Sciweavers

91 search results - page 11 / 19
» Software-Assisted Cache Replacement Mechanisms for Embedded ...
Sort
View
SAMOS
2007
Springer
15 years 4 months ago
Online Prediction of Applications Cache Utility
— General purpose architectures are designed to offer average high performance regardless of the particular application that is being run. Performance and power inefficiencies a...
Miquel Moretó, Francisco J. Cazorla, Alex R...
SIGARCH
2008
97views more  SIGARCH 2008»
14 years 10 months ago
SP-NUCA: a cost effective dynamic non-uniform cache architecture
1 This paper presents a simple but effective method to reduce on-chip access latency and improve core isolation in CMP Non-Uniform Cache Architectures (NUCA). The paper introduces ...
Javier Merino, Valentin Puente, Pablo Prieto, Jos&...
NOCS
2007
IEEE
15 years 4 months ago
The Power of Priority: NoC Based Distributed Cache Coherency
The paper introduces Network-on-Chip (NoC) design methodology and low cost mechanisms for supporting efficient cache access and cache coherency in future high-performance Chip Mul...
Evgeny Bolotin, Zvika Guz, Israel Cidon, Ran Ginos...
ISLPED
2010
ACM
169views Hardware» more  ISLPED 2010»
14 years 10 months ago
TurboTag: lookup filtering to reduce coherence directory power
On-chip coherence directories of today's multi-core systems are not energy efficient. Coherence directories dissipate a significant fraction of their power on unnecessary loo...
Pejman Lotfi-Kamran, Michael Ferdman, Daniel Crisa...
CDES
2008
166views Hardware» more  CDES 2008»
14 years 12 months ago
Scalable Directory Organization for Tiled CMP Architectures
Although directory-based cache coherence protocols are the best choice when designing chip multiprocessor architectures (CMPs) with tens of processor cores on chip, the memory ove...
Alberto Ros, Manuel E. Acacio, José M. Garc...