How to use "mkl_mic_free_memory"?
Dear all,I would like to use AO and CAO. I could enable/disable AO and set max. memory, but mkl_mic_free_memory is not working.Here is an example: dim = 1024*8 allocate (A(dim*dim)) allocate...
View Articlehow to tell mkl the underlying microarchitecture
Hi: I read the gcc document as well as intel compiler document, they both said that the default behavior will not detect the underlying microarchitecture in linux x86-64 (default is -xsse2). As a...
View ArticleRun time problems with eigenvalue decomposition
Dear all, I have the following problem with the LAPACK driver routines used for solving symmetric eigenvalue problems in C++. As the input, I have complex Hermitian matrices with the dimension ~30X30....
View ArticleHow to use complex data type in MKL C program?
Dear all:I am facing a problem on how to use lapack_complex_double data type, Including multiply, divide,conjugate(I can do this using z_imag=-z_imag, is this the best way?), and print the...
View Articleciting intel mkl libraries and ifort
Dear all,How should I cite the MKL and ifort all together in a paper manuscript?BR,Umut
View Articleintel mkl mkl_freeBuffer() access violation exception error
hi i use mkl c++ compiler 11.0.066 and mkl10.1 and c++/clr vs2008i use fft and conv function from mkl in multi thread realtime application (each thread exec fft and conv parallel)but after little time...
View ArticleXeon w3680 runs slower than i5-3320M
Hi,I have strange problem where the same program runs slower on a i5-3320M than an Xeon w3680. The main part of the code is FFT. Could anyone shine some light on me? Thanks!
View ArticleMKL DGEMM thread safety
When I run my threaded application (several threads calling Fortran subroutines that use MKL lapack function DGEMM), Im getting the "DGEMM parameter number x had an illegal value" where X could be 8,...
View ArticleEigenvalue precision
Hello everyone,I am working on a project where it is important to distinguish between 0 eigenvalues and non zero eigenvalues. Using the MKL routine LAPACKE_zheev returns me a list of eigenvalues which...
View Articlecannot find ScaLAPACK libraries in Composer XE 2015 for C++ Linux
Hello,I've downloaded Intel Parallel Studio XE Composed Edition for C++ Linux, (composer_xe_2015) and tried to compile a test program for ScaLAPACK. However, I cannot find the ScaLAPACK libraries in...
View ArticleClik here to view.
Improve Intel MKL Performance for Small Problems: The Use of MKL_DIRECT_CALL
One of the big new features introduced in the Intel MKL 11.2 is the greatly improved performance for small problem sizes. In 11.2, this improvement focuses on xGEMM functions (matrix multiplication)....
View ArticleCompiling R 3.1.1 with MKL - undefined reference to symbol...
Hello,I need to compile R with shared library (--enable-R-shlib) in order to use a specific IDE (rstudio) and I am running into trouble. Hopefully I'll be able to get some help from you.I previously...
View ArticleSparse Matrix
Steve:I have stumbled into this interesting problem - I need to invert a large (5000 by 5000) sparse matrix.Clearly I am going to use MKL but I have not played previously with sparse matrices. The...
View ArticleWant to link MKL to existing code
Hi, I am replacing certain operations specifically vector dot product,matrix vector multiplication and solve AX=b in existing code by calls to lapack subroutines. Do I need to link the MKL in the...
View ArticleGetting very low efficiency for mkl_dcsrmv function
Hi,I am trying to benchmark the intel mkl library function mkl_dcsrmv. I tried running the function for single, three,five and seven diagonals nnz entries and i repeated it multiple times with...
View ArticlePerformance of offloaded MKL FFTs on the MIC, anyone?
My initial experiments offloading MKL FFTs into the MIC (using C language in Linux) give me approximately 9.3 GFLOPS of performance, judging by the reported [MIC Time] numbers when I set the...
View Articledjacobix only uses 4 threads on a 16 CPUs virtual machine
Hello,I'm using djacobix in Intel MKL. My testing machine is a virtual Windows Server 2012 with 16 CPUs, . I'm use the following statements in my code: mkl_set_dynamic(0);...
View Articledgemm - Intel inspector: "uninitialized memory acces"
Hi,I launched an Memory Error Analysis with Intel Inspector on simple test of the dgemm function and i got this warning:"uninitialized memory access"located on the dgemm call.Here is my test (really...
View Article