From ffa75cdcf82ef2034249a313b9276eaa1bee6c43 Mon Sep 17 00:00:00 2001
From: Dan Gohman <gohman@apple.com>
Date: Sat, 4 Sep 2010 02:42:48 +0000
Subject: [PATCH] Fix LoopSimplify to notify ScalarEvolution when splitting a
 loop backedge into an inner loop, as the new loop iteration may differ
 substantially. This fixes PR8078.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@113057 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Transforms/Utils/LoopSimplify.cpp         | 11 +++-
 test/Transforms/LoopSimplify/preserve-scev.ll | 50 +++++++++++++++++++
 2 files changed, 60 insertions(+), 1 deletion(-)
 create mode 100644 test/Transforms/LoopSimplify/preserve-scev.ll

diff --git a/lib/Transforms/Utils/LoopSimplify.cpp b/lib/Transforms/Utils/LoopSimplify.cpp
index 2f0a175d5cd..b3c4801a4f1 100644
--- a/lib/Transforms/Utils/LoopSimplify.cpp
+++ b/lib/Transforms/Utils/LoopSimplify.cpp
@@ -46,6 +46,7 @@
 #include "llvm/LLVMContext.h"
 #include "llvm/Type.h"
 #include "llvm/Analysis/AliasAnalysis.h"
+#include "llvm/Analysis/ScalarEvolution.h"
 #include "llvm/Analysis/Dominators.h"
 #include "llvm/Analysis/LoopPass.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
@@ -71,6 +72,7 @@ namespace {
     AliasAnalysis *AA;
     LoopInfo *LI;
     DominatorTree *DT;
+    ScalarEvolution *SE;
     Loop *L;
     virtual bool runOnLoop(Loop *L, LPPassManager &LPM);
 
@@ -83,7 +85,7 @@ namespace {
       AU.addPreserved<LoopInfo>();
 
       AU.addPreserved<AliasAnalysis>();
-      AU.addPreserved("scalar-evolution");
+      AU.addPreserved<ScalarEvolution>();
       AU.addPreservedID(BreakCriticalEdgesID);  // No critical edges added.
       AU.addPreserved<DominanceFrontier>();
       AU.addPreservedID(LCSSAID);
@@ -121,6 +123,7 @@ bool LoopSimplify::runOnLoop(Loop *l, LPPassManager &LPM) {
   LI = &getAnalysis<LoopInfo>();
   AA = getAnalysisIfAvailable<AliasAnalysis>();
   DT = &getAnalysis<DominatorTree>();
+  SE = getAnalysisIfAvailable<ScalarEvolution>();
 
   Changed |= ProcessLoop(L, LPM);
 
@@ -532,6 +535,12 @@ Loop *LoopSimplify::SeparateNestedLoop(Loop *L, LPPassManager &LPM) {
 
   DEBUG(dbgs() << "LoopSimplify: Splitting out a new outer loop\n");
 
+  // If ScalarEvolution is around and knows anything about values in
+  // this loop, tell it to forget them, because we're about to
+  // substantially change it.
+  if (SE)
+    SE->forgetLoop(L);
+
   BasicBlock *Header = L->getHeader();
   BasicBlock *NewBB = SplitBlockPredecessors(Header, &OuterLoopPreds[0],
                                              OuterLoopPreds.size(),
diff --git a/test/Transforms/LoopSimplify/preserve-scev.ll b/test/Transforms/LoopSimplify/preserve-scev.ll
new file mode 100644
index 00000000000..017a0d21084
--- /dev/null
+++ b/test/Transforms/LoopSimplify/preserve-scev.ll
@@ -0,0 +1,50 @@
+; RUN: opt -S < %s -indvars | opt -analyze -iv-users | grep {%cmp = icmp slt i32} | grep {= \{%\\.ph,+,1\}<%for.cond>}
+; PR8079
+
+; LoopSimplify should invalidate indvars when splitting out the
+; inner loop.
+
+@maxStat = external global i32
+
+define i32 @test() nounwind {
+entry:
+  br label %for.cond
+
+for.cond:                                         ; preds = %if.then5, %if.end, %entry
+  %cuts.1 = phi i32 [ 0, %entry ], [ %inc, %if.then5 ], [ %cuts.1, %if.end ]
+  %0 = phi i32 [ 0, %entry ], [ %add, %if.end ], [ %add, %if.then5 ]
+  %add = add i32 %0, 1
+  %cmp = icmp slt i32 %0, 1
+  %tmp1 = load i32* @maxStat, align 4
+  br i1 %cmp, label %for.body, label %for.cond14.preheader
+
+for.cond14.preheader:                             ; preds = %for.cond
+  %cmp1726 = icmp sgt i32 %tmp1, 0
+  br i1 %cmp1726, label %for.body18, label %return
+
+for.body:                                         ; preds = %for.cond
+  %cmp2 = icmp sgt i32 %tmp1, 100
+  br i1 %cmp2, label %return, label %if.end
+
+if.end:                                           ; preds = %for.body
+  %cmp4 = icmp sgt i32 %tmp1, -1
+  br i1 %cmp4, label %if.then5, label %for.cond
+
+if.then5:                                         ; preds = %if.end
+  call void @foo() nounwind
+  %inc = add i32 %cuts.1, 1
+  br label %for.cond
+
+for.body18:                                       ; preds = %for.body18, %for.cond14.preheader
+  %i13.027 = phi i32 [ %1, %for.body18 ], [ 0, %for.cond14.preheader ]
+  call void @foo() nounwind
+  %1 = add nsw i32 %i13.027, 1
+  %tmp16 = load i32* @maxStat, align 4
+  %cmp17 = icmp slt i32 %1, %tmp16
+  br i1 %cmp17, label %for.body18, label %return
+
+return:                                           ; preds = %for.body18, %for.body, %for.cond14.preheader
+  ret i32 0
+}
+
+declare void @foo() nounwind