llvm-project/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.td

436 lines
15 KiB
TableGen

//===-- AMDGPUInstrInfo.td - AMDGPU DAG nodes --------------*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains DAG node defintions for the AMDGPU target.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// AMDGPU DAG Profiles
//===----------------------------------------------------------------------===//
def AMDGPUDTIntTernaryOp : SDTypeProfile<1, 3, [
SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>, SDTCisInt<0>, SDTCisInt<3>
]>;
def AMDGPUTrigPreOp : SDTypeProfile<1, 2,
[SDTCisSameAs<0, 1>, SDTCisFP<0>, SDTCisInt<2>]
>;
def AMDGPULdExpOp : SDTypeProfile<1, 2,
[SDTCisSameAs<0, 1>, SDTCisFP<0>, SDTCisInt<2>]
>;
def AMDGPUFPClassOp : SDTypeProfile<1, 2,
[SDTCisInt<0>, SDTCisFP<1>, SDTCisInt<2>]
>;
def AMDGPUFPPackOp : SDTypeProfile<1, 2,
[SDTCisFP<1>, SDTCisSameAs<1, 2>]
>;
def AMDGPUIntPackOp : SDTypeProfile<1, 2,
[SDTCisInt<1>, SDTCisSameAs<1, 2>]
>;
def AMDGPUDivScaleOp : SDTypeProfile<2, 3,
[SDTCisFP<0>, SDTCisInt<1>, SDTCisSameAs<0, 2>, SDTCisSameAs<0, 3>, SDTCisSameAs<0, 4>]
>;
// float, float, float, vcc
def AMDGPUFmasOp : SDTypeProfile<1, 4,
[SDTCisFP<0>, SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>, SDTCisSameAs<0, 3>, SDTCisInt<4>]
>;
def AMDGPUKillSDT : SDTypeProfile<0, 1, [SDTCisInt<0>]>;
def AMDGPUIfOp : SDTypeProfile<1, 2,
[SDTCisVT<0, i64>, SDTCisVT<1, i1>, SDTCisVT<2, OtherVT>]
>;
def AMDGPUElseOp : SDTypeProfile<1, 2,
[SDTCisVT<0, i64>, SDTCisVT<1, i64>, SDTCisVT<2, OtherVT>]
>;
def AMDGPULoopOp : SDTypeProfile<0, 2,
[SDTCisVT<0, i64>, SDTCisVT<1, OtherVT>]
>;
def AMDGPUBreakOp : SDTypeProfile<1, 1,
[SDTCisVT<0, i64>, SDTCisVT<1, i64>]
>;
def AMDGPUIfBreakOp : SDTypeProfile<1, 2,
[SDTCisVT<0, i64>, SDTCisVT<1, i1>, SDTCisVT<2, i64>]
>;
def AMDGPUElseBreakOp : SDTypeProfile<1, 2,
[SDTCisVT<0, i64>, SDTCisVT<1, i64>, SDTCisVT<2, i64>]
>;
def AMDGPUAddeSubeOp : SDTypeProfile<2, 3,
[SDTCisSameAs<0, 2>, SDTCisSameAs<0, 3>, SDTCisVT<0, i32>, SDTCisVT<1, i1>, SDTCisVT<4, i1>]
>;
def SDT_AMDGPUTCRET : SDTypeProfile<0, 2, [SDTCisPtrTy<0>]>;
//===----------------------------------------------------------------------===//
// AMDGPU DAG Nodes
//
def AMDGPUif : SDNode<"AMDGPUISD::IF", AMDGPUIfOp, [SDNPHasChain]>;
def AMDGPUelse : SDNode<"AMDGPUISD::ELSE", AMDGPUElseOp, [SDNPHasChain]>;
def AMDGPUloop : SDNode<"AMDGPUISD::LOOP", AMDGPULoopOp, [SDNPHasChain]>;
def callseq_start : SDNode<"ISD::CALLSEQ_START",
SDCallSeqStart<[ SDTCisVT<0, i32>, SDTCisVT<1, i32> ]>,
[SDNPHasChain, SDNPOutGlue]
>;
def callseq_end : SDNode<"ISD::CALLSEQ_END",
SDCallSeqEnd<[ SDTCisVT<0, i32>, SDTCisVT<1, i32> ]>,
[SDNPHasChain, SDNPOptInGlue, SDNPOutGlue]
>;
def AMDGPUcall : SDNode<"AMDGPUISD::CALL",
SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>,
[SDNPHasChain, SDNPOptInGlue, SDNPOutGlue,
SDNPVariadic]
>;
def AMDGPUtc_return: SDNode<"AMDGPUISD::TC_RETURN", SDT_AMDGPUTCRET,
[SDNPHasChain, SDNPOptInGlue, SDNPVariadic]
>;
def AMDGPUtrap : SDNode<"AMDGPUISD::TRAP",
SDTypeProfile<0, -1, [SDTCisVT<0, i16>]>,
[SDNPHasChain, SDNPVariadic, SDNPSideEffect, SDNPInGlue]
>;
def AMDGPUconstdata_ptr : SDNode<
"AMDGPUISD::CONST_DATA_PTR", SDTypeProfile <1, 1, [SDTCisVT<0, iPTR>,
SDTCisVT<0, iPTR>]>
>;
// This argument to this node is a dword address.
