; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -p loop-vectorize -force-vector-width=4 -enable-epilogue-vectorization -epilogue-vectorization-force-VF=4 -S %s | FileCheck %s

target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"

define void @trunc_iv_steps_with_epilogue(ptr %A, i64 %N) {
; CHECK-LABEL: define void @trunc_iv_steps_with_epilogue(
; CHECK-SAME: ptr [[A:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  iter.check:
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[N]], 1
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
; CHECK:       vector.scevcheck:
; CHECK-NEXT:    [[TMP1:%.*]] = trunc i64 [[N]] to i32
; CHECK-NEXT:    [[TMP2:%.*]] = icmp slt i32 [[TMP1]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = icmp ugt i64 [[N]], 4294967295
; CHECK-NEXT:    [[TMP4:%.*]] = or i1 [[TMP2]], [[TMP3]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[VEC_EPILOG_SCALAR_PH]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
; CHECK:       vector.main.loop.iter.check:
; CHECK-NEXT:    [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[TMP0]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK1]], label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP5:%.*]] = trunc i64 [[INDEX]] to i32
; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[TMP5]], 0
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i8, ptr [[A]], i32 [[TMP6]]
; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[TMP7]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr [[TMP8]], align 1
; CHECK-NEXT:    [[TMP9:%.*]] = add <4 x i8> [[WIDE_LOAD]], splat (i8 2)
; CHECK-NEXT:    store <4 x i8> [[TMP9]], ptr [[TMP8]], align 1
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
; CHECK:       vec.epilog.iter.check:
; CHECK-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[TMP0]], [[N_VEC]]
; CHECK-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 4
; CHECK-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
; CHECK:       vec.epilog.ph:
; CHECK-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
; CHECK-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[TMP0]], 4
; CHECK-NEXT:    [[N_VEC3:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF2]]
; CHECK-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
; CHECK:       vec.epilog.vector.body:
; CHECK-NEXT:    [[INDEX5:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT7:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP11:%.*]] = trunc i64 [[INDEX5]] to i32
; CHECK-NEXT:    [[TMP12:%.*]] = add i32 [[TMP11]], 0
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i8, ptr [[A]], i32 [[TMP12]]
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i8, ptr [[TMP13]], i32 0
; CHECK-NEXT:    [[WIDE_LOAD6:%.*]] = load <4 x i8>, ptr [[TMP14]], align 1
; CHECK-NEXT:    [[TMP15:%.*]] = add <4 x i8> [[WIDE_LOAD6]], splat (i8 2)
; CHECK-NEXT:    store <4 x i8> [[TMP15]], ptr [[TMP14]], align 1
; CHECK-NEXT:    [[INDEX_NEXT7]] = add nuw i64 [[INDEX5]], 4
; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i64 [[INDEX_NEXT7]], [[N_VEC3]]
; CHECK-NEXT:    br i1 [[TMP16]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       vec.epilog.middle.block:
; CHECK-NEXT:    [[CMP_N4:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC3]]
; CHECK-NEXT:    br i1 [[CMP_N4]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK:       vec.epilog.scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC3]], [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV_I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[T_IV:%.*]] = trunc i64 [[IV_I]] to i32
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i8, ptr [[A]], i32 [[T_IV]]
; CHECK-NEXT:    [[L:%.*]] = load i8, ptr [[GEP]], align 1
; CHECK-NEXT:    [[ADD:%.*]] = add i8 [[L]], 2
; CHECK-NEXT:    store i8 [[ADD]], ptr [[GEP]], align 1
; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV_I]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV_I]], [[N]]
; CHECK-NEXT:    br i1 [[EC]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv.i = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %t.iv = trunc i64 %iv.i to i32
  %gep = getelementptr i8, ptr %A, i32 %t.iv
  %l = load i8, ptr %gep, align 1
  %add = add i8 %l, 2
  store i8 %add, ptr %gep
  %iv.next = add i64 %iv.i, 1
  %ec = icmp eq i64 %iv.i, %N
  br i1 %ec, label %exit, label %loop

exit:
  ret void
}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META1]], [[META2]]}
; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]]}
;.