forked from OSchip/llvm-project
8213 lines
307 KiB
TableGen
8213 lines
307 KiB
TableGen
//===- ARM64InstrFormats.td - ARM64 Instruction Formats ------*- tblgen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Describe ARM64 instructions format here
|
|
//
|
|
|
|
// Format specifies the encoding used by the instruction. This is part of the
|
|
// ad-hoc solution used to emit machine instruction encodings by our machine
|
|
// code emitter.
|
|
class Format<bits<2> val> {
|
|
bits<2> Value = val;
|
|
}
|
|
|
|
def PseudoFrm : Format<0>;
|
|
def NormalFrm : Format<1>; // Do we need any others?
|
|
|
|
// ARM64 Instruction Format
|
|
class ARM64Inst<Format f, string cstr> : Instruction {
|
|
field bits<32> Inst; // Instruction encoding.
|
|
// Mask of bits that cause an encoding to be UNPREDICTABLE.
|
|
// If a bit is set, then if the corresponding bit in the
|
|
// target encoding differs from its value in the "Inst" field,
|
|
// the instruction is UNPREDICTABLE (SoftFail in abstract parlance).
|
|
field bits<32> Unpredictable = 0;
|
|
// SoftFail is the generic name for this field, but we alias it so
|
|
// as to make it more obvious what it means in ARM-land.
|
|
field bits<32> SoftFail = Unpredictable;
|
|
let Namespace = "ARM64";
|
|
Format F = f;
|
|
bits<2> Form = F.Value;
|
|
let Pattern = [];
|
|
let Constraints = cstr;
|
|
}
|
|
|
|
// Pseudo instructions (don't have encoding information)
|
|
class Pseudo<dag oops, dag iops, list<dag> pattern, string cstr = "">
|
|
: ARM64Inst<PseudoFrm, cstr> {
|
|
dag OutOperandList = oops;
|
|
dag InOperandList = iops;
|
|
let Pattern = pattern;
|
|
let isCodeGenOnly = 1;
|
|
}
|
|
|
|
// Real instructions (have encoding information)
|
|
class EncodedI<string cstr, list<dag> pattern> : ARM64Inst<NormalFrm, cstr> {
|
|
let Pattern = pattern;
|
|
let Size = 4;
|
|
}
|
|
|
|
// Normal instructions
|
|
class I<dag oops, dag iops, string asm, string operands, string cstr,
|
|
list<dag> pattern>
|
|
: EncodedI<cstr, pattern> {
|
|
dag OutOperandList = oops;
|
|
dag InOperandList = iops;
|
|
let AsmString = !strconcat(asm, operands);
|
|
}
|
|
|
|
class TriOpFrag<dag res> : PatFrag<(ops node:$LHS, node:$MHS, node:$RHS), res>;
|
|
class BinOpFrag<dag res> : PatFrag<(ops node:$LHS, node:$RHS), res>;
|
|
class UnOpFrag<dag res> : PatFrag<(ops node:$LHS), res>;
|
|
|
|
// Helper fragment for an extract of the high portion of a 128-bit vector.
|
|
def extract_high_v16i8 :
|
|
UnOpFrag<(extract_subvector (v16i8 node:$LHS), (i64 8))>;
|
|
def extract_high_v8i16 :
|
|
UnOpFrag<(extract_subvector (v8i16 node:$LHS), (i64 4))>;
|
|
def extract_high_v4i32 :
|
|
UnOpFrag<(extract_subvector (v4i32 node:$LHS), (i64 2))>;
|
|
def extract_high_v2i64 :
|
|
UnOpFrag<(extract_subvector (v2i64 node:$LHS), (i64 1))>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Asm Operand Classes.
|
|
//
|
|
|
|
// Shifter operand for arithmetic shifted encodings.
|
|
def ShifterOperand : AsmOperandClass {
|
|
let Name = "Shifter";
|
|
}
|
|
|
|
// Shifter operand for mov immediate encodings.
|
|
def MovImm32ShifterOperand : AsmOperandClass {
|
|
let SuperClasses = [ShifterOperand];
|
|
let Name = "MovImm32Shifter";
|
|
}
|
|
def MovImm64ShifterOperand : AsmOperandClass {
|
|
let SuperClasses = [ShifterOperand];
|
|
let Name = "MovImm64Shifter";
|
|
}
|
|
|
|
// Shifter operand for arithmetic register shifted encodings.
|
|
def ArithmeticShifterOperand : AsmOperandClass {
|
|
let SuperClasses = [ShifterOperand];
|
|
let Name = "ArithmeticShifter";
|
|
}
|
|
|
|
// Shifter operand for arithmetic shifted encodings for ADD/SUB instructions.
|
|
def AddSubShifterOperand : AsmOperandClass {
|
|
let SuperClasses = [ArithmeticShifterOperand];
|
|
let Name = "AddSubShifter";
|
|
}
|
|
|
|
// Shifter operand for logical vector 128/64-bit shifted encodings.
|
|
def LogicalVecShifterOperand : AsmOperandClass {
|
|
let SuperClasses = [ShifterOperand];
|
|
let Name = "LogicalVecShifter";
|
|
}
|
|
def LogicalVecHalfWordShifterOperand : AsmOperandClass {
|
|
let SuperClasses = [LogicalVecShifterOperand];
|
|
let Name = "LogicalVecHalfWordShifter";
|
|
}
|
|
|
|
// The "MSL" shifter on the vector MOVI instruction.
|
|
def MoveVecShifterOperand : AsmOperandClass {
|
|
let SuperClasses = [ShifterOperand];
|
|
let Name = "MoveVecShifter";
|
|
}
|
|
|
|
// Extend operand for arithmetic encodings.
|
|
def ExtendOperand : AsmOperandClass { let Name = "Extend"; }
|
|
def ExtendOperand64 : AsmOperandClass {
|
|
let SuperClasses = [ExtendOperand];
|
|
let Name = "Extend64";
|
|
}
|
|
// 'extend' that's a lsl of a 64-bit register.
|
|
def ExtendOperandLSL64 : AsmOperandClass {
|
|
let SuperClasses = [ExtendOperand];
|
|
let Name = "ExtendLSL64";
|
|
}
|
|
|
|
// 8-bit floating-point immediate encodings.
|
|
def FPImmOperand : AsmOperandClass {
|
|
let Name = "FPImm";
|
|
let ParserMethod = "tryParseFPImm";
|
|
}
|
|
|
|
// 8-bit immediate for AdvSIMD where 64-bit values of the form:
|
|
// aaaaaaaa bbbbbbbb cccccccc dddddddd eeeeeeee ffffffff gggggggg hhhhhhhh
|
|
// are encoded as the eight bit value 'abcdefgh'.
|
|
def SIMDImmType10Operand : AsmOperandClass { let Name = "SIMDImmType10"; }
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Operand Definitions.
|
|
//
|
|
|
|
// ADR[P] instruction labels.
|
|
def AdrpOperand : AsmOperandClass {
|
|
let Name = "AdrpLabel";
|
|
let ParserMethod = "tryParseAdrpLabel";
|
|
}
|
|
def adrplabel : Operand<i64> {
|
|
let EncoderMethod = "getAdrLabelOpValue";
|
|
let PrintMethod = "printAdrpLabel";
|
|
let ParserMatchClass = AdrpOperand;
|
|
}
|
|
|
|
def AdrOperand : AsmOperandClass {
|
|
let Name = "AdrLabel";
|
|
let ParserMethod = "tryParseAdrLabel";
|
|
}
|
|
def adrlabel : Operand<i64> {
|
|
let EncoderMethod = "getAdrLabelOpValue";
|
|
let ParserMatchClass = AdrOperand;
|
|
}
|
|
|
|
// simm9 predicate - True if the immediate is in the range [-256, 255].
|
|
def SImm9Operand : AsmOperandClass {
|
|
let Name = "SImm9";
|
|
let DiagnosticType = "InvalidMemoryIndexedSImm9";
|
|
}
|
|
def simm9 : Operand<i64>, ImmLeaf<i64, [{ return Imm >= -256 && Imm < 256; }]> {
|
|
let ParserMatchClass = SImm9Operand;
|
|
}
|
|
|
|
// simm7s4 predicate - True if the immediate is a multiple of 4 in the range
|
|
// [-256, 252].
|
|
def SImm7s4Operand : AsmOperandClass {
|
|
let Name = "SImm7s4";
|
|
let DiagnosticType = "InvalidMemoryIndexed32SImm7";
|
|
}
|
|
def simm7s4 : Operand<i32> {
|
|
let ParserMatchClass = SImm7s4Operand;
|
|
let PrintMethod = "printImmScale4";
|
|
}
|
|
|
|
// simm7s8 predicate - True if the immediate is a multiple of 8 in the range
|
|
// [-512, 504].
|
|
def SImm7s8Operand : AsmOperandClass {
|
|
let Name = "SImm7s8";
|
|
let DiagnosticType = "InvalidMemoryIndexed64SImm7";
|
|
}
|
|
def simm7s8 : Operand<i32> {
|
|
let ParserMatchClass = SImm7s8Operand;
|
|
let PrintMethod = "printImmScale8";
|
|
}
|
|
|
|
// simm7s16 predicate - True if the immediate is a multiple of 16 in the range
|
|
// [-1024, 1008].
|
|
def SImm7s16Operand : AsmOperandClass {
|
|
let Name = "SImm7s16";
|
|
let DiagnosticType = "InvalidMemoryIndexed64SImm7";
|
|
}
|
|
def simm7s16 : Operand<i32> {
|
|
let ParserMatchClass = SImm7s16Operand;
|
|
let PrintMethod = "printImmScale16";
|
|
}
|
|
|
|
// imm0_65535 predicate - True if the immediate is in the range [0,65535].
|
|
def Imm0_65535Operand : AsmOperandClass { let Name = "Imm0_65535"; }
|
|
def imm0_65535 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint32_t)Imm) < 65536;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_65535Operand;
|
|
}
|
|
|
|
def Imm1_8Operand : AsmOperandClass {
|
|
let Name = "Imm1_8";
|
|
let DiagnosticType = "InvalidImm1_8";
|
|
}
|
|
def Imm1_16Operand : AsmOperandClass {
|
|
let Name = "Imm1_16";
|
|
let DiagnosticType = "InvalidImm1_16";
|
|
}
|
|
def Imm1_32Operand : AsmOperandClass {
|
|
let Name = "Imm1_32";
|
|
let DiagnosticType = "InvalidImm1_32";
|
|
}
|
|
def Imm1_64Operand : AsmOperandClass {
|
|
let Name = "Imm1_64";
|
|
let DiagnosticType = "InvalidImm1_64";
|
|
}
|
|
|
|
def MovZSymbolG3AsmOperand : AsmOperandClass {
|
|
let Name = "MovZSymbolG3";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def movz_symbol_g3 : Operand<i32> {
|
|
let ParserMatchClass = MovZSymbolG3AsmOperand;
|
|
}
|
|
|
|
def MovZSymbolG2AsmOperand : AsmOperandClass {
|
|
let Name = "MovZSymbolG2";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def movz_symbol_g2 : Operand<i32> {
|
|
let ParserMatchClass = MovZSymbolG2AsmOperand;
|
|
}
|
|
|
|
def MovZSymbolG1AsmOperand : AsmOperandClass {
|
|
let Name = "MovZSymbolG1";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def movz_symbol_g1 : Operand<i32> {
|
|
let ParserMatchClass = MovZSymbolG1AsmOperand;
|
|
}
|
|
|
|
def MovZSymbolG0AsmOperand : AsmOperandClass {
|
|
let Name = "MovZSymbolG0";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def movz_symbol_g0 : Operand<i32> {
|
|
let ParserMatchClass = MovZSymbolG0AsmOperand;
|
|
}
|
|
|
|
def MovKSymbolG2AsmOperand : AsmOperandClass {
|
|
let Name = "MovKSymbolG2";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def movk_symbol_g2 : Operand<i32> {
|
|
let ParserMatchClass = MovKSymbolG2AsmOperand;
|
|
}
|
|
|
|
def MovKSymbolG1AsmOperand : AsmOperandClass {
|
|
let Name = "MovKSymbolG1";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def movk_symbol_g1 : Operand<i32> {
|
|
let ParserMatchClass = MovKSymbolG1AsmOperand;
|
|
}
|
|
|
|
def MovKSymbolG0AsmOperand : AsmOperandClass {
|
|
let Name = "MovKSymbolG0";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def movk_symbol_g0 : Operand<i32> {
|
|
let ParserMatchClass = MovKSymbolG0AsmOperand;
|
|
}
|
|
|
|
def fixedpoint32 : Operand<i32> {
|
|
let EncoderMethod = "getFixedPointScaleOpValue";
|
|
let DecoderMethod = "DecodeFixedPointScaleImm";
|
|
let ParserMatchClass = Imm1_32Operand;
|
|
}
|
|
def fixedpoint64 : Operand<i64> {
|
|
let EncoderMethod = "getFixedPointScaleOpValue";
|
|
let DecoderMethod = "DecodeFixedPointScaleImm";
|
|
let ParserMatchClass = Imm1_64Operand;
|
|
}
|
|
|
|
def vecshiftR8 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) > 0) && (((uint32_t)Imm) < 9);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftR8OpValue";
|
|
let DecoderMethod = "DecodeVecShiftR8Imm";
|
|
let ParserMatchClass = Imm1_8Operand;
|
|
}
|
|
def vecshiftR16 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) > 0) && (((uint32_t)Imm) < 17);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftR16OpValue";
|
|
let DecoderMethod = "DecodeVecShiftR16Imm";
|
|
let ParserMatchClass = Imm1_16Operand;
|
|
}
|
|
def vecshiftR16Narrow : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) > 0) && (((uint32_t)Imm) < 9);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftR16OpValue";
|
|
let DecoderMethod = "DecodeVecShiftR16ImmNarrow";
|
|
let ParserMatchClass = Imm1_8Operand;
|
|
}
|
|
def vecshiftR32 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) > 0) && (((uint32_t)Imm) < 33);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftR32OpValue";
|
|
let DecoderMethod = "DecodeVecShiftR32Imm";
|
|
let ParserMatchClass = Imm1_32Operand;
|
|
}
|
|
def vecshiftR32Narrow : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) > 0) && (((uint32_t)Imm) < 17);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftR32OpValue";
|
|
let DecoderMethod = "DecodeVecShiftR32ImmNarrow";
|
|
let ParserMatchClass = Imm1_16Operand;
|
|
}
|
|
def vecshiftR64 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) > 0) && (((uint32_t)Imm) < 65);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftR64OpValue";
|
|
let DecoderMethod = "DecodeVecShiftR64Imm";
|
|
let ParserMatchClass = Imm1_64Operand;
|
|
}
|
|
def vecshiftR64Narrow : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) > 0) && (((uint32_t)Imm) < 33);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftR64OpValue";
|
|
let DecoderMethod = "DecodeVecShiftR64ImmNarrow";
|
|
let ParserMatchClass = Imm1_32Operand;
|
|
}
|
|
|
|
def Imm0_7Operand : AsmOperandClass { let Name = "Imm0_7"; }
|
|
def Imm0_15Operand : AsmOperandClass { let Name = "Imm0_15"; }
|
|
def Imm0_31Operand : AsmOperandClass { let Name = "Imm0_31"; }
|
|
def Imm0_63Operand : AsmOperandClass { let Name = "Imm0_63"; }
|
|
|
|
def vecshiftL8 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) < 8);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftL8OpValue";
|
|
let DecoderMethod = "DecodeVecShiftL8Imm";
|
|
let ParserMatchClass = Imm0_7Operand;
|
|
}
|
|
def vecshiftL16 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) < 16);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftL16OpValue";
|
|
let DecoderMethod = "DecodeVecShiftL16Imm";
|
|
let ParserMatchClass = Imm0_15Operand;
|
|
}
|
|
def vecshiftL32 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) < 32);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftL32OpValue";
|
|
let DecoderMethod = "DecodeVecShiftL32Imm";
|
|
let ParserMatchClass = Imm0_31Operand;
|
|
}
|
|
def vecshiftL64 : Operand<i32>, ImmLeaf<i32, [{
|
|
return (((uint32_t)Imm) < 64);
|
|
}]> {
|
|
let EncoderMethod = "getVecShiftL64OpValue";
|
|
let DecoderMethod = "DecodeVecShiftL64Imm";
|
|
let ParserMatchClass = Imm0_63Operand;
|
|
}
|
|
|
|
|
|
// Crazy immediate formats used by 32-bit and 64-bit logical immediate
|
|
// instructions for splatting repeating bit patterns across the immediate.
|
|
def logical_imm32_XFORM : SDNodeXForm<imm, [{
|
|
uint64_t enc = ARM64_AM::encodeLogicalImmediate(N->getZExtValue(), 32);
|
|
return CurDAG->getTargetConstant(enc, MVT::i32);
|
|
}]>;
|
|
def logical_imm64_XFORM : SDNodeXForm<imm, [{
|
|
uint64_t enc = ARM64_AM::encodeLogicalImmediate(N->getZExtValue(), 64);
|
|
return CurDAG->getTargetConstant(enc, MVT::i32);
|
|
}]>;
|
|
|
|
def LogicalImm32Operand : AsmOperandClass { let Name = "LogicalImm32"; }
|
|
def LogicalImm64Operand : AsmOperandClass { let Name = "LogicalImm64"; }
|
|
def logical_imm32 : Operand<i32>, PatLeaf<(imm), [{
|
|
return ARM64_AM::isLogicalImmediate(N->getZExtValue(), 32);
|
|
}], logical_imm32_XFORM> {
|
|
let PrintMethod = "printLogicalImm32";
|
|
let ParserMatchClass = LogicalImm32Operand;
|
|
}
|
|
def logical_imm64 : Operand<i64>, PatLeaf<(imm), [{
|
|
return ARM64_AM::isLogicalImmediate(N->getZExtValue(), 64);
|
|
}], logical_imm64_XFORM> {
|
|
let PrintMethod = "printLogicalImm64";
|
|
let ParserMatchClass = LogicalImm64Operand;
|
|
}
|
|
|
|
// imm0_255 predicate - True if the immediate is in the range [0,255].
|
|
def Imm0_255Operand : AsmOperandClass { let Name = "Imm0_255"; }
|
|
def imm0_255 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint32_t)Imm) < 256;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_255Operand;
|
|
}
|
|
|
|
// imm0_127 predicate - True if the immediate is in the range [0,127]
|
|
def Imm0_127Operand : AsmOperandClass { let Name = "Imm0_127"; }
|
|
def imm0_127 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint32_t)Imm) < 128;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_127Operand;
|
|
}
|
|
|
|
// imm0_63 predicate - True if the immediate is in the range [0,63]
|
|
// NOTE: This has to be of type i64 because i64 is the shift-amount-size
|
|
// for X registers.
|
|
def imm0_63 : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 64;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_63Operand;
|
|
}
|
|
|
|
// imm0_31x predicate - True if the immediate is in the range [0,31]
|
|
// NOTE: This has to be of type i64 because i64 is the shift-amount-size
|
|
// for X registers.
|
|
def imm0_31x : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 32;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_31Operand;
|
|
}
|
|
|
|
// imm0_15x predicate - True if the immediate is in the range [0,15]
|
|
def imm0_15x : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 16;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_15Operand;
|
|
}
|
|
|
|
// imm0_7x predicate - True if the immediate is in the range [0,7]
|
|
def imm0_7x : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 8;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_7Operand;
|
|
}
|
|
|
|
// imm0_31 predicate - True if the immediate is in the range [0,31]
|
|
// NOTE: This has to be of type i32 because i32 is the shift-amount-size
|
|
// for W registers.
|
|
def imm0_31 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint32_t)Imm) < 32;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_31Operand;
|
|
}
|
|
|
|
// imm0_15 predicate - True if the immediate is in the range [0,15]
|
|
def imm0_15 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint32_t)Imm) < 16;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_15Operand;
|
|
}
|
|
|
|
// imm0_7 predicate - True if the immediate is in the range [0,7]
|
|
def imm0_7 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint32_t)Imm) < 8;
|
|
}]> {
|
|
let ParserMatchClass = Imm0_7Operand;
|
|
}
|
|
|
|
// An arithmetic shifter operand:
|
|
// {7-6} - shift type: 00 = lsl, 01 = lsr, 10 = asr
|
|
// {5-0} - imm6
|
|
def arith_shift : Operand<i32> {
|
|
let PrintMethod = "printShifter";
|
|
let ParserMatchClass = ArithmeticShifterOperand;
|
|
}
|
|
|
|
class arith_shifted_reg<ValueType Ty, RegisterClass regclass>
|
|
: Operand<Ty>,
|
|
ComplexPattern<Ty, 2, "SelectArithShiftedRegister", []> {
|
|
let PrintMethod = "printShiftedRegister";
|
|
let MIOperandInfo = (ops regclass, arith_shift);
|
|
}
|
|
|
|
def arith_shifted_reg32 : arith_shifted_reg<i32, GPR32>;
|
|
def arith_shifted_reg64 : arith_shifted_reg<i64, GPR64>;
|
|
|
|
// An arithmetic shifter operand:
|
|
// {7-6} - shift type: 00 = lsl, 01 = lsr, 10 = asr, 11 = ror
|
|
// {5-0} - imm6
|
|
def logical_shift : Operand<i32> {
|
|
let PrintMethod = "printShifter";
|
|
let ParserMatchClass = ShifterOperand;
|
|
}
|
|
|
|
class logical_shifted_reg<ValueType Ty, RegisterClass regclass>
|
|
: Operand<Ty>,
|
|
ComplexPattern<Ty, 2, "SelectLogicalShiftedRegister", []> {
|
|
let PrintMethod = "printShiftedRegister";
|
|
let MIOperandInfo = (ops regclass, logical_shift);
|
|
}
|
|
|
|
def logical_shifted_reg32 : logical_shifted_reg<i32, GPR32>;
|
|
def logical_shifted_reg64 : logical_shifted_reg<i64, GPR64>;
|
|
|
|
// A logical vector shifter operand:
|
|
// {7-6} - shift type: 00 = lsl
|
|
// {5-0} - imm6: #0, #8, #16, or #24
|
|
def logical_vec_shift : Operand<i32> {
|
|
let PrintMethod = "printShifter";
|
|
let EncoderMethod = "getVecShifterOpValue";
|
|
let ParserMatchClass = LogicalVecShifterOperand;
|
|
}
|
|
|
|
// A logical vector half-word shifter operand:
|
|
// {7-6} - shift type: 00 = lsl
|
|
// {5-0} - imm6: #0 or #8
|
|
def logical_vec_hw_shift : Operand<i32> {
|
|
let PrintMethod = "printShifter";
|
|
let EncoderMethod = "getVecShifterOpValue";
|
|
let ParserMatchClass = LogicalVecHalfWordShifterOperand;
|
|
}
|
|
|
|
// A vector move shifter operand:
|
|
// {0} - imm1: #8 or #16
|
|
def move_vec_shift : Operand<i32> {
|
|
let PrintMethod = "printShifter";
|
|
let EncoderMethod = "getMoveVecShifterOpValue";
|
|
let ParserMatchClass = MoveVecShifterOperand;
|
|
}
|
|
|
|
// An ADD/SUB immediate shifter operand:
|
|
// {7-6} - shift type: 00 = lsl
|
|
// {5-0} - imm6: #0 or #12
|
|
def addsub_shift : Operand<i32> {
|
|
let ParserMatchClass = AddSubShifterOperand;
|
|
}
|
|
|
|
class addsub_shifted_imm<ValueType Ty>
|
|
: Operand<Ty>, ComplexPattern<Ty, 2, "SelectArithImmed", [imm]> {
|
|
let PrintMethod = "printAddSubImm";
|
|
let EncoderMethod = "getAddSubImmOpValue";
|
|
let MIOperandInfo = (ops i32imm, addsub_shift);
|
|
}
|
|
|
|
def addsub_shifted_imm32 : addsub_shifted_imm<i32>;
|
|
def addsub_shifted_imm64 : addsub_shifted_imm<i64>;
|
|
|
|
class neg_addsub_shifted_imm<ValueType Ty>
|
|
: Operand<Ty>, ComplexPattern<Ty, 2, "SelectNegArithImmed", [imm]> {
|
|
let PrintMethod = "printAddSubImm";
|
|
let EncoderMethod = "getAddSubImmOpValue";
|
|
let MIOperandInfo = (ops i32imm, addsub_shift);
|
|
}
|
|
|
|
def neg_addsub_shifted_imm32 : neg_addsub_shifted_imm<i32>;
|
|
def neg_addsub_shifted_imm64 : neg_addsub_shifted_imm<i64>;
|
|
|
|
// An extend operand:
|
|
// {5-3} - extend type
|
|
// {2-0} - imm3
|
|
def arith_extend : Operand<i32> {
|
|
let PrintMethod = "printExtend";
|
|
let ParserMatchClass = ExtendOperand;
|
|
}
|
|
def arith_extend64 : Operand<i32> {
|
|
let PrintMethod = "printExtend";
|
|
let ParserMatchClass = ExtendOperand64;
|
|
}
|
|
|
|
// 'extend' that's a lsl of a 64-bit register.
|
|
def arith_extendlsl64 : Operand<i32> {
|
|
let PrintMethod = "printExtend";
|
|
let ParserMatchClass = ExtendOperandLSL64;
|
|
}
|
|
|
|
class arith_extended_reg32<ValueType Ty> : Operand<Ty>,
|
|
ComplexPattern<Ty, 2, "SelectArithExtendedRegister", []> {
|
|
let PrintMethod = "printExtendedRegister";
|
|
let MIOperandInfo = (ops GPR32, arith_extend);
|
|
}
|
|
|
|
class arith_extended_reg32to64<ValueType Ty> : Operand<Ty>,
|
|
ComplexPattern<Ty, 2, "SelectArithExtendedRegister", []> {
|
|
let PrintMethod = "printExtendedRegister";
|
|
let MIOperandInfo = (ops GPR32, arith_extend64);
|
|
}
|
|
|
|
// Floating-point immediate.
|
|
def fpimm32 : Operand<f32>,
|
|
PatLeaf<(f32 fpimm), [{
|
|
return ARM64_AM::getFP32Imm(N->getValueAPF()) != -1;
|
|
}], SDNodeXForm<fpimm, [{
|
|
APFloat InVal = N->getValueAPF();
|
|
uint32_t enc = ARM64_AM::getFP32Imm(InVal);
|
|
return CurDAG->getTargetConstant(enc, MVT::i32);
|
|
}]>> {
|
|
let ParserMatchClass = FPImmOperand;
|
|
let PrintMethod = "printFPImmOperand";
|
|
}
|
|
def fpimm64 : Operand<f64>,
|
|
PatLeaf<(f64 fpimm), [{
|
|
return ARM64_AM::getFP64Imm(N->getValueAPF()) != -1;
|
|
}], SDNodeXForm<fpimm, [{
|
|
APFloat InVal = N->getValueAPF();
|
|
uint32_t enc = ARM64_AM::getFP64Imm(InVal);
|
|
return CurDAG->getTargetConstant(enc, MVT::i32);
|
|
}]>> {
|
|
let ParserMatchClass = FPImmOperand;
|
|
let PrintMethod = "printFPImmOperand";
|
|
}
|
|
|
|
def fpimm8 : Operand<i32> {
|
|
let ParserMatchClass = FPImmOperand;
|
|
let PrintMethod = "printFPImmOperand";
|
|
}
|
|
|
|
def fpimm0 : PatLeaf<(fpimm), [{
|
|
return N->isExactlyValue(+0.0);
|
|
}]>;
|
|
|
|
// 8-bit immediate for AdvSIMD where 64-bit values of the form:
|
|
// aaaaaaaa bbbbbbbb cccccccc dddddddd eeeeeeee ffffffff gggggggg hhhhhhhh
|
|
// are encoded as the eight bit value 'abcdefgh'.
|
|
def simdimmtype10 : Operand<i32>,
|
|
PatLeaf<(f64 fpimm), [{
|
|
return ARM64_AM::isAdvSIMDModImmType10(N->getValueAPF()
|
|
.bitcastToAPInt()
|
|
.getZExtValue());
|
|
}], SDNodeXForm<fpimm, [{
|
|
APFloat InVal = N->getValueAPF();
|
|
uint32_t enc = ARM64_AM::encodeAdvSIMDModImmType10(N->getValueAPF()
|
|
.bitcastToAPInt()
|
|
.getZExtValue());
|
|
return CurDAG->getTargetConstant(enc, MVT::i32);
|
|
}]>> {
|
|
let ParserMatchClass = SIMDImmType10Operand;
|
|
let PrintMethod = "printSIMDType10Operand";
|
|
}
|
|
|
|
|
|
//---
|
|
// Sytem management
|
|
//---
|
|
|
|
// Base encoding for system instruction operands.
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
|
|
class BaseSystemI<bit L, dag oops, dag iops, string asm, string operands>
|
|
: I<oops, iops, asm, operands, "", []> {
|
|
let Inst{31-22} = 0b1101010100;
|
|
let Inst{21} = L;
|
|
}
|
|
|
|
// System instructions which do not have an Rt register.
|
|
class SimpleSystemI<bit L, dag iops, string asm, string operands>
|
|
: BaseSystemI<L, (outs), iops, asm, operands> {
|
|
let Inst{4-0} = 0b11111;
|
|
}
|
|
|
|
// System instructions which have an Rt register.
|
|
class RtSystemI<bit L, dag oops, dag iops, string asm, string operands>
|
|
: BaseSystemI<L, oops, iops, asm, operands>,
|
|
Sched<[WriteSys]> {
|
|
bits<5> Rt;
|
|
let Inst{4-0} = Rt;
|
|
}
|
|
|
|
// Hint instructions that take both a CRm and a 3-bit immediate.
|
|
class HintI<string mnemonic>
|
|
: SimpleSystemI<0, (ins imm0_127:$imm), mnemonic#" $imm", "">,
|
|
Sched<[WriteHint]> {
|
|
bits <7> imm;
|
|
let Inst{20-12} = 0b000110010;
|
|
let Inst{11-5} = imm;
|
|
}
|
|
|
|
// System instructions taking a single literal operand which encodes into
|
|
// CRm. op2 differentiates the opcodes.
|
|
def BarrierAsmOperand : AsmOperandClass {
|
|
let Name = "Barrier";
|
|
let ParserMethod = "tryParseBarrierOperand";
|
|
}
|
|
def barrier_op : Operand<i32> {
|
|
let PrintMethod = "printBarrierOption";
|
|
let ParserMatchClass = BarrierAsmOperand;
|
|
}
|
|
class CRmSystemI<Operand crmtype, bits<3> opc, string asm>
|
|
: SimpleSystemI<0, (ins crmtype:$CRm), asm, "\t$CRm">,
|
|
Sched<[WriteBarrier]> {
|
|
bits<4> CRm;
|
|
let Inst{20-12} = 0b000110011;
|
|
let Inst{11-8} = CRm;
|
|
let Inst{7-5} = opc;
|
|
}
|
|
|
|
// MRS/MSR system instructions.
|
|
def SystemRegisterOperand : AsmOperandClass {
|
|
let Name = "SystemRegister";
|
|
let ParserMethod = "tryParseSystemRegister";
|
|
}
|
|
// concatenation of 1, op0, op1, CRn, CRm, op2. 16-bit immediate.
|
|
def sysreg_op : Operand<i32> {
|
|
let ParserMatchClass = SystemRegisterOperand;
|
|
let DecoderMethod = "DecodeSystemRegister";
|
|
let PrintMethod = "printSystemRegister";
|
|
}
|
|
|
|
class MRSI : RtSystemI<1, (outs GPR64:$Rt), (ins sysreg_op:$systemreg),
|
|
"mrs", "\t$Rt, $systemreg"> {
|
|
bits<15> systemreg;
|
|
let Inst{20} = 1;
|
|
let Inst{19-5} = systemreg;
|
|
}
|
|
|
|
// FIXME: Some of these def CPSR, others don't. Best way to model that?
|
|
// Explicitly modeling each of the system register as a register class
|
|
// would do it, but feels like overkill at this point.
|
|
class MSRI : RtSystemI<0, (outs), (ins sysreg_op:$systemreg, GPR64:$Rt),
|
|
"msr", "\t$systemreg, $Rt"> {
|
|
bits<15> systemreg;
|
|
let Inst{20} = 1;
|
|
let Inst{19-5} = systemreg;
|
|
}
|
|
|
|
def SystemCPSRFieldOperand : AsmOperandClass {
|
|
let Name = "SystemCPSRField";
|
|
let ParserMethod = "tryParseCPSRField";
|
|
}
|
|
def cpsrfield_op : Operand<i32> {
|
|
let ParserMatchClass = SystemCPSRFieldOperand;
|
|
let PrintMethod = "printSystemCPSRField";
|
|
}
|
|
|
|
let Defs = [CPSR] in
|
|
class MSRcpsrI : SimpleSystemI<0, (ins cpsrfield_op:$cpsr_field, imm0_15:$imm),
|
|
"msr", "\t$cpsr_field, $imm">,
|
|
Sched<[WriteSys]> {
|
|
bits<6> cpsrfield;
|
|
bits<4> imm;
|
|
let Inst{20-19} = 0b00;
|
|
let Inst{18-16} = cpsrfield{5-3};
|
|
let Inst{15-12} = 0b0100;
|
|
let Inst{11-8} = imm;
|
|
let Inst{7-5} = cpsrfield{2-0};
|
|
|
|
let DecoderMethod = "DecodeSystemCPSRInstruction";
|
|
}
|
|
|
|
// SYS and SYSL generic system instructions.
