Overview

Intel® C++ Composer XE 2013 has several software features that can improve the performance of your serial applications by using parallel processing.

OpenMP* is a collection of compiler directives, library functions, and environment variables that adds shared-memory parallelism to your application.
Intel® Threading Building Blocks (TBB) provides common parallel algorithm patterns in the form of function templates.
Intel® Cilk™ Plus adds parallelism to new or existing applications.

About This Tutorial

This tutorial demonstrates how you can improve the performance of the sample application by building different parallel implementations of the same function using both the gcc compiler and the Intel® Composer XE compiler.

After building the sample code with the different features, running the application displays the execution time required to render the object in the terminal session.

Estimated Duration

15-20 minutes.

Learning Objectives

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

Build a serial version and establish a performance baseline
Build a version that uses OpenMP* and compare the performance to the serial version
Build a version that uses Intel® TBB and compare the performance to the serial version
Build a version that uses Intel® Cilk™ Plus and compare the performance to the serial version