llvm-project/llvm/lib/Target/RISCV/RISCVInstrInfoF.td

391 lines
16 KiB
TableGen

//===-- RISCVInstrInfoF.td - RISC-V 'F' instructions -------*- tablegen -*-===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file describes the RISC-V instructions from the standard 'F',
// Single-Precision Floating-Point instruction set extension.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// RISC-V specific DAG Nodes.
//===----------------------------------------------------------------------===//
def SDT_RISCVFMV_W_X_RV64
: SDTypeProfile<1, 1, [SDTCisVT<0, f32>, SDTCisVT<1, i64>]>;
def SDT_RISCVFMV_X_ANYEXTW_RV64
: SDTypeProfile<1, 1, [SDTCisVT<0, i64>, SDTCisVT<1, f32>]>;
def riscv_fmv_w_x_rv64
: SDNode<"RISCVISD::FMV_W_X_RV64", SDT_RISCVFMV_W_X_RV64>;
def riscv_fmv_x_anyextw_rv64
: SDNode<"RISCVISD::FMV_X_ANYEXTW_RV64", SDT_RISCVFMV_X_ANYEXTW_RV64>;
//===----------------------------------------------------------------------===//
// Operand and SDNode transformation definitions.
//===----------------------------------------------------------------------===//
// Floating-point rounding mode
def FRMArg : AsmOperandClass {
let Name = "FRMArg";
let RenderMethod = "addFRMArgOperands";
let DiagnosticType = "InvalidFRMArg";
}
def frmarg : Operand<XLenVT> {
let ParserMatchClass = FRMArg;
let PrintMethod = "printFRMArg";
let DecoderMethod = "decodeFRMArg";
}
//===----------------------------------------------------------------------===//
// Instruction class templates
//===----------------------------------------------------------------------===//
let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
class FPFMAS_rrr_frm<RISCVOpcode opcode, string opcodestr>
: RVInstR4<0b00, opcode, (outs FPR32:$rd),
(ins FPR32:$rs1, FPR32:$rs2, FPR32:$rs3, frmarg:$funct3),
opcodestr, "$rd, $rs1, $rs2, $rs3, $funct3">;
class FPFMASDynFrmAlias<FPFMAS_rrr_frm Inst, string OpcodeStr>
: InstAlias<OpcodeStr#" $rd, $rs1, $rs2, $rs3",
(Inst FPR32:$rd, FPR32:$rs1, FPR32:$rs2, FPR32:$rs3, 0b111)>;
let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
class FPALUS_rr<bits<7> funct7, bits<3> funct3, string opcodestr>
: RVInstR<funct7, funct3, OPC_OP_FP, (outs FPR32:$rd),
(ins FPR32:$rs1, FPR32:$rs2), opcodestr, "$rd, $rs1, $rs2">;
let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
class FPALUS_rr_frm<bits<7> funct7, string opcodestr>
: RVInstRFrm<funct7, OPC_OP_FP, (outs FPR32:$rd),
(ins FPR32:$rs1, FPR32:$rs2, frmarg:$funct3), opcodestr,
"$rd, $rs1, $rs2, $funct3">;
class FPALUSDynFrmAlias<FPALUS_rr_frm Inst, string OpcodeStr>
: InstAlias<OpcodeStr#" $rd, $rs1, $rs2",
(Inst FPR32:$rd, FPR32:$rs1, FPR32:$rs2, 0b111)>;
let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
class FPUnaryOp_r<bits<7> funct7, bits<3> funct3, RegisterClass rdty,
RegisterClass rs1ty, string opcodestr>
: RVInstR<funct7, funct3, OPC_OP_FP, (outs rdty:$rd), (ins rs1ty:$rs1),
opcodestr, "$rd, $rs1">;
let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
class FPUnaryOp_r_frm<bits<7> funct7, RegisterClass rdty, RegisterClass rs1ty,
string opcodestr>
: RVInstRFrm<funct7, OPC_OP_FP, (outs rdty:$rd),
(ins rs1ty:$rs1, frmarg:$funct3), opcodestr,
"$rd, $rs1, $funct3">;
class FPUnaryOpDynFrmAlias<FPUnaryOp_r_frm Inst, string OpcodeStr,
RegisterClass rdty, RegisterClass rs1ty>
: InstAlias<OpcodeStr#" $rd, $rs1",
(Inst rdty:$rd, rs1ty:$rs1, 0b111)>;
let hasSideEffects = 0, mayLoad = 0, mayStore = 0 in
class FPCmpS_rr<bits<3> funct3, string opcodestr>
: RVInstR<0b1010000, funct3, OPC_OP_FP, (outs GPR:$rd),
(ins FPR32:$rs1, FPR32:$rs2), opcodestr, "$rd, $rs1, $rs2">;
//===----------------------------------------------------------------------===//
// Instructions
//===----------------------------------------------------------------------===//
let Predicates = [HasStdExtF] in {
let hasSideEffects = 0, mayLoad = 1, mayStore = 0 in
def FLW : RVInstI<0b010, OPC_LOAD_FP, (outs FPR32:$rd),
(ins GPR:$rs1, simm12:$imm12),
"flw", "$rd, ${imm12}(${rs1})">;
// Operands for stores are in the order srcreg, base, offset rather than
// reflecting the order these fields are specified in the instruction
// encoding.
let hasSideEffects = 0, mayLoad = 0, mayStore = 1 in
def FSW : RVInstS<0b010, OPC_STORE_FP, (outs),
(ins FPR32:$rs2, GPR:$rs1, simm12:$imm12),
"fsw", "$rs2, ${imm12}(${rs1})">;
def FMADD_S : FPFMAS_rrr_frm<OPC_MADD, "fmadd.s">;
def : FPFMASDynFrmAlias<FMADD_S, "fmadd.s">;
def FMSUB_S : FPFMAS_rrr_frm<OPC_MSUB, "fmsub.s">;
def : FPFMASDynFrmAlias<FMSUB_S, "fmsub.s">;
def FNMSUB_S : FPFMAS_rrr_frm<OPC_NMSUB, "fnmsub.s">;
def : FPFMASDynFrmAlias<FNMSUB_S, "fnmsub.s">;
def FNMADD_S : FPFMAS_rrr_frm<OPC_NMADD, "fnmadd.s">;
def : FPFMASDynFrmAlias<FNMADD_S, "fnmadd.s">;
def FADD_S : FPALUS_rr_frm<0b0000000, "fadd.s">;
def : FPALUSDynFrmAlias<FADD_S, "fadd.s">;
def FSUB_S : FPALUS_rr_frm<0b0000100, "fsub.s">;
def : FPALUSDynFrmAlias<FSUB_S, "fsub.s">;
def FMUL_S : FPALUS_rr_frm<0b0001000, "fmul.s">;
def : FPALUSDynFrmAlias<FMUL_S, "fmul.s">;
def FDIV_S : FPALUS_rr_frm<0b0001100, "fdiv.s">;
def : FPALUSDynFrmAlias<FDIV_S, "fdiv.s">;
def FSQRT_S : FPUnaryOp_r_frm<0b0101100, FPR32, FPR32, "fsqrt.s"> {
let rs2 = 0b00000;
}
def : FPUnaryOpDynFrmAlias<FSQRT_S, "fsqrt.s", FPR32, FPR32>;
def FSGNJ_S : FPALUS_rr<0b0010000, 0b000, "fsgnj.s">;
def FSGNJN_S : FPALUS_rr<0b0010000, 0b001, "fsgnjn.s">;
def FSGNJX_S : FPALUS_rr<0b0010000, 0b010, "fsgnjx.s">;
def FMIN_S : FPALUS_rr<0b0010100, 0b000, "fmin.s">;
def FMAX_S : FPALUS_rr<0b0010100, 0b001, "fmax.s">;
def FCVT_W_S : FPUnaryOp_r_frm<0b1100000, GPR, FPR32, "fcvt.w.s"> {
let rs2 = 0b00000;
}
def : FPUnaryOpDynFrmAlias<FCVT_W_S, "fcvt.w.s", GPR, FPR32>;
def FCVT_WU_S : FPUnaryOp_r_frm<0b1100000, GPR, FPR32, "fcvt.wu.s"> {
let rs2 = 0b00001;
}
def : FPUnaryOpDynFrmAlias<FCVT_WU_S, "fcvt.wu.s", GPR, FPR32>;
def FMV_X_W : FPUnaryOp_r<0b1110000, 0b000, GPR, FPR32, "fmv.x.w"> {
let rs2 = 0b00000;
}
def FEQ_S : FPCmpS_rr<0b010, "feq.s">;
def FLT_S : FPCmpS_rr<0b001, "flt.s">;
def FLE_S : FPCmpS_rr<0b000, "fle.s">;
def FCLASS_S : FPUnaryOp_r<0b1110000, 0b001, GPR, FPR32, "fclass.s"> {
let rs2 = 0b00000;
}
def FCVT_S_W : FPUnaryOp_r_frm<0b1101000, FPR32, GPR, "fcvt.s.w"> {
let rs2 = 0b00000;
}
def : FPUnaryOpDynFrmAlias<FCVT_S_W, "fcvt.s.w", FPR32, GPR>;
def FCVT_S_WU : FPUnaryOp_r_frm<0b1101000, FPR32, GPR, "fcvt.s.wu"> {
let rs2 = 0b00001;
}
def : FPUnaryOpDynFrmAlias<FCVT_S_WU, "fcvt.s.wu", FPR32, GPR>;
def FMV_W_X : FPUnaryOp_r<0b1111000, 0b000, FPR32, GPR, "fmv.w.x"> {
let rs2 = 0b00000;
}
} // Predicates = [HasStdExtF]
let Predicates = [HasStdExtF, IsRV64] in {
def FCVT_L_S : FPUnaryOp_r_frm<0b1100000, GPR, FPR32, "fcvt.l.s"> {
let rs2 = 0b00010;
}
def : FPUnaryOpDynFrmAlias<FCVT_L_S, "fcvt.l.s", GPR, FPR32>;
def FCVT_LU_S : FPUnaryOp_r_frm<0b1100000, GPR, FPR32, "fcvt.lu.s"> {
let rs2 = 0b00011;
