[llvm] r302988 - [LoopOptimizer][Fix]PR32859, PR24738

[Simon Pilgrim via llvm-commits]

Author: rksimon
Date: Sat May 13 08:25:57 2017
New Revision: 302988

URL: http://llvm.org/viewvc/llvm-project?rev=302988&view=rev
Log:
[LoopOptimizer][Fix]PR32859, PR24738

The Loop vectorizer pass introduced undef value while it is fixing output of LCSSA form.
Here it is:

before: %e.0.ph = phi i32 [ 0, %for.inc.2.i ]
after: %e.0.ph = phi i32 [ 0, %for.inc.2.i ], [ undef, %middle.block ]

and after this change we have:

%e.0.ph = phi i32 [ 0, %for.inc.2.i ]
%e.0.ph = phi i32 [ 0, %for.inc.2.i ], [ 0, %middle.block ]

Committed on behalf of @dtemirbulatov

Differential Revision: https://reviews.llvm.org/D33055

Added:
    llvm/trunk/test/Transforms/LoopVectorize/pr32859.ll
Modified:
    llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp

Modified: llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp?rev=302988&r1=302987&r2=302988&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp (original)
+++ llvm/trunk/lib/Transforms/Vectorize/LoopVectorize.cpp Sat May 13 08:25:57 2017
@@ -446,10 +446,10 @@ protected:
   /// vectorizing this phi node.
   void fixReduction(PHINode *Phi);
 
-  /// \brief The Loop exit block may have single value PHI nodes where the
-  /// incoming value is 'Undef'. While vectorizing we only handled real values
-  /// that were defined inside the loop. Here we fix the 'undef case'.
-  /// See PR14725.
+  /// \brief The Loop exit block may have single value PHI nodes with some
+  /// incoming value. While vectorizing we only handled real values
+  /// that were defined inside the loop and we should have one value for
+  /// each predecessor of its parent basic block. See PR14725.
   void fixLCSSAPHIs();
 
   /// Iteratively sink the scalarized operands of a predicated instruction into
@@ -4300,9 +4300,11 @@ void InnerLoopVectorizer::fixLCSSAPHIs()
     auto *LCSSAPhi = dyn_cast<PHINode>(&LEI);
     if (!LCSSAPhi)
       break;
-    if (LCSSAPhi->getNumIncomingValues() == 1)
-      LCSSAPhi->addIncoming(UndefValue::get(LCSSAPhi->getType()),
-                            LoopMiddleBlock);
+    if (LCSSAPhi->getNumIncomingValues() == 1) {
+      assert(OrigLoop->isLoopInvariant(LCSSAPhi->getIncomingValue(0)) &&
+             "Incoming value isn't loop invariant");
+      LCSSAPhi->addIncoming(LCSSAPhi->getIncomingValue(0), LoopMiddleBlock);
+    }
   }
 }
 

Added: llvm/trunk/test/Transforms/LoopVectorize/pr32859.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/LoopVectorize/pr32859.ll?rev=302988&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/LoopVectorize/pr32859.ll (added)
+++ llvm/trunk/test/Transforms/LoopVectorize/pr32859.ll Sat May 13 08:25:57 2017
@@ -0,0 +1,30 @@
+; RUN: opt < %s -loop-vectorize -S | FileCheck %s
+
+; Out of the LCSSA form we could have 'phi i32 [ loop-invariant, %for.inc.2.i ]'
+; but the IR Verifier requires for PHI one entry for each predecessor of
+; it's parent basic block. The original PR14725 solution for the issue just
+; added 'undef' for an predecessor BB and which is not correct. We copy the real
+; value for another predecessor instead of bringing 'undef'.
+
+; CHECK-LABEL: for.cond.preheader:
+; CHECK: %e.0.ph = phi i32 [ 0, %if.end.2.i ], [ 0, %middle.block ]
+
+; Function Attrs: nounwind uwtable
+define void @main() #0 {
+entry:
+  br label %for.cond1.preheader.i
+
+for.cond1.preheader.i:                            ; preds = %if.end.2.i, %entry
+  %c.06.i = phi i32 [ 0, %entry ], [ %inc5.i, %if.end.2.i ]
+  %tobool.i = icmp ne i32 undef, 0
+  br label %if.end.2.i
+
+if.end.2.i:                                       ; preds = %for.cond1.preheader.i
+  %inc5.i = add nsw i32 %c.06.i, 1
+  %cmp.i = icmp slt i32 %inc5.i, 16
+  br i1 %cmp.i, label %for.cond1.preheader.i, label %for.cond.preheader
+
+for.cond.preheader:                               ; preds = %if.end.2.i
+  %e.0.ph = phi i32 [ 0, %if.end.2.i ]
+  unreachable
+}