[AArch64][SVE] Remove index_vector node.

[junparser]

Summary

Since index_vector is lowered into step_vector in D100816, we can just remove
index_vector, use step_vector for codegen directly.

[junparser]

rebased.

[paulwalker-arm]

Please can you also remove INDEX_VECTOR from the AArch64ISD enum.

llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td

1371–1375

As a tidy up I'd say these multiclasses are intrinsically linked to stepvector and related nodes. As these nodes now have a unified form I personally don't see much value with the indirection and think they can use all the operations directly within the multiclass.

llvm/lib/Target/AArch64/SVEInstrFormats.td

4875–4876

The add(mul(step_vector comments in this class and sve_int_index_rr are missing a close ) for the mul.

[junparser]

llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td

1371–1375

Yep, It maybe nice to move these Pat to here.

llvm/lib/Target/AArch64/AArch64ISelLowering.cpp

if (!T->isSized() ||
     return SDValue();
 
   SDLoc DL(GN);
   SDValue Result = DAG.getGlobalAddress(GV, DL, MVT::i64, Offset);
   return DAG.getNode(ISD::SUB, DL, MVT::i64, Result,
                      DAG.getConstant(MinOffset, DL, MVT::i64));
 }
 
-static SDValue performStepVectorCombine(SDNode *N,
-                                        TargetLowering::DAGCombinerInfo &DCI,
-                                        SelectionDAG &DAG) {
-  if (!DCI.isAfterLegalizeDAG())
-    return SDValue();
-
-  SDLoc DL(N);
-  EVT VT = N->getValueType(0);
-  SDValue StepVal = N->getOperand(0);
-  SDValue Zero = DAG.getConstant(0, DL, StepVal.getValueType());
-  return DAG.getNode(AArch64ISD::INDEX_VECTOR, DL, VT, Zero, StepVal);
-}
-
 // Turns the vector of indices into a vector of byte offstes by scaling Offset
 // by (BitWidth / 8).
 static SDValue getScaledOffsetForBitWidth(SelectionDAG &DAG, SDValue Offset,
                                           SDLoc DL, unsigned BitWidth) {
   assert(Offset.getValueType().isScalableVector() &&
          "This method is only for scalable vectors of offsets");
 
   SDValue Shift = DAG.getConstant(Log2_32(BitWidth / 8), DL, MVT::i64);
SDValue AArch64TargetLowering::PerformDAGCombine(SDNode *N,
   case AArch64ISD::GLD1S_IMM_MERGE_ZERO:
     return performGLD1Combine(N, DAG);
   case ISD::INSERT_VECTOR_ELT:
     return performInsertVectorEltCombine(N, DCI);
   case ISD::EXTRACT_VECTOR_ELT:
     return performExtractVectorEltCombine(N, DAG);
   case ISD::VECREDUCE_ADD:
     return performVecReduceAddCombine(N, DCI.DAG, Subtarget);
-  case ISD::STEP_VECTOR:
-    return performStepVectorCombine(N, DCI, DAG);
   case ISD::INTRINSIC_VOID:
   case ISD::INTRINSIC_W_CHAIN:
     switch (cast<ConstantSDNode>(N->getOperand(1))->getZExtValue()) {
     case Intrinsic::aarch64_sve_prfb_gather_scalar_offset:
       return combineSVEPrefetchVecBaseImmOff(N, DAG, 1 /*=ScalarSizeInBytes*/);
     case Intrinsic::aarch64_sve_prfh_gather_scalar_offset:
       return combineSVEPrefetchVecBaseImmOff(N, DAG, 2 /*=ScalarSizeInBytes*/);
     case Intrinsic::aarch64_sve_prfw_gather_scalar_offset:

llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td

 def AArch64fadda_p    : SDNode<"AArch64ISD::FADDA_PRED", SDT_AArch64ReduceWithInit>;
 
 def SDT_AArch64PTest : SDTypeProfile<0, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
 def AArch64ptest     : SDNode<"AArch64ISD::PTEST", SDT_AArch64PTest>;
 
 def SDT_AArch64DUP_PRED  : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0, 3>, SDTCisVec<1>, SDTCVecEltisVT<1,i1>]>;
 def AArch64dup_mt : SDNode<"AArch64ISD::DUP_MERGE_PASSTHRU", SDT_AArch64DUP_PRED>;
 
