The following components of Intel® MKL 11.0.1 and higher are tuned for the Intel® Xeon Phi Architecture:
Intel® Math Kernel Library
How to control the work division in Intel MKL on Intel Xeon Phi
In Intel MKL, for the automatic offloaded Level 3 BLAS functions (?GEMM, ?TRMM, ?TRSM), the computation can be divided among host CPU and Xeon Phi coprocessors by either using an environment variable or by calling a function and allow users to override the default work division decided by Intel MKL runtime.
The table below gives a few examples showing how to set and manage the division of work between the host and coprocessor(s).
Intel® MKL programming models for Intel® Xeon Phi
Users can take advantage of Intel® MKL on Intel® Xeon Phi by using the following usage models:
Intel® System Studio Training Materials
Here are useful slide decks to enhance your learning of Intel System Studio:
- Overview
- Build and Design
A Matrix Multiplication Routine that Updates Only the Upper or Lower Triangular Part of the Result Matrix
Background
Intel® MKL provides the general purpose BLAS* matrix multiply routines ?GEMM defined as follows:
C := alpha*op(A)*op(B) + beta*C
where alpha and beta are scalars, op(A) is an m-by-k matrix, op(B) is a k-by-n matrix, C is an m-by-n matrix, with op(X) being either X, or XT, or XH.
Contratto di licenza:
Introduction to the Intel MKL Extended Eigensolver
Intel® MKL 11.0 Update 2 introduced a new component called Extended Eigensolver routines. These routines solve standard and generalized Eigenvalue problems for symmetric/Hermitian and symmetric/Hermitian positive definite sparse matrices. Specifically, these routines computes all the Eigenvalues and the corresponding Eigenvectors within a given search interval [λmin, λmax]:
Intel® System Studio
The Intel® System Studio is a new integrated software development tools solution for Intel® architecture based Intelligent Systems and Embedded Devices.
Offload Runtime for the Intel® Xeon Phi™ Coprocessor
Contratto di licenza:
Tuning the Intel MKL DFT functions performance on Intel® Xeon Phi™ coprocessors
Overview
Intel® Math Kernel Library (Intel® MKL) includes the optimized DFT transform functions on Intel® Xeon Phi™ coprocessors. These functions are carefully vectorized and threaded to take advantage of the hardware features. This article provides some performance tuning tips on running MKL DFT function on Intel Xeon Phi coprocessors. We will start with some simple example code.
Building the example code
Pagine
