Sciweavers

535 search results - page 45 / 107
» The Cache Performance and Optimizations of Blocked Algorithm...
Sort
View
CODES
2004
IEEE
15 years 3 months ago
Optimizing the memory bandwidth with loop fusion
The memory bandwidth largely determines the performance and energy cost of embedded systems. At the compiler level, several techniques improve the memory bandwidth at the scope of...
Paul Marchal, José Ignacio Gómez, Fr...
EUC
2004
Springer
15 years 5 months ago
On the Effects of Bandwidth Reduction Techniques in Distributed Applications
Communication optimization plays an important role in building networked distributed applications. In this paper, we systematically evaluate four bandwidth reduction algorithms, n...
Hanping Lufei, Weisong Shi, Lucia Zamorano
USENIX
1994
15 years 1 months ago
A Better Update Policy
y-filled data block results in a delayed write,Abstract while a modification that fills a block results in an immediate, although asynchronous, write. TheSome file systems can dela...
Jeffrey C. Mogul
ICIAP
2009
ACM
16 years 11 days ago
Connected Component Labeling Techniques on Modern Architectures
In this paper we present an overview of the historical evolution of connected component labeling algorithms, and in particular the ones applied on images stored in raster scan orde...
Costantino Grana, Daniele Borghesani, Rita Cucchia...
MICRO
2005
IEEE
125views Hardware» more  MICRO 2005»
15 years 5 months ago
Improving Region Selection in Dynamic Optimization Systems
The performance of a dynamic optimization system depends heavily on the code it selects to optimize. Many current systems follow the design of HP Dynamo and select a single interp...
David Hiniker, Kim M. Hazelwood, Michael D. Smith