Page 9 of 17

Re: About DGDenoise

Posted: Fri Feb 24, 2017 6:06 pm
by admin
I can't believe no-one went :wow: :wow: :wow: over my CUDASynth idea. Just ahead of the times, what can I do?

Re: About DGDenoise

Posted: Fri Feb 24, 2017 6:16 pm
by Guest
CUDASynth
That would be awesome!

Re: About DGDenoise

Posted: Fri Feb 24, 2017 6:18 pm
by admin
How much memory on your GPU, gonca? I'm going to need a power tester for CUDASynth.

Re: About DGDenoise

Posted: Fri Feb 24, 2017 6:25 pm
by Guest
8 GB of GDDR5

Re: About DGDenoise

Posted: Fri Feb 24, 2017 6:31 pm
by admin
Sweet, how many CUDA cores?

I tried to play with core clock but it was too unstable and didn't give much improvement.

Re: About DGDenoise

Posted: Fri Feb 24, 2017 6:39 pm
by Guest
1920 cuda cores

Cuda is scalable through SLI is it not?

Re: About DGDenoise

Posted: Fri Feb 24, 2017 6:47 pm
by admin
Perhaps, but we don't need SLI to use multiple GPUs. We would expect CUDASynth to handle it transparently.

Re: About DGDenoise

Posted: Mon Feb 27, 2017 12:37 pm
by Guest 2
admin wrote:I haven't decided the exact temporal denoising to be implemented [thank you for pointing out TemporalSoften()], but it will surely be done with additional parameters and not by adding a new filter.
As first iteration, get a look to KNLMeansCL source and just kick in the temporal part. I am curious to see speed.

And, please, give us more parameters to play with frame span, noise window, etc :bow:

Re: About DGDenoise

Posted: Mon Feb 27, 2017 12:51 pm
by admin
Greetings Guest 2.

Good advice, thanks. I'll have a look. I don't know if it uses a full 3D NLM or if it just hacks in some kind of temporal filter. I'm close to deciding not to bother anyway, unless someone shows me a clip that really needs the temporal component.

Exposing the search size and patch size by making them parameters is not so easy when the loops are unrolled at compile time (loop unrolling gives a massive speed-up). I could provide a set of selectable kernels with different fixed parameters (call them presets). What fixed parameter sets would be useful for you?

I've been looking for ways to make NLM separable, as that could give a substantial speed-up. One paper I saw does it by recasting NLM as a convolution, but I'm still grokking the details.

BTW, I added licensing checks to DGDecodeNV.dll in order to protect included standalone filters that don't depend on a DGI file. I want to reward only legit and loyal DG users (and not people at other forums that abuse me with full support of the administrators; at my core I am a decent, generous guy, but I hit back hard when attacked). Anyway, gonca kept asking me to add licensing. :D

Re: About DGDenoise

Posted: Mon Feb 27, 2017 3:32 pm
by Guest
Anyway, gonca kept asking me to add licensing. :D
Just thought you should be rewarded for your hard work, or at least some of your server costs covered.
Besides that, good beer and triple malt scotch aint cheap!! :(
Your loyalty and devotion to legitimate DG tools users is appreciated. :D

Re: About DGDenoise

Posted: Mon Feb 27, 2017 3:56 pm
by admin
Thanks! Getting ready to optimize the inner loop...

Image

Re: About DGDenoise

Posted: Mon Feb 27, 2017 4:26 pm
by Guest
Moonshine? :wow:

Re: About DGDenoise

Posted: Mon Feb 27, 2017 4:30 pm
by admin
Heck no, only the best for DG.

Re: About DGDenoise

Posted: Tue Feb 28, 2017 11:03 am
by admin
I slipstreamed 2053 to add a searchw parameter for the denoising. You can set it to 5, 7, or 9. The default is 5, corresponding to a=2 for KNLMeansCL.

Re: About DGDenoise

Posted: Tue Feb 28, 2017 12:07 pm
by Guest 2
admin wrote:What fixed parameter sets would be useful for you?
Fixed is of little use, as every movie has different noise (and film grain too).

Anyway, time is on your side. Thanks for all your efforts. :bow:

Re: About DGDenoise

Posted: Tue Feb 28, 2017 12:19 pm
by admin
Fixed doesn't mean you can't change the settings. It just means I have to limit the combinations I offer, due to the inability to unroll at run time. How long are you willing to wait for JIT compilation of the PTX code? 1ms? 10ms? 100ms? 1 sec? 10 seconds? 10 minutes?

So I ask again, what combinations of parameters do you need? If you say all of them, then it means you should use KNLMeansCL and be happy with the performance degradation you pay for your freedom. I wish I could offer you a free lunch, but reality bites.

Re: About DGDenoise

Posted: Wed Mar 01, 2017 5:30 pm
by admin
Gals and guys, have you checked out the 1080Ti? At $699 this will likely be my next GPU card. What say you, gonca?

Re: About DGDenoise

Posted: Wed Mar 01, 2017 5:50 pm
by Guest
Looks highly impressive, my 1070 looks weak all of the sudden.
Are you a gamer?
What about the Pascal Titan?
250 watts though, how big is your power supply?

Re: About DGDenoise

Posted: Wed Mar 01, 2017 6:07 pm
by admin
I'm not a gamer; I want lots of cores for running multiple CUDA kernels in a pipeline (via CUDA streams): CUDASynth.

1080Ti edges out Titan X, except for 1GB less memory. nVidia acknowledges the market will move from Titan X to 1080Ti.

I'll take my big tower and 850W supply out of the shed to build a new system.

Re: About DGDenoise

Posted: Wed Mar 01, 2017 6:14 pm
by Guest
:lol: If your shed is anything like mine, just get a new tower and power supply

Re: About DGDenoise

Posted: Sat Mar 04, 2017 8:37 am
by admin
I located gonca's shed on Google street view.

Image

Re: About DGDenoise

Posted: Sat Mar 04, 2017 10:57 am
by Guest
Hey, who fixed my shed without telling me?

Re: About DGDenoise

Posted: Sat Mar 04, 2017 11:22 am
by admin
I did my best last night but I think it's a lost cause.

BTW, I grabbed an old TRS-80 I found in there but it had a rat's nest inside and the 10MB disk was rusted.

Re: About DGDenoise

Posted: Sat Mar 04, 2017 11:34 am
by Guest
article-2251639-169BBDF3000005DC-137_634x461.jpg
"lost cause" -- never looked better
Thanks for cleaning up my backyard, by the way, it couldn't be a rats nest - a squirrels nest yes.

Re: About DGDenoise

Posted: Sat Mar 04, 2017 11:39 am
by Guest
Quick question
How do you get the pics to show the way they do? No attachment etc.