Sciweavers

257 search results - page 17 / 52
» MPI on a Million Processors
Sort
View
IPPS
2006
IEEE
14 years 1 months ago
Topology-aware task mapping for reducing communication contention on large parallel machines
Communication latencies constitute a significant factor in the performance of parallel applications. With techniques such as wormhole routing, the variation in no-load latencies ...
T. Agarwal, Amit Sharma, A. Laxmikant, Laxmikant V...
ICML
2009
IEEE
14 years 8 months ago
Large-scale deep unsupervised learning using graphics processors
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
Rajat Raina, Anand Madhavan, Andrew Y. Ng
SIAMCOMP
2010
109views more  SIAMCOMP 2010»
13 years 2 months ago
Analysis of Delays Caused by Local Synchronization
Synchronization is often necessary in parallel computing, but it can create delays whenever the receiving processor is idle, waiting for the information to arrive. This is especia...
Julia Lipman, Quentin F. Stout
IPPS
2010
IEEE
13 years 5 months ago
Oversubscription on multicore processors
Abstract: Existing multicore systems already provide deep levels of thread parallelism. Hybrid programming models and composability of parallel libraries are very active areas of r...
Costin Iancu, Steven Hofmeyr, Filip Blagojevic, Yi...
IPPS
2007
IEEE
14 years 1 months ago
A Fault Tolerance Protocol with Fast Fault Recovery
Fault tolerance is an important issue for large machines with tens or hundreds of thousands of processors. Checkpoint-based methods, currently used on most machines, rollback all ...
Sayantan Chakravorty, Laxmikant V. Kalé