; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
; RUN: opt -passes=loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s

define void @pr63340(ptr %A, ptr %B) {
; CHECK-LABEL: define void @pr63340
; CHECK-SAME: (ptr [[A:%.*]], ptr [[B:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr i8, ptr [[A]], i64 1
; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <4 x ptr> [[DOTSPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
; 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:%.*]] = trunc i32 [[INDEX]] to i8
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds ptr, ptr [[B]], i8 [[OFFSET_IDX]]
; CHECK-NEXT:    store <4 x ptr> [[DOTSPLAT]], ptr [[TMP1]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP2:%.*]] = icmp eq i32 [[INDEX_NEXT]], 128
; CHECK-NEXT:    br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[EXIT:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[LOOP_HEADER:%.*]]
; CHECK:       loop.header:
; CHECK-NEXT:    [[IV:%.*]] = phi i8 [ 0, [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
; CHECK-NEXT:    br label [[LOOP_LATCH]]
; CHECK:       loop.latch:
; CHECK-NEXT:    [[F_0_I:%.*]] = phi ptr [ [[A]], [[LOOP_HEADER]] ]
; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i8, ptr [[F_0_I]], i64 1
; CHECK-NEXT:    [[GEP_B:%.*]] = getelementptr inbounds ptr, ptr [[B]], i8 [[IV]]
; CHECK-NEXT:    store ptr [[GEP]], ptr [[GEP_B]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add i8 [[IV]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], -128
; CHECK-NEXT:    br i1 [[EC]], label [[EXIT]], label [[LOOP_HEADER]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop.header

loop.header:
  %iv = phi i8 [ 0, %entry ], [ %iv.next, %loop.latch ]
  br label %loop.latch

loop.latch:
  %f.0.i = phi ptr [ %A, %loop.header ]
  %gep = getelementptr i8, ptr %f.0.i, i64 1
  %gep.B = getelementptr inbounds ptr, ptr %B, i8 %iv
  store ptr %gep, ptr %gep.B
  %iv.next = add i8 %iv, 1
  %ec = icmp eq i8 %iv.next, 128
  br i1 %ec, label %exit, label %loop.header

exit:
  ret void
}

; FIXME: Redundant broadcast in vector.ph only feeds an extract only.
define void @wide_gep_index_invariant(ptr noalias %dst, ptr noalias %src, i64 %n) {
; CHECK-LABEL: define void @wide_gep_index_invariant
; CHECK-SAME: (ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_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:%.*]] = load ptr, ptr [[SRC]], align 8
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr float, <4 x ptr> [[BROADCAST_SPLAT]], i64 [[N]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr ptr, ptr [[DST]], i64 [[INDEX]]
; CHECK-NEXT:    store <4 x ptr> [[TMP1]], ptr [[TMP2]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 100
; CHECK-NEXT:    br i1 [[TMP3]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[EXIT:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[L:%.*]] = load ptr, ptr [[SRC]], align 8
; CHECK-NEXT:    [[GEP_L:%.*]] = getelementptr float, ptr [[L]], i64 [[N]]
; CHECK-NEXT:    [[GEP_DST:%.*]] = getelementptr ptr, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT:    store ptr [[GEP_L]], ptr [[GEP_DST]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], 100
; CHECK-NEXT:    br i1 [[EC]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %l = load ptr, ptr %src, align 8
  %gep.l = getelementptr float, ptr %l, i64 %n
  %gep.dst = getelementptr ptr, ptr %dst, i64 %iv
  store ptr %gep.l, ptr %gep.dst, align 8
  %iv.next = add nuw nsw i64 %iv, 1
  %ec = icmp eq i64 %iv.next, 100
  br i1 %ec, label %exit, label %loop

exit:
  ret void
}

define void @wide_gep_multiple_indices_some_invariant(ptr noalias %dst, ptr noalias %src, i32 %x) {
; CHECK-LABEL: define void @wide_gep_multiple_indices_some_invariant
; CHECK-SAME: (ptr noalias [[DST:%.*]], ptr noalias [[SRC:%.*]], i32 [[X:%.*]]) {
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 false, label [[SCALAR_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:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[SRC]], align 8
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x ptr> poison, ptr [[TMP0]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x ptr> [[BROADCAST_SPLATINSERT]], <4 x ptr> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr [10 x float], <4 x ptr> [[BROADCAST_SPLAT]], i32 [[X]], <4 x i64> [[VEC_IND]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr ptr, ptr [[DST]], i64 [[INDEX]]
; CHECK-NEXT:    store <4 x ptr> [[TMP1]], ptr [[TMP2]], align 8
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], splat (i64 4)
; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 100
; CHECK-NEXT:    br i1 [[TMP3]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[EXIT:%.*]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[L:%.*]] = load ptr, ptr [[SRC]], align 8
; CHECK-NEXT:    [[GEP_L:%.*]] = getelementptr [10 x float], ptr [[L]], i32 [[X]], i64 [[IV]]
; CHECK-NEXT:    [[GEP_DST:%.*]] = getelementptr ptr, ptr [[DST]], i64 [[IV]]
; CHECK-NEXT:    store ptr [[GEP_L]], ptr [[GEP_DST]], align 8
; CHECK-NEXT:    [[IV_NEXT]] = add nuw nsw i64 [[IV]], 1
; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], 100
; CHECK-NEXT:    br i1 [[EC]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP7:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %l = load ptr, ptr %src, align 8
  %gep.l = getelementptr [10 x float], ptr %l, i32 %x, i64 %iv
  %gep.dst = getelementptr ptr, ptr %dst, i64 %iv
  store ptr %gep.l, ptr %gep.dst, align 8
  %iv.next = add nuw nsw i64 %iv, 1
  %ec = icmp eq i64 %iv.next, 100
  br i1 %ec, label %exit, label %loop

exit:
  ret void
}