MKL 2017 Update 1, MKL_DIRECT_CALL and zgetri issue
I have found that when MKL_DIRECT_CALL is on, there seems to be an issue with one of the zgetrf/zgetri and 5x5 matrices. I am getting quite different results compared to MKL 2016 ( which did not have...
View Articleusing TBB thread local storage with MKL
Suppose I have the following code:tbb::enumerable_thread_specific<DataType> tls; tbb::parallel_for ( [&] () { DataType &data = tls.local(); cblas_....(data); });When the MKL is compiled...
View Articleblacs_gridmap globally blocking
Dear all,I have a question about how to perform ScaLAPACK operations in parallel. To be more specific, I want several MPI subcommunicators to call ScaLAPACK routines independently of each other,...
View ArticleUpgrading MKL completely trashed Visual Studio 15
I updated the MKL toolkit today to 2017 Update 1 (even though I had just installed it yesterday --, for whatever reason, the intel manager thought it needed to be updated), and immediately after this,...
View ArticleNMAKE unresolved external symbols
Hi,I'm playing around with the custom dll builder tool (windows\mkl\tools\builder) to make a stdcall BLAS dll for Win32.I'm using blas_stdcall_example_list provided in the same directory, with the...
View ArticleParallel Studio 2017 Update 2 breaks MKL auto linking in Studio
Automatic linking (in Visual Studio 2015 )of MKL is broken in Update 2. Previously if you selected MKL in Intel Performance Libraries the linker would get the MKL libraries automatically. I now have to...
View ArticlePardiso crashes with severe(172): Program Exception - access violation
I am trying to use Pardiso, but it keeps crashing with the error message "forrtl: severe(172): Program Exception - access violation" in the console and with the error message "Access violation reading...
View Articlecgelss parameter error
Hi,I am using cgelss() in a C++ program I am working on. Ever so often, the function prints out this error: "Intel MKL ERROR: Parameter 6 was incorrect on entry to CGELSS." Can someone explain to me...
View ArticleAccess violation for phase -1 of Pardiso
I am using Pardiso and everything works well except one thing. I noticed that my application keeps increasing the memory usage when Pardiso is repeatedly called. I found in the documentation that I...
View ArticleNumerical Integration Routines
Hello,Is there any MKL routine for numerical integration?We are interesting in numerical integration in a semiinfinite region and our integrand is oscillating but it decay quikly to zero (like a...
View Articlepardiso access violation problem
I am running a program which is basically an example code of pasdiso in mkl. The program successfully solved the example equations in my computer. When I added a line to make a file connection without...
View Articlepardiso_getdiag problem
Hello everyone!I am using pardiso to solve nonsymmetric system, but i don't get result that i expect. Today i tried pardiso_getdiag to understand what is going on with diagonal after factorization and...
View Articlefailure pardiso with CBWR
Hello everyone.I am using pardiso to solve unsymmetric system with CBWR(Conditional Bitwise Reproducibility) , but some special case it didn't work in symbolic factorize.The test matrix is simple 3x3...
View ArticleIntel Dfti equivalent to FFTW "fftw_plan_many_dft"
I am using the Intel Fortran compiler for Windows, Composer XE 2013 SP1. I am trying to convert my FORTRAN code to use the MKL FFT's, i.e., Dfti library. I could not find any reference or examples on...
View ArticleMKL licence for cloud machines?
We are a small company that has recently moved to using MKL for some of our core technologies. We use Amazon EC2 for both deployment and testing. We understand that the MKL licence is per-user and each...
View ArticleLinpack: Why do we run with LDA greater than the problem size N?
I am new to running Linpack. From the extended help, I see:The leading dimension must be no less than the number of equations. Experience has shown that the best performance for a given problem size...
View ArticleCan LINPACK be run on NUMA-enabled memory configurations?
I see in the documentation that LINPACK is run on SMP modes.Can LINPACK also be run on NUMA-enabled memory configurations?Any advantages or disadvantages?Thanks!Zone: Server
View Articlehow to include intel math kernel library in abaqus subroutine
I am trying to include the in-build subroutines of intel math kernel library in ABAQUS UMAT. I included 'mkl.fi' but it is showing the error as shown below (It is ABAQUS generated job...
View ArticleHow to activate MKL after installing via yum or apt
If one installs MKL via yum [1] or apt [2] how should one activate the product?When installing manually, by following the installation guide [3], one needs to either enter a serial number, to have the...
View ArticleProblem with Pardiso and indefinite matrix
Hello,I am using Pardiso to solve linear equations with an symmetric indefinite matrix (saddle-point structure). Usually this works quite good, however sometimes the solver teminates with the error...
View Article