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

LoadStoreVectorizer crashes due to unsized type 

When we skip bitcasts while looking for GEP in LoadSoreVectorizer
we should also verify that the type is sized otherwise we assert

Differential Revision: https://reviews.llvm.org/D45709

llvm-svn: 330221
This commit is contained in:
Stanislav Mekhanoshin 2018-04-17 21:40:04 +00:00
parent f437e35671
commit 0bee630814
2 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
View File

@ -284,8 +284,10 @@ GetElementPtrInst *Vectorizer::getSourceGEP(Value *Src) const {
// in pointee type size here. Currently it will not be vectorized.
Value *SrcPtr = getLoadStorePointerOperand(Src);
Value *SrcBase = SrcPtr->stripPointerCasts();
if (DL.getTypeStoreSize(SrcPtr->getType()->getPointerElementType()) ==
DL.getTypeStoreSize(SrcBase->getType()->getPointerElementType()))
Type *SrcPtrType = SrcPtr->getType()->getPointerElementType();
Type *SrcBaseType = SrcBase->getType()->getPointerElementType();
if (SrcPtrType->isSized() && SrcBaseType->isSized() &&
DL.getTypeStoreSize(SrcPtrType) == DL.getTypeStoreSize(SrcBaseType))
SrcPtr = SrcBase;
return dyn_cast<GetElementPtrInst>(SrcPtr);
}

16
llvm/test/CodeGen/X86/loadStore_vectorizer.ll Normal file
View File

@ -0,0 +1,16 @@
; RUN: opt -load-store-vectorizer < %s -S | FileCheck %s
%struct_render_pipeline_state = type opaque
define fastcc void @main(%struct_render_pipeline_state addrspace(1)* %pso) unnamed_addr {
; CHECK: load i16
; CHECK: load i16
entry:
%tmp = bitcast %struct_render_pipeline_state addrspace(1)* %pso to i16 addrspace(1)*
%tmp1 = load i16, i16 addrspace(1)* %tmp, align 2
%tmp2 = bitcast %struct_render_pipeline_state addrspace(1)* %pso to i8 addrspace(1)*
%sunkaddr51 = getelementptr i8, i8 addrspace(1)* %tmp2, i64 6
%tmp3 = bitcast i8 addrspace(1)* %sunkaddr51 to i16 addrspace(1)*
%tmp4 = load i16, i16 addrspace(1)* %tmp3, align 2
ret void
}