[RISCV] Use tablegen size for getInstSizeInBytes.

[craig.topper]

Summary

Fix the pseudos to have the correct size in the MCInstrDesc description.

Inspired by D118009 and D117970.

[asb]

This is definitely cleaner, thanks.

[jrtc27]

llvm/lib/Target/RISCV/RISCVInstrInfo.cpp

988

Hm, we've lost these cross-references, and RISCVExpandAtomicPseudo::expandMI, RISCVExpandPseudo::expandMI and ISCVMCCodeEmitter::encodeInstruction now have stale references back to here

llvm/lib/Target/RISCV/RISCVInstrInfo.cpp

 //===-- RISCVInstrInfo.cpp - RISCV Instruction Information ------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
bool RISCVInstrInfo::isBranchOffsetInRange(unsigned BranchOp,
   case RISCV::PseudoBR:
     return isIntN(21, BrOffset);
   case RISCV::PseudoJump:
     return isIntN(32, SignExtend64(BrOffset + 0x800, XLen));
   }
 }
 
 unsigned RISCVInstrInfo::getInstSizeInBytes(const MachineInstr &MI) const {
+  if (MI.isMetaInstruction())
+    return 0;
+
   unsigned Opcode = MI.getOpcode();
 
-  switch (Opcode) {
-  default: {
-    if (MI.getParent() && MI.getParent()->getParent()) {
-      const auto MF = MI.getMF();
-      const auto &TM = static_cast<const RISCVTargetMachine &>(MF->getTarget());
-      const MCRegisterInfo &MRI = *TM.getMCRegisterInfo();
-      const MCSubtargetInfo &STI = *TM.getMCSubtargetInfo();
-      const RISCVSubtarget &ST = MF->getSubtarget<RISCVSubtarget>();
-      if (isCompressibleInst(MI, &ST, MRI, STI))
-        return 2;
-    }
-    return get(Opcode).getSize();
-  }
-  case TargetOpcode::EH_LABEL:
-  case TargetOpcode::IMPLICIT_DEF:
-  case TargetOpcode::KILL:
-  case TargetOpcode::DBG_VALUE:
-    return 0;
-  // These values are determined based on RISCVExpandAtomicPseudoInsts,
-  // RISCVExpandPseudoInsts and RISCVMCCodeEmitter, depending on where the
-  // pseudos are expanded.
-  case RISCV::PseudoCALLReg:
-  case RISCV::PseudoCALL:
-  case RISCV::PseudoJump:
-  case RISCV::PseudoTAIL:
-  case RISCV::PseudoLLA:
-  case RISCV::PseudoLA:
-  case RISCV::PseudoLA_TLS_IE:
-  case RISCV::PseudoLA_TLS_GD:
-    return 8;
-  case RISCV::PseudoAtomicLoadNand32:
-  case RISCV::PseudoAtomicLoadNand64:
-    return 20;
-  case RISCV::PseudoMaskedAtomicSwap32:
-  case RISCV::PseudoMaskedAtomicLoadAdd32:
-  case RISCV::PseudoMaskedAtomicLoadSub32:
-    return 28;
-  case RISCV::PseudoMaskedAtomicLoadNand32:
-    return 32;
-  case RISCV::PseudoMaskedAtomicLoadMax32:
-  case RISCV::PseudoMaskedAtomicLoadMin32:
-    return 44;
-  case RISCV::PseudoMaskedAtomicLoadUMax32:
-  case RISCV::PseudoMaskedAtomicLoadUMin32:
-    return 36;
-  case RISCV::PseudoCmpXchg32:
-  case RISCV::PseudoCmpXchg64:
-    return 16;
-  case RISCV::PseudoMaskedCmpXchg32:
-    return 32;
-  case TargetOpcode::INLINEASM:
-  case TargetOpcode::INLINEASM_BR: {
-    const MachineFunction &MF = *MI.getParent()->getParent();
-    const auto &TM = static_cast<const RISCVTargetMachine &>(MF.getTarget());
-    return getInlineAsmLength(MI.getOperand(0).getSymbolName(),
-                              *TM.getMCAsmInfo());
-  }
-  case RISCV::PseudoVSPILL2_M1:
-  case RISCV::PseudoVSPILL2_M2:
-  case RISCV::PseudoVSPILL2_M4:
-  case RISCV::PseudoVSPILL3_M1:
-  case RISCV::PseudoVSPILL3_M2:
-  case RISCV::PseudoVSPILL4_M1:
-  case RISCV::PseudoVSPILL4_M2:
-  case RISCV::PseudoVSPILL5_M1:
-  case RISCV::PseudoVSPILL6_M1:
-  case RISCV::PseudoVSPILL7_M1:
-  case RISCV::PseudoVSPILL8_M1:
-  case RISCV::PseudoVRELOAD2_M1:
-  case RISCV::PseudoVRELOAD2_M2:
-  case RISCV::PseudoVRELOAD2_M4:
-  case RISCV::PseudoVRELOAD3_M1:
-  case RISCV::PseudoVRELOAD3_M2:
-  case RISCV::PseudoVRELOAD4_M1:
-  case RISCV::PseudoVRELOAD4_M2:
-  case RISCV::PseudoVRELOAD5_M1:
-  case RISCV::PseudoVRELOAD6_M1:
-  case RISCV::PseudoVRELOAD7_M1:
-  case RISCV::PseudoVRELOAD8_M1: {
-    // The values are determined based on expandVSPILL and expandVRELOAD that
-    // expand the pseudos depending on NF.
-    unsigned NF = isRVVSpillForZvlsseg(Opcode)->first;
-    return 4 * (2 * NF - 1);
-  }
-  }
-}
+  if (Opcode == TargetOpcode::INLINEASM ||
+      Opcode == TargetOpcode::INLINEASM_BR) {
+    const MachineFunction &MF = *MI.getParent()->getParent();
+    const auto &TM = static_cast<const RISCVTargetMachine &>(MF.getTarget());
+    return getInlineAsmLength(MI.getOperand(0).getSymbolName(),
+                              *TM.getMCAsmInfo());
+  }
+
 
