llvm-D9168_argument_alignment.patch
Index: lib/Target/NVPTX/NVPTXISelLowering.h
===================================================================
--- a/lib/Target/NVPTX/NVPTXISelLowering.h
+++ b/lib/Target/NVPTX/NVPTXISelLowering.h
@@ -539,7 +539,8 @@
SDValue PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) const override;
unsigned getArgumentAlignment(SDValue Callee, const ImmutableCallSite *CS,
- Type *Ty, unsigned Idx) const;
+ Type *Ty, unsigned Idx,
+ const DataLayout &DL) const;
};
} // namespace llvm
Index: lib/Target/NVPTX/NVPTXISelLowering.cpp
===================================================================
--- a/lib/Target/NVPTX/NVPTXISelLowering.cpp
+++ b/lib/Target/NVPTX/NVPTXISelLowering.cpp
@@ -1024,11 +1024,15 @@
return O.str();
}
-unsigned
-NVPTXTargetLowering::getArgumentAlignment(SDValue Callee,
- const ImmutableCallSite *CS,
- Type *Ty,
- unsigned Idx) const {
+unsigned NVPTXTargetLowering::getArgumentAlignment(SDValue Callee,
+ const ImmutableCallSite *CS,
+ Type *Ty, unsigned Idx,
+ const DataLayout &DL) const {
+ if (!CS) {
+ // CallSite is zero, fallback to ABI type alignment
+ return DL.getABITypeAlignment(Ty);
+ }
+
unsigned Align = 0;
const Value *DirectCallee = CS->getCalledFunction();
@@ -1046,7 +1050,7 @@
const Value *CalleeV = cast<CallInst>(CalleeI)->getCalledValue();
// Ignore any bitcast instructions
- while(isa<ConstantExpr>(CalleeV)) {
+ while (isa<ConstantExpr>(CalleeV)) {
const ConstantExpr *CE = cast<ConstantExpr>(CalleeV);
if (!CE->isCast())
break;
@@ -1069,7 +1073,6 @@
// Call is indirect or alignment information is not available, fall back to
// the ABI type alignment
- auto &DL = CS->getCaller()->getParent()->getDataLayout();
return DL.getABITypeAlignment(Ty);
}
@@ -1126,7 +1129,8 @@
ComputePTXValueVTs(*this, DAG.getDataLayout(), Ty, vtparts, &Offsets,
0);
- unsigned align = getArgumentAlignment(Callee, CS, Ty, paramCount + 1);
+ unsigned align =
+ getArgumentAlignment(Callee, CS, Ty, paramCount + 1, DL);
// declare .param .align <align> .b8 .param<n>[<size>];
unsigned sz = DL.getTypeAllocSize(Ty);
SDVTList DeclareParamVTs = DAG.getVTList(MVT::Other, MVT::Glue);
@@ -1166,7 +1170,8 @@
}
if (Ty->isVectorTy()) {
EVT ObjectVT = getValueType(DL, Ty);
- unsigned align = getArgumentAlignment(Callee, CS, Ty, paramCount + 1);
+ unsigned align =
+ getArgumentAlignment(Callee, CS, Ty, paramCount + 1, DL);
// declare .param .align <align> .b8 .param<n>[<size>];
unsigned sz = DL.getTypeAllocSize(Ty);
SDVTList DeclareParamVTs = DAG.getVTList(MVT::Other, MVT::Glue);
@@ -1426,7 +1431,7 @@
DeclareRetOps);
InFlag = Chain.getValue(1);
} else {
- retAlignment = getArgumentAlignment(Callee, CS, retTy, 0);
+ retAlignment = getArgumentAlignment(Callee, CS, retTy, 0, DL);
SDVTList DeclareRetVTs = DAG.getVTList(MVT::Other, MVT::Glue);
SDValue DeclareRetOps[] = { Chain,
DAG.getConstant(retAlignment, dl, MVT::i32),
@@ -1633,9 +1638,10 @@
} else {
SmallVector<EVT, 16> VTs;
SmallVector<uint64_t, 16> Offsets;
- ComputePTXValueVTs(*this, DAG.getDataLayout(), retTy, VTs, &Offsets, 0);
+ auto &DL = DAG.getDataLayout();
+ ComputePTXValueVTs(*this, DL, retTy, VTs, &Offsets, 0);
assert(VTs.size() == Ins.size() && "Bad value decomposition");
- unsigned RetAlign = getArgumentAlignment(Callee, CS, retTy, 0);
+ unsigned RetAlign = getArgumentAlignment(Callee, CS, retTy, 0, DL);
for (unsigned i = 0, e = Ins.size(); i != e; ++i) {
unsigned sz = VTs[i].getSizeInBits();
unsigned AlignI = GreatestCommonDivisor64(RetAlign, Offsets[i]);