Intel® C++ Compiler Tutorials

Using Auto Vectorization

The auto-vectorizer detects operations in the application that can be done in parallel and converts sequential operations to parallel operations by using the Single Instruction Multiple Data (SIMD) instruction set.

In this tutorial, you will be introduced to adding parallelism to your serial application by using the auto-vectorizer on the sample code. You will then compare the performance of the serial version and the version that was compiled with the auto-vectorizer.

Using the Intel® Xeon Phi™ Coprocessor

A system with the Intel® Xeon Phi™ coprocessor can run your application on both the CPU and the coprocessor. The application starts at the CPU with user-defined sections of the source code offloaded to the coprocessor.

In this tutorial, you will compile the sample source code into an application that runs on both the CPU and the coprocessor. You will then examine the source code to see how you can define sections to run on both the host CPU and the coprocessor.

Note: You will need a system based on the Intel® Xeon Phi™ products to complete this tutorial.

Threading Your Application

This product has several software features that can improve the performance of your serial applications by using parallel processing. Open Multi-Processing (OpenMP*) is an API that supports multi-platform shared-memory parallel programming in all architectures. Intel® Threading Building Blocks (Intel® TBB) provides common parallel algorithm patterns in the form of function templates. Intel® Cilk™ Plus adds parallelism to new or existing programs.

In this tutorial, you will improve sample code by compiling a version using OpenMP, Intel® TBB, and Intel® Cilk™ Plus. You will then see the performance difference between the serial version and versions using these features.

Using Intel® Graphics Technology

A system with Intel® Graphics Technology can run an application on both the CPU and the processor graphics. The application starts at the CPU with user-defined sections of the source code offloaded to the processor graphics.

In this tutorial, you will compile the sample source code into an application that runs on both the CPU and the processor graphics. The source code contains sections that are defined to run on both the CPU and the processor graphics. After compiling the source code, you will then look at the source code to see how you can define sections to run on both the CPU and the processor graphics. Finally, you will compile the same source code into an application that runs only on the CPU.

Getting Started with Intel® Cilk™ Plus SIMD Vectorization and SIMD-enabled Functions

SIMD Vectorization and SIMD-enabled Functions are a part of Intel® Cilk™ Plus that provide ways to vectorize loops and user defined functions.

In this tutorial, you will be introduced to using vector SIMD-enabled functions and SIMD directives from Intel® Cilk™ Plus to help the compiler vectorize C/C++ code. This tutorial is available from the Intel® Developer Zone at this URL: http://software.intel.com/en-us/articles/getting-started-with-intel-cilk-plus-simd-vectorization-and-elemental-functions.

Getting Started with Intel® Cilk™ Plus Array Notations

Array Notations is an Intel-specific language extension that is a part of Intel® Cilk™ Plus that provides ways to express data parallel operation on ordinary declared C/C++ arrays.

In this tutorial, you will be introduced to the Array Notations feature from Intel® Cilk™ Plus to help the compiler vectorize C/C++ code. This tutorial is available from the Intel® Developer Zone at this URL: http://software.intel.com/en-us/articles/getting-started-with-intel-cilk-plus-array-notations/.