Sciweavers

1263 search results - page 215 / 253
» Performance of the IBM General Parallel File System
Sort
View
PODC
2006
ACM
15 years 3 months ago
Grouped distributed queues: distributed queue, proportional share multiprocessor scheduling
We present Grouped Distributed Queues (GDQ), the first proportional share scheduler for multiprocessor systems that scales well with a large number of processors and processes. G...
Bogdan Caprita, Jason Nieh, Clifford Stein
HPDC
2007
IEEE
15 years 1 months ago
MOB: zero-configuration high-throughput multicasting for grid applications
Grid applications often need to distribute large amounts of data efficiently from one cluster to multiple others (multicast). Existing methods usually arrange nodes in optimized t...
Mathijs den Burger, Thilo Kielmann
IEEEPACT
2006
IEEE
15 years 3 months ago
Communist, utilitarian, and capitalist cache policies on CMPs: caches as a shared resource
As chip multiprocessors (CMPs) become increasingly mainstream, architects have likewise become more interested in how best to share a cache hierarchy among multiple simultaneous t...
Lisa R. Hsu, Steven K. Reinhardt, Ravishankar R. I...
ASPLOS
2010
ACM
15 years 4 months ago
COMPASS: a programmable data prefetcher using idle GPU shaders
A traditional fixed-function graphics accelerator has evolved into a programmable general-purpose graphics processing unit over the last few years. These powerful computing cores...
Dong Hyuk Woo, Hsien-Hsin S. Lee
HPCA
2011
IEEE
14 years 1 months ago
HAQu: Hardware-accelerated queueing for fine-grained threading on a chip multiprocessor
Queues are commonly used in multithreaded programs for synchronization and communication. However, because software queues tend to be too expensive to support finegrained paralle...
Sanghoon Lee, Devesh Tiwari, Yan Solihin, James Tu...