forked from OSchip/llvm-project
5126 lines
210 KiB
TableGen
5126 lines
210 KiB
TableGen
//===----- AArch64InstrInfo.td - AArch64 Instruction Info ----*- tablegen -*-=//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file describes the AArch64 scalar instructions in TableGen format.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "AArch64InstrFormats.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Target-specific ISD nodes and profiles
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def SDT_A64ret : SDTypeProfile<0, 0, []>;
|
|
def A64ret : SDNode<"AArch64ISD::Ret", SDT_A64ret, [SDNPHasChain,
|
|
SDNPOptInGlue,
|
|
SDNPVariadic]>;
|
|
|
|
// (ins NZCV, Condition, Dest)
|
|
def SDT_A64br_cc : SDTypeProfile<0, 3, [SDTCisVT<0, i32>]>;
|
|
def A64br_cc : SDNode<"AArch64ISD::BR_CC", SDT_A64br_cc, [SDNPHasChain]>;
|
|
|
|
// (outs Result), (ins NZCV, IfTrue, IfFalse, Condition)
|
|
def SDT_A64select_cc : SDTypeProfile<1, 4, [SDTCisVT<1, i32>,
|
|
SDTCisSameAs<0, 2>,
|
|
SDTCisSameAs<2, 3>]>;
|
|
def A64select_cc : SDNode<"AArch64ISD::SELECT_CC", SDT_A64select_cc>;
|
|
|
|
// (outs NZCV), (ins LHS, RHS, Condition)
|
|
def SDT_A64setcc : SDTypeProfile<1, 3, [SDTCisVT<0, i32>,
|
|
SDTCisSameAs<1, 2>]>;
|
|
def A64setcc : SDNode<"AArch64ISD::SETCC", SDT_A64setcc>;
|
|
|
|
|
|
// (outs GPR64), (ins)
|
|
def A64threadpointer : SDNode<"AArch64ISD::THREAD_POINTER", SDTPtrLeaf>;
|
|
|
|
// A64 compares don't care about the cond really (they set all flags) so a
|
|
// simple binary operator is useful.
|
|
def A64cmp : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(A64setcc node:$lhs, node:$rhs, cond)>;
|
|
|
|
|
|
// When matching a notional (CMP op1, (sub 0, op2)), we'd like to use a CMN
|
|
// instruction on the grounds that "op1 - (-op2) == op1 + op2". However, the C
|
|
// and V flags can be set differently by this operation. It comes down to
|
|
// whether "SInt(~op2)+1 == SInt(~op2+1)" (and the same for UInt). If they are
|
|
// then everything is fine. If not then the optimization is wrong. Thus general
|
|
// comparisons are only valid if op2 != 0.
|
|
|
|
// So, finally, the only LLVM-native comparisons that don't mention C and V are
|
|
// SETEQ and SETNE. They're the only ones we can safely use CMN for in the
|
|
// absence of information about op2.
|
|
def equality_cond : PatLeaf<(cond), [{
|
|
return N->get() == ISD::SETEQ || N->get() == ISD::SETNE;
|
|
}]>;
|
|
|
|
def A64cmn : PatFrag<(ops node:$lhs, node:$rhs),
|
|
(A64setcc node:$lhs, (sub 0, node:$rhs), equality_cond)>;
|
|
|
|
// There are two layers of indirection here, driven by the following
|
|
// considerations.
|
|
// + TableGen does not know CodeModel or Reloc so that decision should be
|
|
// made for a variable/address at ISelLowering.
|
|
// + The output of ISelLowering should be selectable (hence the Wrapper,
|
|
// rather than a bare target opcode)
|
|
def SDTAArch64WrapperLarge : SDTypeProfile<1, 4, [SDTCisSameAs<0, 1>,
|
|
SDTCisSameAs<0, 2>,
|
|
SDTCisSameAs<0, 3>,
|
|
SDTCisSameAs<0, 4>,
|
|
SDTCisPtrTy<0>]>;
|
|
|
|
def A64WrapperLarge :SDNode<"AArch64ISD::WrapperLarge", SDTAArch64WrapperLarge>;
|
|
|
|
def SDTAArch64WrapperSmall : SDTypeProfile<1, 3, [SDTCisSameAs<0, 1>,
|
|
SDTCisSameAs<1, 2>,
|
|
SDTCisVT<3, i32>,
|
|
SDTCisPtrTy<0>]>;
|
|
|
|
def A64WrapperSmall :SDNode<"AArch64ISD::WrapperSmall", SDTAArch64WrapperSmall>;
|
|
|
|
|
|
def SDTAArch64GOTLoad : SDTypeProfile<1, 1, [SDTCisPtrTy<0>, SDTCisPtrTy<1>]>;
|
|
def A64GOTLoad : SDNode<"AArch64ISD::GOTLoad", SDTAArch64GOTLoad,
|
|
[SDNPHasChain]>;
|
|
|
|
|
|
// (A64BFI LHS, RHS, LSB, Width)
|
|
def SDTA64BFI : SDTypeProfile<1, 4, [SDTCisSameAs<0, 1>,
|
|
SDTCisSameAs<1, 2>,
|
|
SDTCisVT<3, i64>,
|
|
SDTCisVT<4, i64>]>;
|
|
|
|
def A64Bfi : SDNode<"AArch64ISD::BFI", SDTA64BFI>;
|
|
|
|
// (A64EXTR HiReg, LoReg, LSB)
|
|
def SDTA64EXTR : SDTypeProfile<1, 3, [SDTCisSameAs<0, 1>, SDTCisSameAs<1, 2>,
|
|
SDTCisVT<3, i64>]>;
|
|
def A64Extr : SDNode<"AArch64ISD::EXTR", SDTA64EXTR>;
|
|
|
|
// (A64[SU]BFX Field, ImmR, ImmS).
|
|
//
|
|
// Note that ImmR and ImmS are already encoded for the actual instructions. The
|
|
// more natural LSB and Width mix together to form ImmR and ImmS, something
|
|
// which TableGen can't handle.
|
|
def SDTA64BFX : SDTypeProfile<1, 3, [SDTCisVT<2, i64>, SDTCisVT<3, i64>]>;
|
|
def A64Sbfx : SDNode<"AArch64ISD::SBFX", SDTA64BFX>;
|
|
|
|
def A64Ubfx : SDNode<"AArch64ISD::UBFX", SDTA64BFX>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Call sequence pseudo-instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
def SDT_AArch64Call : SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>;
|
|
def AArch64Call : SDNode<"AArch64ISD::Call", SDT_AArch64Call,
|
|
[SDNPHasChain, SDNPOptInGlue, SDNPOutGlue, SDNPVariadic]>;
|
|
|
|
def AArch64tcret : SDNode<"AArch64ISD::TC_RETURN", SDT_AArch64Call,
|
|
[SDNPHasChain, SDNPOptInGlue, SDNPVariadic]>;
|
|
|
|
// The TLSDESCCALL node is a variant call which goes to an indirectly calculated
|
|
// destination but needs a relocation against a fixed symbol. As such it has two
|
|
// certain operands: the callee and the relocated variable.
|
|
//
|
|
// The TLS ABI only allows it to be selected to a BLR instructin (with
|
|
// appropriate relocation).
|
|
def SDTTLSDescCall : SDTypeProfile<0, -2, [SDTCisPtrTy<0>, SDTCisPtrTy<1>]>;
|
|
|
|
def A64tlsdesc_blr : SDNode<"AArch64ISD::TLSDESCCALL", SDTTLSDescCall,
|
|
[SDNPInGlue, SDNPOutGlue, SDNPHasChain,
|
|
SDNPVariadic]>;
|
|
|
|
|
|
def SDT_AArch64CallSeqStart : SDCallSeqStart<[ SDTCisPtrTy<0> ]>;
|
|
def AArch64callseq_start : SDNode<"ISD::CALLSEQ_START", SDT_AArch64CallSeqStart,
|
|
[SDNPHasChain, SDNPOutGlue]>;
|
|
|
|
def SDT_AArch64CallSeqEnd : SDCallSeqEnd<[ SDTCisPtrTy<0>, SDTCisPtrTy<1> ]>;
|
|
def AArch64callseq_end : SDNode<"ISD::CALLSEQ_END", SDT_AArch64CallSeqEnd,
|
|
[SDNPHasChain, SDNPOptInGlue, SDNPOutGlue]>;
|
|
|
|
|
|
|
|
// These pseudo-instructions have special semantics by virtue of being passed to
|
|
// the InstrInfo constructor. CALLSEQ_START/CALLSEQ_END are produced by
|
|
// LowerCall to (in our case) tell the back-end about stack adjustments for
|
|
// arguments passed on the stack. Here we select those markers to
|
|
// pseudo-instructions which explicitly set the stack, and finally in the
|
|
// RegisterInfo we convert them to a true stack adjustment.
|
|
let Defs = [XSP], Uses = [XSP] in {
|
|
def ADJCALLSTACKDOWN : PseudoInst<(outs), (ins i64imm:$amt),
|
|
[(AArch64callseq_start timm:$amt)]>;
|
|
|
|
def ADJCALLSTACKUP : PseudoInst<(outs), (ins i64imm:$amt1, i64imm:$amt2),
|
|
[(AArch64callseq_end timm:$amt1, timm:$amt2)]>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Atomic operation pseudo-instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// These get selected from C++ code as a pretty much direct translation from the
|
|
// generic DAG nodes. The one exception is the AtomicOrdering is added as an
|
|
// operand so that the eventual lowering can make use of it and choose
|
|
// acquire/release operations when required.
|
|
|
|
let usesCustomInserter = 1, hasCtrlDep = 1, mayLoad = 1, mayStore = 1 in {
|
|
multiclass AtomicSizes {
|
|
def _I8 : PseudoInst<(outs GPR32:$dst),
|
|
(ins GPR64xsp:$ptr, GPR32:$incr, i32imm:$ordering), []>;
|
|
def _I16 : PseudoInst<(outs GPR32:$dst),
|
|
(ins GPR64xsp:$ptr, GPR32:$incr, i32imm:$ordering), []>;
|
|
def _I32 : PseudoInst<(outs GPR32:$dst),
|
|
(ins GPR64xsp:$ptr, GPR32:$incr, i32imm:$ordering), []>;
|
|
def _I64 : PseudoInst<(outs GPR64:$dst),
|
|
(ins GPR64xsp:$ptr, GPR64:$incr, i32imm:$ordering), []>;
|
|
}
|
|
}
|
|
|
|
defm ATOMIC_LOAD_ADD : AtomicSizes;
|
|
defm ATOMIC_LOAD_SUB : AtomicSizes;
|
|
defm ATOMIC_LOAD_AND : AtomicSizes;
|
|
defm ATOMIC_LOAD_OR : AtomicSizes;
|
|
defm ATOMIC_LOAD_XOR : AtomicSizes;
|
|
defm ATOMIC_LOAD_NAND : AtomicSizes;
|
|
defm ATOMIC_SWAP : AtomicSizes;
|
|
let Defs = [NZCV] in {
|
|
// These operations need a CMP to calculate the correct value
|
|
defm ATOMIC_LOAD_MIN : AtomicSizes;
|
|
defm ATOMIC_LOAD_MAX : AtomicSizes;
|
|
defm ATOMIC_LOAD_UMIN : AtomicSizes;
|
|
defm ATOMIC_LOAD_UMAX : AtomicSizes;
|
|
}
|
|
|
|
class AtomicCmpSwap<RegisterClass GPRData>
|
|
: PseudoInst<(outs GPRData:$dst),
|
|
(ins GPR64xsp:$ptr, GPRData:$old, GPRData:$new,
|
|
i32imm:$ordering), []> {
|
|
let usesCustomInserter = 1;
|
|
let hasCtrlDep = 1;
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
let Defs = [NZCV];
|
|
}
|
|
|
|
def ATOMIC_CMP_SWAP_I8 : AtomicCmpSwap<GPR32>;
|
|
def ATOMIC_CMP_SWAP_I16 : AtomicCmpSwap<GPR32>;
|
|
def ATOMIC_CMP_SWAP_I32 : AtomicCmpSwap<GPR32>;
|
|
def ATOMIC_CMP_SWAP_I64 : AtomicCmpSwap<GPR64>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Add-subtract (extended register) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: ADD, ADDS, SUB, SUBS + aliases CMN, CMP
|
|
|
|
// The RHS of these operations is conceptually a sign/zero-extended
|
|
// register, optionally shifted left by 1-4. The extension can be a
|
|
// NOP (e.g. "sxtx" sign-extending a 64-bit register to 64-bits) but
|
|
// must be specified with one exception:
|
|
|
|
// If one of the registers is sp/wsp then LSL is an alias for UXTW in
|
|
// 32-bit instructions and UXTX in 64-bit versions, the shift amount
|
|
// is not optional in that case (but can explicitly be 0), and the
|
|
// entire suffix can be skipped (e.g. "add sp, x3, x2").
|
|
|
|
multiclass extend_operands<string PREFIX, string Diag> {
|
|
def _asmoperand : AsmOperandClass {
|
|
let Name = PREFIX;
|
|
let RenderMethod = "addRegExtendOperands";
|
|
let PredicateMethod = "isRegExtend<A64SE::" # PREFIX # ">";
|
|
let DiagnosticType = "AddSubRegExtend" # Diag;
|
|
}
|
|
|
|
def _operand : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 0 && Imm <= 4; }]> {
|
|
let PrintMethod = "printRegExtendOperand<A64SE::" # PREFIX # ">";
|
|
let DecoderMethod = "DecodeRegExtendOperand";
|
|
let ParserMatchClass = !cast<AsmOperandClass>(PREFIX # "_asmoperand");
|
|
}
|
|
}
|
|
|
|
defm UXTB : extend_operands<"UXTB", "Small">;
|
|
defm UXTH : extend_operands<"UXTH", "Small">;
|
|
defm UXTW : extend_operands<"UXTW", "Small">;
|
|
defm UXTX : extend_operands<"UXTX", "Large">;
|
|
defm SXTB : extend_operands<"SXTB", "Small">;
|
|
defm SXTH : extend_operands<"SXTH", "Small">;
|
|
defm SXTW : extend_operands<"SXTW", "Small">;
|
|
defm SXTX : extend_operands<"SXTX", "Large">;
|
|
|
|
def LSL_extasmoperand : AsmOperandClass {
|
|
let Name = "RegExtendLSL";
|
|
let RenderMethod = "addRegExtendOperands";
|
|
let DiagnosticType = "AddSubRegExtendLarge";
|
|
}
|
|
|
|
def LSL_extoperand : Operand<i64> {
|
|
let ParserMatchClass = LSL_extasmoperand;
|
|
}
|
|
|
|
|
|
// The patterns for various sign-extensions are a little ugly and
|
|
// non-uniform because everything has already been promoted to the
|
|
// legal i64 and i32 types. We'll wrap the various variants up in a
|
|
// class for use later.
|
|
class extend_types {
|
|
dag uxtb; dag uxth; dag uxtw; dag uxtx;
|
|
dag sxtb; dag sxth; dag sxtw; dag sxtx;
|
|
ValueType ty;
|
|
RegisterClass GPR;
|
|
}
|
|
|
|
def extends_to_i64 : extend_types {
|
|
let uxtb = (and (anyext i32:$Rm), 255);
|
|
let uxth = (and (anyext i32:$Rm), 65535);
|
|
let uxtw = (zext i32:$Rm);
|
|
let uxtx = (i64 $Rm);
|
|
|
|
let sxtb = (sext_inreg (anyext i32:$Rm), i8);
|
|
let sxth = (sext_inreg (anyext i32:$Rm), i16);
|
|
let sxtw = (sext i32:$Rm);
|
|
let sxtx = (i64 $Rm);
|
|
|
|
let ty = i64;
|
|
let GPR = GPR64xsp;
|
|
}
|
|
|
|
|
|
def extends_to_i32 : extend_types {
|
|
let uxtb = (and i32:$Rm, 255);
|
|
let uxth = (and i32:$Rm, 65535);
|
|
let uxtw = (i32 i32:$Rm);
|
|
let uxtx = (i32 i32:$Rm);
|
|
|
|
let sxtb = (sext_inreg i32:$Rm, i8);
|
|
let sxth = (sext_inreg i32:$Rm, i16);
|
|
let sxtw = (i32 i32:$Rm);
|
|
let sxtx = (i32 i32:$Rm);
|
|
|
|
let ty = i32;
|
|
let GPR = GPR32wsp;
|
|
}
|
|
|
|
// Now, six of the extensions supported are easy and uniform: if the source size
|
|
// is 32-bits or less, then Rm is always a 32-bit register. We'll instantiate
|
|
// those instructions in one block.
|
|
|
|
// The uxtx/sxtx could potentially be merged in, but three facts dissuaded me:
|
|
// + It would break the naming scheme: either ADDxx_uxtx or ADDww_uxtx would
|
|
// be impossible.
|
|
// + Patterns are very different as well.
|
|
// + Passing different registers would be ugly (more fields in extend_types
|
|
// would probably be the best option).
|
|
multiclass addsub_exts<bit sf, bit op, bit S, string asmop,
|
|
SDPatternOperator opfrag,
|
|
dag outs, extend_types exts> {
|
|
def w_uxtb : A64I_addsubext<sf, op, S, 0b00, 0b000,
|
|
outs, (ins exts.GPR:$Rn, GPR32:$Rm, UXTB_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[(opfrag exts.ty:$Rn, (shl exts.uxtb, UXTB_operand:$Imm3))],
|
|
NoItinerary>;
|
|
def w_uxth : A64I_addsubext<sf, op, S, 0b00, 0b001,
|
|
outs, (ins exts.GPR:$Rn, GPR32:$Rm, UXTH_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[(opfrag exts.ty:$Rn, (shl exts.uxth, UXTH_operand:$Imm3))],
|
|
NoItinerary>;
|
|
def w_uxtw : A64I_addsubext<sf, op, S, 0b00, 0b010,
|
|
outs, (ins exts.GPR:$Rn, GPR32:$Rm, UXTW_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[(opfrag exts.ty:$Rn, (shl exts.uxtw, UXTW_operand:$Imm3))],
|
|
NoItinerary>;
|
|
|
|
def w_sxtb : A64I_addsubext<sf, op, S, 0b00, 0b100,
|
|
outs, (ins exts.GPR:$Rn, GPR32:$Rm, SXTB_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[(opfrag exts.ty:$Rn, (shl exts.sxtb, SXTB_operand:$Imm3))],
|
|
NoItinerary>;
|
|
def w_sxth : A64I_addsubext<sf, op, S, 0b00, 0b101,
|
|
outs, (ins exts.GPR:$Rn, GPR32:$Rm, SXTH_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[(opfrag exts.ty:$Rn, (shl exts.sxth, SXTH_operand:$Imm3))],
|
|
NoItinerary>;
|
|
def w_sxtw : A64I_addsubext<sf, op, S, 0b00, 0b110,
|
|
outs, (ins exts.GPR:$Rn, GPR32:$Rm, SXTW_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[(opfrag exts.ty:$Rn, (shl exts.sxtw, SXTW_operand:$Imm3))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
// These two could be merge in with the above, but their patterns aren't really
|
|
// necessary and the naming-scheme would necessarily break:
|
|
multiclass addsub_xxtx<bit op, bit S, string asmop, SDPatternOperator opfrag,
|
|
dag outs> {
|
|
def x_uxtx : A64I_addsubext<0b1, op, S, 0b00, 0b011,
|
|
outs,
|
|
(ins GPR64xsp:$Rn, GPR64:$Rm, UXTX_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[(opfrag i64:$Rn, (shl i64:$Rm, UXTX_operand:$Imm3))],
|
|
NoItinerary>;
|
|
|
|
def x_sxtx : A64I_addsubext<0b1, op, S, 0b00, 0b111,
|
|
outs,
|
|
(ins GPR64xsp:$Rn, GPR64:$Rm, SXTX_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[/* No Pattern: same as uxtx */],
|
|
NoItinerary>;
|
|
}
|
|
|
|
multiclass addsub_wxtx<bit op, bit S, string asmop, dag outs> {
|
|
def w_uxtx : A64I_addsubext<0b0, op, S, 0b00, 0b011,
|
|
outs,
|
|
(ins GPR32wsp:$Rn, GPR32:$Rm, UXTX_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[/* No pattern: probably same as uxtw */],
|
|
NoItinerary>;
|
|
|
|
def w_sxtx : A64I_addsubext<0b0, op, S, 0b00, 0b111,
|
|
outs,
|
|
(ins GPR32wsp:$Rn, GPR32:$Rm, SXTX_operand:$Imm3),
|
|
!strconcat(asmop, "$Rn, $Rm, $Imm3"),
|
|
[/* No Pattern: probably same as uxtw */],
|
|
NoItinerary>;
|
|
}
|
|
|
|
class SetRD<RegisterClass RC, SDPatternOperator op>
|
|
: PatFrag<(ops node:$lhs, node:$rhs), (set RC:$Rd, (op node:$lhs, node:$rhs))>;
|
|
class SetNZCV<SDPatternOperator op>
|
|
: PatFrag<(ops node:$lhs, node:$rhs), (set NZCV, (op node:$lhs, node:$rhs))>;
|
|
|
|
defm ADDxx :addsub_exts<0b1, 0b0, 0b0, "add\t$Rd, ", SetRD<GPR64xsp, add>,
|
|
(outs GPR64xsp:$Rd), extends_to_i64>,
|
|
addsub_xxtx< 0b0, 0b0, "add\t$Rd, ", SetRD<GPR64xsp, add>,
|
|
(outs GPR64xsp:$Rd)>;
|
|
defm ADDww :addsub_exts<0b0, 0b0, 0b0, "add\t$Rd, ", SetRD<GPR32wsp, add>,
|
|
(outs GPR32wsp:$Rd), extends_to_i32>,
|
|
addsub_wxtx< 0b0, 0b0, "add\t$Rd, ",
|
|
(outs GPR32wsp:$Rd)>;
|
|
defm SUBxx :addsub_exts<0b1, 0b1, 0b0, "sub\t$Rd, ", SetRD<GPR64xsp, sub>,
|
|
(outs GPR64xsp:$Rd), extends_to_i64>,
|
|
addsub_xxtx< 0b1, 0b0, "sub\t$Rd, ", SetRD<GPR64xsp, sub>,
|
|
(outs GPR64xsp:$Rd)>;
|
|
defm SUBww :addsub_exts<0b0, 0b1, 0b0, "sub\t$Rd, ", SetRD<GPR32wsp, sub>,
|
|
(outs GPR32wsp:$Rd), extends_to_i32>,
|
|
addsub_wxtx< 0b1, 0b0, "sub\t$Rd, ",
|
|
(outs GPR32wsp:$Rd)>;
|
|
|
|
let Defs = [NZCV] in {
|
|
defm ADDSxx :addsub_exts<0b1, 0b0, 0b1, "adds\t$Rd, ", SetRD<GPR64, addc>,
|
|
(outs GPR64:$Rd), extends_to_i64>,
|
|
addsub_xxtx< 0b0, 0b1, "adds\t$Rd, ", SetRD<GPR64, addc>,
|
|
(outs GPR64:$Rd)>;
|
|
defm ADDSww :addsub_exts<0b0, 0b0, 0b1, "adds\t$Rd, ", SetRD<GPR32, addc>,
|
|
(outs GPR32:$Rd), extends_to_i32>,
|
|
addsub_wxtx< 0b0, 0b1, "adds\t$Rd, ",
|
|
(outs GPR32:$Rd)>;
|
|
defm SUBSxx :addsub_exts<0b1, 0b1, 0b1, "subs\t$Rd, ", SetRD<GPR64, subc>,
|
|
(outs GPR64:$Rd), extends_to_i64>,
|
|
addsub_xxtx< 0b1, 0b1, "subs\t$Rd, ", SetRD<GPR64, subc>,
|
|
(outs GPR64:$Rd)>;
|
|
defm SUBSww :addsub_exts<0b0, 0b1, 0b1, "subs\t$Rd, ", SetRD<GPR32, subc>,
|
|
(outs GPR32:$Rd), extends_to_i32>,
|
|
addsub_wxtx< 0b1, 0b1, "subs\t$Rd, ",
|
|
(outs GPR32:$Rd)>;
|
|
|
|
|
|
let Rd = 0b11111, isCompare = 1 in {
|
|
defm CMNx : addsub_exts<0b1, 0b0, 0b1, "cmn\t", SetNZCV<A64cmn>,
|
|
(outs), extends_to_i64>,
|
|
addsub_xxtx< 0b0, 0b1, "cmn\t", SetNZCV<A64cmn>, (outs)>;
|
|
defm CMNw : addsub_exts<0b0, 0b0, 0b1, "cmn\t", SetNZCV<A64cmn>,
|
|
(outs), extends_to_i32>,
|
|
addsub_wxtx< 0b0, 0b1, "cmn\t", (outs)>;
|
|
defm CMPx : addsub_exts<0b1, 0b1, 0b1, "cmp\t", SetNZCV<A64cmp>,
|
|
(outs), extends_to_i64>,
|
|
addsub_xxtx< 0b1, 0b1, "cmp\t", SetNZCV<A64cmp>, (outs)>;
|
|
defm CMPw : addsub_exts<0b0, 0b1, 0b1, "cmp\t", SetNZCV<A64cmp>,
|
|
(outs), extends_to_i32>,
|
|
addsub_wxtx< 0b1, 0b1, "cmp\t", (outs)>;
|
|
}
|
|
}
|
|
|
|
// Now patterns for the operation without a shift being needed. No patterns are
|
|
// created for uxtx/sxtx since they're non-uniform and it's expected that
|
|
// add/sub (shifted register) will handle those cases anyway.
|
|
multiclass addsubext_noshift_patterns<string prefix, SDPatternOperator nodeop,
|
|
extend_types exts> {
|
|
def : Pat<(nodeop exts.ty:$Rn, exts.uxtb),
|
|
(!cast<Instruction>(prefix # "w_uxtb") $Rn, $Rm, 0)>;
|
|
def : Pat<(nodeop exts.ty:$Rn, exts.uxth),
|
|
(!cast<Instruction>(prefix # "w_uxth") $Rn, $Rm, 0)>;
|
|
def : Pat<(nodeop exts.ty:$Rn, exts.uxtw),
|
|
(!cast<Instruction>(prefix # "w_uxtw") $Rn, $Rm, 0)>;
|
|
|
|
def : Pat<(nodeop exts.ty:$Rn, exts.sxtb),
|
|
(!cast<Instruction>(prefix # "w_sxtb") $Rn, $Rm, 0)>;
|
|
def : Pat<(nodeop exts.ty:$Rn, exts.sxth),
|
|
(!cast<Instruction>(prefix # "w_sxth") $Rn, $Rm, 0)>;
|
|
def : Pat<(nodeop exts.ty:$Rn, exts.sxtw),
|
|
(!cast<Instruction>(prefix # "w_sxtw") $Rn, $Rm, 0)>;
|
|
}
|
|
|
|
defm : addsubext_noshift_patterns<"ADDxx", add, extends_to_i64>;
|
|
defm : addsubext_noshift_patterns<"ADDww", add, extends_to_i32>;
|
|
defm : addsubext_noshift_patterns<"SUBxx", sub, extends_to_i64>;
|
|
defm : addsubext_noshift_patterns<"SUBww", sub, extends_to_i32>;
|
|
|
|
defm : addsubext_noshift_patterns<"CMNx", A64cmn, extends_to_i64>;
|
|
defm : addsubext_noshift_patterns<"CMNw", A64cmn, extends_to_i32>;
|
|
defm : addsubext_noshift_patterns<"CMPx", A64cmp, extends_to_i64>;
|
|
defm : addsubext_noshift_patterns<"CMPw", A64cmp, extends_to_i32>;
|
|
|
|
// An extend of "lsl #imm" is valid if and only if one of Rn and Rd is
|
|
// sp/wsp. It is synonymous with uxtx/uxtw depending on the size of the
|
|
// operation. Also permitted in this case is complete omission of the argument,
|
|
// which implies "lsl #0".
|
|
multiclass lsl_aliases<string asmop, Instruction inst, RegisterClass GPR_Rd,
|
|
RegisterClass GPR_Rn, RegisterClass GPR_Rm> {
|
|
def : InstAlias<!strconcat(asmop, " $Rd, $Rn, $Rm"),
|
|
(inst GPR_Rd:$Rd, GPR_Rn:$Rn, GPR_Rm:$Rm, 0)>;
|
|
|
|
def : InstAlias<!strconcat(asmop, " $Rd, $Rn, $Rm, $LSL"),
|
|
(inst GPR_Rd:$Rd, GPR_Rn:$Rn, GPR_Rm:$Rm, LSL_extoperand:$LSL)>;
|
|
|
|
}
|
|
|
|
defm : lsl_aliases<"add", ADDxxx_uxtx, Rxsp, GPR64xsp, GPR64>;
|
|
defm : lsl_aliases<"add", ADDxxx_uxtx, GPR64xsp, Rxsp, GPR64>;
|
|
defm : lsl_aliases<"add", ADDwww_uxtw, Rwsp, GPR32wsp, GPR32>;
|
|
defm : lsl_aliases<"add", ADDwww_uxtw, GPR32wsp, Rwsp, GPR32>;
|
|
defm : lsl_aliases<"sub", SUBxxx_uxtx, Rxsp, GPR64xsp, GPR64>;
|
|
defm : lsl_aliases<"sub", SUBxxx_uxtx, GPR64xsp, Rxsp, GPR64>;
|
|
defm : lsl_aliases<"sub", SUBwww_uxtw, Rwsp, GPR32wsp, GPR32>;
|
|
defm : lsl_aliases<"sub", SUBwww_uxtw, GPR32wsp, Rwsp, GPR32>;
|
|
|
|
// Rd cannot be sp for flag-setting variants so only half of the aliases are
|
|
// needed.
|
|
defm : lsl_aliases<"adds", ADDSxxx_uxtx, GPR64, Rxsp, GPR64>;
|
|
defm : lsl_aliases<"adds", ADDSwww_uxtw, GPR32, Rwsp, GPR32>;
|
|
defm : lsl_aliases<"subs", SUBSxxx_uxtx, GPR64, Rxsp, GPR64>;
|
|
defm : lsl_aliases<"subs", SUBSwww_uxtw, GPR32, Rwsp, GPR32>;
|
|
|
|
// CMP unfortunately has to be different because the instruction doesn't have a
|
|
// dest register.
|
|
multiclass cmp_lsl_aliases<string asmop, Instruction inst,
|
|
RegisterClass GPR_Rn, RegisterClass GPR_Rm> {
|
|
def : InstAlias<!strconcat(asmop, " $Rn, $Rm"),
|
|
(inst GPR_Rn:$Rn, GPR_Rm:$Rm, 0)>;
|
|
|
|
def : InstAlias<!strconcat(asmop, " $Rn, $Rm, $LSL"),
|
|
(inst GPR_Rn:$Rn, GPR_Rm:$Rm, LSL_extoperand:$LSL)>;
|
|
}
|
|
|
|
defm : cmp_lsl_aliases<"cmp", CMPxx_uxtx, Rxsp, GPR64>;
|
|
defm : cmp_lsl_aliases<"cmp", CMPww_uxtw, Rwsp, GPR32>;
|
|
defm : cmp_lsl_aliases<"cmn", CMNxx_uxtx, Rxsp, GPR64>;
|
|
defm : cmp_lsl_aliases<"cmn", CMNww_uxtw, Rwsp, GPR32>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Add-subtract (immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: ADD, ADDS, SUB, SUBS + aliases CMN, CMP, MOV
|
|
|
|
// These instructions accept a 12-bit unsigned immediate, optionally shifted
|
|
// left by 12 bits. Official assembly format specifies a 12 bit immediate with
|
|
// one of "", "LSL #0", "LSL #12" supplementary operands.
|
|
|
|
// There are surprisingly few ways to make this work with TableGen, so this
|
|
// implementation has separate instructions for the "LSL #0" and "LSL #12"
|
|
// variants.
|
|
|
|
// If the MCInst retained a single combined immediate (which could be 0x123000,
|
|
// for example) then both components (imm & shift) would have to be delegated to
|
|
// a single assembly operand. This would entail a separate operand parser
|
|
// (because the LSL would have to live in the same AArch64Operand as the
|
|
// immediate to be accessible); assembly parsing is rather complex and
|
|
// error-prone C++ code.
|
|
//
|
|
// By splitting the immediate, we can delegate handling this optional operand to
|
|
// an InstAlias. Supporting functions to generate the correct MCInst are still
|
|
// required, but these are essentially trivial and parsing can remain generic.
