// 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 <4 x i32> @_Z17ReturnOnesSwizzleu11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnOnesSwizzle(int4x4 A) {
    return A._11_12_13_14;
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z18ReturnOnesSwizzle2u11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnOnesSwizzle2(int4x4 A) {
    return A._11_21_31_41;
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z17ReturnTwosSwizzleu11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnTwosSwizzle(int4x4 A) {
    return A._21_22_23_24;
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z18ReturnTwosSwizzle2u11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnTwosSwizzle2(int4x4 A) {
    return A._12_22_32_42;
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z19ReturnThreesSwizzleu11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnThreesSwizzle(int4x4 A) {
    return A._31_32_33_34;
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z20ReturnThreesSwizzle2u11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnThreesSwizzle2(int4x4 A) {
    return A._13_23_33_43;
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z18ReturnFoursSwizzleu11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnFoursSwizzle(int4x4 A) {
    return A._41_42_43_44;
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z19ReturnFoursSwizzle2u11matrix_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:%.*]] = shufflevector <16 x i32> [[TMP0]], <16 x i32> poison, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
// CHECK-NEXT:    ret <4 x i32> [[TMP1]]
//
int4 ReturnFoursSwizzle2(int4x4 A) {
    return A._14_24_34_44;
}