Ah, yes, didn't take into account multiple platform support at all. Practically ATI is the only one with mature OpenCL drivers at the moment (at least from my testing).
This is expected to improve, though.
Thanks for the info on what you've found to be the current issues.
Search found 14 matches
- Thu Sep 29, 2011 3:49 pm
- Forum: Improvements, new features
- Topic: GPU assisted possible / useful?
- Replies: 52
- Views: 61333
- Thu Sep 29, 2011 2:07 pm
- Forum: Improvements, new features
- Topic: GPU assisted possible / useful?
- Replies: 52
- Views: 61333
- Thu Sep 29, 2011 1:55 pm
- Forum: Improvements, new features
- Topic: GPU assisted possible / useful?
- Replies: 52
- Views: 61333
Implementing support for a new GPU platform is not easy and certainly not fast. Please be patient. Really? I find porting CUDA to OpenCL quite trivial... Are you using some CUDA exclusive features extensively which make this difficult? I realize, due to some options available for CUDA memory handli...
- Wed Feb 04, 2009 10:04 am
- Forum: Improvements, new features
- Topic: GPU assisted possible / useful?
- Replies: 52
- Views: 61333
That's not possible; wrapper won't help, a plugin rewrite is required to take advantage of GPUs. (technically, it would be possible to write an emulation layer which would translate CPU instructions to GPU instructions, but that would only make things slower) Also, I wouldn't promote GPU acceleratio...
- Fri Feb 08, 2008 10:24 am
- Forum: Improvements, new features
- Topic: Particle Swarm Optimization
- Replies: 2
- Views: 7367
- Thu Feb 07, 2008 1:37 pm
- Forum: Improvements, new features
- Topic: Particle Swarm Optimization
- Replies: 2
- Views: 7367
Particle Swarm Optimization
Just wondering, if you have ever looked into the subject matter? (I've always been interested in different optimization algorithms and their uses) Recent developments: http://www.eurekalert.org/pub_releases/2008-02/ip-sat020108.php Edit: As there was not a "general discussion" forum separa...
- Sat Sep 22, 2007 8:54 am
- Forum: Improvements, new features
- Topic: Keyboard support in select frame for vdub filter
- Replies: 2
- Views: 7177
Thank you for the reply. I've had a long session of editing and was forced to seek some solutions to this (got a bit too frustrated about the clickety-click slowness). Found out that some other filters, which have a similar preview window, allow keyboard navigation, so at least we know it is doable ...
- Sat Sep 22, 2007 3:56 am
- Forum: Improvements, new features
- Topic: Keyboard support in select frame for vdub filter
- Replies: 2
- Views: 7177
Keyboard support in select frame for vdub filter
Hi, One suggestion - please enable keyboard navigation with 'select a frame for analysis' as it is with vdub (i.e. arrows & modifiers, like Alt for 50 frames at a time etc). It is a painful process clicking with a mouse one frame at a time, especially on a long video file to get to a desired pos...
- Fri Apr 20, 2007 2:01 pm
- Forum: Improvements, new features
- Topic: Define frame range for autoprofiling
- Replies: 1
- Views: 7099
Define frame range for autoprofiling
Hi, First of all, thanks for 2.0 - seems excellent (running now for first analogue capture, ab 12h left still). I would've wished there would've been one particular improvement: define frames for autoprofiling candidate. Many times, we have a flat surface available for example for 20 frames but the ...
- Fri Apr 13, 2007 6:33 pm
- Forum: Improvements, new features
- Topic: VIDEO SPECTRAL Analyze and Joseph FOURIER Method
- Replies: 2
- Views: 8560
Probably because recognizing noise in spectral view for audio is _quite_ different than in video? There's a reason why it is very useful for audio (I've used audition and tried it - very useful). FFT methods are very useful to remove noise in video too. There are some pretty impressive noise filters...
- Mon Apr 02, 2007 10:02 am
- Forum: Improvements, new features
- Topic: VideoEnhancer support
- Replies: 2
- Views: 8150
Thank you for your reply! I also got a reply from VideoEnhancer people, and they suspect the problem is that VideoEnhancer has not implemented frameserving yet. I agree, that would render NeatVideo configuration quite impossible. :) They're planning to implement frameserving during April/May, so mig...
- Sun Apr 01, 2007 3:02 pm
- Forum: Improvements, new features
- Topic: VideoEnhancer support
- Replies: 2
- Views: 8150
VideoEnhancer support
Hi, Tried to use NeatVideo in VideoEnhancer (http://www.thedeemon.com/VideoEnhancer) as it implements MSU Super Video Resolution (http://www.compression.ru/video/super_resolution/super_resolution_en.html) but unfortunately the VDub plugin version was not working so well (not possible to configure, a...
- Thu Oct 26, 2006 5:07 pm
- Forum: General questions
- Topic: Any chance for a native Avisynth version of Neatvideo?
- Replies: 11
- Views: 21236
Hi, I would also like to add my vote for native AviSynth version of the plugin. Less the colorspace conversions the better and many avisynth plugins require yv12/yuy2 for processing, often resulting in the script of the form: some processing->convertorgb->neatvideo->convertoyv12/yuy2->more processin...
- Fri Oct 13, 2006 7:31 am
- Forum: Improvements, new features
- Topic: GPU assisted possible / useful?
- Replies: 52
- Views: 61333
GPU assisted possible / useful?
Hi, Loving neatvideo, as it made my analogue captures so much easier (used to all filtering in avisynth with plugins, but the need for constant tweaking drove me nuts as I wasn't very good at it :wink:). However, speed improvements would be nice. (filtering 1:40h video at full res takes a day with m...