[SLP]Fix hanging on small trees with phis only with adjusted cost threshold

Need to check if the tree is too small before attempting to vectorize the tree to prevent hanging on small trees with phis only.

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -12130,6 +12130,30 @@ bool BoUpSLP::isTreeTinyAndNotFullyVectorizable(bool ForReduction) const {
       }))
     return true;
 
+  // Do not vectorize small tree of phis only, if all vector phis are also
+  // gathered.
+  if (!ForReduction && SLPCostThreshold.getNumOccurrences() &&
+      VectorizableTree.size() <= Limit &&
+      all_of(VectorizableTree,
+             [&](const std::unique_ptr<TreeEntry> &TE) {
+               return (TE->isGather() &&
+                       (!TE->hasState() ||
+                        TE->getOpcode() != Instruction::ExtractElement) &&
+                       count_if(TE->Scalars, IsaPred<ExtractElementInst>) <=
+                           Limit) ||
+                      (TE->hasState() &&
+                       (TE->getOpcode() == Instruction::InsertElement ||
+                        (TE->getOpcode() == Instruction::PHI &&
+                         all_of(TE->Scalars, [&](Value *V) {
+                           return isa<PoisonValue>(V) || MustGather.contains(V);
+                         }))));
+             }) &&
+      any_of(VectorizableTree, [&](const std::unique_ptr<TreeEntry> &TE) {
+        return TE->State == TreeEntry::Vectorize &&
+               TE->getOpcode() == Instruction::PHI;
+      }))
+    return true;
+
   // We can vectorize the tree if its size is greater than or equal to the
   // minimum size specified by the MinTreeSize command line option.
   if (VectorizableTree.size() >= MinTreeSize)

llvm/test/Transforms/SLPVectorizer/RISCV/small-phi-tree.ll

@@ -0,0 +1,40 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -mtriple=riscv64 -mcpu=sifive-x280 -passes=slp-vectorizer -S -slp-threshold=-11 < %s | FileCheck %s
+
+define float @test(ptr %call78) {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <2 x ptr> <ptr null, ptr poison>, ptr [[CALL78:%.*]], i32 1
+; CHECK-NEXT:    br label [[FOR_BODY194:%.*]]
+; CHECK:       for.body194:
+; CHECK-NEXT:    [[INDVARS_IV132:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ 0, [[FOR_BODY194]] ]
+; CHECK-NEXT:    [[CURRENTW_031:%.*]] = phi ptr [ [[CALL78]], [[ENTRY]] ], [ [[PREVIOUSW_030:%.*]], [[FOR_BODY194]] ]
+; CHECK-NEXT:    [[PREVIOUSW_030]] = phi ptr [ null, [[ENTRY]] ], [ [[CURRENTW_031]], [[FOR_BODY194]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x ptr> [ [[TMP0]], [[ENTRY]] ], [ [[TMP3:%.*]], [[FOR_BODY194]] ]
+; CHECK-NEXT:    store float 0.000000e+00, ptr [[CURRENTW_031]], align 4
+; CHECK-NEXT:    tail call void null(ptr [[PREVIOUSW_030]], ptr null, ptr null, i32 0, i32 0, ptr null, ptr null, i32 0)
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x ptr> poison, ptr [[CURRENTW_031]], i32 0
+; CHECK-NEXT:    [[TMP3]] = insertelement <2 x ptr> [[TMP2]], ptr [[PREVIOUSW_030]], i32 1
+; CHECK-NEXT:    br i1 false, label [[FOR_END286_LOOPEXIT:%.*]], label [[FOR_BODY194]]
+; CHECK:       for.end286.loopexit:
+; CHECK-NEXT:    [[TMP4:%.*]] = phi <2 x ptr> [ [[TMP1]], [[FOR_BODY194]] ]
+; CHECK-NEXT:    ret float 0.000000e+00
+;
+entry:
+  br label %for.body194
+
+for.body194:
+  %indvars.iv132 = phi i64 [ 0, %entry ], [ 0, %for.body194 ]
+  %currentw.031 = phi ptr [ %call78, %entry ], [ %previousw.030, %for.body194 ]
+  %previousw.030 = phi ptr [ null, %entry ], [ %currentw.031, %for.body194 ]
+  store float 0.000000e+00, ptr %currentw.031, align 4
+  tail call void null(ptr %previousw.030, ptr null, ptr null, i32 0, i32 0, ptr null, ptr null, i32 0)
+  br i1 false, label %for.end286.loopexit, label %for.body194
+
+for.end286.loopexit:
+  %currentw.031.lcssa = phi ptr [ %currentw.031, %for.body194 ]
+  %previousw.030.lcssa = phi ptr [ %previousw.030, %for.body194 ]
+  ret float 0.000000e+00
+}
+
+