Problem computation of1D FFT
I want to compute a 1d fft with dfti.Here is my code #include "mkl_dfti.h" #include <stdio.h> int main() { float y[8]; for (int i=0; i<4; i++) { y[i] = i+1; } DFTI_DESCRIPTOR_HANDLE handle;...
View ArticleClik here to view.
Problem with dstebz and dormtr (dense eigenvalue solver)
Hello,I'm trying to solve a symmetric generalized eigenvalue problem with the BLAS Fortran bindings inside C and I'm facing two problem with the following piece of code:if I want all eigenvalues...
View ArticleProblem with scale factor in 2d fft
I am using mkl to do a 2d image fft. First, I used mkl to compute forward the 2d fft of the initial image and I computed backward. I think it should get a image where every pixel gray scale is scaled...
View ArticleClik here to view.
Different matrix multiplication results between C and Matlab.
Let covold be a matrix of size 72x72, theta be a vector of size 1x72 and meanold a vector of size 1x72. I want to compute [(w-1)/w ]* covold + [ 1/(1+w) ] * (theta - meanold)' * (theta - meanold)...
View ArticleMKL v11.1.2 link failure with scalapack
Hi,After updating from MKL 11.0.5 to 11.1.2, I keep getting link failures on mkl_scalapack_ilp64.lib. After some searching, I see that for 11.0.5, all mkl library files are in C:\Program Files...
View ArticleSpeed up the PARDISO solver
Hi,I have a problem while using the PARDISO in FORTRAN to solve a large sparse system. The processor of my computer is Intel i7-3770 CPU 3.40GHz. I tried to call the MKL_SET_NUM_THREADS() and the...
View ArticleBLACS context value and multiple MPI communicators
Hello everybody, I am trying to make some tests with BLACS/Scalapack (C interface, Intel MKL version) making use multiple MPI communicators: particularly, what I am trying to obtain is a set of BLACS...
View ArticleCopy a submatrix to another matrix.
Hi! I want to copy the first 2 columns of a matrix A to the last two columns of another matrix B. A and B is matrices of size 3x3. I found that this can be done with the function p?lacpy ( I don't...
View ArticleHow prevent termination due to Zero Pivot?
Hi,I use DSS interface to solve a sparse symmetric linear system. When a matrix is singular, the code is terminated at dss_factor_real() with a message "MKL-DSS-DSS-Error, Zero Pivot detected". It...
View ArticleParallel algorithm used by mkl_?csrmultcsr
I am wondering which algorithm and parallelization strategy is utilized in mkl_?csrmultcsr? Does this function scale well on Intel Xeon Phi architecture?
View ArticleSimple task from example failing to execute
Hi all,I' ve got a simple example from http://software.intel.com/sites/products/documentation/doclib/mkl_sa/11/mklman/index.htmwhich works fine.I wrote the pretty similar code #include <stdio.h>...
View ArticleClik here to view.
Excessive memory allocation in DftiCommitDescriptor()
Hi everyone!When designing your project, I was faced with the problem of excessive memory allocation. In the course of the analysis found that the function DftiCommitDescriptor in the implementation...
View Articleopnemp dynamically switch on/off in mkl
Hello! I am trying to mix mkl and TBB in my project, therefore I am trying to make MKL dynamically switch on/off as I wish. I use the mkl_set_num_threads() to set the number of threads, when I want the...
View Articlecblas_cdotu_sub and cblas_cdoc_sub
Hi,I have noticed that the cblas functions cblas_cdotu_sub and cblas_cdotc_sub are returning 0 for the scalar product instead of the correct value. In earlier versions of MKL, the bug was also present...
View Article-mkl=parallel appears to link with both ilp64 and lp64 MKL libraries
As the number of data elements in the application data gets bigger we're moving to use the ilp64 MKL routines.I used the Intel Link Line Advisor to specify the required link libraries. Based on this...
View ArticleClik here to view.
SVD with via "divide and conquer" method (LAPACKE_sgesdd)
Hi,I am searching for the most efficient SVD calculation approach in MKL and about to conclude this is "LAPACKE_sgesdd". Could you please help me with two questions:1. Is "LAPACKE_sgesdd" really the...
View ArticleDSBGVX documentation: ifail dimension is n?
dsbgvx kept crashing on me with an access violation for large enough problems (n=3636). I am compiling for an x64 target.Meticulously studying the manual,...
View ArticleMKL_PARDISO in os x
Hello, I am trying to solve a sparse linear system in fortran 90 using the mkl pardiso solver as in the following code: do i = 1, 64 iparm(i) = 0 end do error = 0 ! initialize error flag msglvl = 1 !...
View ArticleError linking with Lapack
HiI am trying to run an example that solves a set of linear equations using SGESV, but during linking I get the following error messages: 1>mkl_intel_c.lib(_sgesv.obj) : error LNK2019: unresolved...
View ArticlePARDISO: Large number of subsequent identical calls result in very different...
Hi,I am working with Pardiso in C++ on sparse symmetric positive definite matrices. Unexpectedly slow performance led me to do the following experiment:I define a matrix and run phase 11 (symbolic...
View Article