From 21f8ac235ec3c1312f835c988a7c2b456a702806 Mon Sep 17 00:00:00 2001
From: Xin Tong <trent.xin.tong@gmail.com>
Date: Mon, 1 May 2017 15:34:17 +0000
Subject: [PATCH] [JumpThread] Do RAUW in case Cond folds to a constant in the
 CFG

Summary: [JumpThread] Do RAUW in case Cond folds to a constant in the CFG

Reviewers: sanjoy

Reviewed By: sanjoy

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D32407

llvm-svn: 301804
---
 llvm/lib/Transforms/Scalar/JumpThreading.cpp       | 32 +++++++++---
 .../Transforms/JumpThreading/fold-not-thread.ll    | 57 ++++++++++++++++++++++
 2 files changed, 81 insertions(+), 8 deletions(-)

diff --git a/llvm/lib/Transforms/Scalar/JumpThreading.cpp b/llvm/lib/Transforms/Scalar/JumpThreading.cpp
index 340b0d0..d9717628 100644
--- a/llvm/lib/Transforms/Scalar/JumpThreading.cpp
+++ b/llvm/lib/Transforms/Scalar/JumpThreading.cpp
@@ -1250,6 +1250,8 @@ bool JumpThreadingPass::ProcessThreadableEdges(Value *Cond, BasicBlock *BB,
 
   BasicBlock *OnlyDest = nullptr;
   BasicBlock *MultipleDestSentinel = (BasicBlock*)(intptr_t)~0ULL;
+  Constant *OnlyVal = nullptr;
+  Constant *MultipleVal = (Constant *)(intptr_t)~0ULL;
 
   for (const auto &PredValue : PredValues) {
     BasicBlock *Pred = PredValue.second;
@@ -1277,10 +1279,17 @@ bool JumpThreadingPass::ProcessThreadableEdges(Value *Cond, BasicBlock *BB,
     }
 
     // If we have exactly one destination, remember it for efficiency below.
-    if (PredToDestList.empty())
+    if (PredToDestList.empty()) {
       OnlyDest = DestBB;
-    else if (OnlyDest != DestBB)
-      OnlyDest = MultipleDestSentinel;
+      OnlyVal = Val;
+    } else {
+      if (OnlyDest != DestBB)
+        OnlyDest = MultipleDestSentinel;
+      // It possible we have same destination, but different value, e.g. default
+      // case in switchinst.
+      if (Val != OnlyVal)
+        OnlyVal = MultipleVal;
+    }
 
     PredToDestList.push_back(std::make_pair(Pred, DestBB));
   }
@@ -1310,11 +1319,18 @@ bool JumpThreadingPass::ProcessThreadableEdges(Value *Cond, BasicBlock *BB,
 
       // If the condition is now dead due to the removal of the old terminator,
       // erase it.
-      auto *CondInst = dyn_cast<Instruction>(Cond);
-      if (CondInst && CondInst->use_empty())
-        CondInst->eraseFromParent();
-      // FIXME: in case this instruction is defined in the current BB and it
-      // resolves to a single value from all predecessors, we can do RAUW.
+      if (auto *CondInst = dyn_cast<Instruction>(Cond)) {
+        if (CondInst->use_empty() && !CondInst->mayHaveSideEffects())
+          CondInst->eraseFromParent();
+        else if (OnlyVal && OnlyVal != MultipleVal &&
+                 CondInst->getParent() == BB) {
+          // If we just learned Cond is the same value for all uses of the
+          // condition, replace it with a constant value
+          CondInst->replaceAllUsesWith(OnlyVal);
+          if (!CondInst->mayHaveSideEffects())
+            CondInst->eraseFromParent();
+        }
+      }
       return true;
     }
   }
diff --git a/llvm/test/Transforms/JumpThreading/fold-not-thread.ll b/llvm/test/Transforms/JumpThreading/fold-not-thread.ll
index 75deca6..3bd7106 100644
--- a/llvm/test/Transforms/JumpThreading/fold-not-thread.ll
+++ b/llvm/test/Transforms/JumpThreading/fold-not-thread.ll
@@ -133,3 +133,60 @@ L3:
   ret void
 }
 
+; Make sure we can do the RAUW for %add...
+;
+; CHECK-LABEL: @rauw_if_possible(
+; CHECK: call void @f4(i32 96) 
+define void @rauw_if_possible(i32 %value) nounwind {
+entry:
+  %cmp = icmp eq i32 %value, 32
+  br i1 %cmp, label %L0, label %L3 
+L0:
+  call i32 @f2()
+  call i32 @f2()
+  %add = add i32 %value, 64
+  switch i32 %add, label %L3 [
+    i32 32, label %L1
+    i32 96, label %L2
+    ]
+
+L1:
+  call void @f3()
+  ret void
+L2:
+  call void @f4(i32 %add)
+  ret void
+L3:
+  call void @f3()
+  ret void
+}
+
+; Make sure we can NOT do the RAUW for %add...
+;
+; CHECK-LABEL: @rauw_if_possible2(
+; CHECK: call void @f4(i32 %add) 
+define void @rauw_if_possible2(i32 %value) nounwind {
+entry:
+  %cmp = icmp eq i32 %value, 32
+  %add = add i32 %value, 64
+  br i1 %cmp, label %L0, label %L2 
+L0:
+  call i32 @f2()
+  call i32 @f2()
+  switch i32 %add, label %L3 [
+    i32 32, label %L1
+    i32 96, label %L2
+    ]
+
+L1:
+  call void @f3()
+  ret void
+L2:
+  call void @f4(i32 %add)
+  ret void
+L3:
+  call void @f3()
+  ret void
+}
+
+
-- 
2.7.4