-def SDT_IndexVector : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<1, 2>, SDTCisInt<2>]>;
-def index_vector : SDNode<"AArch64ISD::INDEX_VECTOR", SDT_IndexVector, []>;
-def index_vector_oneuse : PatFrag<(ops node:$base, node:$idx),
-                                  (index_vector node:$base, node:$idx), [{
+def step_vector_oneuse : PatFrag<(ops node:$idx),
+                                  (step_vector node:$idx), [{
   return N->hasOneUse();
 }]>;
 
 def reinterpret_cast : SDNode<"AArch64ISD::REINTERPRET_CAST", SDTUnaryOp>;
 
 def AArch64mul_p_oneuse : PatFrag<(ops node:$pred, node:$src1, node:$src2),
                                   (AArch64mul_p node:$pred, node:$src1, node:$src2), [{
   return N->hasOneUse();
def : Pat<(nxv2f64 (AArch64dup (f64 fpimm:$val))),
 
   defm SQINCP_ZP   : sve_int_count_v<0b00000, "sqincp", int_aarch64_sve_sqincp>;
   defm UQINCP_ZP   : sve_int_count_v<0b00100, "uqincp", int_aarch64_sve_uqincp>;
   defm SQDECP_ZP   : sve_int_count_v<0b01000, "sqdecp", int_aarch64_sve_sqdecp>;
   defm UQDECP_ZP   : sve_int_count_v<0b01100, "uqdecp", int_aarch64_sve_uqdecp>;
   defm INCP_ZP     : sve_int_count_v<0b10000, "incp">;
   defm DECP_ZP     : sve_int_count_v<0b10100, "decp">;
 
-  defm INDEX_RR : sve_int_index_rr<"index", index_vector, index_vector_oneuse, AArch64mul_p_oneuse>;
-  defm INDEX_IR : sve_int_index_ir<"index", index_vector, index_vector_oneuse, AArch64mul_p, AArch64mul_p_oneuse>;
-  defm INDEX_RI : sve_int_index_ri<"index", index_vector, index_vector_oneuse>;
-  defm INDEX_II : sve_int_index_ii<"index", index_vector, index_vector_oneuse>;
+  defm INDEX_RR : sve_int_index_rr<"index", step_vector, step_vector_oneuse, AArch64mul_p_oneuse>;
+  defm INDEX_IR : sve_int_index_ir<"index", step_vector, step_vector_oneuse, AArch64mul_p, AArch64mul_p_oneuse>;
+  defm INDEX_RI : sve_int_index_ri<"index", step_vector, step_vector_oneuse>;
+  defm INDEX_II : sve_int_index_ii<"index", step_vector, step_vector_oneuse>;
 
   // Unpredicated shifts
   defm ASR_ZZI : sve_int_bin_cons_shift_imm_right<0b00, "asr", AArch64asr_p>;
   defm LSR_ZZI : sve_int_bin_cons_shift_imm_right<0b01, "lsr", AArch64lsr_p>;
   defm LSL_ZZI : sve_int_bin_cons_shift_imm_left< 0b11, "lsl", AArch64lsl_p>;
 
   defm ASR_WIDE_ZZZ : sve_int_bin_cons_shift_wide<0b00, "asr">;
   defm LSR_WIDE_ZZZ : sve_int_bin_cons_shift_wide<0b01, "lsr">;
   defm LSL_WIDE_ZZZ : sve_int_bin_cons_shift_wide<0b11, "lsl">;

llvm/lib/Target/AArch64/SVEInstrFormats.td

 }
 
 multiclass sve_int_index_ii<string asm, SDPatternOperator op, SDPatternOperator oneuseop> {
   def _B : sve_int_index_ii<0b00, asm, ZPR8, simm5_8b>;
   def _H : sve_int_index_ii<0b01, asm, ZPR16, simm5_16b>;
   def _S : sve_int_index_ii<0b10, asm, ZPR32, simm5_32b>;
   def _D : sve_int_index_ii<0b11, asm, ZPR64, simm5_64b>;
 
