[SelectionDAG] Add an ISD node for for get.active.lane.mask (#139084)

For now expansion still happens in SelectionDAGBuilder when
GET_ACTIVE_LANE_MASK is not legal on the target.

This patch also includes changes in AArch64ISelLowering to replace
handling of the get.active.lane.mask intrinsic to use the ISD node.
Tablegen patterns are added which match to whilelo for scalable types.

A follow up change will add support for more types to be lowered to
GET_ACTIVE_LANE_MASK by allowing splitting of the node.

Author: kmclaughlin-arm

llvm/include/llvm/CodeGen/ISDOpcodes.h

@@ -1533,6 +1533,15 @@ enum NodeType {
   // Operands: Mask
   VECTOR_FIND_LAST_ACTIVE,
 
+  // GET_ACTIVE_LANE_MASK - this corrosponds to the llvm.get.active.lane.mask
+  // intrinsic. It creates a mask representing active and inactive vector
+  // lanes, active while Base + index < Trip Count. As with the intrinsic,
+  // the operands Base and Trip Count have the same scalar integer type and
+  // the internal addition of Base + index cannot overflow. However, the ISD
+  // node supports result types which are wider than i1, where the high
+  // bits conform to getBooleanContents similar to the SETCC operator.
+  GET_ACTIVE_LANE_MASK,
+
   // llvm.clear_cache intrinsic
   // Operands: Input Chain, Start Addres, End Address
   // Outputs: Output Chain

llvm/include/llvm/Target/TargetSelectionDAG.td

@@ -860,6 +860,12 @@ def find_last_active
     : SDNode<"ISD::VECTOR_FIND_LAST_ACTIVE",
              SDTypeProfile<1, 1, [SDTCisInt<0>, SDTCisVec<1>]>, []>;
 
+def get_active_lane_mask
+    : SDNode<
+          "ISD::GET_ACTIVE_LANE_MASK",
+          SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisInt<1>, SDTCisSameAs<1, 2>]>,
+          []>;
+
 // Nodes for intrinsics, you should use the intrinsic itself and let tblgen use
 // these internally.  Don't reference these directly.
 def intrinsic_void : SDNode<"ISD::INTRINSIC_VOID",

llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp

@@ -160,6 +160,10 @@ void DAGTypeLegalizer::PromoteIntegerResult(SDNode *N, unsigned ResNo) {
     Res = PromoteIntRes_VECTOR_FIND_LAST_ACTIVE(N);
     break;
 
+  case ISD::GET_ACTIVE_LANE_MASK:
+    Res = PromoteIntRes_GET_ACTIVE_LANE_MASK(N);
+    break;
+
   case ISD::PARTIAL_REDUCE_UMLA:
   case ISD::PARTIAL_REDUCE_SMLA:
     Res = PromoteIntRes_PARTIAL_REDUCE_MLA(N);
@@ -6222,6 +6226,12 @@ SDValue DAGTypeLegalizer::PromoteIntRes_VECTOR_FIND_LAST_ACTIVE(SDNode *N) {
   return DAG.getNode(ISD::VECTOR_FIND_LAST_ACTIVE, SDLoc(N), NVT, N->ops());
 }
 
+SDValue DAGTypeLegalizer::PromoteIntRes_GET_ACTIVE_LANE_MASK(SDNode *N) {
+  EVT VT = N->getValueType(0);
+  EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), VT);
+  return DAG.getNode(ISD::GET_ACTIVE_LANE_MASK, SDLoc(N), NVT, N->ops());
+}
+
 SDValue DAGTypeLegalizer::PromoteIntRes_PARTIAL_REDUCE_MLA(SDNode *N) {
   SDLoc DL(N);
   EVT VT = N->getValueType(0);

llvm/lib/CodeGen/SelectionDAG/LegalizeTypes.h

@@ -379,6 +379,7 @@ class LLVM_LIBRARY_VISIBILITY DAGTypeLegalizer {
   SDValue PromoteIntRes_IS_FPCLASS(SDNode *N);
   SDValue PromoteIntRes_PATCHPOINT(SDNode *N);
   SDValue PromoteIntRes_VECTOR_FIND_LAST_ACTIVE(SDNode *N);
+  SDValue PromoteIntRes_GET_ACTIVE_LANE_MASK(SDNode *N);
   SDValue PromoteIntRes_PARTIAL_REDUCE_MLA(SDNode *N);
 
   // Integer Operand Promotion.

llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -7987,14 +7987,15 @@ void SelectionDAGBuilder::visitIntrinsicCall(const CallInst &I,
   case Intrinsic::get_active_lane_mask: {
     EVT CCVT = TLI.getValueType(DAG.getDataLayout(), I.getType());
     SDValue Index = getValue(I.getOperand(0));
+    SDValue TripCount = getValue(I.getOperand(1));
     EVT ElementVT = Index.getValueType();
 
     if (!TLI.shouldExpandGetActiveLaneMask(CCVT, ElementVT)) {
-      visitTargetIntrinsic(I, Intrinsic);
+      setValue(&I, DAG.getNode(ISD::GET_ACTIVE_LANE_MASK, sdl, CCVT, Index,
+                               TripCount));
       return;
     }
 
-    SDValue TripCount = getValue(I.getOperand(1));
     EVT VecTy = EVT::getVectorVT(*DAG.getContext(), ElementVT,
                                  CCVT.getVectorElementCount());
 

llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp

@@ -577,6 +577,9 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const {
   case ISD::VECTOR_FIND_LAST_ACTIVE:
     return "find_last_active";
 
+  case ISD::GET_ACTIVE_LANE_MASK:
+    return "get_active_lane_mask";
+
   case ISD::PARTIAL_REDUCE_UMLA:
     return "partial_reduce_umla";
   case ISD::PARTIAL_REDUCE_SMLA: