madVR - high quality video renderer (GPU assisted)

[kasper93]

@Siso: Try latest MPC-HC's beta version https://nightly.mpc-hc.org/ It shouldn't affect madVR's render times anymore.

[Siso]

Originally Posted by kasper93

@Siso: Try latest MPC-HC's beta version https://nightly.mpc-hc.org/ It shouldn't affect madVR's render times anymore.

I tried it but not much of a difference...

[rbej]

Originally Posted by madshi

Can you upload a debug log for me? 20 seconds windowed playback, then 20 seconds fullscreen playback, then please close the media player directly, if possible without switching back to windowed again. Please zip the debug log and upload it somewhere (don't attach to this forum). Thanks.

Full screen DXVA Scaling Off

http://www18.zippyshare.com/v/hDhY6T1f/file.html

Windowed playback (DXVA Scaling On) with debug mode is very poor. Without debug mode windowed playback is very smooth.

[zveroboy]

Originally Posted by madshi

Ah, thanks! I think I know what this is:

The D3D11 presentation mode *requires* desktop composition to be enabled. So if you activate D3D11 presentation mode, madVR cannot disable desktop composition, anymore.

http://forum.doom9.org/showthread.ph...68#post1722068

Originally Posted by madshi

Can you confirm that when disabling D3D11 presentation mode, disabling desktop composition works fine again?

No. The check box "use Direct3D 11 for presentation" is off, but disabling desktop composition dont work.
0.89.5 - the same behavior.

[madshi]

Here is a new test build for those that had freezes with v0.89.5 when closing the media player, or when switching video files, or moving the media player to a different monitor:

http://madshi.net/madVR895d.rar

Does this build fix those freezes/stability issues?

Originally Posted by rbej

How enable debug mode in madVR?.

When i run "activate debug mode" - "file madVR.ax not found'. Very strange. madVR.ax is here.....

If the batch file doesn't work, open it with an editor to see what it does, and do it manually instead. The batch file simply renames some files, it's very simple.

Originally Posted by rbej

Full screen DXVA Scaling Off

http://www18.zippyshare.com/v/hDhY6T1f/file.html

Windowed playback (DXVA Scaling On) with debug mode is very poor. Without debug mode windowed playback is very smooth.

That's strange, there should be no big difference between debug and release builds.

Anyway, the log only contains fullscreen playback. I asked for 20 seconds windowed and fullscreen each, so I can compare.

Originally Posted by zveroboy

No. The check box "use Direct3D 11 for presentation" is off, but disabling desktop composition dont work.
0.89.5 - the same behavior.

Ok, try this build from the top of this comment. Does that help?

[zveroboy]

Originally Posted by madshi

Ok, try this build from the top of this comment. Does that help?

Yes.
madVR895d is OK.
Many thanks!

[rbej]

Originally Posted by madshi

Anyway, the log only contains fullscreen playback. I asked for 20 seconds windowed and fullscreen each, so I can compare.

Windowed mode

http://www69.zippyshare.com/v/8GnhYMKu/file.html

Full screen mode

http://www18.zippyshare.com/v/hDhY6T1f/file.html

[madshi]

Originally Posted by zveroboy

madVR895d is OK.

Good to hear!

Originally Posted by rbej

Windowed mode

http://www69.zippyshare.com/v/8GnhYMKu/file.html

Full screen mode

http://www18.zippyshare.com/v/hDhY6T1f/file.html

Ok, thanks. Which trade quality for performance options do you have set?

The new windowed mode doesn't work well for you?

[madshi]

Originally Posted by XRyche

Yes, I'll be around next weekend for testing. No problem.

Ok, here's a new test build. Will need a new log, thanks.

http://madshi.net/madVR895f.rar

Doubling with e.g. super-xbr works without that delay for you now? It's only NNEDI3 making trouble, correct?

[rbej]

Originally Posted by madshi

Good to hear!


Ok, thanks. Which trade quality for performance options do you have set?

The new windowed mode doesn't work well for you?

Trade quality - default. i dont change anything.

New windowed mode working well.

[madshi]

Originally Posted by rbej

Trade quality - default. i dont change anything.

New windowed mode working well.

The new windowed mode works well in fullscreen, too? Is there a reason why you were using the old mode?

[rbej]

Originally Posted by madshi

The new windowed mode works well in fullscreen, too? Is there a reason why you were using the old mode?

New windowed mode not working well in full screen. Playback is still poor.

No reason. I tested new and old windowed mode.

[Damien147]

Subtitles are in the center when being fullscreen,anyone else?

[kasper93]

@Damien147: You can always read few posts before and you will know what to do.

[Damien147]

Ok,thanks.

[Stan]

Originally Posted by madshi

Here is a new test build for those that had freezes with v0.89.5 when closing the media player, or when switching video files, or moving the media player to a different monitor:

http://madshi.net/madVR895d.rar

Does this build fix those freezes/stability issues?

Fixed for me, thank you very much!

[XRyche]

Originally Posted by madshi

Ok, here's a new test build. Will need a new log, thanks.

http://madshi.net/madVR895f.rar

Doubling with e.g. super-xbr works without that delay for you now? It's only NNEDI3 making trouble, correct?

Yes only NNEDI3 image doubling is giving me issue and NNEDI3 chroma upsampling as well. Although, as I stated previously, NNEDI3 chroma upsampling shows the correct colours when used in conjunction with Super-Res.

