Abstract

This chapter presents the history of high performance machines. The development of high performance machines has advanced over the past 30 years. Parallel supercomputer architecture had traditionally been broken up into three distinct kinds: pipelined supercomputers, vector supercomputers, and multiprocessor supercomputers. In addition, high speed memory systems have been developed to keep up with the processor performance. Parallel processor machines allow for different kinds of parallelism. These include control parallelism, data parallelism, and task parallelism. Traditionally, supercomputers have been grouped into categories of architectures that reflect the relationship between the hardware and the kind of parallelism: (1) SISD (single instruction stream, single data stream); (2) SIMD (single instruction stream, multiple data stream); (3) MISD (multiple instruction stream, single data stream); and (4) MIMD (multiple instruction stream, multiple data stream). Multiprocessor systems usually have at least two processors that are controlled by a single operating system.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call