12.1
Following the instructions given in /opt/intel/compilers_and_libraries_2017.0.102/mac/mkl/interfaces/fftw3xf/makefile to compile the fftw3 wrapper, the following does not work, instead giving the fatal...
View ArticleIntel MKL version name convention & build number
Is there a way to establish the relationship between MKL build number (returned by mkl_get_version_string) and the version update number (a mapping table similar to the one existing for the compiler...
View ArticleQR algorithm scalability problems
Dear support team! We’ve faced some problems with QR algorithm scalability, implemented using MKL functions LAPACKE_sgehrd to reduce our matrix to Hessenberg form and LAPACKE_shseqr to perform...
View Article