-  def : Pat<(nxv16i8 (op simm5_8b:$imm5, simm5_8b:$imm5b)),
-            (!cast<Instruction>(NAME # "_B") simm5_8b:$imm5, simm5_8b:$imm5b)>;
-  def : Pat<(nxv8i16 (op simm5_16b:$imm5, simm5_16b:$imm5b)),
-            (!cast<Instruction>(NAME # "_H") simm5_16b:$imm5, simm5_16b:$imm5b)>;
-  def : Pat<(nxv4i32 (op simm5_32b:$imm5, simm5_32b:$imm5b)),
-            (!cast<Instruction>(NAME # "_S") simm5_32b:$imm5, simm5_32b:$imm5b)>;
-  def : Pat<(nxv2i64 (op simm5_64b:$imm5, simm5_64b:$imm5b)),
-            (!cast<Instruction>(NAME # "_D") simm5_64b:$imm5, simm5_64b:$imm5b)>;
+  def : Pat<(nxv16i8 (op simm5_8b:$imm5b)),
+            (!cast<Instruction>(NAME # "_B") (i32 0), simm5_8b:$imm5b)>;
+  def : Pat<(nxv8i16 (op simm5_16b:$imm5b)),
+            (!cast<Instruction>(NAME # "_H") (i32 0), simm5_16b:$imm5b)>;
+  def : Pat<(nxv4i32 (op simm5_32b:$imm5b)),
+            (!cast<Instruction>(NAME # "_S") (i32 0), simm5_32b:$imm5b)>;
+  def : Pat<(nxv2i64 (op simm5_64b:$imm5b)),
+            (!cast<Instruction>(NAME # "_D") (i64 0), simm5_64b:$imm5b)>;
 
-  // add(index_vector(zero, step), dup(X)) -> index_vector(X, step).
-  def : Pat<(add (nxv16i8 (oneuseop (i32 0), simm5_8b:$imm5b)), (nxv16i8 (AArch64dup(simm5_8b:$imm5)))),
+  // add(step_vector(step), dup(X)) -> index(X, step).
+  def : Pat<(add (nxv16i8 (oneuseop simm5_8b:$imm5b)), (nxv16i8 (AArch64dup(simm5_8b:$imm5)))),
             (!cast<Instruction>(NAME # "_B") simm5_8b:$imm5, simm5_8b:$imm5b)>;
-  def : Pat<(add (nxv8i16 (oneuseop (i32 0), simm5_16b:$imm5b)), (nxv8i16 (AArch64dup(simm5_16b:$imm5)))),
+  def : Pat<(add (nxv8i16 (oneuseop simm5_16b:$imm5b)), (nxv8i16 (AArch64dup(simm5_16b:$imm5)))),
             (!cast<Instruction>(NAME # "_H") simm5_16b:$imm5, simm5_16b:$imm5b)>;
-  def : Pat<(add (nxv4i32 (oneuseop (i32 0), simm5_32b:$imm5b)), (nxv4i32 (AArch64dup(simm5_32b:$imm5)))),
+  def : Pat<(add (nxv4i32 (oneuseop simm5_32b:$imm5b)), (nxv4i32 (AArch64dup(simm5_32b:$imm5)))),
             (!cast<Instruction>(NAME # "_S") simm5_32b:$imm5, simm5_32b:$imm5b)>;
-  def : Pat<(add (nxv2i64 (oneuseop (i64 0), simm5_64b:$imm5b)), (nxv2i64 (AArch64dup(simm5_64b:$imm5)))),
+  def : Pat<(add (nxv2i64 (oneuseop simm5_64b:$imm5b)), (nxv2i64 (AArch64dup(simm5_64b:$imm5)))),
             (!cast<Instruction>(NAME # "_D") simm5_64b:$imm5, simm5_64b:$imm5b)>;
 }
 
 class sve_int_index_ir<bits<2> sz8_64, string asm, ZPRRegOp zprty,
                        RegisterClass srcRegType, Operand imm_ty>
 : I<(outs zprty:$Zd), (ins imm_ty:$imm5, srcRegType:$Rm),
   asm, "\t$Zd, $imm5, $Rm",
   "", []>, Sched<[]> {

 }
 
 multiclass sve_int_index_ir<string asm, SDPatternOperator op, SDPatternOperator oneuseop, SDPatternOperator mulop, SDPatternOperator muloneuseop> {
   def _B : sve_int_index_ir<0b00, asm, ZPR8, GPR32, simm5_8b>;
   def _H : sve_int_index_ir<0b01, asm, ZPR16, GPR32, simm5_16b>;
   def _S : sve_int_index_ir<0b10, asm, ZPR32, GPR32, simm5_32b>;
   def _D : sve_int_index_ir<0b11, asm, ZPR64, GPR64, simm5_64b>;
 
