Sciweavers

1933 search results - page 126 / 387
» High-performance computing using accelerators
Sort
View
OOPSLA
2010
Springer
13 years 8 months ago
Hera-JVM: a runtime system for heterogeneous multi-core architectures
Heterogeneous multi-core processors, such as the IBM Cell processor, can deliver high performance. However, these processors are notoriously difficult to program: different cores...
Ross McIlroy, Joe Sventek
SAC
2009
ACM
14 years 4 months ago
Bulk based preconditioning for quantum dot computations
Abstract— This article describes how to accelerate the convergence of Preconditioned Conjugate Gradient (PCG) type eigensolvers for the computation of several states around the b...
Christof Vömel, Stanimire Tomov, Osni Marques
CF
2009
ACM
14 years 4 months ago
Towards automatic program partitioning
There is a trend towards using accelerators to increase performance and energy efficiency of general-purpose processors. Adoption of accelerators, however, depends on the availabi...
Sean Rul, Hans Vandierendonck, Koen De Bosschere
IJCNN
2000
IEEE
14 years 1 months ago
A Training Method with Small Computation for Classification
A training data selection method for multi-class data is proposed. This method can be used for multilayer neural networks (MLNN). The MLNN can be applied to pattern classification...
Kazuyuki Hara, Kenji Nakayama
JCP
2007
98views more  JCP 2007»
13 years 10 months ago
Computation of Immittance and Line Spectral Frequencies Based on Inter-frame Ordering Property
— Line spectral frequencies (LSF) and immittance spectral frequencies (ISF) are widely used in modern speech codecs based on autoregressive model. This paper addresses LSF and IS...
Vasyl Semenov