|
|
def SysCRAsmOperand : AsmOperandClass {
|
|
let Name = "SysCR";
|
|
let ParserMethod = "tryParseSysCROperand";
|
|
}
|
|
|
|
def sys_cr_op : Operand<i32> {
|
|
let PrintMethod = "printSysCROperand";
|
|
let ParserMatchClass = SysCRAsmOperand;
|
|
}
|
|
|
|
class SystemI<bit L, string asm>
|
|
: SimpleSystemI<L,
|
|
(ins imm0_7:$op1, sys_cr_op:$Cn, sys_cr_op:$Cm, imm0_7:$op2),
|
|
asm, "\t$op1, $Cn, $Cm, $op2">,
|
|
Sched<[WriteSys]> {
|
|
bits<3> op1;
|
|
bits<4> Cn;
|
|
bits<4> Cm;
|
|
bits<3> op2;
|
|
let Inst{20-19} = 0b01;
|
|
let Inst{18-16} = op1;
|
|
let Inst{15-12} = Cn;
|
|
let Inst{11-8} = Cm;
|
|
let Inst{7-5} = op2;
|
|
}
|
|
|
|
class SystemXtI<bit L, string asm>
|
|
: RtSystemI<L, (outs),
|
|
(ins imm0_7:$op1, sys_cr_op:$Cn, sys_cr_op:$Cm, imm0_7:$op2, GPR64:$Rt),
|
|
asm, "\t$op1, $Cn, $Cm, $op2, $Rt"> {
|
|
bits<3> op1;
|
|
bits<4> Cn;
|
|
bits<4> Cm;
|
|
bits<3> op2;
|
|
let Inst{20-19} = 0b01;
|
|
let Inst{18-16} = op1;
|
|
let Inst{15-12} = Cn;
|
|
let Inst{11-8} = Cm;
|
|
let Inst{7-5} = op2;
|
|
}
|
|
|
|
class SystemLXtI<bit L, string asm>
|
|
: RtSystemI<L, (outs),
|
|
(ins GPR64:$Rt, imm0_7:$op1, sys_cr_op:$Cn, sys_cr_op:$Cm, imm0_7:$op2),
|
|
asm, "\t$Rt, $op1, $Cn, $Cm, $op2"> {
|
|
bits<3> op1;
|
|
bits<4> Cn;
|
|
bits<4> Cm;
|
|
bits<3> op2;
|
|
let Inst{20-19} = 0b01;
|
|
let Inst{18-16} = op1;
|
|
let Inst{15-12} = Cn;
|
|
let Inst{11-8} = Cm;
|
|
let Inst{7-5} = op2;
|
|
}
|
|
|
|
|
|
// Branch (register) instructions:
|
|
//
|
|
// case opc of
|
|
// 0001 blr
|
|
// 0000 br
|
|
// 0101 dret
|
|
// 0100 eret
|
|
// 0010 ret
|
|
// otherwise UNDEFINED
|
|
class BaseBranchReg<bits<4> opc, dag oops, dag iops, string asm,
|
|
string operands, list<dag> pattern>
|
|
: I<oops, iops, asm, operands, "", pattern>, Sched<[WriteBrReg]> {
|
|
let Inst{31-25} = 0b1101011;
|
|
let Inst{24-21} = opc;
|
|
let Inst{20-16} = 0b11111;
|
|
let Inst{15-10} = 0b000000;
|
|
let Inst{4-0} = 0b00000;
|
|
}
|
|
|
|
class BranchReg<bits<4> opc, string asm, list<dag> pattern>
|
|
: BaseBranchReg<opc, (outs), (ins GPR64:$Rn), asm, "\t$Rn", pattern> {
|
|
bits<5> Rn;
|
|
let Inst{9-5} = Rn;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1, isReturn = 1 in
|
|
class SpecialReturn<bits<4> opc, string asm>
|
|
: BaseBranchReg<opc, (outs), (ins), asm, "", []> {
|
|
let Inst{9-5} = 0b11111;
|
|
}
|
|
|
|
//---
|
|
// Conditional branch instruction.
|
|
//---
|
|
// Branch condition code.
|
|
// 4-bit immediate. Pretty-printed as .<cc>
|
|
def dotCcode : Operand<i32> {
|
|
let PrintMethod = "printDotCondCode";
|
|
}
|
|
|
|
// Conditional branch target. 19-bit immediate. The low two bits of the target
|
|
// offset are implied zero and so are not part of the immediate.
|
|
def BranchTarget19Operand : AsmOperandClass {
|
|
let Name = "BranchTarget19";
|
|
}
|
|
def am_brcond : Operand<OtherVT> {
|
|
let EncoderMethod = "getCondBranchTargetOpValue";
|
|
let DecoderMethod = "DecodeCondBranchTarget";
|
|
let PrintMethod = "printAlignedBranchTarget";
|
|
let ParserMatchClass = BranchTarget19Operand;
|
|
}
|
|
|
|
class BranchCond : I<(outs), (ins dotCcode:$cond, am_brcond:$target),
|
|
"b", "$cond\t$target", "",
|
|
[(ARM64brcond bb:$target, imm:$cond, CPSR)]>,
|
|
Sched<[WriteBr]> {
|
|
let isBranch = 1;
|
|
let isTerminator = 1;
|
|
let Uses = [CPSR];
|
|
|
|
bits<4> cond;
|
|
bits<19> target;
|
|
let Inst{31-24} = 0b01010100;
|
|
let Inst{23-5} = target;
|
|
let Inst{4} = 0;
|
|
let Inst{3-0} = cond;
|
|
}
|
|
|
|
//---
|
|
// Compare-and-branch instructions.
|
|
//---
|
|
class BaseCmpBranch<RegisterClass regtype, bit op, string asm, SDNode node>
|
|
: I<(outs), (ins regtype:$Rt, am_brcond:$target),
|
|
asm, "\t$Rt, $target", "",
|
|
[(node regtype:$Rt, bb:$target)]>,
|
|
Sched<[WriteBr]> {
|
|
let isBranch = 1;
|
|
let isTerminator = 1;
|
|
|
|
bits<5> Rt;
|
|
bits<19> target;
|
|
let Inst{30-25} = 0b011010;
|
|
let Inst{24} = op;
|
|
let Inst{23-5} = target;
|
|
let Inst{4-0} = Rt;
|
|
}
|
|
|
|
multiclass CmpBranch<bit op, string asm, SDNode node> {
|
|
def W : BaseCmpBranch<GPR32, op, asm, node> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def X : BaseCmpBranch<GPR64, op, asm, node> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Test-bit-and-branch instructions.
|
|
//---
|
|
// Test-and-branch target. 14-bit sign-extended immediate. The low two bits of
|
|
// the target offset are implied zero and so are not part of the immediate.
|
|
def BranchTarget14Operand : AsmOperandClass {
|
|
let Name = "BranchTarget14";
|
|
}
|
|
def am_tbrcond : Operand<OtherVT> {
|
|
let EncoderMethod = "getTestBranchTargetOpValue";
|
|
let PrintMethod = "printAlignedBranchTarget";
|
|
let ParserMatchClass = BranchTarget14Operand;
|
|
}
|
|
|
|
class TestBranch<bit op, string asm, SDNode node>
|
|
: I<(outs), (ins GPR64:$Rt, imm0_63:$bit_off, am_tbrcond:$target),
|
|
asm, "\t$Rt, $bit_off, $target", "",
|
|
[(node GPR64:$Rt, imm0_63:$bit_off, bb:$target)]>,
|
|
Sched<[WriteBr]> {
|
|
let isBranch = 1;
|
|
let isTerminator = 1;
|
|
|
|
bits<5> Rt;
|
|
bits<6> bit_off;
|
|
bits<14> target;
|
|
|
|
let Inst{31} = bit_off{5};
|
|
let Inst{30-25} = 0b011011;
|
|
let Inst{24} = op;
|
|
let Inst{23-19} = bit_off{4-0};
|
|
let Inst{18-5} = target;
|
|
let Inst{4-0} = Rt;
|
|
|
|
let DecoderMethod = "DecodeTestAndBranch";
|
|
}
|
|
|
|
//---
|
|
// Unconditional branch (immediate) instructions.
|
|
//---
|
|
def BranchTarget26Operand : AsmOperandClass {
|
|
let Name = "BranchTarget26";
|
|
}
|
|
def am_b_target : Operand<OtherVT> {
|
|
let EncoderMethod = "getBranchTargetOpValue";
|
|
let PrintMethod = "printAlignedBranchTarget";
|
|
let ParserMatchClass = BranchTarget26Operand;
|
|
}
|
|
def am_bl_target : Operand<i64> {
|
|
let EncoderMethod = "getBranchTargetOpValue";
|
|
let PrintMethod = "printAlignedBranchTarget";
|
|
let ParserMatchClass = BranchTarget26Operand;
|
|
}
|
|
|
|
class BImm<bit op, dag iops, string asm, list<dag> pattern>
|
|
: I<(outs), iops, asm, "\t$addr", "", pattern>, Sched<[WriteBr]> {
|
|
bits<26> addr;
|
|
let Inst{31} = op;
|
|
let Inst{30-26} = 0b00101;
|
|
let Inst{25-0} = addr;
|
|
|
|
let DecoderMethod = "DecodeUnconditionalBranch";
|
|
}
|
|
|
|
class BranchImm<bit op, string asm, list<dag> pattern>
|
|
: BImm<op, (ins am_b_target:$addr), asm, pattern>;
|
|
class CallImm<bit op, string asm, list<dag> pattern>
|
|
: BImm<op, (ins am_bl_target:$addr), asm, pattern>;
|
|
|
|
//---
|
|
// Basic one-operand data processing instructions.
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseOneOperandData<bits<3> opc, RegisterClass regtype, string asm,
|
|
SDPatternOperator node>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn), asm, "\t$Rd, $Rn", "",
|
|
[(set regtype:$Rd, (node regtype:$Rn))]>,
|
|
Sched<[WriteI]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
|
|
let Inst{30-13} = 0b101101011000000000;
|
|
let Inst{12-10} = opc;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass OneOperandData<bits<3> opc, string asm,
|
|
SDPatternOperator node = null_frag> {
|
|
def Wr : BaseOneOperandData<opc, GPR32, asm, node> {
|
|
let Inst{31} = 0;
|
|
}
|
|
|
|
def Xr : BaseOneOperandData<opc, GPR64, asm, node> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
class OneWRegData<bits<3> opc, string asm, SDPatternOperator node>
|
|
: BaseOneOperandData<opc, GPR32, asm, node> {
|
|
let Inst{31} = 0;
|
|
}
|
|
|
|
class OneXRegData<bits<3> opc, string asm, SDPatternOperator node>
|
|
: BaseOneOperandData<opc, GPR64, asm, node> {
|
|
let Inst{31} = 1;
|
|
}
|
|
|
|
//---
|
|
// Basic two-operand data processing instructions.
|
|
//---
|
|
class BaseBaseAddSubCarry<bit isSub, RegisterClass regtype, string asm,
|
|
list<dag> pattern>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm),
|
|
asm, "\t$Rd, $Rn, $Rm", "", pattern>,
|
|
Sched<[WriteI]> {
|
|
let Uses = [CPSR];
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{30} = isSub;
|
|
let Inst{28-21} = 0b11010000;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-10} = 0;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class BaseAddSubCarry<bit isSub, RegisterClass regtype, string asm,
|
|
SDNode OpNode>
|
|
: BaseBaseAddSubCarry<isSub, regtype, asm,
|
|
[(set regtype:$Rd, (OpNode regtype:$Rn, regtype:$Rm, CPSR))]>;
|
|
|
|
class BaseAddSubCarrySetFlags<bit isSub, RegisterClass regtype, string asm,
|
|
SDNode OpNode>
|
|
: BaseBaseAddSubCarry<isSub, regtype, asm,
|
|
[(set regtype:$Rd, (OpNode regtype:$Rn, regtype:$Rm, CPSR)),
|
|
(implicit CPSR)]> {
|
|
let Defs = [CPSR];
|
|
}
|
|
|
|
multiclass AddSubCarry<bit isSub, string asm, string asm_setflags,
|
|
SDNode OpNode, SDNode OpNode_setflags> {
|
|
def Wr : BaseAddSubCarry<isSub, GPR32, asm, OpNode> {
|
|
let Inst{31} = 0;
|
|
let Inst{29} = 0;
|
|
}
|
|
def Xr : BaseAddSubCarry<isSub, GPR64, asm, OpNode> {
|
|
let Inst{31} = 1;
|
|
let Inst{29} = 0;
|
|
}
|
|
|
|
// Sets flags.
|
|
def SWr : BaseAddSubCarrySetFlags<isSub, GPR32, asm_setflags,
|
|
OpNode_setflags> {
|
|
let Inst{31} = 0;
|
|
let Inst{29} = 1;
|
|
}
|
|
def SXr : BaseAddSubCarrySetFlags<isSub, GPR64, asm_setflags,
|
|
OpNode_setflags> {
|
|
let Inst{31} = 1;
|
|
let Inst{29} = 1;
|
|
}
|
|
}
|
|
|
|
class BaseTwoOperand<bits<4> opc, RegisterClass regtype, string asm,
|
|
SDPatternOperator OpNode>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm),
|
|
asm, "\t$Rd, $Rn, $Rm", "",
|
|
[(set regtype:$Rd, (OpNode regtype:$Rn, regtype:$Rm))]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{30-21} = 0b0011010110;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-14} = 0b00;
|
|
let Inst{13-10} = opc;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class BaseDiv<bit isSigned, RegisterClass regtype, string asm,
|
|
SDPatternOperator OpNode>
|
|
: BaseTwoOperand<{0,0,1,?}, regtype, asm, OpNode> {
|
|
let Inst{10} = isSigned;
|
|
}
|
|
|
|
multiclass Div<bit isSigned, string asm, SDPatternOperator OpNode> {
|
|
def Wr : BaseDiv<isSigned, GPR32, asm, OpNode>,
|
|
Sched<[WriteID32]> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xr : BaseDiv<isSigned, GPR64, asm, OpNode>,
|
|
Sched<[WriteID64]> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
class BaseShift<bits<2> shift_type, RegisterClass regtype,
|
|
string asm, SDNode OpNode>
|
|
: BaseTwoOperand<{1,0,?,?}, regtype, asm, OpNode>,
|
|
Sched<[WriteIS]> {
|
|
let Inst{11-10} = shift_type;
|
|
}
|
|
|
|
multiclass Shift<bits<2> shift_type, string asm, SDNode OpNode> {
|
|
def Wr : BaseShift<shift_type, GPR32, asm, OpNode> {
|
|
let Inst{31} = 0;
|
|
}
|
|
|
|
def Xr : BaseShift<shift_type, GPR64, asm, OpNode> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
class ShiftAlias<string asm, Instruction inst, RegisterClass regtype>
|
|
: InstAlias<asm#" $dst, $src1, $src2",
|
|
(inst regtype:$dst, regtype:$src1, regtype:$src2)>;
|
|
|
|
class BaseMulAccum<bit isSub, bits<3> opc, RegisterClass multype,
|
|
RegisterClass addtype, string asm,
|
|
list<dag> pattern>
|
|
: I<(outs addtype:$Rd), (ins multype:$Rn, multype:$Rm, addtype:$Ra),
|
|
asm, "\t$Rd, $Rn, $Rm, $Ra", "", pattern> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<5> Ra;
|
|
let Inst{30-24} = 0b0011011;
|
|
let Inst{23-21} = opc;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15} = isSub;
|
|
let Inst{14-10} = Ra;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass MulAccum<bit isSub, string asm, SDNode AccNode> {
|
|
def Wrrr : BaseMulAccum<isSub, 0b000, GPR32, GPR32, asm,
|
|
[(set GPR32:$Rd, (AccNode GPR32:$Ra, (mul GPR32:$Rn, GPR32:$Rm)))]>,
|
|
Sched<[WriteIM32]> {
|
|
let Inst{31} = 0;
|
|
}
|
|
|
|
def Xrrr : BaseMulAccum<isSub, 0b000, GPR64, GPR64, asm,
|
|
[(set GPR64:$Rd, (AccNode GPR64:$Ra, (mul GPR64:$Rn, GPR64:$Rm)))]>,
|
|
Sched<[WriteIM64]> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
class WideMulAccum<bit isSub, bits<3> opc, string asm,
|
|
SDNode AccNode, SDNode ExtNode>
|
|
: BaseMulAccum<isSub, opc, GPR32, GPR64, asm,
|
|
[(set GPR64:$Rd, (AccNode GPR64:$Ra,
|
|
(mul (ExtNode GPR32:$Rn), (ExtNode GPR32:$Rm))))]>,
|
|
Sched<[WriteIM32]> {
|
|
let Inst{31} = 1;
|
|
}
|
|
|
|
class MulHi<bits<3> opc, string asm, SDNode OpNode>
|
|
: I<(outs GPR64:$Rd), (ins GPR64:$Rn, GPR64:$Rm),
|
|
asm, "\t$Rd, $Rn, $Rm", "",
|
|
[(set GPR64:$Rd, (OpNode GPR64:$Rn, GPR64:$Rm))]>,
|
|
Sched<[WriteIM64]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31-24} = 0b10011011;
|
|
let Inst{23-21} = opc;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-10} = 0b011111;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class MulAccumWAlias<string asm, Instruction inst>
|
|
: InstAlias<asm#" $dst, $src1, $src2",
|
|
(inst GPR32:$dst, GPR32:$src1, GPR32:$src2, WZR)>;
|
|
class MulAccumXAlias<string asm, Instruction inst>
|
|
: InstAlias<asm#" $dst, $src1, $src2",
|
|
(inst GPR64:$dst, GPR64:$src1, GPR64:$src2, XZR)>;
|
|
class WideMulAccumAlias<string asm, Instruction inst>
|
|
: InstAlias<asm#" $dst, $src1, $src2",
|
|
(inst GPR64:$dst, GPR32:$src1, GPR32:$src2, XZR)>;
|
|
|
|
class BaseCRC32<bit sf, bits<2> sz, bit C, RegisterClass StreamReg,
|
|
SDPatternOperator OpNode, string asm>
|
|
: I<(outs GPR32:$Rd), (ins GPR32:$Rn, StreamReg:$Rm),
|
|
asm, "\t$Rd, $Rn, $Rm", "",
|
|
[(set GPR32:$Rd, (OpNode GPR32:$Rn, StreamReg:$Rm))]>,
|
|
Sched<[WriteISReg]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
|
|
let Inst{31} = sf;
|
|
let Inst{30-21} = 0b0011010110;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-13} = 0b010;
|
|
let Inst{12} = C;
|
|
let Inst{11-10} = sz;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
//---
|
|
// Address generation.
|
|
//---
|
|
|
|
class ADRI<bit page, string asm, Operand adr, list<dag> pattern>
|
|
: I<(outs GPR64:$Xd), (ins adr:$label), asm, "\t$Xd, $label", "",
|
|
pattern>,
|
|
Sched<[WriteI]> {
|
|
bits<5> Xd;
|
|
bits<21> label;
|
|
let Inst{31} = page;
|
|
let Inst{30-29} = label{1-0};
|
|
let Inst{28-24} = 0b10000;
|
|
let Inst{23-5} = label{20-2};
|
|
let Inst{4-0} = Xd;
|
|
|
|
let DecoderMethod = "DecodeAdrInstruction";
|
|
}
|
|
|
|
//---
|
|
// Move immediate.
|
|
//---
|
|
|
|
def movimm32_imm : Operand<i32> {
|
|
let ParserMatchClass = Imm0_65535Operand;
|
|
let EncoderMethod = "getMoveWideImmOpValue";
|
|
}
|
|
def movimm32_shift : Operand<i32> {
|
|
let PrintMethod = "printShifter";
|
|
let ParserMatchClass = MovImm32ShifterOperand;
|
|
}
|
|
def movimm64_shift : Operand<i32> {
|
|
let PrintMethod = "printShifter";
|
|
let ParserMatchClass = MovImm64ShifterOperand;
|
|
}
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseMoveImmediate<bits<2> opc, RegisterClass regtype, Operand shifter,
|
|
string asm>
|
|
: I<(outs regtype:$Rd), (ins movimm32_imm:$imm, shifter:$shift),
|
|
asm, "\t$Rd, $imm$shift", "", []>,
|
|
Sched<[WriteImm]> {
|
|
bits<5> Rd;
|
|
bits<16> imm;
|
|
bits<6> shift;
|
|
let Inst{30-29} = opc;
|
|
let Inst{28-23} = 0b100101;
|
|
let Inst{22-21} = shift{5-4};
|
|
let Inst{20-5} = imm;
|
|
let Inst{4-0} = Rd;
|
|
|
|
let DecoderMethod = "DecodeMoveImmInstruction";
|
|
}
|
|
|
|
multiclass MoveImmediate<bits<2> opc, string asm> {
|
|
def Wi : BaseMoveImmediate<opc, GPR32, movimm32_shift, asm> {
|
|
let Inst{31} = 0;
|
|
}
|
|
|
|
def Xi : BaseMoveImmediate<opc, GPR64, movimm64_shift, asm> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseInsertImmediate<bits<2> opc, RegisterClass regtype, Operand shifter,
|
|
string asm>
|
|
: I<(outs regtype:$Rd),
|
|
(ins regtype:$src, movimm32_imm:$imm, shifter:$shift),
|
|
asm, "\t$Rd, $imm$shift", "$src = $Rd", []>,
|
|
Sched<[WriteI]> {
|
|
bits<5> Rd;
|
|
bits<16> imm;
|
|
bits<6> shift;
|
|
let Inst{30-29} = opc;
|
|
let Inst{28-23} = 0b100101;
|
|
let Inst{22-21} = shift{5-4};
|
|
let Inst{20-5} = imm;
|
|
let Inst{4-0} = Rd;
|
|
|
|
let DecoderMethod = "DecodeMoveImmInstruction";
|
|
}
|
|
|
|
multiclass InsertImmediate<bits<2> opc, string asm> {
|
|
def Wi : BaseInsertImmediate<opc, GPR32, movimm32_shift, asm> {
|
|
let Inst{31} = 0;
|
|
}
|
|
|
|
def Xi : BaseInsertImmediate<opc, GPR64, movimm64_shift, asm> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Add/Subtract
|
|
//---
|
|
|
|
class BaseAddSubImm<bit isSub, bit setFlags, RegisterClass dstRegtype,
|
|
RegisterClass srcRegtype, addsub_shifted_imm immtype,
|
|
string asm, SDPatternOperator OpNode>
|
|
: I<(outs dstRegtype:$Rd), (ins srcRegtype:$Rn, immtype:$imm),
|
|
asm, "\t$Rd, $Rn, $imm", "",
|
|
[(set dstRegtype:$Rd, (OpNode srcRegtype:$Rn, immtype:$imm))]>,
|
|
Sched<[WriteI]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<14> imm;
|
|
let Inst{30} = isSub;
|
|
let Inst{29} = setFlags;
|
|
let Inst{28-24} = 0b10001;
|
|
let Inst{23-22} = imm{13-12}; // '00' => lsl #0, '01' => lsl #12
|
|
let Inst{21-10} = imm{11-0};
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
let DecoderMethod = "DecodeBaseAddSubImm";
|
|
}
|
|
|
|
class BaseAddSubRegPseudo<RegisterClass regtype,
|
|
SDPatternOperator OpNode>
|
|
: Pseudo<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm),
|
|
[(set regtype:$Rd, (OpNode regtype:$Rn, regtype:$Rm))]>,
|
|
Sched<[WriteI]>;
|
|
|
|
class BaseAddSubSReg<bit isSub, bit setFlags, RegisterClass regtype,
|
|
arith_shifted_reg shifted_regtype, string asm,
|
|
SDPatternOperator OpNode>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, shifted_regtype:$Rm),
|
|
asm, "\t$Rd, $Rn, $Rm", "",
|
|
[(set regtype:$Rd, (OpNode regtype:$Rn, shifted_regtype:$Rm))]>,
|
|
Sched<[WriteISReg]> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> src1;
|
|
bits<5> src2;
|
|
bits<8> shift;
|
|
let Inst{30} = isSub;
|
|
let Inst{29} = setFlags;
|
|
let Inst{28-24} = 0b01011;
|
|
let Inst{23-22} = shift{7-6};
|
|
let Inst{21} = 0;
|
|
let Inst{20-16} = src2;
|
|
let Inst{15-10} = shift{5-0};
|
|
let Inst{9-5} = src1;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeThreeAddrSRegInstruction";
|
|
}
|
|
|
|
class BaseAddSubEReg<bit isSub, bit setFlags, RegisterClass dstRegtype,
|
|
RegisterClass src1Regtype, Operand src2Regtype,
|
|
string asm, SDPatternOperator OpNode>
|
|
: I<(outs dstRegtype:$R1),
|
|
(ins src1Regtype:$R2, src2Regtype:$R3),
|
|
asm, "\t$R1, $R2, $R3", "",
|
|
[(set dstRegtype:$R1, (OpNode src1Regtype:$R2, src2Regtype:$R3))]>,
|
|
Sched<[WriteIEReg]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<6> ext;
|
|
let Inst{30} = isSub;
|
|
let Inst{29} = setFlags;
|
|
let Inst{28-24} = 0b01011;
|
|
let Inst{23-21} = 0b001;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-13} = ext{5-3};
|
|
let Inst{12-10} = ext{2-0};
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
|
|
let DecoderMethod = "DecodeAddSubERegInstruction";
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseAddSubEReg64<bit isSub, bit setFlags, RegisterClass dstRegtype,
|
|
RegisterClass src1Regtype, RegisterClass src2Regtype,
|
|
Operand ext_op, string asm>
|
|
: I<(outs dstRegtype:$Rd),
|
|
(ins src1Regtype:$Rn, src2Regtype:$Rm, ext_op:$ext),
|
|
asm, "\t$Rd, $Rn, $Rm$ext", "", []>,
|
|
Sched<[WriteIEReg]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<6> ext;
|
|
let Inst{30} = isSub;
|
|
let Inst{29} = setFlags;
|
|
let Inst{28-24} = 0b01011;
|
|
let Inst{23-21} = 0b001;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15} = ext{5};
|
|
let Inst{12-10} = ext{2-0};
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
|
|
let DecoderMethod = "DecodeAddSubERegInstruction";
|
|
}
|
|
|
|
// Aliases for register+register add/subtract.
|
|
class AddSubRegAlias<string asm, Instruction inst, RegisterClass dstRegtype,
|
|
RegisterClass src1Regtype, RegisterClass src2Regtype,
|
|
int shiftExt>
|
|
: InstAlias<asm#" $dst, $src1, $src2",
|
|
(inst dstRegtype:$dst, src1Regtype:$src1, src2Regtype:$src2,
|
|
shiftExt)>;
|
|
|
|
multiclass AddSub<bit isSub, string mnemonic,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
let hasSideEffects = 0 in {
|
|
// Add/Subtract immediate
|
|
def Wri : BaseAddSubImm<isSub, 0, GPR32sp, GPR32sp, addsub_shifted_imm32,
|
|
mnemonic, OpNode> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xri : BaseAddSubImm<isSub, 0, GPR64sp, GPR64sp, addsub_shifted_imm64,
|
|
mnemonic, OpNode> {
|
|
let Inst{31} = 1;
|
|
}
|
|
|
|
// Add/Subtract register - Only used for CodeGen
|
|
def Wrr : BaseAddSubRegPseudo<GPR32, OpNode>;
|
|
def Xrr : BaseAddSubRegPseudo<GPR64, OpNode>;
|
|
|
|
// Add/Subtract shifted register
|
|
def Wrs : BaseAddSubSReg<isSub, 0, GPR32, arith_shifted_reg32, mnemonic,
|
|
OpNode> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xrs : BaseAddSubSReg<isSub, 0, GPR64, arith_shifted_reg64, mnemonic,
|
|
OpNode> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
// Add/Subtract extended register
|
|
let AddedComplexity = 1, hasSideEffects = 0 in {
|
|
def Wrx : BaseAddSubEReg<isSub, 0, GPR32sp, GPR32sp,
|
|
arith_extended_reg32<i32>, mnemonic, OpNode> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xrx : BaseAddSubEReg<isSub, 0, GPR64sp, GPR64sp,
|
|
arith_extended_reg32to64<i64>, mnemonic, OpNode> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
def Xrx64 : BaseAddSubEReg64<isSub, 0, GPR64sp, GPR64sp, GPR64,
|
|
arith_extendlsl64, mnemonic> {
|
|
// UXTX and SXTX only.
|
|
let Inst{14-13} = 0b11;
|
|
let Inst{31} = 1;
|
|
}
|
|
|
|
// Register/register aliases with no shift when SP is not used.
|
|
def : AddSubRegAlias<mnemonic, !cast<Instruction>(NAME#"Wrs"),
|
|
GPR32, GPR32, GPR32, 0>;
|
|
def : AddSubRegAlias<mnemonic, !cast<Instruction>(NAME#"Xrs"),
|
|
GPR64, GPR64, GPR64, 0>;
|
|
|
|
// Register/register aliases with no shift when either the destination or
|
|
// first source register is SP. This relies on the shifted register aliases
|
|
// above matching first in the case when SP is not used.
|
|
def : AddSubRegAlias<mnemonic, !cast<Instruction>(NAME#"Wrx"),
|
|
GPR32sp, GPR32sp, GPR32, 16>; // UXTW #0
|
|
def : AddSubRegAlias<mnemonic,
|
|
!cast<Instruction>(NAME#"Xrx64"),
|
|
GPR64sp, GPR64sp, GPR64, 24>; // UXTX #0
|
|
}
|
|
|
|
multiclass AddSubS<bit isSub, string mnemonic, SDNode OpNode> {
|
|
let isCompare = 1, Defs = [CPSR] in {
|
|
// Add/Subtract immediate
|
|
def Wri : BaseAddSubImm<isSub, 1, GPR32, GPR32sp, addsub_shifted_imm32,
|
|
mnemonic, OpNode> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xri : BaseAddSubImm<isSub, 1, GPR64, GPR64sp, addsub_shifted_imm64,
|
|
mnemonic, OpNode> {
|
|
let Inst{31} = 1;
|
|
}
|
|
|
|
// Add/Subtract register
|
|
def Wrr : BaseAddSubRegPseudo<GPR32, OpNode>;
|
|
def Xrr : BaseAddSubRegPseudo<GPR64, OpNode>;
|
|
|
|
// Add/Subtract shifted register
|
|
def Wrs : BaseAddSubSReg<isSub, 1, GPR32, arith_shifted_reg32, mnemonic,
|
|
OpNode> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xrs : BaseAddSubSReg<isSub, 1, GPR64, arith_shifted_reg64, mnemonic,
|
|
OpNode> {
|
|
let Inst{31} = 1;
|
|
}
|
|
|
|
// Add/Subtract extended register
|
|
let AddedComplexity = 1 in {
|
|
def Wrx : BaseAddSubEReg<isSub, 1, GPR32, GPR32sp,
|
|
arith_extended_reg32<i32>, mnemonic, OpNode> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xrx : BaseAddSubEReg<isSub, 1, GPR64, GPR64sp,
|
|
arith_extended_reg32<i64>, mnemonic, OpNode> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
def Xrx64 : BaseAddSubEReg64<isSub, 1, GPR64, GPR64sp, GPR64,
|
|
arith_extendlsl64, mnemonic> {
|
|
// UXTX and SXTX only.
|
|
let Inst{14-13} = 0b11;
|
|
let Inst{31} = 1;
|
|
}
|
|
} // Defs = [CPSR]
|
|
|
|
// Register/register aliases with no shift when SP is not used.
|
|
def : AddSubRegAlias<mnemonic, !cast<Instruction>(NAME#"Wrs"),
|
|
GPR32, GPR32, GPR32, 0>;
|
|
def : AddSubRegAlias<mnemonic, !cast<Instruction>(NAME#"Xrs"),
|
|
GPR64, GPR64, GPR64, 0>;
|
|
|
|
// Register/register aliases with no shift when the first source register
|
|
// is SP. This relies on the shifted register aliases above matching first
|
|
// in the case when SP is not used.
