Description
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; technical difficulties and policy issues are closely linked. This text clarifies a number of technical points and policy directions in proposing steps toward practical processing. Computing as a whole is at a crossroads because hardware technology appears unable to provide continuing speed increases; parallel architectures and software are not sufficiently developed to provide the practical solutions that have seemed tantalizingly close for some time. After more than a decade of commercial development, no standard or widely accepted systems have emerged. This text defines practical parallelism tests and suggests how they can be passed, by giving specific technical suggestions and by outlining policy steps that should be taken. Students in high performance computing courses will benefit from the text's discussion of these major issues, as they will be dealing with these problems now and in the future.
