On Wed, 09 May 2012 08:46:30 -0700, Ian Romanick <i...@freedesktop.org> wrote: > On 05/08/2012 05:59 PM, Eric Anholt wrote: > > Total instructions: 261582 -> 261316 > > 135/2147 programs affected (6.3%) > > 36752 -> 36486 instructions in affected programs (0.7% reduction) > > > > This excludes a tropics shader that now gets 16-wide mode and throws > > off the numbers. 5 shaders are hurt: two extra MOVs in 4 tropics > > shaders it looks like because we don't split register names according > > to independent webs, and one gstreamer shader where it looks like > > try_rewrite_rhs_to_dst() is falling on its face. > > > > This should also help avoid a regression in VSes from idr's ARB > > programs to GLSL work. > > Sort of, but not really. It seems to change cases like
[...] Yeah, we seriously need to do coalescing in the VS. One thing related to this failure that I'd thought about was doing pushing of swizzles down expression trees at the IR level: (mul a, b).y -> (mul a.y, b.y). It would tell this dead code elimination a lot more about what was dead, and it should avoid the failure you highlighted for some expressions.
pgpPzZYN8VH4b.pgp
Description: PGP signature
_______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
