Sneaky, sneaky: move the -1 to the outside of the SMax. Reinstate the

optimization of SGE/SLE with unit stride, now that it works properly.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@60881 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Analysis/ScalarEvolution.cpp b/lib/Analysis/ScalarEvolution.cpp
index 2b714de3b3fac130bb8c2edb6d2c4fced74a79fa..1dd5026d7493e63c3dfc3c9bc27169ade656b90c 100644 (file)
--- a/lib/Analysis/ScalarEvolution.cpp
+++ b/lib/Analysis/ScalarEvolution.cpp
@@ -2924,8 +2924,12 @@ bool ScalarEvolutionsImpl::potentialInfiniteLoop(SCEV *Stride, SCEV *RHS,
   if (!R)
     return true;
 
-  if (isSigned)
+  if (isSigned) {
+    if (SC->getValue()->isOne())
+      return R->getValue()->isMaxValue(true);
+
     return true;  // XXX: because we don't have an sdiv scev.
+  }
 
   // If negative, it wraps around every iteration, but we don't care about that.
   APInt S = SC->getValue()->getValue().abs();
@@ -2971,14 +2975,6 @@ HowManyLessThans(SCEV *LHS, SCEV *RHS, const Loop *L,
     // run (m-n)/s times.
     SCEVHandle End = RHS;
 
-    if (!executesAtLeastOnce(L, isSigned, trueWhenEqual,
-                             SE.getMinusSCEV(Start, One), RHS)) {
-      // If not, we get the value of the LHS in the first iteration in which
-      // the above condition doesn't hold.  This equals to max(m,n).
-      End = isSigned ? SE.getSMaxExpr(RHS, Start)
-                     : SE.getUMaxExpr(RHS, Start);
-    }
-
     // If the expression is less-than-or-equal to, we need to extend the
     // loop by one iteration.
     //
@@ -2987,12 +2983,16 @@ HowManyLessThans(SCEV *LHS, SCEV *RHS, const Loop *L,
     // division would equal one, but the loop runs twice putting the
     // induction variable at 12.
 
-    if (!trueWhenEqual)
-      // (Stride - 1) is correct only because we know it's unsigned.
-      // What we really want is to decrease the magnitude of Stride by one.
-      Start = SE.getMinusSCEV(Start, SE.getMinusSCEV(Stride, One));
-    else
-      Start = SE.getMinusSCEV(Start, Stride);
+    if (trueWhenEqual)
+      End = SE.getAddExpr(End, One);
+
+    if (!executesAtLeastOnce(L, isSigned, trueWhenEqual,
+                             SE.getMinusSCEV(Start, One), RHS)) {
+      // If not, we get the value of the LHS in the first iteration in which
+      // the above condition doesn't hold.  This equals to max(m,n).
+      End = isSigned ? SE.getSMaxExpr(End, Start)
+                     : SE.getUMaxExpr(End, Start);
+    }
 
     // Finally, we subtract these two values to get the number of times the
     // backedge is executed: max(m,n)-n.

diff --git a/test/Analysis/ScalarEvolution/2008-12-08-FiniteSGE.ll b/test/Analysis/ScalarEvolution/2008-12-08-FiniteSGE.ll
index 1bf24d7f487aee81879dc3b5a7ed9f1631780eef..a9a7c0565859d48d5991a1c88fb10f4fe1075e94 100644 (file)
--- a/test/Analysis/ScalarEvolution/2008-12-08-FiniteSGE.ll
+++ b/test/Analysis/ScalarEvolution/2008-12-08-FiniteSGE.ll
@@ -1,5 +1,4 @@
 ; RUN: llvm-as < %s | opt -analyze -scalar-evolution | grep {255 iterations}
-; XFAIL: *
 
 define i32 @foo(i32 %x, i32 %y, i32* %lam, i32* %alp) nounwind {
 bb1.thread:

diff --git a/test/Analysis/ScalarEvolution/2008-12-11-SMaxOverflow.ll b/test/Analysis/ScalarEvolution/2008-12-11-SMaxOverflow.ll
new file mode 100644 (file)
index 0000000..1e8787d
--- /dev/null
+++ b/test/Analysis/ScalarEvolution/2008-12-11-SMaxOverflow.ll
@@ -0,0 +1,27 @@
+; RUN: llvm-as < %s | opt -analyze -scalar-evolution | grep {0 smax}
+
+define i32 @f(i32 %c.idx.val) {
+
+bb2:
+       %k.018 = add i32 %c.idx.val, -1         ; <i32> [#uses=2]
+       %a14 = icmp slt i32 %k.018, 0           ; <i1> [#uses=1]
+       br i1 %a14, label %bb19, label %bb16.preheader
+
+bb16.preheader:
+       %k.019 = phi i32 [ %k.0, %bb18 ], [ %k.018, %bb2 ]              ; <i32> [#uses=5]
+       %x = phi i32 [ 0, %bb2 ], [ %x.1, %bb18]
+       br label %bb18
+
+bb18:          ; preds = %bb18.loopexit
+       %x.1 = add i32 %x, 1
+       %k.0 = add i32 %k.019, -1               ; <i32> [#uses=2]
+       %a107 = icmp slt i32 %k.0, 0            ; <i1> [#uses=1]
+       br i1 %a107, label %bb18.bb19_crit_edge, label %bb16.preheader
+
+bb18.bb19_crit_edge:
+       ret i32 %x
+
+bb19:
+       ret i32 0
+
+}