|
|
//
|
|
// Rejected plans with rationale:
|
|
// ------------------------------
|
|
//
|
|
// In an ideal world you'de have two first class immediate operands (in
|
|
// InOperandList, specifying imm12 and shift). Unfortunately this is not
|
|
// selectable by any means I could discover.
|
|
//
|
|
// An Instruction with two MCOperands hidden behind a single entry in
|
|
// InOperandList (expanded by ComplexPatterns and MIOperandInfo) was functional,
|
|
// but required more C++ code to handle encoding/decoding. Parsing (the intended
|
|
// main beneficiary) ended up equally complex because of the optional nature of
|
|
// "LSL #0".
|
|
//
|
|
// Attempting to circumvent the need for a custom OperandParser above by giving
|
|
// InstAliases without the "lsl #0" failed. add/sub could be accommodated but
|
|
// the cmp/cmn aliases didn't use the MIOperandInfo to determine how operands
|
|
// should be parsed: there was no way to accommodate an "lsl #12".
|
|
|
|
let ParserMethod = "ParseImmWithLSLOperand",
|
|
RenderMethod = "addImmWithLSLOperands" in {
|
|
// Derived PredicateMethod fields are different for each
|
|
def addsubimm_lsl0_asmoperand : AsmOperandClass {
|
|
let Name = "AddSubImmLSL0";
|
|
// If an error is reported against this operand, instruction could also be a
|
|
// register variant.
|
|
let DiagnosticType = "AddSubSecondSource";
|
|
}
|
|
|
|
def addsubimm_lsl12_asmoperand : AsmOperandClass {
|
|
let Name = "AddSubImmLSL12";
|
|
let DiagnosticType = "AddSubSecondSource";
|
|
}
|
|
}
|
|
|
|
def shr_12_XFORM : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(N->getSExtValue() >> 12, MVT::i32);
|
|
}]>;
|
|
|
|
def shr_12_neg_XFORM : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant((-N->getSExtValue()) >> 12, MVT::i32);
|
|
}]>;
|
|
|
|
def neg_XFORM : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(-N->getSExtValue(), MVT::i32);
|
|
}]>;
|
|
|
|
|
|
multiclass addsub_imm_operands<ValueType ty> {
|
|
let PrintMethod = "printAddSubImmLSL0Operand",
|
|
EncoderMethod = "getAddSubImmOpValue",
|
|
ParserMatchClass = addsubimm_lsl0_asmoperand in {
|
|
def _posimm_lsl0 : Operand<ty>,
|
|
ImmLeaf<ty, [{ return Imm >= 0 && (Imm & ~0xfff) == 0; }]>;
|
|
def _negimm_lsl0 : Operand<ty>,
|
|
ImmLeaf<ty, [{ return Imm < 0 && (-Imm & ~0xfff) == 0; }],
|
|
neg_XFORM>;
|
|
}
|
|
|
|
let PrintMethod = "printAddSubImmLSL12Operand",
|
|
EncoderMethod = "getAddSubImmOpValue",
|
|
ParserMatchClass = addsubimm_lsl12_asmoperand in {
|
|
def _posimm_lsl12 : Operand<ty>,
|
|
ImmLeaf<ty, [{ return Imm >= 0 && (Imm & ~0xfff000) == 0; }],
|
|
shr_12_XFORM>;
|
|
|
|
def _negimm_lsl12 : Operand<ty>,
|
|
ImmLeaf<ty, [{ return Imm < 0 && (-Imm & ~0xfff000) == 0; }],
|
|
shr_12_neg_XFORM>;
|
|
}
|
|
}
|
|
|
|
// The add operands don't need any transformation
|
|
defm addsubimm_operand_i32 : addsub_imm_operands<i32>;
|
|
defm addsubimm_operand_i64 : addsub_imm_operands<i64>;
|
|
|
|
multiclass addsubimm_varieties<string prefix, bit sf, bit op, bits<2> shift,
|
|
string asmop, string cmpasmop,
|
|
Operand imm_operand, Operand cmp_imm_operand,
|
|
RegisterClass GPR, RegisterClass GPRsp,
|
|
AArch64Reg ZR, ValueType Ty> {
|
|
// All registers for non-S variants allow SP
|
|
def _s : A64I_addsubimm<sf, op, 0b0, shift,
|
|
(outs GPRsp:$Rd),
|
|
(ins GPRsp:$Rn, imm_operand:$Imm12),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Imm12"),
|
|
[(set Ty:$Rd, (add Ty:$Rn, imm_operand:$Imm12))],
|
|
NoItinerary>;
|
|
|
|
|
|
// S variants can read SP but would write to ZR
|
|
def _S : A64I_addsubimm<sf, op, 0b1, shift,
|
|
(outs GPR:$Rd),
|
|
(ins GPRsp:$Rn, imm_operand:$Imm12),
|
|
!strconcat(asmop, "s\t$Rd, $Rn, $Imm12"),
|
|
[(set Ty:$Rd, (addc Ty:$Rn, imm_operand:$Imm12))],
|
|
NoItinerary> {
|
|
let Defs = [NZCV];
|
|
}
|
|
|
|
// Note that the pattern here for ADDS is subtle. Canonically CMP
|
|
// a, b becomes SUBS a, b. If b < 0 then this is equivalent to
|
|
// ADDS a, (-b). This is not true in general.
|
|
def _cmp : A64I_addsubimm<sf, op, 0b1, shift,
|
|
(outs), (ins GPRsp:$Rn, imm_operand:$Imm12),
|
|
!strconcat(cmpasmop, " $Rn, $Imm12"),
|
|
[(set NZCV,
|
|
(A64cmp Ty:$Rn, cmp_imm_operand:$Imm12))],
|
|
NoItinerary> {
|
|
let Rd = 0b11111;
|
|
let Defs = [NZCV];
|
|
let isCompare = 1;
|
|
}
|
|
}
|
|
|
|
|
|
multiclass addsubimm_shifts<string prefix, bit sf, bit op,
|
|
string asmop, string cmpasmop, string operand, string cmpoperand,
|
|
RegisterClass GPR, RegisterClass GPRsp, AArch64Reg ZR,
|
|
ValueType Ty> {
|
|
defm _lsl0 : addsubimm_varieties<prefix # "_lsl0", sf, op, 0b00,
|
|
asmop, cmpasmop,
|
|
!cast<Operand>(operand # "_lsl0"),
|
|
!cast<Operand>(cmpoperand # "_lsl0"),
|
|
GPR, GPRsp, ZR, Ty>;
|
|
|
|
defm _lsl12 : addsubimm_varieties<prefix # "_lsl12", sf, op, 0b01,
|
|
asmop, cmpasmop,
|
|
!cast<Operand>(operand # "_lsl12"),
|
|
!cast<Operand>(cmpoperand # "_lsl12"),
|
|
GPR, GPRsp, ZR, Ty>;
|
|
}
|
|
|
|
defm ADDwwi : addsubimm_shifts<"ADDwi", 0b0, 0b0, "add", "cmn",
|
|
"addsubimm_operand_i32_posimm",
|
|
"addsubimm_operand_i32_negimm",
|
|
GPR32, GPR32wsp, WZR, i32>;
|
|
defm ADDxxi : addsubimm_shifts<"ADDxi", 0b1, 0b0, "add", "cmn",
|
|
"addsubimm_operand_i64_posimm",
|
|
"addsubimm_operand_i64_negimm",
|
|
GPR64, GPR64xsp, XZR, i64>;
|
|
defm SUBwwi : addsubimm_shifts<"SUBwi", 0b0, 0b1, "sub", "cmp",
|
|
"addsubimm_operand_i32_negimm",
|
|
"addsubimm_operand_i32_posimm",
|
|
GPR32, GPR32wsp, WZR, i32>;
|
|
defm SUBxxi : addsubimm_shifts<"SUBxi", 0b1, 0b1, "sub", "cmp",
|
|
"addsubimm_operand_i64_negimm",
|
|
"addsubimm_operand_i64_posimm",
|
|
GPR64, GPR64xsp, XZR, i64>;
|
|
|
|
multiclass MOVsp<RegisterClass GPRsp, RegisterClass SP, Instruction addop> {
|
|
def _fromsp : InstAlias<"mov $Rd, $Rn",
|
|
(addop GPRsp:$Rd, SP:$Rn, 0),
|
|
0b1>;
|
|
|
|
def _tosp : InstAlias<"mov $Rd, $Rn",
|
|
(addop SP:$Rd, GPRsp:$Rn, 0),
|
|
0b1>;
|
|
}
|
|
|
|
// Recall Rxsp is a RegisterClass containing *just* xsp.
|
|
defm MOVxx : MOVsp<GPR64xsp, Rxsp, ADDxxi_lsl0_s>;
|
|
defm MOVww : MOVsp<GPR32wsp, Rwsp, ADDwwi_lsl0_s>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Add-subtract (shifted register) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: ADD, ADDS, SUB, SUBS + aliases CMN, CMP, NEG, NEGS
|
|
|
|
//===-------------------------------
|
|
// 1. The "shifed register" operands. Shared with logical insts.
|
|
//===-------------------------------
|
|
|
|
multiclass shift_operands<string prefix, string form> {
|
|
def _asmoperand_i32 : AsmOperandClass {
|
|
let Name = "Shift" # form # "i32";
|
|
let RenderMethod = "addShiftOperands";
|
|
let PredicateMethod = "isShift<A64SE::" # form # ", false>";
|
|
let DiagnosticType = "AddSubRegShift32";
|
|
}
|
|
|
|
// Note that the operand type is intentionally i64 because the DAGCombiner
|
|
// puts these into a canonical form.
|
|
def _i32 : Operand<i64>, ImmLeaf<i64, [{ return Imm >= 0 && Imm <= 31; }]> {
|
|
let ParserMatchClass
|
|
= !cast<AsmOperandClass>(prefix # "_asmoperand_i32");
|
|
let PrintMethod = "printShiftOperand<A64SE::" # form # ">";
|
|
let DecoderMethod = "Decode32BitShiftOperand";
|
|
}
|
|
|
|
def _asmoperand_i64 : AsmOperandClass {
|
|
let Name = "Shift" # form # "i64";
|
|
let RenderMethod = "addShiftOperands";
|
|
let PredicateMethod = "isShift<A64SE::" # form # ", true>";
|
|
let DiagnosticType = "AddSubRegShift64";
|
|
}
|
|
|
|
def _i64 : Operand<i64>, ImmLeaf<i64, [{ return Imm >= 0 && Imm <= 63; }]> {
|
|
let ParserMatchClass
|
|
= !cast<AsmOperandClass>(prefix # "_asmoperand_i64");
|
|
let PrintMethod = "printShiftOperand<A64SE::" # form # ">";
|
|
}
|
|
}
|
|
|
|
defm lsl_operand : shift_operands<"lsl_operand", "LSL">;
|
|
defm lsr_operand : shift_operands<"lsr_operand", "LSR">;
|
|
defm asr_operand : shift_operands<"asr_operand", "ASR">;
|
|
|
|
// Not used for add/sub, but defined here for completeness. The "logical
|
|
// (shifted register)" instructions *do* have an ROR variant.
|
|
defm ror_operand : shift_operands<"ror_operand", "ROR">;
|
|
|
|
//===-------------------------------
|
|
// 2. The basic 3.5-operand ADD/SUB/ADDS/SUBS instructions.
|
|
//===-------------------------------
|
|
|
|
// N.b. the commutable parameter is just !N. It will be first against the wall
|
|
// when the revolution comes.
|
|
multiclass addsub_shifts<string prefix, bit sf, bit op, bit s, bit commutable,
|
|
string asmop, SDPatternOperator opfrag, ValueType ty,
|
|
RegisterClass GPR, list<Register> defs> {
|
|
let isCommutable = commutable, Defs = defs in {
|
|
def _lsl : A64I_addsubshift<sf, op, s, 0b00,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Imm6"),
|
|
[(set GPR:$Rd, (opfrag ty:$Rn, (shl ty:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
|
|
def _lsr : A64I_addsubshift<sf, op, s, 0b01,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Imm6"),
|
|
[(set ty:$Rd, (opfrag ty:$Rn, (srl ty:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
|
|
def _asr : A64I_addsubshift<sf, op, s, 0b10,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Imm6"),
|
|
[(set ty:$Rd, (opfrag ty:$Rn, (sra ty:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
}
|
|
|
|
def _noshift
|
|
: InstAlias<!strconcat(asmop, " $Rd, $Rn, $Rm"),
|
|
(!cast<Instruction>(prefix # "_lsl") GPR:$Rd, GPR:$Rn,
|
|
GPR:$Rm, 0)>;
|
|
|
|
def : Pat<(opfrag ty:$Rn, ty:$Rm),
|
|
(!cast<Instruction>(prefix # "_lsl") $Rn, $Rm, 0)>;
|
|
}
|
|
|
|
multiclass addsub_sizes<string prefix, bit op, bit s, bit commutable,
|
|
string asmop, SDPatternOperator opfrag,
|
|
list<Register> defs> {
|
|
defm xxx : addsub_shifts<prefix # "xxx", 0b1, op, s,
|
|
commutable, asmop, opfrag, i64, GPR64, defs>;
|
|
defm www : addsub_shifts<prefix # "www", 0b0, op, s,
|
|
commutable, asmop, opfrag, i32, GPR32, defs>;
|
|
}
|
|
|
|
|
|
defm ADD : addsub_sizes<"ADD", 0b0, 0b0, 0b1, "add", add, []>;
|
|
defm SUB : addsub_sizes<"SUB", 0b1, 0b0, 0b0, "sub", sub, []>;
|
|
|
|
defm ADDS : addsub_sizes<"ADDS", 0b0, 0b1, 0b1, "adds", addc, [NZCV]>;
|
|
defm SUBS : addsub_sizes<"SUBS", 0b1, 0b1, 0b0, "subs", subc, [NZCV]>;
|
|
|
|
//===-------------------------------
|
|
// 1. The NEG/NEGS aliases
|
|
//===-------------------------------
|
|
|
|
multiclass neg_alias<Instruction INST, RegisterClass GPR, Register ZR,
|
|
ValueType ty, Operand shift_operand, SDNode shiftop> {
|
|
def : InstAlias<"neg $Rd, $Rm, $Imm6",
|
|
(INST GPR:$Rd, ZR, GPR:$Rm, shift_operand:$Imm6)>;
|
|
|
|
def : Pat<(sub 0, (shiftop ty:$Rm, shift_operand:$Imm6)),
|
|
(INST ZR, $Rm, shift_operand:$Imm6)>;
|
|
}
|
|
|
|
defm : neg_alias<SUBwww_lsl, GPR32, WZR, i32, lsl_operand_i32, shl>;
|
|
defm : neg_alias<SUBwww_lsr, GPR32, WZR, i32, lsr_operand_i32, srl>;
|
|
defm : neg_alias<SUBwww_asr, GPR32, WZR, i32, asr_operand_i32, sra>;
|
|
def : InstAlias<"neg $Rd, $Rm", (SUBwww_lsl GPR32:$Rd, WZR, GPR32:$Rm, 0)>;
|
|
def : Pat<(sub 0, i32:$Rm), (SUBwww_lsl WZR, $Rm, 0)>;
|
|
|
|
defm : neg_alias<SUBxxx_lsl, GPR64, XZR, i64, lsl_operand_i64, shl>;
|
|
defm : neg_alias<SUBxxx_lsr, GPR64, XZR, i64, lsr_operand_i64, srl>;
|
|
defm : neg_alias<SUBxxx_asr, GPR64, XZR, i64, asr_operand_i64, sra>;
|
|
def : InstAlias<"neg $Rd, $Rm", (SUBxxx_lsl GPR64:$Rd, XZR, GPR64:$Rm, 0)>;
|
|
def : Pat<(sub 0, i64:$Rm), (SUBxxx_lsl XZR, $Rm, 0)>;
|
|
|
|
// NEGS doesn't get any patterns yet: defining multiple outputs means C++ has to
|
|
// be involved.
|
|
class negs_alias<Instruction INST, RegisterClass GPR,
|
|
Register ZR, Operand shift_operand, SDNode shiftop>
|
|
: InstAlias<"negs $Rd, $Rm, $Imm6",
|
|
(INST GPR:$Rd, ZR, GPR:$Rm, shift_operand:$Imm6)>;
|
|
|
|
def : negs_alias<SUBSwww_lsl, GPR32, WZR, lsl_operand_i32, shl>;
|
|
def : negs_alias<SUBSwww_lsr, GPR32, WZR, lsr_operand_i32, srl>;
|
|
def : negs_alias<SUBSwww_asr, GPR32, WZR, asr_operand_i32, sra>;
|
|
def : InstAlias<"negs $Rd, $Rm", (SUBSwww_lsl GPR32:$Rd, WZR, GPR32:$Rm, 0)>;
|
|
|
|
def : negs_alias<SUBSxxx_lsl, GPR64, XZR, lsl_operand_i64, shl>;
|
|
def : negs_alias<SUBSxxx_lsr, GPR64, XZR, lsr_operand_i64, srl>;
|
|
def : negs_alias<SUBSxxx_asr, GPR64, XZR, asr_operand_i64, sra>;
|
|
def : InstAlias<"negs $Rd, $Rm", (SUBSxxx_lsl GPR64:$Rd, XZR, GPR64:$Rm, 0)>;
|
|
|
|
//===-------------------------------
|
|
// 1. The CMP/CMN aliases
|
|
//===-------------------------------
|
|
|
|
multiclass cmp_shifts<string prefix, bit sf, bit op, bit commutable,
|
|
string asmop, SDPatternOperator opfrag, ValueType ty,
|
|
RegisterClass GPR> {
|
|
let isCommutable = commutable, Rd = 0b11111, Defs = [NZCV] in {
|
|
def _lsl : A64I_addsubshift<sf, op, 0b1, 0b00,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rn, $Rm, $Imm6"),
|
|
[(set NZCV, (opfrag ty:$Rn, (shl ty:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
|
|
def _lsr : A64I_addsubshift<sf, op, 0b1, 0b01,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rn, $Rm, $Imm6"),
|
|
[(set NZCV, (opfrag ty:$Rn, (srl ty:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
|
|
def _asr : A64I_addsubshift<sf, op, 0b1, 0b10,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rn, $Rm, $Imm6"),
|
|
[(set NZCV, (opfrag ty:$Rn, (sra ty:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
}
|
|
|
|
def _noshift
|
|
: InstAlias<!strconcat(asmop, " $Rn, $Rm"),
|
|
(!cast<Instruction>(prefix # "_lsl") GPR:$Rn, GPR:$Rm, 0)>;
|
|
|
|
def : Pat<(opfrag ty:$Rn, ty:$Rm),
|
|
(!cast<Instruction>(prefix # "_lsl") $Rn, $Rm, 0)>;
|
|
}
|
|
|
|
defm CMPww : cmp_shifts<"CMPww", 0b0, 0b1, 0b0, "cmp", A64cmp, i32, GPR32>;
|
|
defm CMPxx : cmp_shifts<"CMPxx", 0b1, 0b1, 0b0, "cmp", A64cmp, i64, GPR64>;
|
|
|
|
defm CMNww : cmp_shifts<"CMNww", 0b0, 0b0, 0b1, "cmn", A64cmn, i32, GPR32>;
|
|
defm CMNxx : cmp_shifts<"CMNxx", 0b1, 0b0, 0b1, "cmn", A64cmn, i64, GPR64>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Add-subtract (with carry) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: ADC, ADCS, SBC, SBCS + aliases NGC, NGCS
|
|
|
|
multiclass A64I_addsubcarrySizes<bit op, bit s, string asmop> {
|
|
let Uses = [NZCV] in {
|
|
def www : A64I_addsubcarry<0b0, op, s, 0b000000,
|
|
(outs GPR32:$Rd), (ins GPR32:$Rn, GPR32:$Rm),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm"),
|
|
[], NoItinerary>;
|
|
|
|
def xxx : A64I_addsubcarry<0b1, op, s, 0b000000,
|
|
(outs GPR64:$Rd), (ins GPR64:$Rn, GPR64:$Rm),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm"),
|
|
[], NoItinerary>;
|
|
}
|
|
}
|
|
|
|
let isCommutable = 1 in {
|
|
defm ADC : A64I_addsubcarrySizes<0b0, 0b0, "adc">;
|
|
}
|
|
|
|
defm SBC : A64I_addsubcarrySizes<0b1, 0b0, "sbc">;
|
|
|
|
let Defs = [NZCV] in {
|
|
let isCommutable = 1 in {
|
|
defm ADCS : A64I_addsubcarrySizes<0b0, 0b1, "adcs">;
|
|
}
|
|
|
|
defm SBCS : A64I_addsubcarrySizes<0b1, 0b1, "sbcs">;
|
|
}
|
|
|
|
def : InstAlias<"ngc $Rd, $Rm", (SBCwww GPR32:$Rd, WZR, GPR32:$Rm)>;
|
|
def : InstAlias<"ngc $Rd, $Rm", (SBCxxx GPR64:$Rd, XZR, GPR64:$Rm)>;
|
|
def : InstAlias<"ngcs $Rd, $Rm", (SBCSwww GPR32:$Rd, WZR, GPR32:$Rm)>;
|
|
def : InstAlias<"ngcs $Rd, $Rm", (SBCSxxx GPR64:$Rd, XZR, GPR64:$Rm)>;
|
|
|
|
// Note that adde and sube can form a chain longer than two (e.g. for 256-bit
|
|
// addition). So the flag-setting instructions are appropriate.
|
|
def : Pat<(adde i32:$Rn, i32:$Rm), (ADCSwww $Rn, $Rm)>;
|
|
def : Pat<(adde i64:$Rn, i64:$Rm), (ADCSxxx $Rn, $Rm)>;
|
|
def : Pat<(sube i32:$Rn, i32:$Rm), (SBCSwww $Rn, $Rm)>;
|
|
def : Pat<(sube i64:$Rn, i64:$Rm), (SBCSxxx $Rn, $Rm)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Bitfield
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: SBFM, BFM, UBFM, [SU]XT[BHW], ASR, LSR, LSL, SBFI[ZX], BFI, BFXIL,
|
|
// UBFIZ, UBFX
|
|
|
|
// Because of the rather complicated nearly-overlapping aliases, the decoding of
|
|
// this range of instructions is handled manually. The architectural
|
|
// instructions are BFM, SBFM and UBFM but a disassembler should never produce
|
|
// these.
|
|
//
|
|
// In the end, the best option was to use BFM instructions for decoding under
|
|
// almost all circumstances, but to create aliasing *Instructions* for each of
|
|
// the canonical forms and specify a completely custom decoder which would
|
|
// substitute the correct MCInst as needed.
|
|
//
|
|
// This also simplifies instruction selection, parsing etc because the MCInsts
|
|
// have a shape that's closer to their use in code.
|
|
|
|
//===-------------------------------
|
|
// 1. The architectural BFM instructions
|
|
//===-------------------------------
|
|
|
|
def uimm5_asmoperand : AsmOperandClass {
|
|
let Name = "UImm5";
|
|
let PredicateMethod = "isUImm<5>";
|
|
let RenderMethod = "addImmOperands";
|
|
let DiagnosticType = "UImm5";
|
|
}
|
|
|
|
def uimm6_asmoperand : AsmOperandClass {
|
|
let Name = "UImm6";
|
|
let PredicateMethod = "isUImm<6>";
|
|
let RenderMethod = "addImmOperands";
|
|
let DiagnosticType = "UImm6";
|
|
}
|
|
|
|
def bitfield32_imm : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 0 && Imm < 32; }]> {
|
|
let ParserMatchClass = uimm5_asmoperand;
|
|
|
|
let DecoderMethod = "DecodeBitfield32ImmOperand";
|
|
}
|
|
|
|
|
|
def bitfield64_imm : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 0 && Imm < 64; }]> {
|
|
let ParserMatchClass = uimm6_asmoperand;
|
|
|
|
// Default decoder works in 64-bit case: the 6-bit field can take any value.
|
|
}
|
|
|
|
multiclass A64I_bitfieldSizes<bits<2> opc, string asmop> {
|
|
def wwii : A64I_bitfield<0b0, opc, 0b0, (outs GPR32:$Rd),
|
|
(ins GPR32:$Rn, bitfield32_imm:$ImmR, bitfield32_imm:$ImmS),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR, $ImmS"),
|
|
[], NoItinerary> {
|
|
let DecoderMethod = "DecodeBitfieldInstruction";
|
|
}
|
|
|
|
def xxii : A64I_bitfield<0b1, opc, 0b1, (outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, bitfield64_imm:$ImmR, bitfield64_imm:$ImmS),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR, $ImmS"),
|
|
[], NoItinerary> {
|
|
let DecoderMethod = "DecodeBitfieldInstruction";
|
|
}
|
|
}
|
|
|
|
defm SBFM : A64I_bitfieldSizes<0b00, "sbfm">;
|
|
defm UBFM : A64I_bitfieldSizes<0b10, "ubfm">;
|
|
|
|
// BFM instructions modify the destination register rather than defining it
|
|
// completely.
|
|
def BFMwwii :
|
|
A64I_bitfield<0b0, 0b01, 0b0, (outs GPR32:$Rd),
|
|
(ins GPR32:$src, GPR32:$Rn, bitfield32_imm:$ImmR, bitfield32_imm:$ImmS),
|
|
"bfm\t$Rd, $Rn, $ImmR, $ImmS", [], NoItinerary> {
|
|
let DecoderMethod = "DecodeBitfieldInstruction";
|
|
let Constraints = "$src = $Rd";
|
|
}
|
|
|
|
def BFMxxii :
|
|
A64I_bitfield<0b1, 0b01, 0b1, (outs GPR64:$Rd),
|
|
(ins GPR64:$src, GPR64:$Rn, bitfield64_imm:$ImmR, bitfield64_imm:$ImmS),
|
|
"bfm\t$Rd, $Rn, $ImmR, $ImmS", [], NoItinerary> {
|
|
let DecoderMethod = "DecodeBitfieldInstruction";
|
|
let Constraints = "$src = $Rd";
|
|
}
|
|
|
|
|
|
//===-------------------------------
|
|
// 2. Extend aliases to 64-bit dest
|
|
//===-------------------------------
|
|
|
|
// Unfortunately the extensions that end up as 64-bits cannot be handled by an
|
|
// instruction alias: their syntax is (for example) "SXTB x0, w0", which needs
|
|
// to be mapped to "SBFM x0, x0, #0, 7" (changing the class of Rn). InstAlias is
|
|
// not capable of such a map as far as I'm aware
|
|
|
|
// Note that these instructions are strictly more specific than the
|
|
// BFM ones (in ImmR) so they can handle their own decoding.
|
|
class A64I_bf_ext<bit sf, bits<2> opc, RegisterClass GPRDest, ValueType dty,
|
|
string asmop, bits<6> imms, dag pattern>
|
|
: A64I_bitfield<sf, opc, sf,
|
|
(outs GPRDest:$Rd), (ins GPR32:$Rn),
|
|
!strconcat(asmop, "\t$Rd, $Rn"),
|
|
[(set dty:$Rd, pattern)], NoItinerary> {
|
|
let ImmR = 0b000000;
|
|
let ImmS = imms;
|
|
}
|
|
|
|
// Signed extensions
|
|
def SXTBxw : A64I_bf_ext<0b1, 0b00, GPR64, i64, "sxtb", 7,
|
|
(sext_inreg (anyext i32:$Rn), i8)>;
|
|
def SXTBww : A64I_bf_ext<0b0, 0b00, GPR32, i32, "sxtb", 7,
|
|
(sext_inreg i32:$Rn, i8)>;
|
|
def SXTHxw : A64I_bf_ext<0b1, 0b00, GPR64, i64, "sxth", 15,
|
|
(sext_inreg (anyext i32:$Rn), i16)>;
|
|
def SXTHww : A64I_bf_ext<0b0, 0b00, GPR32, i32, "sxth", 15,
|
|
(sext_inreg i32:$Rn, i16)>;
|
|
def SXTWxw : A64I_bf_ext<0b1, 0b00, GPR64, i64, "sxtw", 31, (sext i32:$Rn)>;
|
|
|
|
// Unsigned extensions
|
|
def UXTBww : A64I_bf_ext<0b0, 0b10, GPR32, i32, "uxtb", 7,
|
|
(and i32:$Rn, 255)>;
|
|
def UXTHww : A64I_bf_ext<0b0, 0b10, GPR32, i32, "uxth", 15,
|
|
(and i32:$Rn, 65535)>;
|
|
|
|
// The 64-bit unsigned variants are not strictly architectural but recommended
|
|
// for consistency.
|
|
let isAsmParserOnly = 1 in {
|
|
def UXTBxw : A64I_bf_ext<0b0, 0b10, GPR64, i64, "uxtb", 7,
|
|
(and (anyext i32:$Rn), 255)>;
|
|
def UXTHxw : A64I_bf_ext<0b0, 0b10, GPR64, i64, "uxth", 15,
|
|
(and (anyext i32:$Rn), 65535)>;
|
|
}
|
|
|
|
// Extra patterns for when the source register is actually 64-bits
|
|
// too. There's no architectural difference here, it's just LLVM
|
|
// shinanigans. There's no need for equivalent zero-extension patterns
|
|
// because they'll already be caught by logical (immediate) matching.
|
|
def : Pat<(sext_inreg i64:$Rn, i8),
|
|
(SXTBxw (EXTRACT_SUBREG $Rn, sub_32))>;
|
|
def : Pat<(sext_inreg i64:$Rn, i16),
|
|
(SXTHxw (EXTRACT_SUBREG $Rn, sub_32))>;
|
|
def : Pat<(sext_inreg i64:$Rn, i32),
|
|
(SXTWxw (EXTRACT_SUBREG $Rn, sub_32))>;
|
|
|
|
|
|
//===-------------------------------
|
|
// 3. Aliases for ASR and LSR (the simple shifts)
|
|
//===-------------------------------
|
|
|
|
// These also handle their own decoding because ImmS being set makes
|
|
// them take precedence over BFM.
|
|
multiclass A64I_shift<bits<2> opc, string asmop, SDNode opnode> {
|
|
def wwi : A64I_bitfield<0b0, opc, 0b0,
|
|
(outs GPR32:$Rd), (ins GPR32:$Rn, bitfield32_imm:$ImmR),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR"),
|
|
[(set i32:$Rd, (opnode i32:$Rn, bitfield32_imm:$ImmR))],
|
|
NoItinerary> {
|
|
let ImmS = 31;
|
|
}
|
|
|
|
def xxi : A64I_bitfield<0b1, opc, 0b1,
|
|
(outs GPR64:$Rd), (ins GPR64:$Rn, bitfield64_imm:$ImmR),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR"),
|
|
[(set i64:$Rd, (opnode i64:$Rn, bitfield64_imm:$ImmR))],
|
|
NoItinerary> {
|
|
let ImmS = 63;
|
|
}
|
|
|
|
}
|
|
|
|
defm ASR : A64I_shift<0b00, "asr", sra>;
|
|
defm LSR : A64I_shift<0b10, "lsr", srl>;
|
|
|
|
//===-------------------------------
|
|
// 4. Aliases for LSL
|
|
//===-------------------------------
|
|
|
|
// Unfortunately LSL and subsequent aliases are much more complicated. We need
|
|
// to be able to say certain output instruction fields depend in a complex
|
|
// manner on combinations of input assembly fields).
|
|
//
|
|
// MIOperandInfo *might* have been able to do it, but at the cost of
|
|
// significantly more C++ code.
|
|
|
|
// N.b. contrary to usual practice these operands store the shift rather than
|
|
// the machine bits in an MCInst. The complexity overhead of consistency
|
|
// outweighed the benefits in this case (custom asmparser, printer and selection
|
|
// vs custom encoder).
|
|
def bitfield32_lsl_imm : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 0 && Imm <= 31; }]> {
|
|
let ParserMatchClass = uimm5_asmoperand;
|
|
let EncoderMethod = "getBitfield32LSLOpValue";
|
|
}
|
|
|
|
def bitfield64_lsl_imm : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 0 && Imm <= 63; }]> {
|
|
let ParserMatchClass = uimm6_asmoperand;
|
|
let EncoderMethod = "getBitfield64LSLOpValue";
|
|
}
|
|
|
|
class A64I_bitfield_lsl<bit sf, RegisterClass GPR, ValueType ty,
|
|
Operand operand>
|
|
: A64I_bitfield<sf, 0b10, sf, (outs GPR:$Rd), (ins GPR:$Rn, operand:$FullImm),
|
|
"lsl\t$Rd, $Rn, $FullImm",
|
|
[(set ty:$Rd, (shl ty:$Rn, operand:$FullImm))],
|
|
NoItinerary> {
|
|
bits<12> FullImm;
|
|
let ImmR = FullImm{5-0};
|
|
let ImmS = FullImm{11-6};
|
|
|
|
// No disassembler allowed because it would overlap with BFM which does the
|
|
// actual work.
