Memory intrinsic value profile optimization: Improve debug output (NFC)

[tejohnson]

Summary

Misc improvements to debug output. Fix a couple typos and also dump the
value profile before we make any profitability checks.

[davidxl]

lgtm

lib/Transforms/Instrumentation/IndirectCallPromotion.cpp

void perform() {
     WorkList.clear();
     visit(Func);
 
     for (auto &MI : WorkList) {
       ++NumOfPGOMemOPAnnotate;
       if (perform(MI)) {
         Changed = true;
         ++NumOfPGOMemOPOpt;
-        DEBUG(dbgs() << "MemOP calls: " << MI->getCalledFunction()->getName()
+        DEBUG(dbgs() << "MemOP call: " << MI->getCalledFunction()->getName()
                      << "is Transformed.\n");
       }
     }
   }
 
   void visitMemIntrinsic(MemIntrinsic &MI) {
     Value *Length = MI.getLength();
     // Not perform on constant length calls.
bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
   uint64_t SavedTotalCount = TotalCount;
   if (MemOPScaleCount) {
     auto BBEdgeCount = BFI.getBlockProfileCount(MI->getParent());
     if (!BBEdgeCount)
       return false;
     ActualCount = *BBEdgeCount;
   }
 
+  ArrayRef<InstrProfValueData> VDs(ValueDataArray.get(), NumVals);
+  DEBUG(dbgs() << "Read one memory intrinsic profile with count " << ActualCount
+               << "\n");
+  DEBUG(
+      for (auto &VD
+           : VDs) { dbgs() << "  (" << VD.Value << "," << VD.Count << ")\n"; });
+
   if (ActualCount < MemOPCountThreshold)
     return false;
 
-  ArrayRef<InstrProfValueData> VDs(ValueDataArray.get(), NumVals);
   TotalCount = ActualCount;
   if (MemOPScaleCount)
-    DEBUG(dbgs() << "Scale counts: numberator = " << ActualCount
+    DEBUG(dbgs() << "Scale counts: numerator = " << ActualCount
                  << " denominator = " << SavedTotalCount << "\n");
 
   // Keeping track of the count of the default case:
   uint64_t RemainCount = TotalCount;
   SmallVector<uint64_t, 16> SizeIds;
   SmallVector<uint64_t, 16> CaseCounts;
   uint64_t MaxCount = 0;
   unsigned Version = 0;
bool MemOPSizeOpt::perform(MemIntrinsic *MI) {
   if (Version == 0)
     return false;
 
   CaseCounts[0] = RemainCount;
   if (RemainCount > MaxCount)
     MaxCount = RemainCount;
 
   uint64_t SumForOpt = TotalCount - RemainCount;
-  DEBUG(dbgs() << "Read one memory intrinsic profile: " << SumForOpt << " vs "
-               << TotalCount << "\n");
-  DEBUG(
-      for (auto &VD
-           : VDs) { dbgs() << "  (" << VD.Value << "," << VD.Count << ")\n"; });
 
   DEBUG(dbgs() << "Optimize one memory intrinsic call to " << Version
-               << " Versions\n");
+               << " Versions (covering " << SumForOpt << " out of "
+               << TotalCount << ")\n");
 
   // mem_op(..., size)
   // ==>
   // switch (size) {
   //   case s1:
   //      mem_op(..., s1);
   //      goto merge_bb;
   //   case s2: