Sciweavers

Share
IPPS
2010
IEEE
8 years 8 months ago
Improving MapReduce performance through data placement in heterogeneous Hadoop clusters
MapReduce has become an important distributed processing model for large-scale data-intensive applications like data mining and web indexing. Hadoop
Jiong Xie, Shu Yin, Xiaojun Ruan, Zhiyang Ding, Yu...
NPC
2010
Springer
8 years 8 months ago
Exposing Tunable Parameters in Multi-threaded Numerical Code
Achieving high performance on today’s architectures requires careful orchestration of many optimization parameters. In particular, the presence of shared-caches on multicore arch...
Apan Qasem, Jichi Guo, Faizur Rahman, Qing Yi
JISE
2002
165views more  JISE 2002»
8 years 10 months ago
Locality-Preserving Dynamic Load Balancing for Data-Parallel Applications on Distributed-Memory Multiprocessors
Load balancing and data locality are the two most important factors in the performance of parallel programs on distributed-memory multiprocessors. A good balancing scheme should e...
Pangfeng Liu, Jan-Jan Wu, Chih-Hsuae Yang
CODES
2001
IEEE
9 years 2 months ago
Compiler-directed selection of dynamic memory layouts
Compiler technology is becoming a key component in the design of embedded systems, mostly due to increasing participation of software in the design process. Meeting system-level ob...
Mahmut T. Kandemir, Ismail Kadayif
CIKM
2009
Springer
9 years 2 months ago
Scalable indexing of RDF graphs for efficient join processing
Current approaches to RDF graph indexing suffer from weak data locality, i.e., information regarding a piece of data appears in multiple locations, spanning multiple data structur...
George H. L. Fletcher, Peter W. Beck
ICS
1992
Tsinghua U.
9 years 2 months ago
Optimizing for parallelism and data locality
Previous research has used program transformation to introduce parallelism and to exploit data locality. Unfortunately,these twoobjectives have usuallybeen considered independentl...
Ken Kennedy, Kathryn S. McKinley
LCPC
1993
Springer
9 years 2 months ago
Maximizing Loop Parallelism and Improving Data Locality via Loop Fusion and Distribution
Abstract. Loop fusion is a program transformation that merges multiple loops into one. It is e ective for reducing the synchronization overhead of parallel loops and for improving ...
Ken Kennedy, Kathryn S. McKinley
ASPLOS
1994
ACM
9 years 2 months ago
Compiler Optimizations for Improving Data Locality
In the past decade, processor speed has become significantly faster than memory speed. Small, fast cache memories are designed to overcome this discrepancy, but they are only effe...
Steve Carr, Kathryn S. McKinley, Chau-Wen Tseng
ICPP
1996
IEEE
9 years 2 months ago
Polynomial-Time Nested Loop Fusion with Full Parallelism
Data locality and synchronization overhead are two important factors that affect the performance of applications on multiprocessors. Loop fusion is an effective way for reducing s...
Edwin Hsing-Mean Sha, Chenhua Lang, Nelson L. Pass...
ICCS
2004
Springer
9 years 3 months ago
Improving Geographical Locality of Data for Shared Memory Implementations of PDE Solvers
On cc-NUMA multi-processors, the non-uniformity of main memory latencies motivates the need for co-location of threads and data. We call this special form of data locality, geogra...
Henrik Löf, Markus Nordén, Sverker Hol...
books