|
|
let isAsmParserOnly = 1;
|
|
}
|
|
|
|
def LSLwwi : A64I_bitfield_lsl<0b0, GPR32, i32, bitfield32_lsl_imm>;
|
|
def LSLxxi : A64I_bitfield_lsl<0b1, GPR64, i64, bitfield64_lsl_imm>;
|
|
|
|
//===-------------------------------
|
|
// 5. Aliases for bitfield extract instructions
|
|
//===-------------------------------
|
|
|
|
def bfx32_width_asmoperand : AsmOperandClass {
|
|
let Name = "BFX32Width";
|
|
let PredicateMethod = "isBitfieldWidth<32>";
|
|
let RenderMethod = "addBFXWidthOperands";
|
|
let DiagnosticType = "Width32";
|
|
}
|
|
|
|
def bfx32_width : Operand<i64>, ImmLeaf<i64, [{ return true; }]> {
|
|
let PrintMethod = "printBFXWidthOperand";
|
|
let ParserMatchClass = bfx32_width_asmoperand;
|
|
}
|
|
|
|
def bfx64_width_asmoperand : AsmOperandClass {
|
|
let Name = "BFX64Width";
|
|
let PredicateMethod = "isBitfieldWidth<64>";
|
|
let RenderMethod = "addBFXWidthOperands";
|
|
let DiagnosticType = "Width64";
|
|
}
|
|
|
|
def bfx64_width : Operand<i64> {
|
|
let PrintMethod = "printBFXWidthOperand";
|
|
let ParserMatchClass = bfx64_width_asmoperand;
|
|
}
|
|
|
|
|
|
multiclass A64I_bitfield_extract<bits<2> opc, string asmop, SDNode op> {
|
|
def wwii : A64I_bitfield<0b0, opc, 0b0, (outs GPR32:$Rd),
|
|
(ins GPR32:$Rn, bitfield32_imm:$ImmR, bfx32_width:$ImmS),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR, $ImmS"),
|
|
[(set i32:$Rd, (op i32:$Rn, imm:$ImmR, imm:$ImmS))],
|
|
NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
}
|
|
|
|
def xxii : A64I_bitfield<0b1, opc, 0b1, (outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, bitfield64_imm:$ImmR, bfx64_width:$ImmS),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR, $ImmS"),
|
|
[(set i64:$Rd, (op i64:$Rn, imm:$ImmR, imm:$ImmS))],
|
|
NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
}
|
|
}
|
|
|
|
defm SBFX : A64I_bitfield_extract<0b00, "sbfx", A64Sbfx>;
|
|
defm UBFX : A64I_bitfield_extract<0b10, "ubfx", A64Ubfx>;
|
|
|
|
// Again, variants based on BFM modify Rd so need it as an input too.
|
|
def BFXILwwii : A64I_bitfield<0b0, 0b01, 0b0, (outs GPR32:$Rd),
|
|
(ins GPR32:$src, GPR32:$Rn, bitfield32_imm:$ImmR, bfx32_width:$ImmS),
|
|
"bfxil\t$Rd, $Rn, $ImmR, $ImmS", [], NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
let Constraints = "$src = $Rd";
|
|
}
|
|
|
|
def BFXILxxii : A64I_bitfield<0b1, 0b01, 0b1, (outs GPR64:$Rd),
|
|
(ins GPR64:$src, GPR64:$Rn, bitfield64_imm:$ImmR, bfx64_width:$ImmS),
|
|
"bfxil\t$Rd, $Rn, $ImmR, $ImmS", [], NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
let Constraints = "$src = $Rd";
|
|
}
|
|
|
|
// SBFX instructions can do a 1-instruction sign-extension of boolean values.
|
|
def : Pat<(sext_inreg i64:$Rn, i1), (SBFXxxii $Rn, 0, 0)>;
|
|
def : Pat<(sext_inreg i32:$Rn, i1), (SBFXwwii $Rn, 0, 0)>;
|
|
def : Pat<(i64 (sext_inreg (anyext i32:$Rn), i1)),
|
|
(SBFXxxii (SUBREG_TO_REG (i64 0), $Rn, sub_32), 0, 0)>;
|
|
|
|
// UBFX makes sense as an implementation of a 64-bit zero-extension too. Could
|
|
// use either 64-bit or 32-bit variant, but 32-bit might be more efficient.
|
|
def : Pat<(zext i32:$Rn), (SUBREG_TO_REG (i64 0), (UBFXwwii $Rn, 0, 31),
|
|
sub_32)>;
|
|
|
|
//===-------------------------------
|
|
// 6. Aliases for bitfield insert instructions
|
|
//===-------------------------------
|
|
|
|
def bfi32_lsb_asmoperand : AsmOperandClass {
|
|
let Name = "BFI32LSB";
|
|
let PredicateMethod = "isUImm<5>";
|
|
let RenderMethod = "addBFILSBOperands<32>";
|
|
let DiagnosticType = "UImm5";
|
|
}
|
|
|
|
def bfi32_lsb : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 0 && Imm <= 31; }]> {
|
|
let PrintMethod = "printBFILSBOperand<32>";
|
|
let ParserMatchClass = bfi32_lsb_asmoperand;
|
|
}
|
|
|
|
def bfi64_lsb_asmoperand : AsmOperandClass {
|
|
let Name = "BFI64LSB";
|
|
let PredicateMethod = "isUImm<6>";
|
|
let RenderMethod = "addBFILSBOperands<64>";
|
|
let DiagnosticType = "UImm6";
|
|
}
|
|
|
|
def bfi64_lsb : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 0 && Imm <= 63; }]> {
|
|
let PrintMethod = "printBFILSBOperand<64>";
|
|
let ParserMatchClass = bfi64_lsb_asmoperand;
|
|
}
|
|
|
|
// Width verification is performed during conversion so width operand can be
|
|
// shared between 32/64-bit cases. Still needed for the print method though
|
|
// because ImmR encodes "width - 1".
|
|
def bfi32_width_asmoperand : AsmOperandClass {
|
|
let Name = "BFI32Width";
|
|
let PredicateMethod = "isBitfieldWidth<32>";
|
|
let RenderMethod = "addBFIWidthOperands";
|
|
let DiagnosticType = "Width32";
|
|
}
|
|
|
|
def bfi32_width : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 1 && Imm <= 32; }]> {
|
|
let PrintMethod = "printBFIWidthOperand";
|
|
let ParserMatchClass = bfi32_width_asmoperand;
|
|
}
|
|
|
|
def bfi64_width_asmoperand : AsmOperandClass {
|
|
let Name = "BFI64Width";
|
|
let PredicateMethod = "isBitfieldWidth<64>";
|
|
let RenderMethod = "addBFIWidthOperands";
|
|
let DiagnosticType = "Width64";
|
|
}
|
|
|
|
def bfi64_width : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= 1 && Imm <= 64; }]> {
|
|
let PrintMethod = "printBFIWidthOperand";
|
|
let ParserMatchClass = bfi64_width_asmoperand;
|
|
}
|
|
|
|
multiclass A64I_bitfield_insert<bits<2> opc, string asmop> {
|
|
def wwii : A64I_bitfield<0b0, opc, 0b0, (outs GPR32:$Rd),
|
|
(ins GPR32:$Rn, bfi32_lsb:$ImmR, bfi32_width:$ImmS),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR, $ImmS"),
|
|
[], NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
}
|
|
|
|
def xxii : A64I_bitfield<0b1, opc, 0b1, (outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, bfi64_lsb:$ImmR, bfi64_width:$ImmS),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $ImmR, $ImmS"),
|
|
[], NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
}
|
|
}
|
|
|
|
defm SBFIZ : A64I_bitfield_insert<0b00, "sbfiz">;
|
|
defm UBFIZ : A64I_bitfield_insert<0b10, "ubfiz">;
|
|
|
|
|
|
def BFIwwii : A64I_bitfield<0b0, 0b01, 0b0, (outs GPR32:$Rd),
|
|
(ins GPR32:$src, GPR32:$Rn, bfi32_lsb:$ImmR, bfi32_width:$ImmS),
|
|
"bfi\t$Rd, $Rn, $ImmR, $ImmS", [], NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
let Constraints = "$src = $Rd";
|
|
}
|
|
|
|
def BFIxxii : A64I_bitfield<0b1, 0b01, 0b1, (outs GPR64:$Rd),
|
|
(ins GPR64:$src, GPR64:$Rn, bfi64_lsb:$ImmR, bfi64_width:$ImmS),
|
|
"bfi\t$Rd, $Rn, $ImmR, $ImmS", [], NoItinerary> {
|
|
// As above, no disassembler allowed.
|
|
let isAsmParserOnly = 1;
|
|
let Constraints = "$src = $Rd";
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Compare and branch (immediate)
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: CBZ, CBNZ
|
|
|
|
class label_asmoperand<int width, int scale> : AsmOperandClass {
|
|
let Name = "Label" # width # "_" # scale;
|
|
let PredicateMethod = "isLabel<" # width # "," # scale # ">";
|
|
let RenderMethod = "addLabelOperands<" # width # ", " # scale # ">";
|
|
let DiagnosticType = "Label";
|
|
}
|
|
|
|
def label_wid19_scal4_asmoperand : label_asmoperand<19, 4>;
|
|
|
|
// All conditional immediate branches are the same really: 19 signed bits scaled
|
|
// by the instruction-size (4).
|
|
def bcc_target : Operand<OtherVT> {
|
|
// This label is a 19-bit offset from PC, scaled by the instruction-width: 4.
|
|
let ParserMatchClass = label_wid19_scal4_asmoperand;
|
|
let PrintMethod = "printLabelOperand<19, 4>";
|
|
let EncoderMethod = "getLabelOpValue<AArch64::fixup_a64_condbr>";
|
|
let OperandType = "OPERAND_PCREL";
|
|
}
|
|
|
|
multiclass cmpbr_sizes<bit op, string asmop, ImmLeaf SETOP> {
|
|
let isBranch = 1, isTerminator = 1 in {
|
|
def x : A64I_cmpbr<0b1, op,
|
|
(outs),
|
|
(ins GPR64:$Rt, bcc_target:$Label),
|
|
!strconcat(asmop,"\t$Rt, $Label"),
|
|
[(A64br_cc (A64cmp i64:$Rt, 0), SETOP, bb:$Label)],
|
|
NoItinerary>;
|
|
|
|
def w : A64I_cmpbr<0b0, op,
|
|
(outs),
|
|
(ins GPR32:$Rt, bcc_target:$Label),
|
|
!strconcat(asmop,"\t$Rt, $Label"),
|
|
[(A64br_cc (A64cmp i32:$Rt, 0), SETOP, bb:$Label)],
|
|
NoItinerary>;
|
|
}
|
|
}
|
|
|
|
defm CBZ : cmpbr_sizes<0b0, "cbz", ImmLeaf<i32, [{
|
|
return Imm == A64CC::EQ;
|
|
}]> >;
|
|
defm CBNZ : cmpbr_sizes<0b1, "cbnz", ImmLeaf<i32, [{
|
|
return Imm == A64CC::NE;
|
|
}]> >;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Conditional branch (immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: B.cc
|
|
|
|
def cond_code_asmoperand : AsmOperandClass {
|
|
let Name = "CondCode";
|
|
let DiagnosticType = "CondCode";
|
|
}
|
|
|
|
def cond_code : Operand<i32>, ImmLeaf<i32, [{
|
|
return Imm >= 0 && Imm <= 15;
|
|
}]> {
|
|
let PrintMethod = "printCondCodeOperand";
|
|
let ParserMatchClass = cond_code_asmoperand;
|
|
}
|
|
|
|
def Bcc : A64I_condbr<0b0, 0b0, (outs),
|
|
(ins cond_code:$Cond, bcc_target:$Label),
|
|
"b.$Cond $Label", [(A64br_cc NZCV, (i32 imm:$Cond), bb:$Label)],
|
|
NoItinerary> {
|
|
let Uses = [NZCV];
|
|
let isBranch = 1;
|
|
let isTerminator = 1;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Conditional compare (immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: CCMN, CCMP
|
|
|
|
def uimm4_asmoperand : AsmOperandClass {
|
|
let Name = "UImm4";
|
|
let PredicateMethod = "isUImm<4>";
|
|
let RenderMethod = "addImmOperands";
|
|
let DiagnosticType = "UImm4";
|
|
}
|
|
|
|
def uimm4 : Operand<i32> {
|
|
let ParserMatchClass = uimm4_asmoperand;
|
|
}
|
|
|
|
def uimm5 : Operand<i32> {
|
|
let ParserMatchClass = uimm5_asmoperand;
|
|
}
|
|
|
|
// The only difference between this operand and the one for instructions like
|
|
// B.cc is that it's parsed manually. The other get parsed implicitly as part of
|
|
// the mnemonic handling.
|
|
def cond_code_op_asmoperand : AsmOperandClass {
|
|
let Name = "CondCodeOp";
|
|
let RenderMethod = "addCondCodeOperands";
|
|
let PredicateMethod = "isCondCode";
|
|
let ParserMethod = "ParseCondCodeOperand";
|
|
let DiagnosticType = "CondCode";
|
|
}
|
|
|
|
def cond_code_op : Operand<i32> {
|
|
let PrintMethod = "printCondCodeOperand";
|
|
let ParserMatchClass = cond_code_op_asmoperand;
|
|
}
|
|
|
|
class A64I_condcmpimmImpl<bit sf, bit op, RegisterClass GPR, string asmop>
|
|
: A64I_condcmpimm<sf, op, 0b0, 0b0, 0b1, (outs),
|
|
(ins GPR:$Rn, uimm5:$UImm5, uimm4:$NZCVImm, cond_code_op:$Cond),
|
|
!strconcat(asmop, "\t$Rn, $UImm5, $NZCVImm, $Cond"),
|
|
[], NoItinerary> {
|
|
let Defs = [NZCV];
|
|
}
|
|
|
|
def CCMNwi : A64I_condcmpimmImpl<0b0, 0b0, GPR32, "ccmn">;
|
|
def CCMNxi : A64I_condcmpimmImpl<0b1, 0b0, GPR64, "ccmn">;
|
|
def CCMPwi : A64I_condcmpimmImpl<0b0, 0b1, GPR32, "ccmp">;
|
|
def CCMPxi : A64I_condcmpimmImpl<0b1, 0b1, GPR64, "ccmp">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Conditional compare (register) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: CCMN, CCMP
|
|
|
|
class A64I_condcmpregImpl<bit sf, bit op, RegisterClass GPR, string asmop>
|
|
: A64I_condcmpreg<sf, op, 0b0, 0b0, 0b1,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm, uimm4:$NZCVImm, cond_code_op:$Cond),
|
|
!strconcat(asmop, "\t$Rn, $Rm, $NZCVImm, $Cond"),
|
|
[], NoItinerary> {
|
|
let Defs = [NZCV];
|
|
}
|
|
|
|
def CCMNww : A64I_condcmpregImpl<0b0, 0b0, GPR32, "ccmn">;
|
|
def CCMNxx : A64I_condcmpregImpl<0b1, 0b0, GPR64, "ccmn">;
|
|
def CCMPww : A64I_condcmpregImpl<0b0, 0b1, GPR32, "ccmp">;
|
|
def CCMPxx : A64I_condcmpregImpl<0b1, 0b1, GPR64, "ccmp">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Conditional select instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: CSEL, CSINC, CSINV, CSNEG + aliases CSET, CSETM, CINC, CINV, CNEG
|
|
|
|
// Condition code which is encoded as the inversion (semantically rather than
|
|
// bitwise) in the instruction.
|
|
def inv_cond_code_op_asmoperand : AsmOperandClass {
|
|
let Name = "InvCondCodeOp";
|
|
let RenderMethod = "addInvCondCodeOperands";
|
|
let PredicateMethod = "isCondCode";
|
|
let ParserMethod = "ParseCondCodeOperand";
|
|
let DiagnosticType = "CondCode";
|
|
}
|
|
|
|
def inv_cond_code_op : Operand<i32> {
|
|
let ParserMatchClass = inv_cond_code_op_asmoperand;
|
|
}
|
|
|
|
// Having a separate operand for the selectable use-case is debatable, but gives
|
|
// consistency with cond_code.
|
|
def inv_cond_XFORM : SDNodeXForm<imm, [{
|
|
A64CC::CondCodes CC = static_cast<A64CC::CondCodes>(N->getZExtValue());
|
|
return CurDAG->getTargetConstant(A64InvertCondCode(CC), MVT::i32);
|
|
}]>;
|
|
|
|
def inv_cond_code
|
|
: ImmLeaf<i32, [{ return Imm >= 0 && Imm <= 15; }], inv_cond_XFORM>;
|
|
|
|
|
|
multiclass A64I_condselSizes<bit op, bits<2> op2, string asmop,
|
|
SDPatternOperator select> {
|
|
let Uses = [NZCV] in {
|
|
def wwwc : A64I_condsel<0b0, op, 0b0, op2,
|
|
(outs GPR32:$Rd),
|
|
(ins GPR32:$Rn, GPR32:$Rm, cond_code_op:$Cond),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Cond"),
|
|
[(set i32:$Rd, (select i32:$Rn, i32:$Rm))],
|
|
NoItinerary>;
|
|
|
|
|
|
def xxxc : A64I_condsel<0b1, op, 0b0, op2,
|
|
(outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, GPR64:$Rm, cond_code_op:$Cond),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Cond"),
|
|
[(set i64:$Rd, (select i64:$Rn, i64:$Rm))],
|
|
NoItinerary>;
|
|
}
|
|
}
|
|
|
|
def simple_select
|
|
: PatFrag<(ops node:$lhs, node:$rhs),
|
|
(A64select_cc NZCV, node:$lhs, node:$rhs, (i32 imm:$Cond))>;
|
|
|
|
class complex_select<SDPatternOperator opnode>
|
|
: PatFrag<(ops node:$lhs, node:$rhs),
|
|
(A64select_cc NZCV, node:$lhs, (opnode node:$rhs), (i32 imm:$Cond))>;
|
|
|
|
|
|
defm CSEL : A64I_condselSizes<0b0, 0b00, "csel", simple_select>;
|
|
defm CSINC : A64I_condselSizes<0b0, 0b01, "csinc",
|
|
complex_select<PatFrag<(ops node:$val),
|
|
(add node:$val, 1)>>>;
|
|
defm CSINV : A64I_condselSizes<0b1, 0b00, "csinv", complex_select<not>>;
|
|
defm CSNEG : A64I_condselSizes<0b1, 0b01, "csneg", complex_select<ineg>>;
|
|
|
|
// Now the instruction aliases, which fit nicely into LLVM's model:
|
|
|
|
def : InstAlias<"cset $Rd, $Cond",
|
|
(CSINCwwwc GPR32:$Rd, WZR, WZR, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"cset $Rd, $Cond",
|
|
(CSINCxxxc GPR64:$Rd, XZR, XZR, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"csetm $Rd, $Cond",
|
|
(CSINVwwwc GPR32:$Rd, WZR, WZR, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"csetm $Rd, $Cond",
|
|
(CSINVxxxc GPR64:$Rd, XZR, XZR, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"cinc $Rd, $Rn, $Cond",
|
|
(CSINCwwwc GPR32:$Rd, GPR32:$Rn, GPR32:$Rn, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"cinc $Rd, $Rn, $Cond",
|
|
(CSINCxxxc GPR64:$Rd, GPR64:$Rn, GPR64:$Rn, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"cinv $Rd, $Rn, $Cond",
|
|
(CSINVwwwc GPR32:$Rd, GPR32:$Rn, GPR32:$Rn, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"cinv $Rd, $Rn, $Cond",
|
|
(CSINVxxxc GPR64:$Rd, GPR64:$Rn, GPR64:$Rn, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"cneg $Rd, $Rn, $Cond",
|
|
(CSNEGwwwc GPR32:$Rd, GPR32:$Rn, GPR32:$Rn, inv_cond_code_op:$Cond)>;
|
|
def : InstAlias<"cneg $Rd, $Rn, $Cond",
|
|
(CSNEGxxxc GPR64:$Rd, GPR64:$Rn, GPR64:$Rn, inv_cond_code_op:$Cond)>;
|
|
|
|
// Finally some helper patterns.
|
|
|
|
// For CSET (a.k.a. zero-extension of icmp)
|
|
def : Pat<(A64select_cc NZCV, 0, 1, cond_code:$Cond),
|
|
(CSINCwwwc WZR, WZR, cond_code:$Cond)>;
|
|
def : Pat<(A64select_cc NZCV, 1, 0, inv_cond_code:$Cond),
|
|
(CSINCwwwc WZR, WZR, inv_cond_code:$Cond)>;
|
|
|
|
def : Pat<(A64select_cc NZCV, 0, 1, cond_code:$Cond),
|
|
(CSINCxxxc XZR, XZR, cond_code:$Cond)>;
|
|
def : Pat<(A64select_cc NZCV, 1, 0, inv_cond_code:$Cond),
|
|
(CSINCxxxc XZR, XZR, inv_cond_code:$Cond)>;
|
|
|
|
// For CSETM (a.k.a. sign-extension of icmp)
|
|
def : Pat<(A64select_cc NZCV, 0, -1, cond_code:$Cond),
|
|
(CSINVwwwc WZR, WZR, cond_code:$Cond)>;
|
|
def : Pat<(A64select_cc NZCV, -1, 0, inv_cond_code:$Cond),
|
|
(CSINVwwwc WZR, WZR, inv_cond_code:$Cond)>;
|
|
|
|
def : Pat<(A64select_cc NZCV, 0, -1, cond_code:$Cond),
|
|
(CSINVxxxc XZR, XZR, cond_code:$Cond)>;
|
|
def : Pat<(A64select_cc NZCV, -1, 0, inv_cond_code:$Cond),
|
|
(CSINVxxxc XZR, XZR, inv_cond_code:$Cond)>;
|
|
|
|
// CINC, CINV and CNEG get dealt with automatically, which leaves the issue of
|
|
// commutativity. The instructions are to complex for isCommutable to be used,
|
|
// so we have to create the patterns manually:
|
|
|
|
// No commutable pattern for CSEL since the commuted version is isomorphic.
|
|
|
|
// CSINC
|
|
def :Pat<(A64select_cc NZCV, (add i32:$Rm, 1), i32:$Rn, inv_cond_code:$Cond),
|
|
(CSINCwwwc $Rn, $Rm, inv_cond_code:$Cond)>;
|
|
def :Pat<(A64select_cc NZCV, (add i64:$Rm, 1), i64:$Rn, inv_cond_code:$Cond),
|
|
(CSINCxxxc $Rn, $Rm, inv_cond_code:$Cond)>;
|
|
|
|
// CSINV
|
|
def :Pat<(A64select_cc NZCV, (not i32:$Rm), i32:$Rn, inv_cond_code:$Cond),
|
|
(CSINVwwwc $Rn, $Rm, inv_cond_code:$Cond)>;
|
|
def :Pat<(A64select_cc NZCV, (not i64:$Rm), i64:$Rn, inv_cond_code:$Cond),
|
|
(CSINVxxxc $Rn, $Rm, inv_cond_code:$Cond)>;
|
|
|
|
// CSNEG
|
|
def :Pat<(A64select_cc NZCV, (ineg i32:$Rm), i32:$Rn, inv_cond_code:$Cond),
|
|
(CSNEGwwwc $Rn, $Rm, inv_cond_code:$Cond)>;
|
|
def :Pat<(A64select_cc NZCV, (ineg i64:$Rm), i64:$Rn, inv_cond_code:$Cond),
|
|
(CSNEGxxxc $Rn, $Rm, inv_cond_code:$Cond)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Data Processing (1 source) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: RBIT, REV16, REV, REV32, CLZ, CLS.
|
|
|
|
// We define an unary operator which always fails. We will use this to
|
|
// define unary operators that cannot be matched.
|
|
|
|
class A64I_dp_1src_impl<bit sf, bits<6> opcode, string asmop,
|
|
list<dag> patterns, RegisterClass GPRrc,
|
|
InstrItinClass itin>:
|
|
A64I_dp_1src<sf,
|
|
0,
|
|
0b00000,
|
|
opcode,
|
|
!strconcat(asmop, "\t$Rd, $Rn"),
|
|
(outs GPRrc:$Rd),
|
|
(ins GPRrc:$Rn),
|
|
patterns,
|
|
itin>;
|
|
|
|
multiclass A64I_dp_1src <bits<6> opcode, string asmop> {
|
|
let hasSideEffects = 0 in {
|
|
def ww : A64I_dp_1src_impl<0b0, opcode, asmop, [], GPR32, NoItinerary>;
|
|
def xx : A64I_dp_1src_impl<0b1, opcode, asmop, [], GPR64, NoItinerary>;
|
|
}
|
|
}
|
|
|
|
defm RBIT : A64I_dp_1src<0b000000, "rbit">;
|
|
defm CLS : A64I_dp_1src<0b000101, "cls">;
|
|
defm CLZ : A64I_dp_1src<0b000100, "clz">;
|
|
|
|
def : Pat<(ctlz i32:$Rn), (CLZww $Rn)>;
|
|
def : Pat<(ctlz i64:$Rn), (CLZxx $Rn)>;
|
|
def : Pat<(ctlz_zero_undef i32:$Rn), (CLZww $Rn)>;
|
|
def : Pat<(ctlz_zero_undef i64:$Rn), (CLZxx $Rn)>;
|
|
|
|
def : Pat<(cttz i32:$Rn), (CLZww (RBITww $Rn))>;
|
|
def : Pat<(cttz i64:$Rn), (CLZxx (RBITxx $Rn))>;
|
|
def : Pat<(cttz_zero_undef i32:$Rn), (CLZww (RBITww $Rn))>;
|
|
def : Pat<(cttz_zero_undef i64:$Rn), (CLZxx (RBITxx $Rn))>;
|
|
|
|
|
|
def REVww : A64I_dp_1src_impl<0b0, 0b000010, "rev",
|
|
[(set i32:$Rd, (bswap i32:$Rn))],
|
|
GPR32, NoItinerary>;
|
|
def REVxx : A64I_dp_1src_impl<0b1, 0b000011, "rev",
|
|
[(set i64:$Rd, (bswap i64:$Rn))],
|
|
GPR64, NoItinerary>;
|
|
def REV32xx : A64I_dp_1src_impl<0b1, 0b000010, "rev32",
|
|
[(set i64:$Rd, (bswap (rotr i64:$Rn, (i64 32))))],
|
|
GPR64, NoItinerary>;
|
|
def REV16ww : A64I_dp_1src_impl<0b0, 0b000001, "rev16",
|
|
[(set i32:$Rd, (bswap (rotr i32:$Rn, (i64 16))))],
|
|
GPR32,
|
|
NoItinerary>;
|
|
def REV16xx : A64I_dp_1src_impl<0b1, 0b000001, "rev16", [], GPR64, NoItinerary>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Data Processing (2 sources) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: CRC32C?[BHWX], UDIV, SDIV, LSLV, LSRV, ASRV, RORV + aliases LSL,
|
|
// LSR, ASR, ROR
|
|
|
|
|
|
class dp_2src_impl<bit sf, bits<6> opcode, string asmop, list<dag> patterns,
|
|
RegisterClass GPRsp,
|
|
InstrItinClass itin>:
|
|
A64I_dp_2src<sf,
|
|
opcode,
|
|
0,
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm"),
|
|
(outs GPRsp:$Rd),
|
|
(ins GPRsp:$Rn, GPRsp:$Rm),
|
|
patterns,
|
|
itin>;
|
|
|
|
multiclass dp_2src_crc<bit c, string asmop> {
|
|
def B_www : dp_2src_impl<0b0, {0, 1, 0, c, 0, 0},
|
|
!strconcat(asmop, "b"), [], GPR32, NoItinerary>;
|
|
def H_www : dp_2src_impl<0b0, {0, 1, 0, c, 0, 1},
|
|
!strconcat(asmop, "h"), [], GPR32, NoItinerary>;
|
|
def W_www : dp_2src_impl<0b0, {0, 1, 0, c, 1, 0},
|
|
!strconcat(asmop, "w"), [], GPR32, NoItinerary>;
|
|
def X_wwx : A64I_dp_2src<0b1, {0, 1, 0, c, 1, 1}, 0b0,
|
|
!strconcat(asmop, "x\t$Rd, $Rn, $Rm"),
|
|
(outs GPR32:$Rd), (ins GPR32:$Rn, GPR64:$Rm), [],
|
|
NoItinerary>;
|
|
}
|
|
|
|
multiclass dp_2src_zext <bits<6> opcode, string asmop, SDPatternOperator op> {
|
|
def www : dp_2src_impl<0b0,
|
|
opcode,
|
|
asmop,
|
|
[(set i32:$Rd,
|
|
(op i32:$Rn, (i64 (zext i32:$Rm))))],
|
|
GPR32,
|
|
NoItinerary>;
|
|
def xxx : dp_2src_impl<0b1,
|
|
opcode,
|
|
asmop,
|
|
[(set i64:$Rd, (op i64:$Rn, i64:$Rm))],
|
|
GPR64,
|
|
NoItinerary>;
|
|
}
|
|
|
|
|
|
multiclass dp_2src <bits<6> opcode, string asmop, SDPatternOperator op> {
|
|
def www : dp_2src_impl<0b0,
|
|
opcode,
|
|
asmop,
|
|
[(set i32:$Rd, (op i32:$Rn, i32:$Rm))],
|
|
GPR32,
|
|
NoItinerary>;
|
|
def xxx : dp_2src_impl<0b1,
|
|
opcode,
|
|
asmop,
|
|
[(set i64:$Rd, (op i64:$Rn, i64:$Rm))],
|
|
GPR64,
|
|
NoItinerary>;
|
|
}
|
|
|
|
// Here we define the data processing 2 source instructions.
|
|
defm CRC32 : dp_2src_crc<0b0, "crc32">;
|
|
defm CRC32C : dp_2src_crc<0b1, "crc32c">;
|
|
|
|
defm UDIV : dp_2src<0b000010, "udiv", udiv>;
|
|
defm SDIV : dp_2src<0b000011, "sdiv", sdiv>;
|
|
|
|
defm LSLV : dp_2src_zext<0b001000, "lsl", shl>;
|
|
defm LSRV : dp_2src_zext<0b001001, "lsr", srl>;
|
|
defm ASRV : dp_2src_zext<0b001010, "asr", sra>;
|
|
defm RORV : dp_2src_zext<0b001011, "ror", rotr>;
|
|
|
|
// Extra patterns for an incoming 64-bit value for a 32-bit
|
|
// operation. Since the LLVM operations are undefined (as in C) if the
|
|
// RHS is out of range, it's perfectly permissible to discard the high
|
|
// bits of the GPR64.
|
|
def : Pat<(shl i32:$Rn, i64:$Rm),
|
|
(LSLVwww $Rn, (EXTRACT_SUBREG $Rm, sub_32))>;
|
|
def : Pat<(srl i32:$Rn, i64:$Rm),
|
|
(LSRVwww $Rn, (EXTRACT_SUBREG $Rm, sub_32))>;
|
|
def : Pat<(sra i32:$Rn, i64:$Rm),
|
|
(ASRVwww $Rn, (EXTRACT_SUBREG $Rm, sub_32))>;
|
|
def : Pat<(rotr i32:$Rn, i64:$Rm),
|
|
(RORVwww $Rn, (EXTRACT_SUBREG $Rm, sub_32))>;
|
|
|
|
// Here we define the aliases for the data processing 2 source instructions.
