//===-- SystemZOperators.td - SystemZ-specific operators ------*- tblgen-*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// Type profiles
//===----------------------------------------------------------------------===//
def SDT_CallSeqStart : SDCallSeqStart<[SDTCisVT<0, i64>]>;
def SDT_CallSeqEnd : SDCallSeqEnd<[SDTCisVT<0, i64>,
SDTCisVT<1, i64>]>;
def SDT_ZCall : SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>;
def SDT_ZCmp : SDTypeProfile<0, 2, [SDTCisSameAs<0, 1>]>;
def SDT_ZICmp : SDTypeProfile<0, 3,
[SDTCisSameAs<0, 1>,
SDTCisVT<2, i32>]>;
def SDT_ZBRCCMask : SDTypeProfile<0, 3,
[SDTCisVT<0, i32>,
SDTCisVT<1, i32>,
SDTCisVT<2, OtherVT>]>;
def SDT_ZSelectCCMask : SDTypeProfile<1, 4,
[SDTCisSameAs<0, 1>,
SDTCisSameAs<1, 2>,
SDTCisVT<3, i32>,
SDTCisVT<4, i32>]>;
def SDT_ZWrapPtr : SDTypeProfile<1, 1,
[SDTCisSameAs<0, 1>,
SDTCisPtrTy<0>]>;
def SDT_ZWrapOffset : SDTypeProfile<1, 2,
[SDTCisSameAs<0, 1>,
SDTCisSameAs<0, 2>,
SDTCisPtrTy<0>]>;
def SDT_ZAdjDynAlloc : SDTypeProfile<1, 0, [SDTCisVT<0, i64>]>;
def SDT_ZExtractAccess : SDTypeProfile<1, 1,
[SDTCisVT<0, i32>,
SDTCisVT<1, i32>]>;
def SDT_ZGR128Binary32 : SDTypeProfile<1, 2,
[SDTCisVT<0, untyped>,
SDTCisVT<1, untyped>,
SDTCisVT<2, i32>]>;
def SDT_ZGR128Binary64 : SDTypeProfile<1, 2,
[SDTCisVT<0, untyped>,
SDTCisVT<1, untyped>,
SDTCisVT<2, i64>]>;
def SDT_ZAtomicLoadBinaryW : SDTypeProfile<1, 5,
[SDTCisVT<0, i32>,
SDTCisPtrTy<1>,
SDTCisVT<2, i32>,
SDTCisVT<3, i32>,
SDTCisVT<4, i32>,
SDTCisVT<5, i32>]>;
def SDT_ZAtomicCmpSwapW : SDTypeProfile<1, 6,
[SDTCisVT<0, i32>,
SDTCisPtrTy<1>,
SDTCisVT<2, i32>,
SDTCisVT<3, i32>,
SDTCisVT<4, i32>,
SDTCisVT<5, i32>,
SDTCisVT<6, i32>]>;
def SDT_ZMemMemLength : SDTypeProfile<0, 3,
[SDTCisPtrTy<0>,
SDTCisPtrTy<1>,
SDTCisVT<2, i64>]>;
def SDT_ZMemMemLoop : SDTypeProfile<0, 4,
[SDTCisPtrTy<0>,
SDTCisPtrTy<1>,
SDTCisVT<2, i64>,
SDTCisVT<3, i64>]>;
def SDT_ZString : SDTypeProfile<1, 3,
[SDTCisPtrTy<0>,
SDTCisPtrTy<1>,
SDTCisPtrTy<2>,
SDTCisVT<3, i32>]>;
def SDT_ZI32Intrinsic : SDTypeProfile<1, 0, [SDTCisVT<0, i32>]>;
def SDT_ZPrefetch : SDTypeProfile<0, 2,
[SDTCisVT<0, i32>,
SDTCisPtrTy<1>]>;
def SDT_ZTBegin : SDTypeProfile<0, 2,
[SDTCisPtrTy<0>,
SDTCisVT<1, i32>]>;
def SDT_ZInsertVectorElt : SDTypeProfile<1, 3,
[SDTCisVec<0>,
SDTCisSameAs<0, 1>,
SDTCisVT<3, i32>]>;
def SDT_ZExtractVectorElt : SDTypeProfile<1, 2,
[SDTCisVec<1>,
SDTCisVT<2, i32>]>;
def SDT_ZReplicate : SDTypeProfile<1, 1,
[SDTCisVec<0>]>;
def SDT_ZVecUnaryConv : SDTypeProfile<1, 1,
[SDTCisVec<0>,
SDTCisVec<1>]>;
def SDT_ZVecUnary : SDTypeProfile<1, 1,
[SDTCisVec<0>,
SDTCisSameAs<0, 1>]>;
def SDT_ZVecBinary : SDTypeProfile<1, 2,
[SDTCisVec<0>,
SDTCisSameAs<0, 1>,
SDTCisSameAs<0, 2>]>;
def SDT_ZVecBinaryInt : SDTypeProfile<1, 2,
[SDTCisVec<0>,
SDTCisSameAs<0, 1>,
SDTCisVT<2, i32>]>;
def SDT_ZVecBinaryConv : SDTypeProfile<1, 2,
[SDTCisVec<0>,
SDTCisVec<1>,
SDTCisSameAs<1, 2>]>;
def SDT_ZVecBinaryConvInt : SDTypeProfile<1, 2,
[SDTCisVec<0>,
SDTCisVec<1>,
SDTCisVT<2, i32>]>;
def SDT_ZRotateMask : SDTypeProfile<1, 2,
[SDTCisVec<0>,
