[X86] Correct the MaskVT for avx512 gather/scatter intrinsics to use the min of the number of index and data elements.

When the result type is v2i64/v2f64 and the index element size is i32, the index vector has two unused elements making the type v4i32. The mask VT should match the number of memory accesses that will be made.

This is consistent with the isel patterns used for the target independent gather/scatter intrinsic.

llvm-svn: 350687

1 files changed, 7 insertions, 4 deletions

diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index d3cc1f8ff29..ae7e120cd6b 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -22248,14 +22248,16 @@ static SDValue getGatherNode(unsigned Opc, SDValue Op, SelectionDAG &DAG,
                               SDValue Src, SDValue Mask, SDValue Base,
                               SDValue Index, SDValue ScaleOp, SDValue Chain,
                               const X86Subtarget &Subtarget) {
+  MVT VT = Op.getSimpleValueType();
   SDLoc dl(Op);
   auto *C = dyn_cast<ConstantSDNode>(ScaleOp);
   // Scale must be constant.
   if (!C)
     return SDValue();
   SDValue Scale = DAG.getTargetConstant(C->getZExtValue(), dl, MVT::i8);
-  MVT MaskVT = MVT::getVectorVT(MVT::i1,
-                             Index.getSimpleValueType().getVectorNumElements());
+  unsigned MinElts = std::min(Index.getSimpleValueType().getVectorNumElements(),
+                              VT.getVectorNumElements());
+  MVT MaskVT = MVT::getVectorVT(MVT::i1, MinElts);
 
   SDValue VMask = getMaskNode(Mask, MaskVT, Subtarget, DAG, dl);
   SDVTList VTs = DAG.getVTList(Op.getValueType(), MaskVT, MVT::Other);
@@ -22284,8 +22286,9 @@ static SDValue getScatterNode(unsigned Opc, SDValue Op, SelectionDAG &DAG,
   SDValue Scale = DAG.getTargetConstant(C->getZExtValue(), dl, MVT::i8);
   SDValue Disp = DAG.getTargetConstant(0, dl, MVT::i32);
   SDValue Segment = DAG.getRegister(0, MVT::i32);
-  MVT MaskVT = MVT::getVectorVT(MVT::i1,
-                             Index.getSimpleValueType().getVectorNumElements());
+  unsigned MinElts = std::min(Index.getSimpleValueType().getVectorNumElements(),
+                              Src.getSimpleValueType().getVectorNumElements());
+  MVT MaskVT = MVT::getVectorVT(MVT::i1, MinElts);
 
   SDValue VMask = getMaskNode(Mask, MaskVT, Subtarget, DAG, dl);
   SDVTList VTs = DAG.getVTList(MaskVT, MVT::Other);