Intel® Math Kernel Library

Which of libmkl_blacs_* should be use?

Hi all,

I've installed Intel C++ & Fortran 10.1.008 Compilers on an AMD64 opetron cluster.

MKL - is also installed.

One of the application's makefile contains following BLACS( libraries :

To replace these libraries with MKL libraries, which of the following blacs libraries to use?


hello every body,
please i need ur help ..

in my project, i will work with PDGETRF routine for Lu factoriztion,
and i think that MKL library is useful for me , and i installed it on my machine.
but, my problem is after the installation what i can do? and how i can using this library in my code which i use C language and MPI...

please help me

best regards

Problems with linux and libmkl_gnu_ilp64.a


Ive got some problems with the static library libmkl_gnu_ilp64.a!

The whole thing! We can compile our project with the linux icc (intel-compiler) and the libmkl_intel_ilp64.a. Now we want to test the compiling with the gcc. The problem is that we cannot find this library. It was not include in the normal directory /lib/em64t.

For a non 64 bit version it is possible to link with the libmkl.a library. Please can anyone send or tell me where the libmkl_gnu_ilp64.a library is.

Thanks for the help! fachfan

libiomp5md vs libguide40 in MKL 10

What is the difference between libiomp5md.dll and libguide40.dll in the context of MKL 10? In the User Guide, the first is described as the compatibility threading library, and the second as the legacy threading library. From the names, I guess that I should use the compatibilty library except when circumstances force me to use the legacy library. But there is no clue about what such circumstances might be.


I am a new user to FORTRAN and I had a question about the MKL function vsceil. I am not getting the results I expect.

for example,

call vsceil(1,4.5,test)
print '(I)',test

returns 1084227584.

Am I doing something wrong here? I should expect to see 5 right?


Pb at the execution of a code linked with Intel Cluster Toolkit

Hi again,

I have a code parallelized by using Scalapack and MPI that works on a first cluster when compiled with PGI pgf90 and linked with MPICH2 and MPICH2 version of BLACS and SCALAPACK.

I want to port this code to a new Intel Xeon quadcores cluster on which we do not have pgf90 but Intel compilers, MKL and ICT

When I try to execute a binary created by:

unresolved __I_MPI__intel_fast_memcpy


I have a hard time trying to compile and run a code using the scalapack version included in Intel cluster toolkit :

my LD_LIBRARY_PATH variable will give you the version numbers:


When I try to make a static link with ifort:

Intel® Math Kernel Library abonnieren