}
def : FPUnaryOpDynFrmAlias<FCVT_LU_S, "fcvt.lu.s", GPR, FPR32>;
def FCVT_S_L : FPUnaryOp_r_frm<0b1101000, FPR32, GPR, "fcvt.s.l"> {
let rs2 = 0b00010;
}
def : FPUnaryOpDynFrmAlias<FCVT_S_L, "fcvt.s.l", FPR32, GPR>;
def FCVT_S_LU : FPUnaryOp_r_frm<0b1101000, FPR32, GPR, "fcvt.s.lu"> {
let rs2 = 0b00011;
}
def : FPUnaryOpDynFrmAlias<FCVT_S_LU, "fcvt.s.lu", FPR32, GPR>;
} // Predicates = [HasStdExtF, IsRV64]
//===----------------------------------------------------------------------===//
// Assembler Pseudo Instructions (User-Level ISA, Version 2.2, Chapter 20)
//===----------------------------------------------------------------------===//
let Predicates = [HasStdExtF] in {
def : InstAlias<"flw $rd, (${rs1})", (FLW FPR32:$rd, GPR:$rs1, 0), 0>;
def : InstAlias<"fsw $rs2, (${rs1})", (FSW FPR32:$rs2, GPR:$rs1, 0), 0>;
def : InstAlias<"fmv.s $rd, $rs", (FSGNJ_S FPR32:$rd, FPR32:$rs, FPR32:$rs)>;
def : InstAlias<"fabs.s $rd, $rs", (FSGNJX_S FPR32:$rd, FPR32:$rs, FPR32:$rs)>;
def : InstAlias<"fneg.s $rd, $rs", (FSGNJN_S FPR32:$rd, FPR32:$rs, FPR32:$rs)>;
// fgt.s/fge.s are recognised by the GNU assembler but the canonical
// flt.s/fle.s forms will always be printed. Therefore, set a zero weight.
def : InstAlias<"fgt.s $rd, $rs, $rt",
(FLT_S GPR:$rd, FPR32:$rt, FPR32:$rs), 0>;
def : InstAlias<"fge.s $rd, $rs, $rt",
(FLE_S GPR:$rd, FPR32:$rt, FPR32:$rs), 0>;
// The following csr instructions actually alias instructions from the base ISA.
// However, it only makes sense to support them when the F extension is enabled.
// CSR Addresses: 0x003 == fcsr, 0x002 == frm, 0x001 == fflags
// NOTE: "frcsr", "frrm", and "frflags" are more specialized version of "csrr".
def : InstAlias<"frcsr $rd", (CSRRS GPR:$rd, 0x003, X0), 2>;
def : InstAlias<"fscsr $rd, $rs", (CSRRW GPR:$rd, 0x003, GPR:$rs)>;
def : InstAlias<"fscsr $rs", (CSRRW X0, 0x003, GPR:$rs), 2>;
def : InstAlias<"frrm $rd", (CSRRS GPR:$rd, 0x002, X0), 2>;
def : InstAlias<"fsrm $rd, $rs", (CSRRW GPR:$rd, 0x002, GPR:$rs)>;
def : InstAlias<"fsrm $rs", (CSRRW X0, 0x002, GPR:$rs), 2>;
def : InstAlias<"fsrmi $rd, $imm", (CSRRWI GPR:$rd, 0x002, uimm5:$imm)>;
def : InstAlias<"fsrmi $imm", (CSRRWI X0, 0x002, uimm5:$imm), 2>;
def : InstAlias<"frflags $rd", (CSRRS GPR:$rd, 0x001, X0), 2>;
def : InstAlias<"fsflags $rd, $rs", (CSRRW GPR:$rd, 0x001, GPR:$rs)>;
def : InstAlias<"fsflags $rs", (CSRRW X0, 0x001, GPR:$rs), 2>;
def : InstAlias<"fsflagsi $rd, $imm", (CSRRWI GPR:$rd, 0x001, uimm5:$imm)>;
def : InstAlias<"fsflagsi $imm", (CSRRWI X0, 0x001, uimm5:$imm), 2>;
// fmv.w.x and fmv.x.w were previously known as fmv.s.x and fmv.x.s. Both
// spellings should be supported by standard tools.