|
|
def LSL_mnemonic : MnemonicAlias<"lslv", "lsl">;
|
|
def LSR_mnemonic : MnemonicAlias<"lsrv", "lsr">;
|
|
def ASR_menmonic : MnemonicAlias<"asrv", "asr">;
|
|
def ROR_menmonic : MnemonicAlias<"rorv", "ror">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Data Processing (3 sources) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: MADD, MSUB, SMADDL, SMSUBL, SMULH, UMADDL, UMSUBL, UMULH
|
|
// + aliases MUL, MNEG, SMULL, SMNEGL, UMULL, UMNEGL
|
|
|
|
class A64I_dp3_4operand<bit sf, bits<6> opcode, RegisterClass AccReg,
|
|
ValueType AccTy, RegisterClass SrcReg,
|
|
string asmop, dag pattern>
|
|
: A64I_dp3<sf, opcode,
|
|
(outs AccReg:$Rd), (ins SrcReg:$Rn, SrcReg:$Rm, AccReg:$Ra),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Ra"),
|
|
[(set AccTy:$Rd, pattern)], NoItinerary> {
|
|
RegisterClass AccGPR = AccReg;
|
|
RegisterClass SrcGPR = SrcReg;
|
|
}
|
|
|
|
def MADDwwww : A64I_dp3_4operand<0b0, 0b000000, GPR32, i32, GPR32, "madd",
|
|
(add i32:$Ra, (mul i32:$Rn, i32:$Rm))>;
|
|
def MADDxxxx : A64I_dp3_4operand<0b1, 0b000000, GPR64, i64, GPR64, "madd",
|
|
(add i64:$Ra, (mul i64:$Rn, i64:$Rm))>;
|
|
|
|
def MSUBwwww : A64I_dp3_4operand<0b0, 0b000001, GPR32, i32, GPR32, "msub",
|
|
(sub i32:$Ra, (mul i32:$Rn, i32:$Rm))>;
|
|
def MSUBxxxx : A64I_dp3_4operand<0b1, 0b000001, GPR64, i64, GPR64, "msub",
|
|
(sub i64:$Ra, (mul i64:$Rn, i64:$Rm))>;
|
|
|
|
def SMADDLxwwx : A64I_dp3_4operand<0b1, 0b000010, GPR64, i64, GPR32, "smaddl",
|
|
(add i64:$Ra, (mul (i64 (sext i32:$Rn)), (sext i32:$Rm)))>;
|
|
def SMSUBLxwwx : A64I_dp3_4operand<0b1, 0b000011, GPR64, i64, GPR32, "smsubl",
|
|
(sub i64:$Ra, (mul (i64 (sext i32:$Rn)), (sext i32:$Rm)))>;
|
|
|
|
def UMADDLxwwx : A64I_dp3_4operand<0b1, 0b001010, GPR64, i64, GPR32, "umaddl",
|
|
(add i64:$Ra, (mul (i64 (zext i32:$Rn)), (zext i32:$Rm)))>;
|
|
def UMSUBLxwwx : A64I_dp3_4operand<0b1, 0b001011, GPR64, i64, GPR32, "umsubl",
|
|
(sub i64:$Ra, (mul (i64 (zext i32:$Rn)), (zext i32:$Rm)))>;
|
|
|
|
let isCommutable = 1, PostEncoderMethod = "fixMulHigh" in {
|
|
def UMULHxxx : A64I_dp3<0b1, 0b001100, (outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, GPR64:$Rm),
|
|
"umulh\t$Rd, $Rn, $Rm",
|
|
[(set i64:$Rd, (mulhu i64:$Rn, i64:$Rm))],
|
|
NoItinerary>;
|
|
|
|
def SMULHxxx : A64I_dp3<0b1, 0b000100, (outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, GPR64:$Rm),
|
|
"smulh\t$Rd, $Rn, $Rm",
|
|
[(set i64:$Rd, (mulhs i64:$Rn, i64:$Rm))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
multiclass A64I_dp3_3operand<string asmop, A64I_dp3_4operand INST,
|
|
Register ZR, dag pattern> {
|
|
def : InstAlias<asmop # " $Rd, $Rn, $Rm",
|
|
(INST INST.AccGPR:$Rd, INST.SrcGPR:$Rn, INST.SrcGPR:$Rm, ZR)>;
|
|
|
|
def : Pat<pattern, (INST $Rn, $Rm, ZR)>;
|
|
}
|
|
|
|
defm : A64I_dp3_3operand<"mul", MADDwwww, WZR, (mul i32:$Rn, i32:$Rm)>;
|
|
defm : A64I_dp3_3operand<"mul", MADDxxxx, XZR, (mul i64:$Rn, i64:$Rm)>;
|
|
|
|
defm : A64I_dp3_3operand<"mneg", MSUBwwww, WZR,
|
|
(sub 0, (mul i32:$Rn, i32:$Rm))>;
|
|
defm : A64I_dp3_3operand<"mneg", MSUBxxxx, XZR,
|
|
(sub 0, (mul i64:$Rn, i64:$Rm))>;
|
|
|
|
defm : A64I_dp3_3operand<"smull", SMADDLxwwx, XZR,
|
|
(mul (i64 (sext i32:$Rn)), (sext i32:$Rm))>;
|
|
defm : A64I_dp3_3operand<"smnegl", SMSUBLxwwx, XZR,
|
|
(sub 0, (mul (i64 (sext i32:$Rn)), (sext i32:$Rm)))>;
|
|
|
|
defm : A64I_dp3_3operand<"umull", UMADDLxwwx, XZR,
|
|
(mul (i64 (zext i32:$Rn)), (zext i32:$Rm))>;
|
|
defm : A64I_dp3_3operand<"umnegl", UMSUBLxwwx, XZR,
|
|
(sub 0, (mul (i64 (zext i32:$Rn)), (zext i32:$Rm)))>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Exception generation
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: SVC, HVC, SMC, BRK, HLT, DCPS1, DCPS2, DCPS3
|
|
|
|
def uimm16_asmoperand : AsmOperandClass {
|
|
let Name = "UImm16";
|
|
let PredicateMethod = "isUImm<16>";
|
|
let RenderMethod = "addImmOperands";
|
|
let DiagnosticType = "UImm16";
|
|
}
|
|
|
|
def uimm16 : Operand<i32> {
|
|
let ParserMatchClass = uimm16_asmoperand;
|
|
}
|
|
|
|
class A64I_exceptImpl<bits<3> opc, bits<2> ll, string asmop>
|
|
: A64I_exception<opc, 0b000, ll, (outs), (ins uimm16:$UImm16),
|
|
!strconcat(asmop, "\t$UImm16"), [], NoItinerary> {
|
|
let isBranch = 1;
|
|
let isTerminator = 1;
|
|
}
|
|
|
|
def SVCi : A64I_exceptImpl<0b000, 0b01, "svc">;
|
|
def HVCi : A64I_exceptImpl<0b000, 0b10, "hvc">;
|
|
def SMCi : A64I_exceptImpl<0b000, 0b11, "smc">;
|
|
def BRKi : A64I_exceptImpl<0b001, 0b00, "brk">;
|
|
def HLTi : A64I_exceptImpl<0b010, 0b00, "hlt">;
|
|
|
|
def DCPS1i : A64I_exceptImpl<0b101, 0b01, "dcps1">;
|
|
def DCPS2i : A64I_exceptImpl<0b101, 0b10, "dcps2">;
|
|
def DCPS3i : A64I_exceptImpl<0b101, 0b11, "dcps3">;
|
|
|
|
// The immediate is optional for the DCPS instructions, defaulting to 0.
|
|
def : InstAlias<"dcps1", (DCPS1i 0)>;
|
|
def : InstAlias<"dcps2", (DCPS2i 0)>;
|
|
def : InstAlias<"dcps3", (DCPS3i 0)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Extract (immediate)
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: EXTR + alias ROR
|
|
|
|
def EXTRwwwi : A64I_extract<0b0, 0b000, 0b0,
|
|
(outs GPR32:$Rd),
|
|
(ins GPR32:$Rn, GPR32:$Rm, bitfield32_imm:$LSB),
|
|
"extr\t$Rd, $Rn, $Rm, $LSB",
|
|
[(set i32:$Rd,
|
|
(A64Extr i32:$Rn, i32:$Rm, imm:$LSB))],
|
|
NoItinerary>;
|
|
def EXTRxxxi : A64I_extract<0b1, 0b000, 0b1,
|
|
(outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, GPR64:$Rm, bitfield64_imm:$LSB),
|
|
"extr\t$Rd, $Rn, $Rm, $LSB",
|
|
[(set i64:$Rd,
|
|
(A64Extr i64:$Rn, i64:$Rm, imm:$LSB))],
|
|
NoItinerary>;
|
|
|
|
def : InstAlias<"ror $Rd, $Rs, $LSB",
|
|
(EXTRwwwi GPR32:$Rd, GPR32:$Rs, GPR32:$Rs, bitfield32_imm:$LSB)>;
|
|
def : InstAlias<"ror $Rd, $Rs, $LSB",
|
|
(EXTRxxxi GPR64:$Rd, GPR64:$Rs, GPR64:$Rs, bitfield64_imm:$LSB)>;
|
|
|
|
def : Pat<(rotr i32:$Rn, bitfield32_imm:$LSB),
|
|
(EXTRwwwi $Rn, $Rn, bitfield32_imm:$LSB)>;
|
|
def : Pat<(rotr i64:$Rn, bitfield64_imm:$LSB),
|
|
(EXTRxxxi $Rn, $Rn, bitfield64_imm:$LSB)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point compare instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FCMP, FCMPE
|
|
|
|
def fpzero_asmoperand : AsmOperandClass {
|
|
let Name = "FPZero";
|
|
let ParserMethod = "ParseFPImmOperand";
|
|
let DiagnosticType = "FPZero";
|
|
}
|
|
|
|
def fpz32 : Operand<f32>,
|
|
ComplexPattern<f32, 1, "SelectFPZeroOperand", [fpimm]> {
|
|
let ParserMatchClass = fpzero_asmoperand;
|
|
let PrintMethod = "printFPZeroOperand";
|
|
let DecoderMethod = "DecodeFPZeroOperand";
|
|
}
|
|
|
|
def fpz64 : Operand<f64>,
|
|
ComplexPattern<f64, 1, "SelectFPZeroOperand", [fpimm]> {
|
|
let ParserMatchClass = fpzero_asmoperand;
|
|
let PrintMethod = "printFPZeroOperand";
|
|
let DecoderMethod = "DecodeFPZeroOperand";
|
|
}
|
|
|
|
multiclass A64I_fpcmpSignal<bits<2> type, bit imm, dag ins, dag pattern> {
|
|
def _quiet : A64I_fpcmp<0b0, 0b0, type, 0b00, {0b0, imm, 0b0, 0b0, 0b0},
|
|
(outs), ins, "fcmp\t$Rn, $Rm", [pattern],
|
|
NoItinerary> {
|
|
let Defs = [NZCV];
|
|
}
|
|
|
|
def _sig : A64I_fpcmp<0b0, 0b0, type, 0b00, {0b1, imm, 0b0, 0b0, 0b0},
|
|
(outs), ins, "fcmpe\t$Rn, $Rm", [], NoItinerary> {
|
|
let Defs = [NZCV];
|
|
}
|
|
}
|
|
|
|
defm FCMPss : A64I_fpcmpSignal<0b00, 0b0, (ins FPR32:$Rn, FPR32:$Rm),
|
|
(set NZCV, (A64cmp f32:$Rn, f32:$Rm))>;
|
|
defm FCMPdd : A64I_fpcmpSignal<0b01, 0b0, (ins FPR64:$Rn, FPR64:$Rm),
|
|
(set NZCV, (A64cmp f64:$Rn, f64:$Rm))>;
|
|
|
|
// What would be Rm should be written as 0; note that even though it's called
|
|
// "$Rm" here to fit in with the InstrFormats, it's actually an immediate.
|
|
defm FCMPsi : A64I_fpcmpSignal<0b00, 0b1, (ins FPR32:$Rn, fpz32:$Rm),
|
|
(set NZCV, (A64cmp f32:$Rn, fpz32:$Rm))>;
|
|
|
|
defm FCMPdi : A64I_fpcmpSignal<0b01, 0b1, (ins FPR64:$Rn, fpz64:$Rm),
|
|
(set NZCV, (A64cmp f64:$Rn, fpz64:$Rm))>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point conditional compare instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FCCMP, FCCMPE
|
|
|
|
class A64I_fpccmpImpl<bits<2> type, bit op, RegisterClass FPR, string asmop>
|
|
: A64I_fpccmp<0b0, 0b0, type, op,
|
|
(outs),
|
|
(ins FPR:$Rn, FPR:$Rm, uimm4:$NZCVImm, cond_code_op:$Cond),
|
|
!strconcat(asmop, "\t$Rn, $Rm, $NZCVImm, $Cond"),
|
|
[], NoItinerary> {
|
|
let Defs = [NZCV];
|
|
}
|
|
|
|
def FCCMPss : A64I_fpccmpImpl<0b00, 0b0, FPR32, "fccmp">;
|
|
def FCCMPEss : A64I_fpccmpImpl<0b00, 0b1, FPR32, "fccmpe">;
|
|
def FCCMPdd : A64I_fpccmpImpl<0b01, 0b0, FPR64, "fccmp">;
|
|
def FCCMPEdd : A64I_fpccmpImpl<0b01, 0b1, FPR64, "fccmpe">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point conditional select instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FCSEL
|
|
|
|
let Uses = [NZCV] in {
|
|
def FCSELsssc : A64I_fpcondsel<0b0, 0b0, 0b00, (outs FPR32:$Rd),
|
|
(ins FPR32:$Rn, FPR32:$Rm, cond_code_op:$Cond),
|
|
"fcsel\t$Rd, $Rn, $Rm, $Cond",
|
|
[(set f32:$Rd,
|
|
(simple_select f32:$Rn, f32:$Rm))],
|
|
NoItinerary>;
|
|
|
|
|
|
def FCSELdddc : A64I_fpcondsel<0b0, 0b0, 0b01, (outs FPR64:$Rd),
|
|
(ins FPR64:$Rn, FPR64:$Rm, cond_code_op:$Cond),
|
|
"fcsel\t$Rd, $Rn, $Rm, $Cond",
|
|
[(set f64:$Rd,
|
|
(simple_select f64:$Rn, f64:$Rm))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point data-processing (1 source)
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FMOV, FABS, FNEG, FSQRT, FCVT, FRINT[NPMZAXI].
|
|
|
|
def FPNoUnop : PatFrag<(ops node:$val), (fneg node:$val),
|
|
[{ (void)N; return false; }]>;
|
|
|
|
// First we do the fairly trivial bunch with uniform "OP s, s" and "OP d, d"
|
|
// syntax. Default to no pattern because most are odd enough not to have one.
|
|
multiclass A64I_fpdp1sizes<bits<6> opcode, string asmstr,
|
|
SDPatternOperator opnode = FPNoUnop> {
|
|
def ss : A64I_fpdp1<0b0, 0b0, 0b00, opcode, (outs FPR32:$Rd), (ins FPR32:$Rn),
|
|
!strconcat(asmstr, "\t$Rd, $Rn"),
|
|
[(set f32:$Rd, (opnode f32:$Rn))],
|
|
NoItinerary>;
|
|
|
|
def dd : A64I_fpdp1<0b0, 0b0, 0b01, opcode, (outs FPR64:$Rd), (ins FPR64:$Rn),
|
|
!strconcat(asmstr, "\t$Rd, $Rn"),
|
|
[(set f64:$Rd, (opnode f64:$Rn))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
defm FMOV : A64I_fpdp1sizes<0b000000, "fmov">;
|
|
defm FABS : A64I_fpdp1sizes<0b000001, "fabs", fabs>;
|
|
defm FNEG : A64I_fpdp1sizes<0b000010, "fneg", fneg>;
|
|
defm FSQRT : A64I_fpdp1sizes<0b000011, "fsqrt", fsqrt>;
|
|
|
|
defm FRINTN : A64I_fpdp1sizes<0b001000, "frintn">;
|
|
defm FRINTP : A64I_fpdp1sizes<0b001001, "frintp", fceil>;
|
|
defm FRINTM : A64I_fpdp1sizes<0b001010, "frintm", ffloor>;
|
|
defm FRINTZ : A64I_fpdp1sizes<0b001011, "frintz", ftrunc>;
|
|
defm FRINTA : A64I_fpdp1sizes<0b001100, "frinta">;
|
|
defm FRINTX : A64I_fpdp1sizes<0b001110, "frintx", frint>;
|
|
defm FRINTI : A64I_fpdp1sizes<0b001111, "frinti", fnearbyint>;
|
|
|
|
// The FCVT instrucitons have different source and destination register-types,
|
|
// but the fields are uniform everywhere a D-register (say) crops up. Package
|
|
// this information in a Record.
|
|
class FCVTRegType<RegisterClass rc, bits<2> fld, ValueType vt> {
|
|
RegisterClass Class = rc;
|
|
ValueType VT = vt;
|
|
bit t1 = fld{1};
|
|
bit t0 = fld{0};
|
|
}
|
|
|
|
def FCVT16 : FCVTRegType<FPR16, 0b11, f16>;
|
|
def FCVT32 : FCVTRegType<FPR32, 0b00, f32>;
|
|
def FCVT64 : FCVTRegType<FPR64, 0b01, f64>;
|
|
|
|
class A64I_fpdp1_fcvt<FCVTRegType DestReg, FCVTRegType SrcReg, SDNode opnode>
|
|
: A64I_fpdp1<0b0, 0b0, {SrcReg.t1, SrcReg.t0},
|
|
{0,0,0,1, DestReg.t1, DestReg.t0},
|
|
(outs DestReg.Class:$Rd), (ins SrcReg.Class:$Rn),
|
|
"fcvt\t$Rd, $Rn",
|
|
[(set DestReg.VT:$Rd, (opnode SrcReg.VT:$Rn))], NoItinerary>;
|
|
|
|
def FCVTds : A64I_fpdp1_fcvt<FCVT64, FCVT32, fextend>;
|
|
def FCVThs : A64I_fpdp1_fcvt<FCVT16, FCVT32, fround>;
|
|
def FCVTsd : A64I_fpdp1_fcvt<FCVT32, FCVT64, fround>;
|
|
def FCVThd : A64I_fpdp1_fcvt<FCVT16, FCVT64, fround>;
|
|
def FCVTsh : A64I_fpdp1_fcvt<FCVT32, FCVT16, fextend>;
|
|
def FCVTdh : A64I_fpdp1_fcvt<FCVT64, FCVT16, fextend>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point data-processing (2 sources) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FMUL, FDIV, FADD, FSUB, FMAX, FMIN, FMAXNM, FMINNM, FNMUL
|
|
|
|
def FPNoBinop : PatFrag<(ops node:$lhs, node:$rhs), (fadd node:$lhs, node:$rhs),
|
|
[{ (void)N; return false; }]>;
|
|
|
|
multiclass A64I_fpdp2sizes<bits<4> opcode, string asmstr,
|
|
SDPatternOperator opnode> {
|
|
def sss : A64I_fpdp2<0b0, 0b0, 0b00, opcode,
|
|
(outs FPR32:$Rd),
|
|
(ins FPR32:$Rn, FPR32:$Rm),
|
|
!strconcat(asmstr, "\t$Rd, $Rn, $Rm"),
|
|
[(set f32:$Rd, (opnode f32:$Rn, f32:$Rm))],
|
|
NoItinerary>;
|
|
|
|
def ddd : A64I_fpdp2<0b0, 0b0, 0b01, opcode,
|
|
(outs FPR64:$Rd),
|
|
(ins FPR64:$Rn, FPR64:$Rm),
|
|
!strconcat(asmstr, "\t$Rd, $Rn, $Rm"),
|
|
[(set f64:$Rd, (opnode f64:$Rn, f64:$Rm))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
let isCommutable = 1 in {
|
|
defm FMUL : A64I_fpdp2sizes<0b0000, "fmul", fmul>;
|
|
defm FADD : A64I_fpdp2sizes<0b0010, "fadd", fadd>;
|
|
|
|
// No patterns for these.
|
|
defm FMAX : A64I_fpdp2sizes<0b0100, "fmax", FPNoBinop>;
|
|
defm FMIN : A64I_fpdp2sizes<0b0101, "fmin", FPNoBinop>;
|
|
defm FMAXNM : A64I_fpdp2sizes<0b0110, "fmaxnm", FPNoBinop>;
|
|
defm FMINNM : A64I_fpdp2sizes<0b0111, "fminnm", FPNoBinop>;
|
|
|
|
defm FNMUL : A64I_fpdp2sizes<0b1000, "fnmul",
|
|
PatFrag<(ops node:$lhs, node:$rhs),
|
|
(fneg (fmul node:$lhs, node:$rhs))> >;
|
|
}
|
|
|
|
defm FDIV : A64I_fpdp2sizes<0b0001, "fdiv", fdiv>;
|
|
defm FSUB : A64I_fpdp2sizes<0b0011, "fsub", fsub>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point data-processing (3 sources) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FMADD, FMSUB, FNMADD, FNMSUB
|
|
|
|
def fmsub : PatFrag<(ops node:$Rn, node:$Rm, node:$Ra),
|
|
(fma (fneg node:$Rn), node:$Rm, node:$Ra)>;
|
|
def fnmadd : PatFrag<(ops node:$Rn, node:$Rm, node:$Ra),
|
|
(fma node:$Rn, node:$Rm, (fneg node:$Ra))>;
|
|
def fnmsub : PatFrag<(ops node:$Rn, node:$Rm, node:$Ra),
|
|
(fma (fneg node:$Rn), node:$Rm, (fneg node:$Ra))>;
|
|
|
|
class A64I_fpdp3Impl<string asmop, RegisterClass FPR, ValueType VT,
|
|
bits<2> type, bit o1, bit o0, SDPatternOperator fmakind>
|
|
: A64I_fpdp3<0b0, 0b0, type, o1, o0, (outs FPR:$Rd),
|
|
(ins FPR:$Rn, FPR:$Rm, FPR:$Ra),
|
|
!strconcat(asmop,"\t$Rd, $Rn, $Rm, $Ra"),
|
|
[(set VT:$Rd, (fmakind VT:$Rn, VT:$Rm, VT:$Ra))],
|
|
NoItinerary>;
|
|
|
|
def FMADDssss : A64I_fpdp3Impl<"fmadd", FPR32, f32, 0b00, 0b0, 0b0, fma>;
|
|
def FMSUBssss : A64I_fpdp3Impl<"fmsub", FPR32, f32, 0b00, 0b0, 0b1, fmsub>;
|
|
def FNMADDssss : A64I_fpdp3Impl<"fnmadd", FPR32, f32, 0b00, 0b1, 0b0, fnmadd>;
|
|
def FNMSUBssss : A64I_fpdp3Impl<"fnmsub", FPR32, f32, 0b00, 0b1, 0b1, fnmsub>;
|
|
|
|
def FMADDdddd : A64I_fpdp3Impl<"fmadd", FPR64, f64, 0b01, 0b0, 0b0, fma>;
|
|
def FMSUBdddd : A64I_fpdp3Impl<"fmsub", FPR64, f64, 0b01, 0b0, 0b1, fmsub>;
|
|
def FNMADDdddd : A64I_fpdp3Impl<"fnmadd", FPR64, f64, 0b01, 0b1, 0b0, fnmadd>;
|
|
def FNMSUBdddd : A64I_fpdp3Impl<"fnmsub", FPR64, f64, 0b01, 0b1, 0b1, fnmsub>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point <-> fixed-point conversion instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FCVTZS, FCVTZU, SCVTF, UCVTF
|
|
|
|
// #1-#32 allowed, encoded as "64 - <specified imm>
|
|
def fixedpos_asmoperand_i32 : AsmOperandClass {
|
|
let Name = "CVTFixedPos32";
|
|
let RenderMethod = "addCVTFixedPosOperands";
|
|
let PredicateMethod = "isCVTFixedPos<32>";
|
|
let DiagnosticType = "CVTFixedPos32";
|
|
}
|
|
|
|
// Also encoded as "64 - <specified imm>" but #1-#64 allowed.
|
|
def fixedpos_asmoperand_i64 : AsmOperandClass {
|
|
let Name = "CVTFixedPos64";
|
|
let RenderMethod = "addCVTFixedPosOperands";
|
|
let PredicateMethod = "isCVTFixedPos<64>";
|
|
let DiagnosticType = "CVTFixedPos64";
|
|
}
|
|
|
|
// We need the cartesian product of f32/f64 i32/i64 operands for
|
|
// conversions:
|
|
// + Selection needs to use operands of correct floating type
|
|
// + Assembly parsing and decoding depend on integer width
|
|
class cvtfix_i32_op<ValueType FloatVT>
|
|
: Operand<FloatVT>,
|
|
ComplexPattern<FloatVT, 1, "SelectCVTFixedPosOperand<32>", [fpimm]> {
|
|
let ParserMatchClass = fixedpos_asmoperand_i32;
|
|
let DecoderMethod = "DecodeCVT32FixedPosOperand";
|
|
let PrintMethod = "printCVTFixedPosOperand";
|
|
}
|
|
|
|
class cvtfix_i64_op<ValueType FloatVT>
|
|
: Operand<FloatVT>,
|
|
ComplexPattern<FloatVT, 1, "SelectCVTFixedPosOperand<64>", [fpimm]> {
|
|
let ParserMatchClass = fixedpos_asmoperand_i64;
|
|
let PrintMethod = "printCVTFixedPosOperand";
|
|
}
|
|
|
|
// Because of the proliferation of weird operands, it's not really
|
|
// worth going for a multiclass here. Oh well.
|
|
|
|
class A64I_fptofix<bit sf, bits<2> type, bits<3> opcode,
|
|
RegisterClass GPR, RegisterClass FPR,
|
|
ValueType DstTy, ValueType SrcTy,
|
|
Operand scale_op, string asmop, SDNode cvtop>
|
|
: A64I_fpfixed<sf, 0b0, type, 0b11, opcode,
|
|
(outs GPR:$Rd), (ins FPR:$Rn, scale_op:$Scale),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Scale"),
|
|
[(set DstTy:$Rd, (cvtop (fmul SrcTy:$Rn, scale_op:$Scale)))],
|
|
NoItinerary>;
|
|
|
|
def FCVTZSwsi : A64I_fptofix<0b0, 0b00, 0b000, GPR32, FPR32, i32, f32,
|
|
cvtfix_i32_op<f32>, "fcvtzs", fp_to_sint>;
|
|
def FCVTZSxsi : A64I_fptofix<0b1, 0b00, 0b000, GPR64, FPR32, i64, f32,
|
|
cvtfix_i64_op<f32>, "fcvtzs", fp_to_sint>;
|
|
def FCVTZUwsi : A64I_fptofix<0b0, 0b00, 0b001, GPR32, FPR32, i32, f32,
|
|
cvtfix_i32_op<f32>, "fcvtzu", fp_to_uint>;
|
|
def FCVTZUxsi : A64I_fptofix<0b1, 0b00, 0b001, GPR64, FPR32, i64, f32,
|
|
cvtfix_i64_op<f32>, "fcvtzu", fp_to_uint>;
|
|
|
|
def FCVTZSwdi : A64I_fptofix<0b0, 0b01, 0b000, GPR32, FPR64, i32, f64,
|
|
cvtfix_i32_op<f64>, "fcvtzs", fp_to_sint>;
|
|
def FCVTZSxdi : A64I_fptofix<0b1, 0b01, 0b000, GPR64, FPR64, i64, f64,
|
|
cvtfix_i64_op<f64>, "fcvtzs", fp_to_sint>;
|
|
def FCVTZUwdi : A64I_fptofix<0b0, 0b01, 0b001, GPR32, FPR64, i32, f64,
|
|
cvtfix_i32_op<f64>, "fcvtzu", fp_to_uint>;
|
|
def FCVTZUxdi : A64I_fptofix<0b1, 0b01, 0b001, GPR64, FPR64, i64, f64,
|
|
cvtfix_i64_op<f64>, "fcvtzu", fp_to_uint>;
|
|
|
|
|
|
class A64I_fixtofp<bit sf, bits<2> type, bits<3> opcode,
|
|
RegisterClass FPR, RegisterClass GPR,
|
|
ValueType DstTy, ValueType SrcTy,
|
|
Operand scale_op, string asmop, SDNode cvtop>
|
|
: A64I_fpfixed<sf, 0b0, type, 0b00, opcode,
|
|
(outs FPR:$Rd), (ins GPR:$Rn, scale_op:$Scale),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Scale"),
|
|
[(set DstTy:$Rd, (fdiv (cvtop SrcTy:$Rn), scale_op:$Scale))],
|
|
NoItinerary>;
|
|
|
|
def SCVTFswi : A64I_fixtofp<0b0, 0b00, 0b010, FPR32, GPR32, f32, i32,
|
|
cvtfix_i32_op<f32>, "scvtf", sint_to_fp>;
|
|
def SCVTFsxi : A64I_fixtofp<0b1, 0b00, 0b010, FPR32, GPR64, f32, i64,
|
|
cvtfix_i64_op<f32>, "scvtf", sint_to_fp>;
|
|
def UCVTFswi : A64I_fixtofp<0b0, 0b00, 0b011, FPR32, GPR32, f32, i32,
|
|
cvtfix_i32_op<f32>, "ucvtf", uint_to_fp>;
|
|
def UCVTFsxi : A64I_fixtofp<0b1, 0b00, 0b011, FPR32, GPR64, f32, i64,
|
|
cvtfix_i64_op<f32>, "ucvtf", uint_to_fp>;
|
|
def SCVTFdwi : A64I_fixtofp<0b0, 0b01, 0b010, FPR64, GPR32, f64, i32,
|
|
cvtfix_i32_op<f64>, "scvtf", sint_to_fp>;
|
|
def SCVTFdxi : A64I_fixtofp<0b1, 0b01, 0b010, FPR64, GPR64, f64, i64,
|
|
cvtfix_i64_op<f64>, "scvtf", sint_to_fp>;
|
|
def UCVTFdwi : A64I_fixtofp<0b0, 0b01, 0b011, FPR64, GPR32, f64, i32,
|
|
cvtfix_i32_op<f64>, "ucvtf", uint_to_fp>;
|
|
def UCVTFdxi : A64I_fixtofp<0b1, 0b01, 0b011, FPR64, GPR64, f64, i64,
|
|
cvtfix_i64_op<f64>, "ucvtf", uint_to_fp>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point <-> integer conversion instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FCVTZS, FCVTZU, SCVTF, UCVTF
|
|
|
|
class A64I_fpintI<bit sf, bits<2> type, bits<2> rmode, bits<3> opcode,
|
|
RegisterClass DestPR, RegisterClass SrcPR, string asmop>
|
|
: A64I_fpint<sf, 0b0, type, rmode, opcode, (outs DestPR:$Rd), (ins SrcPR:$Rn),
|
|
!strconcat(asmop, "\t$Rd, $Rn"), [], NoItinerary>;
|
|
|
|
multiclass A64I_fptointRM<bits<2> rmode, bit o2, string asmop> {
|
|
def Sws : A64I_fpintI<0b0, 0b00, rmode, {o2, 0, 0},
|
|
GPR32, FPR32, asmop # "s">;
|
|
def Sxs : A64I_fpintI<0b1, 0b00, rmode, {o2, 0, 0},
|
|
GPR64, FPR32, asmop # "s">;
|
|
def Uws : A64I_fpintI<0b0, 0b00, rmode, {o2, 0, 1},
|
|
GPR32, FPR32, asmop # "u">;
|
|
def Uxs : A64I_fpintI<0b1, 0b00, rmode, {o2, 0, 1},
|
|
GPR64, FPR32, asmop # "u">;
|
|
|
|
def Swd : A64I_fpintI<0b0, 0b01, rmode, {o2, 0, 0},
|
|
GPR32, FPR64, asmop # "s">;
|
|
def Sxd : A64I_fpintI<0b1, 0b01, rmode, {o2, 0, 0},
|
|
GPR64, FPR64, asmop # "s">;
|
|
def Uwd : A64I_fpintI<0b0, 0b01, rmode, {o2, 0, 1},
|
|
GPR32, FPR64, asmop # "u">;
|
|
def Uxd : A64I_fpintI<0b1, 0b01, rmode, {o2, 0, 1},
|
|
GPR64, FPR64, asmop # "u">;
|
|
}
|
|
|
|
defm FCVTN : A64I_fptointRM<0b00, 0b0, "fcvtn">;
|
|
defm FCVTP : A64I_fptointRM<0b01, 0b0, "fcvtp">;
|
|
defm FCVTM : A64I_fptointRM<0b10, 0b0, "fcvtm">;
|
|
defm FCVTZ : A64I_fptointRM<0b11, 0b0, "fcvtz">;
|
|
defm FCVTA : A64I_fptointRM<0b00, 0b1, "fcvta">;
|
|
|
|
def : Pat<(i32 (fp_to_sint f32:$Rn)), (FCVTZSws $Rn)>;
|
|
def : Pat<(i64 (fp_to_sint f32:$Rn)), (FCVTZSxs $Rn)>;
|
|
def : Pat<(i32 (fp_to_uint f32:$Rn)), (FCVTZUws $Rn)>;
|
|
def : Pat<(i64 (fp_to_uint f32:$Rn)), (FCVTZUxs $Rn)>;
|
|
def : Pat<(i32 (fp_to_sint f64:$Rn)), (FCVTZSwd $Rn)>;
|
|
def : Pat<(i64 (fp_to_sint f64:$Rn)), (FCVTZSxd $Rn)>;
|
|
def : Pat<(i32 (fp_to_uint f64:$Rn)), (FCVTZUwd $Rn)>;
|
|
def : Pat<(i64 (fp_to_uint f64:$Rn)), (FCVTZUxd $Rn)>;
|
|
|
|
multiclass A64I_inttofp<bit o0, string asmop> {
|
|
def CVTFsw : A64I_fpintI<0b0, 0b00, 0b00, {0, 1, o0}, FPR32, GPR32, asmop>;
|
|
def CVTFsx : A64I_fpintI<0b1, 0b00, 0b00, {0, 1, o0}, FPR32, GPR64, asmop>;
|
|
def CVTFdw : A64I_fpintI<0b0, 0b01, 0b00, {0, 1, o0}, FPR64, GPR32, asmop>;
|
|
def CVTFdx : A64I_fpintI<0b1, 0b01, 0b00, {0, 1, o0}, FPR64, GPR64, asmop>;
|
|
}
|
|
|
|
defm S : A64I_inttofp<0b0, "scvtf">;
|
|
defm U : A64I_inttofp<0b1, "ucvtf">;
|
|
|
|
def : Pat<(f32 (sint_to_fp i32:$Rn)), (SCVTFsw $Rn)>;
|
|
def : Pat<(f32 (sint_to_fp i64:$Rn)), (SCVTFsx $Rn)>;
|
|
def : Pat<(f64 (sint_to_fp i32:$Rn)), (SCVTFdw $Rn)>;
|
|
def : Pat<(f64 (sint_to_fp i64:$Rn)), (SCVTFdx $Rn)>;
|
|
def : Pat<(f32 (uint_to_fp i32:$Rn)), (UCVTFsw $Rn)>;
|
|
def : Pat<(f32 (uint_to_fp i64:$Rn)), (UCVTFsx $Rn)>;
|
|
def : Pat<(f64 (uint_to_fp i32:$Rn)), (UCVTFdw $Rn)>;
|
|
def : Pat<(f64 (uint_to_fp i64:$Rn)), (UCVTFdx $Rn)>;
|
|
|
|
def FMOVws : A64I_fpintI<0b0, 0b00, 0b00, 0b110, GPR32, FPR32, "fmov">;
|
|
def FMOVsw : A64I_fpintI<0b0, 0b00, 0b00, 0b111, FPR32, GPR32, "fmov">;
|
|
def FMOVxd : A64I_fpintI<0b1, 0b01, 0b00, 0b110, GPR64, FPR64, "fmov">;
|
|
def FMOVdx : A64I_fpintI<0b1, 0b01, 0b00, 0b111, FPR64, GPR64, "fmov">;
|
|
|
|
def : Pat<(i32 (bitconvert f32:$Rn)), (FMOVws $Rn)>;
|
|
def : Pat<(f32 (bitconvert i32:$Rn)), (FMOVsw $Rn)>;
|
|
def : Pat<(i64 (bitconvert f64:$Rn)), (FMOVxd $Rn)>;
|
|
def : Pat<(f64 (bitconvert i64:$Rn)), (FMOVdx $Rn)>;
|
|
|
|
def lane1_asmoperand : AsmOperandClass {
|
|
let Name = "Lane1";
|
|
let RenderMethod = "addImmOperands";
|
|
let DiagnosticType = "Lane1";
|
|
}
|
|
|
|
def lane1 : Operand<i32> {
|
|
let ParserMatchClass = lane1_asmoperand;
|
|
let PrintMethod = "printBareImmOperand";
|
|
}
|
|
|
|
let DecoderMethod = "DecodeFMOVLaneInstruction" in {
|
|
def FMOVxv : A64I_fpint<0b1, 0b0, 0b10, 0b01, 0b110,
|
|
(outs GPR64:$Rd), (ins VPR128:$Rn, lane1:$Lane),
|
|
"fmov\t$Rd, $Rn.d[$Lane]", [], NoItinerary>;
|
|
|
|
def FMOVvx : A64I_fpint<0b1, 0b0, 0b10, 0b01, 0b111,
|
|
(outs VPR128:$Rd), (ins GPR64:$Rn, lane1:$Lane),
|
|
"fmov\t$Rd.d[$Lane], $Rn", [], NoItinerary>;
|
|
}
|
|
|
|
def : InstAlias<"fmov $Rd, $Rn.2d[$Lane]",
|
|
(FMOVxv GPR64:$Rd, VPR128:$Rn, lane1:$Lane), 0b0>;
|
|
|
|
def : InstAlias<"fmov $Rd.2d[$Lane], $Rn",
|
|
(FMOVvx VPR128:$Rd, GPR64:$Rn, lane1:$Lane), 0b0>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Floating-point immediate instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: FMOV
|
|
|
|
def fpimm_asmoperand : AsmOperandClass {
|
|
let Name = "FMOVImm";
|
|
let ParserMethod = "ParseFPImmOperand";
|
|
let DiagnosticType = "FPImm";
|
|
}
|
|
|
|
// The MCOperand for these instructions are the encoded 8-bit values.
