Refactor target hook for tail duplication as requested by Chris.

Make tail duplication of indirect branches much more aggressive (for targets
that indicate that it is profitable), based on further experience with
this transformation.  I compiled 3 large applications with and without
this more aggressive tail duplication and measured minimal changes in code
size.  ("size" on Darwin seems to round the text size up to the nearest
page boundary, so I can only say that any code size increase was less than
one 4k page.) Radar 7421267.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@89814 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Target/TargetInstrInfo.h

@@ -544,12 +544,9 @@ public:
   virtual unsigned getInlineAsmLength(const char *Str,
                                       const MCAsmInfo &MAI) const;
 
-  /// TailDuplicationLimit - Returns the limit on the number of instructions
-  /// in basic block MBB beyond which it will not be tail-duplicated.
-  virtual unsigned TailDuplicationLimit(const MachineBasicBlock &MBB,
-                                        unsigned DefaultLimit) const {
-    return DefaultLimit;
-  }
+  /// isProfitableToDuplicateIndirectBranch - Returns true if tail duplication
+  /// is especially profitable for indirect branches.
+  virtual bool isProfitableToDuplicateIndirectBranch() const { return false; }
 };
 
 /// TargetInstrInfoImpl - This is the default implementation of

lib/CodeGen/BranchFolding.cpp

@@ -1043,9 +1043,18 @@ bool BranchFolder::TailDuplicate(MachineBasicBlock *TailBB,
   // of one less than the tail-merge threshold. When optimizing for size,
   // duplicate only one, because one branch instruction can be eliminated to
   // compensate for the duplication.
-  unsigned MaxDuplicateCount =
-    MF.getFunction()->hasFnAttr(Attribute::OptimizeForSize) ?
-    1 : TII->TailDuplicationLimit(*TailBB, TailMergeSize - 1);
+  unsigned MaxDuplicateCount;
+  if (MF.getFunction()->hasFnAttr(Attribute::OptimizeForSize))
+    MaxDuplicateCount = 1;
+  else if (TII->isProfitableToDuplicateIndirectBranch() &&
+           !TailBB->empty() && TailBB->back().getDesc().isIndirectBranch())
+    // If the target has hardware branch prediction that can handle indirect
+    // branches, duplicating them can often make them predictable when there
+    // are common paths through the code.  The limit needs to be high enough
+    // to allow undoing the effects of tail merging.
+    MaxDuplicateCount = 20;
+  else
+    MaxDuplicateCount = TailMergeSize - 1;
 
   // Check the instructions in the block to determine whether tail-duplication
   // is invalid or unlikely to be profitable.

lib/Target/ARM/ARMBaseInstrInfo.cpp

@@ -1027,14 +1027,10 @@ bool ARMBaseInstrInfo::isIdentical(const MachineInstr *MI0,
   return TargetInstrInfoImpl::isIdentical(MI0, MI1, MRI);
 }
 
-unsigned ARMBaseInstrInfo::TailDuplicationLimit(const MachineBasicBlock &MBB,
-                                                unsigned DefaultLimit) const {
+bool ARMBaseInstrInfo::isProfitableToDuplicateIndirectBranch() const {
   // If the target processor can predict indirect branches, it is highly
   // desirable to duplicate them, since it can often make them predictable.
-  if (!MBB.empty() && isIndirectBranchOpcode(MBB.back().getOpcode()) &&
-      getSubtarget().hasBranchTargetBuffer())
-    return DefaultLimit + 2;
-  return DefaultLimit;
+  return getSubtarget().hasBranchTargetBuffer();
 }
 
 /// getInstrPredicate - If instruction is predicated, returns its predicate

lib/Target/ARM/ARMBaseInstrInfo.h

@@ -291,8 +291,7 @@ public:
   virtual bool isIdentical(const MachineInstr *MI, const MachineInstr *Other,
                            const MachineRegisterInfo *MRI) const;
 
-  virtual unsigned TailDuplicationLimit(const MachineBasicBlock &MBB,
-                                        unsigned DefaultLimit) const;
+  virtual bool isProfitableToDuplicateIndirectBranch() const;
 };
 
 static inline