[clang] [CIR][AArch64] Upstream addition-across-vector (incl. widening) NEON builtins (PR #193396)

[Vicky Nguyen via cfe-commits]

================
@@ -6576,65 +6569,32 @@ Value *CodeGenFunction::EmitAArch64BuiltinExpr(unsigned BuiltinID,
     Value *RHS = Builder.CreateBitCast(Ops[1], DoubleTy);
     return Builder.CreateFMul(Ops[0], RHS);
   }
-  case NEON::BI__builtin_neon_vaddlv_u8: {
-    Int = Intrinsic::aarch64_neon_uaddlv;
-    Ty = Int32Ty;
-    VTy = llvm::FixedVectorType::get(Int8Ty, 8);
-    llvm::Type *Tys[2] = {Ty, VTy};
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
-    return Builder.CreateTrunc(Ops[0], Int16Ty);
-  }
-  case NEON::BI__builtin_neon_vaddlv_u16: {
-    Int = Intrinsic::aarch64_neon_uaddlv;
-    Ty = Int32Ty;
-    VTy = llvm::FixedVectorType::get(Int16Ty, 4);
-    llvm::Type *Tys[2] = {Ty, VTy};
-    return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
-  }
-  case NEON::BI__builtin_neon_vaddlvq_u8: {
-    Int = Intrinsic::aarch64_neon_uaddlv;
-    Ty = Int32Ty;
-    VTy = llvm::FixedVectorType::get(Int8Ty, 16);
-    llvm::Type *Tys[2] = {Ty, VTy};
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
-    return Builder.CreateTrunc(Ops[0], Int16Ty);
-  }
-  case NEON::BI__builtin_neon_vaddlvq_u16: {
-    Int = Intrinsic::aarch64_neon_uaddlv;
-    Ty = Int32Ty;
-    VTy = llvm::FixedVectorType::get(Int16Ty, 8);
-    llvm::Type *Tys[2] = {Ty, VTy};
-    return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
-  }
-  case NEON::BI__builtin_neon_vaddlv_s8: {
-    Int = Intrinsic::aarch64_neon_saddlv;
-    Ty = Int32Ty;
-    VTy = llvm::FixedVectorType::get(Int8Ty, 8);
-    llvm::Type *Tys[2] = {Ty, VTy};
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
-    return Builder.CreateTrunc(Ops[0], Int16Ty);
-  }
-  case NEON::BI__builtin_neon_vaddlv_s16: {
-    Int = Intrinsic::aarch64_neon_saddlv;
-    Ty = Int32Ty;
-    VTy = llvm::FixedVectorType::get(Int16Ty, 4);
-    llvm::Type *Tys[2] = {Ty, VTy};
-    return EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
-  }
-  case NEON::BI__builtin_neon_vaddlvq_s8: {
-    Int = Intrinsic::aarch64_neon_saddlv;
-    Ty = Int32Ty;
-    VTy = llvm::FixedVectorType::get(Int8Ty, 16);
-    llvm::Type *Tys[2] = {Ty, VTy};
-    Ops[0] = EmitNeonCall(CGM.getIntrinsic(Int, Tys), Ops, "vaddlv");
-    return Builder.CreateTrunc(Ops[0], Int16Ty);
-  }
+  case NEON::BI__builtin_neon_vaddlv_u8:
+  case NEON::BI__builtin_neon_vaddlvq_u8:
+  case NEON::BI__builtin_neon_vaddlv_u16:
+  case NEON::BI__builtin_neon_vaddlvq_u16:
+  case NEON::BI__builtin_neon_vaddlv_s8:
+  case NEON::BI__builtin_neon_vaddlvq_s8:
+  case NEON::BI__builtin_neon_vaddlv_s16:
   case NEON::BI__builtin_neon_vaddlvq_s16: {
-    Int = Intrinsic::aarch64_neon_saddlv;
+    switch (BuiltinID) {
+    case NEON::BI__builtin_neon_vaddlv_u8:
+    case NEON::BI__builtin_neon_vaddlvq_u8:
+    case NEON::BI__builtin_neon_vaddlv_u16:
+    case NEON::BI__builtin_neon_vaddlvq_u16:
+      Int = Intrinsic::aarch64_neon_uaddlv;
+      break;
+    default:
+      Int = Intrinsic::aarch64_neon_saddlv;
+      break;
+    }
----------------
iamvickynguyen wrote:

Got it! I split the signed and unsigned case groups.

https://github.com/llvm/llvm-project/pull/193396