Jump to content

Processor-in-memory

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by Sam Korn (talk | contribs) at 16:50, 1 June 2005 ('bandwith' -> 'bandwidth'; -- Join and fix more! & stub notic). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

A Processor-in-memory refers to a computer processor tightly coupled to memory, generally on the same silicon chip. Notable PIM projects include the UC Berkeley IRAM or Notre Dame PIM efforts.

The chief goal of merging the processing and memory components in this way is to reduce memory latency and increase bandwidth.