Stack Overflow
Stack Overflow

Questions tagged [intel-mkl]

Intel MKL (Math Kernel Library) is a high performance math library specifically optimised for Intel processors. Its core functions include BLAS and LAPACK linear algebra routines, fast Fourier transforms and vector math functions amongst others.

Intel MKL (Math Kernel Library) is a high performance math library specifically optimised for Intel processors and explicitly parallelised with a version specifically available for High End Supercomputer clusters. Its core functions include BLAS and LAPACK linear algebra routines, fast Fourier transforms and vector math functions amongst others.

Intel MKL only supports Intel and compatible processors and is available for Windows, Linux and OS X as part of Intel® Parallel Studio and Intel® System Studio. There are free versions available for Students and Academic researchers at qualifying institutions.

The Intel® Math Kernel Library includes the following groups of routines:

  • Basic Linear Algebra Subprograms (BLAS):
    • vector operations
    • matrix-vector operations
    • matrix-matrix operations
  • Sparse BLAS Level 1, 2, and 3 (basic operations on sparse vectors and matrices)
  • LAPACK routines for solving systems of linear equations
  • LAPACK routines for solving least squares problems, eigenvalue and singular value problems, and Sylvester's equations
  • Auxiliary, utility, and test LAPACK routines
  • ScaLAPACK computational, driver and auxiliary routines (only in Intel MKL for Linux* and Windows* operating systems)
  • PBLAS routines for distributed vector, matrix-vector, and matrix-matrix operation
  • Direct and Iterative Sparse Solver routines, including a solver based on the PARDISO* sparse solver and the Intel MKL Parallel Direct Sparse Solver for Clusters
  • Direct Sparse Solver (DSS)
  • Extended Eigensolver routines for solving symmetric standard or generalized symmetric definite eigenvalue problems using the Feast algorithm
  • Vector Mathematical Library (VML) functions for computing core mathematical functions on vector arguments (with Fortran and C interfaces)
  • Vector Statistical Library (VSL) functions for generating vectors of pseudorandom numbers with different types of statistical distributions and for performing convolution and correlation computations
  • General Fast Fourier Transform (FFT) Functions, providing fast computation of Discrete Fourier Transform via the FFT algorithms and having Fortran and C interfaces
  • Cluster FFT functions (only in Intel MKL for Linux* and Windows* operating systems)
  • Tools for solving partial differential equations - trigonometric transform routines and Poisson solver
  • Optimization Solver routines for solving nonlinear least squares problems through the Trust-Region (TR) algorithms and computing Jacobi matrix by central differences
  • Basic Linear Algebra Communication Subprograms (BLACS) that are used to support a linear algebra oriented message passing interface
  • Data Fitting functions for spline-based approximation of functions, derivatives and integrals of functions, and search
798 questions
0
votes
1 answer

What sparse solver supports diagonal storage format

I'm writing finite-difference method program using C. The stiffness matrix is symmetrical and band. For its storage I'd like to use Sparse Diagonal Storage format. Could someone tell please, what solvers can use diagonal storage format? Intel MKL's…
Ivan Kush
  • 2,958
  • 2
  • 23
  • 39
0
votes
1 answer

How to link MKL with MPI?

I want to compile this C code with MKL, but when I run it using the command mpicc -mkl mkl_thread.c, it gives me an error about an unrecognized command line option -mkl. When I run it as mpicc mkl_thread.c -o mkl_thread, it gives a different error,…
Gevni
  • 43
  • 2
  • 10
0
votes
1 answer

Alg. MKL Threaded DGEMV

As we all may know, there are lots of different ways to implement DGEMV in parallel (column or block -wise etc) resulting in different communication overheads. I have been looking through both the MKL and all the reference manuals to BLAS to try…
user1978271
  • 1
0
votes
1 answer

Why is solving system of linear equations using cula(dgesv) slower than mkl (dgesv) for small data sets

I have written a CUDA C and C program to solve a matrix equation Ax=b using CULA routine dgesv and MKL routine dgesv. It seems like for a small data set, the CPU program is faster than the GPU program. But the GPU overcomes the CPU as the data set…
Kofi Baah
  • 1
  • 3
0
votes
1 answer

