maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[LV] Emitting SCEV checks with OptForSize 

When optimising for size and SCEV runtime checks need to be emitted to check
overflow behaviour, the loop vectorizer can run in this assert:

  LoopVectorize.cpp:2699: void llvm::InnerLoopVectorizer::emitSCEVChecks(
  llvm::Loop *, llvm::BasicBlock *): Assertion `!BB->getParent()->hasOptSize()
  && "Cannot SCEV check stride or overflow when opt

We should not generate predicates while optimising for size because
code will be generated for predicates such as these SCEV overflow runtime
checks.

This should fix PR43371.

Differential Revision: https://reviews.llvm.org/D68082

llvm-svn: 374166
This commit is contained in:
Sjoerd Meijer 2019-10-09 13:19:41 +00:00
parent dde0fe5db5
commit d1170dbe58
2 changed files with 39 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
View File

@ -409,7 +409,8 @@ int LoopVectorizationLegality::isConsecutivePtr(Value *Ptr) {
const ValueToValueMap &Strides =
getSymbolicStrides() ? *getSymbolicStrides() : ValueToValueMap();
int Stride = getPtrStride(PSE, Ptr, TheLoop, Strides, true, false);
bool CanAddPredicate = !TheLoop->getHeader()->getParent()->hasOptSize();
int Stride = getPtrStride(PSE, Ptr, TheLoop, Strides, CanAddPredicate, false);
if (Stride == 1 || Stride == -1)
return Stride;
return 0;

37
llvm/test/Transforms/LoopVectorize/optsize.ll
View File

@ -84,6 +84,43 @@ for.end: ; preds = %for.body
ret i32 0
}
; PR43371: don't run into an assert due to emitting SCEV runtime checks
; with OptForSize.
;
@cm_array = external global [2592 x i16], align 1
define void @pr43371() optsize {
;
; CHECK-LABEL: @pr43371
; CHECK-NOT: vector.scevcheck
;
; We do not want to generate SCEV predicates when optimising for size, because
; that will lead to extra code generation such as the SCEV overflow runtime
; checks. Not generating SCEV predicates can still result in vectorisation as
; the non-consecutive loads/stores can be scalarized:
;
; CHECK: vector.body:
; CHECK: store i16 0, i16* %{{.*}}, align 1
; CHECK: store i16 0, i16* %{{.*}}, align 1
; CHECK: br i1 {{.*}}, label %vector.body
;
entry:
br label %for.body29
for.cond.cleanup28:
unreachable
for.body29:
%i24.0170 = phi i16 [ 0, %entry], [ %inc37, %for.body29]
%add33 = add i16 undef, %i24.0170
%idxprom34 = zext i16 %add33 to i32
%arrayidx35 = getelementptr [2592 x i16], [2592 x i16] * @cm_array, i32 0, i32 %idxprom34
store i16 0, i16 * %arrayidx35, align 1
%inc37 = add i16 %i24.0170, 1
%cmp26 = icmp ult i16 %inc37, 756
br i1 %cmp26, label %for.body29, label %for.cond.cleanup28
}
!llvm.module.flags = !{!0}
!0 = !{i32 1, !"ProfileSummary", !1}
!1 = !{!2, !3, !4, !5, !6, !7, !8, !9}