Fixed a bug in type legalizer for masked load/store intrinsics.
The problem occurs when after vectorization we have type
<2 x i32>. This type is promoted to <2 x i64> and then requires
additional efforts for expanding loads and truncating stores.
I added EXPAND / TRUNCATE attributes to the masked load/store
SDNodes. The code now contains additional shuffles.
I've prepared changes in the cost estimation for masked memory
operations, it will be submitted separately.
llvm-svn: 226808
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index ea76bc6..4566792 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -3697,7 +3697,8 @@
getMachineMemOperand(MachinePointerInfo(PtrOperand),
MachineMemOperand::MOStore, VT.getStoreSize(),
Alignment, AAInfo);
- SDValue StoreNode = DAG.getMaskedStore(getRoot(), sdl, Src0, Ptr, Mask, MMO);
+ SDValue StoreNode = DAG.getMaskedStore(getRoot(), sdl, Src0, Ptr, Mask, VT,
+ MMO, false);
DAG.setRoot(StoreNode);
setValue(&I, StoreNode);
}
@@ -3736,7 +3737,8 @@
MachineMemOperand::MOLoad, VT.getStoreSize(),
Alignment, AAInfo, Ranges);
- SDValue Load = DAG.getMaskedLoad(VT, sdl, InChain, Ptr, Mask, Src0, MMO);
+ SDValue Load = DAG.getMaskedLoad(VT, sdl, InChain, Ptr, Mask, Src0, VT, MMO,
+ ISD::NON_EXTLOAD);
SDValue OutChain = Load.getValue(1);
DAG.setRoot(OutChain);
setValue(&I, Load);