About This Tutorial

This tutorial demonstrates how to use oneMKL in your applications:

• Multiplying matrices using oneMKL routines

• Measuring performance of matrix multiplication

• Controlling threading

Estimated Duration

10-20 minutes.

Learning Objectives

After you complete this tutorial, you should be able to:

• Use oneMKL routines for linear algebra

• Compile and link your code

• Measure performance using support functions

• Understand the impact of threading on oneMKL performance

• Control threading for oneMKL functions

More Resources

This tutorial uses the Fortran language, but the concepts and procedures in this tutorial apply regardless of programming language. A similar tutorial using a sample application in another programming language may be available at https://software.intel.com/content/www/us/en/develop/documentation.html.

The Developer Guide contains detailed information about several topics, including: compiling and linking applications, building custom DLLs, threading, and memory management. You can find the developer guide(s) here:

• Intel® oneAPI Math Kernel Library Developer Guide for Linux*
• Intel® oneAPI Math Kernel Library Developer Guide for Windows*
• Intel® oneAPI Math Kernel Library Developer Guide for macOS*

The Developer Reference (in C, Fotran, and DPC++ formats) contains detailed descriptions of the functions and interfaces for all library domains. You can find the developer reference(s) here:

• Developer Reference for Intel® oneAPI Math Kernel Library - C
• Developer Reference for Intel® oneAPI Math Kernel Library - Fortran
• Intel® oneAPI Math Kernel Library - Data Parallel C++ Developer Reference

In addition, you can find more resources at https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl.html.