[clang-tools-extra] [clang-doc] Improve performance by adding a short circuit (PR #96809)

[via cfe-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-clang-tools-extra

Author: None (PeterChou1)

<details>
<summary>Changes</summary>

This patch adds a short circuit which address performance problem referenced in 
issue: https://github.com/llvm/llvm-project/issues/96570

>From my local testing it cut the runtime of generating LLVM docs from 10 hours to 30 mins



---
Full diff: https://github.com/llvm/llvm-project/pull/96809.diff


1 Files Affected:

- (modified) clang-tools-extra/clang-doc/Mapper.cpp (+19-1) 


``````````diff
diff --git a/clang-tools-extra/clang-doc/Mapper.cpp b/clang-tools-extra/clang-doc/Mapper.cpp
index bb8b7952980ac..b9ca6edd03b8c 100644
--- a/clang-tools-extra/clang-doc/Mapper.cpp
+++ b/clang-tools-extra/clang-doc/Mapper.cpp
@@ -12,11 +12,17 @@
 #include "clang/AST/Comment.h"
 #include "clang/Index/USRGeneration.h"
 #include "llvm/ADT/StringExtras.h"
-#include "llvm/Support/Error.h"
+#include "llvm/Support/Mutex.h"
+#include <unordered_set>
 
 namespace clang {
 namespace doc {
 
+
+static std::unordered_set<std::string> USRVisited;
+
+static llvm::sys::Mutex USRVisitedGuard;
+
 void MapASTVisitor::HandleTranslationUnit(ASTContext &Context) {
   TraverseDecl(Context.getTranslationUnitDecl());
 }
@@ -34,6 +40,17 @@ template <typename T> bool MapASTVisitor::mapDecl(const T *D) {
   // If there is an error generating a USR for the decl, skip this decl.
   if (index::generateUSRForDecl(D, USR))
     return true;
+
+  // Prevent Visiting USR twice
+  {
+    std::lock_guard<llvm::sys::Mutex> Guard(USRVisitedGuard);
+    std::string Visited = USR.str().str();
+    if (USRVisited.count(Visited)) {
+      return true;
+    }
+    USRVisited.insert(Visited);
+  }
+
   bool IsFileInRootDir;
   llvm::SmallString<128> File =
       getFile(D, D->getASTContext(), CDCtx.SourceRoot, IsFileInRootDir);
@@ -41,6 +58,7 @@ template <typename T> bool MapASTVisitor::mapDecl(const T *D) {
                                getLine(D, D->getASTContext()), File,
                                IsFileInRootDir, CDCtx.PublicOnly);
 
+
   // A null in place of I indicates that the serializer is skipping this decl
   // for some reason (e.g. we're only reporting public decls).
   if (I.first)

``````````

</details>


https://github.com/llvm/llvm-project/pull/96809