|
|
def : AddSubRegAlias<mnemonic, !cast<Instruction>(NAME#"Wrx"),
|
|
GPR32, GPR32sp, GPR32, 16>; // UXTW #0
|
|
def : AddSubRegAlias<mnemonic,
|
|
!cast<Instruction>(NAME#"Xrx64"),
|
|
GPR64, GPR64sp, GPR64, 24>; // UXTX #0
|
|
}
|
|
|
|
//---
|
|
// Extract
|
|
//---
|
|
def SDTA64EXTR : SDTypeProfile<1, 3, [SDTCisSameAs<0, 1>, SDTCisSameAs<0, 2>,
|
|
SDTCisSameAs<0, 3>]>;
|
|
def ARM64Extr : SDNode<"ARM64ISD::EXTR", SDTA64EXTR>;
|
|
|
|
class BaseExtractImm<RegisterClass regtype, Operand imm_type, string asm,
|
|
list<dag> patterns>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm, imm_type:$imm),
|
|
asm, "\t$Rd, $Rn, $Rm, $imm", "", patterns>,
|
|
Sched<[WriteExtr, ReadExtrHi]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<6> imm;
|
|
|
|
let Inst{30-23} = 0b00100111;
|
|
let Inst{21} = 0;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-10} = imm;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass ExtractImm<string asm> {
|
|
def Wrri : BaseExtractImm<GPR32, imm0_31, asm,
|
|
[(set GPR32:$Rd,
|
|
(ARM64Extr GPR32:$Rn, GPR32:$Rm, imm0_31:$imm))]> {
|
|
let Inst{31} = 0;
|
|
let Inst{22} = 0;
|
|
}
|
|
def Xrri : BaseExtractImm<GPR64, imm0_63, asm,
|
|
[(set GPR64:$Rd,
|
|
(ARM64Extr GPR64:$Rn, GPR64:$Rm, imm0_63:$imm))]> {
|
|
|
|
let Inst{31} = 1;
|
|
let Inst{22} = 1;
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Bitfield
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseBitfieldImm<bits<2> opc,
|
|
RegisterClass regtype, Operand imm_type, string asm>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, imm_type:$immr, imm_type:$imms),
|
|
asm, "\t$Rd, $Rn, $immr, $imms", "", []>,
|
|
Sched<[WriteIS]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<6> immr;
|
|
bits<6> imms;
|
|
|
|
let Inst{30-29} = opc;
|
|
let Inst{28-23} = 0b100110;
|
|
let Inst{21-16} = immr;
|
|
let Inst{15-10} = imms;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass BitfieldImm<bits<2> opc, string asm> {
|
|
def Wri : BaseBitfieldImm<opc, GPR32, imm0_31, asm> {
|
|
let Inst{31} = 0;
|
|
let Inst{22} = 0;
|
|
}
|
|
def Xri : BaseBitfieldImm<opc, GPR64, imm0_63, asm> {
|
|
let Inst{31} = 1;
|
|
let Inst{22} = 1;
|
|
}
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseBitfieldImmWith2RegArgs<bits<2> opc,
|
|
RegisterClass regtype, Operand imm_type, string asm>
|
|
: I<(outs regtype:$Rd), (ins regtype:$src, regtype:$Rn, imm_type:$immr,
|
|
imm_type:$imms),
|
|
asm, "\t$Rd, $Rn, $immr, $imms", "$src = $Rd", []>,
|
|
Sched<[WriteIS]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<6> immr;
|
|
bits<6> imms;
|
|
|
|
let Inst{30-29} = opc;
|
|
let Inst{28-23} = 0b100110;
|
|
let Inst{21-16} = immr;
|
|
let Inst{15-10} = imms;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass BitfieldImmWith2RegArgs<bits<2> opc, string asm> {
|
|
def Wri : BaseBitfieldImmWith2RegArgs<opc, GPR32, imm0_31, asm> {
|
|
let Inst{31} = 0;
|
|
let Inst{22} = 0;
|
|
}
|
|
def Xri : BaseBitfieldImmWith2RegArgs<opc, GPR64, imm0_63, asm> {
|
|
let Inst{31} = 1;
|
|
let Inst{22} = 1;
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Logical
|
|
//---
|
|
|
|
// Logical (immediate)
|
|
class BaseLogicalImm<bits<2> opc, RegisterClass dregtype,
|
|
RegisterClass sregtype, Operand imm_type, string asm,
|
|
list<dag> pattern>
|
|
: I<(outs dregtype:$Rd), (ins sregtype:$Rn, imm_type:$imm),
|
|
asm, "\t$Rd, $Rn, $imm", "", pattern>,
|
|
Sched<[WriteI]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<13> imm;
|
|
let Inst{30-29} = opc;
|
|
let Inst{28-23} = 0b100100;
|
|
let Inst{22} = imm{12};
|
|
let Inst{21-16} = imm{11-6};
|
|
let Inst{15-10} = imm{5-0};
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
|
|
let DecoderMethod = "DecodeLogicalImmInstruction";
|
|
}
|
|
|
|
// Logical (shifted register)
|
|
class BaseLogicalSReg<bits<2> opc, bit N, RegisterClass regtype,
|
|
logical_shifted_reg shifted_regtype, string asm,
|
|
list<dag> pattern>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, shifted_regtype:$Rm),
|
|
asm, "\t$Rd, $Rn, $Rm", "", pattern>,
|
|
Sched<[WriteISReg]> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> src1;
|
|
bits<5> src2;
|
|
bits<8> shift;
|
|
let Inst{30-29} = opc;
|
|
let Inst{28-24} = 0b01010;
|
|
let Inst{23-22} = shift{7-6};
|
|
let Inst{21} = N;
|
|
let Inst{20-16} = src2;
|
|
let Inst{15-10} = shift{5-0};
|
|
let Inst{9-5} = src1;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeThreeAddrSRegInstruction";
|
|
}
|
|
|
|
// Aliases for register+register logical instructions.
|
|
class LogicalRegAlias<string asm, Instruction inst, RegisterClass regtype>
|
|
: InstAlias<asm#" $dst, $src1, $src2",
|
|
(inst regtype:$dst, regtype:$src1, regtype:$src2, 0)>;
|
|
|
|
let AddedComplexity = 6 in
|
|
multiclass LogicalImm<bits<2> opc, string mnemonic, SDNode OpNode> {
|
|
def Wri : BaseLogicalImm<opc, GPR32sp, GPR32, logical_imm32, mnemonic,
|
|
[(set GPR32sp:$Rd, (OpNode GPR32:$Rn,
|
|
logical_imm32:$imm))]> {
|
|
let Inst{31} = 0;
|
|
let Inst{22} = 0; // 64-bit version has an additional bit of immediate.
|
|
}
|
|
def Xri : BaseLogicalImm<opc, GPR64sp, GPR64, logical_imm64, mnemonic,
|
|
[(set GPR64sp:$Rd, (OpNode GPR64:$Rn,
|
|
logical_imm64:$imm))]> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
multiclass LogicalImmS<bits<2> opc, string mnemonic, SDNode OpNode> {
|
|
let isCompare = 1, Defs = [CPSR] in {
|
|
def Wri : BaseLogicalImm<opc, GPR32, GPR32, logical_imm32, mnemonic,
|
|
[(set GPR32:$Rd, (OpNode GPR32:$Rn, logical_imm32:$imm))]> {
|
|
let Inst{31} = 0;
|
|
let Inst{22} = 0; // 64-bit version has an additional bit of immediate.
|
|
}
|
|
def Xri : BaseLogicalImm<opc, GPR64, GPR64, logical_imm64, mnemonic,
|
|
[(set GPR64:$Rd, (OpNode GPR64:$Rn, logical_imm64:$imm))]> {
|
|
let Inst{31} = 1;
|
|
}
|
|
} // end Defs = [CPSR]
|
|
}
|
|
|
|
class BaseLogicalRegPseudo<RegisterClass regtype, SDPatternOperator OpNode>
|
|
: Pseudo<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm),
|
|
[(set regtype:$Rd, (OpNode regtype:$Rn, regtype:$Rm))]>,
|
|
Sched<[WriteI]>;
|
|
|
|
// Split from LogicalImm as not all instructions have both.
|
|
multiclass LogicalReg<bits<2> opc, bit N, string mnemonic,
|
|
SDPatternOperator OpNode> {
|
|
def Wrr : BaseLogicalRegPseudo<GPR32, OpNode>;
|
|
def Xrr : BaseLogicalRegPseudo<GPR64, OpNode>;
|
|
|
|
def Wrs : BaseLogicalSReg<opc, N, GPR32, logical_shifted_reg32, mnemonic,
|
|
[(set GPR32:$Rd, (OpNode GPR32:$Rn,
|
|
logical_shifted_reg32:$Rm))]> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xrs : BaseLogicalSReg<opc, N, GPR64, logical_shifted_reg64, mnemonic,
|
|
[(set GPR64:$Rd, (OpNode GPR64:$Rn,
|
|
logical_shifted_reg64:$Rm))]> {
|
|
let Inst{31} = 1;
|
|
}
|
|
|
|
def : LogicalRegAlias<mnemonic,
|
|
!cast<Instruction>(NAME#"Wrs"), GPR32>;
|
|
def : LogicalRegAlias<mnemonic,
|
|
!cast<Instruction>(NAME#"Xrs"), GPR64>;
|
|
}
|
|
|
|
// Split from LogicalReg to allow setting CPSR Defs
|
|
multiclass LogicalRegS<bits<2> opc, bit N, string mnemonic> {
|
|
let Defs = [CPSR], mayLoad = 0, mayStore = 0, hasSideEffects = 0 in {
|
|
def Wrs : BaseLogicalSReg<opc, N, GPR32, logical_shifted_reg32, mnemonic, []>{
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xrs : BaseLogicalSReg<opc, N, GPR64, logical_shifted_reg64, mnemonic, []>{
|
|
let Inst{31} = 1;
|
|
}
|
|
} // Defs = [CPSR]
|
|
|
|
def : LogicalRegAlias<mnemonic,
|
|
!cast<Instruction>(NAME#"Wrs"), GPR32>;
|
|
def : LogicalRegAlias<mnemonic,
|
|
!cast<Instruction>(NAME#"Xrs"), GPR64>;
|
|
}
|
|
|
|
//---
|
|
// Conditionally set flags
|
|
//---
|
|
|
|
// Condition code.
|
|
// 4-bit immediate. Pretty-printed as <cc>
|
|
def ccode : Operand<i32> {
|
|
let PrintMethod = "printCondCode";
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseCondSetFlagsImm<bit op, RegisterClass regtype, string asm>
|
|
: I<(outs), (ins regtype:$Rn, imm0_31:$imm, imm0_15:$nzcv, ccode:$cond),
|
|
asm, "\t$Rn, $imm, $nzcv, $cond", "", []>,
|
|
Sched<[WriteI]> {
|
|
let Uses = [CPSR];
|
|
let Defs = [CPSR];
|
|
|
|
bits<5> Rn;
|
|
bits<5> imm;
|
|
bits<4> nzcv;
|
|
bits<4> cond;
|
|
|
|
let Inst{30} = op;
|
|
let Inst{29-21} = 0b111010010;
|
|
let Inst{20-16} = imm;
|
|
let Inst{15-12} = cond;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4} = 0b0;
|
|
let Inst{3-0} = nzcv;
|
|
}
|
|
|
|
multiclass CondSetFlagsImm<bit op, string asm> {
|
|
def Wi : BaseCondSetFlagsImm<op, GPR32, asm> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xi : BaseCondSetFlagsImm<op, GPR64, asm> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseCondSetFlagsReg<bit op, RegisterClass regtype, string asm>
|
|
: I<(outs), (ins regtype:$Rn, regtype:$Rm, imm0_15:$nzcv, ccode:$cond),
|
|
asm, "\t$Rn, $Rm, $nzcv, $cond", "", []>,
|
|
Sched<[WriteI]> {
|
|
let Uses = [CPSR];
|
|
let Defs = [CPSR];
|
|
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<4> nzcv;
|
|
bits<4> cond;
|
|
|
|
let Inst{30} = op;
|
|
let Inst{29-21} = 0b111010010;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = cond;
|
|
let Inst{11-10} = 0b00;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4} = 0b0;
|
|
let Inst{3-0} = nzcv;
|
|
}
|
|
|
|
multiclass CondSetFlagsReg<bit op, string asm> {
|
|
def Wr : BaseCondSetFlagsReg<op, GPR32, asm> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xr : BaseCondSetFlagsReg<op, GPR64, asm> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Conditional select
|
|
//---
|
|
|
|
class BaseCondSelect<bit op, bits<2> op2, RegisterClass regtype, string asm>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm, ccode:$cond),
|
|
asm, "\t$Rd, $Rn, $Rm, $cond", "",
|
|
[(set regtype:$Rd,
|
|
(ARM64csel regtype:$Rn, regtype:$Rm, (i32 imm:$cond), CPSR))]>,
|
|
Sched<[WriteI]> {
|
|
let Uses = [CPSR];
|
|
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<4> cond;
|
|
|
|
let Inst{30} = op;
|
|
let Inst{29-21} = 0b011010100;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = cond;
|
|
let Inst{11-10} = op2;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass CondSelect<bit op, bits<2> op2, string asm> {
|
|
def Wr : BaseCondSelect<op, op2, GPR32, asm> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xr : BaseCondSelect<op, op2, GPR64, asm> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
class BaseCondSelectOp<bit op, bits<2> op2, RegisterClass regtype, string asm,
|
|
PatFrag frag>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm, ccode:$cond),
|
|
asm, "\t$Rd, $Rn, $Rm, $cond", "",
|
|
[(set regtype:$Rd,
|
|
(ARM64csel regtype:$Rn, (frag regtype:$Rm),
|
|
(i32 imm:$cond), CPSR))]>,
|
|
Sched<[WriteI]> {
|
|
let Uses = [CPSR];
|
|
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<4> cond;
|
|
|
|
let Inst{30} = op;
|
|
let Inst{29-21} = 0b011010100;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = cond;
|
|
let Inst{11-10} = op2;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass CondSelectOp<bit op, bits<2> op2, string asm, PatFrag frag> {
|
|
def Wr : BaseCondSelectOp<op, op2, GPR32, asm, frag> {
|
|
let Inst{31} = 0;
|
|
}
|
|
def Xr : BaseCondSelectOp<op, op2, GPR64, asm, frag> {
|
|
let Inst{31} = 1;
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Special Mask Value
|
|
//---
|
|
def maski8_or_more : Operand<i32>,
|
|
ImmLeaf<i32, [{ return (Imm & 0xff) == 0xff; }]> {
|
|
}
|
|
def maski16_or_more : Operand<i32>,
|
|
ImmLeaf<i32, [{ return (Imm & 0xffff) == 0xffff; }]> {
|
|
}
|
|
|
|
|
|
//---
|
|
// Load/store
|
|
//---
|
|
|
|
// (unsigned immediate)
|
|
// Indexed for 8-bit registers. offset is in range [0,4095].
|
|
def MemoryIndexed8Operand : AsmOperandClass {
|
|
let Name = "MemoryIndexed8";
|
|
let DiagnosticType = "InvalidMemoryIndexed8";
|
|
}
|
|
def am_indexed8 : Operand<i64>,
|
|
ComplexPattern<i64, 2, "SelectAddrModeIndexed8", []> {
|
|
let PrintMethod = "printAMIndexed8";
|
|
let EncoderMethod
|
|
= "getAMIndexed8OpValue<ARM64::fixup_arm64_ldst_imm12_scale1>";
|
|
let ParserMatchClass = MemoryIndexed8Operand;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
|
|
}
|
|
|
|
// Indexed for 16-bit registers. offset is multiple of 2 in range [0,8190],
|
|
// stored as immval/2 (the 12-bit literal that encodes directly into the insn).
|
|
def MemoryIndexed16Operand : AsmOperandClass {
|
|
let Name = "MemoryIndexed16";
|
|
let DiagnosticType = "InvalidMemoryIndexed16";
|
|
}
|
|
def am_indexed16 : Operand<i64>,
|
|
ComplexPattern<i64, 2, "SelectAddrModeIndexed16", []> {
|
|
let PrintMethod = "printAMIndexed16";
|
|
let EncoderMethod
|
|
= "getAMIndexed8OpValue<ARM64::fixup_arm64_ldst_imm12_scale2>";
|
|
let ParserMatchClass = MemoryIndexed16Operand;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
|
|
}
|
|
|
|
// Indexed for 32-bit registers. offset is multiple of 4 in range [0,16380],
|
|
// stored as immval/4 (the 12-bit literal that encodes directly into the insn).
|
|
def MemoryIndexed32Operand : AsmOperandClass {
|
|
let Name = "MemoryIndexed32";
|
|
let DiagnosticType = "InvalidMemoryIndexed32";
|
|
}
|
|
def am_indexed32 : Operand<i64>,
|
|
ComplexPattern<i64, 2, "SelectAddrModeIndexed32", []> {
|
|
let PrintMethod = "printAMIndexed32";
|
|
let EncoderMethod
|
|
= "getAMIndexed8OpValue<ARM64::fixup_arm64_ldst_imm12_scale4>";
|
|
let ParserMatchClass = MemoryIndexed32Operand;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
|
|
}
|
|
|
|
// Indexed for 64-bit registers. offset is multiple of 8 in range [0,32760],
|
|
// stored as immval/8 (the 12-bit literal that encodes directly into the insn).
|
|
def MemoryIndexed64Operand : AsmOperandClass {
|
|
let Name = "MemoryIndexed64";
|
|
let DiagnosticType = "InvalidMemoryIndexed64";
|
|
}
|
|
def am_indexed64 : Operand<i64>,
|
|
ComplexPattern<i64, 2, "SelectAddrModeIndexed64", []> {
|
|
let PrintMethod = "printAMIndexed64";
|
|
let EncoderMethod
|
|
= "getAMIndexed8OpValue<ARM64::fixup_arm64_ldst_imm12_scale8>";
|
|
let ParserMatchClass = MemoryIndexed64Operand;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
|
|
}
|
|
|
|
// Indexed for 128-bit registers. offset is multiple of 16 in range [0,65520],
|
|
// stored as immval/16 (the 12-bit literal that encodes directly into the insn).
