[CodeGen] Do the Simple Early Return in block-placement pass to optimize the blocks

Summary:

Fix a bug of preducessors.

In `block-placement` pass, it will create some patterns for unconditional we can do the simple early retrun.
But the `early-ret` pass is before `block-placement`, we don't want to run it again.
This patch is to do the simple early return to optimize the blocks at the last of `block-placement`.

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D63972


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@369191 91177308-0d34-0410-b5e6-96231b3b80d8

lib/CodeGen/MachineBlockPlacement.cpp

@@ -2711,6 +2711,7 @@ void MachineBlockPlacement::optimizeBranches() {
   // cannot because all branches may not be analyzable.
   // E.g., the target may be able to remove an unconditional branch to
   // a fallthrough when it occurs after predicated terminators.
+  SmallVector<MachineBasicBlock*, 4> EmptyBB;
   for (MachineBasicBlock *ChainBB : FunctionChain) {
     Cond.clear();
     MachineBasicBlock *TBB = nullptr, *FBB = nullptr; // For AnalyzeBranch.
@@ -2730,9 +2731,45 @@ void MachineBlockPlacement::optimizeBranches() {
         TII->removeBranch(*ChainBB);
         TII->insertBranch(*ChainBB, FBB, TBB, Cond, dl);
         ChainBB->updateTerminator();
+      } else if (Cond.empty() && TBB && ChainBB != TBB && !TBB->empty() &&
+                 !TBB->canFallThrough()) {
+        // When ChainBB is unconditional branch to the TBB, and TBB has no
+        // fallthrough predecessor and fallthrough successor, try to merge
+        // ChainBB and TBB. This is legal under the one of following conditions:
+        // 1. ChainBB is empty except for an unconditional branch.
+        // 2. TBB has only one predecessor.
+        MachineFunction::iterator I(TBB);
+        if (((TBB == &*F->begin()) || !std::prev(I)->canFallThrough()) &&
+             (TailDup.isSimpleBB(ChainBB) || (TBB->pred_size() == 1))) {
+          TII->removeBranch(*ChainBB);
+          ChainBB->removeSuccessor(TBB);
+
+          // Update the CFG.
+          while (!TBB->pred_empty()) {
+            MachineBasicBlock *Pred = *(TBB->pred_end() - 1);
+            Pred->ReplaceUsesOfBlockWith(TBB, ChainBB);
+          }
+
+          while (!TBB->succ_empty()) {
+            MachineBasicBlock *Succ = *(TBB->succ_end() - 1);
+            ChainBB->addSuccessor(Succ, MBPI->getEdgeProbability(TBB, Succ));
+            TBB->removeSuccessor(Succ);
+          }
+
+          // Move all the instructions of TBB to ChainBB.
+          ChainBB->splice(ChainBB->end(), TBB, TBB->begin(), TBB->end());
+          EmptyBB.push_back(TBB);
+        }
       }
     }
   }
+
+  for (auto BB: EmptyBB) {
+    MLI->removeBlock(BB);
+    FunctionChain.remove(BB);
+    BlockToChain.erase(BB);
+    F->erase(BB);
+  }
 }
 
 void MachineBlockPlacement::alignBlocks() {
@@ -3052,6 +3089,9 @@ bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &MF) {
     }
   }
 
+  // optimizeBranches() may change the blocks, but we haven't updated the
+  // post-dominator tree. Because the post-dominator tree won't be used after
+  // this function and this pass don't preserve the post-dominator tree.
   optimizeBranches();
   alignBlocks();
 

test/CodeGen/PowerPC/block-placement.mir

@@ -209,14 +209,10 @@ body:             |
     BLR8 implicit $lr8, implicit $rm, implicit killed $x3
 
   ; CHECK:      bb.5.if.else.i:
-  ; CHECK:        successors: %bb.11(0x80000000)
-  ; CHECK:        B %bb.11
+  ; CHECK-NEXT:   renamable $x3 = LI8 1
+  ; CHECK-NEXT:   BLR8 implicit $lr8, implicit $rm, implicit killed $x3
 
   ; CHECK:      bb.8.while.body.i (align 4):
-  ; CHECK:        successors: %bb.11(0x04000000), %bb.9(0x7c000000)
-  ; CHECK:        BCC 76, killed renamable $cr0, %bb.11
-
-  ; CHECK:      bb.11:
-  ; CHECK:        renamable $x3 = LI8 1
-  ; CHECK-NEXT:   BLR8 implicit $lr8, implicit $rm, implicit killed $x3
+  ; CHECK:        successors: %bb.5(0x04000000), %bb.9(0x7c000000)
+  ; CHECK:        BCC 76, killed renamable $cr0, %bb.5
 ...