-  def : Pat<(nxv16i8 (op simm5_8b:$imm5, GPR32:$Rm)),
-            (!cast<Instruction>(NAME # "_B") simm5_8b:$imm5, GPR32:$Rm)>;
-  def : Pat<(nxv8i16 (op simm5_16b:$imm5, GPR32:$Rm)),
-            (!cast<Instruction>(NAME # "_H") simm5_16b:$imm5, GPR32:$Rm)>;
-  def : Pat<(nxv4i32 (op simm5_32b:$imm5, GPR32:$Rm)),
-            (!cast<Instruction>(NAME # "_S") simm5_32b:$imm5, GPR32:$Rm)>;
-  def : Pat<(nxv2i64 (op simm5_64b:$imm5, GPR64:$Rm)),
-            (!cast<Instruction>(NAME # "_D") simm5_64b:$imm5, GPR64:$Rm)>;
+  def : Pat<(nxv16i8 (op GPR32:$Rm)),
+            (!cast<Instruction>(NAME # "_B") (i32 0), GPR32:$Rm)>;
+  def : Pat<(nxv8i16 (op GPR32:$Rm)),
+            (!cast<Instruction>(NAME # "_H") (i32 0), GPR32:$Rm)>;
+  def : Pat<(nxv4i32 (op GPR32:$Rm)),
+            (!cast<Instruction>(NAME # "_S") (i32 0), GPR32:$Rm)>;
+  def : Pat<(nxv2i64 (op GPR64:$Rm)),
+            (!cast<Instruction>(NAME # "_D") (i64 0), GPR64:$Rm)>;
 
-  // add(index_vector(zero, step), dup(X)) -> index_vector(X, step).
-  def : Pat<(add (nxv16i8 (oneuseop (i32 0), GPR32:$Rm)), (nxv16i8 (AArch64dup(simm5_8b:$imm5)))),
+  // add(step_vector(step), dup(X)) -> index(X, step).
+  def : Pat<(add (nxv16i8 (oneuseop GPR32:$Rm)), (nxv16i8 (AArch64dup(simm5_8b:$imm5)))),
             (!cast<Instruction>(NAME # "_B") simm5_8b:$imm5, GPR32:$Rm)>;
-  def : Pat<(add (nxv8i16 (oneuseop (i32 0), GPR32:$Rm)), (nxv8i16 (AArch64dup(simm5_16b:$imm5)))),
+  def : Pat<(add (nxv8i16 (oneuseop GPR32:$Rm)), (nxv8i16 (AArch64dup(simm5_16b:$imm5)))),
             (!cast<Instruction>(NAME # "_H") simm5_16b:$imm5, GPR32:$Rm)>;
-  def : Pat<(add (nxv4i32 (oneuseop (i32 0), GPR32:$Rm)), (nxv4i32 (AArch64dup(simm5_32b:$imm5)))),
+  def : Pat<(add (nxv4i32 (oneuseop GPR32:$Rm)), (nxv4i32 (AArch64dup(simm5_32b:$imm5)))),
             (!cast<Instruction>(NAME # "_S") simm5_32b:$imm5, GPR32:$Rm)>;
-  def : Pat<(add (nxv2i64 (oneuseop (i64 0), GPR64:$Rm)), (nxv2i64 (AArch64dup(simm5_64b:$imm5)))),
+  def : Pat<(add (nxv2i64 (oneuseop GPR64:$Rm)), (nxv2i64 (AArch64dup(simm5_64b:$imm5)))),
             (!cast<Instruction>(NAME # "_D") simm5_64b:$imm5, GPR64:$Rm)>;
 
-  // mul(index_vector(0, 1), dup(Y)) -> index_vector(0, Y).
-  def : Pat<(mulop (nxv16i1 (AArch64ptrue 31)), (nxv16i8 (oneuseop (i32 0), (i32 1))), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))),
+  // mul(step_vector(1), dup(Y)) -> index(0, Y).
+  def : Pat<(mulop (nxv16i1 (AArch64ptrue 31)), (nxv16i8 (oneuseop (i32 1))), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))),
             (!cast<Instruction>(NAME # "_B") (i32 0), GPR32:$Rm)>;
-  def : Pat<(mulop (nxv8i1 (AArch64ptrue 31)), (nxv8i16 (oneuseop (i32 0), (i32 1))), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))),
+  def : Pat<(mulop (nxv8i1 (AArch64ptrue 31)), (nxv8i16 (oneuseop (i32 1))), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))),
             (!cast<Instruction>(NAME # "_H") (i32 0), GPR32:$Rm)>;
-  def : Pat<(mulop (nxv4i1 (AArch64ptrue 31)), (nxv4i32 (oneuseop (i32 0), (i32 1))), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))),
+  def : Pat<(mulop (nxv4i1 (AArch64ptrue 31)), (nxv4i32 (oneuseop (i32 1))), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))),
             (!cast<Instruction>(NAME # "_S") (i32 0), GPR32:$Rm)>;
-  def : Pat<(mulop (nxv2i1 (AArch64ptrue 31)), (nxv2i64 (oneuseop (i64 0), (i64 1))), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))),
+  def : Pat<(mulop (nxv2i1 (AArch64ptrue 31)), (nxv2i64 (oneuseop (i64 1))), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))),
             (!cast<Instruction>(NAME # "_D") (i64 0), GPR64:$Rm)>;
 