On an unrelated note, madVR895c is positioning the internal subtitle renderers subtitle placement correctly for me now as well.

[XRyche]

Originally Posted by madshi

Ok, here's a new test build. Will need a new log, thanks.

http://madshi.net/madVR895f.rar

Here's the log: https://www.mediafire.com/?auan6vyygdwfrra .

[madshi]

Originally Posted by Stan

Fixed for me, thank you very much!

Good to hear!

Originally Posted by XRyche

Here's the log: https://www.mediafire.com/?auan6vyygdwfrra .

Thanks. Ok, it's official now: For some reason, creating the OpenCL command queue takes about 10 seconds on your PC. I don't know why, but that's how it is. This looks like a problem with your OpenCL installation. There's nothing I can do about it. It seems you can either try repairing your OpenCL installation somehow (I don't know how). Or alternatively you'll have to give up on NNEDI3 for now. I might offer a NNEDI3 option without OpenCL in the future.

Originally Posted by rbej

New windowed mode not working well in full screen. Playback is still poor.

Ok, can you please make a debug log with this test build?

http://madshi.net/madVR895g.rar

[chros]

Originally Posted by aufkrawall

There's no difference for me. On the right side, there is new windowed path and on the left side, it's old FSE mode:

It's the same with old windowed path.
My test case was 1080p60 -> WQHD with Jinc3 + SuperRes 2 passes + Adaptive Sharpen.

Hhmmm... That's interesting. Maybe your card is so powerful, or it depends on lot's of things. Are you sure that you used D3D9 exlusive (old path)?

Here're my results (see my signature for details):
0. I'd been done testing on the 1080p TV, using nvidia with DXVA-copyback in LAV video, dithering on, all trading performance are switched off, no smooth motion, no other processing. I tried to select the lowest gpu and memory freq where the queues are still full. (max values: gpu 745MHz, ram: 2000MHz)
1. I managed to use Overlay mode (finally): but only with iGPU (intel) and only when I was tested on TV (my AV receiver is recognized otherwise as a cloned display device, that's why I got blank picture when I tried it on my laptop screen )
2. 720p (1280x720) 25fps video, chroma Jinc+AR, luma Jinc+AR:
- D3D9 FSE new path: gpu 690MHz, mem 2000MHz (gpu usage: 90-92%)
- D3D9 FSE old path: gpu 450MHz, mem 800MHz !!! (gpu usage: 97-99%, but playback is without a problem)
3. 1080p (1920x1080) 23.976fps video, chroma super-xbr+AR:
- D3D9 FSE new path: gpu 490MHz, mem 900MHz (gpu usage: 90-92%)
- D3D9 FSE old path: gpu 405MHz, mem 405MHz !!! (gpu usage: 80-82%) This result is actually insane!!! -> we use the lowest settings in P8 state (P12->P8->P5->P0)
4. The above values are valid. Both GPU-Z and nvidiainspector shows them, plus the thermal monitor app for CPU and GPU is also right on both cases.
5. I noticed 1 more thing in my system: the new path is way more ram consuming then the old one. In both tests I had to raise the ram clock not just the gpu clock.
6. All the rest of the modes (FS Windowed new/old path, FS Overlay, FS D3D11) were about the same speed like FSE new path was (only D3D9 old path is different completely).
7. The results were similar when I tried it out on the intel iGPU (with different scaling algos, since it's not so powerful than the nvidia), D3D9 FSE old path was way faster than the rest.
8. conclusion: if you do care about performance AND you don't/can't use NNEDI3 AND you don't use 10bit output, then give the D3D9 old path a chance! You can test how it behaves within 5 minutes.

Madshi, what could cause such a big performance difference?

Originally Posted by madshi

It's a technical limitation and there's not much I can do about it, without totally rewriting the "old exclusive mode".

You don't need t worry about it, since it's the fastest mode for me, thanks!

Originally Posted by madshi

It's possible, but difficult, due to 2 reasons:
1) You'd need to find an image, ideally some high quality RGB photo, where different chroma upscaling algorithms would show clear differences. In order to find such an image, you need to know what to look for. E.g. dark content with lots of black and red usually is a good idea. You should use an RGB photo which has full resolution chroma, maybe even scale it down a bit in RGB, so that the chroma channels really have full resolution and quality.
2) You need to convert the image to YCbCr 4:2:0, and you can't do that by simple downscaling chroma. You need to use the correct chroma offset, too! The chroma channel is not in center position compared to luma channel. It's slightly offset for all newer video codecs (MPEG2, h264, VC-1, h265 etc). Maybe LAV Video Decoder applies the proper offset when forcing it to output NV12? I'm not sure. @nevcairiel?

Sorry, but this was like Chinese language to me
I made a chroma comparison test with the video "mp4.v2c\Misc Patterns\A - Additional\3-Color Steps.mp4" from AVS.HD.709.v2d.Calibration of AVSforum, in windowed fullscreen mode, the zipped pngs are here: http://www10.zippyshare.com/v/bDzpW31T/file.html
(NN: nearest neighbour, SX: super-xbr+AR, Jinc: Jinc+AR, SR: superres strenght1, SR2: superres strenght2)
What I can see on the images that Superres adds unwanted bright edges that can be visible at the red rectangles on the right side of the pictures.
Apart from this, I can't tell the difference between the tested 3 algos (NN, Jinc+AR, SX+AR), maybe the test video wasn't aproppriate for this.