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

Summary:

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

llvm-svn: 368509

1 files changed, 36 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/MachineBlockPlacement.cpp b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
index 3000a7d..c34166d 100644
--- a/llvm/lib/CodeGen/MachineBlockPlacement.cpp
+++ b/llvm/lib/CodeGen/MachineBlockPlacement.cpp
@@ -2755,6 +2755,7 @@ 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.
@@ -2774,9 +2775,41 @@ void MachineBlockPlacement::optimizeBranches() {
         TII->removeBranch(*ChainBB);
         TII->insertBranch(*ChainBB, FBB, TBB, Cond, dl);
         ChainBB->updateTerminator();
+      } else if (Cond.empty() && TBB && ChainBB != TBB &&
+                 !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.
+          for (MachineBasicBlock::pred_iterator PI = TBB->pred_begin(),
+               PE = TBB->pred_end(); PI != PE; PI++)
+            (*PI)->ReplaceUsesOfBlockWith(TBB, ChainBB);
+
+          for (MachineBasicBlock *Succ : TBB->successors())
+            ChainBB->addSuccessor(Succ, MBPI->getEdgeProbability(TBB, 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() {
@@ -3096,6 +3129,9 @@ 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();