 bool RISCVInstrInfo::isAsCheapAsAMove(const MachineInstr &MI) const {
   const unsigned Opcode = MI.getOpcode();
   switch (Opcode) {
   default:
     break;
   case RISCV::FSGNJ_D:
   case RISCV::FSGNJ_S:

llvm/lib/Target/RISCV/RISCVInstrInfo.td

 def : Pat<(brind (add GPRJALR:$rs1, simm12:$imm12)),
           (PseudoBRIND GPRJALR:$rs1, simm12:$imm12)>;
 
 // PseudoCALLReg is a generic pseudo instruction for calls which will eventually
 // expand to auipc and jalr while encoding, with any given register used as the
 // destination.
 // Define AsmString to print "call" when compile with -S flag.
 // Define isCodeGenOnly = 0 to support parsing assembly "call" instruction.
-let isCall = 1, isBarrier = 1, isCodeGenOnly = 0, hasSideEffects = 0,
+let isCall = 1, isBarrier = 1, isCodeGenOnly = 0, Size = 8, hasSideEffects = 0,
     mayStore = 0, mayLoad = 0 in
 def PseudoCALLReg : Pseudo<(outs GPR:$rd), (ins call_symbol:$func), []> {
   let AsmString = "call\t$rd, $func";
 }
 
 // PseudoCALL is a pseudo instruction which will eventually expand to auipc
 // and jalr while encoding. This is desirable, as an auipc+jalr pair with
 // R_RISCV_CALL and R_RISCV_RELAX relocations can be be relaxed by the linker
 // if the offset fits in a signed 21-bit immediate.
 // Define AsmString to print "call" when compile with -S flag.
 // Define isCodeGenOnly = 0 to support parsing assembly "call" instruction.
-let isCall = 1, Defs = [X1], isCodeGenOnly = 0 in
+let isCall = 1, Defs = [X1], isCodeGenOnly = 0, Size = 8 in
 def PseudoCALL : Pseudo<(outs), (ins call_symbol:$func), []> {
   let AsmString = "call\t$func";
 }
 
 def : Pat<(riscv_call tglobaladdr:$func), (PseudoCALL tglobaladdr:$func)>;
 def : Pat<(riscv_call texternalsym:$func), (PseudoCALL texternalsym:$func)>;
 
 def : Pat<(riscv_uret_flag), (URET X0, X0)>;
 def : Pat<(riscv_sret_flag), (SRET X0, X0)>;
 def : Pat<(riscv_mret_flag), (MRET X0, X0)>;
 
 let isCall = 1, Defs = [X1] in
 def PseudoCALLIndirect : Pseudo<(outs), (ins GPRJALR:$rs1),
                                 [(riscv_call GPRJALR:$rs1)]>,
                          PseudoInstExpansion<(JALR X1, GPR:$rs1, 0)>;
 
 let isBarrier = 1, isReturn = 1, isTerminator = 1 in
 def PseudoRET : Pseudo<(outs), (ins), [(riscv_ret_flag)]>,
                 PseudoInstExpansion<(JALR X0, X1, 0)>;
 
 // PseudoTAIL is a pseudo instruction similar to PseudoCALL and will eventually
 // expand to auipc and jalr while encoding.
 // Define AsmString to print "tail" when compile with -S flag.
 let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1, Uses = [X2],
-    isCodeGenOnly = 0 in
+    Size = 8, isCodeGenOnly = 0 in
 def PseudoTAIL : Pseudo<(outs), (ins call_symbol:$dst), []> {
   let AsmString = "tail\t$dst";
 }
 
 let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1, Uses = [X2] in
 def PseudoTAILIndirect : Pseudo<(outs), (ins GPRTC:$rs1),
                                 [(riscv_tail GPRTC:$rs1)]>,
                          PseudoInstExpansion<(JALR X0, GPR:$rs1, 0)>;
 
 def : Pat<(riscv_tail (iPTR tglobaladdr:$dst)),
           (PseudoTAIL texternalsym:$dst)>;
 def : Pat<(riscv_tail (iPTR texternalsym:$dst)),
           (PseudoTAIL texternalsym:$dst)>;
 
-let isCall = 0, isBarrier = 1, isBranch = 1, isTerminator = 1,
+let isCall = 0, isBarrier = 1, isBranch = 1, isTerminator = 1, Size = 8,
     isCodeGenOnly = 0, hasSideEffects = 0, mayStore = 0, mayLoad = 0 in
 def PseudoJump : Pseudo<(outs GPR:$rd), (ins pseudo_jump_symbol:$target), []> {
   let AsmString = "jump\t$target, $rd";
 }
 
-let hasSideEffects = 0, mayLoad = 0, mayStore = 0, isCodeGenOnly = 0,
+let hasSideEffects = 0, mayLoad = 0, mayStore = 0, Size = 8, isCodeGenOnly = 0,
     isAsmParserOnly = 1 in
 def PseudoLLA : Pseudo<(outs GPR:$dst), (ins bare_symbol:$src), [],
                        "lla", "$dst, $src">;
 
-let hasSideEffects = 0, mayLoad = 1, mayStore = 0, isCodeGenOnly = 0,
+let hasSideEffects = 0, mayLoad = 1, mayStore = 0, Size = 8, isCodeGenOnly = 0,
     isAsmParserOnly = 1 in
 def PseudoLA : Pseudo<(outs GPR:$dst), (ins bare_symbol:$src), [],
                       "la", "$dst, $src">;
 
-let hasSideEffects = 0, mayLoad = 1, mayStore = 0, isCodeGenOnly = 0,
+let hasSideEffects = 0, mayLoad = 1, mayStore = 0, Size = 8, isCodeGenOnly = 0,
     isAsmParserOnly = 1 in
 def PseudoLA_TLS_IE : Pseudo<(outs GPR:$dst), (ins bare_symbol:$src), [],
                              "la.tls.ie", "$dst, $src">;
 
-let hasSideEffects = 0, mayLoad = 1, mayStore = 0, isCodeGenOnly = 0,
+let hasSideEffects = 0, mayLoad = 1, mayStore = 0, Size = 8, isCodeGenOnly = 0,
     isAsmParserOnly = 1 in
 def PseudoLA_TLS_GD : Pseudo<(outs GPR:$dst), (ins bare_symbol:$src), [],
                              "la.tls.gd", "$dst, $src">;
 
 
 /// Sign/Zero Extends
 
 // There are single-instruction versions of these in Zbb, so disable these

llvm/lib/Target/RISCV/RISCVInstrInfoA.td

 class PseudoAMO : Pseudo<(outs GPR:$res, GPR:$scratch),
                          (ins GPR:$addr, GPR:$incr, ixlenimm:$ordering), []> {
   let Constraints = "@earlyclobber $res,@earlyclobber $scratch";
   let mayLoad = 1;
   let mayStore = 1;
   let hasSideEffects = 0;
 }
 