SDTCisVT<1, i32>,
SDTCisVT<2, i32>]>;
def SDT_ZJoinDwords : SDTypeProfile<1, 2,
[SDTCisVT<0, v2i64>,
SDTCisVT<1, i64>,
SDTCisVT<2, i64>]>;
def SDT_ZVecTernary : SDTypeProfile<1, 3,
[SDTCisVec<0>,
SDTCisSameAs<0, 1>,
SDTCisSameAs<0, 2>,
SDTCisSameAs<0, 3>]>;
def SDT_ZVecTernaryInt : SDTypeProfile<1, 3,
[SDTCisVec<0>,
SDTCisSameAs<0, 1>,
SDTCisSameAs<0, 2>,
SDTCisVT<3, i32>]>;
def SDT_ZVecQuaternaryInt : SDTypeProfile<1, 4,
[SDTCisVec<0>,
SDTCisSameAs<0, 1>,
SDTCisSameAs<0, 2>,
SDTCisSameAs<0, 3>,
SDTCisVT<4, i32>]>;
//===----------------------------------------------------------------------===//
// Node definitions
//===----------------------------------------------------------------------===//
// These are target-independent nodes, but have target-specific formats.
def callseq_start : SDNode<"ISD::CALLSEQ_START", SDT_CallSeqStart,
[SDNPHasChain, SDNPSideEffect, SDNPOutGlue]>;
def callseq_end : SDNode<"ISD::CALLSEQ_END", SDT_CallSeqEnd,
[SDNPHasChain, SDNPSideEffect, SDNPOptInGlue,
SDNPOutGlue]>;
def global_offset_table : SDNode<"ISD::GLOBAL_OFFSET_TABLE", SDTPtrLeaf>;
// Nodes for SystemZISD::*. See SystemZISelLowering.h for more details.
def z_retflag : SDNode<"SystemZISD::RET_FLAG", SDTNone,
[SDNPHasChain, SDNPOptInGlue, SDNPVariadic]>;
def z_call : SDNode<"SystemZISD::CALL", SDT_ZCall,
[SDNPHasChain, SDNPOutGlue, SDNPOptInGlue,
SDNPVariadic]>;
def z_sibcall : SDNode<"SystemZISD::SIBCALL", SDT_ZCall,
[SDNPHasChain, SDNPOutGlue, SDNPOptInGlue,
SDNPVariadic]>;
def z_tls_gdcall : SDNode<"SystemZISD::TLS_GDCALL", SDT_ZCall,
[SDNPHasChain, SDNPInGlue, SDNPOutGlue,
SDNPVariadic]>;
def z_tls_ldcall : SDNode<"SystemZISD::TLS_LDCALL", SDT_ZCall,
[SDNPHasChain, SDNPInGlue, SDNPOutGlue,
SDNPVariadic]>;
def z_pcrel_wrapper : SDNode<"SystemZISD::PCREL_WRAPPER", SDT_ZWrapPtr, []>;
def z_pcrel_offset : SDNode<"SystemZISD::PCREL_OFFSET",
SDT_ZWrapOffset, []>;
def z_iabs : SDNode<"SystemZISD::IABS", SDTIntUnaryOp, []>;
def z_icmp : SDNode<"SystemZISD::ICMP", SDT_ZICmp, [SDNPOutGlue]>;
def z_fcmp : SDNode<"SystemZISD::FCMP", SDT_ZCmp, [SDNPOutGlue]>;
def z_tm : SDNode<"SystemZISD::TM", SDT_ZICmp, [SDNPOutGlue]>;
def z_br_ccmask : SDNode<"SystemZISD::BR_CCMASK", SDT_ZBRCCMask,
[SDNPHasChain, SDNPInGlue]>;
def z_select_ccmask : SDNode<"SystemZISD::SELECT_CCMASK", SDT_ZSelectCCMask,
[SDNPInGlue]>;
def z_adjdynalloc : SDNode<"SystemZISD::ADJDYNALLOC", SDT_ZAdjDynAlloc>;
def z_extract_access : SDNode<"SystemZISD::EXTRACT_ACCESS",
SDT_ZExtractAccess>;
def z_popcnt : SDNode<"SystemZISD::POPCNT", SDTIntUnaryOp>;
def z_umul_lohi64 : SDNode<"SystemZISD::UMUL_LOHI64", SDT_ZGR128Binary64>;
def z_sdivrem32 : SDNode<"SystemZISD::SDIVREM32", SDT_ZGR128Binary32>;
def z_sdivrem64 : SDNode<"SystemZISD::SDIVREM64", SDT_ZGR128Binary64>;
def z_udivrem32 : SDNode<"SystemZISD::UDIVREM32", SDT_ZGR128Binary32>;
def z_udivrem64 : SDNode<"SystemZISD::UDIVREM64", SDT_ZGR128Binary64>;
def z_serialize : SDNode<"SystemZISD::SERIALIZE", SDTNone,
[SDNPHasChain, SDNPMayStore]>;
// Defined because the index is an i32 rather than a pointer.
