// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 6
// RUN: %clang_cc1 -fenable-matrix -triple arm64-apple-macosx %s -emit-llvm -disable-llvm-passes -o - | FileCheck %s

typedef float float3 __attribute__((ext_vector_type(3)));
struct Vec3 {
  union {
    struct {
      float x;
      float y;
      float z;
    };
    float vec __attribute__((ext_vector_type(3)));
  };
};

// CHECK-LABEL: define i128 @add(
// CHECK-SAME: i128 [[A_COERCE:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    [[RETVAL:%.*]] = alloca [[STRUCT_VEC3:%.*]], align 16
// CHECK-NEXT:    [[A:%.*]] = alloca [[STRUCT_VEC3]], align 16
// CHECK-NEXT:    [[COERCE_DIVE:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[A]], i32 0, i32 0
// CHECK-NEXT:    store i128 [[A_COERCE]], ptr [[COERCE_DIVE]], align 16
// CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[A]], i32 0, i32 0
// CHECK-NEXT:    [[LOADVECN:%.*]] = load <4 x float>, ptr [[TMP0]], align 16
// CHECK-NEXT:    [[EXTRACTVEC:%.*]] = shufflevector <4 x float> [[LOADVECN]], <4 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>
// CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[A]], i32 0, i32 0
// CHECK-NEXT:    [[LOADVECN1:%.*]] = load <4 x float>, ptr [[TMP1]], align 16
// CHECK-NEXT:    [[EXTRACTVEC2:%.*]] = shufflevector <4 x float> [[LOADVECN1]], <4 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>
// CHECK-NEXT:    [[ADD:%.*]] = fadd <3 x float> [[EXTRACTVEC]], [[EXTRACTVEC2]]
// CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT:    [[EXTRACTVEC3:%.*]] = shufflevector <3 x float> [[ADD]], <3 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK-NEXT:    store <4 x float> [[EXTRACTVEC3]], ptr [[TMP2]], align 16
// CHECK-NEXT:    [[COERCE_DIVE4:%.*]] = getelementptr inbounds nuw [[STRUCT_VEC3]], ptr [[RETVAL]], i32 0, i32 0
// CHECK-NEXT:    [[TMP3:%.*]] = load i128, ptr [[COERCE_DIVE4]], align 16
// CHECK-NEXT:    ret i128 [[TMP3]]
//
struct Vec3 add(struct Vec3 a) {
  struct Vec3 res;
  res.vec = a.vec + a.vec;
  return res;
}