NTRS - NASA Technical Reports Server

Back to Results
avoiding and tolerating latency in large-scale next-generation shared-memory multiprocessorsA scalable solution to the memory-latency problem is necessary to prevent the large latencies of synchronization and memory operations inherent in large-scale shared-memory multiprocessors from reducing high performance. We distinguish latency avoidance and latency tolerance. Latency is avoided when data is brought to nearby locales for future reference. Latency is tolerated when references are overlapped with other computation. Latency-avoiding locales include: processor registers, data caches used temporally, and nearby memory modules. Tolerating communication latency requires parallelism, allowing the overlap of communication and computation. Latency-tolerating techniques include: vector pipelining, data caches used spatially, prefetching in various forms, and multithreading in various forms. Relaxing the consistency model permits increased use of avoidance and tolerance techniques. Each model is a mapping from the program text to sets of partial orders on program operations; it is a convention about which temporal precedences among program operations are necessary. Information about temporal locality and parallelism constrains the use of avoidance and tolerance techniques. Suitable architectural primitives and compiler technology are required to exploit the increased freedom to reorder and overlap operations in relaxed models.
Document ID
Document Type
Conference Paper
Probst, David K.
(Concordia Univ. Montreal Quebec, Canada)
Date Acquired
September 6, 2013
Publication Date
January 1, 1993
Publication Information
Publication: New Mexico Univ., The Fifth NASA Symposium on VLSI Design
Subject Category
Funding Number(s)
Distribution Limits
Work of the US Gov. Public Use Permitted.

Related Records

IDRelationTitle19940016163Analytic PrimaryTwenty-Fourth Lunar and Planetary Science Conference. Part 3: N-Z