def z_vector_insert : SDNode<"ISD::INSERT_VECTOR_ELT",
SDT_ZInsertVectorElt>;
def z_vector_extract : SDNode<"ISD::EXTRACT_VECTOR_ELT",
SDT_ZExtractVectorElt>;
def z_byte_mask : SDNode<"SystemZISD::BYTE_MASK", SDT_ZReplicate>;
def z_rotate_mask : SDNode<"SystemZISD::ROTATE_MASK", SDT_ZRotateMask>;
def z_replicate : SDNode<"SystemZISD::REPLICATE", SDT_ZReplicate>;
def z_join_dwords : SDNode<"SystemZISD::JOIN_DWORDS", SDT_ZJoinDwords>;
def z_splat : SDNode<"SystemZISD::SPLAT", SDT_ZVecBinaryInt>;
def z_merge_high : SDNode<"SystemZISD::MERGE_HIGH", SDT_ZVecBinary>;
def z_merge_low : SDNode<"SystemZISD::MERGE_LOW", SDT_ZVecBinary>;
def z_shl_double : SDNode<"SystemZISD::SHL_DOUBLE", SDT_ZVecTernaryInt>;
def z_permute_dwords : SDNode<"SystemZISD::PERMUTE_DWORDS",
SDT_ZVecTernaryInt>;
def z_permute : SDNode<"SystemZISD::PERMUTE", SDT_ZVecTernary>;
def z_pack : SDNode<"SystemZISD::PACK", SDT_ZVecBinaryConv>;
def z_packs_cc : SDNode<"SystemZISD::PACKS_CC", SDT_ZVecBinaryConv,
[SDNPOutGlue]>;
def z_packls_cc : SDNode<"SystemZISD::PACKLS_CC", SDT_ZVecBinaryConv,
[SDNPOutGlue]>;
def z_unpack_high : SDNode<"SystemZISD::UNPACK_HIGH", SDT_ZVecUnaryConv>;
def z_unpackl_high : SDNode<"SystemZISD::UNPACKL_HIGH", SDT_ZVecUnaryConv>;
def z_unpack_low : SDNode<"SystemZISD::UNPACK_LOW", SDT_ZVecUnaryConv>;
def z_unpackl_low : SDNode<"SystemZISD::UNPACKL_LOW", SDT_ZVecUnaryConv>;
def z_vshl_by_scalar : SDNode<"SystemZISD::VSHL_BY_SCALAR",
SDT_ZVecBinaryInt>;
def z_vsrl_by_scalar : SDNode<"SystemZISD::VSRL_BY_SCALAR",
SDT_ZVecBinaryInt>;
def z_vsra_by_scalar : SDNode<"SystemZISD::VSRA_BY_SCALAR",
SDT_ZVecBinaryInt>;
def z_vsum : SDNode<"SystemZISD::VSUM", SDT_ZVecBinaryConv>;
def z_vicmpe : SDNode<"SystemZISD::VICMPE", SDT_ZVecBinary>;
def z_vicmph : SDNode<"SystemZISD::VICMPH", SDT_ZVecBinary>;
def z_vicmphl : SDNode<"SystemZISD::VICMPHL", SDT_ZVecBinary>;
def z_vicmpes : SDNode<"SystemZISD::VICMPES", SDT_ZVecBinary,
[SDNPOutGlue]>;
def z_vicmphs : SDNode<"SystemZISD::VICMPHS", SDT_ZVecBinary,
[SDNPOutGlue]>;
def z_vicmphls : SDNode<"SystemZISD::VICMPHLS", SDT_ZVecBinary,
[SDNPOutGlue]>;
def z_vfcmpe : SDNode<"SystemZISD::VFCMPE", SDT_ZVecBinaryConv>;
def z_vfcmph : SDNode<"SystemZISD::VFCMPH", SDT_ZVecBinaryConv>;
def z_vfcmphe : SDNode<"SystemZISD::VFCMPHE", SDT_ZVecBinaryConv>;
def z_vfcmpes : SDNode<"SystemZISD::VFCMPES", SDT_ZVecBinaryConv,
[SDNPOutGlue]>;
def z_vfcmphs : SDNode<"SystemZISD::VFCMPHS", SDT_ZVecBinaryConv,
[SDNPOutGlue]>;
def z_vfcmphes : SDNode<"SystemZISD::VFCMPHES", SDT_ZVecBinaryConv,
[SDNPOutGlue]>;
def z_vextend : SDNode<"SystemZISD::VEXTEND", SDT_ZVecUnaryConv>;
def z_vround : SDNode<"SystemZISD::VROUND", SDT_ZVecUnaryConv>;
def z_vtm : SDNode<"SystemZISD::VTM", SDT_ZCmp, [SDNPOutGlue]>;
def z_vfae_cc : SDNode<"SystemZISD::VFAE_CC", SDT_ZVecTernaryInt,
[SDNPOutGlue]>;
def z_vfaez_cc : SDNode<"SystemZISD::VFAEZ_CC", SDT_ZVecTernaryInt,
[SDNPOutGlue]>;
def z_vfee_cc : SDNode<"SystemZISD::VFEE_CC", SDT_ZVecBinary,
[SDNPOutGlue]>;
def z_vfeez_cc : SDNode<"SystemZISD::VFEEZ_CC", SDT_ZVecBinary,
[SDNPOutGlue]>;
def z_vfene_cc : SDNode<"SystemZISD::VFENE_CC", SDT_ZVecBinary,
[SDNPOutGlue]>;
def z_vfenez_cc : SDNode<"SystemZISD::VFENEZ_CC", SDT_ZVecBinary,
[SDNPOutGlue]>;
def z_vistr_cc : SDNode<"SystemZISD::VISTR_CC", SDT_ZVecUnary,
[SDNPOutGlue]>;
def z_vstrc_cc : SDNode<"SystemZISD::VSTRC_CC", SDT_ZVecQuaternaryInt,
[SDNPOutGlue]>;
def z_vstrcz_cc : SDNode<"SystemZISD::VSTRCZ_CC",
SDT_ZVecQuaternaryInt, [SDNPOutGlue]>;
def z_vftci : SDNode<"SystemZISD::VFTCI", SDT_ZVecBinaryConvInt,
[SDNPOutGlue]>;
class AtomicWOp<string name, SDTypeProfile profile = SDT_ZAtomicLoadBinaryW>
: SDNode<"SystemZISD::"##name, profile,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad, SDNPMemOperand]>;
def z_atomic_swapw : AtomicWOp<"ATOMIC_SWAPW">;
def z_atomic_loadw_add : AtomicWOp<"ATOMIC_LOADW_ADD">;
def z_atomic_loadw_sub : AtomicWOp<"ATOMIC_LOADW_SUB">;
def z_atomic_loadw_and : AtomicWOp<"ATOMIC_LOADW_AND">;
def z_atomic_loadw_or : AtomicWOp<"ATOMIC_LOADW_OR">;
def z_atomic_loadw_xor : AtomicWOp<"ATOMIC_LOADW_XOR">;
def z_atomic_loadw_nand : AtomicWOp<"ATOMIC_LOADW_NAND">;
def z_atomic_loadw_min : AtomicWOp<"ATOMIC_LOADW_MIN">;
def z_atomic_loadw_max : AtomicWOp<"ATOMIC_LOADW_MAX">;
def z_atomic_loadw_umin : AtomicWOp<"ATOMIC_LOADW_UMIN">;
def z_atomic_loadw_umax : AtomicWOp<"ATOMIC_LOADW_UMAX">;
def z_atomic_cmp_swapw : AtomicWOp<"ATOMIC_CMP_SWAPW", SDT_ZAtomicCmpSwapW>;
def z_mvc : SDNode<"SystemZISD::MVC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_mvc_loop : SDNode<"SystemZISD::MVC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_nc : SDNode<"SystemZISD::NC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_nc_loop : SDNode<"SystemZISD::NC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_oc : SDNode<"SystemZISD::OC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_oc_loop : SDNode<"SystemZISD::OC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_xc : SDNode<"SystemZISD::XC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_xc_loop : SDNode<"SystemZISD::XC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_clc : SDNode<"SystemZISD::CLC", SDT_ZMemMemLength,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_clc_loop : SDNode<"SystemZISD::CLC_LOOP", SDT_ZMemMemLoop,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_strcmp : SDNode<"SystemZISD::STRCMP", SDT_ZString,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_stpcpy : SDNode<"SystemZISD::STPCPY", SDT_ZString,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad]>;
def z_search_string : SDNode<"SystemZISD::SEARCH_STRING", SDT_ZString,
