I'm going to guess that he doesn't know anything at all about the OGP, or else he's not very well informed about what we're doing now. Right now, our primary objective is to provide research tools for students and other academics currently stumbling around without a decent simulator.
We're the SESC of GPU simulators. (SESC is a really awful CPU simulator, relatively speaking, but it's cycle-accurate and energy-accurate.) We also want an open architecture for research purposes. That makes us the OpenRISC of GPUs. Actually, more like ZPU. We'd flatter ourselves too much to compare ourselves to OpenSPARC. Sure, there's the theoretical possibility of putting our design into silicon. And maybe, if we get enough help, it'll be really good. But most of our innovations will find their way into other GPUs anyway. We target PowerVR's space not because we expect to compete with them but because it's a reachable goal. He does have a point. The critics of the Pi need to quit pestering those who don't want to make an open GPU and start helping out those who do. Maybe we could really get somewhere with that. Maybe if we tell Upton about our project, he can point people to us so that they will get off his back about it. On Thu, Jan 17, 2013 at 5:57 PM, <[email protected]> wrote: > http://www.zdnet.com/we-**thought-wed-sell-1000-the-** > inside-story-of-the-raspberry-**pi_p4-7000009718/<http://www.zdnet.com/we-thought-wed-sell-1000-the-inside-story-of-the-raspberry-pi_p4-7000009718/> > > ~~~~~~~~~~~~~~~~~~~ > > Upton believes the platform is as open as it can be, given the need of > companies like Broadcom to protect their intellectual property — the > designs of the underlying chip architecture — and also questions the > pragmatic benefits of making the platform this open. > > "It would be lovely if we distributed the source for everything, including > the firmware and the documentation for all of the registers. I'm not quite > sure I can understand the benefit it would bring to the community," he said. > > "We and Broadcom put an enormous amount of effort where we could do that > level of open source. I would like to open more stuff up but it's going to > be tough. If you can't articulate a tangible commercial benefit to the IP > holder, the person who has borrowed money from their IP investor, then you > are on a hiding to nothing. > > "My view is where we've got to is sufficient to give people the goals of > free software, which is for you to have control over what your machine > does." > > He jokes that he is tempted to test the Pi's critics' commitment to having > an open-source GPU. > > "I'm tempted to do a Kickstarter and say 'I'm going to produce an > open-source GPU'. I want $2m from all the people who've criticised me," he > said. > > ~~~~~~~~~~~~~~~~~~~ > > yeah, sounds nice from him... > > yg > > > ______________________________**_________________ > Open-graphics mailing list > [email protected] > http://lists.duskglow.com/**mailman/listinfo/open-graphics<http://lists.duskglow.com/mailman/listinfo/open-graphics> > List service provided by Duskglow Consulting, LLC (www.duskglow.com) -- Timothy Normand Miller, PhD Assistant Professor of Computer Science, Binghamton University http://www.cs.binghamton.edu/~millerti/ Open Graphics Project
_______________________________________________ Open-graphics mailing list [email protected] http://lists.duskglow.com/mailman/listinfo/open-graphics List service provided by Duskglow Consulting, LLC (www.duskglow.com)
