[clang] SourceManager: Cache offsets for LastFileIDLookup to speed up getFileID (llvm#146782)

`getFileID` is a hot method. By caching the offset range in
`LastFileIDLookup`, we can more quickly check whether a given offset
falls within it, avoiding calling `isOffsetInFileID`.

https://llvm-compile-time-tracker.com/compare.php?from=0588e8188c647460b641b09467fe6b13a8d510d5&to=64843a500f0191b79a8109da9acd7e80d961c7a3&stat=instructions:u

Author: hokein

clang/include/clang/Basic/SourceManager.h

@@ -767,6 +767,8 @@ class SourceManager : public RefCountedBase<SourceManager> {
   /// LastFileIDLookup records the last FileID looked up or created, because it
   /// is very common to look up many tokens from the same file.
   mutable FileID LastFileIDLookup;
+  mutable SourceLocation::UIntTy LastLookupStartOffset;
+  mutable SourceLocation::UIntTy LastLookupEndOffset; // exclude
 
   /// Holds information for \#line directives.
   ///
@@ -1904,9 +1906,8 @@ class SourceManager : public RefCountedBase<SourceManager> {
 
   FileID getFileID(SourceLocation::UIntTy SLocOffset) const {
     // If our one-entry cache covers this offset, just return it.
-    if (isOffsetInFileID(LastFileIDLookup, SLocOffset))
+    if (SLocOffset >= LastLookupStartOffset && SLocOffset < LastLookupEndOffset)
       return LastFileIDLookup;
-
     return getFileIDSlow(SLocOffset);
   }
 

clang/lib/Basic/SourceManager.cpp

@@ -335,6 +335,7 @@ void SourceManager::clearIDTables() {
   LastLineNoFileIDQuery = FileID();
   LastLineNoContentCache = nullptr;
   LastFileIDLookup = FileID();
+  LastLookupStartOffset = LastLookupEndOffset = 0;
 
   IncludedLocMap.clear();
   if (LineTable)
@@ -640,9 +641,11 @@ FileID SourceManager::createFileIDImpl(ContentCache &File, StringRef Filename,
   LocalSLocEntryTable.push_back(
       SLocEntry::get(NextLocalOffset,
                      FileInfo::get(IncludePos, File, FileCharacter, Filename)));
+  LastLookupStartOffset = NextLocalOffset;
   // We do a +1 here because we want a SourceLocation that means "the end of the
   // file", e.g. for the "no newline at the end of the file" diagnostic.
   NextLocalOffset += FileSize + 1;
+  LastLookupEndOffset = NextLocalOffset;
   updateSlocUsageStats();
 
   // Set LastFileIDLookup to the newly created file.  The next getFileID call is
@@ -812,8 +815,9 @@ FileID SourceManager::getFileIDSlow(SourceLocation::UIntTy SLocOffset) const {
 /// loaded one.
 FileID SourceManager::getFileIDLocal(SourceLocation::UIntTy SLocOffset) const {
   assert(SLocOffset < NextLocalOffset && "Bad function choice");
-  assert(SLocOffset >= LocalSLocEntryTable[0].getOffset() &&
+  assert(SLocOffset >= LocalSLocEntryTable[0].getOffset() && SLocOffset > 0 &&
          "Invalid SLocOffset");
+  assert(LastFileIDLookup.ID >= 0 && "Only cache local file sloc entry");
 
   // After the first and second level caches, I see two common sorts of
   // behavior: 1) a lot of searched FileID's are "near" the cached file
@@ -833,13 +837,11 @@ FileID SourceManager::getFileIDLocal(SourceLocation::UIntTy SLocOffset) const {
   unsigned LessIndex = 0;
   // upper bound of the search range.
   unsigned GreaterIndex = LocalSLocEntryTable.size();
-  if (LastFileIDLookup.ID >= 0) {
-    // Use the LastFileIDLookup to prune the search space.
-    if (LocalSLocEntryTable[LastFileIDLookup.ID].getOffset() < SLocOffset)
-      LessIndex = LastFileIDLookup.ID;
-    else
-      GreaterIndex = LastFileIDLookup.ID;
-  }
+  // Use the LastFileIDLookup to prune the search space.
+  if (LastLookupStartOffset < SLocOffset)
+    LessIndex = LastFileIDLookup.ID;
+  else
+    GreaterIndex = LastFileIDLookup.ID;
 
   // Find the FileID that contains this.
   unsigned NumProbes = 0;
@@ -850,7 +852,12 @@ FileID SourceManager::getFileIDLocal(SourceLocation::UIntTy SLocOffset) const {
       FileID Res = FileID::get(int(GreaterIndex));
       // Remember it.  We have good locality across FileID lookups.
       LastFileIDLookup = Res;
-      NumLinearScans += NumProbes+1;
+      LastLookupStartOffset = LocalSLocEntryTable[GreaterIndex].getOffset();
+      LastLookupEndOffset =
+          GreaterIndex + 1 >= LocalSLocEntryTable.size()
+              ? NextLocalOffset
+              : LocalSLocEntryTable[GreaterIndex + 1].getOffset();
+      NumLinearScans += NumProbes + 1;
       return Res;
     }
     if (++NumProbes == 8)
@@ -874,6 +881,8 @@ FileID SourceManager::getFileIDLocal(SourceLocation::UIntTy SLocOffset) const {
   // At this point, LessIndex is the index of the *first element greater than*
   // SLocOffset. The element we are actually looking for is the one immediately
   // before it.
+  LastLookupStartOffset = LocalSLocEntryTable[LessIndex - 1].getOffset();
+  LastLookupEndOffset = LocalSLocEntryTable[LessIndex].getOffset();
   return LastFileIDLookup = FileID::get(LessIndex - 1);
 }