Jump to content

Killer micro

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 128.2.134.157 (talk) at 23:28, 24 April 2013 (The Eugene Brooks cited died in 1947 so he could not have given a talk at Supercomputing 1990. Remove citation to wrong Eugene Brooks.). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

A killer micro is a microprocessor-based machine that infringes on mini, mainframe, or supercomputer performance turf. It originally referred to the replacement of vector supercomputers built with bipolar technology by Massively Parallel Processors (MPP) assembled from a larger number of lower performing microprocessors. These systems faced initial skepticism, based on the assumption that applications do not have significant parallelism, because of Amdahl's law, but the success of early systems such as nCUBE and the fast progress in microprocessor performance following Moore's law led to a fast replacement.

Taken from the title of Eugene Brooks' (of Lawrence Livermore Labs) talk "Attack of the Killer Micros" at Supercomputing 1990. This title was probably chosen after the Attack of the Killer Tomatoes cult film.

References

This article is based on material taken from the Free On-line Dictionary of Computing prior to 1 November 2008 and incorporated under the "relicensing" terms of the GFDL, version 1.3 or later.