[llvm] [BOLT][NFC] Store FILE symbols in a vector (PR #89088)

[Amir Ayupov via llvm-commits]

https://github.com/aaupov updated https://github.com/llvm/llvm-project/pull/89088

>From 1f821db5090237d0eee70caece0a4f994768f539 Mon Sep 17 00:00:00 2001
From: Amir Ayupov <aaupov at fb.com>
Date: Wed, 17 Apr 2024 16:14:46 +0200
Subject: [PATCH] [BOLT][NFC] Keep FILE symbols in a vector

In discoverFileObjects, replace mapping from every local symbol to
associated file name with a vector of symbol data for FILE symbols
only. This cuts down on memory needed to resolve local file names.

Test Plan: NFC
---
 bolt/lib/Rewrite/RewriteInstance.cpp | 33 ++++++++++------------------
 1 file changed, 12 insertions(+), 21 deletions(-)

diff --git a/bolt/lib/Rewrite/RewriteInstance.cpp b/bolt/lib/Rewrite/RewriteInstance.cpp
index 0c8ee0d417233b..916a74095f58b7 100644
--- a/bolt/lib/Rewrite/RewriteInstance.cpp
+++ b/bolt/lib/Rewrite/RewriteInstance.cpp
@@ -813,14 +813,7 @@ void RewriteInstance::discoverFileObjects() {
 
   // For local symbols we want to keep track of associated FILE symbol name for
   // disambiguation by combined name.
-  StringRef FileSymbolName;
-  bool SeenFileName = false;
-  struct SymbolRefHash {
-    size_t operator()(SymbolRef const &S) const {
-      return std::hash<decltype(DataRefImpl::p)>{}(S.getRawDataRefImpl().p);
-    }
-  };
-  std::unordered_map<SymbolRef, StringRef, SymbolRefHash> SymbolToFileName;
+  std::vector<DataRefImpl> FileSymbols;
   for (const ELFSymbolRef &Symbol : InputFile->symbols()) {
     Expected<StringRef> NameOrError = Symbol.getName();
     if (NameOrError && NameOrError->starts_with("__asan_init")) {
@@ -846,13 +839,8 @@ void RewriteInstance::discoverFileObjects() {
       // and this uncertainty is causing havoc in function name matching.
       if (Name == "ld-temp.o")
         continue;
-      FileSymbolName = Name;
-      SeenFileName = true;
-      continue;
+      FileSymbols.emplace_back(Symbol.getRawDataRefImpl());
     }
-    if (!FileSymbolName.empty() &&
-        !(cantFail(Symbol.getFlags()) & SymbolRef::SF_Global))
-      SymbolToFileName[Symbol] = FileSymbolName;
   }
 
   // Sort symbols in the file by value. Ignore symbols from non-allocatable
@@ -1027,14 +1015,17 @@ void RewriteInstance::discoverFileObjects() {
       // The <id> field is used for disambiguation of local symbols since there
       // could be identical function names coming from identical file names
       // (e.g. from different directories).
-      std::string AltPrefix;
-      auto SFI = SymbolToFileName.find(Symbol);
-      if (SymbolType == SymbolRef::ST_Function && SFI != SymbolToFileName.end())
-        AltPrefix = Name + "/" + std::string(SFI->second);
+      auto CompareSymsByIdx = [](const DataRefImpl &A, const DataRefImpl &B) {
+        return A.d.b < B.d.b;
+      };
+      DataRefImpl SymDataRef = Symbol.getRawDataRefImpl();
+      auto It = llvm::upper_bound(FileSymbols, SymDataRef, CompareSymsByIdx);
+      if (SymbolType == SymbolRef::ST_Function && It != FileSymbols.begin()) {
+        StringRef FileName = cantFail(SymbolRef(It[-1], InputFile).getName());
+        AlternativeName = NR.uniquify(Name + "/" + FileName.str());
+      }
 
       UniqueName = NR.uniquify(Name);
-      if (!AltPrefix.empty())
-        AlternativeName = NR.uniquify(AltPrefix);
     }
 
     uint64_t SymbolSize = ELFSymbolRef(Symbol).getSize();
@@ -1285,7 +1276,7 @@ void RewriteInstance::discoverFileObjects() {
                              FDE->getAddressRange());
   }
 
-  BC->setHasSymbolsWithFileName(SeenFileName);
+  BC->setHasSymbolsWithFileName(!FileSymbols.empty());
 
   // Now that all the functions were created - adjust their boundaries.
   adjustFunctionBoundaries();