[SDNPHasChain, SDNPOutGlue, SDNPMayLoad]>;
def z_ipm : SDNode<"SystemZISD::IPM", SDT_ZI32Intrinsic,
[SDNPInGlue]>;
def z_prefetch : SDNode<"SystemZISD::PREFETCH", SDT_ZPrefetch,
[SDNPHasChain, SDNPMayLoad, SDNPMayStore,
SDNPMemOperand]>;
def z_tbegin : SDNode<"SystemZISD::TBEGIN", SDT_ZTBegin,
[SDNPHasChain, SDNPOutGlue, SDNPMayStore,
SDNPSideEffect]>;
def z_tbegin_nofloat : SDNode<"SystemZISD::TBEGIN_NOFLOAT", SDT_ZTBegin,
[SDNPHasChain, SDNPOutGlue, SDNPMayStore,
SDNPSideEffect]>;
def z_tend : SDNode<"SystemZISD::TEND", SDTNone,
[SDNPHasChain, SDNPOutGlue, SDNPSideEffect]>;
def z_vshl : SDNode<"ISD::SHL", SDT_ZVecBinary>;
def z_vsra : SDNode<"ISD::SRA", SDT_ZVecBinary>;
def z_vsrl : SDNode<"ISD::SRL", SDT_ZVecBinary>;
//===----------------------------------------------------------------------===//
// Pattern fragments
//===----------------------------------------------------------------------===//
// Signed and unsigned comparisons.
def z_scmp : PatFrag<(ops node:$a, node:$b), (z_icmp node:$a, node:$b, imm), [{
unsigned Type = cast<ConstantSDNode>(N->getOperand(2))->getZExtValue();
return Type != SystemZICMP::UnsignedOnly;
}]>;
def z_ucmp : PatFrag<(ops node:$a, node:$b), (z_icmp node:$a, node:$b, imm), [{
unsigned Type = cast<ConstantSDNode>(N->getOperand(2))->getZExtValue();
return Type != SystemZICMP::SignedOnly;
}]>;
// Register- and memory-based TEST UNDER MASK.
def z_tm_reg : PatFrag<(ops node:$a, node:$b), (z_tm node:$a, node:$b, imm)>;
def z_tm_mem : PatFrag<(ops node:$a, node:$b), (z_tm node:$a, node:$b, 0)>;
// Register sign-extend operations. Sub-32-bit values are represented as i32s.
def sext8 : PatFrag<(ops node:$src), (sext_inreg node:$src, i8)>;
def sext16 : PatFrag<(ops node:$src), (sext_inreg node:$src, i16)>;
def sext32 : PatFrag<(ops node:$src), (sext (i32 node:$src))>;
// Match extensions of an i32 to an i64, followed by an in-register sign
// extension from a sub-i32 value.
def sext8dbl : PatFrag<(ops node:$src), (sext8 (anyext node:$src))>;
def sext16dbl : PatFrag<(ops node:$src), (sext16 (anyext node:$src))>;
// Register zero-extend operations. Sub-32-bit values are represented as i32s.
def zext8 : PatFrag<(ops node:$src), (and node:$src, 0xff)>;
def zext16 : PatFrag<(ops node:$src), (and node:$src, 0xffff)>;
def zext32 : PatFrag<(ops node:$src), (zext (i32 node:$src))>;
// Match extensions of an i32 to an i64, followed by an AND of the low
// i8 or i16 part.
def zext8dbl : PatFrag<(ops node:$src), (zext8 (anyext node:$src))>;
def zext16dbl : PatFrag<(ops node:$src), (zext16 (anyext node:$src))>;
// Typed floating-point loads.
def loadf32 : PatFrag<(ops node:$src), (f32 (load node:$src))>;
def loadf64 : PatFrag<(ops node:$src), (f64 (load node:$src))>;
// Extending loads in which the extension type can be signed.
