Title :
Parallel implementation of Aggressive PNN method for devices with GPUs
Author :
Wakatani, Akiyoshi ; Murakami, Akira
Author_Institution :
Konan Univ., Konan, Japan
Abstract :
We implement the Aggressive PNN method on GPUs by using CUDA to generate codebooks for VQ compression and the speedup of up to 4.01 is achieved compared with the tau PNN method on the CPU. Our second method enhances the parallelism by using indirect vectors to reduce idle threads. We also improved the algorithm by about 20% by using indirect vectors.
Keywords :
data compression; graphics processing units; parallel architectures; vector quantisation; CUDA; GPU; VQ compression; aggressive PNN method; codebook generation; graphic processing unit; indirect vectors; pairwise nearest neighbor method; vector quantization compression; Algorithm design and analysis; Graphics processing units; Image coding; Instruction sets; Parallel processing; Signal processing algorithms; Vectors;
Conference_Titel :
Consumer Electronics (ICCE), 2013 IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4673-1361-2
DOI :
10.1109/ICCE.2013.6487002
