SPARCLE - AN EVOLUTIONARY PROCESSOR DESIGN FOR LARGE-SCALE MULTIPROCESSORS

被引:46
|
作者
AGARWAL, A
KUBIATOWICZ, J
KRANZ, D
LIM, BH
YEUNG, D
DSOUZA, G
PARKIN, M
机构
[1] MIT,COMP SCI LAB,545 TECHNOL SQ,CAMBRIDGE,MA 02139
[2] LSI LOG,SPARC SYST DIV,MILPITAS,CA
[3] LSI LOG,COREWARE GRP,MILPITAS,CA
[4] MIT,DEPT ELECT & COMP ENGN,CAMBRIDGE,MA 02139
[5] MIT,DEPT ELECT ENGN & COMP SCI,CAMBRIDGE,MA 02139
基金
美国国家科学基金会;
关键词
D O I
10.1109/40.216748
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Working jointly at MIT, LSI Logic, and Sun Microsystems, designers created the sparcle processing chip by evolving an existing RISC architecture toward a processor suited for large-scale multiprocessors. This chip supports three multiprocessor mechanisms: fast context switching, fast, user-level message handling, and fine-grain synchronization. The Sparcle effort demonstrates that RISC architectures coupled with a communications and memory management unit do not require major architectural changes to support multiprocessing efficiently.
引用
收藏
页码:48 / 61
页数:14
相关论文
共 50 条