Intel® Math Kernel Library

slower on a P4 than on a athalon?

I'm using Intel's MKL for linux on a 1.2 Ghz AMD athalon w/ 256k L2 cache running fedora core 3 and a mobile Pentium 4 2.8 GHz w/ 1Mb L2 cache with a much faster FSB. Both systems have 512M of RAM, and I believe the RAM in the P4 computer is on a faster bus and it is dual channel.

I've written some code that exploits all aspects of the MKL: the cblas routines, the vsl, the vml, and even one or two functions from lapack.

I've now compiled and debugged the code on both of the two computers using gcc with the -pg option:

error:could not find required blas library

Although I have already installed the ifc8.1 (which contains g77 compiler as well) in our Itanium workstation,but still a problem persists in compiling a particular code. The reason might be somewhere else, which I am not yet able to find out.
******************************************
checking for sgemm... no
checking for ATL_xerbla in -latlas... no
checking for sgemm in -lmkl_def... no
checking for sgemm in -lblas... no
checking for sgemm in -lblas... no
checking for sgemm in -lmkl... no
checking for sgemm in -lcxml... no

size limitation with the MKL library



Hello


We are working with the Intel-MKL free evaluation library. (We also use Compaq Visual Fortran 6.6 as you recommend). The problem we want to solve is to calculate the pseudoinverse matrix by using the DGESVD routine (i . e. single value decomposition with the double precision option). However we have experience linking problem as the dimension of the matrix we must work is very high (200.000x 200.000).

MKL 7.2 with AMD Athlon processor

Hi,

I would like to know if Intel MKL 7.2 is optimized for AMD athlon processor (32 bit windows XP) machines too.If you got any comments please let me know how the performance would be affected when the following takes place :

MKL 7.2 -> Used in C++ project (FFT module) -> Run on AMD processor

Thanks in advance,
Arun.

: undefined reference to `vmldSinCos2'

Hello,

I am trying to compile an electronic band structure program on p4-ifc-linux.

I have installed mkl 7.2.1, and fftw 3.0.1.
Below is the entry in the Makefile that include BLAS:

BLAS=-L/opt/intel/mkl721/lib/32 -lmkl_p4 -lguide

And this is the line that include FFT3D:

FFT3D = fftw3d.o fft3dlib.o /usr/lib/libfftw3.a

I encounter the following link error:

paw.o(.text+0x8338): In function `paw_mp_augsym_noncol_':
: undefined reference to `vmldSin2'

undefined reference to `dsyev_'

hi,
I'm trying to link mkl version 7.2 with a program using standart LAPACK dsyev, zheev subroutines. Note with generic vendor lapack/blas libraries it works well. Nevertheless using mkl with following linking options:

-L/opt/intel/mkl701/lib/32 -lmkl_lapack32 -lmkl_def -lguide -lpthread -lg2c -O3 -r8 -tpp7

I obtain following errors:

soldm.o(.text+0x787): In function `soldm_':
: undefined reference to `dsyev_'
kspace2.o(.text+0x1943): In function `kspace_':
: undefined reference to `zheev_'

MKL7.2.1 32 bit example and test files' runs.


Hi,
I am currently trying to run example and test files in mkl 7.2.1 product. Even though I was successful running them in 64 bit with Intel 8.0 compilers. I was unsuccessful with them even though I modified the makefile for each test and example for both GNU and Intel Compilers.

The error I am getting is shown below( I also attached the makefile that I modified);

How can I just get a simple uniform random generator?

I don't know many about the random generator, and I just want to get a uniform random generator within 0 to 1, just like the button 'Rnd' on some calculators. I haven't tested some subroutines provided by MKL, but unfortunately, it didn't work yet, mostly caused by the fact that I didn't know what's seed or stream. Could andbody help me? Just telling me the name of the subroutine and usage will be apprciated enough.

Páginas

Assine o Intel® Math Kernel Library