Sciweavers

1914 search results - page 9 / 383
» Using Execution Trace Data to Improve Distributed Systems
Sort
View
CLUSTER
2011
IEEE
13 years 9 months ago
Exploring Fine-Grained Task-Based Execution on Multi-GPU Systems
Using multi-GPU systems, including GPU clusters, is gaining popularity in scientific computing. However, when using multiple GPUs concurrently, the conventional data parallel GPU...
Long Chen, Oreste Villa, Guang R. Gao
PPOPP
2003
ACM
15 years 2 months ago
Compactly representing parallel program executions
Collecting a program’s execution profile is important for many reasons: code optimization, memory layout, program debugging and program comprehension. Path based execution pro...
Ankit Goel, Abhik Roychoudhury, Tulika Mitra
ICPP
2007
IEEE
15 years 4 months ago
Improving Search Using a Fault-Tolerant Overlay in Unstructured P2P Systems
Gnutella overlays have evolved to use a two-tier topology. However, we observed that the new topology had only achieved modest improvements in search success rates. Also, the new ...
William Acosta, Surendar Chandra
IJCAI
2003
14 years 11 months ago
ODISET: On-line Distributed Session Tracing using Agents
When a security incident occurs it is sometimes necessary to identify its causes for legal and cautionary purposes. In an attempt to hide the origin of her connection, a malicious...
Salvador Mandujano, Arturo Galván
ISPA
2004
Springer
15 years 3 months ago
HPL Performance Prevision to Intending System Improvement
HPL is a parallel Linpack benchmark package widely adopted in massive cluster system performance test. On HPL data layout among processors, a law to determine block size NB theoret...
Wenli Zhang, Mingyu Chen, Jianping Fan