def AMDGPUdwordaddr : SDNode<"AMDGPUISD::DWORDADDR", SDTIntUnaryOp>;
// Force dependencies for vector trunc stores
def R600dummy_chain : SDNode<"AMDGPUISD::DUMMY_CHAIN", SDTNone, [SDNPHasChain]>;
def AMDGPUcos : SDNode<"AMDGPUISD::COS_HW", SDTFPUnaryOp>;
def AMDGPUsin : SDNode<"AMDGPUISD::SIN_HW", SDTFPUnaryOp>;
// out = a - floor(a)
def AMDGPUfract : SDNode<"AMDGPUISD::FRACT", SDTFPUnaryOp>;
// out = 1.0 / a
def AMDGPUrcp : SDNode<"AMDGPUISD::RCP", SDTFPUnaryOp>;
// out = 1.0 / sqrt(a)
def AMDGPUrsq : SDNode<"AMDGPUISD::RSQ", SDTFPUnaryOp>;
// out = 1.0 / sqrt(a)
def AMDGPUrcp_legacy : SDNode<"AMDGPUISD::RCP_LEGACY", SDTFPUnaryOp>;
def AMDGPUrsq_legacy : SDNode<"AMDGPUISD::RSQ_LEGACY", SDTFPUnaryOp>;
def AMDGPUrcp_iflag : SDNode<"AMDGPUISD::RCP_IFLAG", SDTFPUnaryOp>;
// out = 1.0 / sqrt(a) result clamped to +/- max_float.
def AMDGPUrsq_clamp : SDNode<"AMDGPUISD::RSQ_CLAMP", SDTFPUnaryOp>;
def AMDGPUldexp : SDNode<"AMDGPUISD::LDEXP", AMDGPULdExpOp>;
def AMDGPUpkrtz_f16_f32 : SDNode<"AMDGPUISD::CVT_PKRTZ_F16_F32", AMDGPUFPPackOp>;
def AMDGPUpknorm_i16_f32 : SDNode<"AMDGPUISD::CVT_PKNORM_I16_F32", AMDGPUFPPackOp>;
def AMDGPUpknorm_u16_f32 : SDNode<"AMDGPUISD::CVT_PKNORM_U16_F32", AMDGPUFPPackOp>;
def AMDGPUpk_i16_i32 : SDNode<"AMDGPUISD::CVT_PK_I16_I32", AMDGPUIntPackOp>;
def AMDGPUpk_u16_u32 : SDNode<"AMDGPUISD::CVT_PK_U16_U32", AMDGPUIntPackOp>;
def AMDGPUfp_to_f16 : SDNode<"AMDGPUISD::FP_TO_FP16" , SDTFPToIntOp>;
def AMDGPUfp16_zext : SDNode<"AMDGPUISD::FP16_ZEXT" , SDTFPToIntOp>;
def AMDGPUfp_class : SDNode<"AMDGPUISD::FP_CLASS", AMDGPUFPClassOp>;
// out = max(a, b) a and b are floats, where a nan comparison fails.
// This is not commutative because this gives the second operand:
// x < nan ? x : nan -> nan
// nan < x ? nan : x -> x
def AMDGPUfmax_legacy : SDNode<"AMDGPUISD::FMAX_LEGACY", SDTFPBinOp,
[]
>;
def AMDGPUfmul_legacy : SDNode<"AMDGPUISD::FMUL_LEGACY", SDTFPBinOp,
[SDNPCommutative, SDNPAssociative]
>;
// out = min(a, b) a and b are floats, where a nan comparison fails.
def AMDGPUfmin_legacy : SDNode<"AMDGPUISD::FMIN_LEGACY", SDTFPBinOp,
[]
>;
// FIXME: TableGen doesn't like commutative instructions with more
// than 2 operands.
