; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
; RUN: opt -passes=gvn -S %s | FileCheck %s

define void @redundant_unstrided_load(ptr %src) {
; CHECK-LABEL: define void @redundant_unstrided_load(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[SRC_OFFSET:%.*]] = getelementptr inbounds double, ptr [[SRC]], i32 8
; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 4, i1 false, i32 4, i32 2)
; CHECK-NEXT:    call void @llvm.matrix.column.major.store.v8f64.i32(<8 x double> [[L]], ptr [[SRC]], i32 4, i1 false, i32 4, i32 2)
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    ret void
;
entry:
  %src.offset = getelementptr inbounds double, ptr %src, i32 8
  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 4, i1 false, i32 4, i32 2)
  call void @llvm.matrix.column.major.store.v8f64(<8 x double> %l, ptr %src, i32 4, i1 false, i32 4, i32 2)
  %l.2 = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 4, i1 false, i32 4, i32 2)
  call void @use(<8 x double> %l)
  call void @use(<8 x double> %l.2)
  ret void
}

define void @redundant_unstrided_load_non_matrix_store(ptr %src) {
; CHECK-LABEL: define void @redundant_unstrided_load_non_matrix_store(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[SRC_OFFSET:%.*]] = getelementptr inbounds double, ptr [[SRC]], i32 1
; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 4, i1 false, i32 4, i32 2)
; CHECK-NEXT:    store double 4.200000e+01, ptr [[SRC]], align 8
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    ret void
;
entry:
  %src.offset = getelementptr inbounds double, ptr %src, i32 1
  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 4, i1 false, i32 4, i32 2)
  store double 42.0, ptr %src
  %l.2 = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 4, i1 false, i32 4, i32 2)
  call void @use(<8 x double> %l)
  call void @use(<8 x double> %l.2)
  ret void
}

define void @redundant_strided_load(ptr %src) {
; CHECK-LABEL: define void @redundant_strided_load(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[SRC_OFFSET:%.*]] = getelementptr inbounds double, ptr [[SRC]], i32 16
; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 8, i1 false, i32 4, i32 2)
; CHECK-NEXT:    call void @llvm.matrix.column.major.store.v8f64.i32(<8 x double> [[L]], ptr [[SRC]], i32 8, i1 false, i32 4, i32 2)
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    ret void
;
entry:
  %src.offset = getelementptr inbounds double, ptr %src, i32 16
  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 8, i1 false, i32 4, i32 2)
  call void @llvm.matrix.column.major.store.v8f64(<8 x double> %l, ptr %src, i32 8, i1 false, i32 4, i32 2)
  %l.2 = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 8, i1 false, i32 4, i32 2)
  call void @use(<8 x double> %l)
  call void @use(<8 x double> %l.2)
  ret void

}

define void @redundant_strided_load_non_matrix_store(ptr %src) {
; CHECK-LABEL: define void @redundant_strided_load_non_matrix_store(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[SRC_OFFSET:%.*]] = getelementptr inbounds double, ptr [[SRC]], i32 16
; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC_OFFSET]], i32 8, i1 false, i32 4, i32 2)
; CHECK-NEXT:    store double 4.200000e+01, ptr [[SRC]], align 8
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    ret void
;
entry:
  %src.offset = getelementptr inbounds double, ptr %src, i32 16
  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 8, i1 false, i32 4, i32 2)
  store double 42.0, ptr %src
  %l.2 = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src.offset, i32 8, i1 false, i32 4, i32 2)
  call void @use(<8 x double> %l)
  call void @use(<8 x double> %l.2)
  ret void
}

define void @repeat_load_dimension_change_project(ptr %src) {
; CHECK-LABEL: define void @repeat_load_dimension_change_project(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC]], i32 4, i1 false, i32 4, i32 2)
; CHECK-NEXT:    [[L_2:%.*]] = call <9 x double> @llvm.matrix.column.major.load.v9f64.i32(ptr [[SRC]], i32 3, i1 false, i32 3, i32 3)
; CHECK-NEXT:    [[L_3:%.*]] = shufflevector <9 x double> [[L_2]], <9 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    call void @use(<8 x double> [[L_3]])
; CHECK-NEXT:    ret void
;
entry:
  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src, i32 4, i1 false, i32 4, i32 2)
  %l.2 = call <9 x double> @llvm.matrix.column.major.load.v9f64.i32(ptr %src, i32 3, i1 false, i32 3, i32 3)
  %l.3 = shufflevector <9 x double> %l.2, <9 x double> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  call void @use(<8 x double> %l)
  call void @use(<8 x double> %l.3)
  ret void
}

define void @repeat_load_dimension_change_shuffle(ptr %src) {
; CHECK-LABEL: define void @repeat_load_dimension_change_shuffle(
; CHECK-SAME: ptr [[SRC:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[L:%.*]] = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr [[SRC]], i32 4, i1 false, i32 4, i32 2)
; CHECK-NEXT:    [[L_2:%.*]] = call <9 x double> @llvm.matrix.column.major.load.v9f64.i32(ptr [[SRC]], i32 3, i1 false, i32 3, i32 3)
; CHECK-NEXT:    [[L_3:%.*]] = shufflevector <9 x double> [[L_2]], <9 x double> zeroinitializer, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; CHECK-NEXT:    call void @use(<8 x double> [[L]])
; CHECK-NEXT:    call void @use(<8 x double> [[L_3]])
; CHECK-NEXT:    ret void
;
entry:
  %l = call <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr %src, i32 4, i1 false, i32 4, i32 2)
  %l.2 = call <9 x double> @llvm.matrix.column.major.load.v9f64.i32(ptr %src, i32 3, i1 false, i32 3, i32 3)
  %l.3 = shufflevector <9 x double> %l.2, <9 x double> zeroinitializer, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
  call void @use(<8 x double> %l)
  call void @use(<8 x double> %l.3)
  ret void
}

declare <8 x double> @llvm.matrix.column.major.load.v8f64.i32(ptr, i32, i1, i32, i32)
declare <9 x double> @llvm.matrix.column.major.load.v9f64.i32(ptr, i32, i1, i32, i32)
declare void @llvm.matrix.column.major.store.v8f64.i32(<8 x double>, ptr, i32, i1, i32, i32)
declare void @use(<8 x double>)