Re: ARM 3D support was Re: [fedora-arm] ARM summit at Plumbers 2011
On Wed, 24 Aug 2011 12:00:43 +0100, Luke Kenneth Casson Leighton wrote: [ok i'm going to do another cross-post in a bit which will give some background and also perhaps some other topics for discussion, but i wanted to cover this first. apologies for people for whom this is just noise] On Tue, Aug 23, 2011 at 7:01 PM, wrote: the xilinx zynq-7000 or similar (dual core Cortex A9 + FPGA). The idea is to have an OGP GPU in firmware in FPGA. In terms of the power budget, it seems to work relatively sanely considering what it is, and it is as ideal as it gets as far as openness and flexibility goes. I just thought it's worthy of a mention. It does seem outlandish, but it is kind of cool. Is it going to give enough 3d speed? The next gen tegra is supposed to have a 24 core GPU. if nvidia have a published announcement of their plans to release a fully free-software-compliant 3D driver to match the proprietary hardware, then that would be brilliant news [about their next gen GPU]. about the zynq idea: it actually doesn't matter if it's "enough". the very fact that free software developers - and people who want to be free software developers - around the world could even _remotely_ consider buying one of these for an affordable price instead of $750 for the present OGP card means that more people can at least begin to try to address the unbelievably wide and very discouraging gap between us and proprietary 3D hardware. the NREs on producing a set of masks are _only_ $250,000 if you are a taiwanese company asking TSMC, but for everyone else they're at least $2 million. the development costs if you use off-the-shelf tools before you even _get_ to the point where you can ask a fab to produce those masks spiral out of control (Mentor Graphics charges something like $250,000 per month or maybe per week per user; NREs for peripheral hard macros can be $50k to $100k each etc. etc.), taking the total development costs in many cases to well above $USD 30 million. and that's excluding all that "proprietary software" which of course is utterly useless without the corresponding hardware but, because of USA Accountancy Rules, where "IP" can be added to the books to increase the value of a company, there's a strong financial disincentive to consider just "givvin it aww away 4 fwee". and here we are with a CPU which could well be around the $25 - $30 mark in large enough volumes, presented with the possibility to say " u all, you proprietary GPU companies and your greed, fear, patent warfare and lack of willingness to collaborate and cooperate". ok maybe not those exact words but you know what i mean :) I quite like the wording, actually. :) Gordan -- ubuntu-devel mailing list ubuntu-devel@lists.ubuntu.com Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-devel
Re: ARM 3D support was Re: [fedora-arm] ARM summit at Plumbers 2011
[ok i'm going to do another cross-post in a bit which will give some background and also perhaps some other topics for discussion, but i wanted to cover this first. apologies for people for whom this is just noise] On Tue, Aug 23, 2011 at 7:01 PM, wrote: >> the xilinx zynq-7000 or similar (dual core Cortex A9 + FPGA). The idea >> is to have an OGP GPU in firmware in FPGA. In terms of the power budget, >> it seems to work relatively sanely considering what it is, and it is as >> ideal as it gets as far as openness and flexibility goes. >> >> I just thought it's worthy of a mention. > > It does seem outlandish, but it is kind of cool. Is it going to give enough > 3d speed? The next gen tegra is supposed to have a 24 core GPU. if nvidia have a published announcement of their plans to release a fully free-software-compliant 3D driver to match the proprietary hardware, then that would be brilliant news [about their next gen GPU]. about the zynq idea: it actually doesn't matter if it's "enough". the very fact that free software developers - and people who want to be free software developers - around the world could even _remotely_ consider buying one of these for an affordable price instead of $750 for the present OGP card means that more people can at least begin to try to address the unbelievably wide and very discouraging gap between us and proprietary 3D hardware. the NREs on producing a set of masks are _only_ $250,000 if you are a taiwanese company asking TSMC, but for everyone else they're at least $2 million. the development