; NOTE: Assertions have been autogenerated by utils/update_test_checks.py


; RUN: opt --mve-gather-scatter-lowering -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -enable-arm-maskedgatscat %s -S -o 2>/dev/null - | FileCheck %s

define arm_aapcs_vfpcc void @push_out_add_sub_block(i32* noalias nocapture readonly %data, i32* noalias nocapture %dst, i32 %n.vec) {
; CHECK-LABEL: @push_out_add_sub_block(
; CHECK-NEXT:  vector.ph:
; CHECK-NEXT:    [[IND_END:%.*]] = shl i32 [[N_VEC:%.*]], 1
; CHECK-NEXT:    [[PUSHEDOUTADD:%.*]] = add <4 x i32> <i32 0, i32 2, i32 4, i32 6>, <i32 6, i32 6, i32 6, i32 6>
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY_END:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ [[PUSHEDOUTADD]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY_END]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp eq i32 [[INDEX]], 50
; CHECK-NEXT:    br i1 [[TMP0]], label [[LOWER_BLOCK:%.*]], label [[END:%.*]]
; CHECK:       lower.block:
; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i32.v4i32(i32* [[DATA:%.*]], <4 x i32> [[VEC_IND]], i32 32, i32 2, i32 1)
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP1]], <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 8, i32 8, i32 8, i32 8>
; CHECK-NEXT:    br label [[VECTOR_BODY_END]]
; CHECK:       vector.body.end:
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[END]], label [[VECTOR_BODY]]
; CHECK:       end:
; CHECK-NEXT:    ret void
;

vector.ph:
  %ind.end = shl i32 %n.vec, 1
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body.end ]
  %vec.ind = phi <4 x i32> [ <i32 0, i32 2, i32 4, i32 6>, %vector.ph ], [ %vec.ind.next, %vector.body.end ]
  %0 = icmp eq i32 %index, 50
  br i1 %0, label %lower.block, label %end

lower.block:                             ; preds = %vector.body
  %1 = add <4 x i32> %vec.ind, <i32 6, i32 6, i32 6, i32 6>
  %2 = getelementptr inbounds i32, i32* %data, <4 x i32> %1
  %wide.masked.gather = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %2, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
  %3 = getelementptr inbounds i32, i32* %dst, i32 %index
  %4 = bitcast i32* %3 to <4 x i32>*
  store <4 x i32> %wide.masked.gather, <4 x i32>* %4, align 4
  %index.next = add i32 %index, 4
  %vec.ind.next = add <4 x i32> %vec.ind, <i32 8, i32 8, i32 8, i32 8>
  br label %vector.body.end

vector.body.end:                             ; preds = %lower.block
  %5 = icmp eq i32 %index.next, %n.vec
  br i1 %5, label %end, label %vector.body

end:
  ret void;
}

define arm_aapcs_vfpcc void @push_out_mul_sub_block(i32* noalias nocapture readonly %data, i32* noalias nocapture %dst, i32 %n.vec) {
; CHECK-LABEL: @push_out_mul_sub_block(
; CHECK-NEXT:  vector.ph:
; CHECK-NEXT:    [[IND_END:%.*]] = shl i32 [[N_VEC:%.*]], 1
; CHECK-NEXT:    [[PUSHEDOUTMUL:%.*]] = mul <4 x i32> <i32 0, i32 2, i32 4, i32 6>, <i32 3, i32 3, i32 3, i32 3>
; CHECK-NEXT:    [[PRODUCT:%.*]] = mul <4 x i32> <i32 8, i32 8, i32 8, i32 8>, <i32 3, i32 3, i32 3, i32 3>
; CHECK-NEXT:    [[PUSHEDOUTADD:%.*]] = add <4 x i32> [[PUSHEDOUTMUL]], <i32 6, i32 6, i32 6, i32 6>
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY_END:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ [[PUSHEDOUTADD]], [[VECTOR_PH]] ], [ [[INCREMENTPUSHEDOUTMUL:%.*]], [[VECTOR_BODY_END]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp eq i32 [[INDEX]], 50
; CHECK-NEXT:    br i1 [[TMP0]], label [[LOWER_BLOCK:%.*]], label [[END:%.*]]
; CHECK:       lower.block:
; CHECK-NEXT:    [[TMP1:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i32.v4i32(i32* [[DATA:%.*]], <4 x i32> [[VEC_IND]], i32 32, i32 2, i32 1)
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP1]], <4 x i32>* [[TMP3]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    br label [[VECTOR_BODY_END]]
; CHECK:       vector.body.end:
; CHECK-NEXT:    [[INCREMENTPUSHEDOUTMUL]] = add <4 x i32> [[VEC_IND]], [[PRODUCT]]
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP4]], label [[END]], label [[VECTOR_BODY]]
; CHECK:       end:
; CHECK-NEXT:    ret void
;

vector.ph:
  %ind.end = shl i32 %n.vec, 1
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body.end ]
  %vec.ind = phi <4 x i32> [ <i32 0, i32 2, i32 4, i32 6>, %vector.ph ], [ %vec.ind.next, %vector.body.end ]
  %0 = icmp eq i32 %index, 50
  br i1 %0, label %lower.block, label %end

