Abstract
A new efficient parallel wavelet algorithm was presented in order to speed up wavelet transform in three-dimensional surface texture analysis. It is based NVIDIA's CUDA (Compute Unified Device Architecture), a new general purpose parallel programming model and instruction set architecture that leverage computational problems on GPU more efficient than CPU. Compared with CPU, GPU has evolved into a highly parallel, multithread, multicore processor with tremendous computational horsepower and very high memory bandwidth. GPU is well-suited to address data-parallel computation problems rather than flow controlled problems. Wavelet transform can use data-parallel programming model so data elements will be mapped to parallel processing threads to speed up the computations. CUDA wavelet decomposition and reconstruction algorithms were realized based on the analysis above. Experiments show that the parallelization of the fast wavelet decomposition transform for GPU speedup 34x38x over CPU, reconstruction transform speedup 29x33x over CPU.
Original language | English |
---|---|
Title of host publication | 2011 International Conference on Electric Information and Control Engineering |
Publisher | IEEE |
Pages | 2249-2252 |
Number of pages | 4 |
ISBN (Electronic) | 9781424480395, 9781424480388 |
ISBN (Print) | 9781424480364 |
DOIs | |
Publication status | Published - 7 Jul 2011 |
Event | 2011 International Conference on Electric Information and Control Engineering - Wuhan, China Duration: 15 Apr 2011 → 17 Apr 2011 http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=10179©ownerid=12479 |
Conference
Conference | 2011 International Conference on Electric Information and Control Engineering |
---|---|
Abbreviated title | ICEICE 2011 |
Country/Territory | China |
City | Wuhan |
Period | 15/04/11 → 17/04/11 |
Internet address |