llvm/test/Transforms/LoopInterchange/confused-dependence.ll

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

;; In the following case, p0 and p1 may alias, so the direction vector must be [* *].
;;
;; void may_alias(float *p0, float *p1) {
;;   for (int i = 0; i < 4; i++)
;;     for (int j = 0; j < 4; j++)
;;       p0[4 * i + j] = p1[4 * j + i];
;; }

define void @may_alias(ptr %p0, ptr %p1) {
; CHECK-LABEL: define void @may_alias(
; CHECK-SAME: ptr [[P0:%.*]], ptr [[P1:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*]]:
; CHECK-NEXT:    br label %[[FOR_I_HEADER:.*]]
; CHECK:       [[FOR_I_HEADER]]:
; CHECK-NEXT:    [[I:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[I_INC:%.*]], %[[FOR_I_LATCH:.*]] ]
; CHECK-NEXT:    br label %[[FOR_J:.*]]
; CHECK:       [[FOR_J]]:
; CHECK-NEXT:    [[J:%.*]] = phi i32 [ 0, %[[FOR_I_HEADER]] ], [ [[J_INC:%.*]], %[[FOR_J]] ]
; CHECK-NEXT:    [[IDX_0:%.*]] = getelementptr inbounds [4 x [4 x float]], ptr [[P0]], i32 0, i32 [[J]], i32 [[I]]
; CHECK-NEXT:    [[IDX_1:%.*]] = getelementptr inbounds [4 x [4 x float]], ptr [[P1]], i32 0, i32 [[I]], i32 [[J]]
; CHECK-NEXT:    [[TMP0:%.*]] = load float, ptr [[IDX_0]], align 4
; CHECK-NEXT:    store float [[TMP0]], ptr [[IDX_1]], align 4
; CHECK-NEXT:    [[J_INC]] = add nuw nsw i32 [[J]], 1
; CHECK-NEXT:    [[CMP_J:%.*]] = icmp slt i32 [[J_INC]], 4
; CHECK-NEXT:    br i1 [[CMP_J]], label %[[FOR_J]], label %[[FOR_I_LATCH]]
; CHECK:       [[FOR_I_LATCH]]:
; CHECK-NEXT:    [[I_INC]] = add nuw nsw i32 [[I]], 1
; CHECK-NEXT:    [[CMP_I:%.*]] = icmp slt i32 [[I_INC]], 4
; CHECK-NEXT:    br i1 [[CMP_I]], label %[[FOR_I_HEADER]], label %[[EXIT:.*]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    ret void
;
entry:
  br label %for.i.header

for.i.header:
  %i = phi i32 [ 0, %entry ], [ %i.inc, %for.i.latch ]
  br label %for.j

for.j:
  %j = phi i32 [ 0, %for.i.header ], [ %j.inc, %for.j ]
  %idx.0 = getelementptr inbounds [4 x [4 x float]], ptr %p0, i32 0, i32 %j, i32 %i
  %idx.1 = getelementptr inbounds [4 x [4 x float]], ptr %p1, i32 0, i32 %i, i32 %j
  %0 = load float, ptr %idx.0, align 4
  store float %0, ptr %idx.1, align 4
  %j.inc = add nuw nsw i32 %j, 1
  %cmp.j = icmp slt i32 %j.inc, 4
  br i1 %cmp.j, label %for.j, label %for.i.latch

for.i.latch:
  %i.inc = add nuw nsw i32 %i, 1
  %cmp.i = icmp slt i32 %i.inc, 4
  br i1 %cmp.i, label %for.i.header, label %exit

exit:
  ret void
}