forked from OSchip/llvm-project
[ConstantFold] Return the correct type when folding a GEP with vector indices.
As Eli pointed out (and I got wrong in the first place), langref says: "The getelementptr returns a vector of pointers, instead of a single address, when one or more of its arguments is a vector. In such cases, all vector arguments should have the same number of elements, and every scalar argument will be effectively broadcast into a vector during address calculation." Costantfold for gep doesn't really take in account this paragraph, returning a pointer instead of a vector of pointer which triggers an assertion in RAUW, as we're trying to replace values with mistmatching types. Differential Revision: https://reviews.llvm.org/D37928 llvm-svn: 313394
This commit is contained in:
parent
66a99e41cd
commit
dee018c51f
|
@ -2062,9 +2062,20 @@ Constant *llvm::ConstantFoldGetElementPtr(Type *PointeeTy, Constant *C,
|
|||
Type *Ty = GetElementPtrInst::getIndexedType(PointeeTy, Idxs);
|
||||
|
||||
assert(Ty && "Invalid indices for GEP!");
|
||||
Type *OrigGEPTy = PointerType::get(Ty, PtrTy->getAddressSpace());
|
||||
Type *GEPTy = PointerType::get(Ty, PtrTy->getAddressSpace());
|
||||
if (VectorType *VT = dyn_cast<VectorType>(C->getType()))
|
||||
GEPTy = VectorType::get(GEPTy, VT->getNumElements());
|
||||
GEPTy = VectorType::get(OrigGEPTy, VT->getNumElements());
|
||||
|
||||
// The GEP returns a vector of pointers when one of more of
|
||||
// its arguments is a vector.
|
||||
for (unsigned i = 0, e = Idxs.size(); i != e; ++i) {
|
||||
if (auto *VT = dyn_cast<VectorType>(Idxs[i]->getType())) {
|
||||
GEPTy = VectorType::get(OrigGEPTy, VT->getNumElements());
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return Constant::getNullValue(GEPTy);
|
||||
}
|
||||
}
|
||||
|
|
|
@ -0,0 +1,11 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt -S -instcombine %s |FileCheck %s
|
||||
|
||||
define <2 x i16> @patatino() {
|
||||
; CHECK-LABEL: @patatino(
|
||||
; CHECK-NEXT: ret <2 x i16> zeroinitializer
|
||||
;
|
||||
%tmp2 = getelementptr inbounds [1 x i16], [1 x i16]* null, i16 0, <2 x i16> undef
|
||||
%tmp3 = ptrtoint <2 x i16*> %tmp2 to <2 x i16>
|
||||
ret <2 x i16> %tmp3
|
||||
}
|
Loading…
Reference in New Issue