When analyzing loop exit conditions combined with and and or, don't

make any assumptions about when the two conditions will agree on when
to permit the loop to exit. This fixes PR7845.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110758 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Analysis/ScalarEvolution.cpp b/lib/Analysis/ScalarEvolution.cpp
index f5a762af82590d12837518056977e941ec87d8d0..b3ddfc032f50f3d78afbafb22ba27e563a440fdc 100644 (file)
--- a/lib/Analysis/ScalarEvolution.cpp
+++ b/lib/Analysis/ScalarEvolution.cpp
@@ -3854,14 +3854,13 @@ ScalarEvolution::ComputeBackedgeTakenCountFromExitCond(const Loop *L,
         else
           MaxBECount = getUMinFromMismatchedTypes(BTI0.Max, BTI1.Max);
       } else {
-        // Both conditions must be true for the loop to exit.
+        // Both conditions must be true at the same time for the loop to exit.
+        // For now, be conservative.
         assert(L->contains(FBB) && "Loop block has no successor in loop!");
-        if (BTI0.Exact != getCouldNotCompute() &&
-            BTI1.Exact != getCouldNotCompute())
-          BECount = getUMaxFromMismatchedTypes(BTI0.Exact, BTI1.Exact);
-        if (BTI0.Max != getCouldNotCompute() &&
-            BTI1.Max != getCouldNotCompute())
-          MaxBECount = getUMaxFromMismatchedTypes(BTI0.Max, BTI1.Max);
+        if (BTI0.Max == BTI1.Max)
+          MaxBECount = BTI0.Max;
+        if (BTI0.Exact == BTI1.Exact)
+          BECount = BTI0.Exact;
       }
 
       return BackedgeTakenInfo(BECount, MaxBECount);
@@ -3889,14 +3888,13 @@ ScalarEvolution::ComputeBackedgeTakenCountFromExitCond(const Loop *L,
         else
           MaxBECount = getUMinFromMismatchedTypes(BTI0.Max, BTI1.Max);
       } else {
-        // Both conditions must be false for the loop to exit.
+        // Both conditions must be false at the same time for the loop to exit.
+        // For now, be conservative.
         assert(L->contains(TBB) && "Loop block has no successor in loop!");
-        if (BTI0.Exact != getCouldNotCompute() &&
-            BTI1.Exact != getCouldNotCompute())
-          BECount = getUMaxFromMismatchedTypes(BTI0.Exact, BTI1.Exact);
-        if (BTI0.Max != getCouldNotCompute() &&
-            BTI1.Max != getCouldNotCompute())
-          MaxBECount = getUMaxFromMismatchedTypes(BTI0.Max, BTI1.Max);
+        if (BTI0.Max == BTI1.Max)
+          MaxBECount = BTI0.Max;
+        if (BTI0.Exact == BTI1.Exact)
+          BECount = BTI0.Exact;
       }
 
       return BackedgeTakenInfo(BECount, MaxBECount);

diff --git a/test/Analysis/ScalarEvolution/max-trip-count.ll b/test/Analysis/ScalarEvolution/max-trip-count.ll
index a8966be4ccd46a99f1a10687765073704c4f4318..843fb073087c65b70fdfd23da2162a6c63a3d089 100644 (file)
--- a/test/Analysis/ScalarEvolution/max-trip-count.ll
+++ b/test/Analysis/ScalarEvolution/max-trip-count.ll
@@ -1,8 +1,9 @@
-; RUN: opt < %s -analyze -scalar-evolution \
-; RUN:   | grep {\{%d,+,\[^\{\}\]\*\}<%bb>}
+; RUN: opt < %s -analyze -scalar-evolution | FileCheck %s
 
 ; ScalarEvolution should be able to understand the loop and eliminate the casts.
 
+; CHECK: {%d,+,sizeof(i32)}
+
 define void @foo(i32* nocapture %d, i32 %n) nounwind {
 entry:
        %0 = icmp sgt i32 %n, 0         ; <i1> [#uses=1]
@@ -32,3 +33,40 @@ bb1.return_crit_edge:                ; preds = %bb1
 return:                ; preds = %bb1.return_crit_edge, %entry
        ret void
 }
+
+; ScalarEvolution should be able to find the maximum tripcount
+; of this multiple-exit loop, and if it doesn't know the exact
+; count, it should say so.
+
+; PR7845
+; CHECK: Loop %for.cond: <multiple exits> Unpredictable backedge-taken count. 
+; CHECK: Loop %for.cond: max backedge-taken count is 5
+
+@.str = private constant [4 x i8] c"%d\0A\00"     ; <[4 x i8]*> [#uses=2]
+
+define i32 @main() nounwind {
+entry:
+  br label %for.cond
+
+for.cond:                                         ; preds = %for.inc, %entry
+  %g_4.0 = phi i32 [ 0, %entry ], [ %add, %for.inc ] ; <i32> [#uses=5]
+  %cmp = icmp slt i32 %g_4.0, 5                   ; <i1> [#uses=1]
+  br i1 %cmp, label %for.body, label %for.end
+
+for.body:                                         ; preds = %for.cond
+  %conv = trunc i32 %g_4.0 to i16                 ; <i16> [#uses=1]
+  %tobool.not = icmp eq i16 %conv, 0              ; <i1> [#uses=1]
+  %tobool3 = icmp ne i32 %g_4.0, 0                ; <i1> [#uses=1]
+  %or.cond = and i1 %tobool.not, %tobool3         ; <i1> [#uses=1]
+  br i1 %or.cond, label %for.end, label %for.inc
+
+for.inc:                                          ; preds = %for.body
+  %add = add nsw i32 %g_4.0, 1                    ; <i32> [#uses=1]
+  br label %for.cond
+
+for.end:                                          ; preds = %for.body, %for.cond
+  %call = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([4 x i8]* @.str, i64 0, i64 0), i32 %g_4.0) nounwind ; <i32> [#uses=0]
+  ret i32 0
+}
+
+declare i32 @printf(i8*, ...)