[msan] Generalize handleVectorReduceIntrinsic to support Arm NEON add reduction to scalar (#125288)

This generalizes handleVectorReduceIntrinsic to allow intrinsics where
the return type is not the same as the fields. This patch then applies
the generalized handleVectorReduceIntrinsic to support the following Arm
NEON add reduction to scalar intrinsics: llvm.aarch64.neon.{faddv,
saddv, uaddv}.

Updates the tests from #125271

Author: thurstond

llvm/lib/Transforms/Instrumentation/MemorySanitizer.cpp

@@ -3493,11 +3493,15 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
 
   // Instrument generic vector reduction intrinsics
   // by ORing together all their fields.
+  //
+  // The return type does not need to be the same type as the fields
+  // e.g., declare i32 @llvm.aarch64.neon.uaddv.i32.v16i8(<16 x i8>)
   void handleVectorReduceIntrinsic(IntrinsicInst &I) {
     IRBuilder<> IRB(&I);
     Value *S = IRB.CreateOrReduce(getShadow(&I, 0));
+    S = CreateShadowCast(IRB, S, getShadowTy(&I));
     setShadow(&I, S);
-    setOrigin(&I, getOrigin(&I, 0));
+    setOriginForNaryOp(I);
   }
 
   // Instrument vector.reduce.or intrinsic.
@@ -4346,6 +4350,10 @@ struct MemorySanitizerVisitor : public InstVisitor<MemorySanitizerVisitor> {
     case Intrinsic::vector_reduce_add:
     case Intrinsic::vector_reduce_xor:
     case Intrinsic::vector_reduce_mul:
+    // Add reduction to scalar
+    case Intrinsic::aarch64_neon_faddv:
+    case Intrinsic::aarch64_neon_saddv:
+    case Intrinsic::aarch64_neon_uaddv:
       handleVectorReduceIntrinsic(I);
       break;
     case Intrinsic::x86_sse_stmxcsr: