// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 6
// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.7-library -disable-llvm-passes -emit-llvm -finclude-default-header -o - %s | FileCheck %s

// CHECK-LABEL: define hidden noundef nofpclass(nan inf) <4 x float> @_Z24getFloatVecMatrixDynamicu11matrix_typeILm4ELm4EfEi(
// CHECK-SAME: <16 x float> noundef nofpclass(nan inf) [[M:%.*]], i32 noundef [[INDEX:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [4 x <4 x float>], align 4
// CHECK-NEXT:    [[INDEX_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT:    store <16 x float> [[M]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    store i32 [[INDEX]], ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = load <16 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP2:%.*]] = add i32 0, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <16 x float> [[TMP1]], i32 [[TMP2]]
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <4 x float> poison, float [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[TMP3:%.*]] = add i32 4, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM1:%.*]] = extractelement <16 x float> [[TMP1]], i32 [[TMP3]]
// CHECK-NEXT:    [[MATRIX_ROW_INS2:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS]], float [[MATRIX_ELEM1]], i32 1
// CHECK-NEXT:    [[TMP4:%.*]] = add i32 8, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM3:%.*]] = extractelement <16 x float> [[TMP1]], i32 [[TMP4]]
// CHECK-NEXT:    [[MATRIX_ROW_INS4:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS2]], float [[MATRIX_ELEM3]], i32 2
// CHECK-NEXT:    [[TMP5:%.*]] = add i32 12, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM5:%.*]] = extractelement <16 x float> [[TMP1]], i32 [[TMP5]]
// CHECK-NEXT:    [[MATRIX_ROW_INS6:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS4]], float [[MATRIX_ELEM5]], i32 3
// CHECK-NEXT:    ret <4 x float> [[MATRIX_ROW_INS6]]
//
float4 getFloatVecMatrixDynamic(float4x4 M, int index) {
    return M[index];
}

// CHECK-LABEL: define hidden noundef nofpclass(nan inf) float @_Z27getFloatScalarMatrixDynamicu11matrix_typeILm2ELm1EfEi(
// CHECK-SAME: <2 x float> noundef nofpclass(nan inf) [[M:%.*]], i32 noundef [[INDEX:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [1 x <2 x float>], align 4
// CHECK-NEXT:    [[INDEX_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT:    store <2 x float> [[M]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    store i32 [[INDEX]], ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = load <2 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP2:%.*]] = add i32 0, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <2 x float> [[TMP1]], i32 [[TMP2]]
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <1 x float> poison, float [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[CAST_VTRUNC:%.*]] = extractelement <1 x float> [[MATRIX_ROW_INS]], i32 0
// CHECK-NEXT:    ret float [[CAST_VTRUNC]]
//
float getFloatScalarMatrixDynamic(float2x1 M, int index) {
    return M[index];
}

// CHECK-LABEL: define hidden noundef nofpclass(nan inf) float @_Z28getFloatScalarMatrixConstantu11matrix_typeILm2ELm1EfE(
// CHECK-SAME: <2 x float> noundef nofpclass(nan inf) [[M:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [1 x <2 x float>], align 4
// CHECK-NEXT:    store <2 x float> [[M]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <2 x float> [[TMP0]], i32 0
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <1 x float> poison, float [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[CAST_VTRUNC:%.*]] = extractelement <1 x float> [[MATRIX_ROW_INS]], i32 0
// CHECK-NEXT:    ret float [[CAST_VTRUNC]]
//
float getFloatScalarMatrixConstant(float2x1 M) {
    return M[0];
}

// CHECK-LABEL: define hidden noundef nofpclass(nan inf) float @_Z29getFloatScalarMatrixConstant2u11matrix_typeILm2ELm1EfE(
// CHECK-SAME: <2 x float> noundef nofpclass(nan inf) [[M:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [1 x <2 x float>], align 4
// CHECK-NEXT:    store <2 x float> [[M]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <2 x float> [[TMP0]], i32 1
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <1 x float> poison, float [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[CAST_VTRUNC:%.*]] = extractelement <1 x float> [[MATRIX_ROW_INS]], i32 0
// CHECK-NEXT:    ret float [[CAST_VTRUNC]]
//
float getFloatScalarMatrixConstant2(float2x1 M) {
    return M[1];
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z19getIntMatrixDynamicu11matrix_typeILm4ELm4EiEi(
// CHECK-SAME: <16 x i32> noundef [[M:%.*]], i32 noundef [[INDEX:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    [[INDEX_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT:    store <16 x i32> [[M]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    store i32 [[INDEX]], ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP2:%.*]] = add i32 0, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <16 x i32> [[TMP1]], i32 [[TMP2]]
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <4 x i32> poison, i32 [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[TMP3:%.*]] = add i32 4, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM1:%.*]] = extractelement <16 x i32> [[TMP1]], i32 [[TMP3]]
// CHECK-NEXT:    [[MATRIX_ROW_INS2:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS]], i32 [[MATRIX_ELEM1]], i32 1
// CHECK-NEXT:    [[TMP4:%.*]] = add i32 8, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM3:%.*]] = extractelement <16 x i32> [[TMP1]], i32 [[TMP4]]
// CHECK-NEXT:    [[MATRIX_ROW_INS4:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS2]], i32 [[MATRIX_ELEM3]], i32 2
// CHECK-NEXT:    [[TMP5:%.*]] = add i32 12, [[TMP0]]
// CHECK-NEXT:    [[MATRIX_ELEM5:%.*]] = extractelement <16 x i32> [[TMP1]], i32 [[TMP5]]
// CHECK-NEXT:    [[MATRIX_ROW_INS6:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS4]], i32 [[MATRIX_ELEM5]], i32 3
// CHECK-NEXT:    ret <4 x i32> [[MATRIX_ROW_INS6]]
//
int4 getIntMatrixDynamic(int4x4 M, int index) {
    return M[index];
}

// CHECK-LABEL: define hidden noundef nofpclass(nan inf) <4 x float> @_Z22AddFloatMatrixConstantu11matrix_typeILm4ELm4EfE(
// CHECK-SAME: <16 x float> noundef nofpclass(nan inf) [[M:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [4 x <4 x float>], align 4
// CHECK-NEXT:    store <16 x float> [[M]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <16 x float> [[TMP0]], i32 0
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <4 x float> poison, float [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM1:%.*]] = extractelement <16 x float> [[TMP0]], i32 4
// CHECK-NEXT:    [[MATRIX_ROW_INS2:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS]], float [[MATRIX_ELEM1]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM3:%.*]] = extractelement <16 x float> [[TMP0]], i32 8
// CHECK-NEXT:    [[MATRIX_ROW_INS4:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS2]], float [[MATRIX_ELEM3]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM5:%.*]] = extractelement <16 x float> [[TMP0]], i32 12
// CHECK-NEXT:    [[MATRIX_ROW_INS6:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS4]], float [[MATRIX_ELEM5]], i32 3
// CHECK-NEXT:    [[TMP1:%.*]] = load <16 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM7:%.*]] = extractelement <16 x float> [[TMP1]], i32 1
// CHECK-NEXT:    [[MATRIX_ROW_INS8:%.*]] = insertelement <4 x float> poison, float [[MATRIX_ELEM7]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM9:%.*]] = extractelement <16 x float> [[TMP1]], i32 5
// CHECK-NEXT:    [[MATRIX_ROW_INS10:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS8]], float [[MATRIX_ELEM9]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM11:%.*]] = extractelement <16 x float> [[TMP1]], i32 9
// CHECK-NEXT:    [[MATRIX_ROW_INS12:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS10]], float [[MATRIX_ELEM11]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM13:%.*]] = extractelement <16 x float> [[TMP1]], i32 13
// CHECK-NEXT:    [[MATRIX_ROW_INS14:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS12]], float [[MATRIX_ELEM13]], i32 3
// CHECK-NEXT:    [[ADD:%.*]] = fadd reassoc nnan ninf nsz arcp afn <4 x float> [[MATRIX_ROW_INS6]], [[MATRIX_ROW_INS14]]
// CHECK-NEXT:    [[TMP2:%.*]] = load <16 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM15:%.*]] = extractelement <16 x float> [[TMP2]], i32 2
// CHECK-NEXT:    [[MATRIX_ROW_INS16:%.*]] = insertelement <4 x float> poison, float [[MATRIX_ELEM15]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM17:%.*]] = extractelement <16 x float> [[TMP2]], i32 6
// CHECK-NEXT:    [[MATRIX_ROW_INS18:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS16]], float [[MATRIX_ELEM17]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM19:%.*]] = extractelement <16 x float> [[TMP2]], i32 10
// CHECK-NEXT:    [[MATRIX_ROW_INS20:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS18]], float [[MATRIX_ELEM19]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM21:%.*]] = extractelement <16 x float> [[TMP2]], i32 14
// CHECK-NEXT:    [[MATRIX_ROW_INS22:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS20]], float [[MATRIX_ELEM21]], i32 3
// CHECK-NEXT:    [[ADD23:%.*]] = fadd reassoc nnan ninf nsz arcp afn <4 x float> [[ADD]], [[MATRIX_ROW_INS22]]
// CHECK-NEXT:    [[TMP3:%.*]] = load <16 x float>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM24:%.*]] = extractelement <16 x float> [[TMP3]], i32 3
// CHECK-NEXT:    [[MATRIX_ROW_INS25:%.*]] = insertelement <4 x float> poison, float [[MATRIX_ELEM24]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM26:%.*]] = extractelement <16 x float> [[TMP3]], i32 7
// CHECK-NEXT:    [[MATRIX_ROW_INS27:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS25]], float [[MATRIX_ELEM26]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM28:%.*]] = extractelement <16 x float> [[TMP3]], i32 11
// CHECK-NEXT:    [[MATRIX_ROW_INS29:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS27]], float [[MATRIX_ELEM28]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM30:%.*]] = extractelement <16 x float> [[TMP3]], i32 15
// CHECK-NEXT:    [[MATRIX_ROW_INS31:%.*]] = insertelement <4 x float> [[MATRIX_ROW_INS29]], float [[MATRIX_ELEM30]], i32 3
// CHECK-NEXT:    [[ADD32:%.*]] = fadd reassoc nnan ninf nsz arcp afn <4 x float> [[ADD23]], [[MATRIX_ROW_INS31]]
// CHECK-NEXT:    ret <4 x float> [[ADD32]]
//
float4 AddFloatMatrixConstant(float4x4 M) {
    return M[0] + M[1] + M[2] + M[3];
}

// CHECK-LABEL: define hidden noundef <4 x i32> @_Z20AddIntMatrixConstantu11matrix_typeILm4ELm4EiE(
// CHECK-SAME: <16 x i32> noundef [[M:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    store <16 x i32> [[M]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = load <16 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <16 x i32> [[TMP0]], i32 0
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <4 x i32> poison, i32 [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM1:%.*]] = extractelement <16 x i32> [[TMP0]], i32 4
// CHECK-NEXT:    [[MATRIX_ROW_INS2:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS]], i32 [[MATRIX_ELEM1]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM3:%.*]] = extractelement <16 x i32> [[TMP0]], i32 8
// CHECK-NEXT:    [[MATRIX_ROW_INS4:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS2]], i32 [[MATRIX_ELEM3]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM5:%.*]] = extractelement <16 x i32> [[TMP0]], i32 12
// CHECK-NEXT:    [[MATRIX_ROW_INS6:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS4]], i32 [[MATRIX_ELEM5]], i32 3
// CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM7:%.*]] = extractelement <16 x i32> [[TMP1]], i32 1
// CHECK-NEXT:    [[MATRIX_ROW_INS8:%.*]] = insertelement <4 x i32> poison, i32 [[MATRIX_ELEM7]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM9:%.*]] = extractelement <16 x i32> [[TMP1]], i32 5
// CHECK-NEXT:    [[MATRIX_ROW_INS10:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS8]], i32 [[MATRIX_ELEM9]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM11:%.*]] = extractelement <16 x i32> [[TMP1]], i32 9
// CHECK-NEXT:    [[MATRIX_ROW_INS12:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS10]], i32 [[MATRIX_ELEM11]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM13:%.*]] = extractelement <16 x i32> [[TMP1]], i32 13
// CHECK-NEXT:    [[MATRIX_ROW_INS14:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS12]], i32 [[MATRIX_ELEM13]], i32 3
// CHECK-NEXT:    [[ADD:%.*]] = add <4 x i32> [[MATRIX_ROW_INS6]], [[MATRIX_ROW_INS14]]
// CHECK-NEXT:    [[TMP2:%.*]] = load <16 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM15:%.*]] = extractelement <16 x i32> [[TMP2]], i32 2
// CHECK-NEXT:    [[MATRIX_ROW_INS16:%.*]] = insertelement <4 x i32> poison, i32 [[MATRIX_ELEM15]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM17:%.*]] = extractelement <16 x i32> [[TMP2]], i32 6
// CHECK-NEXT:    [[MATRIX_ROW_INS18:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS16]], i32 [[MATRIX_ELEM17]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM19:%.*]] = extractelement <16 x i32> [[TMP2]], i32 10
// CHECK-NEXT:    [[MATRIX_ROW_INS20:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS18]], i32 [[MATRIX_ELEM19]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM21:%.*]] = extractelement <16 x i32> [[TMP2]], i32 14
// CHECK-NEXT:    [[MATRIX_ROW_INS22:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS20]], i32 [[MATRIX_ELEM21]], i32 3
// CHECK-NEXT:    [[ADD23:%.*]] = add <4 x i32> [[ADD]], [[MATRIX_ROW_INS22]]
// CHECK-NEXT:    [[TMP3:%.*]] = load <16 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM24:%.*]] = extractelement <16 x i32> [[TMP3]], i32 3
// CHECK-NEXT:    [[MATRIX_ROW_INS25:%.*]] = insertelement <4 x i32> poison, i32 [[MATRIX_ELEM24]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM26:%.*]] = extractelement <16 x i32> [[TMP3]], i32 7
// CHECK-NEXT:    [[MATRIX_ROW_INS27:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS25]], i32 [[MATRIX_ELEM26]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM28:%.*]] = extractelement <16 x i32> [[TMP3]], i32 11
// CHECK-NEXT:    [[MATRIX_ROW_INS29:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS27]], i32 [[MATRIX_ELEM28]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM30:%.*]] = extractelement <16 x i32> [[TMP3]], i32 15
// CHECK-NEXT:    [[MATRIX_ROW_INS31:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS29]], i32 [[MATRIX_ELEM30]], i32 3
// CHECK-NEXT:    [[ADD32:%.*]] = add <4 x i32> [[ADD23]], [[MATRIX_ROW_INS31]]
// CHECK-NEXT:    ret <4 x i32> [[ADD32]]
//
int4 AddIntMatrixConstant(int4x4 M) {
   return M[0] + M[1] + M[2] + M[3];
}

// CHECK-LABEL: define hidden noundef <3 x i1> @_Z23getBoolVecMatrixDynamicu11matrix_typeILm2ELm3EbEi(
// CHECK-SAME: <6 x i1> noundef [[M:%.*]], i32 noundef [[INDEX:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [3 x <2 x i32>], align 4
// CHECK-NEXT:    [[INDEX_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT:    [[TMP0:%.*]] = zext <6 x i1> [[M]] to <6 x i32>
// CHECK-NEXT:    store <6 x i32> [[TMP0]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    store i32 [[INDEX]], ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = load i32, ptr [[INDEX_ADDR]], align 4
// CHECK-NEXT:    [[TMP2:%.*]] = load <6 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP3:%.*]] = add i32 0, [[TMP1]]
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <6 x i32> [[TMP2]], i32 [[TMP3]]
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <3 x i32> poison, i32 [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[TMP4:%.*]] = add i32 2, [[TMP1]]
// CHECK-NEXT:    [[MATRIX_ELEM1:%.*]] = extractelement <6 x i32> [[TMP2]], i32 [[TMP4]]
// CHECK-NEXT:    [[MATRIX_ROW_INS2:%.*]] = insertelement <3 x i32> [[MATRIX_ROW_INS]], i32 [[MATRIX_ELEM1]], i32 1
// CHECK-NEXT:    [[TMP5:%.*]] = add i32 4, [[TMP1]]
// CHECK-NEXT:    [[MATRIX_ELEM3:%.*]] = extractelement <6 x i32> [[TMP2]], i32 [[TMP5]]
// CHECK-NEXT:    [[MATRIX_ROW_INS4:%.*]] = insertelement <3 x i32> [[MATRIX_ROW_INS2]], i32 [[MATRIX_ELEM3]], i32 2
// CHECK-NEXT:    [[LOADEDV:%.*]] = icmp ne <3 x i32> [[MATRIX_ROW_INS4]], zeroinitializer
// CHECK-NEXT:    ret <3 x i1> [[LOADEDV]]
//
bool3 getBoolVecMatrixDynamic(bool2x3 M, int index) {
    return M[index];
}

