pardiso error with a particular set of data
Today in running a simulation test case I have found the following error:See attached txt file since by copying the test I received 'Your submission contains invalid characters ....".The compiler used...
View ArticleWarning signs when compiling Fortran 2008 code that uses...
Hello, I'm compiling a code that is linked to the MKL cluster sparse solver. This code is written in Fortran 2008 and compilation uses the -stand:f08 intel Fortran compiler flag. I use the include...
View Articlequestion about the blacs library in MKL
I can find a lot of examples use the syntax like Cblacs_get(...), Cblacs_pinfo(...), but I can not find the c-type declaration in the "mkl_cblacs.h". Is it legal to use this kind of c-wrapper function...
View Articleprogram sleep when set OMP_NUM_THREADS more than one
Dear all, I have written some codes with MKL, but recently I found this codes did not work if the set OMP_NUM_THREADS more than one. Here is an example code. I compile it with icc test.c -mkl. When I...
View ArticleChanges to the routine CGETRS between MKL 11.1.3 and MKL 11.3.3
Hi,After an upgrade from MKL 11.1.3 to MKL 11.3.3 I suspect that the mkl routine CGETRS gives slightly different results. This sounds very strange (since I believe it just forwards the calculation to...
View ArticleGuidance on integrating cluster_sparse_solver into my application
I am trying to integrate cluster_sparse_solver into my application, however, I am confused by this in the documentation:NoteMost of the input parameters (except for the pt, phase, and comm parameters...
View Articlein-core and out-of-core mode in pardiso
Hi, i am a beginner of MKL and am recently using the pardiso package as slover. I am hoping to run parallel cases by turn on the OpenMP in the solver. However, i do not know whether i should use the...
View ArticleIntel® Math Kernel Library (Intel® MKL) on CentOS 7, CPU IA-64 E5-2683v3
Hi all,I registered free license for MKL and installed on CentOS 7.2, CPU E5-2683v3 with errors:Error: A license for MKernL could not be obtained Your license restricts the platforms on which our...
View ArticleProblem compiling MKL with OpenMP
I'm trying to compile and load a code that uses MKL libraries to solve an eigenvalue problem. I use the following commands based on what the Intel MKL link line advisor tells me: ifort -c -i8 -qopenmp...
View ArticleCan't set number of threads >32 for Pardiso solver in MKL library
I'm running the pardiso solver on a machine with CentOS 6.5 using Fortran. I'm using MKL v 11.3When I set the number of threads using either environment variable MKL_NUM_THREADS or inside the Fortran...
View ArticleRe-use cluster pardiso factorization crashed
I'm trying to use cluster pardiso to solve large equations with complex hermitian matrix. I have multiple (>1000) right hand side but matrix A is the same, so I do phase 11 and 22 factorization...
View ArticleThe use of FFTW3 on my Xeon phi card (MIC)
hello , When i use the fftw3 in the MKL on the Intel Xeon Phi, i use the followed compile command : icpc -g -O0 -tbb -mkl=parallel...
View ArticleCNR setting does not work as expected
I am working on different machines (notebook and cloud, all Win7) and thus want to set CNR manually to get reproducible results (e.g. when working with Matlab).Thus, and using the latest MKL version, I...
View Articledf?dSearchCells1D give different result between Composer 16 and 16 Update3
Hello,I'm using the MKL in the Composer 16update 3 release and I notice a weird behaviour of the df?dSearchCells1D routine when a sitePoint is equal to the last breakPoint.I did a little test : const...
View ArticleAbout the set of padding_leading_dim or input(output) strides for (complex to...
Hello,I want to find some methods to increase my 4096*4096 complex to complex DFT performance on MIC using the MKL-DFT. In the following website, I find the attract method:Tip3: the leading dimension...
View ArticleBLACS and multiple MPI communicators
Dear all,I am trying to use parallel version of ?heevr (i.e., p?heevr of SCALAPACK) to get eigenvalues. To do so, it seems that I need to initialize BLACS.There are N cores in the system, which I...
View ArticleWhat is the recommend MKL re-distrubutables we should use?
There is a list of re-distrubutable files in the redist.txt file. Should we supply ALL of these re-distributales libs to our end customer to cover all bases and a chip sets etc, since some of these...
View ArticleAre there functions to calculate the local indexes of block-cyclic distribution?
I want to transfer a global index m to local indexes (p,b,i) and vice versa.Are there functions to do the calculations, m -> (p,b,i) and (p,b,i) -> m, in scalapack?
View ArticleHow to choose the block size and process number?
I want to diagonalize a large matrix, which size is about 40000*40000.Our supercomputer has 80 nodes and there are two cpus in each node with eight-core. I think it is very hard to diagonalize such a...
View ArticleWhat is the unit of workspace query?
For the scalapack, when I set the lwork = -1, I can get a result from work[0].For example, the work[0] == 900000000.So the lwork = 900000000. How about the length of work? is it lwork *...
View Article