[clang] 8c7f0ea - Reduce memory usage in AST parent map generation by lazily checking if nodes have been seen (#129934)

[via cfe-commits]

Author: higher-performance
Date: 2025-03-13T16:02:39-04:00
New Revision: 8c7f0eaa6ee3f84e3d8260535cced234bed4fa28

URL: https://github.com/llvm/llvm-project/commit/8c7f0eaa6ee3f84e3d8260535cced234bed4fa28
DIFF: https://github.com/llvm/llvm-project/commit/8c7f0eaa6ee3f84e3d8260535cced234bed4fa28.diff

LOG: Reduce memory usage in AST parent map generation by lazily checking if nodes have been seen (#129934)

This mitigates a regression introduced in #87824.

The mitigation here is to store pointers the deduplicated AST nodes, rather than copies of the nodes themselves. This allows a pointer-optimized set to be used and saves a lot of memory because `clang::DynTypedNode` is ~5 times larger than a pointer.

Fixes #129808.

Added: 
    

Modified: 
    clang/lib/AST/ParentMapContext.cpp

Removed: 
    


################################################################################
diff  --git a/clang/lib/AST/ParentMapContext.cpp b/clang/lib/AST/ParentMapContext.cpp
index e9387ec79c373..6337605a07738 100644
--- a/clang/lib/AST/ParentMapContext.cpp
+++ b/clang/lib/AST/ParentMapContext.cpp
@@ -12,10 +12,11 @@
 //===----------------------------------------------------------------------===//
 
 #include "clang/AST/ParentMapContext.h"
-#include "clang/AST/RecursiveASTVisitor.h"
 #include "clang/AST/Decl.h"
 #include "clang/AST/Expr.h"
+#include "clang/AST/RecursiveASTVisitor.h"
 #include "clang/AST/TemplateBase.h"
+#include "llvm/ADT/SmallPtrSet.h"
 
 using namespace clang;
 
@@ -69,17 +70,21 @@ class ParentMapContext::ParentMap {
       for (; N > 0; --N)
         push_back(Value);
     }
-    bool contains(const DynTypedNode &Value) {
-      return Seen.contains(Value);
+    bool contains(const DynTypedNode &Value) const {
+      const void *Identity = Value.getMemoizationData();
+      assert(Identity);
+      return Dedup.contains(Identity);
     }
     void push_back(const DynTypedNode &Value) {
-      if (!Value.getMemoizationData() || Seen.insert(Value).second)
+      const void *Identity = Value.getMemoizationData();
+      if (!Identity || Dedup.insert(Identity).second) {
         Items.push_back(Value);
+      }
     }
     llvm::ArrayRef<DynTypedNode> view() const { return Items; }
   private:
-    llvm::SmallVector<DynTypedNode, 2> Items;
-    llvm::SmallDenseSet<DynTypedNode, 2> Seen;
+    llvm::SmallVector<DynTypedNode, 1> Items;
+    llvm::SmallPtrSet<const void *, 2> Dedup;
   };
 
   /// Maps from a node to its parents. This is used for nodes that have