Evan Cheng 9f27046dc9 - movlp{s|d} and movhp{s|d} support. ...

- Normalize shuffle nodes so result vector lower half elements come from the
  first vector, the rest come from the second vector. (Except for the
  exceptions :-).
- Other minor fixes.

llvm-svn: 27474

2006-04-06 23:23:56 +00:00

..

Analysis

Move this to lib/Analysis.

2006-04-06 22:58:58 +00:00

AsmParser

…

Bytecode

…

CodeGen

1. If both vector operands of a vector_shuffle are undef, turn it into an undef.

2006-04-06 23:20:43 +00:00

Debugger

…

ExecutionEngine

…

Linker

…

Support

…

System

…

Target

- movlp{s|d} and movhp{s|d} support.

2006-04-06 23:23:56 +00:00

Transforms

Lower vperm(x,y, mask) -> shuffle(x,y,mask) if mask is constant. This allows

2006-04-06 19:19:17 +00:00

VMCore

Move this to lib/Analysis.

2006-04-06 22:58:58 +00:00

Makefile

…