X86 Peephole: fold loads to the source register operand if possible.

Machine CSE and other optimizations can remove instructions so folding
is possible at peephole while not possible at ISel.

This patch is a rework of r160919 and was tested on clang self-host on my local
machine.

rdar://10554090 and rdar://11873276


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@161152 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Target/TargetInstrInfo.h

@@ -14,6 +14,7 @@
 #ifndef LLVM_TARGET_TARGETINSTRINFO_H
 #define LLVM_TARGET_TARGETINSTRINFO_H
 
+#include "llvm/ADT/SmallSet.h"
 #include "llvm/MC/MCInstrInfo.h"
 #include "llvm/CodeGen/DFAPacketizer.h"
 #include "llvm/CodeGen/MachineFunction.h"
@@ -693,6 +694,16 @@ public:
     return false;
   }
 
+  /// optimizeLoadInstr - Try to remove the load by folding it to a register
+  /// operand at the use. We fold the load instructions if and only if the
+  /// def and use are in the same BB.
+  virtual MachineInstr* optimizeLoadInstr(MachineInstr *MI,
+                        const MachineRegisterInfo *MRI,
+                        unsigned &FoldAsLoadDefReg,
+                        MachineInstr *&DefMI) const {
+    return 0;
+  }
+
   /// FoldImmediate - 'Reg' is known to be defined by a move immediate
   /// instruction, try to fold the immediate into the use instruction.
   virtual bool FoldImmediate(MachineInstr *UseMI, MachineInstr *DefMI,