-  // add(mul(index_vector(0, 1), dup(Y), dup(X)) -> index_vector(X, Y).
-  def : Pat<(add (muloneuseop (nxv16i1 (AArch64ptrue 31)), (nxv16i8 (oneuseop (i32 0), (i32 1))), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))), (nxv16i8 (AArch64dup(simm5_8b:$imm5)))),
+  // add(mul(step_vector(1), dup(Y), dup(X)) -> index(X, Y).
+  def : Pat<(add (muloneuseop (nxv16i1 (AArch64ptrue 31)), (nxv16i8 (oneuseop (i32 1))), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))), (nxv16i8 (AArch64dup(simm5_8b:$imm5)))),
             (!cast<Instruction>(NAME # "_B") simm5_8b:$imm5, GPR32:$Rm)>;
-  def : Pat<(add (muloneuseop (nxv8i1 (AArch64ptrue 31)), (nxv8i16 (oneuseop (i32 0), (i32 1))), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))), (nxv8i16 (AArch64dup(simm5_16b:$imm5)))),
+  def : Pat<(add (muloneuseop (nxv8i1 (AArch64ptrue 31)), (nxv8i16 (oneuseop (i32 1))), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))), (nxv8i16 (AArch64dup(simm5_16b:$imm5)))),
             (!cast<Instruction>(NAME # "_H") simm5_16b:$imm5, GPR32:$Rm)>;
-  def : Pat<(add (muloneuseop (nxv4i1 (AArch64ptrue 31)), (nxv4i32 (oneuseop (i32 0), (i32 1))), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))), (nxv4i32 (AArch64dup(simm5_32b:$imm5)))),
+  def : Pat<(add (muloneuseop (nxv4i1 (AArch64ptrue 31)), (nxv4i32 (oneuseop (i32 1))), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))), (nxv4i32 (AArch64dup(simm5_32b:$imm5)))),
             (!cast<Instruction>(NAME # "_S") simm5_32b:$imm5, GPR32:$Rm)>;
-  def : Pat<(add (muloneuseop (nxv2i1 (AArch64ptrue 31)), (nxv2i64 (oneuseop (i64 0), (i64 1))), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))), (nxv2i64 (AArch64dup(simm5_64b:$imm5)))),
+  def : Pat<(add (muloneuseop (nxv2i1 (AArch64ptrue 31)), (nxv2i64 (oneuseop (i64 1))), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))), (nxv2i64 (AArch64dup(simm5_64b:$imm5)))),
             (!cast<Instruction>(NAME # "_D") simm5_64b:$imm5, GPR64:$Rm)>;
 }
 
 class sve_int_index_ri<bits<2> sz8_64, string asm, ZPRRegOp zprty,
                        RegisterClass srcRegType, Operand imm_ty>
 : I<(outs zprty:$Zd), (ins srcRegType:$Rn, imm_ty:$imm5),
   asm, "\t$Zd, $Rn, $imm5",
   "", []>, Sched<[]> {

 }
 
 multiclass sve_int_index_ri<string asm, SDPatternOperator op, SDPatternOperator oneuseop> {
   def _B : sve_int_index_ri<0b00, asm, ZPR8, GPR32, simm5_8b>;
   def _H : sve_int_index_ri<0b01, asm, ZPR16, GPR32, simm5_16b>;
   def _S : sve_int_index_ri<0b10, asm, ZPR32, GPR32, simm5_32b>;
   def _D : sve_int_index_ri<0b11, asm, ZPR64, GPR64, simm5_64b>;
 
-  def : Pat<(nxv16i8 (op GPR32:$Rm, simm5_8b:$imm5)),
+  // add(step_vector(step), dup(X)) -> index(X, step).
+  def : Pat<(add (nxv16i8 (oneuseop simm5_8b:$imm5)), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))),
             (!cast<Instruction>(NAME # "_B") GPR32:$Rm, simm5_8b:$imm5)>;
-  def : Pat<(nxv8i16 (op GPR32:$Rm, simm5_16b:$imm5)),
+  def : Pat<(add (nxv8i16 (oneuseop simm5_16b:$imm5)), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))),
             (!cast<Instruction>(NAME # "_H") GPR32:$Rm, simm5_16b:$imm5)>;
-  def : Pat<(nxv4i32 (op GPR32:$Rm, simm5_32b:$imm5)),
+  def : Pat<(add (nxv4i32 (oneuseop simm5_32b:$imm5)), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))),
             (!cast<Instruction>(NAME # "_S") GPR32:$Rm, simm5_32b:$imm5)>;
-  def : Pat<(nxv2i64 (op GPR64:$Rm, simm5_64b:$imm5)),
-            (!cast<Instruction>(NAME # "_D") GPR64:$Rm, simm5_64b:$imm5)>;
-
-  // add(index_vector(zero, step), dup(X)) -> index_vector(X, step).
-  def : Pat<(add (nxv16i8 (oneuseop (i32 0), simm5_8b:$imm5)), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))),
-            (!cast<Instruction>(NAME # "_B") GPR32:$Rm, simm5_8b:$imm5)>;
-  def : Pat<(add (nxv8i16 (oneuseop (i32 0), simm5_16b:$imm5)), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))),
-            (!cast<Instruction>(NAME # "_H") GPR32:$Rm, simm5_16b:$imm5)>;
-  def : Pat<(add (nxv4i32 (oneuseop (i32 0), simm5_32b:$imm5)), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))),
-            (!cast<Instruction>(NAME # "_S") GPR32:$Rm, simm5_32b:$imm5)>;
-  def : Pat<(add (nxv2i64 (oneuseop (i64 0), simm5_64b:$imm5)), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))),
+  def : Pat<(add (nxv2i64 (oneuseop simm5_64b:$imm5)), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))),
             (!cast<Instruction>(NAME # "_D") GPR64:$Rm, simm5_64b:$imm5)>;
 }
 
 class sve_int_index_rr<bits<2> sz8_64, string asm, ZPRRegOp zprty,
                        RegisterClass srcRegType>
 : I<(outs zprty:$Zd), (ins srcRegType:$Rn, srcRegType:$Rm),
   asm, "\t$Zd, $Rn, $Rm",
   "", []>, Sched<[]> {

 }
 
 multiclass sve_int_index_rr<string asm, SDPatternOperator op, SDPatternOperator oneuseop, SDPatternOperator mulop> {
   def _B : sve_int_index_rr<0b00, asm, ZPR8, GPR32>;
   def _H : sve_int_index_rr<0b01, asm, ZPR16, GPR32>;
   def _S : sve_int_index_rr<0b10, asm, ZPR32, GPR32>;
   def _D : sve_int_index_rr<0b11, asm, ZPR64, GPR64>;
 
-  def : SVE_2_Op_Pat<nxv16i8, op, i32, i32, !cast<Instruction>(NAME # _B)>;
-  def : SVE_2_Op_Pat<nxv8i16, op, i32, i32, !cast<Instruction>(NAME # _H)>;
-  def : SVE_2_Op_Pat<nxv4i32, op, i32, i32, !cast<Instruction>(NAME # _S)>;
-  def : SVE_2_Op_Pat<nxv2i64, op, i64, i64, !cast<Instruction>(NAME # _D)>;
-
-  // add(index_vector(zero, step), dup(X)) -> index_vector(X, step).
-  def : Pat<(add (nxv16i8 (oneuseop (i32 0), GPR32:$Rm)), (nxv16i8 (AArch64dup(i32 GPR32:$Rn)))),
+  // add(step_vector(step), dup(X)) -> index(X, step).
+  def : Pat<(add (nxv16i8 (oneuseop GPR32:$Rm)), (nxv16i8 (AArch64dup(i32 GPR32:$Rn)))),
             (!cast<Instruction>(NAME # "_B") GPR32:$Rn, GPR32:$Rm)>;
-  def : Pat<(add (nxv8i16 (oneuseop (i32 0), GPR32:$Rm)), (nxv8i16 (AArch64dup(i32 GPR32:$Rn)))),
+  def : Pat<(add (nxv8i16 (oneuseop GPR32:$Rm)), (nxv8i16 (AArch64dup(i32 GPR32:$Rn)))),
             (!cast<Instruction>(NAME # "_H") GPR32:$Rn, GPR32:$Rm)>;
-  def : Pat<(add (nxv4i32 (oneuseop (i32 0), GPR32:$Rm)), (nxv4i32 (AArch64dup(i32 GPR32:$Rn)))),
+  def : Pat<(add (nxv4i32 (oneuseop GPR32:$Rm)), (nxv4i32 (AArch64dup(i32 GPR32:$Rn)))),
             (!cast<Instruction>(NAME # "_S") GPR32:$Rn, GPR32:$Rm)>;
-  def : Pat<(add (nxv2i64 (oneuseop (i64 0), GPR64:$Rm)), (nxv2i64 (AArch64dup(i64 GPR64:$Rn)))),
+  def : Pat<(add (nxv2i64 (oneuseop GPR64:$Rm)), (nxv2i64 (AArch64dup(i64 GPR64:$Rn)))),
             (!cast<Instruction>(NAME # "_D") GPR64:$Rn, GPR64:$Rm)>;
 
-  // add(mul(index_vector(0, 1), dup(Y), dup(X)) -> index_vector(X, Y).
-  def : Pat<(add (mulop (nxv16i1 (AArch64ptrue 31)), (nxv16i8 (oneuseop (i32 0), (i32 1))), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))), (nxv16i8 (AArch64dup(i32 GPR32:$Rn)))),
+  // add(mul(step_vector(1), dup(Y), dup(X)) -> index(X, Y).
+  def : Pat<(add (mulop (nxv16i1 (AArch64ptrue 31)), (nxv16i8 (oneuseop (i32 1))), (nxv16i8 (AArch64dup(i32 GPR32:$Rm)))), (nxv16i8 (AArch64dup(i32 GPR32:$Rn)))),
             (!cast<Instruction>(NAME # "_B") GPR32:$Rn, GPR32:$Rm)>;
-  def : Pat<(add (mulop (nxv8i1 (AArch64ptrue 31)), (nxv8i16 (oneuseop (i32 0), (i32 1))), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))),(nxv8i16 (AArch64dup(i32 GPR32:$Rn)))),
+  def : Pat<(add (mulop (nxv8i1 (AArch64ptrue 31)), (nxv8i16 (oneuseop (i32 1))), (nxv8i16 (AArch64dup(i32 GPR32:$Rm)))),(nxv8i16 (AArch64dup(i32 GPR32:$Rn)))),
             (!cast<Instruction>(NAME # "_H") GPR32:$Rn, GPR32:$Rm)>;
-  def : Pat<(add (mulop (nxv4i1 (AArch64ptrue 31)), (nxv4i32 (oneuseop (i32 0), (i32 1))), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))),(nxv4i32 (AArch64dup(i32 GPR32:$Rn)))),
+  def : Pat<(add (mulop (nxv4i1 (AArch64ptrue 31)), (nxv4i32 (oneuseop (i32 1))), (nxv4i32 (AArch64dup(i32 GPR32:$Rm)))),(nxv4i32 (AArch64dup(i32 GPR32:$Rn)))),
             (!cast<Instruction>(NAME # "_S") GPR32:$Rn, GPR32:$Rm)>;
-  def : Pat<(add (mulop (nxv2i1 (AArch64ptrue 31)), (nxv2i64 (oneuseop (i64 0), (i64 1))), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))),(nxv2i64 (AArch64dup(i64 GPR64:$Rn)))),
+  def : Pat<(add (mulop (nxv2i1 (AArch64ptrue 31)), (nxv2i64 (oneuseop (i64 1))), (nxv2i64 (AArch64dup(i64 GPR64:$Rm)))),(nxv2i64 (AArch64dup(i64 GPR64:$Rn)))),
             (!cast<Instruction>(NAME # "_D") GPR64:$Rn, GPR64:$Rm)>;
 }
 
 //===----------------------------------------------------------------------===//
 // SVE Bitwise Shift - Predicated Group
 //===----------------------------------------------------------------------===//
 
 class sve_int_bin_pred_shift_imm<bits<4> tsz8_64, bits<4> opc, string asm,