[IR] Store attributes that are available "somewhere" (NFC)

I noticed that for some benchmarks we spend quite a bit of time
inside AttributeList::hasAttrSomewhere(), mainly when checking
for the "returned" attribute. Most of the time the attribute will
not be present, in which case this function has to walk through
the whole attribute list and check for the attribute at each index.

This patch adds a cache of all "available somewhere" attributes
inside AttributeListImpl. This makes the structure 12 bytes larger,
but I don't think that's problematic, as attribute lists are uniqued.
Compile-time in terms of instructions retired improves by 0.4% on
average, but >1% for sqlite.

Differential Revision: https://reviews.llvm.org/D81867

Author: nikic

llvm/lib/IR/AttributeImpl.h

@@ -282,6 +282,8 @@ class AttributeListImpl final
   unsigned NumAttrSets; ///< Number of entries in this set.
   /// Available enum function attributes.
   AttributeBitSet AvailableFunctionAttrs;
+  /// Union of enum attributes available at any index.
+  AttributeBitSet AvailableSomewhereAttrs;
 
   // Helper fn for TrailingObjects class.
   size_t numTrailingObjects(OverloadToken<AttributeSet>) { return NumAttrSets; }
@@ -299,6 +301,12 @@ class AttributeListImpl final
     return AvailableFunctionAttrs.hasAttribute(Kind);
   }
 
+  /// Return true if the specified attribute is set for at least one
+  /// parameter or for the return value. If Index is not nullptr, the index
+  /// of a parameter with the specified attribute is provided.
+  bool hasAttrSomewhere(Attribute::AttrKind Kind,
+                        unsigned *Index = nullptr) const;
+
   using iterator = const AttributeSet *;
 
   iterator begin() const { return getTrailingObjects<AttributeSet>(); }

llvm/lib/IR/Attributes.cpp

@@ -977,13 +977,18 @@ AttributeListImpl::AttributeListImpl(ArrayRef<AttributeSet> Sets)
   // There's memory after the node where we can store the entries in.
   llvm::copy(Sets, getTrailingObjects<AttributeSet>());
 
-  // Initialize AvailableFunctionAttrs summary bitset.
+  // Initialize AvailableFunctionAttrs and AvailableSomewhereAttrs
+  // summary bitsets.
   static_assert(attrIdxToArrayIdx(AttributeList::FunctionIndex) == 0U,
                 "function should be stored in slot 0");
-  for (const auto &I : Sets[0]) {
+  for (const auto &I : Sets[0])
     if (!I.isStringAttribute())
       AvailableFunctionAttrs.addAttribute(I.getKindAsEnum());
-  }
+
+  for (const auto &Set : Sets)
+    for (const auto &I : Set)
+      if (!I.isStringAttribute())
+        AvailableSomewhereAttrs.addAttribute(I.getKindAsEnum());
 }
 
 void AttributeListImpl::Profile(FoldingSetNodeID &ID) const {
@@ -996,6 +1001,24 @@ void AttributeListImpl::Profile(FoldingSetNodeID &ID,
     ID.AddPointer(Set.SetNode);
 }
 
+bool AttributeListImpl::hasAttrSomewhere(Attribute::AttrKind Kind,
+                                        unsigned *Index) const {
+  if (!AvailableSomewhereAttrs.hasAttribute(Kind))
+    return false;
+
+  if (Index) {
+    for (unsigned I = 0, E = NumAttrSets; I != E; ++I) {
+      if (begin()[I].hasAttribute(Kind)) {
+        *Index = I - 1;
+        break;
+      }
+    }
+  }
+
+  return true;
+}
+
+
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 LLVM_DUMP_METHOD void AttributeListImpl::dump() const {
   AttributeList(const_cast<AttributeListImpl *>(this)).dump();
@@ -1401,17 +1424,7 @@ bool AttributeList::hasParamAttribute(unsigned ArgNo,
 
 bool AttributeList::hasAttrSomewhere(Attribute::AttrKind Attr,
                                      unsigned *Index) const {
-  if (!pImpl) return false;
-
-  for (unsigned I = index_begin(), E = index_end(); I != E; ++I) {
-    if (hasAttribute(I, Attr)) {
-      if (Index)
-        *Index = I;
-      return true;
-    }
-  }
-
-  return false;
+  return pImpl && pImpl->hasAttrSomewhere(Attr, Index);
 }
 
 Attribute AttributeList::getAttribute(unsigned Index,