Parallel Processors from Client to Cloud


This chapter explains how computer architects have long sought to create powerful computers simply by connecting many existing smaller ones. It shows that multiprocessor software must be designed to work with a variable number of processors. One consequence of this is that energy has become the overriding issue for both microprocessors and datacenters. Replacing large inefficient processors with many smaller, efficient processors can deliver better performance per joule both in the large and in the small, but only if software can efficiently use them. Improved energy efficiency joins scalable performance in making the case for the use of multiprocessors. This parallel revolution in the hardware/software ...

Get Computer Organization and Design RISC-V Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.