optimize single MBB loops better. In particular, produce:

LBB1_57:        #bb207.i
        movl 72(%esp), %ecx
        movb (%ecx,%eax), %cl
        movl 80(%esp), %edx
        movb %cl, 1(%edx,%eax)
        incl %eax
        cmpl $143, %eax
        jne LBB1_57     #bb207.i
        jmp LBB1_64     #cond_next255.i

intead of:

LBB1_57:        #bb207.i
        movl 72(%esp), %ecx
        movb (%ecx,%eax), %cl
        movl 80(%esp), %edx
        movb %cl, 1(%edx,%eax)
        incl %eax
        cmpl $143, %eax
        je LBB1_64      #cond_next255.i
        jmp LBB1_57     #bb207.i

This eliminates a branch per iteration of the loop.  This hurted PPC
particularly, because the extra branch meant another dispatch group for each
iteration of the loop.

llvm-svn: 31530

llvm/lib/CodeGen/BranchFolding.cpp

@@ -687,6 +687,23 @@ void BranchFolder::OptimizeBlock(MachineBasicBlock *MBB) {
                                        !CurCond.empty(),
                                        ++MachineFunction::iterator(MBB));
 
+    // If this is a two-way branch, and the FBB branches to this block, reverse 
+    // the condition so the single-basic-block loop is faster.  Instead of:
+    //    Loop: xxx; jcc Out; jmp Loop
+    // we want:
+    //    Loop: xxx; jncc Loop; jmp Out
+    if (CurTBB && CurFBB && CurFBB == MBB && CurTBB != MBB) {
+      std::vector<MachineOperand> NewCond(CurCond);
+      if (!TII->ReverseBranchCondition(NewCond)) {
+        TII->RemoveBranch(*MBB);
+        TII->InsertBranch(*MBB, CurFBB, CurTBB, NewCond);
+        MadeChange = true;
+        ++NumBranchOpts;
+        return OptimizeBlock(MBB);
+      }
+    }
+    
+    
     // If this branch is the only thing in its block, see if we can forward
     // other blocks across it.
     if (CurTBB && CurCond.empty() && CurFBB == 0 &&