// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 6

// RUN: %clang_cc1 -std=hlsl202x -finclude-default-header -x hlsl -triple \
// RUN:   dxil-pc-shadermodel6.3-library %s -fnative-half-type \
// RUN:   -emit-llvm -disable-llvm-passes -o - | FileCheck %s

// CHECK-LABEL: define hidden noundef i32 @_Z8Return11u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 0
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return11(int4x4 A) {
    return A._11;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return12u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 4
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return12(int4x4 A) {
    return A._12;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return13u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 8
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return13(int4x4 A) {
    return A._13;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return14u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 12
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return14(int4x4 A) {
    return A._14;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return21u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 1
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return21(int4x4 A) {
    return A._21;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return22u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 5
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return22(int4x4 A) {
    return A._22;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return23u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 9
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return23(int4x4 A) {
    return A._23;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return24u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 13
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return24(int4x4 A) {
    return A._24;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return31u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 2
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return31(int4x4 A) {
    return A._31;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return32u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 6
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return32(int4x4 A) {
    return A._32;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return33u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 10
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return33(int4x4 A) {
    return A._33;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return34u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 14
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return34(int4x4 A) {
    return A._34;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return41u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 3
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return41(int4x4 A) {
    return A._41;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return42u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 7
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return42(int4x4 A) {
    return A._42;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return43u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 11
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return43(int4x4 A) {
    return A._43;
}

// CHECK-LABEL: define hidden noundef i32 @_Z8Return44u11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[A:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[A_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[A]], ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[A_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 15
// CHECK-NEXT:    ret i32 [[TMP1]]
//
int Return44(int4x4 A) {
    return A._44;
}