[PATCH] D80241: [SLP] PR45269 Fix getVectorElementSize() is slow

[Dinar Temirbulatov via Phabricator via llvm-commits]

dtemirbulatov updated this revision to Diff 265254.
dtemirbulatov added a comment.

Addressed remarks.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D80241/new/

https://reviews.llvm.org/D80241

Files:
  llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp


Index: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -629,7 +629,7 @@
   /// the stored value. Otherwise, the size is the width of the largest loaded
   /// value reaching V. This method is used by the vectorizer to calculate
   /// vectorization factors.
-  unsigned getVectorElementSize(Value *V) const;
+  unsigned getVectorElementSize(Value *V);
 
   /// Compute the minimum type sizes required to represent the entries in a
   /// vectorizable tree.
@@ -1715,6 +1715,9 @@
   /// Maps a specific scalar to its tree entry.
   SmallDenseMap<Value*, TreeEntry *> ScalarToTreeEntry;
 
+  /// Maps a value to the proposed vectorizable size.
+  SmallDenseMap<Value *, unsigned> InstrElementSize;
+
   /// A list of scalars that we found that we need to keep as scalars.
   ValueSet MustGather;
 
@@ -4797,6 +4800,7 @@
   }
 
   Builder.ClearInsertionPoint();
+  InstrElementSize.clear();
 
   return VectorizableTree[0]->VectorizedValue;
 }
@@ -5333,12 +5337,16 @@
   BS->ScheduleStart = nullptr;
 }
 
-unsigned BoUpSLP::getVectorElementSize(Value *V) const {
+unsigned BoUpSLP::getVectorElementSize(Value *V) {
   // If V is a store, just return the width of the stored value without
   // traversing the expression tree. This is the common case.
   if (auto *Store = dyn_cast<StoreInst>(V))
     return DL->getTypeSizeInBits(Store->getValueOperand()->getType());
 
+  auto E = InstrElementSize.find(V);
+  if (E != InstrElementSize.end())
+    return E->second;
+
   // If V is not a store, we can traverse the expression tree to find loads
   // that feed it. The type of the loaded value may indicate a more suitable
   // width than V's type. We want to base the vector element size on the width
@@ -5384,13 +5392,16 @@
       FoundUnknownInst = true;
   }
 
+  int Width = MaxWidth;
   // If we didn't encounter a memory access in the expression tree, or if we
   // gave up for some reason, just return the width of V.
   if (!MaxWidth || FoundUnknownInst)
-    return DL->getTypeSizeInBits(V->getType());
+    Width = DL->getTypeSizeInBits(V->getType());
+
+  for (Instruction *I : Visited)
+    InstrElementSize[I] = Width;
 
-  // Otherwise, return the maximum width we found.
-  return MaxWidth;
+  return Width;
 }
 
 // Determine if a value V in a vectorizable expression Expr can be demoted to a


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D80241.265254.patch
Type: text/x-patch
Size: 2486 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200520/cb28dc5d/attachment-0001.bin>