X86 pmovsx/pmovzx ignore the upper half of their inputs.

rdar://problem/6945110


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131493 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 23 insertions, 1 deletions

diff --git a/lib/Transforms/InstCombine/InstCombineCalls.cpp b/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 726105f75d..83653fd6d5 100644
--- a/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -588,6 +588,28 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
     break;
   }
 
+
+  case Intrinsic::x86_sse41_pmovsxbw:
+  case Intrinsic::x86_sse41_pmovsxwd:
+  case Intrinsic::x86_sse41_pmovsxdq:
+  case Intrinsic::x86_sse41_pmovzxbw:
+  case Intrinsic::x86_sse41_pmovzxwd:
+  case Intrinsic::x86_sse41_pmovzxdq: {
+    unsigned VWidth =
+      cast<VectorType>(II->getArgOperand(0)->getType())->getNumElements();
+    unsigned LowHalfElts = VWidth / 2;
+    APInt InputDemandedElts(VWidth, 0);
+    InputDemandedElts = InputDemandedElts.getBitsSet(VWidth, 0, LowHalfElts);
+    APInt UndefElts(VWidth, 0);
+    if (Value *TmpV = SimplifyDemandedVectorElts(II->getArgOperand(0),
+                                                 InputDemandedElts,
+                                                 UndefElts)) {
+      II->setArgOperand(0, TmpV);
+      return II;
+    }
+    break;
+  }
+
   case Intrinsic::ppc_altivec_vperm:
     // Turn vperm(V1,V2,mask) -> shuffle(V1,V2,mask) if mask is a constant.
     if (ConstantVector *Mask = dyn_cast<ConstantVector>(II->getArgOperand(2))) {
diff --git a/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp b/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
index 6e727ce6e3..4c9fed3abc 100644
--- a/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
+++ b/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
@@ -867,7 +867,7 @@ Value *InstCombiner::SimplifyDemandedVectorElts(Value *V, APInt DemandedElts,
   if (Depth == 10)
     return 0;
 
-  // If multiple users are using the root value, procede with
+  // If multiple users are using the root value, proceed with
   // simplification conservatively assuming that all elements
   // are needed.
   if (!V->hasOneUse()) {