// out = max(a, b, c) a, b and c are floats
def AMDGPUfmax3 : SDNode<"AMDGPUISD::FMAX3", SDTFPTernaryOp,
[/*SDNPCommutative, SDNPAssociative*/]
>;
// out = max(a, b, c) a, b, and c are signed ints
def AMDGPUsmax3 : SDNode<"AMDGPUISD::SMAX3", AMDGPUDTIntTernaryOp,
[/*SDNPCommutative, SDNPAssociative*/]
>;
// out = max(a, b, c) a, b and c are unsigned ints
def AMDGPUumax3 : SDNode<"AMDGPUISD::UMAX3", AMDGPUDTIntTernaryOp,
[/*SDNPCommutative, SDNPAssociative*/]
>;
// out = min(a, b, c) a, b and c are floats
def AMDGPUfmin3 : SDNode<"AMDGPUISD::FMIN3", SDTFPTernaryOp,
[/*SDNPCommutative, SDNPAssociative*/]
>;
// out = min(a, b, c) a, b and c are signed ints
def AMDGPUsmin3 : SDNode<"AMDGPUISD::SMIN3", AMDGPUDTIntTernaryOp,
[/*SDNPCommutative, SDNPAssociative*/]
>;
// out = min(a, b) a and b are unsigned ints
def AMDGPUumin3 : SDNode<"AMDGPUISD::UMIN3", AMDGPUDTIntTernaryOp,
[/*SDNPCommutative, SDNPAssociative*/]
>;
// out = (src0 + src1 > 0xFFFFFFFF) ? 1 : 0
def AMDGPUcarry : SDNode<"AMDGPUISD::CARRY", SDTIntBinOp, []>;
// out = (src1 > src0) ? 1 : 0
def AMDGPUborrow : SDNode<"AMDGPUISD::BORROW", SDTIntBinOp, []>;
// TODO: remove AMDGPUadde/AMDGPUsube when ADDCARRY/SUBCARRY get their own
// nodes in TargetSelectionDAG.td.
def AMDGPUadde : SDNode<"ISD::ADDCARRY", AMDGPUAddeSubeOp, []>;
def AMDGPUsube : SDNode<"ISD::SUBCARRY", AMDGPUAddeSubeOp, []>;
def AMDGPUSetCCOp : SDTypeProfile<1, 3, [ // setcc
SDTCisVT<0, i64>, SDTCisSameAs<1, 2>, SDTCisVT<3, OtherVT>
]>;
def AMDGPUsetcc : SDNode<"AMDGPUISD::SETCC", AMDGPUSetCCOp>;
def AMDGPUSetRegOp : SDTypeProfile<0, 2, [
SDTCisInt<0>, SDTCisInt<1>
]>;
def AMDGPUsetreg : SDNode<"AMDGPUISD::SETREG", AMDGPUSetRegOp, [
SDNPHasChain, SDNPSideEffect, SDNPOptInGlue, SDNPOutGlue]>;
def AMDGPUfma : SDNode<"AMDGPUISD::FMA_W_CHAIN", SDTFPTernaryOp, [
SDNPHasChain, SDNPOptInGlue, SDNPOutGlue]>;
def AMDGPUmul : SDNode<"AMDGPUISD::FMUL_W_CHAIN", SDTFPBinOp, [
SDNPHasChain, SDNPOptInGlue, SDNPOutGlue]>;
def AMDGPUcvt_f32_ubyte0 : SDNode<"AMDGPUISD::CVT_F32_UBYTE0",
SDTIntToFPOp, []>;
def AMDGPUcvt_f32_ubyte1 : SDNode<"AMDGPUISD::CVT_F32_UBYTE1",
SDTIntToFPOp, []>;
def AMDGPUcvt_f32_ubyte2 : SDNode<"AMDGPUISD::CVT_F32_UBYTE2",
SDTIntToFPOp, []>;
def AMDGPUcvt_f32_ubyte3 : SDNode<"AMDGPUISD::CVT_F32_UBYTE3",
SDTIntToFPOp, []>;
// urecip - This operation is a helper for integer division, it returns the
// result of 1 / a as a fractional unsigned integer.
// out = (2^32 / a) + e
// e is rounding error
def AMDGPUurecip : SDNode<"AMDGPUISD::URECIP", SDTIntUnaryOp>;
// Special case divide preop and flags.
def AMDGPUdiv_scale : SDNode<"AMDGPUISD::DIV_SCALE", AMDGPUDivScaleOp>;
// Special case divide FMA with scale and flags (src0 = Quotient,
// src1 = Denominator, src2 = Numerator).
def AMDGPUdiv_fmas : SDNode<"AMDGPUISD::DIV_FMAS", AMDGPUFmasOp>;
// Single or double precision division fixup.
