RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 04:02:41 +01:00
Code Issues Projects Releases Wiki Activity

Revert "Revert r342183 "[DAGCombine] Fix crash when store merging created an extract_subvector with invalid index.""

Browse Source 
Fixed the assertion failure.

llvm-svn: 342397
This commit is contained in:
Amara Emerson 2018-09-17 14:40:13 +00:00
parent 537724f5dd
commit 12a3665936
2 changed files with 59 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -13870,17 +13870,26 @@ bool DAGCombiner::MergeStoresOfConstantsOrVecElts(
Val.getOpcode() == ISD::EXTRACT_SUBVECTOR)) {
SDValue Vec = Val.getOperand(0);
EVT MemVTScalarTy = MemVT.getScalarType();
SDValue Idx = Val.getOperand(1);
// We may need to add a bitcast here to get types to line up.
if (MemVTScalarTy != Vec.getValueType()) {
unsigned Elts = Vec.getValueType().getSizeInBits() /
MemVTScalarTy.getSizeInBits();
if (Val.getValueType().isVector() && MemVT.isVector()) {
unsigned IdxC = cast<ConstantSDNode>(Idx)->getZExtValue();
unsigned NewIdx =
((uint64_t)IdxC * MemVT.getVectorNumElements()) / Elts;
Idx = DAG.getConstant(NewIdx, SDLoc(Val), Idx.getValueType());
}
if (!MemVT.isVector() && Val.getValueType().isVector())
dbgs() << "hit!\n";
EVT NewVecTy =
EVT::getVectorVT(*DAG.getContext(), MemVTScalarTy, Elts);
Vec = DAG.getBitcast(NewVecTy, Vec);
}
auto OpC = (MemVT.isVector()) ? ISD::EXTRACT_SUBVECTOR
: ISD::EXTRACT_VECTOR_ELT;
Val = DAG.getNode(OpC, SDLoc(Val), MemVT, Vec, Val.getOperand(1));
Val = DAG.getNode(OpC, SDLoc(Val), MemVT, Vec, Idx);
}
Ops.push_back(Val);
}

49
test/CodeGen/X86/merge-vector-stores-scale-idx-crash.ll Normal file
View File

@ -0,0 +1,49 @@
; RUN: llc < %s -mtriple=x86_64-apple-osx10.14 -mattr=+avx2 | FileCheck %s
; Check that we don't crash due creating invalid extract_subvector indices in store merging.
; CHECK-LABEL: testfn
; CHECK: retq
define void @testfn(i32* nocapture %p) {
%v0 = getelementptr i32, i32* %p, i64 12
%1 = bitcast i32* %v0 to <2 x i64>*
%2 = bitcast i32* %v0 to <4 x i32>*
%3 = getelementptr <2 x i64>, <2 x i64>* %1, i64 -3
store <2 x i64> undef, <2 x i64>* %3, align 16
%4 = shufflevector <4 x i64> zeroinitializer, <4 x i64> undef, <2 x i32> <i32 0, i32 1>
%5 = getelementptr <2 x i64>, <2 x i64>* %1, i64 -2
store <2 x i64> %4, <2 x i64>* %5, align 16
%6 = shufflevector <8 x i32> zeroinitializer, <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
%7 = getelementptr <4 x i32>, <4 x i32>* %2, i64 -1
store <4 x i32> %6, <4 x i32>* %7, align 16
ret void
}
%struct.o.1.5.7.9.13.15.17.19.57 = type { [0 x %struct.d.0.4.6.8.12.14.16.18.56] }
%struct.d.0.4.6.8.12.14.16.18.56 = type { float, float }
; CHECK-LABEL: testfn_scalar
; CHECK: retq
define void @testfn_scalar(%struct.o.1.5.7.9.13.15.17.19.57* nocapture %j) local_unnamed_addr #0 align 2 {
entry:
%0 = bitcast i64 undef to <2 x float>
br i1 undef, label %if.end, label %if.then
if.then: ; preds = %entry
unreachable
if.end: ; preds = %entry
%call.i.i17 = tail call <4 x float> @_Z1bv()
%1 = bitcast <4 x float> %call.i.i17 to <2 x i64>
%extract.i.i15 = extractelement <2 x i64> %1, i64 0
%arrayidx6 = getelementptr inbounds %struct.o.1.5.7.9.13.15.17.19.57, %struct.o.1.5.7.9.13.15.17.19.57* %j, i64 0, i32 0, i64 1
%2 = bitcast %struct.d.0.4.6.8.12.14.16.18.56* %arrayidx6 to i64*
store i64 %extract.i.i15, i64* %2, align 4
%r.sroa.0.0..sroa_cast12 = bitcast %struct.o.1.5.7.9.13.15.17.19.57* %j to <2 x float>*
store <2 x float> %0, <2 x float>* %r.sroa.0.0..sroa_cast12, align 4
ret void
}
declare <4 x float> @_Z1bv() local_unnamed_addr
attributes #0 = { nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="128" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }