NVIDIA Puts Out A Major Beta Linux Driver Update

[phoronix]

Phoronix: NVIDIA Puts Out A Major Beta Linux Driver Update

It was just one week ago that NVIDIA released a stable Linux driver update, but today for those wishing to live on the bleeding edge of NVIDIA's proprietary Linux driver development, the first beta release in the 260.xx series is now available for testing. The NVIDIA 260.19.04 Linux driver brings a lot to the table...

http://www.phoronix.com/vr.php?view=ODU3NQ

[deanjo]

I was wondering when they were going to release these public.

[DeepDayze]

Very sweet...will these play nice with GPU-accelerated Flash or even HTML5?

[deanjo]

Very sweet...will these play nice with GPU-accelerated Flash or even HTML5?

The drivers have played nice with HTML5 for a long time, as far as GPU-accelerated Flash that's a question that you have to ask Adobe.

[deanjo]

Added support for the nvcuvid API.

nvcuvid provides a mechanism for decoding video and exposing the surfaces to CUDA, allowing applications to perform custom processing of the video. nvcuvid is primarily targeted at transcoding and video- processing applications. nvcuvid was already available on other platforms.

This feature is going to be sooooooooo nice for my frame perfect h264 editting app.

[xenogia]

Now we just have to see CUDA added to Mplayer and all the other applications. Unless we have some third-party party application that will do CUDA acceleration. Hopefully this will help the issues with Compiz and it's incompatibilities with VDPAU.

[klikklak]

I like the fact that they have a crippled stereo-3d implementation, sort of. Or even just the fact that they're actually doing something about the lack of stereo-3d on linux, even if it's only for running 3d in 2d.

[brent]

nvcuvid is very similar to the VdpDecoder component of VDPAU. There are no advantages compared to VDPAU. On Windows it's different, since DXVA(2) has some restrictions.

[deanjo]

nvcuvid is very similar to the VdpDecoder component of VDPAU. There are no advantages compared to VDPAU. On Windows it's different, since DXVA(2) has some restrictions.

With nvcuvid it should be a lot simpler to implement cuda post-processing filters and the likes.

[brent]

Yeah, but there's no fundamental difference, so it's not *a lot*. VDPAU surfaces can be reused by CUDA. Also, I'd rather use OpenCL.