llvm/test/Transforms/LoopInterchange/loopnest-with-outer-btc0.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

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

@D = common global [100 x [100 x [100 x i32]]] zeroinitializer

; The outer loop's backedge isn't taken. Check the loop with BTC=0 is considered
; unprofitable, but that we still interchange the two inner loops.
;
;  for(int i=0;i<1;i++)
;    for(int j=0;j<100;j++)
;      for(int k=0;k<100;k++)
;        D[i][k][j] = D[i][k][j]+t;
;

define void @interchange_i_and_j(i32 %t){
; CHECK-LABEL: define void @interchange_i_and_j(
; CHECK-SAME: i32 [[T:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*]]:
; CHECK-NEXT:    br label %[[OUTER_HEADER:.*]]
; CHECK:       [[OUTER_HEADER]]:
; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, %[[ENTRY]] ], [ [[INC16:%.*]], %[[FOR_INC15:.*]] ]
; CHECK-NEXT:    br label %[[INNER2_BODY_PREHEADER:.*]]
; CHECK:       [[INNER1_HEADER_PREHEADER:.*]]:
; CHECK-NEXT:    br label %[[INNER1_HEADER:.*]]
; CHECK:       [[INNER1_HEADER]]:
; CHECK-NEXT:    [[J:%.*]] = phi i64 [ [[INC13:%.*]], %[[FOR_INC12:.*]] ], [ 0, %[[INNER1_HEADER_PREHEADER]] ]
; CHECK-NEXT:    br label %[[INNER2_BODY_SPLIT1:.*]]
; CHECK:       [[INNER2_BODY_PREHEADER]]:
; CHECK-NEXT:    br label %[[INNER2_BODY:.*]]
; CHECK:       [[INNER2_BODY]]:
; CHECK-NEXT:    [[K:%.*]] = phi i64 [ [[TMP1:%.*]], %[[INNER2_BODY_SPLIT:.*]] ], [ 0, %[[INNER2_BODY_PREHEADER]] ]
; CHECK-NEXT:    br label %[[INNER1_HEADER_PREHEADER]]
; CHECK:       [[INNER2_BODY_SPLIT1]]:
; CHECK-NEXT:    [[ARRAYIDX8:%.*]] = getelementptr inbounds [100 x [100 x i32]], ptr @D, i64 [[I]], i64 [[K]], i64 [[J]]
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX8]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP0]], [[T]]
; CHECK-NEXT:    store i32 [[ADD]], ptr [[ARRAYIDX8]], align 4
; CHECK-NEXT:    [[INC:%.*]] = add nuw nsw i64 [[K]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INC]], 100
; CHECK-NEXT:    br label %[[FOR_INC12]]
; CHECK:       [[INNER2_BODY_SPLIT]]:
; CHECK-NEXT:    [[TMP1]] = add nuw nsw i64 [[K]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i64 [[TMP1]], 100
; CHECK-NEXT:    br i1 [[TMP2]], label %[[FOR_INC15]], label %[[INNER2_BODY]]
; CHECK:       [[FOR_INC12]]:
; CHECK-NEXT:    [[INC13]] = add nuw nsw i64 [[J]], 1
; CHECK-NEXT:    [[EXITCOND29:%.*]] = icmp eq i64 [[INC13]], 100
; CHECK-NEXT:    br i1 [[EXITCOND29]], label %[[INNER2_BODY_SPLIT]], label %[[INNER1_HEADER]]
; CHECK:       [[FOR_INC15]]:
; CHECK-NEXT:    [[INC16]] = add nuw nsw i64 [[I]], 1
; CHECK-NEXT:    [[EXITCOND30:%.*]] = icmp eq i64 [[INC16]], 1
; CHECK-NEXT:    br i1 [[EXITCOND30]], label %[[FOR_END17:.*]], label %[[OUTER_HEADER]]
; CHECK:       [[FOR_END17]]:
; CHECK-NEXT:    ret void
;
entry:
  br label %outer.header

outer.header:
  %i = phi i64 [ 0, %entry ], [ %inc16, %for.inc15 ]
  br label %inner1.header

inner1.header:
  %j = phi i64 [ 0, %outer.header ], [ %inc13, %for.inc12 ]
  br label %inner2.body

inner2.body:
  %k = phi i64 [ 0, %inner1.header ], [ %inc, %inner2.body ]
  %arrayidx8 = getelementptr inbounds [100 x [100 x i32]], ptr @D, i64 %i, i64 %k, i64 %j
  %0 = load i32, ptr %arrayidx8
  %add = add nsw i32 %0, %t
  store i32 %add, ptr %arrayidx8
  %inc = add nuw nsw i64 %k, 1
  %exitcond = icmp eq i64 %inc, 100
  br i1 %exitcond, label %for.inc12, label %inner2.body

for.inc12:
  %inc13 = add nuw nsw i64 %j, 1
  %exitcond29 = icmp eq i64 %inc13, 100
  br i1 %exitcond29, label %for.inc15, label %inner1.header

for.inc15:
  %inc16 = add nuw nsw i64 %i, 1
  %exitcond30 = icmp eq i64 %inc16, 1
  br i1 %exitcond30, label %for.end17, label %outer.header

for.end17:
  ret void
}