|
|
def SDXF_fpimm : SDNodeXForm<fpimm, [{
|
|
uint32_t Imm8;
|
|
A64Imms::isFPImm(N->getValueAPF(), Imm8);
|
|
return CurDAG->getTargetConstant(Imm8, MVT::i32);
|
|
}]>;
|
|
|
|
class fmov_operand<ValueType FT>
|
|
: Operand<i32>,
|
|
PatLeaf<(FT fpimm), [{ return A64Imms::isFPImm(N->getValueAPF()); }],
|
|
SDXF_fpimm> {
|
|
let PrintMethod = "printFPImmOperand";
|
|
let ParserMatchClass = fpimm_asmoperand;
|
|
}
|
|
|
|
def fmov32_operand : fmov_operand<f32>;
|
|
def fmov64_operand : fmov_operand<f64>;
|
|
|
|
class A64I_fpimm_impl<bits<2> type, RegisterClass Reg, ValueType VT,
|
|
Operand fmov_operand>
|
|
: A64I_fpimm<0b0, 0b0, type, 0b00000,
|
|
(outs Reg:$Rd),
|
|
(ins fmov_operand:$Imm8),
|
|
"fmov\t$Rd, $Imm8",
|
|
[(set VT:$Rd, fmov_operand:$Imm8)],
|
|
NoItinerary>;
|
|
|
|
def FMOVsi : A64I_fpimm_impl<0b00, FPR32, f32, fmov32_operand>;
|
|
def FMOVdi : A64I_fpimm_impl<0b01, FPR64, f64, fmov64_operand>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-register (literal) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: LDR, LDRSW, PRFM
|
|
|
|
def ldrlit_label_asmoperand : AsmOperandClass {
|
|
let Name = "LoadLitLabel";
|
|
let RenderMethod = "addLabelOperands<19, 4>";
|
|
let DiagnosticType = "Label";
|
|
}
|
|
|
|
def ldrlit_label : Operand<i64> {
|
|
let EncoderMethod = "getLoadLitLabelOpValue";
|
|
|
|
// This label is a 19-bit offset from PC, scaled by the instruction-width: 4.
|
|
let PrintMethod = "printLabelOperand<19, 4>";
|
|
let ParserMatchClass = ldrlit_label_asmoperand;
|
|
let OperandType = "OPERAND_PCREL";
|
|
}
|
|
|
|
// Various instructions take an immediate value (which can always be used),
|
|
// where some numbers have a symbolic name to make things easier. These operands
|
|
// and the associated functions abstract away the differences.
|
|
multiclass namedimm<string prefix, string mapper> {
|
|
def _asmoperand : AsmOperandClass {
|
|
let Name = "NamedImm" # prefix;
|
|
let PredicateMethod = "isUImm";
|
|
let RenderMethod = "addImmOperands";
|
|
let ParserMethod = "ParseNamedImmOperand<" # mapper # ">";
|
|
let DiagnosticType = "NamedImm_" # prefix;
|
|
}
|
|
|
|
def _op : Operand<i32> {
|
|
let ParserMatchClass = !cast<AsmOperandClass>(prefix # "_asmoperand");
|
|
let PrintMethod = "printNamedImmOperand<" # mapper # ">";
|
|
let DecoderMethod = "DecodeNamedImmOperand<" # mapper # ">";
|
|
}
|
|
}
|
|
|
|
defm prefetch : namedimm<"prefetch", "A64PRFM::PRFMMapper">;
|
|
|
|
class A64I_LDRlitSimple<bits<2> opc, bit v, RegisterClass OutReg,
|
|
list<dag> patterns = []>
|
|
: A64I_LDRlit<opc, v, (outs OutReg:$Rt), (ins ldrlit_label:$Imm19),
|
|
"ldr\t$Rt, $Imm19", patterns, NoItinerary>;
|
|
|
|
let mayLoad = 1 in {
|
|
def LDRw_lit : A64I_LDRlitSimple<0b00, 0b0, GPR32>;
|
|
def LDRx_lit : A64I_LDRlitSimple<0b01, 0b0, GPR64>;
|
|
}
|
|
|
|
def LDRs_lit : A64I_LDRlitSimple<0b00, 0b1, FPR32>;
|
|
def LDRd_lit : A64I_LDRlitSimple<0b01, 0b1, FPR64>;
|
|
|
|
let mayLoad = 1 in {
|
|
def LDRq_lit : A64I_LDRlitSimple<0b10, 0b1, FPR128>;
|
|
|
|
|
|
def LDRSWx_lit : A64I_LDRlit<0b10, 0b0,
|
|
(outs GPR64:$Rt),
|
|
(ins ldrlit_label:$Imm19),
|
|
"ldrsw\t$Rt, $Imm19",
|
|
[], NoItinerary>;
|
|
|
|
def PRFM_lit : A64I_LDRlit<0b11, 0b0,
|
|
(outs), (ins prefetch_op:$Rt, ldrlit_label:$Imm19),
|
|
"prfm\t$Rt, $Imm19",
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store exclusive instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: STXRB, STXRH, STXR, LDXRB, LDXRH, LDXR. STXP, LDXP, STLXRB,
|
|
// STLXRH, STLXR, LDAXRB, LDAXRH, LDAXR, STLXP, LDAXP, STLRB,
|
|
// STLRH, STLR, LDARB, LDARH, LDAR
|
|
|
|
// Since these instructions have the undefined register bits set to 1 in
|
|
// their canonical form, we need a post encoder method to set those bits
|
|
// to 1 when encoding these instructions. We do this using the
|
|
// fixLoadStoreExclusive function. This function has template parameters:
|
|
//
|
|
// fixLoadStoreExclusive<int hasRs, int hasRt2>
|
|
//
|
|
// hasRs indicates that the instruction uses the Rs field, so we won't set
|
|
// it to 1 (and the same for Rt2). We don't need template parameters for
|
|
// the other register fiels since Rt and Rn are always used.
|
|
|
|
// This operand parses a GPR64xsp register, followed by an optional immediate
|
|
// #0.
|
|
def GPR64xsp0_asmoperand : AsmOperandClass {
|
|
let Name = "GPR64xsp0";
|
|
let PredicateMethod = "isWrappedReg";
|
|
let RenderMethod = "addRegOperands";
|
|
let ParserMethod = "ParseLSXAddressOperand";
|
|
// Diagnostics are provided by ParserMethod
|
|
}
|
|
|
|
def GPR64xsp0 : RegisterOperand<GPR64xsp> {
|
|
let ParserMatchClass = GPR64xsp0_asmoperand;
|
|
}
|
|
|
|
//===----------------------------------
|
|
// Store-exclusive (releasing & normal)
|
|
//===----------------------------------
|
|
|
|
class A64I_SRexs_impl<bits<2> size, bits<3> opcode, string asm, dag outs,
|
|
dag ins, list<dag> pat,
|
|
InstrItinClass itin> :
|
|
A64I_LDSTex_stn <size,
|
|
opcode{2}, 0, opcode{1}, opcode{0},
|
|
outs, ins,
|
|
!strconcat(asm, "\t$Rs, $Rt, [$Rn]"),
|
|
pat, itin> {
|
|
let mayStore = 1;
|
|
let PostEncoderMethod = "fixLoadStoreExclusive<1,0>";
|
|
}
|
|
|
|
multiclass A64I_SRex<string asmstr, bits<3> opcode, string prefix> {
|
|
def _byte: A64I_SRexs_impl<0b00, opcode, !strconcat(asmstr, "b"),
|
|
(outs GPR32:$Rs), (ins GPR32:$Rt, GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
|
|
def _hword: A64I_SRexs_impl<0b01, opcode, !strconcat(asmstr, "h"),
|
|
(outs GPR32:$Rs), (ins GPR32:$Rt, GPR64xsp0:$Rn),
|
|
[],NoItinerary>;
|
|
|
|
def _word: A64I_SRexs_impl<0b10, opcode, asmstr,
|
|
(outs GPR32:$Rs), (ins GPR32:$Rt, GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
|
|
def _dword: A64I_SRexs_impl<0b11, opcode, asmstr,
|
|
(outs GPR32:$Rs), (ins GPR64:$Rt, GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
defm STXR : A64I_SRex<"stxr", 0b000, "STXR">;
|
|
defm STLXR : A64I_SRex<"stlxr", 0b001, "STLXR">;
|
|
|
|
//===----------------------------------
|
|
// Loads
|
|
//===----------------------------------
|
|
|
|
class A64I_LRexs_impl<bits<2> size, bits<3> opcode, string asm, dag outs,
|
|
dag ins, list<dag> pat,
|
|
InstrItinClass itin> :
|
|
A64I_LDSTex_tn <size,
|
|
opcode{2}, 1, opcode{1}, opcode{0},
|
|
outs, ins,
|
|
!strconcat(asm, "\t$Rt, [$Rn]"),
|
|
pat, itin> {
|
|
let mayLoad = 1;
|
|
let PostEncoderMethod = "fixLoadStoreExclusive<0,0>";
|
|
}
|
|
|
|
multiclass A64I_LRex<string asmstr, bits<3> opcode> {
|
|
def _byte: A64I_LRexs_impl<0b00, opcode, !strconcat(asmstr, "b"),
|
|
(outs GPR32:$Rt), (ins GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
|
|
def _hword: A64I_LRexs_impl<0b01, opcode, !strconcat(asmstr, "h"),
|
|
(outs GPR32:$Rt), (ins GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
|
|
def _word: A64I_LRexs_impl<0b10, opcode, asmstr,
|
|
(outs GPR32:$Rt), (ins GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
|
|
def _dword: A64I_LRexs_impl<0b11, opcode, asmstr,
|
|
(outs GPR64:$Rt), (ins GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
defm LDXR : A64I_LRex<"ldxr", 0b000>;
|
|
defm LDAXR : A64I_LRex<"ldaxr", 0b001>;
|
|
defm LDAR : A64I_LRex<"ldar", 0b101>;
|
|
|
|
class acquiring_load<PatFrag base>
|
|
: PatFrag<(ops node:$ptr), (base node:$ptr), [{
|
|
AtomicOrdering Ordering = cast<AtomicSDNode>(N)->getOrdering();
|
|
return Ordering == Acquire || Ordering == SequentiallyConsistent;
|
|
}]>;
|
|
|
|
def atomic_load_acquire_8 : acquiring_load<atomic_load_8>;
|
|
def atomic_load_acquire_16 : acquiring_load<atomic_load_16>;
|
|
def atomic_load_acquire_32 : acquiring_load<atomic_load_32>;
|
|
def atomic_load_acquire_64 : acquiring_load<atomic_load_64>;
|
|
|
|
def : Pat<(atomic_load_acquire_8 i64:$Rn), (LDAR_byte $Rn)>;
|
|
def : Pat<(atomic_load_acquire_16 i64:$Rn), (LDAR_hword $Rn)>;
|
|
def : Pat<(atomic_load_acquire_32 i64:$Rn), (LDAR_word $Rn)>;
|
|
def : Pat<(atomic_load_acquire_64 i64:$Rn), (LDAR_dword $Rn)>;
|
|
|
|
//===----------------------------------
|
|
// Store-release (no exclusivity)
|
|
//===----------------------------------
|
|
|
|
class A64I_SLexs_impl<bits<2> size, bits<3> opcode, string asm, dag outs,
|
|
dag ins, list<dag> pat,
|
|
InstrItinClass itin> :
|
|
A64I_LDSTex_tn <size,
|
|
opcode{2}, 0, opcode{1}, opcode{0},
|
|
outs, ins,
|
|
!strconcat(asm, "\t$Rt, [$Rn]"),
|
|
pat, itin> {
|
|
let mayStore = 1;
|
|
let PostEncoderMethod = "fixLoadStoreExclusive<0,0>";
|
|
}
|
|
|
|
class releasing_store<PatFrag base>
|
|
: PatFrag<(ops node:$ptr, node:$val), (base node:$ptr, node:$val), [{
|
|
AtomicOrdering Ordering = cast<AtomicSDNode>(N)->getOrdering();
|
|
return Ordering == Release || Ordering == SequentiallyConsistent;
|
|
}]>;
|
|
|
|
def atomic_store_release_8 : releasing_store<atomic_store_8>;
|
|
def atomic_store_release_16 : releasing_store<atomic_store_16>;
|
|
def atomic_store_release_32 : releasing_store<atomic_store_32>;
|
|
def atomic_store_release_64 : releasing_store<atomic_store_64>;
|
|
|
|
multiclass A64I_SLex<string asmstr, bits<3> opcode, string prefix> {
|
|
def _byte: A64I_SLexs_impl<0b00, opcode, !strconcat(asmstr, "b"),
|
|
(outs), (ins GPR32:$Rt, GPR64xsp0:$Rn),
|
|
[(atomic_store_release_8 i64:$Rn, i32:$Rt)],
|
|
NoItinerary>;
|
|
|
|
def _hword: A64I_SLexs_impl<0b01, opcode, !strconcat(asmstr, "h"),
|
|
(outs), (ins GPR32:$Rt, GPR64xsp0:$Rn),
|
|
[(atomic_store_release_16 i64:$Rn, i32:$Rt)],
|
|
NoItinerary>;
|
|
|
|
def _word: A64I_SLexs_impl<0b10, opcode, asmstr,
|
|
(outs), (ins GPR32:$Rt, GPR64xsp0:$Rn),
|
|
[(atomic_store_release_32 i64:$Rn, i32:$Rt)],
|
|
NoItinerary>;
|
|
|
|
def _dword: A64I_SLexs_impl<0b11, opcode, asmstr,
|
|
(outs), (ins GPR64:$Rt, GPR64xsp0:$Rn),
|
|
[(atomic_store_release_64 i64:$Rn, i64:$Rt)],
|
|
NoItinerary>;
|
|
}
|
|
|
|
defm STLR : A64I_SLex<"stlr", 0b101, "STLR">;
|
|
|
|
//===----------------------------------
|
|
// Store-exclusive pair (releasing & normal)
|
|
//===----------------------------------
|
|
|
|
class A64I_SPexs_impl<bits<2> size, bits<3> opcode, string asm, dag outs,
|
|
dag ins, list<dag> pat,
|
|
InstrItinClass itin> :
|
|
A64I_LDSTex_stt2n <size,
|
|
opcode{2}, 0, opcode{1}, opcode{0},
|
|
outs, ins,
|
|
!strconcat(asm, "\t$Rs, $Rt, $Rt2, [$Rn]"),
|
|
pat, itin> {
|
|
let mayStore = 1;
|
|
}
|
|
|
|
|
|
multiclass A64I_SPex<string asmstr, bits<3> opcode> {
|
|
def _word: A64I_SPexs_impl<0b10, opcode, asmstr, (outs),
|
|
(ins GPR32:$Rs, GPR32:$Rt, GPR32:$Rt2,
|
|
GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
|
|
def _dword: A64I_SPexs_impl<0b11, opcode, asmstr, (outs),
|
|
(ins GPR32:$Rs, GPR64:$Rt, GPR64:$Rt2,
|
|
GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
defm STXP : A64I_SPex<"stxp", 0b010>;
|
|
defm STLXP : A64I_SPex<"stlxp", 0b011>;
|
|
|
|
//===----------------------------------
|
|
// Load-exclusive pair (acquiring & normal)
|
|
//===----------------------------------
|
|
|
|
class A64I_LPexs_impl<bits<2> size, bits<3> opcode, string asm, dag outs,
|
|
dag ins, list<dag> pat,
|
|
InstrItinClass itin> :
|
|
A64I_LDSTex_tt2n <size,
|
|
opcode{2}, 1, opcode{1}, opcode{0},
|
|
outs, ins,
|
|
!strconcat(asm, "\t$Rt, $Rt2, [$Rn]"),
|
|
pat, itin>{
|
|
let mayLoad = 1;
|
|
let DecoderMethod = "DecodeLoadPairExclusiveInstruction";
|
|
let PostEncoderMethod = "fixLoadStoreExclusive<0,1>";
|
|
}
|
|
|
|
multiclass A64I_LPex<string asmstr, bits<3> opcode> {
|
|
def _word: A64I_LPexs_impl<0b10, opcode, asmstr,
|
|
(outs GPR32:$Rt, GPR32:$Rt2),
|
|
(ins GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
|
|
def _dword: A64I_LPexs_impl<0b11, opcode, asmstr,
|
|
(outs GPR64:$Rt, GPR64:$Rt2),
|
|
(ins GPR64xsp0:$Rn),
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
defm LDXP : A64I_LPex<"ldxp", 0b010>;
|
|
defm LDAXP : A64I_LPex<"ldaxp", 0b011>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register (unscaled immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: LDURB, LDURH, LDRUSB, LDRUSH, LDRUSW, STUR, STURB, STURH and PRFUM
|
|
//
|
|
// and
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register (register offset) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: LDRB, LDRH, LDRSB, LDRSH, LDRSW, STR, STRB, STRH and PRFM
|
|
//
|
|
// and
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register (unsigned immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: LDRB, LDRH, LDRSB, LDRSH, LDRSW, STR, STRB, STRH and PRFM
|
|
//
|
|
// and
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register (immediate post-indexed) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: STRB, STRH, STR, LDRB, LDRH, LDR, LDRSB, LDRSH, LDRSW
|
|
//
|
|
// and
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register (immediate pre-indexed) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: STRB, STRH, STR, LDRB, LDRH, LDR, LDRSB, LDRSH, LDRSW
|
|
|
|
// Note that patterns are much later on in a completely separate section (they
|
|
// need ADRPxi to be defined).
|
|
|
|
//===-------------------------------
|
|
// 1. Various operands needed
|
|
//===-------------------------------
|
|
|
|
//===-------------------------------
|
|
// 1.1 Unsigned 12-bit immediate operands
|
|
//===-------------------------------
|
|
// The addressing mode for these instructions consists of an unsigned 12-bit
|
|
// immediate which is scaled by the size of the memory access.
|
|
//
|
|
// We represent this in the MC layer by two operands:
|
|
// 1. A base register.
|
|
// 2. A 12-bit immediate: not multiplied by access size, so "LDR x0,[x0,#8]"
|
|
// would have '1' in this field.
|
|
// This means that separate functions are needed for converting representations
|
|
// which *are* aware of the intended access size.
|
|
|
|
// Anything that creates an MCInst (Decoding, selection and AsmParsing) has to
|
|
// know the access size via some means. An isolated operand does not have this
|
|
// information unless told from here, which means we need separate tablegen
|
|
// Operands for each access size. This multiclass takes care of instantiating
|
|
// the correct template functions in the rest of the backend.
|
|
|
|
//===-------------------------------
|
|
// 1.1 Unsigned 12-bit immediate operands
|
|
//===-------------------------------
|
|
|
|
multiclass offsets_uimm12<int MemSize, string prefix> {
|
|
def uimm12_asmoperand : AsmOperandClass {
|
|
let Name = "OffsetUImm12_" # MemSize;
|
|
let PredicateMethod = "isOffsetUImm12<" # MemSize # ">";
|
|
let RenderMethod = "addOffsetUImm12Operands<" # MemSize # ">";
|
|
let DiagnosticType = "LoadStoreUImm12_" # MemSize;
|
|
}
|
|
|
|
// Pattern is really no more than an ImmLeaf, but predicated on MemSize which
|
|
// complicates things beyond TableGen's ken.
|
|
def uimm12 : Operand<i64>,
|
|
ComplexPattern<i64, 1, "SelectOffsetUImm12<" # MemSize # ">"> {
|
|
let ParserMatchClass
|
|
= !cast<AsmOperandClass>(prefix # uimm12_asmoperand);
|
|
|
|
let PrintMethod = "printOffsetUImm12Operand<" # MemSize # ">";
|
|
let EncoderMethod = "getOffsetUImm12OpValue<" # MemSize # ">";
|
|
}
|
|
}
|
|
|
|
defm byte_ : offsets_uimm12<1, "byte_">;
|
|
defm hword_ : offsets_uimm12<2, "hword_">;
|
|
defm word_ : offsets_uimm12<4, "word_">;
|
|
defm dword_ : offsets_uimm12<8, "dword_">;
|
|
defm qword_ : offsets_uimm12<16, "qword_">;
|
|
|
|
//===-------------------------------
|
|
// 1.1 Signed 9-bit immediate operands
|
|
//===-------------------------------
|
|
|
|
// The MCInst is expected to store the bit-wise encoding of the value,
|
|
// which amounts to lopping off the extended sign bits.
|
|
def SDXF_simm9 : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(N->getZExtValue() & 0x1ff, MVT::i32);
|
|
}]>;
|
|
|
|
def simm9_asmoperand : AsmOperandClass {
|
|
let Name = "SImm9";
|
|
let PredicateMethod = "isSImm<9>";
|
|
let RenderMethod = "addSImmOperands<9>";
|
|
let DiagnosticType = "LoadStoreSImm9";
|
|
}
|
|
|
|
def simm9 : Operand<i64>,
|
|
ImmLeaf<i64, [{ return Imm >= -0x100 && Imm <= 0xff; }],
|
|
SDXF_simm9> {
|
|
let PrintMethod = "printOffsetSImm9Operand";
|
|
let ParserMatchClass = simm9_asmoperand;
|
|
}
|
|
|
|
|
|
//===-------------------------------
|
|
// 1.3 Register offset extensions
|
|
//===-------------------------------
|
|
|
|
// The assembly-syntax for these addressing-modes is:
|
|
// [<Xn|SP>, <R><m> {, <extend> {<amount>}}]
|
|
//
|
|
// The essential semantics are:
|
|
// + <amount> is a shift: #<log(transfer size)> or #0
|
|
// + <R> can be W or X.
|
|
// + If <R> is W, <extend> can be UXTW or SXTW
|
|
// + If <R> is X, <extend> can be LSL or SXTX
|
|
//
|
|
// The trickiest of those constraints is that Rm can be either GPR32 or GPR64,
|
|
// which will need separate instructions for LLVM type-consistency. We'll also
|
|
// need separate operands, of course.
|
|
multiclass regexts<int MemSize, int RmSize, RegisterClass GPR,
|
|
string Rm, string prefix> {
|
|
def regext_asmoperand : AsmOperandClass {
|
|
let Name = "AddrRegExtend_" # MemSize # "_" # Rm;
|
|
let PredicateMethod = "isAddrRegExtend<" # MemSize # "," # RmSize # ">";
|
|
let RenderMethod = "addAddrRegExtendOperands<" # MemSize # ">";
|
|
let DiagnosticType = "LoadStoreExtend" # RmSize # "_" # MemSize;
|
|
}
|
|
|
|
def regext : Operand<i64> {
|
|
let PrintMethod
|
|
= "printAddrRegExtendOperand<" # MemSize # ", " # RmSize # ">";
|
|
|
|
let DecoderMethod = "DecodeAddrRegExtendOperand";
|
|
let ParserMatchClass
|
|
= !cast<AsmOperandClass>(prefix # regext_asmoperand);
|
|
}
|
|
}
|
|
|
|
multiclass regexts_wx<int MemSize, string prefix> {
|
|
// Rm is an X-register if LSL or SXTX are specified as the shift.
|
|
defm Xm_ : regexts<MemSize, 64, GPR64, "Xm", prefix # "Xm_">;
|
|
|
|
// Rm is a W-register if UXTW or SXTW are specified as the shift.
|
|
defm Wm_ : regexts<MemSize, 32, GPR32, "Wm", prefix # "Wm_">;
|
|
}
|
|
|
|
defm byte_ : regexts_wx<1, "byte_">;
|
|
defm hword_ : regexts_wx<2, "hword_">;
|
|
defm word_ : regexts_wx<4, "word_">;
|
|
defm dword_ : regexts_wx<8, "dword_">;
|
|
defm qword_ : regexts_wx<16, "qword_">;
|
|
|
|
|
|
//===------------------------------
|
|
// 2. The instructions themselves.
|
|
//===------------------------------
|
|
|
|
// We have the following instructions to implement:
|
|
// | | B | H | W | X |
|
|
// |-----------------+-------+-------+-------+--------|
|
|
// | unsigned str | STRB | STRH | STR | STR |
|
|
// | unsigned ldr | LDRB | LDRH | LDR | LDR |
|
|
// | signed ldr to W | LDRSB | LDRSH | - | - |
|
|
// | signed ldr to X | LDRSB | LDRSH | LDRSW | (PRFM) |
|
|
|
|
// This will instantiate the LDR/STR instructions you'd expect to use for an
|
|
// unsigned datatype (first two rows above) or floating-point register, which is
|
|
// reasonably uniform across all access sizes.
|
|
|
|
|
|
//===------------------------------
|
|
// 2.1 Regular instructions
|
|
//===------------------------------
|
|
|
|
// This class covers the basic unsigned or irrelevantly-signed loads and stores,
|
|
// to general-purpose and floating-point registers.
|
|
|
|
class AddrParams<string prefix> {
|
|
Operand uimm12 = !cast<Operand>(prefix # "_uimm12");
|
|
|
|
Operand regextWm = !cast<Operand>(prefix # "_Wm_regext");
|
|
Operand regextXm = !cast<Operand>(prefix # "_Xm_regext");
|
|
}
|
|
|
|
def byte_addrparams : AddrParams<"byte">;
|
|
def hword_addrparams : AddrParams<"hword">;
|
|
def word_addrparams : AddrParams<"word">;
|
|
def dword_addrparams : AddrParams<"dword">;
|
|
def qword_addrparams : AddrParams<"qword">;
|
|
|
|
multiclass A64I_LDRSTR_unsigned<string prefix, bits<2> size, bit v,
|
|
bit high_opc, string asmsuffix,
|
|
RegisterClass GPR, AddrParams params> {
|
|
// Unsigned immediate
|
|
def _STR : A64I_LSunsigimm<size, v, {high_opc, 0b0},
|
|
(outs), (ins GPR:$Rt, GPR64xsp:$Rn, params.uimm12:$UImm12),
|
|
"str" # asmsuffix # "\t$Rt, [$Rn, $UImm12]",
|
|
[], NoItinerary> {
|
|
let mayStore = 1;
|
|
}
|
|
def : InstAlias<"str" # asmsuffix # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_STR") GPR:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
def _LDR : A64I_LSunsigimm<size, v, {high_opc, 0b1},
|
|
(outs GPR:$Rt), (ins GPR64xsp:$Rn, params.uimm12:$UImm12),
|
|
"ldr" # asmsuffix # "\t$Rt, [$Rn, $UImm12]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"ldr" # asmsuffix # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_LDR") GPR:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
// Register offset (four of these: load/store and Wm/Xm).
|
|
let mayLoad = 1 in {
|
|
def _Wm_RegOffset_LDR : A64I_LSregoff<size, v, {high_opc, 0b1}, 0b0,
|
|
(outs GPR:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR32:$Rm, params.regextWm:$Ext),
|
|
"ldr" # asmsuffix # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
|
|
def _Xm_RegOffset_LDR : A64I_LSregoff<size, v, {high_opc, 0b1}, 0b1,
|
|
(outs GPR:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR64:$Rm, params.regextXm:$Ext),
|
|
"ldr" # asmsuffix # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
}
|
|
def : InstAlias<"ldr" # asmsuffix # " $Rt, [$Rn, $Rm]",
|
|
(!cast<Instruction>(prefix # "_Xm_RegOffset_LDR") GPR:$Rt, GPR64xsp:$Rn,
|
|
GPR64:$Rm, 2)>;
|
|
|
|
let mayStore = 1 in {
|
|
def _Wm_RegOffset_STR : A64I_LSregoff<size, v, {high_opc, 0b0}, 0b0,
|
|
(outs), (ins GPR:$Rt, GPR64xsp:$Rn, GPR32:$Rm,
|
|
params.regextWm:$Ext),
|
|
"str" # asmsuffix # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
|
|
def _Xm_RegOffset_STR : A64I_LSregoff<size, v, {high_opc, 0b0}, 0b1,
|
|
(outs), (ins GPR:$Rt, GPR64xsp:$Rn, GPR64:$Rm,
|
|
params.regextXm:$Ext),
|
|
"str" # asmsuffix # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
}
|
|
def : InstAlias<"str" # asmsuffix # " $Rt, [$Rn, $Rm]",
|
|
(!cast<Instruction>(prefix # "_Xm_RegOffset_STR") GPR:$Rt, GPR64xsp:$Rn,
|
|
GPR64:$Rm, 2)>;
|
|
|
|
// Unaligned immediate
|
|
def _STUR : A64I_LSunalimm<size, v, {high_opc, 0b0},
|
|
(outs), (ins GPR:$Rt, GPR64xsp:$Rn, simm9:$SImm9),
|
|
"stur" # asmsuffix # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary> {
|
|
let mayStore = 1;
|
|
}
|
|
def : InstAlias<"stur" # asmsuffix # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_STUR") GPR:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
def _LDUR : A64I_LSunalimm<size, v, {high_opc, 0b1},
|
|
(outs GPR:$Rt), (ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldur" # asmsuffix # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"ldur" # asmsuffix # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_LDUR") GPR:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
// Post-indexed
|
|
def _PostInd_STR : A64I_LSpostind<size, v, {high_opc, 0b0},
|
|
(outs GPR64xsp:$Rn_wb),
|
|
(ins GPR:$Rt, GPR64xsp:$Rn, simm9:$SImm9),
|
|
"str" # asmsuffix # "\t$Rt, [$Rn], $SImm9",
|
|
[], NoItinerary> {
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let mayStore = 1;
|
|
|
|
// Decoder only needed for unpredictability checking (FIXME).