def asextload : PatFrag<(ops node:$ptr), (unindexedload node:$ptr), [{
unsigned Type = cast<LoadSDNode>(N)->getExtensionType();
return Type == ISD::EXTLOAD || Type == ISD::SEXTLOAD;
}]>;
def asextloadi8 : PatFrag<(ops node:$ptr), (asextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i8;
}]>;
def asextloadi16 : PatFrag<(ops node:$ptr), (asextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i16;
}]>;
def asextloadi32 : PatFrag<(ops node:$ptr), (asextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i32;
}]>;
// Extending loads in which the extension type can be unsigned.
def azextload : PatFrag<(ops node:$ptr), (unindexedload node:$ptr), [{
unsigned Type = cast<LoadSDNode>(N)->getExtensionType();
return Type == ISD::EXTLOAD || Type == ISD::ZEXTLOAD;
}]>;
def azextloadi8 : PatFrag<(ops node:$ptr), (azextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i8;
}]>;
def azextloadi16 : PatFrag<(ops node:$ptr), (azextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i16;
}]>;
def azextloadi32 : PatFrag<(ops node:$ptr), (azextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i32;
}]>;
// Extending loads in which the extension type doesn't matter.
def anyextload : PatFrag<(ops node:$ptr), (unindexedload node:$ptr), [{
return cast<LoadSDNode>(N)->getExtensionType() != ISD::NON_EXTLOAD;
}]>;
def anyextloadi8 : PatFrag<(ops node:$ptr), (anyextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i8;
}]>;
def anyextloadi16 : PatFrag<(ops node:$ptr), (anyextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i16;
}]>;
def anyextloadi32 : PatFrag<(ops node:$ptr), (anyextload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i32;
}]>;
// Aligned loads.
class AlignedLoad<SDPatternOperator load>
: PatFrag<(ops node:$addr), (load node:$addr), [{
auto *Load = cast<LoadSDNode>(N);
return Load->getAlignment() >= Load->getMemoryVT().getStoreSize();
}]>;
def aligned_load : AlignedLoad<load>;
def aligned_asextloadi16 : AlignedLoad<asextloadi16>;
def aligned_asextloadi32 : AlignedLoad<asextloadi32>;
def aligned_azextloadi16 : AlignedLoad<azextloadi16>;
def aligned_azextloadi32 : AlignedLoad<azextloadi32>;
// Aligned stores.
class AlignedStore<SDPatternOperator store>
: PatFrag<(ops node:$src, node:$addr), (store node:$src, node:$addr), [{
auto *Store = cast<StoreSDNode>(N);
return Store->getAlignment() >= Store->getMemoryVT().getStoreSize();
}]>;
def aligned_store : AlignedStore<store>;
def aligned_truncstorei16 : AlignedStore<truncstorei16>;
def aligned_truncstorei32 : AlignedStore<truncstorei32>;
// Non-volatile loads. Used for instructions that might access the storage
// location multiple times.
class NonvolatileLoad<SDPatternOperator load>
: PatFrag<(ops node:$addr), (load node:$addr), [{
auto *Load = cast<LoadSDNode>(N);
return !Load->isVolatile();
}]>;
def nonvolatile_load : NonvolatileLoad<load>;
def nonvolatile_anyextloadi8 : NonvolatileLoad<anyextloadi8>;
def nonvolatile_anyextloadi16 : NonvolatileLoad<anyextloadi16>;
def nonvolatile_anyextloadi32 : NonvolatileLoad<anyextloadi32>;
// Non-volatile stores.
class NonvolatileStore<SDPatternOperator store>
: PatFrag<(ops node:$src, node:$addr), (store node:$src, node:$addr), [{
auto *Store = cast<StoreSDNode>(N);
return !Store->isVolatile();
}]>;
def nonvolatile_store : NonvolatileStore<store>;
def nonvolatile_truncstorei8 : NonvolatileStore<truncstorei8>;
def nonvolatile_truncstorei16 : NonvolatileStore<truncstorei16>;
def nonvolatile_truncstorei32 : NonvolatileStore<truncstorei32>;
// A store of a load that can be implemented using MVC.
def mvc_store : PatFrag<(ops node:$value, node:$addr),
(unindexedstore node:$value, node:$addr),
[{ return storeLoadCanUseMVC(N); }]>;
// Binary read-modify-write operations on memory in which the other
// operand is also memory and for which block operations like NC can
// be used. There are two patterns for each operator, depending on
// which operand contains the "other" load.
