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

[GlobalISel][IRTranslator] When translating vector geps, splat the base pointer if required. 

We can have geps that have a scalar base pointer, and a vector index value, which
means that the base pointer must be splatted into a vector of pointers.

This fixes crashes on arm64 GlobalISel with optimizations enabled.
This commit is contained in:
Amara Emerson 2020-01-30 16:25:20 -08:00
parent 3b23453b6c
commit 84bd851108
2 changed files with 33 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
View File

@ -1062,6 +1062,18 @@ bool IRTranslator::translateGetElementPtr(const User &U,
if (auto *VT = dyn_cast<VectorType>(U.getType()))
VectorWidth = VT->getNumElements();
// We might need to splat the base pointer into a vector if the offsets
// are vectors.
if (VectorWidth && !PtrTy.isVector()) {
BaseReg =
MIRBuilder.buildSplatVector(LLT::vector(VectorWidth, PtrTy), BaseReg)
.getReg(0);
PtrIRTy = VectorType::get(PtrIRTy, VectorWidth);
PtrTy = getLLTForType(*PtrIRTy, *DL);
OffsetIRTy = DL->getIntPtrType(PtrIRTy);
OffsetTy = getLLTForType(*OffsetIRTy, *DL);
}
int64_t Offset = 0;
for (gep_type_iterator GTI = gep_type_begin(&U), E = gep_type_end(&U);
GTI != E; ++GTI) {

21
llvm/test/CodeGen/AArch64/GlobalISel/translate-gep.ll
View File

@ -117,3 +117,24 @@ define i32* @var_then_const(%type1* %addr, i64 %idx) {
%res = getelementptr %type1, %type1* %addr, i64 %idx, i32 2, i32 2
ret i32* %res
}
@arr = external global [8 x i32]
define <2 x i32*> @vec_gep_scalar_base(<2 x i64> %offs) {
; CHECK-LABEL: name: vec_gep_scalar_base
; CHECK: bb.1.entry:
; CHECK: liveins: $q0
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $q0
; CHECK: [[GV:%[0-9]+]]:_(p0) = G_GLOBAL_VALUE @arr
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p0>) = G_BUILD_VECTOR [[GV]](p0), [[GV]](p0)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 4
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[C]](s64), [[C]](s64)
; CHECK: [[MUL:%[0-9]+]]:_(<2 x s64>) = G_MUL [[COPY]], [[BUILD_VECTOR1]]
; CHECK: [[PTR_ADD:%[0-9]+]]:_(<2 x p0>) = G_PTR_ADD [[BUILD_VECTOR]], [[MUL]](<2 x s64>)
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x p0>) = COPY [[PTR_ADD]](<2 x p0>)
; CHECK: $q0 = COPY [[COPY1]](<2 x p0>)
; CHECK: RET_ReallyLR implicit $q0
entry:
%0 = getelementptr inbounds [8 x i32], [8 x i32]* @arr, i64 0, <2 x i64> %offs
ret <2 x i32*> %0
}