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
def _PostInd_LDR : A64I_LSpostind<size, v, {high_opc, 0b1},
|
|
(outs GPR:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldr" # asmsuffix # "\t$Rt, [$Rn], $SImm9",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
// Pre-indexed
|
|
def _PreInd_STR : A64I_LSpreind<size, v, {high_opc, 0b0},
|
|
(outs GPR64xsp:$Rn_wb),
|
|
(ins GPR:$Rt, GPR64xsp:$Rn, simm9:$SImm9),
|
|
"str" # asmsuffix # "\t$Rt, [$Rn, $SImm9]!",
|
|
[], NoItinerary> {
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let mayStore = 1;
|
|
|
|
// Decoder only needed for unpredictability checking (FIXME).
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
def _PreInd_LDR : A64I_LSpreind<size, v, {high_opc, 0b1},
|
|
(outs GPR:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldr" # asmsuffix # "\t$Rt, [$Rn, $SImm9]!",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
}
|
|
|
|
// STRB/LDRB: First define the instructions
|
|
defm LS8
|
|
: A64I_LDRSTR_unsigned<"LS8", 0b00, 0b0, 0b0, "b", GPR32, byte_addrparams>;
|
|
|
|
// STRH/LDRH
|
|
defm LS16
|
|
: A64I_LDRSTR_unsigned<"LS16", 0b01, 0b0, 0b0, "h", GPR32, hword_addrparams>;
|
|
|
|
|
|
// STR/LDR to/from a W register
|
|
defm LS32
|
|
: A64I_LDRSTR_unsigned<"LS32", 0b10, 0b0, 0b0, "", GPR32, word_addrparams>;
|
|
|
|
// STR/LDR to/from an X register
|
|
defm LS64
|
|
: A64I_LDRSTR_unsigned<"LS64", 0b11, 0b0, 0b0, "", GPR64, dword_addrparams>;
|
|
|
|
// STR/LDR to/from a B register
|
|
defm LSFP8
|
|
: A64I_LDRSTR_unsigned<"LSFP8", 0b00, 0b1, 0b0, "", FPR8, byte_addrparams>;
|
|
|
|
// STR/LDR to/from an H register
|
|
defm LSFP16
|
|
: A64I_LDRSTR_unsigned<"LSFP16", 0b01, 0b1, 0b0, "", FPR16, hword_addrparams>;
|
|
|
|
// STR/LDR to/from an S register
|
|
defm LSFP32
|
|
: A64I_LDRSTR_unsigned<"LSFP32", 0b10, 0b1, 0b0, "", FPR32, word_addrparams>;
|
|
// STR/LDR to/from a D register
|
|
defm LSFP64
|
|
: A64I_LDRSTR_unsigned<"LSFP64", 0b11, 0b1, 0b0, "", FPR64, dword_addrparams>;
|
|
// STR/LDR to/from a Q register
|
|
defm LSFP128
|
|
: A64I_LDRSTR_unsigned<"LSFP128", 0b00, 0b1, 0b1, "", FPR128,
|
|
qword_addrparams>;
|
|
|
|
//===------------------------------
|
|
// 2.3 Signed loads
|
|
//===------------------------------
|
|
|
|
// Byte and half-word signed loads can both go into either an X or a W register,
|
|
// so it's worth factoring out. Signed word loads don't fit because there is no
|
|
// W version.
|
|
multiclass A64I_LDR_signed<bits<2> size, string asmopcode, AddrParams params,
|
|
string prefix> {
|
|
// Unsigned offset
|
|
def w : A64I_LSunsigimm<size, 0b0, 0b11,
|
|
(outs GPR32:$Rt),
|
|
(ins GPR64xsp:$Rn, params.uimm12:$UImm12),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $UImm12]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"ldrs" # asmopcode # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # w) GPR32:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
def x : A64I_LSunsigimm<size, 0b0, 0b10,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, params.uimm12:$UImm12),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $UImm12]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"ldrs" # asmopcode # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # x) GPR64:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
// Register offset
|
|
let mayLoad = 1 in {
|
|
def w_Wm_RegOffset : A64I_LSregoff<size, 0b0, 0b11, 0b0,
|
|
(outs GPR32:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR32:$Rm, params.regextWm:$Ext),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
|
|
def w_Xm_RegOffset : A64I_LSregoff<size, 0b0, 0b11, 0b1,
|
|
(outs GPR32:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR64:$Rm, params.regextXm:$Ext),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
|
|
def x_Wm_RegOffset : A64I_LSregoff<size, 0b0, 0b10, 0b0,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR32:$Rm, params.regextWm:$Ext),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
|
|
def x_Xm_RegOffset : A64I_LSregoff<size, 0b0, 0b10, 0b1,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR64:$Rm, params.regextXm:$Ext),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
}
|
|
def : InstAlias<"ldrs" # asmopcode # " $Rt, [$Rn, $Rm]",
|
|
(!cast<Instruction>(prefix # "w_Xm_RegOffset") GPR32:$Rt, GPR64xsp:$Rn,
|
|
GPR64:$Rm, 2)>;
|
|
|
|
def : InstAlias<"ldrs" # asmopcode # " $Rt, [$Rn, $Rm]",
|
|
(!cast<Instruction>(prefix # "x_Xm_RegOffset") GPR64:$Rt, GPR64xsp:$Rn,
|
|
GPR64:$Rm, 2)>;
|
|
|
|
|
|
let mayLoad = 1 in {
|
|
// Unaligned offset
|
|
def w_U : A64I_LSunalimm<size, 0b0, 0b11,
|
|
(outs GPR32:$Rt),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldurs" # asmopcode # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary>;
|
|
|
|
def x_U : A64I_LSunalimm<size, 0b0, 0b10,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldurs" # asmopcode # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary>;
|
|
|
|
|
|
// Post-indexed
|
|
def w_PostInd : A64I_LSpostind<size, 0b0, 0b11,
|
|
(outs GPR32:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn], $SImm9",
|
|
[], NoItinerary> {
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
def x_PostInd : A64I_LSpostind<size, 0b0, 0b10,
|
|
(outs GPR64:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn], $SImm9",
|
|
[], NoItinerary> {
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
// Pre-indexed
|
|
def w_PreInd : A64I_LSpreind<size, 0b0, 0b11,
|
|
(outs GPR32:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $SImm9]!",
|
|
[], NoItinerary> {
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
def x_PreInd : A64I_LSpreind<size, 0b0, 0b10,
|
|
(outs GPR64:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldrs" # asmopcode # "\t$Rt, [$Rn, $SImm9]!",
|
|
[], NoItinerary> {
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
} // let mayLoad = 1
|
|
}
|
|
|
|
// LDRSB
|
|
defm LDRSB : A64I_LDR_signed<0b00, "b", byte_addrparams, "LDRSB">;
|
|
// LDRSH
|
|
defm LDRSH : A64I_LDR_signed<0b01, "h", hword_addrparams, "LDRSH">;
|
|
|
|
// LDRSW: load a 32-bit register, sign-extending to 64-bits.
|
|
def LDRSWx
|
|
: A64I_LSunsigimm<0b10, 0b0, 0b10,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, word_uimm12:$UImm12),
|
|
"ldrsw\t$Rt, [$Rn, $UImm12]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"ldrsw $Rt, [$Rn]", (LDRSWx GPR64:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
let mayLoad = 1 in {
|
|
def LDRSWx_Wm_RegOffset : A64I_LSregoff<0b10, 0b0, 0b10, 0b0,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR32:$Rm, word_Wm_regext:$Ext),
|
|
"ldrsw\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
|
|
def LDRSWx_Xm_RegOffset : A64I_LSregoff<0b10, 0b0, 0b10, 0b1,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, GPR64:$Rm, word_Xm_regext:$Ext),
|
|
"ldrsw\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
}
|
|
def : InstAlias<"ldrsw $Rt, [$Rn, $Rm]",
|
|
(LDRSWx_Xm_RegOffset GPR64:$Rt, GPR64xsp:$Rn, GPR64:$Rm, 2)>;
|
|
|
|
|
|
def LDURSWx
|
|
: A64I_LSunalimm<0b10, 0b0, 0b10,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldursw\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"ldursw $Rt, [$Rn]", (LDURSWx GPR64:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
def LDRSWx_PostInd
|
|
: A64I_LSpostind<0b10, 0b0, 0b10,
|
|
(outs GPR64:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldrsw\t$Rt, [$Rn], $SImm9",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
def LDRSWx_PreInd : A64I_LSpreind<0b10, 0b0, 0b10,
|
|
(outs GPR64:$Rt, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldrsw\t$Rt, [$Rn, $SImm9]!",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeSingleIndexedInstruction";
|
|
}
|
|
|
|
//===------------------------------
|
|
// 2.4 Prefetch operations
|
|
//===------------------------------
|
|
|
|
def PRFM : A64I_LSunsigimm<0b11, 0b0, 0b10, (outs),
|
|
(ins prefetch_op:$Rt, GPR64xsp:$Rn, dword_uimm12:$UImm12),
|
|
"prfm\t$Rt, [$Rn, $UImm12]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"prfm $Rt, [$Rn]",
|
|
(PRFM prefetch_op:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
let mayLoad = 1 in {
|
|
def PRFM_Wm_RegOffset : A64I_LSregoff<0b11, 0b0, 0b10, 0b0, (outs),
|
|
(ins prefetch_op:$Rt, GPR64xsp:$Rn,
|
|
GPR32:$Rm, dword_Wm_regext:$Ext),
|
|
"prfm\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
def PRFM_Xm_RegOffset : A64I_LSregoff<0b11, 0b0, 0b10, 0b1, (outs),
|
|
(ins prefetch_op:$Rt, GPR64xsp:$Rn,
|
|
GPR64:$Rm, dword_Xm_regext:$Ext),
|
|
"prfm\t$Rt, [$Rn, $Rm, $Ext]",
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
def : InstAlias<"prfm $Rt, [$Rn, $Rm]",
|
|
(PRFM_Xm_RegOffset prefetch_op:$Rt, GPR64xsp:$Rn,
|
|
GPR64:$Rm, 2)>;
|
|
|
|
|
|
def PRFUM : A64I_LSunalimm<0b11, 0b0, 0b10, (outs),
|
|
(ins prefetch_op:$Rt, GPR64xsp:$Rn, simm9:$SImm9),
|
|
"prfum\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"prfum $Rt, [$Rn]",
|
|
(PRFUM prefetch_op:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register (unprivileged) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: LDTRB, LDTRH, LDTRSB, LDTRSH, LDTRSW, STTR, STTRB and STTRH
|
|
|
|
// These instructions very much mirror the "unscaled immediate" loads, but since
|
|
// there are no floating-point variants we need to split them out into their own
|
|
// section to avoid instantiation of "ldtr d0, [sp]" etc.
|
|
|
|
multiclass A64I_LDTRSTTR<bits<2> size, string asmsuffix, RegisterClass GPR,
|
|
string prefix> {
|
|
def _UnPriv_STR : A64I_LSunpriv<size, 0b0, 0b00,
|
|
(outs), (ins GPR:$Rt, GPR64xsp:$Rn, simm9:$SImm9),
|
|
"sttr" # asmsuffix # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary> {
|
|
let mayStore = 1;
|
|
}
|
|
|
|
def : InstAlias<"sttr" # asmsuffix # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_UnPriv_STR") GPR:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
def _UnPriv_LDR : A64I_LSunpriv<size, 0b0, 0b01,
|
|
(outs GPR:$Rt), (ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldtr" # asmsuffix # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
|
|
def : InstAlias<"ldtr" # asmsuffix # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_UnPriv_LDR") GPR:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
}
|
|
|
|
// STTRB/LDTRB: First define the instructions
|
|
defm LS8 : A64I_LDTRSTTR<0b00, "b", GPR32, "LS8">;
|
|
|
|
// STTRH/LDTRH
|
|
defm LS16 : A64I_LDTRSTTR<0b01, "h", GPR32, "LS16">;
|
|
|
|
// STTR/LDTR to/from a W register
|
|
defm LS32 : A64I_LDTRSTTR<0b10, "", GPR32, "LS32">;
|
|
|
|
// STTR/LDTR to/from an X register
|
|
defm LS64 : A64I_LDTRSTTR<0b11, "", GPR64, "LS64">;
|
|
|
|
// Now a class for the signed instructions that can go to either 32 or 64
|
|
// bits...
|
|
multiclass A64I_LDTR_signed<bits<2> size, string asmopcode, string prefix> {
|
|
let mayLoad = 1 in {
|
|
def w : A64I_LSunpriv<size, 0b0, 0b11,
|
|
(outs GPR32:$Rt),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldtrs" # asmopcode # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary>;
|
|
|
|
def x : A64I_LSunpriv<size, 0b0, 0b10,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldtrs" # asmopcode # "\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
def : InstAlias<"ldtrs" # asmopcode # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "w") GPR32:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
def : InstAlias<"ldtrs" # asmopcode # " $Rt, [$Rn]",
|
|
(!cast<Instruction>(prefix # "x") GPR64:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
}
|
|
|
|
// LDTRSB
|
|
defm LDTRSB : A64I_LDTR_signed<0b00, "b", "LDTRSB">;
|
|
// LDTRSH
|
|
defm LDTRSH : A64I_LDTR_signed<0b01, "h", "LDTRSH">;
|
|
|
|
// And finally LDTRSW which only goes to 64 bits.
|
|
def LDTRSWx : A64I_LSunpriv<0b10, 0b0, 0b10,
|
|
(outs GPR64:$Rt),
|
|
(ins GPR64xsp:$Rn, simm9:$SImm9),
|
|
"ldtrsw\t$Rt, [$Rn, $SImm9]",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
}
|
|
def : InstAlias<"ldtrsw $Rt, [$Rn]", (LDTRSWx GPR64:$Rt, GPR64xsp:$Rn, 0)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register pair (offset) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// and
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register pair (post-indexed) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: STP, LDP, LDPSW
|
|
//
|
|
// and
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store register pair (pre-indexed) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: STP, LDP, LDPSW
|
|
//
|
|
// and
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// Load-store non-temporal register pair (offset) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: STNP, LDNP
|
|
|
|
|
|
// Anything that creates an MCInst (Decoding, selection and AsmParsing) has to
|
|
// know the access size via some means. An isolated operand does not have this
|
|
// information unless told from here, which means we need separate tablegen
|
|
// Operands for each access size. This multiclass takes care of instantiating
|
|
// the correct template functions in the rest of the backend.
|
|
|
|
multiclass offsets_simm7<string MemSize, string prefix> {
|
|
// The bare signed 7-bit immediate is used in post-indexed instructions, but
|
|
// because of the scaling performed a generic "simm7" operand isn't
|
|
// appropriate here either.
|
|
def simm7_asmoperand : AsmOperandClass {
|
|
let Name = "SImm7_Scaled" # MemSize;
|
|
let PredicateMethod = "isSImm7Scaled<" # MemSize # ">";
|
|
let RenderMethod = "addSImm7ScaledOperands<" # MemSize # ">";
|
|
let DiagnosticType = "LoadStoreSImm7_" # MemSize;
|
|
}
|
|
|
|
def simm7 : Operand<i64> {
|
|
let PrintMethod = "printSImm7ScaledOperand<" # MemSize # ">";
|
|
let ParserMatchClass = !cast<AsmOperandClass>(prefix # "simm7_asmoperand");
|
|
}
|
|
}
|
|
|
|
defm word_ : offsets_simm7<"4", "word_">;
|
|
defm dword_ : offsets_simm7<"8", "dword_">;
|
|
defm qword_ : offsets_simm7<"16", "qword_">;
|
|
|
|
multiclass A64I_LSPsimple<bits<2> opc, bit v, RegisterClass SomeReg,
|
|
Operand simm7, string prefix> {
|
|
def _STR : A64I_LSPoffset<opc, v, 0b0, (outs),
|
|
(ins SomeReg:$Rt, SomeReg:$Rt2, GPR64xsp:$Rn, simm7:$SImm7),
|
|
"stp\t$Rt, $Rt2, [$Rn, $SImm7]", [], NoItinerary> {
|
|
let mayStore = 1;
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
def : InstAlias<"stp $Rt, $Rt2, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_STR") SomeReg:$Rt,
|
|
SomeReg:$Rt2, GPR64xsp:$Rn, 0)>;
|
|
|
|
def _LDR : A64I_LSPoffset<opc, v, 0b1,
|
|
(outs SomeReg:$Rt, SomeReg:$Rt2),
|
|
(ins GPR64xsp:$Rn, simm7:$SImm7),
|
|
"ldp\t$Rt, $Rt2, [$Rn, $SImm7]", [], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
def : InstAlias<"ldp $Rt, $Rt2, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_LDR") SomeReg:$Rt,
|
|
SomeReg:$Rt2, GPR64xsp:$Rn, 0)>;
|
|
|
|
def _PostInd_STR : A64I_LSPpostind<opc, v, 0b0,
|
|
(outs GPR64xsp:$Rn_wb),
|
|
(ins SomeReg:$Rt, SomeReg:$Rt2,
|
|
GPR64xsp:$Rn,
|
|
simm7:$SImm7),
|
|
"stp\t$Rt, $Rt2, [$Rn], $SImm7",
|
|
[], NoItinerary> {
|
|
let mayStore = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
|
|
// Decoder only needed for unpredictability checking (FIXME).
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
|
|
def _PostInd_LDR : A64I_LSPpostind<opc, v, 0b1,
|
|
(outs SomeReg:$Rt, SomeReg:$Rt2, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm7:$SImm7),
|
|
"ldp\t$Rt, $Rt2, [$Rn], $SImm7",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
|
|
def _PreInd_STR : A64I_LSPpreind<opc, v, 0b0, (outs GPR64xsp:$Rn_wb),
|
|
(ins SomeReg:$Rt, SomeReg:$Rt2, GPR64xsp:$Rn, simm7:$SImm7),
|
|
"stp\t$Rt, $Rt2, [$Rn, $SImm7]!",
|
|
[], NoItinerary> {
|
|
let mayStore = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
|
|
def _PreInd_LDR : A64I_LSPpreind<opc, v, 0b1,
|
|
(outs SomeReg:$Rt, SomeReg:$Rt2, GPR64xsp:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, simm7:$SImm7),
|
|
"ldp\t$Rt, $Rt2, [$Rn, $SImm7]!",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
|
|
def _NonTemp_STR : A64I_LSPnontemp<opc, v, 0b0, (outs),
|
|
(ins SomeReg:$Rt, SomeReg:$Rt2, GPR64xsp:$Rn, simm7:$SImm7),
|
|
"stnp\t$Rt, $Rt2, [$Rn, $SImm7]", [], NoItinerary> {
|
|
let mayStore = 1;
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
def : InstAlias<"stnp $Rt, $Rt2, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_NonTemp_STR") SomeReg:$Rt,
|
|
SomeReg:$Rt2, GPR64xsp:$Rn, 0)>;
|
|
|
|
def _NonTemp_LDR : A64I_LSPnontemp<opc, v, 0b1,
|
|
(outs SomeReg:$Rt, SomeReg:$Rt2),
|
|
(ins GPR64xsp:$Rn, simm7:$SImm7),
|
|
"ldnp\t$Rt, $Rt2, [$Rn, $SImm7]", [], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
def : InstAlias<"ldnp $Rt, $Rt2, [$Rn]",
|
|
(!cast<Instruction>(prefix # "_NonTemp_LDR") SomeReg:$Rt,
|
|
SomeReg:$Rt2, GPR64xsp:$Rn, 0)>;
|
|
|
|
}
|
|
|
|
|
|
defm LSPair32 : A64I_LSPsimple<0b00, 0b0, GPR32, word_simm7, "LSPair32">;
|
|
defm LSPair64 : A64I_LSPsimple<0b10, 0b0, GPR64, dword_simm7, "LSPair64">;
|
|
defm LSFPPair32 : A64I_LSPsimple<0b00, 0b1, FPR32, word_simm7, "LSFPPair32">;
|
|
defm LSFPPair64 : A64I_LSPsimple<0b01, 0b1, FPR64, dword_simm7, "LSFPPair64">;
|
|
defm LSFPPair128 : A64I_LSPsimple<0b10, 0b1, FPR128, qword_simm7,
|
|
"LSFPPair128">;
|
|
|
|
|
|
def LDPSWx : A64I_LSPoffset<0b01, 0b0, 0b1,
|
|
(outs GPR64:$Rt, GPR64:$Rt2),
|
|
(ins GPR64xsp:$Rn, word_simm7:$SImm7),
|
|
"ldpsw\t$Rt, $Rt2, [$Rn, $SImm7]", [], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
def : InstAlias<"ldpsw $Rt, $Rt2, [$Rn]",
|
|
(LDPSWx GPR64:$Rt, GPR64:$Rt2, GPR64xsp:$Rn, 0)>;
|
|
|
|
def LDPSWx_PostInd : A64I_LSPpostind<0b01, 0b0, 0b1,
|
|
(outs GPR64:$Rt, GPR64:$Rt2, GPR64:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, word_simm7:$SImm7),
|
|
"ldpsw\t$Rt, $Rt2, [$Rn], $SImm7",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
|
|
def LDPSWx_PreInd : A64I_LSPpreind<0b01, 0b0, 0b1,
|
|
(outs GPR64:$Rt, GPR64:$Rt2, GPR64:$Rn_wb),
|
|
(ins GPR64xsp:$Rn, word_simm7:$SImm7),
|
|
"ldpsw\t$Rt, $Rt2, [$Rn, $SImm7]!",
|
|
[], NoItinerary> {
|
|
let mayLoad = 1;
|
|
let Constraints = "$Rn = $Rn_wb";
|
|
let DecoderMethod = "DecodeLDSTPairInstruction";
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Logical (immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: AND, ORR, EOR, ANDS, + aliases TST, MOV
|
|
|
|
multiclass logical_imm_operands<string prefix, string note,
|
|
int size, ValueType VT> {
|
|
def _asmoperand : AsmOperandClass {
|
|
let Name = "LogicalImm" # note # size;
|
|
let PredicateMethod = "isLogicalImm" # note # "<" # size # ">";
|
|
let RenderMethod = "addLogicalImmOperands<" # size # ">";
|
|
let DiagnosticType = "LogicalSecondSource";
|
|
}
|
|
|
|
def _operand
|
|
: Operand<VT>, ComplexPattern<VT, 1, "SelectLogicalImm", [imm]> {
|
|
let ParserMatchClass = !cast<AsmOperandClass>(prefix # "_asmoperand");
|
|
let PrintMethod = "printLogicalImmOperand<" # size # ">";
|
|
let DecoderMethod = "DecodeLogicalImmOperand<" # size # ">";
|
|
}
|
|
}
|
|
|
|
defm logical_imm32 : logical_imm_operands<"logical_imm32", "", 32, i32>;
|
|
defm logical_imm64 : logical_imm_operands<"logical_imm64", "", 64, i64>;
|
|
|
|
// The mov versions only differ in assembly parsing, where they
|
|
// exclude values representable with either MOVZ or MOVN.
|
|
defm logical_imm32_mov
|
|
: logical_imm_operands<"logical_imm32_mov", "MOV", 32, i32>;
|
|
defm logical_imm64_mov
|
|
: logical_imm_operands<"logical_imm64_mov", "MOV", 64, i64>;
|
|
|
|
|
|
multiclass A64I_logimmSizes<bits<2> opc, string asmop, SDNode opnode> {
|
|
def wwi : A64I_logicalimm<0b0, opc, (outs GPR32wsp:$Rd),
|
|
(ins GPR32:$Rn, logical_imm32_operand:$Imm),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Imm"),
|
|
[(set i32:$Rd,
|
|
(opnode i32:$Rn, logical_imm32_operand:$Imm))],
|
|
NoItinerary>;
|
|
|
|
def xxi : A64I_logicalimm<0b1, opc, (outs GPR64xsp:$Rd),
|
|
(ins GPR64:$Rn, logical_imm64_operand:$Imm),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Imm"),
|
|
[(set i64:$Rd,
|
|
(opnode i64:$Rn, logical_imm64_operand:$Imm))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
defm AND : A64I_logimmSizes<0b00, "and", and>;
|
|
defm ORR : A64I_logimmSizes<0b01, "orr", or>;
|
|
defm EOR : A64I_logimmSizes<0b10, "eor", xor>;
|
|
|
|
let Defs = [NZCV] in {
|
|
def ANDSwwi : A64I_logicalimm<0b0, 0b11, (outs GPR32:$Rd),
|
|
(ins GPR32:$Rn, logical_imm32_operand:$Imm),
|
|
"ands\t$Rd, $Rn, $Imm",
|
|
[], NoItinerary>;
|
|
|
|
def ANDSxxi : A64I_logicalimm<0b1, 0b11, (outs GPR64:$Rd),
|
|
(ins GPR64:$Rn, logical_imm64_operand:$Imm),
|
|
"ands\t$Rd, $Rn, $Imm",
|
|
[], NoItinerary>;
|
|
}
|
|
|
|
|
|
def : InstAlias<"tst $Rn, $Imm",
|
|
(ANDSwwi WZR, GPR32:$Rn, logical_imm32_operand:$Imm)>;
|
|
def : InstAlias<"tst $Rn, $Imm",
|
|
(ANDSxxi XZR, GPR64:$Rn, logical_imm64_operand:$Imm)>;
|
|
def : InstAlias<"mov $Rd, $Imm",
|
|
(ORRwwi GPR32wsp:$Rd, WZR, logical_imm32_mov_operand:$Imm)>;
|
|
def : InstAlias<"mov $Rd, $Imm",
|
|
(ORRxxi GPR64xsp:$Rd, XZR, logical_imm64_mov_operand:$Imm)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Logical (shifted register) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: AND, BIC, ORR, ORN, EOR, EON, ANDS, BICS + aliases TST, MVN, MOV
|
|
|
|
// Operand for optimizing (icmp (and LHS, RHS), 0, SomeCode). In theory "ANDS"
|
|
// behaves differently for unsigned comparisons, so we defensively only allow
|
|
// signed or n/a as the operand. In practice "unsigned greater than 0" is "not
|
|
// equal to 0" and LLVM gives us this.
|
|
def signed_cond : PatLeaf<(cond), [{
|
|
return !isUnsignedIntSetCC(N->get());
|
|
}]>;
|
|
|
|
|
|
// These instructions share their "shift" operands with add/sub (shifted
|
|
// register instructions). They are defined there.
|
|
|
|
// N.b. the commutable parameter is just !N. It will be first against the wall
|
|
// when the revolution comes.
