DMCA
Efficient Shared Memory Multiprocessing and Object-Oriented Programming (1996)
| Citations: | 3 - 3 self |
BibTeX
@MISC{Machanick96efficientshared,
author = {Philip Machanick},
title = {Efficient Shared Memory Multiprocessing and Object-Oriented Programming},
year = {1996}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Object-oriented techniques are shown to hold promise for addressing the growing speed gap between memory and processors on shared-memory multiprocessors. However, reducing cache misses can be at the expense of more misses from the translation lookaside buffer (TLB---a cache of recent page translations). This paper presents simulation results from use of a library called OOSH (Object-Oriented Library for Shared Memory), in which cache behaviour is measured. Even for a well-optimized application, the library improves speedup by over 20% on 32 processors. On the other hand, timing on a real machine shows that the TLB problem can impact performance by as much as 25%. 1. Introduction Shared-memory multiprocessors based on commodity microprocessors are becoming the an increasingly widely accepted architecture for large-scale computation. However, rapid improvement in processor speed is not being matched by improvement in memory speed. This paper illustrates how an object-oriented approach c...
Keyphrases
object-oriented programming efficient shared memory multiprocessing speed gap introduction shared-memory multiprocessor shared memory processor speed library improves tlb problem memory speed accepted architecture real machine cache behaviour rapid improvement recent page translation object-oriented library well-optimized application object-oriented technique simulation result translation lookaside buffer shared-memory multiprocessor commodity microprocessor cache miss large-scale computation object-oriented approach
