Sciweavers

4 search results - page 1 / 1
» InvisiFence: performance-transparent memory ordering in conv...
Sort
View
ISCA
2009
IEEE
123views Hardware» more  ISCA 2009»
13 years 11 months ago
InvisiFence: performance-transparent memory ordering in conventional multiprocessors
Colin Blundell, Milo M. K. Martin, Thomas F. Wenis...
CAL
2010
13 years 1 months ago
SMT-Directory: Efficient Load-Load Ordering for SMT
Memory models like SC, TSO, and PC enforce load-load ordering, requiring that loads from any single thread appear to occur in program order to all other threads. Out-of-order execu...
A. Hilton, A. Roth
ISCA
2007
IEEE
145views Hardware» more  ISCA 2007»
13 years 11 months ago
Mechanisms for store-wait-free multiprocessors
Store misses cause significant delays in shared-memory multiprocessors because of limited store buffering and ordering constraints required for proper synchronization. Today, prog...
Thomas F. Wenisch, Anastassia Ailamaki, Babak Fals...
CF
2009
ACM
13 years 11 months ago
A light-weight fairness mechanism for chip multiprocessor memory systems
Chip Multiprocessor (CMP) memory systems suffer from the effects of destructive thread interference. This interference reduces performance predictability because it depends heavil...
Magnus Jahre, Lasse Natvig