costs if you use off-the-shelf tools before you even _get_ to the point where you can ask a fab to produce those masks spiral out of control (Mentor Graphics charges something like $250,000 per month or maybe per week per user; NREs for peripheral hard macros can be $50k to $100k each etc. etc.), taking the total development costs in many cases to well above $USD 30 million. and that's excluding all that "proprietary software" which of course is utterly useless without the corresponding hardware but, because of USA Accountancy Rules, where "IP" can be added to the books to increase the value of a company, there's a strong financial disincentive to consider just "givvin it aww away 4 fwee". and here we are with a CPU which could well be around the $25 - $30 mark in large enough volumes, presented with the possibility to say " u all, you proprietary GPU companies and your greed, fear, patent warfare and lack of willingness to collaborate and cooperate". ok maybe not those exact words but you know what i mean :) l. -- ubuntu-devel mailing list ubuntu-devel@lists.ubuntu.com Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-devel
Re: ARM 3D support was Re: [fedora-arm] ARM summit at Plumbers 2011
On 08/23/2011 07:01 PM, omall...@msu.edu wrote: Quoting Gordan Bobic : Unfortunately there is no way I could make it, but on the subject of 3D support on ARM, Luke recently mentioned something that initially seemed outlandish but upon closer examination doesn't seem like a bad idea. As we all know, the state of openness of specifications of commonly used ARM 3D GPUs is at best dire. What has been proposed is a bit radical, but it doesn't actually seem that implausible. Specifically, combining Open Graphics Project (http://wiki.opengraphics.org/tiki-index.php) and the xilinx zynq-7000 or similar (dual core Cortex A9 + FPGA). The idea is to have an OGP GPU in firmware in FPGA. In terms of the power budget, it seems to work relatively sanely considering what it is, and it is as ideal as it gets as far as openness and flexibility goes. I just thought it's worthy of a mention. It does seem outlandish, but it is kind of cool. Is it going to give enough 3d speed? The next gen tegra is supposed to have a 24 core GPU. If you can quantify what "enough 3D speed" means, then perhaps that can be assessed. There really aren't many applications around at the moment to make this an issue. I'd be more interested in it's ability to decode 1080p. Then again - it's FPGA! You can load a different "firmware" depending on whether you need 1080p decoding or 3D rendering, or some other kind of specialized DSP offload with only bare minimal VGA. :) Personally, I think OGP would be worth it even if just for the fact that we would no longer have to beg (in vain) the vendors for decent drivers or published specs. The added flexibility on top is just a "free extra". :) Gordan -- ubuntu-devel mailing list ubuntu-devel@lists.ubuntu.com Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-devel
ARM 3D support was Re: [fedora-arm] ARM summit at Plumbers 2011
Quoting Gordan Bobic : Unfortunately there is no way I could make it, but on the subject of 3D support on ARM, Luke recently mentioned something that initially seemed outlandish but upon closer examination doesn't seem like a bad idea. As we all know, the state of openness of specifications of commonly used ARM 3D GPUs is at best dire. What has been proposed is a bit radical, but it doesn't actually seem that implausible. Specifically, combining Open Graphics Project (http://wiki.opengraphics.org/tiki-index.php) and the xilinx zynq-7000 or similar (dual core Cortex A9 + FPGA). The idea is to have an OGP GPU in firmware in FPGA. In terms of the power budget, it seems to work relatively sanely considering what it is, and it is as ideal as it gets as far as openness and flexibility goes. I just thought it's worthy of a mention. It does seem outlandish, but it is kind of cool. Is it going to give enough 3d speed? The next gen tegra is supposed to have a 24 core GPU. It is probably more sane then my idea of just having a test suite from digital video out -> digital video receiver/capture card to get known test results. Then you could set up a hinted genetic algorithm based on a comparison. It would only work with digital video signals though. -- ubuntu-devel mailing list ubuntu-devel@lists.ubuntu.com Modify settings or unsubscribe at: https://lists.ubuntu.com/mailman/listinfo/ubuntu-devel