[PATCH] D65276: [SCEV] Disable canonical expansion for nested recurrences.

[Evgeniy via Phabricator via llvm-commits]

ebrevnov updated this revision to Diff 213570.
ebrevnov added a comment.

Splitting exitsting patch to two parts. The first one is an actual fix for the problem. The second one is an enhancement to evaluateAtIteration which is going to be reviewd and committed separately.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D65276/new/

https://reviews.llvm.org/D65276

Files:
  include/llvm/Analysis/ScalarEvolutionExpressions.h
  lib/Analysis/ScalarEvolution.cpp
  test/Transforms/IndVarSimplify/exit_value_tests.ll


Index: test/Transforms/IndVarSimplify/exit_value_tests.ll
===================================================================
--- test/Transforms/IndVarSimplify/exit_value_tests.ll
+++ test/Transforms/IndVarSimplify/exit_value_tests.ll
@@ -45,34 +45,6 @@
   ret i32 %Y
 }
 
-define i32 @NSquareOver2(i32 %N) {
-; <label>:0
-; CHECK-LABEL: @NSquareOver2(
-; CHECK-NEXT:  Out:
-; CHECK-NEXT:    [[TMP0:%.*]] = zext i32 [[N:%.*]] to i33
-; CHECK-NEXT:    [[TMP1:%.*]] = add i32 [[N]], -1
-; CHECK-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i33
-; CHECK-NEXT:    [[TMP3:%.*]] = mul i33 [[TMP0]], [[TMP2]]
-; CHECK-NEXT:    [[TMP4:%.*]] = lshr i33 [[TMP3]], 1
-; CHECK-NEXT:    [[TMP5:%.*]] = trunc i33 [[TMP4]] to i32
-; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[N]], [[TMP5]]
-; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[TMP6]], 15
-; CHECK-NEXT:    ret i32 [[TMP7]]
-;
-  br label %Loop
-
-Loop:		; preds = %Loop, %0
-  %X = phi i32 [ 0, %0 ], [ %X2, %Loop ]		; <i32> [#uses=3]
-  %Y = phi i32 [ 15, %0 ], [ %Y2, %Loop ]		; <i32> [#uses=1]
-  %Y2 = add i32 %Y, %X		; <i32> [#uses=2]
-  %X2 = add i32 %X, 1		; <i32> [#uses=1]
-  %c = icmp eq i32 %X, %N		; <i1> [#uses=1]
-  br i1 %c, label %Out, label %Loop
-
-Out:		; preds = %Loop
-  ret i32 %Y2
-}
-
 define i32 @strength_reduced() {
 ; <label>:0
 ; CHECK-LABEL: @strength_reduced(
Index: lib/Analysis/ScalarEvolution.cpp
===================================================================
--- lib/Analysis/ScalarEvolution.cpp
+++ lib/Analysis/ScalarEvolution.cpp
@@ -1204,6 +1204,13 @@
   IntegerType *CalculationTy = IntegerType::get(SE.getContext(),
                                                       CalculationBits);
   const SCEV *Dividend = SE.getTruncateOrZeroExtend(It, CalculationTy);
+
+  // Zero extension indicates insufficient precision of incoming "It".
+  // In this case result of calculations may be incorrect. Go ahead and return
+  // SCEVCouldNotCompute.
+  if (isa<SCEVZeroExtendExpr>(Dividend))
+    return SE.getCouldNotCompute();
+
   for (unsigned i = 1; i != K; ++i) {
     const SCEV *S = SE.getMinusSCEV(It, SE.getConstant(It->getType(), i));
     Dividend = SE.getMulExpr(Dividend,
@@ -11660,7 +11667,7 @@
       return (L && !L->contains(I)) ? LoopInvariant : LoopVariant;
     return LoopInvariant;
   case scCouldNotCompute:
-    llvm_unreachable("Attempt to use a SCEVCouldNotCompute object!");
+    return LoopVariant;
   }
   llvm_unreachable("Unknown SCEV kind!");
 }
Index: include/llvm/Analysis/ScalarEvolutionExpressions.h
===================================================================
--- include/llvm/Analysis/ScalarEvolutionExpressions.h
+++ include/llvm/Analysis/ScalarEvolutionExpressions.h
@@ -343,6 +343,10 @@
 
     /// Return the value of this chain of recurrences at the specified
     /// iteration number.
+    ///
+    /// Note that SCEVCouldNotCompute is returned if evaluation attempt failed.
+    /// For example, if precision of \p It is less than required to perform an
+    /// evaluation instance of SCEVCouldNotCompute is returned.
     const SCEV *evaluateAtIteration(const SCEV *It, ScalarEvolution &SE) const;
 
     /// Return the number of iterations of this loop that produce


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D65276.213570.patch
Type: text/x-patch
Size: 3200 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190806/44ce406c/attachment.bin>