Sciweavers

2358 search results - page 104 / 472
» Revisiting communication performance models for computationa...
Sort
View
ICS
2009
Tsinghua U.
14 years 3 months ago
Performance modeling and automatic ghost zone optimization for iterative stencil loops on GPUs
Iterative stencil loops (ISLs) are used in many applications and tiling is a well-known technique to localize their computation. When ISLs are tiled across a parallel architecture...
Jiayuan Meng, Kevin Skadron
PDCN
2007
13 years 10 months ago
One-to-all personalized communication in torus networks
Given a multicomputer system of parallel processors connected in a torus network, the one-to-all personalized communication is to send from the root processor unique data to each ...
Weizhen Mao, Jie Chen, William A. Watson III
ISPD
2003
ACM
132views Hardware» more  ISPD 2003»
14 years 2 months ago
Architecture and synthesis for multi-cycle communication
For multi-gigahertz designs in nanometer technologies, data transfers on global interconnects take multiple clock cycles. In this paper, we propose a regular distributed register ...
Jason Cong, Yiping Fan, Xun Yang, Zhiru Zhang
IPPS
1998
IEEE
14 years 1 months ago
Hiding Communication Latency in Data Parallel Applications
Interprocessor communication times can be a significant fraction of the overall execution time required for data parallel applications. Large communication to computation ratios o...
Vivek Garg, David E. Schimmel
NN
2006
Springer
163views Neural Networks» more  NN 2006»
13 years 8 months ago
Machine learning approaches for estimation of prediction interval for the model output
A novel method for estimating prediction uncertainty using machine learning techniques is presented. Uncertainty is expressed in the form of the two quantiles (constituting the pr...
Durga L. Shrestha, Dimitri P. Solomatine