[RISCV] Use ri.vzip2{a,b} for interleave2 if available (#136364)

If XRivosVizip is available, the ri.vzip2a and ri.vzip2b instructions
can be used perform a interleave shuffle. This patch only effects the
intrinsic lowering (and thus scalable vectors). Fixed vectors go through
shuffle lowering and the zip2a (but not zip2b) case is already handled
there..

Author: preames

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -5027,8 +5027,8 @@ static SDValue lowerVZIP(unsigned Opc, SDValue Op0, SDValue Op1,
                          const SDLoc &DL, SelectionDAG &DAG,
                          const RISCVSubtarget &Subtarget) {
   assert(RISCVISD::RI_VZIPEVEN_VL == Opc || RISCVISD::RI_VZIPODD_VL == Opc ||
-         RISCVISD::RI_VZIP2A_VL == Opc || RISCVISD::RI_VUNZIP2A_VL == Opc ||
-         RISCVISD::RI_VUNZIP2B_VL == Opc);
+         RISCVISD::RI_VZIP2A_VL == Opc || RISCVISD::RI_VZIP2B_VL == Opc ||
+         RISCVISD::RI_VUNZIP2A_VL == Opc || RISCVISD::RI_VUNZIP2B_VL == Opc);
   assert(Op0.getSimpleValueType() == Op1.getSimpleValueType());
 
   MVT VT = Op0.getSimpleValueType();
@@ -6944,7 +6944,7 @@ static bool hasPassthruOp(unsigned Opcode) {
          Opcode <= RISCVISD::LAST_STRICTFP_OPCODE &&
          "not a RISC-V target specific op");
   static_assert(
-      RISCVISD::LAST_VL_VECTOR_OP - RISCVISD::FIRST_VL_VECTOR_OP == 132 &&
+      RISCVISD::LAST_VL_VECTOR_OP - RISCVISD::FIRST_VL_VECTOR_OP == 133 &&
       RISCVISD::LAST_STRICTFP_OPCODE - RISCVISD::FIRST_STRICTFP_OPCODE == 21 &&
       "adding target specific op should update this function");
   if (Opcode >= RISCVISD::ADD_VL && Opcode <= RISCVISD::VFMAX_VL)
@@ -6968,7 +6968,7 @@ static bool hasMaskOp(unsigned Opcode) {
          Opcode <= RISCVISD::LAST_STRICTFP_OPCODE &&
          "not a RISC-V target specific op");
   static_assert(
-      RISCVISD::LAST_VL_VECTOR_OP - RISCVISD::FIRST_VL_VECTOR_OP == 132 &&
+      RISCVISD::LAST_VL_VECTOR_OP - RISCVISD::FIRST_VL_VECTOR_OP == 133 &&
       RISCVISD::LAST_STRICTFP_OPCODE - RISCVISD::FIRST_STRICTFP_OPCODE == 21 &&
       "adding target specific op should update this function");
   if (Opcode >= RISCVISD::TRUNCATE_VECTOR_VL && Opcode <= RISCVISD::SETCC_VL)
@@ -11762,6 +11762,17 @@ SDValue RISCVTargetLowering::lowerVECTOR_INTERLEAVE(SDValue Op,
     return DAG.getMergeValues(Loads, DL);
   }
 
