E. Brooks. The attack of the killer micros. In Teraflop Computing Panel, Supercomputing '89, Reno, Nevada, 1989. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Vector Microprocessors - Asanovic (1998) (17 citations) (Correct)
....on some tasks and at much lower costs. Modern microprocessors have superscalar architectures which appear more flexible than the vector model and so many now believe that vector machines are a dying breed, being pushed aside by the astonishingly rapid evolution of these killer micros [Bro89] But the improved cost performance of microprocessor based systems is due primarily to their use of commodity silicon CMOS fabrication technology. What if we implement vector architectures using the same technology In this thesis, I argue that the resulting vector microprocessors may actually ....
E. Brooks. The attack of the killer micros. In Teraflop Computing Panel, Supercomputing '89, Reno, Nevada, 1989.
Polling Watchdog: Combining Polling and Interrupts for Efficient .. - Maquelin (1996) (33 citations) (Correct)
....with credit is permitted. To copy otherwise, to republish, to post on servers, or to redistribute to lists, requires prior specific permission and or a fee. Request permissions from Publications Dept. ACM Inc. fax 1 (212) 869 0481, or (permissions acm.org) compete with killer micros [3], especially given the relatively small size of the market for supercomputing. If parallel architects have to give in and use off the shelf microprocessors, then it is important to study how best to take advantage of their capabilities. Considerable gains in communication performance can be ....
Eugene Brooks, "The attack of the killer micros." Presentation in the Teraflop Computing Panel Discussion at Supercomputing '89, Reno, Nev., Nov. 1989.
Polling Watchdog: Combining Polling and Interrupts for.. - Maquelin, al. (1995) (33 citations) (Correct)
....by mass markets, they are mostly optimized for use in personal computers and workstations, and offer only limited support for interprocessor communication. Nevertheless, the high development costs of current hardware makes it virtually impossible for custom hardware to compete with killer micros [2], especially given the relatively small size of the market for supercomputing. If parallel architects have to give in and use off the shelf microprocessors, then it is important to study how best to take advantage of their capabilities. Considerable gains in communication performance can be ....
Eugene Brooks, "The attack of the killer micros." Presentation in the Teraflop Computing Panel Discussion at Supercomputing '89, Reno, Nevada, November 1989.
Multithreaded Architectures: Principles, Projects and Issues - Dennis, Gao (1994) (4 citations) (Correct)
....lies at the heart of these developments. It is the engine of workstations and servers in distributed systems, and it has become the key component of today s massively parallel computers for high performance scientific applications. These are the killer micros foreseen by Eugene Brooks [26]. The economics of computer technology ensures that the processor on a chip will continue to be the cost effective basis for high performance computer design. Soon it will be possible to place several complete processing elements on a single chip having several million transistors. Today the most ....
E. Brooks, "The attack of the killer micros." Presentation in the Teraflop Computing Panel Discussion at Supercomputing '89, Reno, Nevada, November 1989.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC