DGDecNV and KNLMeans under Win10_x64
Re: DGDecNV and KNLMeans under Win10_x64
I dont use QTGMC so I dont understand why it is so important to say dont use r1825 in general. I am using hw deint via VP6. I dont see such slowdown between r1576 and r1825. Did you find anyone else who has confirmed general slowdown?
I cannot find recommendation for r1825. So maybe I was not remembered well. But I am sure I have read a post that r1825 in sigle threaded processing is working at least the same well as r1576. If you want I can edit my previous post and delete the sentence about recommendation
I cannot find recommendation for r1825. So maybe I was not remembered well. But I am sure I have read a post that r1825 in sigle threaded processing is working at least the same well as r1576. If you want I can edit my previous post and delete the sentence about recommendation
Re: DGDecNV and KNLMeans under Win10_x64
QTGMC is just used here as test to show a potential global/general issue, not something specific to QTGMC.AJR wrote:I dont use QTGMC
Re: DGDecNV and KNLMeans under Win10_x64
Didn't someone identify the commit that caused it? If so, why can't we have a fixed version pronto?
Re: DGDecNV and KNLMeans under Win10_x64
Have the original developers abandoned Avisynth+? We now have random people trying to hack away on it?
Re: DGDecNV and KNLMeans under Win10_x64
Could you please put version 2049 instead of test in the test builds?
Otherwise staxrip can't recognize them
Otherwise staxrip can't recognize them
Re: DGDecNV and KNLMeans under Win10_x64
I don't know what you are talking about. I don't put "test" anywhere.
Re: DGDecNV and KNLMeans under Win10_x64
Just found that AVSMeter64 and x264_x64 works with 64 bit versions of both DGDecNV and KNLMeansCL:
There must be something wrong with NVIDIA drivers or something else on 32 bit.
I was accustomed with MeGUI, I'll have to use command line. StaxRip gives me problem with demux dependencies.
Code: Select all
LoadPlugin("D:\eseguibili\media\DGDecNV\x64\DGDecodeNV.dll")
DGSource("E:\in\2_01 favoloso mondo di Amelie, Il\amelie.dgi")
KNLMeansCL(D=1, A=1, h=7.0,device_type="GPU")
CompTest(1)
Code: Select all
AVSMeter 2.1.2 (x64)
AviSynth+ 0.1 (r1825, MT, x86_64) (0.1.0.0)
Number of frames: 1764
Length (hh:mm:ss.ms): 00:01:13.500
Frame width: 1920
Frame height: 816
Framerate: 24.000 (24/1)
Colorspace: YV12
Frames processed: 1764 (0 - 1763)
FPS (min | max | average): 2.087 | 41.93 | 22.76
Memory usage (phys | virt): 101 | 389 MB
Thread count: 23
CPU usage (average): 10%
Time (elapsed): 00:01:17.497
I was accustomed with MeGUI, I'll have to use command line. StaxRip gives me problem with demux dependencies.
Re: DGDecNV and KNLMeans under Win10_x64
Thanks for the status report and please keep me informed of any further findings.
Re: DGDecNV and KNLMeans under Win10_x64
No other findings for some time, at least until AviSynth+ gives no image corruption and cretindesalpes compiles an x64 version of modified MVTools.admin wrote:Thanks for the status report and please keep me informed of any further findings.
If you can report this behaviour to your Nvidia contacts, probably you can debug together the problem.
In the mean time I'll be obliged to use Intel GPU to decode videos.
Re: DGDecNV and KNLMeans under Win10_x64
I'm not interested in debugging KNLMeansCL, and I'm certainly not going to bother nVidia about something only one person reports.
Re: DGDecNV and KNLMeans under Win10_x64
It's a pity there are no other working OpenCL AviSynth plugins now.admin wrote:I'm not interested in debugging KNLMeansCL, and I'm certainly not going to bother nVidia about something only one person reports.
Re: DGDecNV and KNLMeans under Win10_x64
Why is it a pity? Who cares about OpenCL?
CUDA outperforms OpenCL by 30% and CUDA performs faster data transfers to and from a GPU's memory.
To protect the source for a closed-source application requires jumping through hoops for OpenCL.
Anyway, it's all moot for DGDecNV which relies on CUVID. I suppose one could try to make a case for OpenCL transform filters on portability grounds, but I speculate that most people are more concerned about performance on their own platform than the theoretical portability to other platforms.
From the internet: "When portability is an issue, it is always better to use a standard. However, an interesting fact on the portability of OpenCL is that while a big part of the same code (mostly the kernels) can be certainly executed in several platforms, the high performance will not be as portable. There will still be a need of making optimizations to exploit the architecture at hand. A code optimized for a GPU does not necessarily work as optimized on a multicore ARM or FPGA. Also the control code is likely not 100% portable and must be re-written when changing the platform to a totally different one."
Flame suit is on, fire away!
CUDA outperforms OpenCL by 30% and CUDA performs faster data transfers to and from a GPU's memory.
To protect the source for a closed-source application requires jumping through hoops for OpenCL.
