Add a late optimization to BranchFolding that hoist common instruction sequences
at the start of basic blocks to their common predecessor. It's actually quite
common (e.g. about 50 times in JM/lencod) and has shown to be a nice code size
benefit. e.g.

        pushq   %rax
        testl   %edi, %edi
        jne     LBB0_2
## BB#1:
        xorb    %al, %al
        popq    %rdx
        ret
LBB0_2:
        xorb    %al, %al
        callq   _foo
        popq    %rdx
        ret

=>

        pushq   %rax
        xorb    %al, %al
        testl   %edi, %edi
        je      LBB0_2
## BB#1:
        callq   _foo
LBB0_2:
        popq    %rdx
        ret

rdar://9145558


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@131172 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/CodeGen/BranchFolding.h b/lib/CodeGen/BranchFolding.h
index 15dfa7f..4daf4ec 100644
--- a/lib/CodeGen/BranchFolding.h
+++ b/lib/CodeGen/BranchFolding.h
@@ -19,11 +19,10 @@
   class RegScavenger;
   class TargetInstrInfo;
   class TargetRegisterInfo;
-  template<typename T> class SmallVectorImpl;
 
   class BranchFolder {
   public:
-    explicit BranchFolder(bool defaultEnableTailMerge);
+    explicit BranchFolder(bool defaultEnableTailMerge, bool CommonHoist);
 
     bool OptimizeFunction(MachineFunction &MF,
                           const TargetInstrInfo *tii,
@@ -85,6 +84,7 @@
     std::vector<SameTailElt> SameTails;
 
     bool EnableTailMerge;
+    bool EnableHoistCommonCode;
     const TargetInstrInfo *TII;
     const TargetRegisterInfo *TRI;
     MachineModuleInfo *MMI;
@@ -110,6 +110,9 @@
     bool OptimizeBlock(MachineBasicBlock *MBB);
     void RemoveDeadBlock(MachineBasicBlock *MBB);
     bool OptimizeImpDefsBlock(MachineBasicBlock *MBB);
+
+    bool HoistCommonCode(MachineFunction &MF);
+    bool HoistCommonCodeInSuccs(MachineBasicBlock *MBB);
   };
 }