X86: Turn mul of <4 x i32> into pmuludq when no SSE4.1 is available.
[oota-llvm.git] / test / CodeGen / X86 / mmx-shift.ll
2010-09-30 Dale JohannesenMassive rewrite of MMX:
2009-09-08 Dan GohmanEliminate more uses of llvm-as and llvm-dis.
2008-05-04 Evan ChengSelect vector shift with non-immediate i32 shift amount...
2008-05-03 Evan ChengAdd separate intrinsics for MMX / SSE shifts with i32...
2008-03-21 Evan ChengUndo 48570. Correctly match mmx shift instructions...
2008-03-19 Evan ChengAdd intrinsics to match mmx shift builtin's with immedi...