July 2011
Intermediate to advanced
648 pages
13h 2m
English
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 ...
Read now
Unlock full access