Sunday, 6 June 2010

Cache oblivious algorithms: Matrix multiply

The F#.NET Journal just published an article about cache oblivious algorithms:

"The widespread adoption of CPU caches around two decades ago forced a change in the way programmers traverse data structures when performance is of interest. The classic style was to iterate directly using for loops. Two new styles have emerged: either a cache aware set of loops that tile the dataset into fixed-size subsets that fit into a cache of a known size, or a cache oblivious style that uses divide and conquer to subdivide the problem until it fits into the cache regardless its size. This article describes the revolutionary idea of cache oblivious algorithms via the elegant and efficient implementation of a matrix multiply in F#. In particular, we demonstrate the importance of these techniques in the context of multicore programming...."

To read this article and more, subscribe to The F#.NET Journal today!


Anonymous said...

Very Interesting!
Thank You!

Anonymous said...

Por que no:)