Pardiso Specify Max CGS Iterations
Is there a way to request a new feature to change the maximum number of CGS iterations in the hybrid Preconditioned CGS/CG solve in Pardiso? iparm[3] allows you to change the convergence tolerance and...
View ArticleUpdating MKL without rebuilding application
Hello,I am using NumPy/SciPy manually built with MKL as BLAS. I am wondering is it possible to update from MKL 2018 update 3 to MKL 2019 without rebuilding NumPy/SciPy?Thanks in advance for providing...
View ArticleCan Intel's Poisson solver routines be applied to the following general...
Hi, I see in the documentation that Intels' Poisson solver routines can be used to solve equations of the form∇.∇u = f Can they also (perhaps via some additional steps) be applied to an equation of the...
View ArticleMissing PARDISO examples
Hi, I've recently downloaded the intel MKL, but am unable to locate example files for PARDISO. I've tried looking in areas suggested here and here , and have tried running commands likefind $MKLROOT...
View Articleproblem with pdsyevx when calculating some eigenvalues only
Dear all,I see the following terminal output when using pdsyevx from Intel MKL 2019.0.117 with mpich 3.2.1 to calculate only some eigenvalues:{ 0, 0}: On entry to PDORMTR parameter number 12 had an...
View ArticleIssues Compiling Intel DAAL Example Code
Hello everyone, I have been trying to compile one of the example source codes using "icl". I have never had issues compiling Intel MKL code by linking to the MKL libraries: icl mkl_code.cpp...
View ArticleWhat is the best option of memory alignment for IA32??
I need your help.My application is running on IA32. I use mkl_malloc(), but, I don't know exactl what i should enter number is 32 or 64 for IA32.I am wating your advice.
View Articlememory allocation
I wrote a sample code to test mkl_malloc as below.When I run this code, I encounted memory error. Could somebody explain to me why this happened and how to slove this problem?? typedef struct _a_ { int...
View ArticleWhere is the value of "CblasRowMajor" set and declared in MKL tutorial sample?
In the C version of MKL's tutorial, source file dgemm_example.c, line 71: cblas_dgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans, m, n, p, alpha, A, p, B, n, beta, C, n); Where is the varialble...
View ArticleContext-sensitive help does not work.
I have integrated MKL into Visual Studio 2015. The MKL developer guide says that as long as I select the function name and press F1, the context-sensitive help will open the function description in Web...
View ArticleDirect Sparse Solver for Clusters poor scaling
Hi,We are currently developing a distributed version of our c++ finite element program. We planned to use the Intel Direct Sparse Solver for Cluster but it seems we can't reach good scalability with...
View ArticleIs mkl speed dependend upon how contiguous memory is?
Does the speed of the mkl blas/lapack library routines change significantly when one has contiguous memory versus not?I have a strange problem that looks like a "Memory Cache Leak" (not a memory leak)...
View ArticleCan PARDISO routines exploit an initial guess?
Hi, I'm using PARDISO to find vector x in the equation Ax = b Where A is a real unsymmetric matrix. In the PARDISO manual, they mention the vector x is only accessed in the solution phase. If I...
View ArticleMeeting Access Conflict when trying to use mkl_sparse_convert_csr
Hi, has anyone encounterd the situation I met? All I did was try to convert a sparse matrix in CSC format to CSR format.At the foremost , I use mkl_sparse_z_creat_csc to create a matrix in CSC format,...
View ArticlePARDISO - different time in factorization step
Hi allWe use the PARDISO solver (Parallel Studio 2018) in our FEM code for a symmetric indefinite system and discovered that the time spent in the factorization step may vary significantly. We use the...
View ArticleIntel MKL FEAST
HiI am using feast extremel eigenvalue solver (dexample_extremal_ev_c1.c). for finding lowest eigenvalues. My matrix size is big 1 million cross 1 million. There are around 31 non zero values in each...
View ArticleLooking for a library or package that can read and write sparse matrices
When Intel visual Fortran call Pardiso in MKL to solve a linear equation group, you need to read the sparse matrix from the file. But there are many ways to store sparse matrices in files (such as:...
View ArticleSchur complement for asymmetric matrix
Hi all,I am using mkl pardiso to do Schur complement. So far I got it working for symmetric matrix. But for asymmetric matrix, I got crash at phase = 11. The error message is "... Access violation...
View ArticleCan I use MKL_DIRECT_CALL JIT on a Core i5 CPU?
The MKL Developer's Guide says JIT can be used on Xeon processor with AVX2, but can it be used on a Core i5 CPU with AVX2?
View ArticleWhat LAPACK function is available to calculate 2-norm of a matrix?
What LAPACK function is available to calculate 2-norm (or spectral norm) of a matrix? Thank you.
View Article