+let Size = 20 in
 def PseudoAtomicLoadNand32 : PseudoAMO;
 // Ordering constants must be kept in sync with the AtomicOrdering enum in
 // AtomicOrdering.h.
 def : Pat<(atomic_load_nand_32_monotonic GPR:$addr, GPR:$incr),
           (PseudoAtomicLoadNand32 GPR:$addr, GPR:$incr, 2)>;
 def : Pat<(atomic_load_nand_32_acquire GPR:$addr, GPR:$incr),
           (PseudoAtomicLoadNand32 GPR:$addr, GPR:$incr, 4)>;
 def : Pat<(atomic_load_nand_32_release GPR:$addr, GPR:$incr),
: Pat<(intrin GPR:$addr, GPR:$incr, GPR:$mask, timm:$ordering),
           (AMOInst GPR:$addr, GPR:$incr, GPR:$mask, timm:$ordering)>;
 
 class PseudoMaskedAMOMinMaxPat<Intrinsic intrin, Pseudo AMOInst>
     : Pat<(intrin GPR:$addr, GPR:$incr, GPR:$mask, GPR:$shiftamt,
            timm:$ordering),
           (AMOInst GPR:$addr, GPR:$incr, GPR:$mask, GPR:$shiftamt,
            timm:$ordering)>;
 
+let Size = 28 in
 def PseudoMaskedAtomicSwap32 : PseudoMaskedAMO;
 def : PseudoMaskedAMOPat<int_riscv_masked_atomicrmw_xchg_i32,
                          PseudoMaskedAtomicSwap32>;
+let Size = 28 in
 def PseudoMaskedAtomicLoadAdd32 : PseudoMaskedAMO;
 def : PseudoMaskedAMOPat<int_riscv_masked_atomicrmw_add_i32,
                          PseudoMaskedAtomicLoadAdd32>;
+let Size = 28 in
 def PseudoMaskedAtomicLoadSub32 : PseudoMaskedAMO;
 def : PseudoMaskedAMOPat<int_riscv_masked_atomicrmw_sub_i32,
                          PseudoMaskedAtomicLoadSub32>;
+let Size = 32 in
 def PseudoMaskedAtomicLoadNand32 : PseudoMaskedAMO;
 def : PseudoMaskedAMOPat<int_riscv_masked_atomicrmw_nand_i32,
                          PseudoMaskedAtomicLoadNand32>;
+let Size = 44 in
 def PseudoMaskedAtomicLoadMax32 : PseudoMaskedAMOMinMax;
 def : PseudoMaskedAMOMinMaxPat<int_riscv_masked_atomicrmw_max_i32,
                                PseudoMaskedAtomicLoadMax32>;
+let Size = 44 in
 def PseudoMaskedAtomicLoadMin32 : PseudoMaskedAMOMinMax;
 def : PseudoMaskedAMOMinMaxPat<int_riscv_masked_atomicrmw_min_i32,
                                PseudoMaskedAtomicLoadMin32>;
+let Size = 36 in
 def PseudoMaskedAtomicLoadUMax32 : PseudoMaskedAMOUMinUMax;
 def : PseudoMaskedAMOPat<int_riscv_masked_atomicrmw_umax_i32,
                          PseudoMaskedAtomicLoadUMax32>;
+let Size = 36 in
 def PseudoMaskedAtomicLoadUMin32 : PseudoMaskedAMOUMinUMax;
 def : PseudoMaskedAMOPat<int_riscv_masked_atomicrmw_umin_i32,
                          PseudoMaskedAtomicLoadUMin32>;
 
 /// Compare and exchange
 
 class PseudoCmpXchg
     : Pseudo<(outs GPR:$res, GPR:$scratch),
              (ins GPR:$addr, GPR:$cmpval, GPR:$newval, ixlenimm:$ordering), []> {
   let Constraints = "@earlyclobber $res,@earlyclobber $scratch";
   let mayLoad = 1;
   let mayStore = 1;
   let hasSideEffects = 0;
+  let Size = 16;
 }
 
 // Ordering constants must be kept in sync with the AtomicOrdering enum in
 // AtomicOrdering.h.
 multiclass PseudoCmpXchgPat<string Op, Pseudo CmpXchgInst> {
   def : Pat<(!cast<PatFrag>(Op#"_monotonic") GPR:$addr, GPR:$cmp, GPR:$new),
             (CmpXchgInst GPR:$addr, GPR:$cmp, GPR:$new, 2)>;
   def : Pat<(!cast<PatFrag>(Op#"_acquire") GPR:$addr, GPR:$cmp, GPR:$new),

 def PseudoMaskedCmpXchg32
     : Pseudo<(outs GPR:$res, GPR:$scratch),
              (ins GPR:$addr, GPR:$cmpval, GPR:$newval, GPR:$mask,
               ixlenimm:$ordering), []> {
   let Constraints = "@earlyclobber $res,@earlyclobber $scratch";
   let mayLoad = 1;
   let mayStore = 1;
   let hasSideEffects = 0;
+  let Size = 32;
 }
 
 def : Pat<(int_riscv_masked_cmpxchg_i32
             GPR:$addr, GPR:$cmpval, GPR:$newval, GPR:$mask, timm:$ordering),
           (PseudoMaskedCmpXchg32
             GPR:$addr, GPR:$cmpval, GPR:$newval, GPR:$mask, timm:$ordering)>;
 
 } // Predicates = [HasStdExtA]
def : Pat<(i64 (atomic_load_sub_64_release GPR:$addr, GPR:$incr)),
           (AMOADD_D_RL GPR:$addr, (SUB X0, GPR:$incr))>;
 def : Pat<(i64 (atomic_load_sub_64_acq_rel GPR:$addr, GPR:$incr)),
           (AMOADD_D_AQ_RL GPR:$addr, (SUB X0, GPR:$incr))>;
 def : Pat<(i64 (atomic_load_sub_64_seq_cst GPR:$addr, GPR:$incr)),
           (AMOADD_D_AQ_RL GPR:$addr, (SUB X0, GPR:$incr))>;
 
 /// 64-bit pseudo AMOs
 
+let Size = 20 in
 def PseudoAtomicLoadNand64 : PseudoAMO;
 // Ordering constants must be kept in sync with the AtomicOrdering enum in
 // AtomicOrdering.h.
 def : Pat<(i64 (atomic_load_nand_64_monotonic GPR:$addr, GPR:$incr)),
           (PseudoAtomicLoadNand64 GPR:$addr, GPR:$incr, 2)>;
 def : Pat<(i64 (atomic_load_nand_64_acquire GPR:$addr, GPR:$incr)),
           (PseudoAtomicLoadNand64 GPR:$addr, GPR:$incr, 4)>;
 def : Pat<(i64 (atomic_load_nand_64_release GPR:$addr, GPR:$incr)),

llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td

let hasSideEffects = 0, mayLoad = 1, mayStore = 0, isCodeGenOnly = 1 in {
   def PseudoVRELOAD_M2 : VPseudo<VL2RE8_V, V_M2, (outs VRM2:$rs1), (ins GPR:$rs2)>;
   def PseudoVRELOAD_M4 : VPseudo<VL4RE8_V, V_M4, (outs VRM4:$rs1), (ins GPR:$rs2)>;
   def PseudoVRELOAD_M8 : VPseudo<VL8RE8_V, V_M8, (outs VRM8:$rs1), (ins GPR:$rs2)>;
 }
 
 foreach lmul = MxList in {
   foreach nf = NFSet<lmul>.L in {
     defvar vreg = SegRegClass<lmul, nf>.RC;
-    let hasSideEffects = 0, mayLoad = 0, mayStore = 1, isCodeGenOnly = 1 in {
+    let hasSideEffects = 0, mayLoad = 0, mayStore = 1, isCodeGenOnly = 1,
+        Size = !mul(4, !sub(!mul(nf, 2), 1)) in {
       def "PseudoVSPILL" # nf # "_" # lmul.MX :
         Pseudo<(outs), (ins vreg:$rs1, GPR:$rs2, GPR:$vlenb), []>;
     }
-    let hasSideEffects = 0, mayLoad = 1, mayStore = 0, isCodeGenOnly = 1 in {
+    let hasSideEffects = 0, mayLoad = 1, mayStore = 0, isCodeGenOnly = 1,
+        Size = !mul(4, !sub(!mul(nf, 2), 1)) in {
       def "PseudoVRELOAD" # nf # "_" # lmul.MX :
         Pseudo<(outs vreg:$rs1), (ins GPR:$rs2, GPR:$vlenb), []>;
     }
   }
 }
 
 //===----------------------------------------------------------------------===//
 // 6. Configuration-Setting Instructions