Shouldn’t the focus be on power rather than raw performance? In terms of the work that has to be performed for rendering web pages, GPUs should be more power efficient than CPUs, especially with some of the mobile GPU architectures. There is a question of whether all of the layers of abstraction above actually pointing the GPU at a command buffer negate this advantage, but if they do then the goal should probably be to eliminate them. This is the direction the industry is going in with APIs like Mantle, DX12, Metal, etc.
Cameron > On Nov 12, 2014, at 5:46 PM, Andreas Gal <andr...@mozilla.com> wrote: > > There are easier ways to compare. D2D is something like 40% faster than > software (Bas, is that the right ballpark?). So if you get a 2x+ speedup with > concurrent software rendering, you win. > > Thanks, > > Andreas > >> On Nov 12, 2014, at 12:08 PM, Jack Moffitt <j...@metajack.im> wrote: >> >>>> We should experiment with parallel software rendering. Using skia on >>>> many cores might be faster than using D2D in practice, for example. >>> >>> Glad to hear you say that, because the first part of that experiment >>> (parallel CPU rendering) is already done and on by default in Servo's master >>> branch. :) All we'd need is the D2D backend to compare it to. >> >> I don't know that there is a blocker to using other Azure backends >> right now, but it doesn't work for some reason. I'm not sure if anyone >> has investigated yet. Obivously for Direct2D there is the matter of >> getting a Windows port up and running. >> >> jack. > > _______________________________________________ > dev-servo mailing list > dev-servo@lists.mozilla.org > https://lists.mozilla.org/listinfo/dev-servo _______________________________________________ dev-servo mailing list dev-servo@lists.mozilla.org https://lists.mozilla.org/listinfo/dev-servo
