memory leak in latest version of MKL
Dear all,I checked my program by Intel's 'Memory and Thread Debugger' and found the function 'dsygv' leak memory when use latest version MKL. The same code compiled by version 2016.3.223 is OK. The...
View ArticleClik here to view.
CSYTRF/CSYTRS give different results 1 thread vs 8 threads (MKL 2019u5)
THREADS=8first 10 values of the Solution 1 (-104034.0,20268.75) 2 (-104099.4,20310.57) 3 (-103879.3,20264.78) 4 (-103980.5,20282.24) 5...
View ArticlePardiso documentation - access denied
Hi,I'm trying to access https://software.intel.com/en-us/onemkl-developer-reference-fortran and get an "Access Denied" message and yet I should have access to MKL from with my 2019 Intel compiler...
View ArticleSegmentation fault CPARDISO
Hello,CPARDISO is segfaulting on my application when I use version 19.0.5.075, but everything runs fine with version 18.0.3.222. Is this a known regression that is being fixed right now?The issue comes...
View ArticleDatafitting - Cubic Spline Boundary Conditions
I would like to fit a cubic spline with the second derivatives at the end points linearly extrapolated from the two closest interior points. Is there a way to specify this type of boundary...
View ArticleClik here to view.
MKL Scalapack uses much more RAM than NETLIB version
Hello,I really enjoy using MKL libraries since they are much faster on our 36 core Intel(R) Xeon(R) Gold 6140 CPU @ 2.30GHz mashine. However our scientific research requires diagonalization of very...
View ArticleOnly positive eigenvalues for ?syevd
For an algorithm I need to get all positive eigenvalues and their corresponding eigenvectors for given real, symmetric matrices frequently (and as fast as possible). ?syevr allows to skip calculating...
View ArticleHyman monotonic cubic spline
Hi,I see in the MKL 2017 release note that the Hyman monotonic cubic spline is available, but I didn't manage to find how to use it in the MKL developer reference guide. Can you help me or provide me...
View ArticleCompact-routine forms of dgbtrf and dgbtrs for vectorizing LU decomp and solver
We see there are a number of vectorized compact routines in the Intel MKL library:https://software.intel.com/en-us/articles/intelr-math-kernel-library-introducing-vectorized-compact-routinesWe are...
View ArticleInstalling and Linking MKL with Intel Fortran and LS-DYNA
My research lab currently has license for Intel Fortran 10.1 to link with LS-DYNA for used defined feature development, but unfortunately not equipped with MKL library (I checked the directories). To...
View Articlegeneralized symmetric-definite eigenvalue problem with a shift
Hello.I have two matrices A and B and I want to solve the general eigenvalue Ax=λBx where B is positive definite and A is semi positive definite with the smallest eigenvalue of 0. So A is...
View Articleillegal instruction error with newer AMD CPU
One of the the illegal instructions is from function mkl_blas_def_dgemm_kernel_bdz() which is in libmkl_core.aNeed help!TCE Open Date: Tuesday, November 26, 2019 - 10:13
View ArticleIncomplete Cholesky decomposition
Hi,my question relates to this previous thread: https://software.intel.com/en-us/forums/intel-math-kernel-library/topic/...I am trying to solve a large (N > 50e6) sparse (~1e-6) symmetric linear...
View ArticleMatrix format support for DSS solver
Hello!I know PARDISO solver supports both CSR and BSR sparse matrix format, but what format does DSS solver support? Only CSR?And what are the other differences between PARDISO and DSS solver? If I...
View Articlemkl_sparse_convert_csr and mkl_sparse_convert_bsr
Hello,I used to assemble a sparse matrix in COO format. When I use mkl_sparse_convert_csr/mkl_sparse_convert_bsr to convert to CSR/BSR format matrix, is the column index in increasing order per row...
View ArticleGeneral question. Seeing error in lower digits when doing simple dgemm example
Hi, I am new to MKL. I started by doing a basic example which creates an NxM matrix A. A consists of random numbers between -1 and 1 and can contain one digit after the decimal point only. For...
View Articlecould pardiso handle a sparse equations with dynamic size?
Hi, I am new to Pardiso and I want to use pardiso to solve a large sparse linear equations in a transient problem. My problem is that my sparse matrix size is not fixed . it is dynamic and varies with...
View Articleis there any MKL function can outputs L matrix of cholesky decomposition
I want to solve some linear equations（Ax=b） with same matrix A and different vector b. So i decided to decompose matrix A with cholesky decomposition to get matrix L (A= LT*L).Is there any MKL...
View Articlepardiso_handle_store hangs
Hi,I'm using pardiso for a project at work. Everything seems to be working well except when attempting to store the handle after performing matrix factorization. For some reason, pardiso_handle_store...
View ArticleOnly positive eigenvalues for ?syevd
For an algorithm I need to get all positive eigenvalues and their corresponding eigenvectors for given real, symmetric matrices frequently (and as fast as possible). ?syevr allows to skip calculating...
View Article