Image Integration/Stacking Benchmark - Feature Request

LuxTerra

Active member
I personally find the existing benchmark script very useful for understanding various hardware choices. However, I think that a second, long duration image integration script would be a substantial improvement. Currently, I think the existing benchmark undersells the benefits of the 24/32/64c ThreadRipper and EYPCs on what is one of the most time consuming steps. Because of the required time to properly benchmark this aspect of the image processing workflow, I would suggest a separate script is better than integrating it into the existing benchmark.
 
Excellent suggestion. Actually, I have been wanting to implement a preprocessing benchmark (including calibration, registration and integration) for a long time, but have never found the time. I'll think about how we can do this as soon as possible.
 
Wow. Thanks for the quick reply!

That would be awesome. I would request, if you’re going to put in the work, that this is a proper benchmark of top end hardware (where the data has the biggest ROI) of existing and future CPUs. If the rumors are true, in the very near future we’ll have 96-128c CPUs and cache is already exploding with things like V-Cache. ServeTheHome ran a good opinion piece, based on their expertise and industry talk, that in the next couple of years we’re going to have CPUs with multi-GB caches.

Can’t wait to see what you come up with. Thanks again.
 
Back
Top