def : MnemonicAlias<"fmv.s.x", "fmv.w.x">;
def : MnemonicAlias<"fmv.x.s", "fmv.x.w">;
def PseudoFLW : PseudoFloatLoad<"flw", FPR32>;
def PseudoFSW : PseudoStore<"fsw", FPR32>;
} // Predicates = [HasStdExtF]
//===----------------------------------------------------------------------===//
// Pseudo-instructions and codegen patterns
//===----------------------------------------------------------------------===//
/// Generic pattern classes
class PatFpr32Fpr32<SDPatternOperator OpNode, RVInstR Inst>
: Pat<(OpNode FPR32:$rs1, FPR32:$rs2), (Inst $rs1, $rs2)>;
class PatFpr32Fpr32DynFrm<SDPatternOperator OpNode, RVInstRFrm Inst>
: Pat<(OpNode FPR32:$rs1, FPR32:$rs2), (Inst $rs1, $rs2, 0b111)>;
let Predicates = [HasStdExtF] in {
/// Float conversion operations
// Moves (no conversion)
def : Pat<(bitconvert GPR:$rs1), (FMV_W_X GPR:$rs1)>;
def : Pat<(bitconvert FPR32:$rs1), (FMV_X_W FPR32:$rs1)>;
// [u]int32<->float conversion patterns must be gated on IsRV32 or IsRV64, so
// are defined later.
/// Float arithmetic operations
def : PatFpr32Fpr32DynFrm<fadd, FADD_S>;
def : PatFpr32Fpr32DynFrm<fsub, FSUB_S>;
def : PatFpr32Fpr32DynFrm<fmul, FMUL_S>;
def : PatFpr32Fpr32DynFrm<fdiv, FDIV_S>;
def : Pat<(fsqrt FPR32:$rs1), (FSQRT_S FPR32:$rs1, 0b111)>;
def : Pat<(fneg FPR32:$rs1), (FSGNJN_S $rs1, $rs1)>;
def : Pat<(fabs FPR32:$rs1), (FSGNJX_S $rs1, $rs1)>;
def : PatFpr32Fpr32<fcopysign, FSGNJ_S>;
def : Pat<(fcopysign FPR32:$rs1, (fneg FPR32:$rs2)), (FSGNJN_S $rs1, $rs2)>;
// fmadd: rs1 * rs2 + rs3
def : Pat<(fma FPR32:$rs1, FPR32:$rs2, FPR32:$rs3),
(FMADD_S $rs1, $rs2, $rs3, 0b111)>;
// fmsub: rs1 * rs2 - rs3
def : Pat<(fma FPR32:$rs1, FPR32:$rs2, (fneg FPR32:$rs3)),
(FMSUB_S FPR32:$rs1, FPR32:$rs2, FPR32:$rs3, 0b111)>;
// fnmsub: -rs1 * rs2 + rs3
def : Pat<(fma (fneg FPR32:$rs1), FPR32:$rs2, FPR32:$rs3),
(FNMSUB_S FPR32:$rs1, FPR32:$rs2, FPR32:$rs3, 0b111)>;
// fnmadd: -rs1 * rs2 - rs3
def : Pat<(fma (fneg FPR32:$rs1), FPR32:$rs2, (fneg FPR32:$rs3)),
(FNMADD_S FPR32:$rs1, FPR32:$rs2, FPR32:$rs3, 0b111)>;
// The RISC-V 2.2 user-level ISA spec defines fmin and fmax as returning the
// canonical NaN when given a signaling NaN. This doesn't match the LLVM
// behaviour (see https://bugs.llvm.org/show_bug.cgi?id=27363). However, the
// draft 2.3 ISA spec changes the definition of fmin and fmax in a way that
// matches LLVM's fminnum and fmaxnum
// <https://github.com/riscv/riscv-isa-manual/commit/cd20cee7efd9bac7c5aa127ec3b451749d2b3cce>.
