Deconvolution CPU usage

peter_4059

Member
May 20, 2012
8
1
I've recently purchased a new PC for PI image processing. During use I noticed the Deconvolution process does not appear to take advantage of the multicore/thread Ryzen 9 processor and in fact seems to just use one thread at 100%. Is that what other people have observed or is there a setting I need to change somewhere?

Thanks

Peter
 

Juan Conejero

PTeam Member
Sep 2, 2004
7,402
67
56
Valencia, Spain
pixinsight.com
Hi Peter,

The Richardson-Lucy and Van-Cittert deconvolution algorithms, being iterative deconvolution algorithms, cannot be parallelized at a high level. Basically, the problem is that each deconvolution iteration depends on all previous iterations. Wavelet transforms, which are used for deconvolution regularization and deringing, cannot be parallelized for the same reason: each wavelet layer depends on all previous layers.

Basically, the only operations that are efficiently parallelized in this process are convolutions and arithmetic operations. However, since parallelization cannot work continually during most of the process, it cannot provide high performance benefits. A GPU-based implementation of convolutions will provide significant performance improvements in a new version of PixInsight to be released after the incoming 1.8.8-6 version (probably 1.8.9, hopefully before the end of this year), but nothing really spectacular in this particular case.
 

peter_4059

Member
May 20, 2012
8
1
Juan,

Thanks for the response. I was wondering if it was a limitation of the deconvolution process as I was seeing all threads being utilised in the benchmark test.

Peter