+  // Use ri.vzip2{a,b} if available
+  // TODO: Figure out the best lowering for the spread variants
+  if (Subtarget.hasVendorXRivosVizip() && !Op.getOperand(0).isUndef() &&
+      !Op.getOperand(1).isUndef()) {
+    SDValue V1 = Op->getOperand(0);
+    SDValue V2 = Op->getOperand(1);
+    SDValue Lo = lowerVZIP(RISCVISD::RI_VZIP2A_VL, V1, V2, DL, DAG, Subtarget);
+    SDValue Hi = lowerVZIP(RISCVISD::RI_VZIP2B_VL, V1, V2, DL, DAG, Subtarget);
+    return DAG.getMergeValues({Lo, Hi}, DL);
+  }
+
   // If the element type is smaller than ELEN, then we can interleave with
   // vwaddu.vv and vwmaccu.vx
   if (VecVT.getScalarSizeInBits() < Subtarget.getELen()) {
@@ -22265,6 +22276,7 @@ const char *RISCVTargetLowering::getTargetNodeName(unsigned Opcode) const {
   NODE_NAME_CASE(RI_VZIPEVEN_VL)
   NODE_NAME_CASE(RI_VZIPODD_VL)
   NODE_NAME_CASE(RI_VZIP2A_VL)
+  NODE_NAME_CASE(RI_VZIP2B_VL)
   NODE_NAME_CASE(RI_VUNZIP2A_VL)
   NODE_NAME_CASE(RI_VUNZIP2B_VL)
   NODE_NAME_CASE(READ_CSR)

llvm/lib/Target/RISCV/RISCVISelLowering.h

@@ -408,6 +408,7 @@ enum NodeType : unsigned {
   RI_VZIPEVEN_VL,
   RI_VZIPODD_VL,
   RI_VZIP2A_VL,
+  RI_VZIP2B_VL,
   RI_VUNZIP2A_VL,
   RI_VUNZIP2B_VL,
 

llvm/lib/Target/RISCV/RISCVInstrInfoXRivos.td

@@ -71,6 +71,7 @@ defm RI_VUNZIP2B_V : VALU_IV_V<"ri.vunzip2b", 0b011000>;
 def ri_vzipeven_vl : SDNode<"RISCVISD::RI_VZIPEVEN_VL", SDT_RISCVIntBinOp_VL>;
 def ri_vzipodd_vl : SDNode<"RISCVISD::RI_VZIPODD_VL", SDT_RISCVIntBinOp_VL>;
 def ri_vzip2a_vl : SDNode<"RISCVISD::RI_VZIP2A_VL", SDT_RISCVIntBinOp_VL>;
+def ri_vzip2b_vl : SDNode<"RISCVISD::RI_VZIP2B_VL", SDT_RISCVIntBinOp_VL>;
 def ri_vunzip2a_vl : SDNode<"RISCVISD::RI_VUNZIP2A_VL", SDT_RISCVIntBinOp_VL>;
 def ri_vunzip2b_vl : SDNode<"RISCVISD::RI_VUNZIP2B_VL", SDT_RISCVIntBinOp_VL>;
 
@@ -84,6 +85,7 @@ let Predicates = [HasVendorXRivosVizip],
 defm PseudoRI_VZIPEVEN   : RIVPseudoVALU_VV;
 defm PseudoRI_VZIPODD   : RIVPseudoVALU_VV;
 defm PseudoRI_VZIP2A   : RIVPseudoVALU_VV;
+defm PseudoRI_VZIP2B   : RIVPseudoVALU_VV;
 defm PseudoRI_VUNZIP2A   : RIVPseudoVALU_VV;
 defm PseudoRI_VUNZIP2B   : RIVPseudoVALU_VV;
 }
@@ -102,6 +104,7 @@ multiclass RIVPatBinaryVL_VV<SDPatternOperator vop, string instruction_name,
 defm : RIVPatBinaryVL_VV<ri_vzipeven_vl, "PseudoRI_VZIPEVEN">;
 defm : RIVPatBinaryVL_VV<ri_vzipodd_vl, "PseudoRI_VZIPODD">;
 defm : RIVPatBinaryVL_VV<ri_vzip2a_vl, "PseudoRI_VZIP2A">;
+defm : RIVPatBinaryVL_VV<ri_vzip2b_vl, "PseudoRI_VZIP2B">;
 defm : RIVPatBinaryVL_VV<ri_vunzip2a_vl, "PseudoRI_VUNZIP2A">;
 defm : RIVPatBinaryVL_VV<ri_vunzip2b_vl, "PseudoRI_VUNZIP2B">;