def : PatFpr32Fpr32<fminnum, FMIN_S>;
def : PatFpr32Fpr32<fmaxnum, FMAX_S>;
/// Setcc
def : PatFpr32Fpr32<seteq, FEQ_S>;
def : PatFpr32Fpr32<setoeq, FEQ_S>;
def : PatFpr32Fpr32<setlt, FLT_S>;
def : PatFpr32Fpr32<setolt, FLT_S>;
def : PatFpr32Fpr32<setle, FLE_S>;
def : PatFpr32Fpr32<setole, FLE_S>;
// Define pattern expansions for setcc operations which aren't directly
// handled by a RISC-V instruction and aren't expanded in the SelectionDAG
// Legalizer.
def : Pat<(seto FPR32:$rs1, FPR32:$rs2),
(AND (FEQ_S FPR32:$rs1, FPR32:$rs1),
(FEQ_S FPR32:$rs2, FPR32:$rs2))>;
def : Pat<(setuo FPR32:$rs1, FPR32:$rs2),
(SLTIU (AND (FEQ_S FPR32:$rs1, FPR32:$rs1),
(FEQ_S FPR32:$rs2, FPR32:$rs2)),
1)>;
def Select_FPR32_Using_CC_GPR : SelectCC_rrirr<FPR32, GPR>;
/// Loads
defm : LdPat<load, FLW>;
/// Stores
defm : StPat<store, FSW, FPR32>;
} // Predicates = [HasStdExtF]
let Predicates = [HasStdExtF, IsRV32] in {
// float->[u]int. Round-to-zero must be used.
def : Pat<(fp_to_sint FPR32:$rs1), (FCVT_W_S $rs1, 0b001)>;
def : Pat<(fp_to_uint FPR32:$rs1), (FCVT_WU_S $rs1, 0b001)>;
// [u]int->float. Match GCC and default to using dynamic rounding mode.
def : Pat<(sint_to_fp GPR:$rs1), (FCVT_S_W $rs1, 0b111)>;
def : Pat<(uint_to_fp GPR:$rs1), (FCVT_S_WU $rs1, 0b111)>;
} // Predicates = [HasStdExtF, IsRV32]
let Predicates = [HasStdExtF, IsRV32] in {
// FP->[u]int. Round-to-zero must be used
def : Pat<(fp_to_sint FPR32:$rs1), (FCVT_W_S $rs1, 0b001)>;
def : Pat<(fp_to_uint FPR32:$rs1), (FCVT_WU_S $rs1, 0b001)>;
// [u]int->fp. Match GCC and default to using dynamic rounding mode.
def : Pat<(sint_to_fp GPR:$rs1), (FCVT_S_W $rs1, 0b111)>;
def : Pat<(uint_to_fp GPR:$rs1), (FCVT_S_WU $rs1, 0b111)>;
} // Predicates = [HasStdExtF, IsRV32]
let Predicates = [HasStdExtF, IsRV64] in {
def : Pat<(riscv_fmv_w_x_rv64 GPR:$src), (FMV_W_X GPR:$src)>;
def : Pat<(riscv_fmv_x_anyextw_rv64 FPR32:$src), (FMV_X_W FPR32:$src)>;
def : Pat<(sexti32 (riscv_fmv_x_anyextw_rv64 FPR32:$src)),
(FMV_X_W FPR32:$src)>;
// FP->[u]int32 is mostly handled by the FP->[u]int64 patterns. This is safe
// because fpto[u|s]i produces poison if the value can't fit into the target.
// We match the single case below because fcvt.wu.s sign-extends its result so
// is cheaper than fcvt.lu.s+sext.w.
def : Pat<(sext_inreg (assertzexti32 (fp_to_uint FPR32:$rs1)), i32),
(FCVT_WU_S $rs1, 0b001)>;
// FP->[u]int64
def : Pat<(fp_to_sint FPR32:$rs1), (FCVT_L_S $rs1, 0b001)>;
def : Pat<(fp_to_uint FPR32:$rs1), (FCVT_LU_S $rs1, 0b001)>;
// [u]int->fp. Match GCC and default to using dynamic rounding mode.
def : Pat<(sint_to_fp (sext_inreg GPR:$rs1, i32)), (FCVT_S_W $rs1, 0b111)>;
def : Pat<(uint_to_fp (zexti32 GPR:$rs1)), (FCVT_S_WU $rs1, 0b111)>;
def : Pat<(sint_to_fp GPR:$rs1), (FCVT_S_L $rs1, 0b111)>;
def : Pat<(uint_to_fp GPR:$rs1), (FCVT_S_LU $rs1, 0b111)>;
} // Predicates = [HasStdExtF, IsRV64]