; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -loop-vectorize -mattr=+armv8.1-m.main,+mve.fp -tail-predication=disabled< %s | FileCheck %s
; RUN: opt -S -loop-vectorize -mattr=+armv8.1-m.main,+mve.fp -tail-predication=enabled < %s | FileCheck %s

; This test should produce the same result (vectorized loop + scalar epilogue) with
; default options and when MVE Tail Predication is enabled, as this loop's tail cannot be folded
; by masking due to an outside user of %incdec.ptr in %end.

target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv8.1m.main-arm-unknown-eabihf"

define void @outside_user_blocks_tail_folding(i8* nocapture readonly %ptr, i32 %size, i8** %pos) {
; CHECK-LABEL: @outside_user_blocks_tail_folding(
; CHECK-NEXT:  header:
; CHECK-NEXT:    [[PTR0:%.*]] = load i8*, i8** [[POS:%.*]], align 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[SIZE:%.*]], 16
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[SIZE]], 16
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[SIZE]], [[N_MOD_VF]]
; CHECK-NEXT:    [[IND_END:%.*]] = sub i32 [[SIZE]], [[N_VEC]]
; CHECK-NEXT:    [[IND_END2:%.*]] = getelementptr i8, i8* [[PTR:%.*]], i32 [[N_VEC]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = sub i32 [[SIZE]], [[INDEX]]
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[OFFSET_IDX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, i8* [[PTR]], i32 [[TMP1]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[NEXT_GEP]], i32 1
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i8, i8* [[TMP2]], i32 0
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i8* [[TMP3]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, <16 x i8>* [[TMP4]], align 1
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr i8, i8* [[NEXT_GEP]], i32 0
; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i8* [[TMP5]] to <16 x i8>*
; CHECK-NEXT:    store <16 x i8> [[WIDE_LOAD]], <16 x i8>* [[TMP6]], align 1
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 16
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[SIZE]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[END:%.*]], label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[SIZE]], [[HEADER:%.*]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i8* [ [[IND_END2]], [[MIDDLE_BLOCK]] ], [ [[PTR]], [[HEADER]] ]
; CHECK-NEXT:    br label [[BODY:%.*]]
; CHECK:       body:
; CHECK-NEXT:    [[DEC66:%.*]] = phi i32 [ [[DEC:%.*]], [[BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[BUFF:%.*]] = phi i8* [ [[INCDEC_PTR:%.*]], [[BODY]] ], [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ]
; CHECK-NEXT:    [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[BUFF]], i32 1
; CHECK-NEXT:    [[DEC]] = add nsw i32 [[DEC66]], -1
; CHECK-NEXT:    [[TMP8:%.*]] = load i8, i8* [[INCDEC_PTR]], align 1
; CHECK-NEXT:    store i8 [[TMP8]], i8* [[BUFF]], align 1
; CHECK-NEXT:    [[TOBOOL11:%.*]] = icmp eq i32 [[DEC]], 0
; CHECK-NEXT:    br i1 [[TOBOOL11]], label [[END]], label [[BODY]], !llvm.loop !2
; CHECK:       end:
; CHECK-NEXT:    [[INCDEC_PTR_LCSSA:%.*]] = phi i8* [ [[INCDEC_PTR]], [[BODY]] ], [ [[IND_END2]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    store i8* [[INCDEC_PTR_LCSSA]], i8** [[POS]], align 4
; CHECK-NEXT:    ret void
;
header:
  %ptr0 = load i8*, i8** %pos, align 4
  br label %body

body:
  %dec66 = phi i32 [ %dec, %body ], [ %size, %header ]
  %buff = phi i8* [ %incdec.ptr, %body ], [ %ptr, %header ]
  %incdec.ptr = getelementptr inbounds i8, i8* %buff, i32 1
  %dec = add nsw i32 %dec66, -1
  %0 = load i8, i8* %incdec.ptr, align 1
  store i8 %0, i8* %buff, align 1
  %tobool11 = icmp eq i32 %dec, 0
  br i1 %tobool11, label %end, label %body

end:
  store i8* %incdec.ptr, i8** %pos, align 4
  ret void
}