On the Scalability of 2-D Discrete Wavelet Transform Algorithms

Fridman, J.; Μανωλάκος, Ηλίας Σ.

doi:10.1007/978-1-4757-5922-8_8

Cited by 11 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A significant amount of work has been done for MIMD parallelization [12,20,8] and old SIMD arrays [15,1,7]. The use of SIMD extensions of modern general purpose processors for wavelet transforms is investigated in [19,2] together with extensive cache optimizations.…”

Section: Introductionmentioning

confidence: 99%

A single-loop approach to SIMD parallelization of 2D wavelet lifting

Kutil

2006

14th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP'06)

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

A single-loop approach to SIMD parallelization of 2D wavelet lifting

Kutil

2006

14th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP'06)

View full text Add to dashboard Cite

show abstract

“…For parallelizing the 2D a`trous algorithm we choose the Stripped-partitioning scheme because it has been shown to be the most suitable one for implementations using the message passing paradigm (see [26] for a corresponding investigation for the FWT -the alternative Checkerboard-partitioning, scheme requires a higher amount of smaller messages to be sent).…”

Section: Message Passing Paradigmmentioning

confidence: 99%

Real-Time Image Analysis Using MIMD Parallel à trous Wavelet Algorithms

Feil

Uhl

2001

Real-Time Imaging

View full text Add to dashboard Cite

“…A significant amount of work has been done for MIMD parallelization [2,3,4] and old SIMD arrays [5,6,7]. The use of SIMD extensions of modern general purpose processors for wavelet transforms is investigated for the 2-D case in [8,9].…”

Section: Introductionmentioning

confidence: 99%

Parallelization of Wavelet Filters Using Simd Extensions

Kutil

Eder

2006

Parallel Process. Lett.

View full text Add to dashboard Cite

Much work has been done to optimize wavelet transforms for SIMD extensions of modern CPUs. However, these approaches are mostly restricted to the vertical part of 2-D transforms with line-wise organized memory layouts because this leads to a rather straight forward SIMD-implementation. This work shows for an example of a common wavelet filter new approaches to use SIMD operations on 1-D transforms that are able to produce reasonable speedups. As a result, the performance of algorithms that use wavelet transforms, such as JPEG2000, can be increased significantly. Various variants of parallelization are presented and compared. Their advantages and disadvantages for general filters are discussed.

show abstract

On the Scalability of 2-D Discrete Wavelet Transform Algorithms

Cited by 11 publications

References 13 publications

A single-loop approach to SIMD parallelization of 2D wavelet lifting

A single-loop approach to SIMD parallelization of 2D wavelet lifting

Real-Time Image Analysis Using MIMD Parallel à trous Wavelet Algorithms

Parallelization of Wavelet Filters Using Simd Extensions

Contact Info

Product

Resources

About