Parallel codebook design for vector quantization on a message passing MIMD architecture

  title={Parallel codebook design for vector quantization on a message passing MIMD architecture},
  author={Hazem M. Abbas and Mohamed M. Bayoumi},
  journal={Parallel Computing},
Vector quantization (VQ) is a widely used algorithm in speech and image data compression. One of the problems of the VQ methodology is that it requires large computation time especially for large codebook size. This paper addresses two issues. The first deals with the parallel construction of the VQ codebook which can drastically reduce the training time. A master/worker parallel implementation of a VQ algorithm is proposed. The algorithm is executed on the DM-MIMD Alex AVX-2 machine using a… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 23 references

The performance of the parallel backpropagation feedforward networks on an MIMD architecture , Concurr

  • M. Bayoumi H. Abbas
  • Ex . Pract .
  • 1998

On the implementation of backpropagation on the Alex AVX–2 parallel system

  • H. Abbas, M. Bayoumi
  • in: IEEE International Conference on Neural…
  • 1997
1 Excerpt

A massively parallel algorithm for vector quantization

  • K. S. Prashant, V. J. Mathews
  • in: Proceedings of the 1995 NASA Space and Earth…
  • 1995
2 Excerpts

Comparison of parallel and serial implementation of feedforward neural networks

  • S. King, P. Saratchandran, N. Sundararajan
  • J. Microcomput. Appl. 17
  • 1995
1 Excerpt

Similar Papers

Loading similar papers…