Phoronix: Intel Wants YOUR Linux Questions, Feedback
Intel's Linux graphics team is seeking any questions or feedback that Phoronix readers have concerning their open-source Linux graphics driver stack...
http://www.phoronix.com/vr.php?view=MTA0MjI
Printable View
Phoronix: Intel Wants YOUR Linux Questions, Feedback
Intel's Linux graphics team is seeking any questions or feedback that Phoronix readers have concerning their open-source Linux graphics driver stack...
http://www.phoronix.com/vr.php?view=MTA0MjI
That unfair.Quote:
and not the notorious Poulsbo or now the Medfield situation
Background: Intel seems to introduce video products before stable support is available. I got caught in that with 4500HD, which had great reviews (even here on Phoronix), but was actually too unstable to use. I ended up getting a standalone GPU, even though I didn't need the additional performance. I've since avoided Intel graphics on all subsequent purchases.
Question: What is Intel doing to insure that drivers and support are available for products at introduction in Linux, not a year or two later?
I am not sure if I got your question correctly, but as Michael has already covered in several articles here on phoronix, Ivy Bridge was fully supported on Linux, in upstream versions of Kernel, Mesa, xf86-video-intel and so on, around 1 year prior to its launch.
For the future graphics adapters, I won't disclose much details, but we expect to improve the pace even a bit further.
There was a graphics test for Fedora 16 in which I participated, I had a pretty old notebook with Intel integrated graphics(128 MB Video) i945. I found some bugs when I did this test but the reporting was to complicated. I wasn't able to report if I did not have a Fedora Wiki account which needed some license agreement and waiting for manual confirmation. My point is that Intel integrated graphics might have a lot of bugs but u maybe don't know about them yet... My problems were that it wasn't displaying the 3d models correctly, were glitchy, instead of seeing a ball for example, I was seeing only a few pixels from 1 surface. That problem was in 2 or 3 tests from something like 10.
Since the new gpus come from a third party there is poor opensource support, is there any plan to fix this introducing new intel gpus that could be supported?
Any plan to support opencl on existing or future gpus?
I'm interested in the following questions:
1) What exactly is RC6?
2) Why does it repeatedly turn out to be non-functional? Is it some unforeseen incompatibility on Intel's side? Are there some BIOS bugs to work around?
3) Can we expect universal support for RC6 (and/or semaphores) in the future?
4) Whereas Intel's integrated graphics are not really competitive in the performance segment, they are vastly ahead regarding power efficiency. Can we expect further driver improvement in that regard?
5) Will we get S3TC?
When can we expect OpenGL 3.3 support on Sandy Bridge?
When do you expect to have OpenGL 4.2 support on Ivy Bridge?
What is the status of OpenCL support on Ivy Bridge?
Will native CUDA support be introduced for Ivy Bridge or will CUDA code continue to require GPU Ocelot:
http://code.google.com/p/gpuocelot/