The case for a multiprocessor on a Die: MoaD

dc.contributor.author	Machanick, P
dc.contributor.editor	Renaud, K.
dc.contributor.editor	Kotze, P
dc.contributor.editor	Barnard, A
dc.date.accessioned	2018-08-23T10:18:31Z
dc.date.available	2018-08-23T10:18:31Z
dc.date.issued	2001
dc.identifier.citation	Machanick, P. (2001) The case for a multiprocessor on a Die: MoaD. Hardware, Software and Peopleware: Proceedings of the Annual Conference of the South African Institute of Computer Scientists and Information Technologists, University of South Africa, Pretoria, 25-28 September 2001	en
dc.identifier.isbn	1-86888-195-4
dc.identifier.uri	http://hdl.handle.net/10500/24764
dc.description.abstract	Increasingly aggressive pipelining achieves diminishing returns. Simultaneous Multi-threading (SMT) attempts to exploit the fact that functional units are frequently idle. This paper argues the case for keeping the processor simple, while looking for parallelism elsewhere, if it is too hard to find at the instruction level. In particular, it makes the case for a less aggressive superscalar implementation, and using the die space instead for a multiprocessor on a die (MoaD), with the same theoretical peak execution rate. It is proposed that this change in design focus is more in line with characteristics of consumer applications than current design trends.	en
dc.language.iso	en	en
dc.title	The case for a multiprocessor on a Die: MoaD	en