|
|
multiclass logical_shifts<string prefix, bit sf, bits<2> opc,
|
|
bit N, bit commutable,
|
|
string asmop, SDPatternOperator opfrag, ValueType ty,
|
|
RegisterClass GPR, list<Register> defs> {
|
|
let isCommutable = commutable, Defs = defs in {
|
|
def _lsl : A64I_logicalshift<sf, opc, 0b00, N,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Imm6"),
|
|
[(set ty:$Rd, (opfrag ty:$Rn, (shl ty:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
|
|
def _lsr : A64I_logicalshift<sf, opc, 0b01, N,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Imm6"),
|
|
[(set ty:$Rd, (opfrag ty:$Rn, (srl ty:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
|
|
def _asr : A64I_logicalshift<sf, opc, 0b10, N,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Imm6"),
|
|
[(set ty:$Rd, (opfrag ty:$Rn, (sra ty:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
|
|
def _ror : A64I_logicalshift<sf, opc, 0b11, N,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("ror_operand_" # ty):$Imm6),
|
|
!strconcat(asmop, "\t$Rd, $Rn, $Rm, $Imm6"),
|
|
[(set ty:$Rd, (opfrag ty:$Rn, (rotr ty:$Rm,
|
|
!cast<Operand>("ror_operand_" # ty):$Imm6))
|
|
)],
|
|
NoItinerary>;
|
|
}
|
|
|
|
def _noshift
|
|
: InstAlias<!strconcat(asmop, " $Rd, $Rn, $Rm"),
|
|
(!cast<Instruction>(prefix # "_lsl") GPR:$Rd, GPR:$Rn,
|
|
GPR:$Rm, 0)>;
|
|
|
|
def : Pat<(opfrag ty:$Rn, ty:$Rm),
|
|
(!cast<Instruction>(prefix # "_lsl") $Rn, $Rm, 0)>;
|
|
}
|
|
|
|
multiclass logical_sizes<string prefix, bits<2> opc, bit N, bit commutable,
|
|
string asmop, SDPatternOperator opfrag,
|
|
list<Register> defs> {
|
|
defm xxx : logical_shifts<prefix # "xxx", 0b1, opc, N,
|
|
commutable, asmop, opfrag, i64, GPR64, defs>;
|
|
defm www : logical_shifts<prefix # "www", 0b0, opc, N,
|
|
commutable, asmop, opfrag, i32, GPR32, defs>;
|
|
}
|
|
|
|
|
|
defm AND : logical_sizes<"AND", 0b00, 0b0, 0b1, "and", and, []>;
|
|
defm ORR : logical_sizes<"ORR", 0b01, 0b0, 0b1, "orr", or, []>;
|
|
defm EOR : logical_sizes<"EOR", 0b10, 0b0, 0b1, "eor", xor, []>;
|
|
defm ANDS : logical_sizes<"ANDS", 0b11, 0b0, 0b1, "ands",
|
|
PatFrag<(ops node:$lhs, node:$rhs), (and node:$lhs, node:$rhs),
|
|
[{ (void)N; return false; }]>,
|
|
[NZCV]>;
|
|
|
|
defm BIC : logical_sizes<"BIC", 0b00, 0b1, 0b0, "bic",
|
|
PatFrag<(ops node:$lhs, node:$rhs),
|
|
(and node:$lhs, (not node:$rhs))>, []>;
|
|
defm ORN : logical_sizes<"ORN", 0b01, 0b1, 0b0, "orn",
|
|
PatFrag<(ops node:$lhs, node:$rhs),
|
|
(or node:$lhs, (not node:$rhs))>, []>;
|
|
defm EON : logical_sizes<"EON", 0b10, 0b1, 0b0, "eon",
|
|
PatFrag<(ops node:$lhs, node:$rhs),
|
|
(xor node:$lhs, (not node:$rhs))>, []>;
|
|
defm BICS : logical_sizes<"BICS", 0b11, 0b1, 0b0, "bics",
|
|
PatFrag<(ops node:$lhs, node:$rhs),
|
|
(and node:$lhs, (not node:$rhs)),
|
|
[{ (void)N; return false; }]>,
|
|
[NZCV]>;
|
|
|
|
multiclass tst_shifts<string prefix, bit sf, ValueType ty, RegisterClass GPR> {
|
|
let isCommutable = 1, Rd = 0b11111, Defs = [NZCV] in {
|
|
def _lsl : A64I_logicalshift<sf, 0b11, 0b00, 0b0,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6),
|
|
"tst\t$Rn, $Rm, $Imm6",
|
|
[(set NZCV, (A64setcc (and ty:$Rn, (shl ty:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6)),
|
|
0, signed_cond))],
|
|
NoItinerary>;
|
|
|
|
|
|
def _lsr : A64I_logicalshift<sf, 0b11, 0b01, 0b0,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6),
|
|
"tst\t$Rn, $Rm, $Imm6",
|
|
[(set NZCV, (A64setcc (and ty:$Rn, (srl ty:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6)),
|
|
0, signed_cond))],
|
|
NoItinerary>;
|
|
|
|
def _asr : A64I_logicalshift<sf, 0b11, 0b10, 0b0,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6),
|
|
"tst\t$Rn, $Rm, $Imm6",
|
|
[(set NZCV, (A64setcc (and ty:$Rn, (sra ty:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6)),
|
|
0, signed_cond))],
|
|
NoItinerary>;
|
|
|
|
def _ror : A64I_logicalshift<sf, 0b11, 0b11, 0b0,
|
|
(outs),
|
|
(ins GPR:$Rn, GPR:$Rm,
|
|
!cast<Operand>("ror_operand_" # ty):$Imm6),
|
|
"tst\t$Rn, $Rm, $Imm6",
|
|
[(set NZCV, (A64setcc (and ty:$Rn, (rotr ty:$Rm,
|
|
!cast<Operand>("ror_operand_" # ty):$Imm6)),
|
|
0, signed_cond))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
def _noshift : InstAlias<"tst $Rn, $Rm",
|
|
(!cast<Instruction>(prefix # "_lsl") GPR:$Rn, GPR:$Rm, 0)>;
|
|
|
|
def : Pat<(A64setcc (and ty:$Rn, ty:$Rm), 0, signed_cond),
|
|
(!cast<Instruction>(prefix # "_lsl") $Rn, $Rm, 0)>;
|
|
}
|
|
|
|
defm TSTxx : tst_shifts<"TSTxx", 0b1, i64, GPR64>;
|
|
defm TSTww : tst_shifts<"TSTww", 0b0, i32, GPR32>;
|
|
|
|
|
|
multiclass mvn_shifts<string prefix, bit sf, ValueType ty, RegisterClass GPR> {
|
|
let isCommutable = 0, Rn = 0b11111 in {
|
|
def _lsl : A64I_logicalshift<sf, 0b01, 0b00, 0b1,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6),
|
|
"mvn\t$Rd, $Rm, $Imm6",
|
|
[(set ty:$Rd, (not (shl ty:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6)))],
|
|
NoItinerary>;
|
|
|
|
|
|
def _lsr : A64I_logicalshift<sf, 0b01, 0b01, 0b1,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6),
|
|
"mvn\t$Rd, $Rm, $Imm6",
|
|
[(set ty:$Rd, (not (srl ty:$Rm,
|
|
!cast<Operand>("lsr_operand_" # ty):$Imm6)))],
|
|
NoItinerary>;
|
|
|
|
def _asr : A64I_logicalshift<sf, 0b01, 0b10, 0b1,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6),
|
|
"mvn\t$Rd, $Rm, $Imm6",
|
|
[(set ty:$Rd, (not (sra ty:$Rm,
|
|
!cast<Operand>("asr_operand_" # ty):$Imm6)))],
|
|
NoItinerary>;
|
|
|
|
def _ror : A64I_logicalshift<sf, 0b01, 0b11, 0b1,
|
|
(outs GPR:$Rd),
|
|
(ins GPR:$Rm,
|
|
!cast<Operand>("ror_operand_" # ty):$Imm6),
|
|
"mvn\t$Rd, $Rm, $Imm6",
|
|
[(set ty:$Rd, (not (rotr ty:$Rm,
|
|
!cast<Operand>("lsl_operand_" # ty):$Imm6)))],
|
|
NoItinerary>;
|
|
}
|
|
|
|
def _noshift : InstAlias<"mvn $Rn, $Rm",
|
|
(!cast<Instruction>(prefix # "_lsl") GPR:$Rn, GPR:$Rm, 0)>;
|
|
|
|
def : Pat<(not ty:$Rm),
|
|
(!cast<Instruction>(prefix # "_lsl") $Rm, 0)>;
|
|
}
|
|
|
|
defm MVNxx : mvn_shifts<"MVNxx", 0b1, i64, GPR64>;
|
|
defm MVNww : mvn_shifts<"MVNww", 0b0, i32, GPR32>;
|
|
|
|
def MOVxx :InstAlias<"mov $Rd, $Rm", (ORRxxx_lsl GPR64:$Rd, XZR, GPR64:$Rm, 0)>;
|
|
def MOVww :InstAlias<"mov $Rd, $Rm", (ORRwww_lsl GPR32:$Rd, WZR, GPR32:$Rm, 0)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Move wide (immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: MOVN, MOVZ, MOVK + MOV aliases
|
|
|
|
// A wide variety of different relocations are needed for variants of these
|
|
// instructions, so it turns out that we need a different operand for all of
|
|
// them.
|
|
multiclass movw_operands<string prefix, string instname, int width> {
|
|
def _imm_asmoperand : AsmOperandClass {
|
|
let Name = instname # width # "Shifted" # shift;
|
|
let PredicateMethod = "is" # instname # width # "Imm";
|
|
let RenderMethod = "addMoveWideImmOperands";
|
|
let ParserMethod = "ParseImmWithLSLOperand";
|
|
let DiagnosticType = "MOVWUImm16";
|
|
}
|
|
|
|
def _imm : Operand<i64> {
|
|
let ParserMatchClass = !cast<AsmOperandClass>(prefix # "_imm_asmoperand");
|
|
let PrintMethod = "printMoveWideImmOperand";
|
|
let EncoderMethod = "getMoveWideImmOpValue";
|
|
let DecoderMethod = "DecodeMoveWideImmOperand<" # width # ">";
|
|
|
|
let MIOperandInfo = (ops uimm16:$UImm16, imm:$Shift);
|
|
}
|
|
}
|
|
|
|
defm movn32 : movw_operands<"movn32", "MOVN", 32>;
|
|
defm movn64 : movw_operands<"movn64", "MOVN", 64>;
|
|
defm movz32 : movw_operands<"movz32", "MOVZ", 32>;
|
|
defm movz64 : movw_operands<"movz64", "MOVZ", 64>;
|
|
defm movk32 : movw_operands<"movk32", "MOVK", 32>;
|
|
defm movk64 : movw_operands<"movk64", "MOVK", 64>;
|
|
|
|
multiclass A64I_movwSizes<bits<2> opc, string asmop, dag ins32bit,
|
|
dag ins64bit> {
|
|
|
|
def wii : A64I_movw<0b0, opc, (outs GPR32:$Rd), ins32bit,
|
|
!strconcat(asmop, "\t$Rd, $FullImm"),
|
|
[], NoItinerary> {
|
|
bits<18> FullImm;
|
|
let UImm16 = FullImm{15-0};
|
|
let Shift = FullImm{17-16};
|
|
}
|
|
|
|
def xii : A64I_movw<0b1, opc, (outs GPR64:$Rd), ins64bit,
|
|
!strconcat(asmop, "\t$Rd, $FullImm"),
|
|
[], NoItinerary> {
|
|
bits<18> FullImm;
|
|
let UImm16 = FullImm{15-0};
|
|
let Shift = FullImm{17-16};
|
|
}
|
|
}
|
|
|
|
let isMoveImm = 1, isReMaterializable = 1,
|
|
isAsCheapAsAMove = 1, hasSideEffects = 0 in {
|
|
defm MOVN : A64I_movwSizes<0b00, "movn",
|
|
(ins movn32_imm:$FullImm),
|
|
(ins movn64_imm:$FullImm)>;
|
|
|
|
// Some relocations are able to convert between a MOVZ and a MOVN. If these
|
|
// are applied the instruction must be emitted with the corresponding bits as
|
|
// 0, which means a MOVZ needs to override that bit from the default.
|
|
let PostEncoderMethod = "fixMOVZ" in
|
|
defm MOVZ : A64I_movwSizes<0b10, "movz",
|
|
(ins movz32_imm:$FullImm),
|
|
(ins movz64_imm:$FullImm)>;
|
|
}
|
|
|
|
let Constraints = "$src = $Rd" in
|
|
defm MOVK : A64I_movwSizes<0b11, "movk",
|
|
(ins GPR32:$src, movk32_imm:$FullImm),
|
|
(ins GPR64:$src, movk64_imm:$FullImm)>;
|
|
|
|
|
|
// And now the "MOV" aliases. These also need their own operands because what
|
|
// they accept is completely different to what the base instructions accept.
|
|
multiclass movalias_operand<string prefix, string basename,
|
|
string immpredicate, int width> {
|
|
def _asmoperand : AsmOperandClass {
|
|
let Name = basename # width # "MovAlias";
|
|
let PredicateMethod
|
|
= "isMoveWideMovAlias<" # width # ", A64Imms::" # immpredicate # ">";
|
|
let RenderMethod
|
|
= "addMoveWideMovAliasOperands<" # width # ", "
|
|
# "A64Imms::" # immpredicate # ">";
|
|
}
|
|
|
|
def _movimm : Operand<i64> {
|
|
let ParserMatchClass = !cast<AsmOperandClass>(prefix # "_asmoperand");
|
|
|
|
let MIOperandInfo = (ops uimm16:$UImm16, imm:$Shift);
|
|
}
|
|
}
|
|
|
|
defm movz32 : movalias_operand<"movz32", "MOVZ", "isMOVZImm", 32>;
|
|
defm movz64 : movalias_operand<"movz64", "MOVZ", "isMOVZImm", 64>;
|
|
defm movn32 : movalias_operand<"movn32", "MOVN", "isOnlyMOVNImm", 32>;
|
|
defm movn64 : movalias_operand<"movn64", "MOVN", "isOnlyMOVNImm", 64>;
|
|
|
|
// FIXME: these are officially canonical aliases, but TableGen is too limited to
|
|
// print them at the moment. I believe in this case an "AliasPredicate" method
|
|
// will need to be implemented. to allow it, as well as the more generally
|
|
// useful handling of non-register, non-constant operands.
|
|
class movalias<Instruction INST, RegisterClass GPR, Operand operand>
|
|
: InstAlias<"mov $Rd, $FullImm", (INST GPR:$Rd, operand:$FullImm)>;
|
|
|
|
def : movalias<MOVZwii, GPR32, movz32_movimm>;
|
|
def : movalias<MOVZxii, GPR64, movz64_movimm>;
|
|
def : movalias<MOVNwii, GPR32, movn32_movimm>;
|
|
def : movalias<MOVNxii, GPR64, movn64_movimm>;
|
|
|
|
def movw_addressref_g0 : ComplexPattern<i64, 2, "SelectMOVWAddressRef<0>">;
|
|
def movw_addressref_g1 : ComplexPattern<i64, 2, "SelectMOVWAddressRef<1>">;
|
|
def movw_addressref_g2 : ComplexPattern<i64, 2, "SelectMOVWAddressRef<2>">;
|
|
def movw_addressref_g3 : ComplexPattern<i64, 2, "SelectMOVWAddressRef<3>">;
|
|
|
|
def : Pat<(A64WrapperLarge movw_addressref_g3:$G3, movw_addressref_g2:$G2,
|
|
movw_addressref_g1:$G1, movw_addressref_g0:$G0),
|
|
(MOVKxii (MOVKxii (MOVKxii (MOVZxii movw_addressref_g3:$G3),
|
|
movw_addressref_g2:$G2),
|
|
movw_addressref_g1:$G1),
|
|
movw_addressref_g0:$G0)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PC-relative addressing instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: ADR, ADRP
|
|
|
|
def adr_label : Operand<i64> {
|
|
let EncoderMethod = "getLabelOpValue<AArch64::fixup_a64_adr_prel>";
|
|
|
|
// This label is a 21-bit offset from PC, unscaled
|
|
let PrintMethod = "printLabelOperand<21, 1>";
|
|
let ParserMatchClass = label_asmoperand<21, 1>;
|
|
let OperandType = "OPERAND_PCREL";
|
|
}
|
|
|
|
def adrp_label_asmoperand : AsmOperandClass {
|
|
let Name = "AdrpLabel";
|
|
let RenderMethod = "addLabelOperands<21, 4096>";
|
|
let DiagnosticType = "Label";
|
|
}
|
|
|
|
def adrp_label : Operand<i64> {
|
|
let EncoderMethod = "getAdrpLabelOpValue";
|
|
|
|
// This label is a 21-bit offset from PC, scaled by the page-size: 4096.
|
|
let PrintMethod = "printLabelOperand<21, 4096>";
|
|
let ParserMatchClass = adrp_label_asmoperand;
|
|
let OperandType = "OPERAND_PCREL";
|
|
}
|
|
|
|
let hasSideEffects = 0 in {
|
|
def ADRxi : A64I_PCADR<0b0, (outs GPR64:$Rd), (ins adr_label:$Label),
|
|
"adr\t$Rd, $Label", [], NoItinerary>;
|
|
|
|
def ADRPxi : A64I_PCADR<0b1, (outs GPR64:$Rd), (ins adrp_label:$Label),
|
|
"adrp\t$Rd, $Label", [], NoItinerary>;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// System instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: HINT, CLREX, DSB, DMB, ISB, MSR, SYS, SYSL, MRS
|
|
// + aliases IC, DC, AT, TLBI, NOP, YIELD, WFE, WFI, SEV, SEVL
|
|
|
|
// Op1 and Op2 fields are sometimes simple 3-bit unsigned immediate values.
|
|
def uimm3_asmoperand : AsmOperandClass {
|
|
let Name = "UImm3";
|
|
let PredicateMethod = "isUImm<3>";
|
|
let RenderMethod = "addImmOperands";
|
|
let DiagnosticType = "UImm3";
|
|
}
|
|
|
|
def uimm3 : Operand<i32> {
|
|
let ParserMatchClass = uimm3_asmoperand;
|
|
}
|
|
|
|
// The HINT alias can accept a simple unsigned 7-bit immediate.
|
|
def uimm7_asmoperand : AsmOperandClass {
|
|
let Name = "UImm7";
|
|
let PredicateMethod = "isUImm<7>";
|
|
let RenderMethod = "addImmOperands";
|
|
let DiagnosticType = "UImm7";
|
|
}
|
|
|
|
def uimm7 : Operand<i32> {
|
|
let ParserMatchClass = uimm7_asmoperand;
|
|
}
|
|
|
|
// Multiclass namedimm is defined with the prefetch operands. Most of these fit
|
|
// into the NamedImmMapper scheme well: they either accept a named operand or
|
|
// any immediate under a particular value (which may be 0, implying no immediate
|
|
// is allowed).
|
|
defm dbarrier : namedimm<"dbarrier", "A64DB::DBarrierMapper">;
|
|
defm isb : namedimm<"isb", "A64ISB::ISBMapper">;
|
|
defm ic : namedimm<"ic", "A64IC::ICMapper">;
|
|
defm dc : namedimm<"dc", "A64DC::DCMapper">;
|
|
defm at : namedimm<"at", "A64AT::ATMapper">;
|
|
defm tlbi : namedimm<"tlbi", "A64TLBI::TLBIMapper">;
|
|
|
|
// However, MRS and MSR are more complicated for a few reasons:
|
|
// * There are ~1000 generic names S3_<op1>_<CRn>_<CRm>_<Op2> which have an
|
|
// implementation-defined effect
|
|
// * Most registers are shared, but some are read-only or write-only.
|
|
// * There is a variant of MSR which accepts the same register name (SPSel),
|
|
// but which would have a different encoding.
|
|
|
|
// In principle these could be resolved in with more complicated subclasses of
|
|
// NamedImmMapper, however that imposes an overhead on other "named
|
|
// immediates". Both in concrete terms with virtual tables and in unnecessary
|
|
// abstraction.
|
|
|
|
// The solution adopted here is to take the MRS/MSR Mappers out of the usual
|
|
// hierarchy (they're not derived from NamedImmMapper) and to add logic for
|
|
// their special situation.
|
|
def mrs_asmoperand : AsmOperandClass {
|
|
let Name = "MRS";
|
|
let ParserMethod = "ParseSysRegOperand";
|
|
let DiagnosticType = "MRS";
|
|
}
|
|
|
|
def mrs_op : Operand<i32> {
|
|
let ParserMatchClass = mrs_asmoperand;
|
|
let PrintMethod = "printMRSOperand";
|
|
let DecoderMethod = "DecodeMRSOperand";
|
|
}
|
|
|
|
def msr_asmoperand : AsmOperandClass {
|
|
let Name = "MSRWithReg";
|
|
|
|
// Note that SPSel is valid for both this and the pstate operands, but with
|
|
// different immediate encodings. This is why these operands provide a string
|
|
// AArch64Operand rather than an immediate. The overlap is small enough that
|
|
// it could be resolved with hackery now, but who can say in future?
|
|
let ParserMethod = "ParseSysRegOperand";
|
|
let DiagnosticType = "MSR";
|
|
}
|
|
|
|
def msr_op : Operand<i32> {
|
|
let ParserMatchClass = msr_asmoperand;
|
|
let PrintMethod = "printMSROperand";
|
|
let DecoderMethod = "DecodeMSROperand";
|
|
}
|
|
|
|
def pstate_asmoperand : AsmOperandClass {
|
|
let Name = "MSRPState";
|
|
// See comment above about parser.
|
|
let ParserMethod = "ParseSysRegOperand";
|
|
let DiagnosticType = "MSR";
|
|
}
|
|
|
|
def pstate_op : Operand<i32> {
|
|
let ParserMatchClass = pstate_asmoperand;
|
|
let PrintMethod = "printNamedImmOperand<A64PState::PStateMapper>";
|
|
let DecoderMethod = "DecodeNamedImmOperand<A64PState::PStateMapper>";
|
|
}
|
|
|
|
// When <CRn> is specified, an assembler should accept something like "C4", not
|
|
// the usual "#4" immediate.
|
|
def CRx_asmoperand : AsmOperandClass {
|
|
let Name = "CRx";
|
|
let PredicateMethod = "isUImm<4>";
|
|
let RenderMethod = "addImmOperands";
|
|
let ParserMethod = "ParseCRxOperand";
|
|
// Diagnostics are handled in all cases by ParseCRxOperand.
|
|
}
|
|
|
|
def CRx : Operand<i32> {
|
|
let ParserMatchClass = CRx_asmoperand;
|
|
let PrintMethod = "printCRxOperand";
|
|
}
|
|
|
|
|
|
// Finally, we can start defining the instructions.
|
|
|
|
// HINT is straightforward, with a few aliases.
|
|
def HINTi : A64I_system<0b0, (outs), (ins uimm7:$UImm7), "hint\t$UImm7",
|
|
[], NoItinerary> {
|
|
bits<7> UImm7;
|
|
let CRm = UImm7{6-3};
|
|
let Op2 = UImm7{2-0};
|
|
|
|
let Op0 = 0b00;
|
|
let Op1 = 0b011;
|
|
let CRn = 0b0010;
|
|
let Rt = 0b11111;
|
|
}
|
|
|
|
def : InstAlias<"nop", (HINTi 0)>;
|
|
def : InstAlias<"yield", (HINTi 1)>;
|
|
def : InstAlias<"wfe", (HINTi 2)>;
|
|
def : InstAlias<"wfi", (HINTi 3)>;
|
|
def : InstAlias<"sev", (HINTi 4)>;
|
|
def : InstAlias<"sevl", (HINTi 5)>;
|
|
|
|
// Quite a few instructions then follow a similar pattern of fixing common
|
|
// fields in the bitpattern, we'll define a helper-class for them.
|
|
class simple_sys<bits<2> op0, bits<3> op1, bits<4> crn, bits<3> op2,
|
|
Operand operand, string asmop>
|
|
: A64I_system<0b0, (outs), (ins operand:$CRm), !strconcat(asmop, "\t$CRm"),
|
|
[], NoItinerary> {
|
|
let Op0 = op0;
|
|
let Op1 = op1;
|
|
let CRn = crn;
|
|
let Op2 = op2;
|
|
let Rt = 0b11111;
|
|
}
|
|
|
|
|
|
def CLREXi : simple_sys<0b00, 0b011, 0b0011, 0b010, uimm4, "clrex">;
|
|
def DSBi : simple_sys<0b00, 0b011, 0b0011, 0b100, dbarrier_op, "dsb">;
|
|
def DMBi : simple_sys<0b00, 0b011, 0b0011, 0b101, dbarrier_op, "dmb">;
|
|
def ISBi : simple_sys<0b00, 0b011, 0b0011, 0b110, isb_op, "isb">;
|
|
|
|
def : InstAlias<"clrex", (CLREXi 0b1111)>;
|
|
def : InstAlias<"isb", (ISBi 0b1111)>;
|
|
|
|
// (DMBi 0xb) is a "DMB ISH" instruciton, appropriate for Linux SMP
|
|
// configurations at least.
|
|
def : Pat<(atomic_fence imm, imm), (DMBi 0xb)>;
|
|
|
|
// Any SYS bitpattern can be represented with a complex and opaque "SYS"
|
|
// instruction.
|
|
def SYSiccix : A64I_system<0b0, (outs),
|
|
(ins uimm3:$Op1, CRx:$CRn, CRx:$CRm,
|
|
uimm3:$Op2, GPR64:$Rt),
|
|
"sys\t$Op1, $CRn, $CRm, $Op2, $Rt",
|
|
[], NoItinerary> {
|
|
let Op0 = 0b01;
|
|
}
|
|
|
|
// You can skip the Xt argument whether it makes sense or not for the generic
|
|
// SYS instruction.
|
|
def : InstAlias<"sys $Op1, $CRn, $CRm, $Op2",
|
|
(SYSiccix uimm3:$Op1, CRx:$CRn, CRx:$CRm, uimm3:$Op2, XZR)>;
|
|
|
|
|
|
// But many have aliases, which obviously don't fit into
|
|
class SYSalias<dag ins, string asmstring>
|
|
: A64I_system<0b0, (outs), ins, asmstring, [], NoItinerary> {
|
|
let isAsmParserOnly = 1;
|
|
|
|
bits<14> SysOp;
|
|
let Op0 = 0b01;
|
|
let Op1 = SysOp{13-11};
|
|
let CRn = SysOp{10-7};
|
|
let CRm = SysOp{6-3};
|
|
let Op2 = SysOp{2-0};
|
|
}
|
|
|
|
def ICix : SYSalias<(ins ic_op:$SysOp, GPR64:$Rt), "ic\t$SysOp, $Rt">;
|
|
|
|
def ICi : SYSalias<(ins ic_op:$SysOp), "ic\t$SysOp"> {
|
|
let Rt = 0b11111;
|
|
}
|
|
|
|
def DCix : SYSalias<(ins dc_op:$SysOp, GPR64:$Rt), "dc\t$SysOp, $Rt">;
|
|
def ATix : SYSalias<(ins at_op:$SysOp, GPR64:$Rt), "at\t$SysOp, $Rt">;
|
|
|
|
def TLBIix : SYSalias<(ins tlbi_op:$SysOp, GPR64:$Rt), "tlbi\t$SysOp, $Rt">;
|
|
|
|
def TLBIi : SYSalias<(ins tlbi_op:$SysOp), "tlbi\t$SysOp"> {
|
|
let Rt = 0b11111;
|
|
}
|
|
|
|
|
|
def SYSLxicci : A64I_system<0b1, (outs GPR64:$Rt),
|
|
(ins uimm3:$Op1, CRx:$CRn, CRx:$CRm, uimm3:$Op2),
|
|
"sysl\t$Rt, $Op1, $CRn, $CRm, $Op2",
|
|
[], NoItinerary> {
|
|
let Op0 = 0b01;
|
|
}
|
|
|
|
// The instructions themselves are rather simple for MSR and MRS.
|
|
def MSRix : A64I_system<0b0, (outs), (ins msr_op:$SysReg, GPR64:$Rt),
|
|
"msr\t$SysReg, $Rt", [], NoItinerary> {
|
|
bits<16> SysReg;
|
|
let Op0 = SysReg{15-14};
|
|
let Op1 = SysReg{13-11};
|
|
let CRn = SysReg{10-7};
|
|
let CRm = SysReg{6-3};
|
|
let Op2 = SysReg{2-0};
|
|
}
|
|
|
|
def MRSxi : A64I_system<0b1, (outs GPR64:$Rt), (ins mrs_op:$SysReg),
|
|
"mrs\t$Rt, $SysReg", [], NoItinerary> {
|
|
bits<16> SysReg;
|
|
let Op0 = SysReg{15-14};
|
|
let Op1 = SysReg{13-11};
|
|
let CRn = SysReg{10-7};
|
|
let CRm = SysReg{6-3};
|
|
let Op2 = SysReg{2-0};
|
|
}
|
|
|
|
def MSRii : A64I_system<0b0, (outs), (ins pstate_op:$PState, uimm4:$CRm),
|
|
"msr\t$PState, $CRm", [], NoItinerary> {
|
|
bits<6> PState;
|
|
|
|
let Op0 = 0b00;
|
|
let Op1 = PState{5-3};
|
|
let CRn = 0b0100;
|
|
let Op2 = PState{2-0};
|
|
let Rt = 0b11111;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Test & branch (immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: TBZ, TBNZ
|
|
|
|
// The bit to test is a simple unsigned 6-bit immediate in the X-register
|
|
// versions.
|
|
def uimm6 : Operand<i64> {
|
|
let ParserMatchClass = uimm6_asmoperand;
|
|
}
|
|
|
|
def label_wid14_scal4_asmoperand : label_asmoperand<14, 4>;
|
|
|
|
def tbimm_target : Operand<OtherVT> {
|
|
let EncoderMethod = "getLabelOpValue<AArch64::fixup_a64_tstbr>";
|
|
|
|
// This label is a 14-bit offset from PC, scaled by the instruction-width: 4.
|
|
let PrintMethod = "printLabelOperand<14, 4>";
|
|
let ParserMatchClass = label_wid14_scal4_asmoperand;
|
|
|
|
let OperandType = "OPERAND_PCREL";
|
|
}
|
|
|
|
def A64eq : ImmLeaf<i32, [{ return Imm == A64CC::EQ; }]>;
|
|
def A64ne : ImmLeaf<i32, [{ return Imm == A64CC::NE; }]>;
|
|
|
|
// These instructions correspond to patterns involving "and" with a power of
|
|
// two, which we need to be able to select.
|
|
def tstb64_pat : ComplexPattern<i64, 1, "SelectTSTBOperand<64>">;
|
|
def tstb32_pat : ComplexPattern<i32, 1, "SelectTSTBOperand<32>">;
|
|
|
|
let isBranch = 1, isTerminator = 1 in {
|
|
def TBZxii : A64I_TBimm<0b0, (outs),
|
|
(ins GPR64:$Rt, uimm6:$Imm, tbimm_target:$Label),
|
|
"tbz\t$Rt, $Imm, $Label",
|
|
[(A64br_cc (A64cmp (and i64:$Rt, tstb64_pat:$Imm), 0),
|
|
A64eq, bb:$Label)],
|
|
NoItinerary>;
|
|
|
|
def TBNZxii : A64I_TBimm<0b1, (outs),
|
|
(ins GPR64:$Rt, uimm6:$Imm, tbimm_target:$Label),
|
|
"tbnz\t$Rt, $Imm, $Label",
|
|
[(A64br_cc (A64cmp (and i64:$Rt, tstb64_pat:$Imm), 0),
|
|
A64ne, bb:$Label)],
|
|
NoItinerary>;
|
|
|
|
|
|
// Note, these instructions overlap with the above 64-bit patterns. This is
|
|
// intentional, "tbz x3, #1, somewhere" and "tbz w3, #1, somewhere" would both
|
|
// do the same thing and are both permitted assembly. They also both have
|
|
// sensible DAG patterns.
|
|
def TBZwii : A64I_TBimm<0b0, (outs),
|
|
(ins GPR32:$Rt, uimm5:$Imm, tbimm_target:$Label),
|
|
"tbz\t$Rt, $Imm, $Label",
|
|
[(A64br_cc (A64cmp (and i32:$Rt, tstb32_pat:$Imm), 0),
|
|
A64eq, bb:$Label)],
|
|
NoItinerary> {
|
|
let Imm{5} = 0b0;
|
|
}
|
|
|
|
def TBNZwii : A64I_TBimm<0b1, (outs),
|
|
(ins GPR32:$Rt, uimm5:$Imm, tbimm_target:$Label),
|
|
"tbnz\t$Rt, $Imm, $Label",
|
|
[(A64br_cc (A64cmp (and i32:$Rt, tstb32_pat:$Imm), 0),
|
|
A64ne, bb:$Label)],
|
|
NoItinerary> {
|
|
let Imm{5} = 0b0;
|
|
}
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Unconditional branch (immediate) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: B, BL
|
|
|
|
def label_wid26_scal4_asmoperand : label_asmoperand<26, 4>;
|
|
|
|
def bimm_target : Operand<OtherVT> {
|
|
let EncoderMethod = "getLabelOpValue<AArch64::fixup_a64_uncondbr>";
|
|
|
|
// This label is a 26-bit offset from PC, scaled by the instruction-width: 4.
|
|
let PrintMethod = "printLabelOperand<26, 4>";
|
|
let ParserMatchClass = label_wid26_scal4_asmoperand;
|
|
|
|
let OperandType = "OPERAND_PCREL";
|
|
}
|
|
|
|
def blimm_target : Operand<i64> {
|
|
let EncoderMethod = "getLabelOpValue<AArch64::fixup_a64_call>";
|
|
|
|
// This label is a 26-bit offset from PC, scaled by the instruction-width: 4.
|
|
let PrintMethod = "printLabelOperand<26, 4>";
|
|
let ParserMatchClass = label_wid26_scal4_asmoperand;
|
|
|
|
let OperandType = "OPERAND_PCREL";
|
|
}
|
|
|
|
class A64I_BimmImpl<bit op, string asmop, list<dag> patterns, Operand lbl_type>
|
|
: A64I_Bimm<op, (outs), (ins lbl_type:$Label),
|
|
!strconcat(asmop, "\t$Label"), patterns,
|
|
NoItinerary>;
|
|
|
|
let isBranch = 1 in {
|
|
def Bimm : A64I_BimmImpl<0b0, "b", [(br bb:$Label)], bimm_target> {
|
|
let isTerminator = 1;
|
|
let isBarrier = 1;
|
|
}
|
|
|
|
def BLimm : A64I_BimmImpl<0b1, "bl",
|
|
[(AArch64Call tglobaladdr:$Label)], blimm_target> {
|
|
let isCall = 1;
|
|
let Defs = [X30];
|
|
}
|
|
}
|
|
|
|
def : Pat<(AArch64Call texternalsym:$Label), (BLimm texternalsym:$Label)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Unconditional branch (register) instructions
|
|
//===----------------------------------------------------------------------===//
|
|
// Contains: BR, BLR, RET, ERET, DRP.
|
|
|
|
// Most of the notional opcode fields in the A64I_Breg format are fixed in A64
|
|
// at the moment.
|
|
class A64I_BregImpl<bits<4> opc,
|
|
dag outs, dag ins, string asmstr, list<dag> patterns,
|
|
InstrItinClass itin = NoItinerary>
|
|
: A64I_Breg<opc, 0b11111, 0b000000, 0b00000,
|
|
outs, ins, asmstr, patterns, itin> {
|
|
let isBranch = 1;
|
|
let isIndirectBranch = 1;
|
|
}
|
|
|
|
// Note that these are not marked isCall or isReturn because as far as LLVM is
|
|
// concerned they're not. "ret" is just another jump unless it has been selected
|
|
// by LLVM as the function's return.
|
|
|
|
let isBranch = 1 in {
|
|
def BRx : A64I_BregImpl<0b0000,(outs), (ins GPR64:$Rn),
|
|
"br\t$Rn", [(brind i64:$Rn)]> {
|
|
let isBarrier = 1;
|
|
let isTerminator = 1;
|
|
}
|
|
|
|
def BLRx : A64I_BregImpl<0b0001, (outs), (ins GPR64:$Rn),
|
|
"blr\t$Rn", [(AArch64Call i64:$Rn)]> {
|
|
let isBarrier = 0;
|
|
let isCall = 1;
|
|
let Defs = [X30];
|
|
}
|
|
|
|
def RETx : A64I_BregImpl<0b0010, (outs), (ins GPR64:$Rn),
|
|
"ret\t$Rn", []> {
|
|
let isBarrier = 1;
|
|
let isTerminator = 1;
|
|
let isReturn = 1;
|
|
}
|
|
|
|
// Create a separate pseudo-instruction for codegen to use so that we don't
|
|
// flag x30 as used in every function. It'll be restored before the RET by the
|
|
// epilogue if it's legitimately used.