|
|
def MemoryIndexed128Operand : AsmOperandClass {
|
|
let Name = "MemoryIndexed128";
|
|
let DiagnosticType = "InvalidMemoryIndexed128";
|
|
}
|
|
def am_indexed128 : Operand<i64>,
|
|
ComplexPattern<i64, 2, "SelectAddrModeIndexed128", []> {
|
|
let PrintMethod = "printAMIndexed128";
|
|
let EncoderMethod
|
|
= "getAMIndexed8OpValue<ARM64::fixup_arm64_ldst_imm12_scale16>";
|
|
let ParserMatchClass = MemoryIndexed128Operand;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
|
|
}
|
|
|
|
// No offset.
|
|
def MemoryNoIndexOperand : AsmOperandClass { let Name = "MemoryNoIndex"; }
|
|
def am_noindex : Operand<i64>,
|
|
ComplexPattern<i64, 1, "SelectAddrModeNoIndex", []> {
|
|
let PrintMethod = "printAMNoIndex";
|
|
let ParserMatchClass = MemoryNoIndexOperand;
|
|
let MIOperandInfo = (ops GPR64sp:$base);
|
|
}
|
|
|
|
class BaseLoadStoreUI<bits<2> sz, bit V, bits<2> opc, dag oops, dag iops,
|
|
string asm, list<dag> pattern>
|
|
: I<oops, iops, asm, "\t$Rt, $addr", "", pattern> {
|
|
bits<5> dst;
|
|
|
|
bits<17> addr;
|
|
bits<5> base = addr{4-0};
|
|
bits<12> offset = addr{16-5};
|
|
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b01;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21-10} = offset;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeUnsignedLdStInstruction";
|
|
}
|
|
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
class LoadUI<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
Operand indextype, string asm, list<dag> pattern>
|
|
: BaseLoadStoreUI<sz, V, opc,
|
|
(outs regtype:$Rt), (ins indextype:$addr), asm, pattern>,
|
|
Sched<[WriteLD]>;
|
|
|
|
let mayLoad = 0, mayStore = 1, hasSideEffects = 0 in
|
|
class StoreUI<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
Operand indextype, string asm, list<dag> pattern>
|
|
: BaseLoadStoreUI<sz, V, opc,
|
|
(outs), (ins regtype:$Rt, indextype:$addr), asm, pattern>,
|
|
Sched<[WriteST]>;
|
|
|
|
def PrefetchOperand : AsmOperandClass {
|
|
let Name = "Prefetch";
|
|
let ParserMethod = "tryParsePrefetch";
|
|
}
|
|
def prfop : Operand<i32> {
|
|
let PrintMethod = "printPrefetchOp";
|
|
let ParserMatchClass = PrefetchOperand;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
|
|
class PrefetchUI<bits<2> sz, bit V, bits<2> opc, string asm, list<dag> pat>
|
|
: BaseLoadStoreUI<sz, V, opc,
|
|
(outs), (ins prfop:$Rt, am_indexed64:$addr), asm, pat>,
|
|
Sched<[WriteLD]>;
|
|
|
|
//---
|
|
// Load literal
|
|
//---
|
|
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
class LoadLiteral<bits<2> opc, bit V, RegisterClass regtype, string asm>
|
|
: I<(outs regtype:$Rt), (ins am_brcond:$label),
|
|
asm, "\t$Rt, $label", "", []>,
|
|
Sched<[WriteLD]> {
|
|
bits<5> Rt;
|
|
bits<19> label;
|
|
let Inst{31-30} = opc;
|
|
let Inst{29-27} = 0b011;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-5} = label;
|
|
let Inst{4-0} = Rt;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
|
|
class PrefetchLiteral<bits<2> opc, bit V, string asm, list<dag> pat>
|
|
: I<(outs), (ins prfop:$Rt, am_brcond:$label),
|
|
asm, "\t$Rt, $label", "", pat>,
|
|
Sched<[WriteLD]> {
|
|
bits<5> Rt;
|
|
bits<19> label;
|
|
let Inst{31-30} = opc;
|
|
let Inst{29-27} = 0b011;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-5} = label;
|
|
let Inst{4-0} = Rt;
|
|
}
|
|
|
|
//---
|
|
// Load/store register offset
|
|
//---
|
|
|
|
class MemROAsmOperand<int sz> : AsmOperandClass {
|
|
let Name = "MemoryRegisterOffset"#sz;
|
|
}
|
|
|
|
def MemROAsmOperand8 : MemROAsmOperand<8>;
|
|
def MemROAsmOperand16 : MemROAsmOperand<16>;
|
|
def MemROAsmOperand32 : MemROAsmOperand<32>;
|
|
def MemROAsmOperand64 : MemROAsmOperand<64>;
|
|
def MemROAsmOperand128 : MemROAsmOperand<128>;
|
|
|
|
class ro_indexed<int sz> : Operand<i64> { // ComplexPattern<...>
|
|
let PrintMethod = "printMemoryRegOffset"#sz;
|
|
let MIOperandInfo = (ops GPR64sp:$base, GPR64:$offset, i32imm:$extend);
|
|
}
|
|
|
|
def ro_indexed8 : ro_indexed<8>, ComplexPattern<i64, 3, "SelectAddrModeRO8", []> {
|
|
let ParserMatchClass = MemROAsmOperand8;
|
|
}
|
|
|
|
def ro_indexed16 : ro_indexed<16>, ComplexPattern<i64, 3, "SelectAddrModeRO16", []> {
|
|
let ParserMatchClass = MemROAsmOperand16;
|
|
}
|
|
|
|
def ro_indexed32 : ro_indexed<32>, ComplexPattern<i64, 3, "SelectAddrModeRO32", []> {
|
|
let ParserMatchClass = MemROAsmOperand32;
|
|
}
|
|
|
|
def ro_indexed64 : ro_indexed<64>, ComplexPattern<i64, 3, "SelectAddrModeRO64", []> {
|
|
let ParserMatchClass = MemROAsmOperand64;
|
|
}
|
|
|
|
def ro_indexed128 : ro_indexed<128>, ComplexPattern<i64, 3, "SelectAddrModeRO128", []> {
|
|
let ParserMatchClass = MemROAsmOperand128;
|
|
}
|
|
|
|
class LoadStore8RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, dag ins, dag outs, list<dag> pat>
|
|
: I<ins, outs, asm, "\t$Rt, $addr", "", pat> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<5> offset;
|
|
bits<4> extend;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = offset;
|
|
let Inst{15-13} = extend{3-1};
|
|
|
|
let Inst{12} = extend{0};
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeRegOffsetLdStInstruction";
|
|
}
|
|
|
|
class Load8RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore8RO<sz, V, opc, regtype, asm,
|
|
(outs regtype:$Rt), (ins ro_indexed8:$addr), pat>,
|
|
Sched<[WriteLDIdx, ReadAdrBase]>;
|
|
|
|
class Store8RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore8RO<sz, V, opc, regtype, asm,
|
|
(outs), (ins regtype:$Rt, ro_indexed8:$addr), pat>,
|
|
Sched<[WriteSTIdx, ReadAdrBase]>;
|
|
|
|
class LoadStore16RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, dag ins, dag outs, list<dag> pat>
|
|
: I<ins, outs, asm, "\t$Rt, $addr", "", pat> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<5> offset;
|
|
bits<4> extend;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = offset;
|
|
let Inst{15-13} = extend{3-1};
|
|
|
|
let Inst{12} = extend{0};
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeRegOffsetLdStInstruction";
|
|
}
|
|
|
|
class Load16RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore16RO<sz, V, opc, regtype, asm,
|
|
(outs regtype:$Rt), (ins ro_indexed16:$addr), pat>,
|
|
Sched<[WriteLDIdx, ReadAdrBase]>;
|
|
|
|
class Store16RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore16RO<sz, V, opc, regtype, asm,
|
|
(outs), (ins regtype:$Rt, ro_indexed16:$addr), pat>,
|
|
Sched<[WriteSTIdx, ReadAdrBase]>;
|
|
|
|
class LoadStore32RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, dag ins, dag outs, list<dag> pat>
|
|
: I<ins, outs, asm, "\t$Rt, $addr", "", pat> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<5> offset;
|
|
bits<4> extend;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = offset;
|
|
let Inst{15-13} = extend{3-1};
|
|
|
|
let Inst{12} = extend{0};
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeRegOffsetLdStInstruction";
|
|
}
|
|
|
|
class Load32RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore32RO<sz, V, opc, regtype, asm,
|
|
(outs regtype:$Rt), (ins ro_indexed32:$addr), pat>,
|
|
Sched<[WriteLDIdx, ReadAdrBase]>;
|
|
|
|
class Store32RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore32RO<sz, V, opc, regtype, asm,
|
|
(outs), (ins regtype:$Rt, ro_indexed32:$addr), pat>,
|
|
Sched<[WriteSTIdx, ReadAdrBase]>;
|
|
|
|
class LoadStore64RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, dag ins, dag outs, list<dag> pat>
|
|
: I<ins, outs, asm, "\t$Rt, $addr", "", pat> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<5> offset;
|
|
bits<4> extend;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = offset;
|
|
let Inst{15-13} = extend{3-1};
|
|
|
|
let Inst{12} = extend{0};
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeRegOffsetLdStInstruction";
|
|
}
|
|
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
class Load64RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore64RO<sz, V, opc, regtype, asm,
|
|
(outs regtype:$Rt), (ins ro_indexed64:$addr), pat>,
|
|
Sched<[WriteLDIdx, ReadAdrBase]>;
|
|
|
|
let mayLoad = 0, mayStore = 1, hasSideEffects = 0 in
|
|
class Store64RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore64RO<sz, V, opc, regtype, asm,
|
|
(outs), (ins regtype:$Rt, ro_indexed64:$addr), pat>,
|
|
Sched<[WriteSTIdx, ReadAdrBase]>;
|
|
|
|
|
|
class LoadStore128RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, dag ins, dag outs, list<dag> pat>
|
|
: I<ins, outs, asm, "\t$Rt, $addr", "", pat> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<5> offset;
|
|
bits<4> extend;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = offset;
|
|
let Inst{15-13} = extend{3-1};
|
|
|
|
let Inst{12} = extend{0};
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeRegOffsetLdStInstruction";
|
|
}
|
|
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
class Load128RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore128RO<sz, V, opc, regtype, asm,
|
|
(outs regtype:$Rt), (ins ro_indexed128:$addr), pat>,
|
|
Sched<[WriteLDIdx, ReadAdrBase]>;
|
|
|
|
let mayLoad = 0, mayStore = 1, hasSideEffects = 0 in
|
|
class Store128RO<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: LoadStore128RO<sz, V, opc, regtype, asm,
|
|
(outs), (ins regtype:$Rt, ro_indexed128:$addr), pat>,
|
|
Sched<[WriteSTIdx, ReadAdrBase]>;
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
|
|
class PrefetchRO<bits<2> sz, bit V, bits<2> opc, string asm, list<dag> pat>
|
|
: I<(outs), (ins prfop:$Rt, ro_indexed64:$addr), asm,
|
|
"\t$Rt, $addr", "", pat>,
|
|
Sched<[WriteLD]> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<5> offset;
|
|
bits<4> extend;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = offset;
|
|
let Inst{15-13} = extend{3-1};
|
|
|
|
let Inst{12} = extend{0};
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeRegOffsetLdStInstruction";
|
|
}
|
|
|
|
//---
|
|
// Load/store unscaled immediate
|
|
//---
|
|
|
|
def MemoryUnscaledOperand : AsmOperandClass {
|
|
let Name = "MemoryUnscaled";
|
|
let DiagnosticType = "InvalidMemoryIndexedSImm9";
|
|
}
|
|
class am_unscaled_operand : Operand<i64> {
|
|
let PrintMethod = "printAMUnscaled";
|
|
let ParserMatchClass = MemoryUnscaledOperand;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
|
|
}
|
|
def am_unscaled : am_unscaled_operand;
|
|
def am_unscaled8 : am_unscaled_operand,
|
|
ComplexPattern<i64, 2, "SelectAddrModeUnscaled8", []>;
|
|
def am_unscaled16 : am_unscaled_operand,
|
|
ComplexPattern<i64, 2, "SelectAddrModeUnscaled16", []>;
|
|
def am_unscaled32 : am_unscaled_operand,
|
|
ComplexPattern<i64, 2, "SelectAddrModeUnscaled32", []>;
|
|
def am_unscaled64 : am_unscaled_operand,
|
|
ComplexPattern<i64, 2, "SelectAddrModeUnscaled64", []>;
|
|
def am_unscaled128 : am_unscaled_operand,
|
|
ComplexPattern<i64, 2, "SelectAddrModeUnscaled128", []>;
|
|
|
|
class BaseLoadStoreUnscale<bits<2> sz, bit V, bits<2> opc, dag oops, dag iops,
|
|
string asm, list<dag> pattern>
|
|
: I<oops, iops, asm, "\t$Rt, $addr", "", pattern> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<9> offset;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 0;
|
|
let Inst{20-12} = offset;
|
|
let Inst{11-10} = 0b00;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeSignedLdStInstruction";
|
|
}
|
|
|
|
let AddedComplexity = 1 in // try this before LoadUI
|
|
class LoadUnscaled<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
Operand amtype, string asm, list<dag> pattern>
|
|
: BaseLoadStoreUnscale<sz, V, opc, (outs regtype:$Rt),
|
|
(ins amtype:$addr), asm, pattern>,
|
|
Sched<[WriteLD]>;
|
|
|
|
let AddedComplexity = 1 in // try this before StoreUI
|
|
class StoreUnscaled<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
Operand amtype, string asm, list<dag> pattern>
|
|
: BaseLoadStoreUnscale<sz, V, opc, (outs),
|
|
(ins regtype:$Rt, amtype:$addr), asm, pattern>,
|
|
Sched<[WriteST]>;
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
|
|
class PrefetchUnscaled<bits<2> sz, bit V, bits<2> opc, string asm, list<dag> pat>
|
|
: BaseLoadStoreUnscale<sz, V, opc, (outs),
|
|
(ins prfop:$Rt, am_unscaled:$addr), asm, pat>,
|
|
Sched<[WriteLD]>;
|
|
|
|
//---
|
|
// Load/store unscaled immediate, unprivileged
|
|
//---
|
|
|
|
class BaseLoadStoreUnprivileged<bits<2> sz, bit V, bits<2> opc,
|
|
dag oops, dag iops, string asm>
|
|
: I<oops, iops, asm, "\t$Rt, $addr", "", []> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<9> offset;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 0;
|
|
let Inst{20-12} = offset;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeSignedLdStInstruction";
|
|
}
|
|
|
|
let mayStore = 0, mayLoad = 1, hasSideEffects = 0 in {
|
|
class LoadUnprivileged<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm>
|
|
: BaseLoadStoreUnprivileged<sz, V, opc,
|
|
(outs regtype:$Rt), (ins am_unscaled:$addr), asm>,
|
|
Sched<[WriteLD]>;
|
|
}
|
|
|
|
let mayStore = 1, mayLoad = 0, hasSideEffects = 0 in {
|
|
class StoreUnprivileged<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm>
|
|
: BaseLoadStoreUnprivileged<sz, V, opc,
|
|
(outs), (ins regtype:$Rt, am_unscaled:$addr), asm>,
|
|
Sched<[WriteST]>;
|
|
}
|
|
|
|
//---
|
|
// Load/store pre-indexed
|
|
//---
|
|
|
|
class BaseLoadStorePreIdx<bits<2> sz, bit V, bits<2> opc, dag oops, dag iops,
|
|
string asm, string cstr>
|
|
: I<oops, iops, asm, "\t$Rt, $addr!", cstr, []> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<9> offset;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 0;
|
|
let Inst{20-12} = offset;
|
|
let Inst{11-10} = 0b11;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeSignedLdStInstruction";
|
|
}
|
|
|
|
let hasSideEffects = 0 in {
|
|
let mayStore = 0, mayLoad = 1 in
|
|
// FIXME: Modeling the write-back of these instructions for isel is tricky.
|
|
// we need the complex addressing mode for the memory reference, but
|
|
// we also need the write-back specified as a tied operand to the
|
|
// base register. That combination does not play nicely with
|
|
// the asm matcher and friends.
