Sciweavers

510 search results - page 83 / 102
» Online Performance Observation of Large-Scale Parallel Appli...
Sort
View
PDP
2009
IEEE
14 years 3 months ago
High Throughput Intra-Node MPI Communication with Open-MX
Abstract—The increasing number of cores per node in highperformance computing requires an efficient intra-node MPI communication subsystem. Most existing MPI implementations rel...
Brice Goglin
IPPS
2006
IEEE
14 years 2 months ago
Enhancing L2 organization for CMPs with a center cell
Chip multiprocessors (CMPs) are becoming a popular way of exploiting ever-increasing number of on-chip transistors. At the same time, the location of data on the chip can play a c...
Chun Liu, Anand Sivasubramaniam, Mahmut T. Kandemi...
CLUSTER
2007
IEEE
14 years 2 months ago
Satisfying your dependencies with SuperMatrix
— SuperMatrix out-of-order scheduling leverages el abstractions and straightforward data dependency analysis to provide a general-purpose mechanism for obtaining parallelism from...
Ernie Chan, Field G. Van Zee, Enrique S. Quintana-...
WWW
2010
ACM
14 years 3 months ago
Find me if you can: improving geographical prediction with social and spatial proximity
Geography and social relationships are inextricably intertwined; the people we interact with on a daily basis almost always live near us. As people spend more time online, data re...
Lars Backstrom, Eric Sun, Cameron Marlow
VLDB
2004
ACM
178views Database» more  VLDB 2004»
14 years 1 months ago
High-Dimensional OLAP: A Minimal Cubing Approach
Data cube has been playing an essential role in fast OLAP (online analytical processing) in many multi-dimensional data warehouses. However, there exist data sets in applications ...
Xiaolei Li, Jiawei Han, Hector Gonzalez