Title | ||
---|---|---|
Optimization and Analysis of Parallel Back Propagation Neural Network on GPU Using CUDA. |
Abstract | ||
---|---|---|
Graphic Processing Unit (GPU) can achieve remarkable performance for dataset-oriented application such as Back Propagation Network (BPN) under reasonable task decomposition and memory optimization. However, advantages of GPU's memory architecture are still not fully exploited to parallel BPN. In this paper, we develop and analyze a parallel implementation of a back propagation neural network using CUDA. It focuses on kernels optimization through the use of shared memory and suitable blocks dimensions. The implementation was tested with seven well-known benchmark data sets and the results show promising 33.8x to 64.3x speedups can be realized compared to a sequential implementation on a CPU. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/978-3-319-26555-1_18 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Back propagation,GPU,Network density,Producer-consumer locality,Bank conflict | Data set,Shared memory,Computer science,CUDA,Parallel computing,Back propagation neural network,Network density,Computational science,Backpropagation,Memory architecture | Conference |
Volume | ISSN | Citations |
9491 | 0302-9743 | 1 |
PageRank | References | Authors |
0.37 | 11 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yaobin Wang | 1 | 31 | 5.77 |
Pingping Tang | 2 | 1 | 0.37 |
Hong An | 3 | 1 | 1.73 |
Zhi-qin Liu | 4 | 12 | 4.93 |
Kun Wang | 5 | 1 | 0.37 |
Yong Zhou | 6 | 1 | 0.71 |