Chapter 21. Matrix Multiplication with OpenCL

Matrix multiplication is commonly used to demonstrate program optimization in high-performance computing. In its most basic form, matrix multiplication is a toy program consisting of a single multiply-accumulate statement buried inside a triply nested loop. Unlike most toy programs, however, matrix multiplication has a more serious side. First, this operation is the single most important building block for dense linear algebra computations. Second, if you work at it hard enough, matrix multiplication can run near the peak performance of most modern processors. Therefore, it presents many opportunities for performance optimization, and making it fast has practical value.

In this discussion, we will ...

Get OpenCL Programming Guide now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.