[msan] Add handlePairwiseShadowOrIntrinsic and use it to handle Arm NEON pairwise add

This adds a function, handlePairwiseShadowOrIntrinsic, that propagates shadow for 1- or 2-vector intrinsics that combine adjacent fields, by OR'ing the corresponding adjacent shadows. It then applies it to Arm NEON pairwise add: llvm.aarch64.neon.{addhn, raddhn} (currently incorrectly handled) and llvm.aarch64.neon.{saddlp, uaddlp} (currently suboptimally handled).

Updates the tests from #125820

Author: thurstond

llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp

@@ -2602,6 +2602,57 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
     SC.Done(&I);
   }
 
+  /// Propagate shadow for 1- or 2-vector intrinsics that combine adjacent
+  /// fields.
+  ///
+  /// e.g., <2 x i32> @llvm.aarch64.neon.saddlp.v2i32.v4i16(<4 x i16>)
+  ///       <16 x i8> @llvm.aarch64.neon.addp.v16i8(<16 x i8>, <16 x i8>)
+  ///
+  /// TODO: adapt this function to handle horizontal add/sub?
+  void handlePairwiseShadowOrIntrinsic(IntrinsicInst &I) {
+    assert(I.arg_size() == 1 || I.arg_size() == 2);
+
+    assert(I.getType()->isVectorTy());
+    assert(I.getArgOperand(0)->getType()->isVectorTy());
+
+    FixedVectorType *ParamType =
+        cast<FixedVectorType>(I.getArgOperand(0)->getType());
+    if (I.arg_size() == 2)
+      assert(ParamType == cast<FixedVectorType>(I.getArgOperand(1)->getType()));
+    FixedVectorType *ReturnType = cast<FixedVectorType>(I.getType());
+    assert(ParamType->getNumElements() * I.arg_size() ==
+           2 * ReturnType->getNumElements());
+
+    IRBuilder<> IRB(&I);
+    unsigned Width = ParamType->getNumElements() * I.arg_size();
+
+    // Horizontal OR of shadow
+    SmallVector<int, 8> EvenMask;
+    SmallVector<int, 8> OddMask;
+    for (unsigned X = 0; X < Width; X += 2) {
+      EvenMask.append(1, X);
+      OddMask.append(1, X + 1);
+    }
+
+    Value *EvenShadow;
+    Value *OddShadow;
+    if (I.arg_size() == 2) {
+      EvenShadow =
+          IRB.CreateShuffleVector(getShadow(&I, 0), getShadow(&I, 1), EvenMask);
+      OddShadow =
+          IRB.CreateShuffleVector(getShadow(&I, 0), getShadow(&I, 1), OddMask);
+    } else {
+      EvenShadow = IRB.CreateShuffleVector(getShadow(&I, 0), EvenMask);
+      OddShadow = IRB.CreateShuffleVector(getShadow(&I, 0), OddMask);
+    }
+
+    Value *OrShadow = IRB.CreateOr(EvenShadow, OddShadow);
+    OrShadow = CreateShadowCast(IRB, OrShadow, getShadowTy(&I));
+
+    setShadow(&I, OrShadow);
+    setOriginForNaryOp(I);
+  }
+
   void visitFNeg(UnaryOperator &I) { handleShadowOr(I); }
 
   // Handle multiplication by constant.
@@ -4781,6 +4832,17 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
       setOrigin(&I, getCleanOrigin());
       break;
 
+    // Add Pairwise
+    case Intrinsic::aarch64_neon_addp:
+    // Floating-point Add Pairwise
+    case Intrinsic::aarch64_neon_faddp:
+    // Add Long Pairwise
+    case Intrinsic::aarch64_neon_saddlp:
+    case Intrinsic::aarch64_neon_uaddlp: {
+      handlePairwiseShadowOrIntrinsic(I);
+      break;
+    }
+
     case Intrinsic::aarch64_neon_st1x2:
     case Intrinsic::aarch64_neon_st1x3:
     case Intrinsic::aarch64_neon_st1x4: