[BOLT] Sort CallSiteInfo targets by symbol name in YAMLWriter

[Amir]

Summary

Align YAML and fdata profiles by sorting CallSiteInfo targets by symbol name,
aligning it to fdata. By default, YAML CallSiteInfo is sorted by function id,
which is the order of function in the binary.

Follow-up to D152731, aligning yaml vs fdata, and in turn all three between to
each other.

[Amir]

Ping @maksfb. This diff is a part of yaml vs fdata alignment.

[rafauler]

LGTM

bolt/lib/Profile/YAMLProfileWriter.cpp

for (const BinaryBasicBlock *BB : BF.dfs()) {
     }
 
     YamlBB.ExecCount = BB->getKnownExecutionCount();
 
     for (const MCInst &Instr : *BB) {
       if (!BC.MIB->isCall(Instr) && !BC.MIB->isIndirectBranch(Instr))
         continue;
 
+      SmallVector<std::pair<StringRef, yaml::bolt::CallSiteInfo>> CSTargets;
       yaml::bolt::CallSiteInfo CSI;
       std::optional<uint32_t> Offset = BC.MIB->getOffset(Instr);
       if (!Offset || *Offset < BB->getInputOffset())
         continue;
       CSI.Offset = *Offset - BB->getInputOffset();
 
       if (BC.MIB->isIndirectCall(Instr) || BC.MIB->isIndirectBranch(Instr)) {
         const auto ICSP = BC.MIB->tryGetAnnotationAs<IndirectCallSiteProfile>(
             Instr, "CallProfile");
         if (!ICSP)
           continue;
         for (const IndirectCallProfile &CSP : ICSP.get()) {
+          StringRef TargetName = "";
           CSI.DestId = 0; // designated for unknown functions
           CSI.EntryDiscriminator = 0;
           if (CSP.Symbol) {
             const BinaryFunction *Callee = BC.getFunctionForSymbol(CSP.Symbol);
-            if (Callee)
+            if (Callee) {
               CSI.DestId = Callee->getFunctionNumber();
+              TargetName = Callee->getOneName();
+            }
           }
           CSI.Count = CSP.Count;
           CSI.Mispreds = CSP.Mispreds;
-          YamlBB.CallSites.push_back(CSI);
+          CSTargets.emplace_back(TargetName, CSI);
         }
       } else { // direct call or a tail call
         uint64_t EntryID = 0;
+        CSI.DestId = 0;
+        StringRef TargetName = "";
         const MCSymbol *CalleeSymbol = BC.MIB->getTargetSymbol(Instr);
         const BinaryFunction *const Callee =
             BC.getFunctionForSymbol(CalleeSymbol, &EntryID);
         if (Callee) {
           CSI.DestId = Callee->getFunctionNumber();
           CSI.EntryDiscriminator = EntryID;
+          TargetName = Callee->getOneName();
         }
 
         if (BC.MIB->getConditionalTailCall(Instr)) {
           auto CTCCount =
               BC.MIB->tryGetAnnotationAs<uint64_t>(Instr, "CTCTakenCount");
           if (CTCCount) {
             CSI.Count = *CTCCount;
             auto CTCMispreds =
                 BC.MIB->tryGetAnnotationAs<uint64_t>(Instr, "CTCMispredCount");
             if (CTCMispreds)
               CSI.Mispreds = *CTCMispreds;
           }
         } else {
           auto Count = BC.MIB->tryGetAnnotationAs<uint64_t>(Instr, "Count");
           if (Count)
             CSI.Count = *Count;
         }
 
         if (CSI.Count)
-          YamlBB.CallSites.emplace_back(CSI);
+          CSTargets.emplace_back(TargetName, CSI);
       }
+      // Sort targets in a similar way to getBranchData, see Location::operator<
+      llvm::sort(CSTargets, [](const auto &RHS, const auto &LHS) {
+        if (RHS.first != LHS.first)
+          return RHS.first < LHS.first;
+        return RHS.second.Offset < LHS.second.Offset;
+      });
+      for (auto &KV : CSTargets)
+        YamlBB.CallSites.push_back(KV.second);
     }
 
-    llvm::sort(YamlBB.CallSites);
-
     // Skip printing if there's no profile data for non-entry basic block.
     // Include landing pads with non-zero execution count.
     if (YamlBB.CallSites.empty() && !BB->isEntryPoint() &&
         !(BB->isLandingPad() && BB->getKnownExecutionCount() != 0)) {
       // Include blocks having successors or predecessors with positive counts.
       uint64_t SuccessorExecCount = 0;
       for (const BinaryBasicBlock::BinaryBranchInfo &BranchInfo :
            BB->branch_info())