Intel® Math Kernel Library

mkl_?csrcoo for rectangular matrices?


I hope this is not too much of a beginner's question, I just started using sparse matrices with MKL a few days ago. This is work within a large codebase so working examples are very time consuming to create. I will try to ask my question without any code snippet. Here goes:

I am using d/zcsrcoo to convert from COO to CSR, for square matrices ~10k-~100k, and it seems that everything is okay. 

However, I need to convert also rectangular sparse matrices with the same number of rows, but the number of columns easily x2~4.

HPL benchmark compilation problem


I am trying to build from sources the Intel version of HPL benchmark which is included in MKL libraries. I am able to make the compilation using the 'non-offload' version. When I try to build using parameter version=offload (as suggested in the guide) I recieve an error when the libhpl_offload.a library is missing. If the missing file is included there are no errors and compilation finishes successfully.

Generate Sobol Sequence


I would like to generate numbers from the Sobol sequence in dimension n (with n < 40). The MKL has a Sobol sequence generator, but reading the documentation only gives me headaches. I gave up when I saw ( that the directory that should contain examples for the VSL is only available on my installation.

Is there anyone who could give me a simple file that generates the Sobol sequence from the MKL ?

Thanks for your help.


Using openmpi with the mkl's cluster library.

Hi all,

I use the following tool chains to compile the vasp.5.3.5:

1- ifort, icc, and mkl are the ones bundled in composer_xe_2011_sp1.11.339.

2- openmpi version is openmpi-1.8.7.

It's well known that linking to mkl is a complicated thing, so I use the mkl_link_tool for my case to obtain the linking line as follows:

werner@debian:/opt/intel/composer_xe_2011_sp1.11.339/mkl/tools$ ./mkl_link_tool -libs -p no --cluster_library=scalapack -m openmpi --f95

1D Convolution


I need to compute the 1d convolution. Intel MKL offers two basic strategies to do this.

1) Explicit implementation of the convolution theorem by the user i.e. perform DFT's on the input data and on the kernel. Multiply the results in the Fourier domain element wise. Next perform an inverse DFT to get the desired result.

2) Compute the convolution directly by using VSL math function in FFT mode.

Is there double complex interface of Iterative Sparse Solvers based on Reverse Communication Interface?

Dear MKL experts,

     I have to solve the sparse complex double symmetric equations in huge size. I am looking for iterative sparse solvers. I found that the MKL just provides  RCI Interface Routines of double precision. Is there a set of RCI interface Routines of double complex precision? Or any suggestion to get around it?



订阅 Intel® Math Kernel Library