// CHECK-LABEL: define hidden noundef <4 x i1> @_Z24getBoolVecMatrixConstantu11matrix_typeILm4ELm4EbE(
// CHECK-SAME: <16 x i1> noundef [[M:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = zext <16 x i1> [[M]] to <16 x i32>
// CHECK-NEXT:    store <16 x i32> [[TMP0]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = load <16 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <16 x i32> [[TMP1]], i32 0
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <4 x i32> poison, i32 [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[MATRIX_ELEM1:%.*]] = extractelement <16 x i32> [[TMP1]], i32 4
// CHECK-NEXT:    [[MATRIX_ROW_INS2:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS]], i32 [[MATRIX_ELEM1]], i32 1
// CHECK-NEXT:    [[MATRIX_ELEM3:%.*]] = extractelement <16 x i32> [[TMP1]], i32 8
// CHECK-NEXT:    [[MATRIX_ROW_INS4:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS2]], i32 [[MATRIX_ELEM3]], i32 2
// CHECK-NEXT:    [[MATRIX_ELEM5:%.*]] = extractelement <16 x i32> [[TMP1]], i32 12
// CHECK-NEXT:    [[MATRIX_ROW_INS6:%.*]] = insertelement <4 x i32> [[MATRIX_ROW_INS4]], i32 [[MATRIX_ELEM5]], i32 3
// CHECK-NEXT:    [[LOADEDV:%.*]] = icmp ne <4 x i32> [[MATRIX_ROW_INS6]], zeroinitializer
// CHECK-NEXT:    ret <4 x i1> [[LOADEDV]]
//
bool4 getBoolVecMatrixConstant(bool4x4 M) {
    return M[0];
}

// CHECK-LABEL: define hidden noundef i1 @_Z27getBoolScalarMatrixConstantu11matrix_typeILm3ELm1EbE(
// CHECK-SAME: <3 x i1> noundef [[M:%.*]]) #[[ATTR0]] {
// CHECK-NEXT:  [[ENTRY:.*:]]
// CHECK-NEXT:    %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT:    [[M_ADDR:%.*]] = alloca [1 x <3 x i32>], align 4
// CHECK-NEXT:    [[TMP0:%.*]] = zext <3 x i1> [[M]] to <3 x i32>
// CHECK-NEXT:    store <3 x i32> [[TMP0]], ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[TMP1:%.*]] = load <3 x i32>, ptr [[M_ADDR]], align 4
// CHECK-NEXT:    [[MATRIX_ELEM:%.*]] = extractelement <3 x i32> [[TMP1]], i32 1
// CHECK-NEXT:    [[MATRIX_ROW_INS:%.*]] = insertelement <1 x i32> poison, i32 [[MATRIX_ELEM]], i32 0
// CHECK-NEXT:    [[LOADEDV:%.*]] = icmp ne <1 x i32> [[MATRIX_ROW_INS]], zeroinitializer
// CHECK-NEXT:    [[CAST_VTRUNC:%.*]] = extractelement <1 x i1> [[LOADEDV]], i32 0
// CHECK-NEXT:    ret i1 [[CAST_VTRUNC]]
//
bool getBoolScalarMatrixConstant(bool3x1 M) {
    return M[1];
}