High performance computing

High performance computing, from PCs to supercomputers, is in a confused state. Which architecture, how much parallelism, which software, and when to innovate are all commonly heard questions. The confusion ranges across industry, government, and academia, and all are closely linked to technical difficulties and policy issues. High Performance Computing clarifies a number of these technical points and policy directions in proposing steps toward practical parallel processing. Because hardware technology appears unable to provide continuing speed increases, and because parallel architectures and software are not sufficiently developed to provide the practical solutions that have seemed tantalizingly close for some time, computing as a whole is at a crossroads. Even after more than a decade of commercial development, no standard or widely accepted systems have emerged. However, this text defines practical parallelism tests and suggests how they can be passed by giving specific technical suggestions and outlining policy steps that should be taken. Also suggested are methods for evolving better systems from those already in use and applying the definitions of what is needed as rules of selection. Students in high performance computing courses, who are dealing with these problems now and in the future, will benefit greatly from the text's discussion of these major issues.