|
|
class LoadPreIdx<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm>
|
|
: BaseLoadStorePreIdx<sz, V, opc,
|
|
(outs regtype:$Rt/*, GPR64sp:$wback*/),
|
|
(ins am_unscaled:$addr), asm, ""/*"$addr.base = $wback"*/>,
|
|
Sched<[WriteLD, WriteAdr]>;
|
|
|
|
let mayStore = 1, mayLoad = 0 in
|
|
class StorePreIdx<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm>
|
|
: BaseLoadStorePreIdx<sz, V, opc,
|
|
(outs/* GPR64sp:$wback*/),
|
|
(ins regtype:$Rt, am_unscaled:$addr),
|
|
asm, ""/*"$addr.base = $wback"*/>,
|
|
Sched<[WriteAdr, WriteST]>;
|
|
} // hasSideEffects = 0
|
|
|
|
// ISel pseudo-instructions which have the tied operands. When the MC lowering
|
|
// logic finally gets smart enough to strip off tied operands that are just
|
|
// for isel convenience, we can get rid of these pseudos and just reference
|
|
// the real instructions directly.
|
|
//
|
|
// Ironically, also because of the writeback operands, we can't put the
|
|
// matcher pattern directly on the instruction, but need to define it
|
|
// separately.
|
|
//
|
|
// Loads aren't matched with patterns here at all, but rather in C++
|
|
// custom lowering.
|
|
let mayStore = 0, mayLoad = 1, hasSideEffects = 0 in {
|
|
class LoadPreIdxPseudo<RegisterClass regtype>
|
|
: Pseudo<(outs regtype:$Rt, GPR64sp:$wback),
|
|
(ins am_noindex:$addr, simm9:$offset), [],
|
|
"$addr.base = $wback,@earlyclobber $wback">,
|
|
Sched<[WriteLD, WriteAdr]>;
|
|
class LoadPostIdxPseudo<RegisterClass regtype>
|
|
: Pseudo<(outs regtype:$Rt, GPR64sp:$wback),
|
|
(ins am_noindex:$addr, simm9:$offset), [],
|
|
"$addr.base = $wback,@earlyclobber $wback">,
|
|
Sched<[WriteLD, WriteI]>;
|
|
}
|
|
multiclass StorePreIdxPseudo<RegisterClass regtype, ValueType Ty,
|
|
SDPatternOperator OpNode> {
|
|
let mayStore = 1, mayLoad = 0, hasSideEffects = 0 in
|
|
def _isel: Pseudo<(outs GPR64sp:$wback),
|
|
(ins regtype:$Rt, am_noindex:$addr, simm9:$offset), [],
|
|
"$addr.base = $wback,@earlyclobber $wback">,
|
|
Sched<[WriteAdr, WriteST]>;
|
|
|
|
def : Pat<(OpNode (Ty regtype:$Rt), am_noindex:$addr, simm9:$offset),
|
|
(!cast<Instruction>(NAME#_isel) regtype:$Rt, am_noindex:$addr,
|
|
simm9:$offset)>;
|
|
}
|
|
|
|
//---
|
|
// Load/store post-indexed
|
|
//---
|
|
|
|
// (pre-index) load/stores.
|
|
class BaseLoadStorePostIdx<bits<2> sz, bit V, bits<2> opc, dag oops, dag iops,
|
|
string asm, string cstr>
|
|
: I<oops, iops, asm, "\t$Rt, $addr, $idx", cstr, []> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling.
|
|
bits<5> dst;
|
|
bits<5> base;
|
|
bits<9> offset;
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-27} = 0b111;
|
|
let Inst{26} = V;
|
|
let Inst{25-24} = 0b00;
|
|
let Inst{23-22} = opc;
|
|
let Inst{21} = 0b0;
|
|
let Inst{20-12} = offset;
|
|
let Inst{11-10} = 0b01;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodeSignedLdStInstruction";
|
|
}
|
|
|
|
let hasSideEffects = 0 in {
|
|
let mayStore = 0, mayLoad = 1 in
|
|
// FIXME: Modeling the write-back of these instructions for isel is tricky.
|
|
// we need the complex addressing mode for the memory reference, but
|
|
// we also need the write-back specified as a tied operand to the
|
|
// base register. That combination does not play nicely with
|
|
// the asm matcher and friends.
|
|
class LoadPostIdx<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm>
|
|
: BaseLoadStorePostIdx<sz, V, opc,
|
|
(outs regtype:$Rt/*, GPR64sp:$wback*/),
|
|
(ins am_noindex:$addr, simm9:$idx),
|
|
asm, ""/*"$addr.base = $wback"*/>,
|
|
Sched<[WriteLD, WriteI]>;
|
|
|
|
let mayStore = 1, mayLoad = 0 in
|
|
class StorePostIdx<bits<2> sz, bit V, bits<2> opc, RegisterClass regtype,
|
|
string asm>
|
|
: BaseLoadStorePostIdx<sz, V, opc,
|
|
(outs/* GPR64sp:$wback*/),
|
|
(ins regtype:$Rt, am_noindex:$addr, simm9:$idx),
|
|
asm, ""/*"$addr.base = $wback"*/>,
|
|
Sched<[WriteAdr, WriteST, ReadAdrBase]>;
|
|
} // hasSideEffects = 0
|
|
|
|
// ISel pseudo-instructions which have the tied operands. When the MC lowering
|
|
// logic finally gets smart enough to strip off tied operands that are just
|
|
// for isel convenience, we can get rid of these pseudos and just reference
|
|
// the real instructions directly.
|
|
//
|
|
// Ironically, also because of the writeback operands, we can't put the
|
|
// matcher pattern directly on the instruction, but need to define it
|
|
// separately.
|
|
multiclass StorePostIdxPseudo<RegisterClass regtype, ValueType Ty,
|
|
SDPatternOperator OpNode, Instruction Insn> {
|
|
let mayStore = 1, mayLoad = 0, hasSideEffects = 0 in
|
|
def _isel: Pseudo<(outs GPR64sp:$wback),
|
|
(ins regtype:$Rt, am_noindex:$addr, simm9:$idx), [],
|
|
"$addr.base = $wback,@earlyclobber $wback">,
|
|
PseudoInstExpansion<(Insn regtype:$Rt, am_noindex:$addr, simm9:$idx)>,
|
|
Sched<[WriteAdr, WriteST, ReadAdrBase]>;
|
|
|
|
def : Pat<(OpNode (Ty regtype:$Rt), am_noindex:$addr, simm9:$idx),
|
|
(!cast<Instruction>(NAME#_isel) regtype:$Rt, am_noindex:$addr,
|
|
simm9:$idx)>;
|
|
}
|
|
|
|
//---
|
|
// Load/store pair
|
|
//---
|
|
|
|
// (indexed, offset)
|
|
|
|
class BaseLoadStorePairOffset<bits<2> opc, bit V, bit L, dag oops, dag iops,
|
|
string asm>
|
|
: I<oops, iops, asm, "\t$Rt, $Rt2, $addr", "", []> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> dst2;
|
|
bits<5> base;
|
|
bits<7> offset;
|
|
let Inst{31-30} = opc;
|
|
let Inst{29-27} = 0b101;
|
|
let Inst{26} = V;
|
|
let Inst{25-23} = 0b010;
|
|
let Inst{22} = L;
|
|
let Inst{21-15} = offset;
|
|
let Inst{14-10} = dst2;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodePairLdStInstruction";
|
|
}
|
|
|
|
let hasSideEffects = 0 in {
|
|
let mayStore = 0, mayLoad = 1 in
|
|
class LoadPairOffset<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand indextype, string asm>
|
|
: BaseLoadStorePairOffset<opc, V, 1,
|
|
(outs regtype:$Rt, regtype:$Rt2),
|
|
(ins indextype:$addr), asm>,
|
|
Sched<[WriteLD, WriteLDHi]>;
|
|
|
|
let mayLoad = 0, mayStore = 1 in
|
|
class StorePairOffset<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand indextype, string asm>
|
|
: BaseLoadStorePairOffset<opc, V, 0, (outs),
|
|
(ins regtype:$Rt, regtype:$Rt2, indextype:$addr),
|
|
asm>,
|
|
Sched<[WriteSTP]>;
|
|
} // hasSideEffects = 0
|
|
|
|
// (pre-indexed)
|
|
|
|
def MemoryIndexed32SImm7 : AsmOperandClass {
|
|
let Name = "MemoryIndexed32SImm7";
|
|
let DiagnosticType = "InvalidMemoryIndexed32SImm7";
|
|
}
|
|
def am_indexed32simm7 : Operand<i32> { // ComplexPattern<...>
|
|
let PrintMethod = "printAMIndexed32";
|
|
let ParserMatchClass = MemoryIndexed32SImm7;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i32imm:$offset);
|
|
}
|
|
|
|
def MemoryIndexed64SImm7 : AsmOperandClass {
|
|
let Name = "MemoryIndexed64SImm7";
|
|
let DiagnosticType = "InvalidMemoryIndexed64SImm7";
|
|
}
|
|
def am_indexed64simm7 : Operand<i32> { // ComplexPattern<...>
|
|
let PrintMethod = "printAMIndexed64";
|
|
let ParserMatchClass = MemoryIndexed64SImm7;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i32imm:$offset);
|
|
}
|
|
|
|
def MemoryIndexed128SImm7 : AsmOperandClass {
|
|
let Name = "MemoryIndexed128SImm7";
|
|
let DiagnosticType = "InvalidMemoryIndexed128SImm7";
|
|
}
|
|
def am_indexed128simm7 : Operand<i32> { // ComplexPattern<...>
|
|
let PrintMethod = "printAMIndexed128";
|
|
let ParserMatchClass = MemoryIndexed128SImm7;
|
|
let MIOperandInfo = (ops GPR64sp:$base, i32imm:$offset);
|
|
}
|
|
|
|
class BaseLoadStorePairPreIdx<bits<2> opc, bit V, bit L, dag oops, dag iops,
|
|
string asm>
|
|
: I<oops, iops, asm, "\t$Rt, $Rt2, $addr!", "", []> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> dst2;
|
|
bits<5> base;
|
|
bits<7> offset;
|
|
let Inst{31-30} = opc;
|
|
let Inst{29-27} = 0b101;
|
|
let Inst{26} = V;
|
|
let Inst{25-23} = 0b011;
|
|
let Inst{22} = L;
|
|
let Inst{21-15} = offset;
|
|
let Inst{14-10} = dst2;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodePairLdStInstruction";
|
|
}
|
|
|
|
let hasSideEffects = 0 in {
|
|
let mayStore = 0, mayLoad = 1 in
|
|
class LoadPairPreIdx<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand addrmode, string asm>
|
|
: BaseLoadStorePairPreIdx<opc, V, 1,
|
|
(outs regtype:$Rt, regtype:$Rt2),
|
|
(ins addrmode:$addr), asm>,
|
|
Sched<[WriteLD, WriteLDHi, WriteAdr]>;
|
|
|
|
let mayStore = 1, mayLoad = 0 in
|
|
class StorePairPreIdx<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand addrmode, string asm>
|
|
: BaseLoadStorePairPreIdx<opc, V, 0, (outs),
|
|
(ins regtype:$Rt, regtype:$Rt2, addrmode:$addr),
|
|
asm>,
|
|
Sched<[WriteAdr, WriteSTP]>;
|
|
} // hasSideEffects = 0
|
|
|
|
// (post-indexed)
|
|
|
|
class BaseLoadStorePairPostIdx<bits<2> opc, bit V, bit L, dag oops, dag iops,
|
|
string asm>
|
|
: I<oops, iops, asm, "\t$Rt, $Rt2, $addr, $idx", "", []> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> dst2;
|
|
bits<5> base;
|
|
bits<7> offset;
|
|
let Inst{31-30} = opc;
|
|
let Inst{29-27} = 0b101;
|
|
let Inst{26} = V;
|
|
let Inst{25-23} = 0b001;
|
|
let Inst{22} = L;
|
|
let Inst{21-15} = offset;
|
|
let Inst{14-10} = dst2;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodePairLdStInstruction";
|
|
}
|
|
|
|
let hasSideEffects = 0 in {
|
|
let mayStore = 0, mayLoad = 1 in
|
|
class LoadPairPostIdx<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand idxtype, string asm>
|
|
: BaseLoadStorePairPostIdx<opc, V, 1,
|
|
(outs regtype:$Rt, regtype:$Rt2),
|
|
(ins am_noindex:$addr, idxtype:$idx), asm>,
|
|
Sched<[WriteLD, WriteLDHi, WriteAdr]>;
|
|
|
|
let mayStore = 1, mayLoad = 0 in
|
|
class StorePairPostIdx<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand idxtype, string asm>
|
|
: BaseLoadStorePairPostIdx<opc, V, 0, (outs),
|
|
(ins regtype:$Rt, regtype:$Rt2,
|
|
am_noindex:$addr, idxtype:$idx),
|
|
asm>,
|
|
Sched<[WriteAdr, WriteSTP]>;
|
|
} // hasSideEffects = 0
|
|
|
|
// (no-allocate)
|
|
|
|
class BaseLoadStorePairNoAlloc<bits<2> opc, bit V, bit L, dag oops, dag iops,
|
|
string asm>
|
|
: I<oops, iops, asm, "\t$Rt, $Rt2, $addr", "", []> {
|
|
// The operands are in order to match the 'addr' MI operands, so we
|
|
// don't need an encoder method and by-name matching. Just use the default
|
|
// in-order handling. Since we're using by-order, make sure the names
|
|
// do not match.
|
|
bits<5> dst;
|
|
bits<5> dst2;
|
|
bits<5> base;
|
|
bits<7> offset;
|
|
let Inst{31-30} = opc;
|
|
let Inst{29-27} = 0b101;
|
|
let Inst{26} = V;
|
|
let Inst{25-23} = 0b000;
|
|
let Inst{22} = L;
|
|
let Inst{21-15} = offset;
|
|
let Inst{14-10} = dst2;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst;
|
|
|
|
let DecoderMethod = "DecodePairLdStInstruction";
|
|
}
|
|
|
|
let hasSideEffects = 0 in {
|
|
let mayStore = 0, mayLoad = 1 in
|
|
class LoadPairNoAlloc<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand indextype, string asm>
|
|
: BaseLoadStorePairNoAlloc<opc, V, 1,
|
|
(outs regtype:$Rt, regtype:$Rt2),
|
|
(ins indextype:$addr), asm>,
|
|
Sched<[WriteLD, WriteLDHi]>;
|
|
|
|
let mayStore = 1, mayLoad = 0 in
|
|
class StorePairNoAlloc<bits<2> opc, bit V, RegisterClass regtype,
|
|
Operand indextype, string asm>
|
|
: BaseLoadStorePairNoAlloc<opc, V, 0, (outs),
|
|
(ins regtype:$Rt, regtype:$Rt2, indextype:$addr),
|
|
asm>,
|
|
Sched<[WriteSTP]>;
|
|
} // hasSideEffects = 0
|
|
|
|
//---
|
|
// Load/store exclusive
|
|
//---
|
|
|
|
// True exclusive operations write to and/or read from the system's exclusive
|
|
// monitors, which as far as a compiler is concerned can be modelled as a
|
|
// random shared memory address. Hence LoadExclusive mayStore.
|
|
let hasSideEffects = 1, mayLoad = 1, mayStore = 1 in
|
|
class BaseLoadStoreExclusive<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
dag oops, dag iops, string asm, string operands>
|
|
: I<oops, iops, asm, operands, "", []> {
|
|
let Inst{31-30} = sz;
|
|
let Inst{29-24} = 0b001000;
|
|
let Inst{23} = o2;
|
|
let Inst{22} = L;
|
|
let Inst{21} = o1;
|
|
let Inst{15} = o0;
|
|
|
|
let DecoderMethod = "DecodeExclusiveLdStInstruction";
|
|
}
|
|
|
|
// Neither Rs nor Rt2 operands.
|
|
class LoadStoreExclusiveSimple<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
dag oops, dag iops, string asm, string operands>
|
|
: BaseLoadStoreExclusive<sz, o2, L, o1, o0, oops, iops, asm, operands> {
|
|
bits<5> reg;
|
|
bits<5> base;
|
|
let Inst{20-16} = 0b11111;
|
|
let Inst{14-10} = 0b11111;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = reg;
|
|
}
|
|
|
|
// Simple load acquires don't set the exclusive monitor
|
|
let mayLoad = 1, mayStore = 0 in
|
|
class LoadAcquire<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
RegisterClass regtype, string asm>
|
|
: LoadStoreExclusiveSimple<sz, o2, L, o1, o0, (outs regtype:$Rt),
|
|
(ins am_noindex:$addr), asm, "\t$Rt, $addr">,
|
|
Sched<[WriteLD]>;
|
|
|
|
class LoadExclusive<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
RegisterClass regtype, string asm>
|
|
: LoadStoreExclusiveSimple<sz, o2, L, o1, o0, (outs regtype:$Rt),
|
|
(ins am_noindex:$addr), asm, "\t$Rt, $addr">,
|
|
Sched<[WriteLD]>;
|
|
|
|
class LoadExclusivePair<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
RegisterClass regtype, string asm>
|
|
: BaseLoadStoreExclusive<sz, o2, L, o1, o0,
|
|
(outs regtype:$Rt, regtype:$Rt2),
|
|
(ins am_noindex:$addr), asm,
|
|
"\t$Rt, $Rt2, $addr">,
|
|
Sched<[WriteLD, WriteLDHi]> {
|
|
bits<5> dst1;
|
|
bits<5> dst2;
|
|
bits<5> base;
|
|
let Inst{20-16} = 0b11111;
|
|
let Inst{14-10} = dst2;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst1;
|
|
}
|
|
|
|
// Simple store release operations do not check the exclusive monitor.