// Special case divide fixup and flags(src0 = Quotient, src1 =
// Denominator, src2 = Numerator).
def AMDGPUdiv_fixup : SDNode<"AMDGPUISD::DIV_FIXUP", SDTFPTernaryOp>;
def AMDGPUfmad_ftz : SDNode<"AMDGPUISD::FMAD_FTZ", SDTFPTernaryOp>;
// Look Up 2.0 / pi src0 with segment select src1[4:0]
def AMDGPUtrig_preop : SDNode<"AMDGPUISD::TRIG_PREOP", AMDGPUTrigPreOp>;
def AMDGPUregister_load : SDNode<"AMDGPUISD::REGISTER_LOAD",
SDTypeProfile<1, 2, [SDTCisPtrTy<1>, SDTCisInt<2>]>,
[SDNPHasChain, SDNPMayLoad]>;
def AMDGPUregister_store : SDNode<"AMDGPUISD::REGISTER_STORE",
SDTypeProfile<0, 3, [SDTCisPtrTy<1>, SDTCisInt<2>]>,
[SDNPHasChain, SDNPMayStore]>;
// MSKOR instructions are atomic memory instructions used mainly for storing
// 8-bit and 16-bit values. The definition is:
//
// MSKOR(dst, mask, src) MEM[dst] = ((MEM[dst] & ~mask) | src)
//
// src0: vec4(src, 0, 0, mask)
// src1: dst - rat offset (aka pointer) in dwords
def AMDGPUstore_mskor : SDNode<"AMDGPUISD::STORE_MSKOR",
SDTypeProfile<0, 2, []>,
[SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def AMDGPUatomic_cmp_swap : SDNode<"AMDGPUISD::ATOMIC_CMP_SWAP",
SDTypeProfile<1, 2, [SDTCisPtrTy<1>, SDTCisVec<2>]>,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad,
SDNPMemOperand]>;
def AMDGPUround : SDNode<"ISD::FROUND",
SDTypeProfile<1, 1, [SDTCisFP<0>, SDTCisSameAs<0,1>]>>;
def AMDGPUbfe_u32 : SDNode<"AMDGPUISD::BFE_U32", AMDGPUDTIntTernaryOp>;
def AMDGPUbfe_i32 : SDNode<"AMDGPUISD::BFE_I32", AMDGPUDTIntTernaryOp>;
def AMDGPUbfi : SDNode<"AMDGPUISD::BFI", AMDGPUDTIntTernaryOp>;
def AMDGPUbfm : SDNode<"AMDGPUISD::BFM", SDTIntBinOp>;
def AMDGPUffbh_u32 : SDNode<"AMDGPUISD::FFBH_U32", SDTIntUnaryOp>;
def AMDGPUffbh_i32 : SDNode<"AMDGPUISD::FFBH_I32", SDTIntUnaryOp>;
def AMDGPUffbl_b32 : SDNode<"AMDGPUISD::FFBL_B32", SDTIntUnaryOp>;
// Signed and unsigned 24-bit multiply. The highest 8-bits are ignore
// when performing the mulitply. The result is a 32-bit value.
def AMDGPUmul_u24 : SDNode<"AMDGPUISD::MUL_U24", SDTIntBinOp,
[SDNPCommutative, SDNPAssociative]
>;
def AMDGPUmul_i24 : SDNode<"AMDGPUISD::MUL_I24", SDTIntBinOp,
[SDNPCommutative, SDNPAssociative]
>;
def AMDGPUmulhi_u24 : SDNode<"AMDGPUISD::MULHI_U24", SDTIntBinOp,
[SDNPCommutative, SDNPAssociative]
>;
def AMDGPUmulhi_i24 : SDNode<"AMDGPUISD::MULHI_I24", SDTIntBinOp,
[SDNPCommutative, SDNPAssociative]
>;
def AMDGPUmad_u24 : SDNode<"AMDGPUISD::MAD_U24", AMDGPUDTIntTernaryOp,
[]
>;
def AMDGPUmad_i24 : SDNode<"AMDGPUISD::MAD_I24", AMDGPUDTIntTernaryOp,
[]
>;
def AMDGPUsmed3 : SDNode<"AMDGPUISD::SMED3", AMDGPUDTIntTernaryOp,
[]
>;
def AMDGPUumed3 : SDNode<"AMDGPUISD::UMED3", AMDGPUDTIntTernaryOp,
[]
>;
def AMDGPUfmed3 : SDNode<"AMDGPUISD::FMED3", SDTFPTernaryOp, []>;
def AMDGPUfdot2 : SDNode<"AMDGPUISD::FDOT2",
SDTypeProfile<1, 4, [SDTCisSameAs<0, 3>, SDTCisSameAs<1, 2>,
