const std::unique_ptr<TreeEntry> &TE) {
if (Optional<OrdersType> CurrentOrder =
getReorderingData(*TE.get(), /*TopToBottom=*/true)) {
+ // Do not include ordering for nodes used in the alt opcode vectorization,
+ // better to reorder them during bottom-to-top stage. If follow the order
+ // here, it causes reordering of the whole graph though actually it is
+ // profitable just to reorder the subgraph that starts from the alternate
+ // opcode vectorization node. Such nodes already end-up with the shuffle
+ // instruction and it is just enough to change this shuffle rather than
+ // rotate the scalars for the whole graph.
+ unsigned Cnt = 0;
+ const TreeEntry *UserTE = TE.get();
+ while (UserTE && Cnt < RecursionMaxDepth) {
+ if (UserTE->UserTreeIndices.size() != 1)
+ break;
+ if (all_of(UserTE->UserTreeIndices, [](const EdgeInfo &EI) {
+ return EI.UserTE->State == TreeEntry::Vectorize &&
+ EI.UserTE->isAltShuffle() && EI.UserTE->Idx != 0;
+ }))
+ return;
+ if (UserTE->UserTreeIndices.empty())
+ UserTE = nullptr;
+ else
+ UserTE = UserTE->UserTreeIndices.back().UserTE;
+ ++Cnt;
+ }
VFToOrderedEntries[TE->Scalars.size()].insert(TE.get());
if (TE->State != TreeEntry::Vectorize)
GathersToOrders.try_emplace(TE.get(), *CurrentOrder);
; CHECK-LABEL: @build_vec_v4i32(
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i32> [[V0:%.*]], [[V1:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = sub <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 3, i32 6>
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 6, i32 3>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 3, i32 6>
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 2, i32 7>
; CHECK-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
-; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> <i32 1, i32 0, i32 2, i32 3>
-; CHECK-NEXT: ret <4 x i32> [[TMP6]]
+; CHECK-NEXT: ret <4 x i32> [[TMP5]]
;
%v0.0 = extractelement <4 x i32> %v0, i32 0
%v0.1 = extractelement <4 x i32> %v0, i32 1
; CHECK-LABEL: @reduction_v4i32(
; CHECK-NEXT: [[TMP1:%.*]] = sub <4 x i32> [[V0:%.*]], [[V1:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 7, i32 2>
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 7, i32 2>
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 6, i32 3>
; CHECK-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
; CHECK-NEXT: [[TMP6:%.*]] = lshr <4 x i32> [[TMP5]], <i32 15, i32 15, i32 15, i32 15>
; CHECK-NEXT: [[TMP7:%.*]] = and <4 x i32> [[TMP6]], <i32 65537, i32 65537, i32 65537, i32 65537>
; CHECK-LABEL: @build_vec_v4i32(
; CHECK-NEXT: [[TMP1:%.*]] = add <4 x i32> [[V0:%.*]], [[V1:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = sub <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 3, i32 6>
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 6, i32 3>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 3, i32 6>
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 2, i32 7>
; CHECK-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
-; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> <i32 1, i32 0, i32 2, i32 3>
-; CHECK-NEXT: ret <4 x i32> [[TMP6]]
+; CHECK-NEXT: ret <4 x i32> [[TMP5]]
;
%v0.0 = extractelement <4 x i32> %v0, i32 0
%v0.1 = extractelement <4 x i32> %v0, i32 1
; CHECK-LABEL: @reduction_v4i32(
; CHECK-NEXT: [[TMP1:%.*]] = sub <4 x i32> [[V0:%.*]], [[V1:%.*]]
; CHECK-NEXT: [[TMP2:%.*]] = add <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 7, i32 2>
-; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT: [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 7, i32 2>
+; CHECK-NEXT: [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 6, i32 3>
; CHECK-NEXT: [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
; CHECK-NEXT: [[TMP6:%.*]] = lshr <4 x i32> [[TMP5]], <i32 15, i32 15, i32 15, i32 15>
; CHECK-NEXT: [[TMP7:%.*]] = and <4 x i32> [[TMP6]], <i32 65537, i32 65537, i32 65537, i32 65537>
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x double>, <2 x double>* [[TMP2]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = fadd <2 x double> [[TMP1]], [[TMP3]]
; CHECK-NEXT: [[TMP5:%.*]] = fsub <2 x double> [[TMP1]], [[TMP3]]
-; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> [[TMP5]], <2 x i32> <i32 2, i32 1>
-; CHECK-NEXT: [[SHUFFLE:%.*]] = shufflevector <2 x double> [[TMP6]], <2 x double> poison, <2 x i32> <i32 1, i32 0>
+; CHECK-NEXT: [[TMP6:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> [[TMP5]], <2 x i32> <i32 1, i32 2>
; CHECK-NEXT: [[TMP7:%.*]] = bitcast double* [[ARRAYIDX10]] to <2 x double>*
-; CHECK-NEXT: store <2 x double> [[SHUFFLE]], <2 x double>* [[TMP7]], align 8
+; CHECK-NEXT: store <2 x double> [[TMP6]], <2 x double>* [[TMP7]], align 8
; CHECK-NEXT: ret void
;
entry: