Slashdot Mirror

AMD engineers have contributed OpenCL code which is an open standard that can run on many different accelerators (some not even GPUs). this is distinctly different from CUDA which only works with Nvidia stuff.

Please mod parent up. Self-hosting is a very important point, it was the second part of my thinking in adopting the new firefox account last month, but I forgot to mention it in my earlier post. The other cool thing about self-hosting it is that organizations can perhaps have internal social bookmarking (which could be awesome for dev teams and ops teams). You'd just have to extend the firefox accounts server with the social features which would enhance colaboration

Self hosting FTW :D I currently have all my bookmarks stored in the owncloud bookmark toolbar but until the improvs i've ordered actually get shipped I don't have a good embedded device to run my owncloud on and the raspberry pi that's currently hosting owncloud is a little slow. Firefox accounts just makes it easier, and I will be able to self host it on my improv or whatever. To the GP, can you tell me what hardware you're using to self host? I've found the raspberry pi unacceptably slow (but I need to give seafile another shot) so I'm considering buying a beagleboard if the improv never ships :( Anyone using a parallela to self-host?

Another choice - Zynq + transputter @ $100
http://www.parallella.org/

Since the Zynq's FPGA is a good match for a GPU project, how about implementing the entire open design on the Parallella board?

In addition to the FPGA, Parallella gives you a very powerful 16-core floating point accelerator in the Epiphany device, so most of the shader work can be done in the Epiphany cores leaving only the most time-critical parts to the FPGA. Needless to say, Epiphany already has the hardware parallelism required for shaders, at least 16 of them, and 64 in the larger board. At most this approach would require a small external PC board carrying the graphics sockets, connected to the Parallella's I/O headers with a short cable.

Refining the shader code on Epiphany would be VASTLY easier than refining the Verilog on the FPGA, by orders of magnitude, and the number of people able to help would be comparatively vast.

Not exactly what you asked for. Only 1 GHz, and less cores than you asked, but there are already plenty of people complaining that it's too distributed to be useful, so I guess something like that needs to prosper before people try that OpenCL chip.

http://www.parallella.org/board/

With the recent success of Parallella, that might actually be feasible. Hmmm....

there was a successful kickstarter campaign some time ago that introduced precisely those chips [Zynq-7020] at quite affordable prices: http://www.kickstarter.com/projects/adapteva/parallella-a-supercomputer-for-everyone/ they are going to have them available for sale soon at http://www.parallella.org/ after the kickstarter pledges are fulfilled. at $100 + shipping they are far more affordable than what you mention, they are also committed to having most (if not all?) things open, so be sure to check out their website.

I think the Pocl project disagrees with you on "won't be seeing any open source OpenCL". GPU-accelerated OpenCL is a sadder story. Also, the Parallella computer with its Epiphany coprocessors should have open source OpenCL acceleration, but will take a while longer for public availability. Of course, both of these are off topic for the original question of supported GPUs in current laptops.