MachineSink: Sort the successors before trying to find SuccToSinkTo.

One motivating example is to sink an instruction from a basic block which has
two successors: one outside the loop, the other inside the loop. We should try
to sink the instruction outside the loop.

rdar://11980766


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@161062 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 69 insertions, 2 deletions

diff --git a/lib/CodeGen/MachineSink.cpp b/lib/CodeGen/MachineSink.cpp
index 1ce546b578..d02aa6fe60 100644
--- a/lib/CodeGen/MachineSink.cpp
+++ b/lib/CodeGen/MachineSink.cpp
@@ -99,6 +99,16 @@ namespace {
     bool PerformTrivialForwardCoalescing(MachineInstr *MI,
                                          MachineBasicBlock *MBB);
   };
+
+  // SuccessorSorter - Sort Successors according to their loop depth. 
+  struct SuccessorSorter {
+    SuccessorSorter(MachineLoopInfo *LoopInfo) : LI(LoopInfo) {}
+    bool operator()(const MachineBasicBlock *LHS,
+                    const MachineBasicBlock *RHS) const {
+      return LI->getLoopDepth(LHS) < LI->getLoopDepth(RHS);
+    }
+    MachineLoopInfo *LI;
+  };
 } // end anonymous namespace
 
 char MachineSinking::ID = 0;
@@ -526,8 +536,11 @@ MachineBasicBlock *MachineSinking::FindSuccToSinkTo(MachineInstr *MI,
 
       // Otherwise, we should look at all the successors and decide which one
       // we should sink to.
-      for (MachineBasicBlock::succ_iterator SI = MBB->succ_begin(),
-           E = MBB->succ_end(); SI != E; ++SI) {
+      // We give successors with smaller loop depth higher priority.
+      SmallVector<MachineBasicBlock*, 4> Succs(MBB->succ_begin(), MBB->succ_end());
+      std::sort(Succs.begin(), Succs.end(), SuccessorSorter(LI));
+      for (SmallVector<MachineBasicBlock*, 4>::iterator SI = Succs.begin(),
+           E = Succs.end(); SI != E; ++SI) {
         MachineBasicBlock *SuccBlock = *SI;
         bool LocalUse = false;
         if (AllUsesDominatedByBlock(Reg, SuccBlock, MBB,
diff --git a/test/CodeGen/X86/sink-out-of-loop.ll b/test/CodeGen/X86/sink-out-of-loop.ll
new file mode 100644
index 0000000000..c600f925a3
--- /dev/null
+++ b/test/CodeGen/X86/sink-out-of-loop.ll
@@ -0,0 +1,54 @@
+; RUN: llc -mtriple=x86_64-apple-darwin < %s | FileCheck %s
+
+; A MOV32ri is inside a loop, it has two successors, one successor is inside the
+; same loop, the other successor is outside the loop. We should be able to sink
+; MOV32ri outside the loop.
+; rdar://11980766
+define i32 @sink_succ(i32 %argc, i8** nocapture %argv) nounwind uwtable ssp {
+; CHECK: sink_succ
+; CHECK: [[OUTER_LN1:LBB0_[0-9]+]]: ## %preheader
+; CHECK: %exit
+; CHECK-NOT: movl
+; CHECK: jne [[OUTER_LN1]]
+; CHECK: movl
+; CHECK: [[LN2:LBB0_[0-9]+]]: ## %for.body2
+; CHECK: jne [[LN2]]
+; CHECK: ret
+entry:
+  br label %preheader
+
+preheader:
+  %i.127 = phi i32 [ 0, %entry ], [ %inc9, %exit ]
+  br label %for.body1.lr
+
+for.body1.lr:
+  %iv30 = phi i32 [ 1, %preheader ], [ %iv.next31, %for.inc40.i ]
+  br label %for.body1
+
+for.body1:
+  %iv.i = phi i64 [ 0, %for.body1.lr ], [ %iv.next.i, %for.body1 ]
+  %iv.next.i = add i64 %iv.i, 1
+  %lftr.wideiv32 = trunc i64 %iv.next.i to i32
+  %exitcond33 = icmp eq i32 %lftr.wideiv32, %iv30
+  br i1 %exitcond33, label %for.inc40.i, label %for.body1
+
+for.inc40.i:
+  %iv.next31 = add i32 %iv30, 1
+  %exitcond49.i = icmp eq i32 %iv.next31, 32
+  br i1 %exitcond49.i, label %exit, label %for.body1.lr
+
+exit:
+  %inc9 = add nsw i32 %i.127, 1
+  %exitcond34 = icmp eq i32 %inc9, 10
+  br i1 %exitcond34, label %for.body2, label %preheader
+
+for.body2:
+  %iv = phi i64 [ %iv.next, %for.body2 ], [ 0, %exit ]
+  %iv.next = add i64 %iv, 1
+  %lftr.wideiv = trunc i64 %iv.next to i32
+  %exitcond = icmp eq i32 %lftr.wideiv, 2048
+  br i1 %exitcond, label %for.end20, label %for.body2
+
+for.end20:
+  ret i32 0
+}