Sciweavers

1296 search results - page 55 / 260
» Exploiting communication concurrency on high performance com...
Sort
View
HPCA
2011
IEEE
14 years 7 months ago
Dynamic parallelization of JavaScript applications using an ultra-lightweight speculation mechanism
As the web becomes the platform of choice for execution of more complex applications, a growing portion of computation is handed off by developers to the client side to reduce net...
Mojtaba Mehrara, Po-Chun Hsu, Mehrzad Samadi, Scot...
CF
2006
ACM
15 years 9 months ago
Exploiting locality to ameliorate packet queue contention and serialization
Packet processing systems maintain high throughput despite relatively high memory latencies by exploiting the coarse-grained parallelism available between packets. In particular, ...
Sailesh Kumar, John Maschmeyer, Patrick Crowley
CCGRID
2007
IEEE
15 years 10 months ago
Exploiting Lustre File Joining for Effective Collective IO
Lustre is a parallel file system that presents high aggregated IO bandwidth by striping file extents across many storage devices. However, our experiments indicate excessively wid...
Weikuan Yu, Jeffrey S. Vetter, Shane Canon, Song J...
IPPS
1999
IEEE
15 years 8 months ago
Implementation of a Virtual Time Synchronizer for Distributed Databases
The availability of high speed networks and improved microprocessor performance have made it possible to build inexpensive cluster of workstations as an appealing platform for par...
Azzedine Boukerche, Sajal K. Das, Ajoy Kumar Datta...
SAMOS
2004
Springer
15 years 9 months ago
A Low-Power Multithreaded Processor for Baseband Communication Systems
Embedded digital signal processors for baseband communication systems have stringent design constraints including high computational bandwidth, low power consumption, and low inter...
Michael J. Schulte, C. John Glossner, Suman Mamidi...