From 207303b4af92c06ae34eea66e90dcdf72b81cd18 Mon Sep 17 00:00:00 2001
From: Kang Zhang <shkzhang@cn.ibm.com>
Date: Fri, 26 Jul 2019 01:58:53 +0000
Subject: [PATCH] [PowerPC] 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`.

Below is an example
```
BB:                   | BB:
   XOR 3, 3, 4        |   XOR 3, 3, 4
   B TBB              |   B ChainBB
...                   | ...
ChainBB:              | ChainBB:
   B TBB              |   ADD 3, 3, 4
...                   |   BLR
TBB:                  |
   ADD 3, 3, 4        |
   BLR                |
```

Reviewed By: efriedma

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

llvm-svn: 367080
---
 lib/CodeGen/MachineBlockPlacement.cpp      | 25 ++++++++++++++++++++++
 test/CodeGen/PowerPC/block-placement-1.mir | 10 ++-------
 test/CodeGen/PowerPC/block-placement.mir   | 12 ++++-------
 3 files changed, 31 insertions(+), 16 deletions(-)

diff --git a/lib/CodeGen/MachineBlockPlacement.cpp b/lib/CodeGen/MachineBlockPlacement.cpp
index 639b588766a..a469f893ce1 100644
--- a/lib/CodeGen/MachineBlockPlacement.cpp
+++ b/lib/CodeGen/MachineBlockPlacement.cpp
@@ -2730,6 +2730,31 @@ 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());
+          F->remove(TBB);
+        }
       }
     }
   }
diff --git a/test/CodeGen/PowerPC/block-placement-1.mir b/test/CodeGen/PowerPC/block-placement-1.mir
index 01967e46da9..fdd57cd4061 100644
--- a/test/CodeGen/PowerPC/block-placement-1.mir
+++ b/test/CodeGen/PowerPC/block-placement-1.mir
@@ -299,14 +299,8 @@ body:             |
   bb.11.unreachable:
 
   ; CHECK:      bb.1.for.body:
-  ; CHECK:        successors: %bb.2(0x7ffff800), %bb.3(0x00000800)
-  ; CHECK:        B %bb.2
+  ; CHECK-NEXT:   successors: %bb.3(0x00000800)
 
   ; CHECK:      bb.4.catch4:
-  ; CHECK:        successors: %bb.11(0x7ffff800), %bb.6(0x00000800)
-  ; CHECK:        B %bb.11
-
-  ; CHECK:      bb.2..noexc:
-
-  ; CHECK:      bb.11.unreachable: 
+  ; CHECK-NEXT:   %bb.6(0x00000800)
 ...
diff --git a/test/CodeGen/PowerPC/block-placement.mir b/test/CodeGen/PowerPC/block-placement.mir
index 9406e13b354..e413e3db2d5 100644
--- a/test/CodeGen/PowerPC/block-placement.mir
+++ b/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
 ...