; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -loop-vectorize -S %s | FileCheck %s

target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128-ni:1-p2:32:8:8:32-ni:2"
target triple = "x86_64-unknown-linux-gnu"

; TODO: Make sure selected VF for the epilog loop doesn't exceed remaining TC.
define void @test1(i8 * noalias %src, i8 * noalias %dst) #0 {
; CHECK-LABEL: @test1(
; CHECK-NEXT:  iter.check:
; CHECK-NEXT:    br i1 false, label [[VEC_EPILOG_SCALAR_PH:%.*]], label [[VECTOR_MAIN_LOOP_ITER_CHECK:%.*]]
; CHECK:       vector.main.loop.iter.check:
; CHECK-NEXT:    br i1 false, label [[VEC_EPILOG_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, i8* [[SRC:%.*]], i64 [[TMP0]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, i8* [[TMP1]], i32 0
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to <16 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <16 x i8>, <16 x i8>* [[TMP3]], align 64
; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i8, i8* [[DST:%.*]], i64 [[TMP0]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i8, i8* [[TMP4]], 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 64
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 17, 16
; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[VEC_EPILOG_ITER_CHECK:%.*]]
; CHECK:       vec.epilog.iter.check:
; CHECK-NEXT:    br i1 true, label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
; CHECK:       vec.epilog.ph:
; CHECK-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ 16, [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
; CHECK-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
; CHECK:       vec.epilog.vector.body:
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = phi i64 [ [[VEC_EPILOG_RESUME_VAL]], [[VEC_EPILOG_PH]] ], [ [[INDEX_NEXT4:%.*]], [[VEC_EPILOG_VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[OFFSET_IDX]], 0
; CHECK-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 [[TMP8]]
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i8, i8* [[TMP9]], i32 0
; CHECK-NEXT:    [[TMP11:%.*]] = bitcast i8* [[TMP10]] to <8 x i8>*
; CHECK-NEXT:    [[WIDE_LOAD3:%.*]] = load <8 x i8>, <8 x i8>* [[TMP11]], align 64
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 [[TMP8]]
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i8, i8* [[TMP12]], i32 0
; CHECK-NEXT:    [[TMP14:%.*]] = bitcast i8* [[TMP13]] to <8 x i8>*
; CHECK-NEXT:    store <8 x i8> [[WIDE_LOAD3]], <8 x i8>* [[TMP14]], align 64
; CHECK-NEXT:    [[INDEX_NEXT4]] = add nuw i64 [[OFFSET_IDX]], 8
; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT4]], 16
; CHECK-NEXT:    br i1 [[TMP15]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
; CHECK:       vec.epilog.middle.block:
; CHECK-NEXT:    [[CMP_N1:%.*]] = icmp eq i64 17, 16
; CHECK-NEXT:    br i1 [[CMP_N1]], label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
; CHECK:       vec.epilog.scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[VEC_EPILOG_MIDDLE_BLOCK]] ], [ 16, [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[ITER_CHECK:%.*]] ]
; CHECK-NEXT:    br label [[LOOP_MEMCPY_EXPANSION:%.*]]
; CHECK:       loop-memcpy-expansion:
; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[VEC_EPILOG_SCALAR_PH]] ], [ [[I_NEXT:%.*]], [[LOOP_MEMCPY_EXPANSION]] ]
; CHECK-NEXT:    [[LDADDR:%.*]] = getelementptr inbounds i8, i8* [[SRC]], i64 [[I]]
; CHECK-NEXT:    [[VAL:%.*]] = load i8, i8* [[LDADDR]], align 64
; CHECK-NEXT:    [[STADDR:%.*]] = getelementptr inbounds i8, i8* [[DST]], i64 [[I]]
; CHECK-NEXT:    store i8 [[VAL]], i8* [[STADDR]], align 64
; CHECK-NEXT:    [[I_NEXT]] = add i64 [[I]], 1
; CHECK-NEXT:    [[IS_NEXT:%.*]] = icmp ult i64 [[I_NEXT]], 17
; CHECK-NEXT:    br i1 [[IS_NEXT]], label [[LOOP_MEMCPY_EXPANSION]], label [[EXIT]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop-memcpy-expansion

loop-memcpy-expansion:
  %i = phi i64 [ 0, %entry ], [ %i.next, %loop-memcpy-expansion ]
  %ldaddr = getelementptr inbounds i8, i8 * %src, i64 %i
  %val = load i8, i8 * %ldaddr, align 64
  %staddr = getelementptr inbounds i8, i8 * %dst, i64 %i
  store i8 %val, i8 * %staddr, align 64
  %i.next = add i64 %i, 1
  %is.next = icmp ult i64 %i.next, 17
  br i1 %is.next, label %loop-memcpy-expansion, label %exit

exit:
  ret void
}

attributes #0 = { "target-features"="+avx512f" }