MKL Intel C++ and quasi-random numbers generator

I am using MKL Intel for random number computation. I use Quasi random algo. Also, it seems to me that number that are generated are not random at all. I understand that Quasi random algo will provide sampled points that maximize space occupation.…
kiriloff
  • 25,609
  • 37
  • 148
  • 229
0
votes
0 answers

mkl random number generator and FLT_MAX

I am using quasi random number generator from mkl Intel. I created my own wrappnig method to allow for definition of maximum and minimum bounds for rng. However, seems not to work when values for bounds aer FLT_MIN FLT_MAX. So that I wonder what is…
kiriloff
  • 25,609
  • 37
  • 148
  • 229
0
votes
1 answer

Why does scipy expose Lapack pbsv (b for banded, e.g. linalg.solveh_banded) but not ptsv (t for tridiagonal)?

Looking at the source for scipy.linalg.solveh_banded, it just wraps Lapack pbsv. I'm looking for a more efficient solver for tridiagonal (Hermitian, or in my case real symmetric) systems which I think should be provided by the Lapack ptsv function.…
Joseph Hastings
  • 561
  • 2
  • 7
  • 14
-1
votes
1 answer

What is the invocation procedure for ifort in an intel oneAPI base installation?

I am trying to use math kernel library of intel along with its fortran compiler, which comes built into the oneAPI basekit. However, the command "ifort" does not work since the terminal complains about it not being found in the system. I had setup…
Dabu
  • 9
  • 5
-1
votes
1 answer

Setting number of threads in python

I have a python script which consist of numpy and scipy functions. I was trying to check the scaling for my code. numpy.show_config() The configuration for the numpy installed in my system shows the following information. blas_mkl_info: …
Jenet Scaria
  • 3
  • 1
-1
votes
1 answer

MKL FFT bin zero real and imaginary parts

I'm trying to do some ffts with MKL's ComputeForward method. Sometimes I get bins with zero on real and imaginary parts. I,.e I'm doing an FFT of floats of 20480 samples of a 16K tone sampled at 1.024 Msps, thus 50 Hz resolution per bin. The bin…
perencia
  • 1,498
  • 3
  • 11
  • 19
-1
votes
1 answer

How to implement numpy broadcast mechanism with mkl?

How to implement numpy broadcast mechanism with mkl?   I have been confused, how to use mkl to efficiently implement the broadcast mechanism in numpy (Element wise operator "+","-","*")? such as 2-D array sub 1-D array [[1,2,3], …
梁先锋
  • 1
-1
votes
1 answer

Solve general eigenproblem with mathnet

I found a very promissing package (MatNet) to work with in my structural engineering program. However, while MathNet relies heavily on MKL from Intel, I cannot see how I can solve a general eigenproblem to find the structure's…
Erik
  • 894
  • 1
  • 8
  • 25
-1
votes
2 answers

Set openmp in MKL Library

I am trying to compile a minimal C++ code #include #include #include int main(int argc, char *argv[]) { omp_set_num_threads(4); return 0; } using the MKL library (icc version 17.0.4) in a MacOSX Sierra 10.12.5, using…
Galuoises
  • 2,630
  • 24
  • 30
-1
votes
3 answers

Ways to accelerate reduce operation on Xeon CPU, GPU and Xeon Phi

I have an application where reduce operations (like sum, max) on a large matrix are bottleneck. I need to make this as fast as possible. Are there vector instructions in mkl to do that? Is there a special hardware unit to deal with it on xeon cpu,…
hrs
  • 487
  • 5
  • 18
-1
votes
1 answer

Did gfortran drop svml support on Cygwin?

I am having some trouble compiling Fortran code on a brand-new Cygwin installation, which I can trace back to undefined references to functions in the Intel svml (Short Vector Math Library) library. Specifically, I am getting errors of the…
E.P.
  • 342
  • 4
  • 13
1 2 3
…
53
54