Index: C:/LLVM/llvm/include/llvm/TableGen/Record.h
===================================================================
--- C:/LLVM/llvm/include/llvm/TableGen/Record.h
+++ C:/LLVM/llvm/include/llvm/TableGen/Record.h
@@ -1307,9 +1307,12 @@
   }
 
   bool isSubClassOf(StringRef Name) const {
-    for (const auto &SCPair : SuperClasses)
+    for (const auto &SCPair : SuperClasses) {
+      // TODO: getNameInitAsString copy constructs a new std::string,
+      // yet we're only using it in this comparison. Is there a better way?
       if (SCPair.first->getNameInitAsString() == Name)
         return true;
+    }
     return false;
   }
 
Index: C:/LLVM/llvm/utils/TableGen/CodeGenInstruction.cpp
===================================================================
--- C:/LLVM/llvm/utils/TableGen/CodeGenInstruction.cpp
+++ C:/LLVM/llvm/utils/TableGen/CodeGenInstruction.cpp
@@ -49,6 +49,11 @@
 
   unsigned MIOperandNo = 0;
   std::set<std::string> OperandNames;
+
+  // TODO: can we reserve space for e elements in OperandList?
+  // Profiling a debug build with ETW revealed that the emplace_back
+  // at the very bottom of this loop can take up to 227ms, largely
+  // spent in reallocation.
   for (unsigned i = 0, e = InDI->getNumArgs()+OutDI->getNumArgs(); i != e; ++i){
     Init *ArgInit;
     std::string ArgName;
Index: C:/LLVM/llvm/utils/TableGen/CodeGenTarget.cpp
===================================================================
--- C:/LLVM/llvm/utils/TableGen/CodeGenTarget.cpp
+++ C:/LLVM/llvm/utils/TableGen/CodeGenTarget.cpp
@@ -441,12 +441,24 @@
   std::vector<Record*> I = RC.getAllDerivedDefinitions("Intrinsic");
 
   std::vector<CodeGenIntrinsic> Result;
+  
+  // Allocate enough memory to hold enough for worst case scenario
+  // in the following loop. Profiling a debug build with ETW
+  // revealed that push_back in the loop could take up to 280ms,
+  // largely spent in reallocation.
+  Result.reserve(I.size());
 
   for (unsigned i = 0, e = I.size(); i != e; ++i) {
     bool isTarget = I[i]->getValueAsBit("isTarget");
     if (isTarget == TargetOnly)
       Result.push_back(CodeGenIntrinsic(I[i]));
   }
+
+  // TODO: does this lambda need to accept parameters by value?
+  // Profiling a debug build with ETW revealed that each call of
+  // std::_Unguarded_partition (an internal function, called by std::sort),
+  // can spend hundreds of milliseconds inside this lambda calling
+  // ~CodeGenIntrinsic(), which is quite wasteful.
   std::sort(Result.begin(), Result.end(),
             [](CodeGenIntrinsic LHS, CodeGenIntrinsic RHS) {
               return LHS.Name < RHS.Name;