lower.block:                             ; preds = %vector.body
  %1 = mul <4 x i32> %vec.ind, <i32 3, i32 3, i32 3, i32 3>
  %2 = add <4 x i32> %1, <i32 6, i32 6, i32 6, i32 6>
  %3 = getelementptr inbounds i32, i32* %data, <4 x i32> %2
  %wide.masked.gather = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %3, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
  %4 = getelementptr inbounds i32, i32* %dst, i32 %index
  %5 = bitcast i32* %4 to <4 x i32>*
  store <4 x i32> %wide.masked.gather, <4 x i32>* %5, align 4
  %index.next = add i32 %index, 4
  %vec.ind.next = add <4 x i32> %vec.ind, <i32 8, i32 8, i32 8, i32 8>
  br label %vector.body.end

vector.body.end:                             ; preds = %lower.block
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %end, label %vector.body

end:
  ret void;
}


define arm_aapcs_vfpcc void @push_out_mul_sub_loop(i32* noalias nocapture readonly %data, i32* noalias nocapture %dst, i32 %n.vec) {
; CHECK-LABEL: @push_out_mul_sub_loop(
; CHECK-NEXT:  vector.ph:
; CHECK-NEXT:    [[IND_END:%.*]] = shl i32 [[N_VEC:%.*]], 2
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY_END:%.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 2, i32 4, i32 6>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY_END]] ]
; CHECK-NEXT:    br label [[VECTOR_2_PH:%.*]]
; CHECK:       vector.2.ph:
; CHECK-NEXT:    br label [[VECTOR_2_BODY:%.*]]
; CHECK:       vector.2.body:
; CHECK-NEXT:    [[TMP0:%.*]] = mul <4 x i32> [[VEC_IND]], <i32 3, i32 3, i32 3, i32 3>
; CHECK-NEXT:    [[TMP1:%.*]] = add <4 x i32> [[TMP0]], <i32 6, i32 6, i32 6, i32 6>
; CHECK-NEXT:    [[TMP2:%.*]] = call <4 x i32> @llvm.arm.mve.vldr.gather.offset.v4i32.p0i32.v4i32(i32* [[DATA:%.*]], <4 x i32> [[TMP1]], i32 32, i32 2, i32 1)
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i32 [[INDEX]]
; CHECK-NEXT:    [[TMP4:%.*]] = bitcast i32* [[TMP3]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP2]], <4 x i32>* [[TMP4]], align 4
; CHECK-NEXT:    br label [[VECTOR_2_BODY_END:%.*]]
; CHECK:       vector.2.body.end:
; CHECK-NEXT:    [[INDEX_2_NEXT:%.*]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[TMP5:%.*]] = icmp eq i32 [[INDEX_2_NEXT]], 15
; CHECK-NEXT:    br i1 [[TMP5]], label [[VECTOR_BODY_END]], label [[VECTOR_2_BODY]]
; CHECK:       vector.body.end:
; CHECK-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 8, i32 8, i32 8, i32 8>
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP6]], label [[END:%.*]], label [[VECTOR_BODY]]
; CHECK:       end:
; CHECK-NEXT:    ret void
;

vector.ph:
  %ind.end = shl i32 %n.vec, 2
  br label %vector.body

vector.body:                                      ; preds = %vector.body, %vector.ph
  %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body.end ]
  %vec.ind = phi <4 x i32> [ <i32 0, i32 2, i32 4, i32 6>, %vector.ph ], [ %vec.ind.next, %vector.body.end ]
  br label %vector.2.ph

vector.2.ph:
  br label %vector.2.body

vector.2.body:                             ; preds = %vector.body
  %index.2 = phi i32 [ 0, %vector.2.ph ], [ %index.2.next, %vector.2.body.end ]
  %0 = mul <4 x i32> %vec.ind, <i32 3, i32 3, i32 3, i32 3>
  %1 = add <4 x i32> %0, <i32 6, i32 6, i32 6, i32 6>
  %2 = getelementptr inbounds i32, i32* %data, <4 x i32> %1
  %wide.masked.gather = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %2, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
  %3 = getelementptr inbounds i32, i32* %dst, i32 %index
  %4 = bitcast i32* %3 to <4 x i32>*
  store <4 x i32> %wide.masked.gather, <4 x i32>* %4, align 4
  br label %vector.2.body.end

vector.2.body.end:                             ; preds = %lower.block
  %index.2.next = add i32 %index, 4
  %5 = icmp eq i32 %index.2.next, 15
  br i1 %5, label %vector.body.end, label %vector.2.body

vector.body.end:                             ; preds = %lower.block
  %index.next = add i32 %index, 4
  %vec.ind.next = add <4 x i32> %vec.ind, <i32 8, i32 8, i32 8, i32 8>
  %6 = icmp eq i32 %index.next, %n.vec
  br i1 %6, label %end, label %vector.body

end:
  ret void;
}

declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)