multiclass block_op<SDPatternOperator operator> {
def "1" : PatFrag<(ops node:$value, node:$addr),
(unindexedstore (operator node:$value,
(unindexedload node:$addr)),
node:$addr),
[{ return storeLoadCanUseBlockBinary(N, 0); }]>;
def "2" : PatFrag<(ops node:$value, node:$addr),
(unindexedstore (operator (unindexedload node:$addr),
node:$value),
node:$addr),
[{ return storeLoadCanUseBlockBinary(N, 1); }]>;
}
defm block_and : block_op<and>;
defm block_or : block_op<or>;
defm block_xor : block_op<xor>;
// Insertions.
def inserti8 : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, -256), node:$src2)>;
def insertll : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffffffffffff0000), node:$src2)>;
def insertlh : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffffffff0000ffff), node:$src2)>;
def inserthl : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffff0000ffffffff), node:$src2)>;
def inserthh : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0x0000ffffffffffff), node:$src2)>;
def insertlf : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0xffffffff00000000), node:$src2)>;
def inserthf : PatFrag<(ops node:$src1, node:$src2),
(or (and node:$src1, 0x00000000ffffffff), node:$src2)>;
// ORs that can be treated as insertions.
def or_as_inserti8 : PatFrag<(ops node:$src1, node:$src2),
(or node:$src1, node:$src2), [{
unsigned BitWidth = N->getValueType(0).getScalarType().getSizeInBits();
return CurDAG->MaskedValueIsZero(N->getOperand(0),
APInt::getLowBitsSet(BitWidth, 8));
}]>;
// ORs that can be treated as reversed insertions.
def or_as_revinserti8 : PatFrag<(ops node:$src1, node:$src2),
(or node:$src1, node:$src2), [{
unsigned BitWidth = N->getValueType(0).getScalarType().getSizeInBits();
return CurDAG->MaskedValueIsZero(N->getOperand(1),
APInt::getLowBitsSet(BitWidth, 8));
}]>;
// Negative integer absolute.
def z_inegabs : PatFrag<(ops node:$src), (ineg (z_iabs node:$src))>;
// Integer absolute, matching the canonical form generated by DAGCombiner.
def z_iabs32 : PatFrag<(ops node:$src),
(xor (add node:$src, (sra node:$src, (i32 31))),
(sra node:$src, (i32 31)))>;
def z_iabs64 : PatFrag<(ops node:$src),
(xor (add node:$src, (sra node:$src, (i32 63))),
(sra node:$src, (i32 63)))>;
def z_inegabs32 : PatFrag<(ops node:$src), (ineg (z_iabs32 node:$src))>;
def z_inegabs64 : PatFrag<(ops node:$src), (ineg (z_iabs64 node:$src))>;
// Integer multiply-and-add
def z_muladd : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(add (mul node:$src1, node:$src2), node:$src3)>;
// Fused multiply-subtract, using the natural operand order.
def fms : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(fma node:$src1, node:$src2, (fneg node:$src3))>;
// Fused multiply-add and multiply-subtract, but with the order of the
// operands matching SystemZ's MA and MS instructions.
def z_fma : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(fma node:$src2, node:$src3, node:$src1)>;
def z_fms : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(fma node:$src2, node:$src3, (fneg node:$src1))>;
// Floating-point negative absolute.
def fnabs : PatFrag<(ops node:$ptr), (fneg (fabs node:$ptr))>;
// Create a unary operator that loads from memory and then performs
// the given operation on it.
class loadu<SDPatternOperator operator, SDPatternOperator load = load>
: PatFrag<(ops node:$addr), (operator (load node:$addr))>;
// Create a store operator that performs the given unary operation
// on the value before storing it.
class storeu<SDPatternOperator operator, SDPatternOperator store = store>
: PatFrag<(ops node:$value, node:$addr),
(store (operator node:$value), node:$addr)>;
// Vector representation of all-zeros and all-ones.
def z_vzero : PatFrag<(ops), (bitconvert (v16i8 (z_byte_mask (i32 0))))>;
def z_vones : PatFrag<(ops), (bitconvert (v16i8 (z_byte_mask (i32 65535))))>;
// Load a scalar and replicate it in all elements of a vector.
class z_replicate_load<ValueType scalartype, SDPatternOperator load>
: PatFrag<(ops node:$addr),
(z_replicate (scalartype (load node:$addr)))>;
def z_replicate_loadi8 : z_replicate_load<i32, anyextloadi8>;
def z_replicate_loadi16 : z_replicate_load<i32, anyextloadi16>;
def z_replicate_loadi32 : z_replicate_load<i32, load>;
def z_replicate_loadi64 : z_replicate_load<i64, load>;
def z_replicate_loadf32 : z_replicate_load<f32, load>;
def z_replicate_loadf64 : z_replicate_load<f64, load>;
// Load a scalar and insert it into a single element of a vector.
