LCSSA should be performed on the outermost affected loop while unrolling loop.

During loop-unroll, loop exits from the current loop may end up in in different
outer loop. This requires to re-form LCSSA recursively for one level down from
the outer most loop where loop exits are landed during unroll. This fixes PR18861.

Differential Revision: http://reviews.llvm.org/D2976

llvm-svn: 209796

diff --git a/llvm/lib/Transforms/Utils/LoopUnroll.cpp b/llvm/lib/Transforms/Utils/LoopUnroll.cpp
index d953e30..16975b9 100644 (file)
--- a/llvm/lib/Transforms/Utils/LoopUnroll.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUnroll.cpp
@@ -487,6 +487,15 @@ bool llvm::UnrollLoop(Loop *L, unsigned Count, unsigned TripCount,
     if (OuterL) {
       ScalarEvolution *SE = PP->getAnalysisIfAvailable<ScalarEvolution>();
       simplifyLoop(OuterL, DT, LI, PP, /*AliasAnalysis*/ nullptr, SE);
+
+      // LCSSA must be performed on the outermost affected loop. The unrolled
+      // loop's last loop latch is guaranteed to be in the outermost loop after
+      // deleteLoopFromQueue updates LoopInfo.
+      Loop *LatchLoop = LI->getLoopFor(Latches.back());
+      if (!OuterL->contains(LatchLoop))
+        while (OuterL->getParentLoop() != LatchLoop)
+          OuterL = OuterL->getParentLoop();
+
       formLCSSARecursively(*OuterL, *DT, SE);
     }
   }

diff --git a/llvm/test/Transforms/LoopUnroll/pr18861.ll b/llvm/test/Transforms/LoopUnroll/pr18861.ll
new file mode 100644 (file)
index 0000000..62f2610
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/pr18861.ll
@@ -0,0 +1,43 @@
+; RUN: opt < %s -loop-unroll -indvars -disable-output
+
+@b = external global i32, align 4
+
+; Function Attrs: nounwind uwtable
+define void @fn1() #0 {
+entry:
+  br label %for.cond1thread-pre-split
+
+for.cond1thread-pre-split:                        ; preds = %for.inc8, %entry
+  %storemerge1 = phi i32 [ 0, %entry ], [ %inc9, %for.inc8 ]
+  br i1 undef, label %for.inc8, label %for.cond2.preheader.lr.ph
+
+for.cond2.preheader.lr.ph:                        ; preds = %for.cond1thread-pre-split
+  br label %for.cond2.preheader
+
+for.cond2.preheader:                              ; preds = %for.inc5, %for.cond2.preheader.lr.ph
+  br label %for.cond2
+
+for.cond2:                                        ; preds = %for.body3, %for.cond2.preheader
+  %storemerge = phi i32 [ %add, %for.body3 ], [ 0, %for.cond2.preheader ]
+  %cmp = icmp slt i32 %storemerge, 1
+  br i1 %cmp, label %for.body3, label %for.inc5
+
+for.body3:                                        ; preds = %for.cond2
+  %tobool4 = icmp eq i32 %storemerge, 0
+  %add = add nsw i32 %storemerge, 1
+  br i1 %tobool4, label %for.cond2, label %if.then
+
+if.then:                                          ; preds = %for.body3
+  store i32 %storemerge1, i32* @b, align 4
+  ret void
+
+for.inc5:                                         ; preds = %for.cond2
+  br i1 undef, label %for.cond1.for.inc8_crit_edge, label %for.cond2.preheader
+
+for.cond1.for.inc8_crit_edge:                     ; preds = %for.inc5
+  br label %for.inc8
+
+for.inc8:                                         ; preds = %for.cond1.for.inc8_crit_edge, %for.cond1thread-pre-split
+  %inc9 = add nsw i32 %storemerge1, 1
+  br label %for.cond1thread-pre-split
+}