|
|
def RET : A64PseudoExpand<(outs), (ins), [(A64ret)], (RETx (ops X30))> {
|
|
let isTerminator = 1;
|
|
let isBarrier = 1;
|
|
let isReturn = 1;
|
|
}
|
|
|
|
def ERET : A64I_BregImpl<0b0100, (outs), (ins), "eret", []> {
|
|
let Rn = 0b11111;
|
|
let isBarrier = 1;
|
|
let isTerminator = 1;
|
|
let isReturn = 1;
|
|
}
|
|
|
|
def DRPS : A64I_BregImpl<0b0101, (outs), (ins), "drps", []> {
|
|
let Rn = 0b11111;
|
|
let isBarrier = 1;
|
|
}
|
|
}
|
|
|
|
def RETAlias : InstAlias<"ret", (RETx X30)>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Address generation patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Primary method of address generation for the small/absolute memory model is
|
|
// an ADRP/ADR pair:
|
|
// ADRP x0, some_variable
|
|
// ADD x0, x0, #:lo12:some_variable
|
|
//
|
|
// The load/store elision of the ADD is accomplished when selecting
|
|
// addressing-modes. This just mops up the cases where that doesn't work and we
|
|
// really need an address in some register.
|
|
|
|
// This wrapper applies a LO12 modifier to the address. Otherwise we could just
|
|
// use the same address.
|
|
|
|
class ADRP_ADD<SDNode Wrapper, SDNode addrop>
|
|
: Pat<(Wrapper addrop:$Hi, addrop:$Lo12, (i32 imm)),
|
|
(ADDxxi_lsl0_s (ADRPxi addrop:$Hi), addrop:$Lo12)>;
|
|
|
|
def : ADRP_ADD<A64WrapperSmall, tblockaddress>;
|
|
def : ADRP_ADD<A64WrapperSmall, texternalsym>;
|
|
def : ADRP_ADD<A64WrapperSmall, tglobaladdr>;
|
|
def : ADRP_ADD<A64WrapperSmall, tglobaltlsaddr>;
|
|
def : ADRP_ADD<A64WrapperSmall, tjumptable>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// GOT access patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class GOTLoadSmall<SDNode addrfrag>
|
|
: Pat<(A64GOTLoad (A64WrapperSmall addrfrag:$Hi, addrfrag:$Lo12, 8)),
|
|
(LS64_LDR (ADRPxi addrfrag:$Hi), addrfrag:$Lo12)>;
|
|
|
|
def : GOTLoadSmall<texternalsym>;
|
|
def : GOTLoadSmall<tglobaladdr>;
|
|
def : GOTLoadSmall<tglobaltlsaddr>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Tail call handling
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1, Uses = [XSP] in {
|
|
def TC_RETURNdi
|
|
: PseudoInst<(outs), (ins i64imm:$dst, i32imm:$FPDiff),
|
|
[(AArch64tcret tglobaladdr:$dst, (i32 timm:$FPDiff))]>;
|
|
|
|
def TC_RETURNxi
|
|
: PseudoInst<(outs), (ins tcGPR64:$dst, i32imm:$FPDiff),
|
|
[(AArch64tcret i64:$dst, (i32 timm:$FPDiff))]>;
|
|
}
|
|
|
|
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1,
|
|
Uses = [XSP] in {
|
|
def TAIL_Bimm : A64PseudoExpand<(outs), (ins bimm_target:$Label), [],
|
|
(Bimm bimm_target:$Label)>;
|
|
|
|
def TAIL_BRx : A64PseudoExpand<(outs), (ins tcGPR64:$Rd), [],
|
|
(BRx GPR64:$Rd)>;
|
|
}
|
|
|
|
|
|
def : Pat<(AArch64tcret texternalsym:$dst, (i32 timm:$FPDiff)),
|
|
(TC_RETURNdi texternalsym:$dst, imm:$FPDiff)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Thread local storage
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// This is a pseudo-instruction representing the ".tlsdesccall" directive in
|
|
// assembly. Its effect is to insert an R_AARCH64_TLSDESC_CALL relocation at the
|
|
// current location. It should always be immediately followed by a BLR
|
|
// instruction, and is intended solely for relaxation by the linker.
|
|
|
|
def : Pat<(A64threadpointer), (MRSxi 0xde82)>;
|
|
|
|
def TLSDESCCALL : PseudoInst<(outs), (ins i64imm:$Lbl), []> {
|
|
let hasSideEffects = 1;
|
|
}
|
|
|
|
def TLSDESC_BLRx : PseudoInst<(outs), (ins GPR64:$Rn, i64imm:$Var),
|
|
[(A64tlsdesc_blr i64:$Rn, tglobaltlsaddr:$Var)]> {
|
|
let isCall = 1;
|
|
let Defs = [X30];
|
|
}
|
|
|
|
def : Pat<(A64tlsdesc_blr i64:$Rn, texternalsym:$Var),
|
|
(TLSDESC_BLRx $Rn, texternalsym:$Var)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Bitfield patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def bfi32_lsb_to_immr : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant((32 - N->getZExtValue()) % 32, MVT::i64);
|
|
}]>;
|
|
|
|
def bfi64_lsb_to_immr : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant((64 - N->getZExtValue()) % 64, MVT::i64);
|
|
}]>;
|
|
|
|
def bfi_width_to_imms : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(N->getZExtValue() - 1, MVT::i64);
|
|
}]>;
|
|
|
|
|
|
// The simpler patterns deal with cases where no AND mask is actually needed
|
|
// (either all bits are used or the low 32 bits are used).
|
|
let AddedComplexity = 10 in {
|
|
|
|
def : Pat<(A64Bfi i64:$src, i64:$Rn, imm:$ImmR, imm:$ImmS),
|
|
(BFIxxii $src, $Rn,
|
|
(bfi64_lsb_to_immr (i64 imm:$ImmR)),
|
|
(bfi_width_to_imms (i64 imm:$ImmS)))>;
|
|
|
|
def : Pat<(A64Bfi i32:$src, i32:$Rn, imm:$ImmR, imm:$ImmS),
|
|
(BFIwwii $src, $Rn,
|
|
(bfi32_lsb_to_immr (i64 imm:$ImmR)),
|
|
(bfi_width_to_imms (i64 imm:$ImmS)))>;
|
|
|
|
|
|
def : Pat<(and (A64Bfi i64:$src, i64:$Rn, imm:$ImmR, imm:$ImmS),
|
|
(i64 4294967295)),
|
|
(SUBREG_TO_REG (i64 0),
|
|
(BFIwwii (EXTRACT_SUBREG $src, sub_32),
|
|
(EXTRACT_SUBREG $Rn, sub_32),
|
|
(bfi32_lsb_to_immr (i64 imm:$ImmR)),
|
|
(bfi_width_to_imms (i64 imm:$ImmS))),
|
|
sub_32)>;
|
|
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Miscellaneous patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Truncation from 64 to 32-bits just involves renaming your register.
|
|
def : Pat<(i32 (trunc i64:$val)), (EXTRACT_SUBREG $val, sub_32)>;
|
|
|
|
// Similarly, extension where we don't care about the high bits is
|
|
// just a rename.
|
|
def : Pat<(i64 (anyext i32:$val)),
|
|
(INSERT_SUBREG (IMPLICIT_DEF), $val, sub_32)>;
|
|
|
|
// SELECT instructions providing f128 types need to be handled by a
|
|
// pseudo-instruction since the eventual code will need to introduce basic
|
|
// blocks and control flow.
|
|
def F128CSEL : PseudoInst<(outs FPR128:$Rd),
|
|
(ins FPR128:$Rn, FPR128:$Rm, cond_code_op:$Cond),
|
|
[(set f128:$Rd, (simple_select f128:$Rn, f128:$Rm))]> {
|
|
let Uses = [NZCV];
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load/store patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// There are lots of patterns here, because we need to allow at least three
|
|
// parameters to vary independently.
|
|
// 1. Instruction: "ldrb w9, [sp]", "ldrh w9, [sp]", ...
|
|
// 2. LLVM source: zextloadi8, anyextloadi8, ...
|
|
// 3. Address-generation: A64Wrapper, (add BASE, OFFSET), ...
|
|
//
|
|
// The biggest problem turns out to be the address-generation variable. At the
|
|
// point of instantiation we need to produce two DAGs, one for the pattern and
|
|
// one for the instruction. Doing this at the lowest level of classes doesn't
|
|
// work.
|
|
//
|
|
// Consider the simple uimm12 addressing mode, and the desire to match both (add
|
|
// GPR64xsp:$Rn, uimm12:$Offset) and GPR64xsp:$Rn, particularly on the
|
|
// instruction side. We'd need to insert either "GPR64xsp" and "uimm12" or
|
|
// "GPR64xsp" and "0" into an unknown dag. !subst is not capable of this
|
|
// operation, and PatFrags are for selection not output.
|
|
//
|
|
// As a result, the address-generation patterns are the final
|
|
// instantiations. However, we do still need to vary the operand for the address
|
|
// further down (At the point we're deciding A64WrapperSmall, we don't know
|
|
// the memory width of the operation).
|
|
|
|
//===------------------------------
|
|
// 1. Basic infrastructural defs
|
|
//===------------------------------
|
|
|
|
// First, some simple classes for !foreach and !subst to use:
|
|
class Decls {
|
|
dag pattern;
|
|
}
|
|
|
|
def decls : Decls;
|
|
def ALIGN;
|
|
def INST;
|
|
def OFFSET;
|
|
def SHIFT;
|
|
|
|
// You can't use !subst on an actual immediate, but you *can* use it on an
|
|
// operand record that happens to match a single immediate. So we do.
|
|
def imm_eq0 : ImmLeaf<i64, [{ return Imm == 0; }]>;
|
|
def imm_eq1 : ImmLeaf<i64, [{ return Imm == 1; }]>;
|
|
def imm_eq2 : ImmLeaf<i64, [{ return Imm == 2; }]>;
|
|
def imm_eq3 : ImmLeaf<i64, [{ return Imm == 3; }]>;
|
|
def imm_eq4 : ImmLeaf<i64, [{ return Imm == 4; }]>;
|
|
|
|
// If the low bits of a pointer are known to be 0 then an "or" is just as good
|
|
// as addition for computing an offset. This fragment forwards that check for
|
|
// TableGen's use.
|
|
def add_like_or : PatFrag<(ops node:$lhs, node:$rhs), (or node:$lhs, node:$rhs),
|
|
[{
|
|
return CurDAG->isBaseWithConstantOffset(SDValue(N, 0));
|
|
}]>;
|
|
|
|
// Load/store (unsigned immediate) operations with relocations against global
|
|
// symbols (for lo12) are only valid if those symbols have correct alignment
|
|
// (since the immediate offset is divided by the access scale, it can't have a
|
|
// remainder).
|
|
//
|
|
// The guaranteed alignment is provided as part of the WrapperSmall
|
|
// operation, and checked against one of these.
|
|
def any_align : ImmLeaf<i32, [{ (void)Imm; return true; }]>;
|
|
def min_align2 : ImmLeaf<i32, [{ return Imm >= 2; }]>;
|
|
def min_align4 : ImmLeaf<i32, [{ return Imm >= 4; }]>;
|
|
def min_align8 : ImmLeaf<i32, [{ return Imm >= 8; }]>;
|
|
def min_align16 : ImmLeaf<i32, [{ return Imm >= 16; }]>;
|
|
|
|
// "Normal" load/store instructions can be used on atomic operations, provided
|
|
// the ordering parameter is at most "monotonic". Anything above that needs
|
|
// special handling with acquire/release instructions.
|
|
class simple_load<PatFrag base>
|
|
: PatFrag<(ops node:$ptr), (base node:$ptr), [{
|
|
return cast<AtomicSDNode>(N)->getOrdering() <= Monotonic;
|
|
}]>;
|
|
|
|
def atomic_load_simple_i8 : simple_load<atomic_load_8>;
|
|
def atomic_load_simple_i16 : simple_load<atomic_load_16>;
|
|
def atomic_load_simple_i32 : simple_load<atomic_load_32>;
|
|
def atomic_load_simple_i64 : simple_load<atomic_load_64>;
|
|
|
|
class simple_store<PatFrag base>
|
|
: PatFrag<(ops node:$ptr, node:$val), (base node:$ptr, node:$val), [{
|
|
return cast<AtomicSDNode>(N)->getOrdering() <= Monotonic;
|
|
}]>;
|
|
|
|
def atomic_store_simple_i8 : simple_store<atomic_store_8>;
|
|
def atomic_store_simple_i16 : simple_store<atomic_store_16>;
|
|
def atomic_store_simple_i32 : simple_store<atomic_store_32>;
|
|
def atomic_store_simple_i64 : simple_store<atomic_store_64>;
|
|
|
|
//===------------------------------
|
|
// 2. UImm12 and SImm9
|
|
//===------------------------------
|
|
|
|
// These instructions have two operands providing the address so they can be
|
|
// treated similarly for most purposes.
|
|
|
|
//===------------------------------
|
|
// 2.1 Base patterns covering extend/truncate semantics
|
|
//===------------------------------
|
|
|
|
// Atomic patterns can be shared between integer operations of all sizes, a
|
|
// quick multiclass here allows reuse.
|
|
multiclass ls_atomic_pats<Instruction LOAD, Instruction STORE, dag Base,
|
|
dag Offset, dag address, ValueType transty,
|
|
ValueType sty> {
|
|
def : Pat<(!cast<PatFrag>("atomic_load_simple_" # sty) address),
|
|
(LOAD Base, Offset)>;
|
|
|
|
def : Pat<(!cast<PatFrag>("atomic_store_simple_" # sty) address, transty:$Rt),
|
|
(STORE $Rt, Base, Offset)>;
|
|
}
|
|
|
|
// Instructions accessing a memory chunk smaller than a register (or, in a
|
|
// pinch, the same size) have a characteristic set of patterns they want to
|
|
// match: extending loads and truncating stores. This class deals with the
|
|
// sign-neutral version of those patterns.
|
|
//
|
|
// It will be instantiated across multiple addressing-modes.
|
|
multiclass ls_small_pats<Instruction LOAD, Instruction STORE,
|
|
dag Base, dag Offset,
|
|
dag address, ValueType sty>
|
|
: ls_atomic_pats<LOAD, STORE, Base, Offset, address, i32, sty> {
|
|
def : Pat<(!cast<SDNode>(zextload # sty) address), (LOAD Base, Offset)>;
|
|
|
|
def : Pat<(!cast<SDNode>(extload # sty) address), (LOAD Base, Offset)>;
|
|
|
|
// For zero-extension to 64-bits we have to tell LLVM that the whole 64-bit
|
|
// register was actually set.
|
|
def : Pat<(i64 (!cast<SDNode>(zextload # sty) address)),
|
|
(SUBREG_TO_REG (i64 0), (LOAD Base, Offset), sub_32)>;
|
|
|
|
def : Pat<(i64 (!cast<SDNode>(extload # sty) address)),
|
|
(SUBREG_TO_REG (i64 0), (LOAD Base, Offset), sub_32)>;
|
|
|
|
def : Pat<(!cast<SDNode>(truncstore # sty) i32:$Rt, address),
|
|
(STORE $Rt, Base, Offset)>;
|
|
|
|
// For truncating store from 64-bits, we have to manually tell LLVM to
|
|
// ignore the high bits of the x register.
|
|
def : Pat<(!cast<SDNode>(truncstore # sty) i64:$Rt, address),
|
|
(STORE (EXTRACT_SUBREG $Rt, sub_32), Base, Offset)>;
|
|
}
|
|
|
|
// Next come patterns for sign-extending loads.
|
|
multiclass load_signed_pats<string T, string U, dag Base, dag Offset,
|
|
dag address, ValueType sty> {
|
|
def : Pat<(i32 (!cast<SDNode>("sextload" # sty) address)),
|
|
(!cast<Instruction>("LDRS" # T # "w" # U) Base, Offset)>;
|
|
|
|
def : Pat<(i64 (!cast<SDNode>("sextload" # sty) address)),
|
|
(!cast<Instruction>("LDRS" # T # "x" # U) Base, Offset)>;
|
|
|
|
}
|
|
|
|
// and finally "natural-width" loads and stores come next.
|
|
multiclass ls_neutral_pats<Instruction LOAD, Instruction STORE, dag Base,
|
|
dag Offset, dag address, ValueType sty> {
|
|
def : Pat<(sty (load address)), (LOAD Base, Offset)>;
|
|
def : Pat<(store sty:$Rt, address), (STORE $Rt, Base, Offset)>;
|
|
}
|
|
|
|
// Integer operations also get atomic instructions to select for.
|
|
multiclass ls_int_neutral_pats<Instruction LOAD, Instruction STORE, dag Base,
|
|
dag Offset, dag address, ValueType sty>
|
|
: ls_neutral_pats<LOAD, STORE, Base, Offset, address, sty>,
|
|
ls_atomic_pats<LOAD, STORE, Base, Offset, address, sty, sty>;
|
|
|
|
//===------------------------------
|
|
// 2.2. Addressing-mode instantiations
|
|
//===------------------------------
|
|
|
|
multiclass uimm12_pats<dag address, dag Base, dag Offset> {
|
|
defm : ls_small_pats<LS8_LDR, LS8_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, byte_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, byte_uimm12,
|
|
!subst(ALIGN, any_align, decls.pattern))),
|
|
i8>;
|
|
defm : ls_small_pats<LS16_LDR, LS16_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, hword_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, hword_uimm12,
|
|
!subst(ALIGN, min_align2, decls.pattern))),
|
|
i16>;
|
|
defm : ls_small_pats<LS32_LDR, LS32_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, word_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, word_uimm12,
|
|
!subst(ALIGN, min_align4, decls.pattern))),
|
|
i32>;
|
|
|
|
defm : ls_int_neutral_pats<LS32_LDR, LS32_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, word_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, word_uimm12,
|
|
!subst(ALIGN, min_align4, decls.pattern))),
|
|
i32>;
|
|
|
|
defm : ls_int_neutral_pats<LS64_LDR, LS64_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, dword_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, dword_uimm12,
|
|
!subst(ALIGN, min_align8, decls.pattern))),
|
|
i64>;
|
|
|
|
defm : ls_neutral_pats<LSFP16_LDR, LSFP16_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, hword_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, hword_uimm12,
|
|
!subst(ALIGN, min_align2, decls.pattern))),
|
|
f16>;
|
|
|
|
defm : ls_neutral_pats<LSFP32_LDR, LSFP32_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, word_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, word_uimm12,
|
|
!subst(ALIGN, min_align4, decls.pattern))),
|
|
f32>;
|
|
|
|
defm : ls_neutral_pats<LSFP64_LDR, LSFP64_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, dword_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, dword_uimm12,
|
|
!subst(ALIGN, min_align8, decls.pattern))),
|
|
f64>;
|
|
|
|
defm : ls_neutral_pats<LSFP128_LDR, LSFP128_STR, Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, qword_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, qword_uimm12,
|
|
!subst(ALIGN, min_align16, decls.pattern))),
|
|
f128>;
|
|
|
|
defm : load_signed_pats<"B", "", Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, byte_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, byte_uimm12,
|
|
!subst(ALIGN, any_align, decls.pattern))),
|
|
i8>;
|
|
|
|
defm : load_signed_pats<"H", "", Base,
|
|
!foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, hword_uimm12, decls.pattern)),
|
|
!foreach(decls.pattern, address,
|
|
!subst(OFFSET, hword_uimm12,
|
|
!subst(ALIGN, min_align2, decls.pattern))),
|
|
i16>;
|
|
|
|
def : Pat<(sextloadi32 !foreach(decls.pattern, address,
|
|
!subst(OFFSET, word_uimm12,
|
|
!subst(ALIGN, min_align4, decls.pattern)))),
|
|
(LDRSWx Base, !foreach(decls.pattern, Offset,
|
|
!subst(OFFSET, word_uimm12, decls.pattern)))>;
|
|
}
|
|
|
|
// Straightforward patterns of last resort: a pointer with or without an
|
|
// appropriate offset.
|
|
defm : uimm12_pats<(i64 i64:$Rn), (i64 i64:$Rn), (i64 0)>;
|
|
defm : uimm12_pats<(add i64:$Rn, OFFSET:$UImm12),
|
|
(i64 i64:$Rn), (i64 OFFSET:$UImm12)>;
|
|
|
|
// The offset could be hidden behind an "or", of course:
|
|
defm : uimm12_pats<(add_like_or i64:$Rn, OFFSET:$UImm12),
|
|
(i64 i64:$Rn), (i64 OFFSET:$UImm12)>;
|
|
|
|
// Global addresses under the small-absolute model should use these
|
|
// instructions. There are ELF relocations specifically for it.
|
|
defm : uimm12_pats<(A64WrapperSmall tglobaladdr:$Hi, tglobaladdr:$Lo12, ALIGN),
|
|
(ADRPxi tglobaladdr:$Hi), (i64 tglobaladdr:$Lo12)>;
|
|
|
|
defm : uimm12_pats<(A64WrapperSmall tglobaltlsaddr:$Hi, tglobaltlsaddr:$Lo12,
|
|
ALIGN),
|
|
(ADRPxi tglobaltlsaddr:$Hi), (i64 tglobaltlsaddr:$Lo12)>;
|
|
|
|
// External symbols that make it this far should also get standard relocations.
|
|
defm : uimm12_pats<(A64WrapperSmall texternalsym:$Hi, texternalsym:$Lo12,
|
|
ALIGN),
|
|
(ADRPxi texternalsym:$Hi), (i64 texternalsym:$Lo12)>;
|
|
|
|
defm : uimm12_pats<(A64WrapperSmall tconstpool:$Hi, tconstpool:$Lo12, ALIGN),
|
|
(ADRPxi tconstpool:$Hi), (i64 tconstpool:$Lo12)>;
|
|
|
|
// We also want to use uimm12 instructions for local variables at the moment.
|
|
def tframeindex_XFORM : SDNodeXForm<frameindex, [{
|
|
int FI = cast<FrameIndexSDNode>(N)->getIndex();
|
|
return CurDAG->getTargetFrameIndex(FI, MVT::i64);
|
|
}]>;
|
|
|
|
defm : uimm12_pats<(i64 frameindex:$Rn),
|
|
(tframeindex_XFORM tframeindex:$Rn), (i64 0)>;
|
|
|
|
// These can be much simpler than uimm12 because we don't to change the operand
|
|
// type (e.g. LDURB and LDURH take the same operands).
|
|
multiclass simm9_pats<dag address, dag Base, dag Offset> {
|
|
defm : ls_small_pats<LS8_LDUR, LS8_STUR, Base, Offset, address, i8>;
|
|
defm : ls_small_pats<LS16_LDUR, LS16_STUR, Base, Offset, address, i16>;
|
|
|
|
defm : ls_int_neutral_pats<LS32_LDUR, LS32_STUR, Base, Offset, address, i32>;
|
|
defm : ls_int_neutral_pats<LS64_LDUR, LS64_STUR, Base, Offset, address, i64>;
|
|
|
|
defm : ls_neutral_pats<LSFP16_LDUR, LSFP16_STUR, Base, Offset, address, f16>;
|
|
defm : ls_neutral_pats<LSFP32_LDUR, LSFP32_STUR, Base, Offset, address, f32>;
|
|
defm : ls_neutral_pats<LSFP64_LDUR, LSFP64_STUR, Base, Offset, address, f64>;
|
|
defm : ls_neutral_pats<LSFP128_LDUR, LSFP128_STUR, Base, Offset, address,
|
|
f128>;
|
|
|
|
def : Pat<(i64 (zextloadi32 address)),
|
|
(SUBREG_TO_REG (i64 0), (LS32_LDUR Base, Offset), sub_32)>;
|
|
|
|
def : Pat<(truncstorei32 i64:$Rt, address),
|
|
(LS32_STUR (EXTRACT_SUBREG $Rt, sub_32), Base, Offset)>;
|
|
|
|
defm : load_signed_pats<"B", "_U", Base, Offset, address, i8>;
|
|
defm : load_signed_pats<"H", "_U", Base, Offset, address, i16>;
|
|
def : Pat<(sextloadi32 address), (LDURSWx Base, Offset)>;
|
|
}
|
|
|
|
defm : simm9_pats<(add i64:$Rn, simm9:$SImm9),
|
|
(i64 $Rn), (SDXF_simm9 simm9:$SImm9)>;
|
|
|
|
defm : simm9_pats<(add_like_or i64:$Rn, simm9:$SImm9),
|
|
(i64 $Rn), (SDXF_simm9 simm9:$SImm9)>;
|
|
|
|
|
|
//===------------------------------
|
|
// 3. Register offset patterns
|
|
//===------------------------------
|
|
|
|
// Atomic patterns can be shared between integer operations of all sizes, a
|
|
// quick multiclass here allows reuse.
|
|
multiclass ro_atomic_pats<Instruction LOAD, Instruction STORE, dag Base,
|
|
dag Offset, dag Extend, dag address,
|
|
ValueType transty, ValueType sty> {
|
|
def : Pat<(!cast<PatFrag>("atomic_load_simple_" # sty) address),
|
|
(LOAD Base, Offset, Extend)>;
|
|
|
|
def : Pat<(!cast<PatFrag>("atomic_store_simple_" # sty) address, transty:$Rt),
|
|
(STORE $Rt, Base, Offset, Extend)>;
|
|
}
|
|
|
|
// The register offset instructions take three operands giving the instruction,
|
|
// and have an annoying split between instructions where Rm is 32-bit and
|
|
// 64-bit. So we need a special hierarchy to describe them. Other than that the
|
|
// same operations should be supported as for simm9 and uimm12 addressing.
|
|
|
|
multiclass ro_small_pats<Instruction LOAD, Instruction STORE,
|
|
dag Base, dag Offset, dag Extend,
|
|
dag address, ValueType sty>
|
|
: ro_atomic_pats<LOAD, STORE, Base, Offset, Extend, address, i32, sty> {
|
|
def : Pat<(!cast<SDNode>(zextload # sty) address),
|
|
(LOAD Base, Offset, Extend)>;
|
|
|
|
def : Pat<(!cast<SDNode>(extload # sty) address),
|
|
(LOAD Base, Offset, Extend)>;
|
|
|
|
// For zero-extension to 64-bits we have to tell LLVM that the whole 64-bit
|
|
// register was actually set.
|
|
def : Pat<(i64 (!cast<SDNode>(zextload # sty) address)),
|
|
(SUBREG_TO_REG (i64 0), (LOAD Base, Offset, Extend), sub_32)>;
|
|
|
|
def : Pat<(i64 (!cast<SDNode>(extload # sty) address)),
|
|
(SUBREG_TO_REG (i64 0), (LOAD Base, Offset, Extend), sub_32)>;
|
|
|
|
def : Pat<(!cast<SDNode>(truncstore # sty) i32:$Rt, address),
|
|
(STORE $Rt, Base, Offset, Extend)>;
|
|
|
|
// For truncating store from 64-bits, we have to manually tell LLVM to
|
|
// ignore the high bits of the x register.
|
|
def : Pat<(!cast<SDNode>(truncstore # sty) i64:$Rt, address),
|
|
(STORE (EXTRACT_SUBREG $Rt, sub_32), Base, Offset, Extend)>;
|
|
|
|
}
|
|
|
|
// Next come patterns for sign-extending loads.
|
|
multiclass ro_signed_pats<string T, string Rm, dag Base, dag Offset, dag Extend,
|
|
dag address, ValueType sty> {
|
|
def : Pat<(i32 (!cast<SDNode>("sextload" # sty) address)),
|
|
(!cast<Instruction>("LDRS" # T # "w_" # Rm # "_RegOffset")
|
|
Base, Offset, Extend)>;
|
|
|
|
def : Pat<(i64 (!cast<SDNode>("sextload" # sty) address)),
|
|
(!cast<Instruction>("LDRS" # T # "x_" # Rm # "_RegOffset")
|
|
Base, Offset, Extend)>;
|
|
}
|
|
|
|
// and finally "natural-width" loads and stores come next.
|
|
multiclass ro_neutral_pats<Instruction LOAD, Instruction STORE,
|
|
dag Base, dag Offset, dag Extend, dag address,
|
|
ValueType sty> {
|
|
def : Pat<(sty (load address)), (LOAD Base, Offset, Extend)>;
|
|
def : Pat<(store sty:$Rt, address),
|
|
(STORE $Rt, Base, Offset, Extend)>;
|
|
}
|
|
|
|
multiclass ro_int_neutral_pats<Instruction LOAD, Instruction STORE,
|
|
dag Base, dag Offset, dag Extend, dag address,
|
|
ValueType sty>
|
|
: ro_neutral_pats<LOAD, STORE, Base, Offset, Extend, address, sty>,
|
|
ro_atomic_pats<LOAD, STORE, Base, Offset, Extend, address, sty, sty>;
|
|
|
|
multiclass regoff_pats<string Rm, dag address, dag Base, dag Offset,
|
|
dag Extend> {
|
|
defm : ro_small_pats<!cast<Instruction>("LS8_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LS8_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq0, decls.pattern)),
|
|
i8>;
|
|
defm : ro_small_pats<!cast<Instruction>("LS16_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LS16_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq1, decls.pattern)),
|
|
i16>;
|
|
defm : ro_small_pats<!cast<Instruction>("LS32_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LS32_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq2, decls.pattern)),
|
|
i32>;
|
|
|
|
defm : ro_int_neutral_pats<
|
|
!cast<Instruction>("LS32_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LS32_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq2, decls.pattern)),
|
|
i32>;
|
|
|
|
defm : ro_int_neutral_pats<
|
|
!cast<Instruction>("LS64_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LS64_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq3, decls.pattern)),
|
|
i64>;
|
|
|
|
defm : ro_neutral_pats<!cast<Instruction>("LSFP16_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LSFP16_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq1, decls.pattern)),
|
|
f16>;
|
|
|
|
defm : ro_neutral_pats<!cast<Instruction>("LSFP32_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LSFP32_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq2, decls.pattern)),
|
|
f32>;
|
|
|
|
defm : ro_neutral_pats<!cast<Instruction>("LSFP64_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LSFP64_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq3, decls.pattern)),
|
|
f64>;
|
|
|
|
defm : ro_neutral_pats<!cast<Instruction>("LSFP128_" # Rm # "_RegOffset_LDR"),
|
|
!cast<Instruction>("LSFP128_" # Rm # "_RegOffset_STR"),
|
|
Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq4, decls.pattern)),
|
|
f128>;
|
|
|
|
defm : ro_signed_pats<"B", Rm, Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq0, decls.pattern)),
|
|
i8>;
|
|
|
|
defm : ro_signed_pats<"H", Rm, Base, Offset, Extend,
|
|
!foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq1, decls.pattern)),
|
|
i16>;
|
|
|
|
def : Pat<(sextloadi32 !foreach(decls.pattern, address,
|
|
!subst(SHIFT, imm_eq2, decls.pattern))),
|
|
(!cast<Instruction>("LDRSWx_" # Rm # "_RegOffset")
|
|
Base, Offset, Extend)>;
|
|
}
|
|
|
|
|
|
// Finally we're in a position to tell LLVM exactly what addresses are reachable
|
|
// using register-offset instructions. Essentially a base plus a possibly
|
|
// extended, possibly shifted (by access size) offset.
|
|
|
|
defm : regoff_pats<"Wm", (add i64:$Rn, (sext i32:$Rm)),
|
|
(i64 i64:$Rn), (i32 i32:$Rm), (i64 6)>;
|
|
|
|
defm : regoff_pats<"Wm", (add i64:$Rn, (shl (sext i32:$Rm), SHIFT)),
|
|
(i64 i64:$Rn), (i32 i32:$Rm), (i64 7)>;
|
|
|
|
defm : regoff_pats<"Wm", (add i64:$Rn, (zext i32:$Rm)),
|
|
(i64 i64:$Rn), (i32 i32:$Rm), (i64 2)>;
|
|
|
|
defm : regoff_pats<"Wm", (add i64:$Rn, (shl (zext i32:$Rm), SHIFT)),
|
|
(i64 i64:$Rn), (i32 i32:$Rm), (i64 3)>;
|
|
|
|
defm : regoff_pats<"Xm", (add i64:$Rn, i64:$Rm),
|
|
(i64 i64:$Rn), (i64 i64:$Rm), (i64 2)>;
|
|
|
|
defm : regoff_pats<"Xm", (add i64:$Rn, (shl i64:$Rm, SHIFT)),
|
|
(i64 i64:$Rn), (i64 i64:$Rm), (i64 3)>;
|