Anyway, it's all moot for DGDecNV which relies on CUVID. I suppose one could try to make a case for OpenCL transform filters on portability grounds, but I speculate that most people are more concerned about performance on their own platform than the theoretical portability to other platforms.
From the internet: "When portability is an issue, it is always better to use a standard. However, an interesting fact on the portability of OpenCL is that while a big part of the same code (mostly the kernels) can be certainly executed in several platforms, the high performance will not be as portable. There will still be a need of making optimizations to exploit the architecture at hand. A code optimized for a GPU does not necessarily work as optimized on a multicore ARM or FPGA. Also the control code is likely not 100% portable and must be re-written when changing the platform to a totally different one."
Flame suit is on, fire away!
Re: DGDecNV and KNLMeans under Win10_x64
Ok, let's try to tell Khanattila to port KNLMeansCL to CUDA.admin wrote:Why is it a pity? Who cares about OpenCL?
CUDA outperforms OpenCL by 30% and CUDA performs faster data transfers to and from a GPU's memory.
Re: DGDecNV and KNLMeans under Win10_x64
KNLMeansCL must be a really big deal to have you in such a state. Help me out, what is so great about it? I'm not doubting, I just don't know anything about it.
- Aleron Ives
- Posts: 126
- Joined: Fri May 31, 2013 8:36 pm
Re: DGDecNV and KNLMeans under Win10_x64
Well, nVidia certainly doesn't. They added a bug for GK104 cards in their 330.x driver branch that cuts OpenCL performance in half, which means I can never upgrade my GPU driver without killing my Folding@home performance. Apparently nVidia doesn't care about the bug at all, because they've released many drivers over the last year and have never taken any steps to fix it. They don't seem to care about supporting their cards with older architectures, either.admin wrote:Why is it a pity? Who cares about OpenCL?
Re: DGDecNV and KNLMeans under Win10_x64
Can you please point me to a reliable source for this claim?Aleron Ives wrote:They added a bug for GK104 cards in their 330.x driver branch that cuts OpenCL performance in half
Yes, I have discovered this the hard way.They don't seem to care about supporting their cards with older architectures, either.
- Aleron Ives
- Posts: 126
- Joined: Fri May 31, 2013 8:36 pm
Re: DGDecNV and KNLMeans under Win10_x64
There have been multiple reports from people with GK104 cards that Folding@home performance gets halved after updating to anything after driver 327:
https://foldingforum.org/viewforum.php?f=80
Here's just one report posted by a forum moderator for why the TC's GTX 770 is folding poorly:
https://foldingforum.org/viewtopic.php?f=80&t=27297
There are other reports, but you'd have to dig through the forum to find them, as the bug was introduced about two years ago now. I've also seen reports on various overclocking/PC enthusiast forums and elsewhere, but it's been more than a year since I did the research that led me to decide to never update my GPU driver (which is annoying, as I can't get any of the benefits bestowed by those new drivers).
https://foldingforum.org/viewforum.php?f=80
Here's just one report posted by a forum moderator for why the TC's GTX 770 is folding poorly:
https://foldingforum.org/viewtopic.php?f=80&t=27297
There are other reports, but you'd have to dig through the forum to find them, as the bug was introduced about two years ago now. I've also seen reports on various overclocking/PC enthusiast forums and elsewhere, but it's been more than a year since I did the research that led me to decide to never update my GPU driver (which is annoying, as I can't get any of the benefits bestowed by those new drivers).
Re: DGDecNV and KNLMeans under Win10_x64
Thank you, Aleron.
Re: DGDecNV and KNLMeans under Win10_x64
While you're here...has this folding stuff ever led to any useful discoveries, treatments, etc.?
- Aleron Ives
- Posts: 126
- Joined: Fri May 31, 2013 8:36 pm
Re: DGDecNV and KNLMeans under Win10_x64
The results are used for peer-reviewed scientific journal articles that a layman such as myself cannot understand, so I can't really comment as to how useful the results have been. All I can do is hope that donating my computing time might help somebody at Stanford learn something important. I can't perform cancer research myself, but I can run a computer program.
Since you have a more scientific background than myself, perhaps you would find some of the articles comprehensible or illuminating. Stanford has a directory of the papers published from F@h projects here. I might think that the most recent paper, "Activation pathway of Src kinase reveals intermediate states as targets for drug design" would sound promising, if I knew what it was about.
Since you have a more scientific background than myself, perhaps you would find some of the articles comprehensible or illuminating. Stanford has a directory of the papers published from F@h projects here. I might think that the most recent paper, "Activation pathway of Src kinase reveals intermediate states as targets for drug design" would sound promising, if I knew what it was about.
Re: DGDecNV and KNLMeans under Win10_x64
I just read a post about 2049 working. Could you please give me a link to download?
Thanks.
Thanks.
Re: DGDecNV and KNLMeans under Win10_x64
I uploaded it to the binaries area.
If it works it is not because of anything different in my code. It is because different versions of CUDA/CUVID are used. That is not within my control, as the latest version of CUDA/CUVID is needed to support HEVC and latest hardware.
If it works it is not because of anything different in my code. It is because different versions of CUDA/CUVID are used. That is not within my control, as the latest version of CUDA/CUVID is needed to support HEVC and latest hardware.