Evan Cheng 5956922a2d Be careful when looking through a vbit_convert. Optimizing this:
(vector_shuffle
  (vbitconvert (vbuildvector (copyfromreg v4f32), 1, v4f32), 4, f32),
  (undef, undef, undef, undef), (0, 0, 0, 0), 4, f32)
to the
  vbitconvert
is a very bad idea.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@30989 91177308-0d34-0410-b5e6-96231b3b80d8
2006-10-16 22:49:37 +00:00
..
2006-10-15 23:27:25 +00:00
2006-10-16 21:50:04 +00:00