// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
// RUN: %clang_cc1 -finclude-default-header -triple dxil-pc-shadermodel6.3-library %s \
// RUN:  -emit-llvm -disable-llvm-passes -o - | \
// RUN:  FileCheck %s --check-prefixes=CHECK


// CHECK-LABEL: define hidden noundef <2 x i32> @_Z20test_AddUint64_uint2Dv2_jS_(
// CHECK-SAME: <2 x i32> noundef [[A:%.*]], <2 x i32> noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca <2 x i32>, align 8
// CHECK-NEXT:    [[B_ADDR:%.*]] = alloca <2 x i32>, align 8
// CHECK-NEXT:    store <2 x i32> [[A]], ptr [[A_ADDR]], align 8
// CHECK-NEXT:    store <2 x i32> [[B]], ptr [[B_ADDR]], align 8
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x i32>, ptr [[A_ADDR]], align 8
// CHECK-NEXT:    [[TMP1:%.*]] = load <2 x i32>, ptr [[B_ADDR]], align 8
// CHECK-NEXT:    [[LOWA:%.*]] = extractelement <2 x i32> [[TMP0]], i64 0
// CHECK-NEXT:    [[HIGHA:%.*]] = extractelement <2 x i32> [[TMP0]], i64 1
// CHECK-NEXT:    [[LOWB:%.*]] = extractelement <2 x i32> [[TMP1]], i64 0
// CHECK-NEXT:    [[HIGHB:%.*]] = extractelement <2 x i32> [[TMP1]], i64 1
// CHECK-NEXT:    [[TMP2:%.*]] = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 [[LOWA]], i32 [[LOWB]])
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { i32, i1 } [[TMP2]], 1
// CHECK-NEXT:    [[TMP4:%.*]] = extractvalue { i32, i1 } [[TMP2]], 0
// CHECK-NEXT:    [[CARRYZEXT:%.*]] = zext i1 [[TMP3]] to i32
// CHECK-NEXT:    [[HIGHSUM:%.*]] = add i32 [[HIGHA]], [[HIGHB]]
// CHECK-NEXT:    [[HIGHSUMPLUSCARRY:%.*]] = add i32 [[HIGHSUM]], [[CARRYZEXT]]
// CHECK-NEXT:    [[HLSL_ADDUINT64_UPTO0:%.*]] = insertelement <2 x i32> poison, i32 [[TMP4]], i64 0
// CHECK-NEXT:    [[HLSL_ADDUINT64:%.*]] = insertelement <2 x i32> [[HLSL_ADDUINT64_UPTO0]], i32 [[HIGHSUMPLUSCARRY]], i64 1
// CHECK-NEXT:    ret <2 x i32> [[HLSL_ADDUINT64]]
//
uint2 test_AddUint64_uint2(uint2 a, uint2 b) {
  return AddUint64(a, b);
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z20test_AddUint64_uint4Dv4_jS_(
// CHECK-SAME: <4 x i32> noundef [[A:%.*]], <4 x i32> noundef [[B:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca <4 x i32>, align 16
// CHECK-NEXT:    [[B_ADDR:%.*]] = alloca <4 x i32>, align 16
// CHECK-NEXT:    store <4 x i32> [[A]], ptr [[A_ADDR]], align 16
// CHECK-NEXT:    store <4 x i32> [[B]], ptr [[B_ADDR]], align 16
// CHECK-NEXT:    [[TMP0:%.*]] = load <4 x i32>, ptr [[A_ADDR]], align 16
// CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, ptr [[B_ADDR]], align 16
// CHECK-NEXT:    [[LOWA:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <2 x i32> <i32 0, i32 2>
// CHECK-NEXT:    [[HIGHA:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <2 x i32> <i32 1, i32 3>
// CHECK-NEXT:    [[LOWB:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> poison, <2 x i32> <i32 0, i32 2>
// CHECK-NEXT:    [[HIGHB:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> poison, <2 x i32> <i32 1, i32 3>
// CHECK-NEXT:    [[TMP2:%.*]] = call { <2 x i32>, <2 x i1> } @llvm.uadd.with.overflow.v2i32(<2 x i32> [[LOWA]], <2 x i32> [[LOWB]])
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { <2 x i32>, <2 x i1> } [[TMP2]], 1
// CHECK-NEXT:    [[TMP4:%.*]] = extractvalue { <2 x i32>, <2 x i1> } [[TMP2]], 0
// CHECK-NEXT:    [[CARRYZEXT:%.*]] = zext <2 x i1> [[TMP3]] to <2 x i32>
// CHECK-NEXT:    [[HIGHSUM:%.*]] = add <2 x i32> [[HIGHA]], [[HIGHB]]
// CHECK-NEXT:    [[HIGHSUMPLUSCARRY:%.*]] = add <2 x i32> [[HIGHSUM]], [[CARRYZEXT]]
// CHECK-NEXT:    [[HLSL_ADDUINT64:%.*]] = shufflevector <2 x i32> [[TMP4]], <2 x i32> [[HIGHSUMPLUSCARRY]], <4 x i32> <i32 0, i32 2, i32 1, i32 3>
// CHECK-NEXT:    ret <4 x i32> [[HLSL_ADDUINT64]]
//
uint4 test_AddUint64_uint4(uint4 a, uint4 b) {
  return AddUint64(a, b);
}