X86: Match pmin/pmax as a target specific dag combine. This occurs during vectorization.
[oota-llvm.git] / test / CodeGen / X86 / narrow_op-1.ll
2009-09-08 Dan GohmanEliminate more uses of llvm-as and llvm-dis.
2009-05-28 Evan ChengAdded optimization that narrow load / op / store and...