1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00

[SelectionDAG] Fix calling convention in expansion of ?MULO.

The SMULO/UMULO DAG nodes, when not directly supported by the target,
expand to a multiplication twice as wide. In case that the resulting
type is not legal, an __mul?i3 intrinsic is used. Since the type is
not legal, the legalizer cannot directly call the intrinsic with
the wide arguments; instead, it "pre-lowers" them by splitting them
in halves.

The "pre-lowering" code in essence made assumptions about
the calling convention, specifically that i(N*2) values will be
split into two iN values and passed in consecutive registers in
little-endian order. This, naturally, breaks on a big-endian system,
such as our OR1K out-of-tree backend.

Thanks to James Miller <james@aatch.net> for help in debugging.

Differential Revision: https://reviews.llvm.org/D25223

llvm-svn: 283203
This commit is contained in:
whitequark 2016-10-04 09:07:49 +00:00
parent 45f9fcff68
commit 954b2ab4fd

View File

@ -3470,8 +3470,18 @@ bool SelectionDAGLegalize::ExpandNode(SDNode *Node) {
// pre-lowered to the correct types. This all depends upon WideVT not
// being a legal type for the architecture and thus has to be split to
// two arguments.
SDValue Args[] = { LHS, HiLHS, RHS, HiRHS };
SDValue Ret = ExpandLibCall(LC, WideVT, Args, 4, isSigned, dl);
SDValue Ret;
if(DAG.getDataLayout().isLittleEndian()) {
// Halves of WideVT are packed into registers in different order
// depending on platform endianness. This is usually handled by
// the C calling convention, but we can't defer to it in
// the legalizer.
SDValue Args[] = { LHS, HiLHS, RHS, HiRHS };
Ret = ExpandLibCall(LC, WideVT, Args, 4, isSigned, dl);
} else {
SDValue Args[] = { HiLHS, LHS, HiRHS, RHS };
Ret = ExpandLibCall(LC, WideVT, Args, 4, isSigned, dl);
}
BottomHalf = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, VT, Ret,
DAG.getIntPtrConstant(0, dl));
TopHalf = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, VT, Ret,