class z_vle<ValueType scalartype, SDPatternOperator load>
: PatFrag<(ops node:$vec, node:$addr, node:$index),
(z_vector_insert node:$vec, (scalartype (load node:$addr)),
node:$index)>;
def z_vlei8 : z_vle<i32, anyextloadi8>;
def z_vlei16 : z_vle<i32, anyextloadi16>;
def z_vlei32 : z_vle<i32, load>;
def z_vlei64 : z_vle<i64, load>;
def z_vlef32 : z_vle<f32, load>;
def z_vlef64 : z_vle<f64, load>;
// Load a scalar and insert it into the low element of the high i64 of a
// zeroed vector.
class z_vllez<ValueType scalartype, SDPatternOperator load, int index>
: PatFrag<(ops node:$addr),
(z_vector_insert (z_vzero),
(scalartype (load node:$addr)), (i32 index))>;
def z_vllezi8 : z_vllez<i32, anyextloadi8, 7>;
def z_vllezi16 : z_vllez<i32, anyextloadi16, 3>;
def z_vllezi32 : z_vllez<i32, load, 1>;
def z_vllezi64 : PatFrag<(ops node:$addr),
(z_join_dwords (i64 (load node:$addr)), (i64 0))>;
// We use high merges to form a v4f32 from four f32s. Propagating zero
// into all elements but index 1 gives this expression.
def z_vllezf32 : PatFrag<(ops node:$addr),
(bitconvert
(z_merge_high
(v2i64
(z_unpackl_high
(v4i32
(bitconvert
(v4f32 (scalar_to_vector
(f32 (load node:$addr)))))))),
(v2i64 (z_vzero))))>;
def z_vllezf64 : PatFrag<(ops node:$addr),
(z_merge_high
(scalar_to_vector (f64 (load node:$addr))),
(z_vzero))>;
// Store one element of a vector.
class z_vste<ValueType scalartype, SDPatternOperator store>
: PatFrag<(ops node:$vec, node:$addr, node:$index),
(store (scalartype (z_vector_extract node:$vec, node:$index)),
node:$addr)>;
def z_vstei8 : z_vste<i32, truncstorei8>;
def z_vstei16 : z_vste<i32, truncstorei16>;
def z_vstei32 : z_vste<i32, store>;
def z_vstei64 : z_vste<i64, store>;
def z_vstef32 : z_vste<f32, store>;
def z_vstef64 : z_vste<f64, store>;
// Arithmetic negation on vectors.
def z_vneg : PatFrag<(ops node:$x), (sub (z_vzero), node:$x)>;
// Bitwise negation on vectors.
def z_vnot : PatFrag<(ops node:$x), (xor node:$x, (z_vones))>;
// Signed "integer greater than zero" on vectors.
def z_vicmph_zero : PatFrag<(ops node:$x), (z_vicmph node:$x, (z_vzero))>;
// Signed "integer less than zero" on vectors.
def z_vicmpl_zero : PatFrag<(ops node:$x), (z_vicmph (z_vzero), node:$x)>;
// Integer absolute on vectors.
class z_viabs<int shift>
: PatFrag<(ops node:$src),
(xor (add node:$src, (z_vsra_by_scalar node:$src, (i32 shift))),
(z_vsra_by_scalar node:$src, (i32 shift)))>;
def z_viabs8 : z_viabs<7>;
def z_viabs16 : z_viabs<15>;
def z_viabs32 : z_viabs<31>;
def z_viabs64 : z_viabs<63>;
// Sign-extend the i64 elements of a vector.
class z_vse<int shift>
: PatFrag<(ops node:$src),
(z_vsra_by_scalar (z_vshl_by_scalar node:$src, shift), shift)>;
def z_vsei8 : z_vse<56>;
def z_vsei16 : z_vse<48>;
def z_vsei32 : z_vse<32>;
// ...and again with the extensions being done on individual i64 scalars.
class z_vse_by_parts<SDPatternOperator operator, int index1, int index2>
: PatFrag<(ops node:$src),
(z_join_dwords
(operator (z_vector_extract node:$src, index1)),
(operator (z_vector_extract node:$src, index2)))>;
def z_vsei8_by_parts : z_vse_by_parts<sext8dbl, 7, 15>;
def z_vsei16_by_parts : z_vse_by_parts<sext16dbl, 3, 7>;
def z_vsei32_by_parts : z_vse_by_parts<sext32, 1, 3>;