SDTCisFP<0>, SDTCisVec<1>,
SDTCisInt<4>]>,
[]>;
def AMDGPUperm : SDNode<"AMDGPUISD::PERM", AMDGPUDTIntTernaryOp, []>;
def AMDGPUinit_exec : SDNode<"AMDGPUISD::INIT_EXEC",
SDTypeProfile<0, 1, [SDTCisInt<0>]>,
[SDNPHasChain, SDNPInGlue]>;
def AMDGPUinit_exec_from_input : SDNode<"AMDGPUISD::INIT_EXEC_FROM_INPUT",
SDTypeProfile<0, 2,
[SDTCisInt<0>, SDTCisInt<1>]>,
[SDNPHasChain, SDNPInGlue]>;
def AMDGPUsendmsg : SDNode<"AMDGPUISD::SENDMSG",
SDTypeProfile<0, 1, [SDTCisInt<0>]>,
[SDNPHasChain, SDNPInGlue]>;
def AMDGPUsendmsghalt : SDNode<"AMDGPUISD::SENDMSGHALT",
SDTypeProfile<0, 1, [SDTCisInt<0>]>,
[SDNPHasChain, SDNPInGlue]>;
def AMDGPUinterp_mov : SDNode<"AMDGPUISD::INTERP_MOV",
SDTypeProfile<1, 3, [SDTCisFP<0>]>,
[SDNPInGlue]>;
def AMDGPUinterp_p1 : SDNode<"AMDGPUISD::INTERP_P1",
SDTypeProfile<1, 3, [SDTCisFP<0>]>,
[SDNPInGlue, SDNPOutGlue]>;
def AMDGPUinterp_p2 : SDNode<"AMDGPUISD::INTERP_P2",
SDTypeProfile<1, 4, [SDTCisFP<0>]>,
[SDNPInGlue]>;
def AMDGPUkill : SDNode<"AMDGPUISD::KILL", AMDGPUKillSDT,
[SDNPHasChain, SDNPSideEffect]>;
// SI+ export
def AMDGPUExportOp : SDTypeProfile<0, 8, [
SDTCisInt<0>, // i8 tgt
SDTCisInt<1>, // i8 en
// i32 or f32 src0
SDTCisSameAs<3, 2>, // f32 src1
SDTCisSameAs<4, 2>, // f32 src2
SDTCisSameAs<5, 2>, // f32 src3
SDTCisInt<6>, // i1 compr
// skip done
SDTCisInt<1> // i1 vm
]>;
def AMDGPUexport: SDNode<"AMDGPUISD::EXPORT", AMDGPUExportOp,
[SDNPHasChain, SDNPMayStore]>;
def AMDGPUexport_done: SDNode<"AMDGPUISD::EXPORT_DONE", AMDGPUExportOp,
[SDNPHasChain, SDNPMayLoad, SDNPMayStore]>;
def R600ExportOp : SDTypeProfile<0, 7, [SDTCisFP<0>, SDTCisInt<1>]>;
def R600_EXPORT: SDNode<"AMDGPUISD::R600_EXPORT", R600ExportOp,
[SDNPHasChain, SDNPSideEffect]>;
//===----------------------------------------------------------------------===//
// Flow Control Profile Types
//===----------------------------------------------------------------------===//
// Branch instruction where second and third are basic blocks
def SDTIL_BRCond : SDTypeProfile<0, 2, [
SDTCisVT<0, OtherVT>
]>;
//===----------------------------------------------------------------------===//
// Flow Control DAG Nodes
//===----------------------------------------------------------------------===//
def IL_brcond : SDNode<"AMDGPUISD::BRANCH_COND", SDTIL_BRCond, [SDNPHasChain]>;
//===----------------------------------------------------------------------===//
// Call/Return DAG Nodes
//===----------------------------------------------------------------------===//
def AMDGPUendpgm : SDNode<"AMDGPUISD::ENDPGM", SDTNone,
[SDNPHasChain, SDNPOptInGlue]>;
def AMDGPUreturn_to_epilog : SDNode<"AMDGPUISD::RETURN_TO_EPILOG", SDTNone,
[SDNPHasChain, SDNPOptInGlue, SDNPVariadic]>;
def AMDGPUret_flag : SDNode<"AMDGPUISD::RET_FLAG", SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>,
[SDNPHasChain, SDNPOptInGlue, SDNPVariadic]
>;