[LoopUnswitch] Fix SCEV invalidation in unswitching

Loop unswitching makes substantial changes to a loop that can also affect cached
SCEV info in its outer loops as well, but it only cares to invalidate SCEV cache for the
innermost loop in case of full unswitching and does not invalidate anything at all in
case of trivial unswitching. As result, we may end up with incorrect data in cache.

Differential Revision: https://reviews.llvm.org/D46045
Reviewed By: mzolotukhin

llvm-svn: 333072
This commit is contained in:
Max Kazantsev 2018-05-23 10:09:53 +00:00
parent fa1c9cecd2
commit 589e2b8a48
2 changed files with 40 additions and 1 deletions

View File

@ -975,6 +975,10 @@ void LoopUnswitch::UnswitchTrivialCondition(Loop *L, Value *Cond, Constant *Val,
<< " blocks] in Function "
<< L->getHeader()->getParent()->getName()
<< " on cond: " << *Val << " == " << *Cond << "\n");
// We are going to make essential changes to CFG. This may invalidate cached
// information for L or one of its parent loops in SCEV.
if (auto *SEWP = getAnalysisIfAvailable<ScalarEvolutionWrapperPass>())
SEWP->getSE().forgetTopmostLoop(L);
// First step, split the preheader, so that we know that there is a safe place
// to insert the conditional branch. We will change loopPreheader to have a
@ -1201,8 +1205,10 @@ void LoopUnswitch::UnswitchNontrivialCondition(Value *LIC, Constant *Val,
<< " blocks] in Function " << F->getName() << " when '"
<< *Val << "' == " << *LIC << "\n");
// We are going to make essential changes to CFG. This may invalidate cached
// information for L or one of its parent loops in SCEV.
if (auto *SEWP = getAnalysisIfAvailable<ScalarEvolutionWrapperPass>())
SEWP->getSE().forgetLoop(L);
SEWP->getSE().forgetTopmostLoop(L);
LoopBlocks.clear();
NewBlocks.clear();

View File

@ -0,0 +1,33 @@
; RUN: opt -S -indvars -loop-unswitch < %s | FileCheck %s
target triple = "x86_64-unknown-linux-gnu"
define void @test_01() {
; Make sure we don't fail by SCEV's assertion due to incorrect invalidation.
; CHECK-LABEL: @test_01
entry:
br label %loop
loop: ; preds = %backedge, %entry
%p_50.addr.0 = phi i16 [ undef, %entry ], [ %add2699, %backedge ]
%idxprom2690 = sext i16 %p_50.addr.0 to i32
%arrayidx2691 = getelementptr inbounds [5 x i32], [5 x i32]* undef, i32 0, i32 %idxprom2690
%0 = load i32, i32* %arrayidx2691, align 1
%tobool2692 = icmp ne i32 %0, 0
br label %inner_loop
inner_loop: ; preds = %inner_backedge, %loop
br i1 %tobool2692, label %backedge, label %inner_backedge
inner_backedge: ; preds = %inner_loop
br label %inner_loop
backedge: ; preds = %inner_loop
%add2699 = add nsw i16 %p_50.addr.0, 1
br i1 false, label %loop, label %exit
exit: ; preds = %backedge
unreachable
}