-lpthread in sequential mkl?
The link line provided by MKL link line advisor(https://software.intel.com/en-us/articles/intel-mkl-link-line-advisor) for linking static sequential libraries is:-Wl,--start-group...
View Articleoptimize 1D FFT performance
Hi,I am trying to apply 1D FFT to a 3D matrix along a single direction. Below is the code I am currently using. It has a nested loop to loop through the other 2 dimensions. It works but I am just...
View ArticleCompiling NumPy+MKL on Windows with Composer XE 2013 SP1
Just bought the entire Composer XE 2013 SP1 package to compile NumPy/SciPy on a Windows Platform.numpy-1.8.1 scipy-0.13.3 What are the proper build instuctions assuming I want to build with a .bat file...
View Articleoutput length of cosine transform
I have a seemingly naive question: why the length of the output of cosine transform might be longer than n? For example, for staggered cosine transform, the output length is 3n/2. But just looking at...
View Articlemkl with matlab mex interface
Dear users:I am having trouble interfacing my intel mkl code with Matlab using the mex interface. I have a code that does a certain factorization based on the pivoted QR decomposition. It works fine...
View Articleproblem with DSS Interface with multiple right hand side
Hi: I try to use mkl_dss to solve a complex symmetric linear algebra. And the c++ code is:#include<iostream> #include<iterator> #include<complex> #include<vector>...
View Articlegetting error mkl_types.h: No such file or directory;
hi,i'm a biginner of intel mkl as I tried to comile .c file with gcc i fot the error mkl_types.h: No such file or directory even though i have that file.can u please suggest me the reason.thanku in...
View ArticleScipy Crash with MKL
hi guysI'm having Scipy crash with MKL on Rhel 6.5.Here is my configuration when i build Scipy:CFLAGS : -m64LDFLAGS : -lmkl_gf_lp64 -lmkl_gnu_thread -lmkl_core -lgomp -lpthread -lmThe Numpy site.cfg...
View ArticleConfused by dsytrf documentation
I have created a wrapper/helper function to call 'dsytrf'. It works (i.e l*d*l' == A) in all cases in which 'ipiv' is simply sequential and all the "blocks" of the "block diagonal"'D' are 1x1. However,...
View Articlepardiso_setenv crashes pardiso
I have a simple example as follows: int n = 5; std::vector<int> ia(6); for(unsigned i=0;i<ia.size();_i++)ia[i]=_i; std::vector<int> ja(5); for(unsigned...
View ArticleMinor error in Link Line Advisor
The Link Line Advisor at https://software.intel.com/sites/products/mkl/mkl_link_line_advisor.htm displays under item 7 ("Select interface layer:") the only choice "LP64" even when the chosen...
View ArticleGetting different time measurement while runs a same code
hi.,as i'm running a example code in intel mkl directory /opt/intel/composer_xe_2013_sp1.0.080/mkl/examples/spblasc with the following time function:#include<mkl.h>double time_st = dsecnd();//...
View ArticleLow Accuracy on dgeevx results, how to increase accuracy?
Dear all,I am trying to solve a non-symmetric tridiagonal eigenvalue problem with dgeevx from MKL, however the accuracy of the eigenvalues are not that good. I am also using dsyevr for symmetric...
View ArticleDifficulty of compiling fortran code while linking with mkl
Hi,I have been trying to compile my fortran code, where I am using a couple of mkl functions such as dss solver, MKL_DCSRMULTCSR, MKL_DCSRGEMV, etc. Previously I had a similar code, from which I was...
View ArticleClik here to view.
getting incorrect fft output
I noticed I was getting some incorrect output for some fft's, I noticed all the incorrect output corresponded to fft's of length 168. Code which reproduces the error, mkl_test.c, and its output...
View ArticleOpenMP vs trigonmetric transforms
Hi, !$omp parallel private(iy,iz,bx,by) shared(ll,nn,mm,b,im1) !$omp do do iz = 1,ll do iy = 1,nn bx=.0 by=.0 !fetch data bx(1:mm)=real(b(1:mm,iy,iz,ik)) by(1:mm)= aimag(b(1:mm,iy,iz,ik)) !compute...
View ArticleClik here to view.
ifort compilation error- failes to recognize MKL Lapack function dlange()
Hi, My question is perhaps very bugging since I'm a complete novice.. Could you please advice me about properly linking & compiling my F90 code to use MKL Lapack routines & libraries.. I can...
View ArticleTypographical slips in documentation for ?stegr()
The reference manual for MKL 11.1 update 3, https://software.intel.com/en-us/node/469068 , has two instances where, under the description of liwork in the input arguments list for ?stegr(), it says...
View ArticlePARDISO Scalability
Hi,I have a question about scalability of the PARDISO solver. I'm using Intel MKL PARDISO with my Finite Element code. I tested simple linear elastic problem with around 800 000 unknowns. The time...
View ArticleChanging the sign of complex exponential in DftiComputeForward()
Hi,I am currently working with FFT tools of MKL 10.3.12, specifically Dfti and Fortran interface. In my Forward transform, complex exponentials have positive sign as opposed to the default negative...
View Article