diff options
| -rw-r--r-- | llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp | 3 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/optsize.ll | 37 |
2 files changed, 39 insertions, 1 deletions
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp index 9731abbb50a..0a20ab71dfa 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp @@ -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; diff --git a/llvm/test/Transforms/LoopVectorize/optsize.ll b/llvm/test/Transforms/LoopVectorize/optsize.ll index 403c006eeb5..1991906494e 100644 --- a/llvm/test/Transforms/LoopVectorize/optsize.ll +++ b/llvm/test/Transforms/LoopVectorize/optsize.ll @@ -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} |
