This past February, Intel's Alan Cox announced an open-source Intel GMA500 driver, with the GMA500 being the notorious "Poulsbo" that's really graphics IP from Imagination Technologies and their PowerVR SGX core. This initial open-source GMA500 driver provided kernel mode-setting support, but went without any form of hardware acceleration. Since the PowerVR hardware isn't publicly documented or supported in open-source by Imagination Technologies, this "GMA500" driver was basically clobbered together from various bits of open-source code and other work by Alan Cox.
This open-source GMA500 driver was merged into the mainline Linux kernel and as of the Linux 3.0 kernel it's still in the staging area. There's still no hardware acceleration, but we're wondering what are the plans for this driver. In May we learned that the next-generation Atom hardware would use more PowerVR IP, but at the same time Intel's been hiring up some former Nokia Linux engineers with PowerVR experience and other activities that are making us wonder if Intel is working on a fully open-source PowerVR driver stack. Intel knows that right now it's a huge and dirty mess.
While we have no further information on that matter, it seems that very soon we should see "Cedar Trail" support landing in that basic GMA500 open-source driver. In response to a GMA500 bug-fix patch on the Linux kernel mailing list, Alan Cox wrote, "Unfortunately this file doesn't even exist in the working tree any more. Please wait until Greg has taken the patch set I sent him to replace the one that didn't apply, and the patch series after that (and quite possibly the one after that assuming I can get Cedartrail to work next week)."
The last bit of Alan's message from this morning is what's most interesting. It appears Alan expects to soon (as in next week) have Cedar Trail working with this driver. Cedar Trail is Intel's codename for the next-generation Atom that bears more PowerVR graphics. Cedar Trail is expected to be released by the end of the year and will be a 32nm Atom CPU with greater battery life, improved graphics, and lower heat output (fan-less designs).
This means that for the Linux 3.1 kernel we could see the Cedar Trail graphics code merged, but more than likely it will still not be accelerated and only just be useful for kernel mode-setting. Before the Cedar Trail hardware is even publicly released we'll see the Linux 3.2 kernel and possibly even the Linux 3.3 release, so at least there's more time to hopefully better the open-source Cedar Trail capabilities.
Cedar Trail will need to compete with AMD's Fusion APUs and their open and closed-source Linux drivers, so it will be interesting to see Intel's play with this next-generation Atom hardware.