|
|
let mayLoad = 0, mayStore = 1 in
|
|
class StoreRelease<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
RegisterClass regtype, string asm>
|
|
: LoadStoreExclusiveSimple<sz, o2, L, o1, o0, (outs),
|
|
(ins regtype:$Rt, am_noindex:$addr),
|
|
asm, "\t$Rt, $addr">,
|
|
Sched<[WriteST]>;
|
|
|
|
let mayLoad = 1, mayStore = 1 in
|
|
class StoreExclusive<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
RegisterClass regtype, string asm>
|
|
: BaseLoadStoreExclusive<sz, o2, L, o1, o0, (outs GPR32:$Ws),
|
|
(ins regtype:$Rt, am_noindex:$addr),
|
|
asm, "\t$Ws, $Rt, $addr">,
|
|
Sched<[WriteSTX]> {
|
|
bits<5> status;
|
|
bits<5> reg;
|
|
bits<5> base;
|
|
let Inst{20-16} = status;
|
|
let Inst{14-10} = 0b11111;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = reg;
|
|
|
|
let Constraints = "@earlyclobber $Ws";
|
|
}
|
|
|
|
class StoreExclusivePair<bits<2> sz, bit o2, bit L, bit o1, bit o0,
|
|
RegisterClass regtype, string asm>
|
|
: BaseLoadStoreExclusive<sz, o2, L, o1, o0,
|
|
(outs GPR32:$Ws),
|
|
(ins regtype:$Rt, regtype:$Rt2, am_noindex:$addr),
|
|
asm, "\t$Ws, $Rt, $Rt2, $addr">,
|
|
Sched<[WriteSTX]> {
|
|
bits<5> status;
|
|
bits<5> dst1;
|
|
bits<5> dst2;
|
|
bits<5> base;
|
|
let Inst{20-16} = status;
|
|
let Inst{14-10} = dst2;
|
|
let Inst{9-5} = base;
|
|
let Inst{4-0} = dst1;
|
|
|
|
let Constraints = "@earlyclobber $Ws";
|
|
}
|
|
|
|
//---
|
|
// Exception generation
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
|
|
class ExceptionGeneration<bits<3> op1, bits<2> ll, string asm>
|
|
: I<(outs), (ins imm0_65535:$imm), asm, "\t$imm", "", []>,
|
|
Sched<[WriteSys]> {
|
|
bits<16> imm;
|
|
let Inst{31-24} = 0b11010100;
|
|
let Inst{23-21} = op1;
|
|
let Inst{20-5} = imm;
|
|
let Inst{4-2} = 0b000;
|
|
let Inst{1-0} = ll;
|
|
}
|
|
|
|
//---
|
|
// Floating point to integer conversion
|
|
//---
|
|
|
|
class BaseFPToIntegerUnscaled<bits<2> type, bits<2> rmode, bits<3> opcode,
|
|
RegisterClass srcType, RegisterClass dstType,
|
|
string asm, list<dag> pattern>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn),
|
|
asm, "\t$Rd, $Rn", "", pattern>,
|
|
Sched<[WriteFCvt]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{30} = 0;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = type;
|
|
let Inst{21} = 1;
|
|
let Inst{20-19} = rmode;
|
|
let Inst{18-16} = opcode;
|
|
let Inst{15-10} = 0;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseFPToInteger<bits<2> type, bits<2> rmode, bits<3> opcode,
|
|
RegisterClass srcType, RegisterClass dstType,
|
|
Operand immType, string asm>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn, immType:$scale),
|
|
asm, "\t$Rd, $Rn, $scale", "", []>,
|
|
Sched<[WriteFCvt]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<6> scale;
|
|
let Inst{30} = 0;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = type;
|
|
let Inst{21} = 0;
|
|
let Inst{20-19} = rmode;
|
|
let Inst{18-16} = opcode;
|
|
let Inst{15-10} = scale;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass FPToInteger<bits<2> rmode, bits<3> opcode, string asm, SDPatternOperator OpN> {
|
|
// Unscaled single-precision to 32-bit
|
|
def UWSr : BaseFPToIntegerUnscaled<0b00, rmode, opcode, FPR32, GPR32, asm,
|
|
[(set GPR32:$Rd, (OpN FPR32:$Rn))]> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
}
|
|
|
|
// Unscaled single-precision to 64-bit
|
|
def UXSr : BaseFPToIntegerUnscaled<0b00, rmode, opcode, FPR32, GPR64, asm,
|
|
[(set GPR64:$Rd, (OpN FPR32:$Rn))]> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
}
|
|
|
|
// Unscaled double-precision to 32-bit
|
|
def UWDr : BaseFPToIntegerUnscaled<0b01, rmode, opcode, FPR64, GPR32, asm,
|
|
[(set GPR32:$Rd, (OpN (f64 FPR64:$Rn)))]> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
}
|
|
|
|
// Unscaled double-precision to 64-bit
|
|
def UXDr : BaseFPToIntegerUnscaled<0b01, rmode, opcode, FPR64, GPR64, asm,
|
|
[(set GPR64:$Rd, (OpN (f64 FPR64:$Rn)))]> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
}
|
|
|
|
// Scaled single-precision to 32-bit
|
|
def SWSri : BaseFPToInteger<0b00, rmode, opcode, FPR32, GPR32,
|
|
fixedpoint32, asm> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
}
|
|
|
|
// Scaled single-precision to 64-bit
|
|
def SXSri : BaseFPToInteger<0b00, rmode, opcode, FPR32, GPR64,
|
|
fixedpoint64, asm> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
}
|
|
|
|
// Scaled double-precision to 32-bit
|
|
def SWDri : BaseFPToInteger<0b01, rmode, opcode, FPR64, GPR32,
|
|
fixedpoint32, asm> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
}
|
|
|
|
// Scaled double-precision to 64-bit
|
|
def SXDri : BaseFPToInteger<0b01, rmode, opcode, FPR64, GPR64,
|
|
fixedpoint64, asm> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Integer to floating point conversion
|
|
//---
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseIntegerToFP<bit isUnsigned,
|
|
RegisterClass srcType, RegisterClass dstType,
|
|
Operand immType, string asm>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn, immType:$scale),
|
|
asm, "\t$Rd, $Rn, $scale", "", []>,
|
|
Sched<[WriteFCvt]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<6> scale;
|
|
let Inst{30-23} = 0b00111100;
|
|
let Inst{21-17} = 0b00001;
|
|
let Inst{16} = isUnsigned;
|
|
let Inst{15-10} = scale;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class BaseIntegerToFPUnscaled<bit isUnsigned,
|
|
RegisterClass srcType, RegisterClass dstType,
|
|
ValueType dvt, string asm, SDNode node>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn),
|
|
asm, "\t$Rd, $Rn", "", [(set (dvt dstType:$Rd), (node srcType:$Rn))]>,
|
|
Sched<[WriteFCvt]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<6> scale;
|
|
let Inst{30-23} = 0b00111100;
|
|
let Inst{21-17} = 0b10001;
|
|
let Inst{16} = isUnsigned;
|
|
let Inst{15-10} = 0b000000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass IntegerToFP<bit isUnsigned, string asm, SDNode node> {
|
|
// Unscaled
|
|
def UWSri: BaseIntegerToFPUnscaled<isUnsigned, GPR32, FPR32, f32, asm, node> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
let Inst{22} = 0; // 32-bit FPR flag
|
|
}
|
|
|
|
def UWDri: BaseIntegerToFPUnscaled<isUnsigned, GPR32, FPR64, f64, asm, node> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
let Inst{22} = 1; // 64-bit FPR flag
|
|
}
|
|
|
|
def UXSri: BaseIntegerToFPUnscaled<isUnsigned, GPR64, FPR32, f32, asm, node> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
let Inst{22} = 0; // 32-bit FPR flag
|
|
}
|
|
|
|
def UXDri: BaseIntegerToFPUnscaled<isUnsigned, GPR64, FPR64, f64, asm, node> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
let Inst{22} = 1; // 64-bit FPR flag
|
|
}
|
|
|
|
// Scaled
|
|
def SWSri: BaseIntegerToFP<isUnsigned, GPR32, FPR32, fixedpoint32, asm> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
let Inst{22} = 0; // 32-bit FPR flag
|
|
}
|
|
|
|
def SWDri: BaseIntegerToFP<isUnsigned, GPR32, FPR64, fixedpoint32, asm> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
let Inst{22} = 1; // 64-bit FPR flag
|
|
}
|
|
|
|
def SXSri: BaseIntegerToFP<isUnsigned, GPR64, FPR32, fixedpoint64, asm> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
let Inst{22} = 0; // 32-bit FPR flag
|
|
}
|
|
|
|
def SXDri: BaseIntegerToFP<isUnsigned, GPR64, FPR64, fixedpoint64, asm> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
let Inst{22} = 1; // 64-bit FPR flag
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Unscaled integer <-> floating point conversion (i.e. FMOV)
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseUnscaledConversion<bits<2> rmode, bits<3> opcode,
|
|
RegisterClass srcType, RegisterClass dstType,
|
|
string asm>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn), asm, "\t$Rd, $Rn", "",
|
|
// We use COPY_TO_REGCLASS for these bitconvert operations.
|
|
// copyPhysReg() expands the resultant COPY instructions after
|
|
// regalloc is done. This gives greater freedom for the allocator
|
|
// and related passes (coalescing, copy propagation, et. al.) to
|
|
// be more effective.
|
|
[/*(set (dvt dstType:$Rd), (bitconvert (svt srcType:$Rn)))*/]>,
|
|
Sched<[WriteFCopy]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{30-23} = 0b00111100;
|
|
let Inst{21} = 1;
|
|
let Inst{20-19} = rmode;
|
|
let Inst{18-16} = opcode;
|
|
let Inst{15-10} = 0b000000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseUnscaledConversionToHigh<bits<2> rmode, bits<3> opcode,
|
|
RegisterClass srcType, RegisterOperand dstType, string asm>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn), asm, "\t$Rd[1], $Rn", "", []>,
|
|
Sched<[WriteFCopy]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{30-23} = 0b00111101;
|
|
let Inst{21} = 1;
|
|
let Inst{20-19} = rmode;
|
|
let Inst{18-16} = opcode;
|
|
let Inst{15-10} = 0b000000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseUnscaledConversionFromHigh<bits<2> rmode, bits<3> opcode,
|
|
RegisterOperand srcType, RegisterClass dstType, string asm>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn), asm, "\t$Rd, $Rn[1]", "", []>,
|
|
Sched<[WriteFCopy]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{30-23} = 0b00111101;
|
|
let Inst{21} = 1;
|
|
let Inst{20-19} = rmode;
|
|
let Inst{18-16} = opcode;
|
|
let Inst{15-10} = 0b000000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
|
|
|
|
multiclass UnscaledConversion<string asm> {
|
|
def WSr : BaseUnscaledConversion<0b00, 0b111, GPR32, FPR32, asm> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
let Inst{22} = 0; // 32-bit FPR flag
|
|
}
|
|
|
|
def XDr : BaseUnscaledConversion<0b00, 0b111, GPR64, FPR64, asm> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
let Inst{22} = 1; // 64-bit FPR flag
|
|
}
|
|
|
|
def SWr : BaseUnscaledConversion<0b00, 0b110, FPR32, GPR32, asm> {
|
|
let Inst{31} = 0; // 32-bit GPR flag
|
|
let Inst{22} = 0; // 32-bit FPR flag
|
|
}
|
|
|
|
def DXr : BaseUnscaledConversion<0b00, 0b110, FPR64, GPR64, asm> {
|
|
let Inst{31} = 1; // 64-bit GPR flag
|
|
let Inst{22} = 1; // 64-bit FPR flag
|
|
}
|
|
|
|
def XDHighr : BaseUnscaledConversionToHigh<0b01, 0b111, GPR64, V128,
|
|
asm#".d"> {
|
|
let Inst{31} = 1;
|
|
let Inst{22} = 0;
|
|
}
|
|
|
|
def DXHighr : BaseUnscaledConversionFromHigh<0b01, 0b110, V128, GPR64,
|
|
asm#".d"> {
|
|
let Inst{31} = 1;
|
|
let Inst{22} = 0;
|
|
}
|
|
|
|
def : InstAlias<asm#"$Vd.d[1], $Rn",
|
|
(!cast<Instruction>(NAME#XDHighr) V128:$Vd, GPR64:$Rn), 0>;
|
|
def : InstAlias<asm#"$Rd, $Vn.d[1]",
|
|
(!cast<Instruction>(NAME#DXHighr) GPR64:$Rd, V128:$Vn), 0>;
|
|
}
|
|
|
|
//---
|
|
// Floating point conversion
|
|
//---
|
|
|
|
class BaseFPConversion<bits<2> type, bits<2> opcode, RegisterClass dstType,
|
|
RegisterClass srcType, string asm, list<dag> pattern>
|
|
: I<(outs dstType:$Rd), (ins srcType:$Rn), asm, "\t$Rd, $Rn", "", pattern>,
|
|
Sched<[WriteFCvt]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-24} = 0b00011110;
|
|
let Inst{23-22} = type;
|
|
let Inst{21-17} = 0b10001;
|
|
let Inst{16-15} = opcode;
|
|
let Inst{14-10} = 0b10000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass FPConversion<string asm> {
|
|
// Double-precision to Half-precision
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
def HDr : BaseFPConversion<0b01, 0b11, FPR16, FPR64, asm, []>;
|
|
|
|
// Double-precision to Single-precision
|
|
def SDr : BaseFPConversion<0b01, 0b00, FPR32, FPR64, asm,
|
|
[(set FPR32:$Rd, (fround FPR64:$Rn))]>;
|
|
|
|
// Half-precision to Double-precision
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
def DHr : BaseFPConversion<0b11, 0b01, FPR64, FPR16, asm, []>;
|
|
|
|
// Half-precision to Single-precision
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
def SHr : BaseFPConversion<0b11, 0b00, FPR32, FPR16, asm, []>;
|
|
|
|
// Single-precision to Double-precision
|
|
def DSr : BaseFPConversion<0b00, 0b01, FPR64, FPR32, asm,
|
|
[(set FPR64:$Rd, (fextend FPR32:$Rn))]>;
|
|
|
|
// Single-precision to Half-precision
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
def HSr : BaseFPConversion<0b00, 0b11, FPR16, FPR32, asm, []>;
|
|
}
|
|
|
|
//---
|
|
// Single operand floating point data processing
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSingleOperandFPData<bits<4> opcode, RegisterClass regtype,
|
|
ValueType vt, string asm, SDPatternOperator node>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn), asm, "\t$Rd, $Rn", "",
|
|
[(set (vt regtype:$Rd), (node (vt regtype:$Rn)))]>,
|
|
Sched<[WriteF]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-23} = 0b000111100;
|
|
let Inst{21-19} = 0b100;
|
|
let Inst{18-15} = opcode;
|
|
let Inst{14-10} = 0b10000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SingleOperandFPData<bits<4> opcode, string asm,
|
|
SDPatternOperator node = null_frag> {
|
|
def Sr : BaseSingleOperandFPData<opcode, FPR32, f32, asm, node> {
|
|
let Inst{22} = 0; // 32-bit size flag
|
|
}
|
|
|
|
def Dr : BaseSingleOperandFPData<opcode, FPR64, f64, asm, node> {
|
|
let Inst{22} = 1; // 64-bit size flag
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Two operand floating point data processing
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseTwoOperandFPData<bits<4> opcode, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm),
|
|
asm, "\t$Rd, $Rn, $Rm", "", pat>,
|
|
Sched<[WriteF]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31-23} = 0b000111100;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass TwoOperandFPData<bits<4> opcode, string asm,
|
|
SDPatternOperator node = null_frag> {
|
|
def Srr : BaseTwoOperandFPData<opcode, FPR32, asm,
|
|
[(set (f32 FPR32:$Rd),
|
|
(node (f32 FPR32:$Rn), (f32 FPR32:$Rm)))]> {
|
|
let Inst{22} = 0; // 32-bit size flag
|
|
}
|
|
|
|
def Drr : BaseTwoOperandFPData<opcode, FPR64, asm,
|
|
[(set (f64 FPR64:$Rd),
|
|
(node (f64 FPR64:$Rn), (f64 FPR64:$Rm)))]> {
|
|
let Inst{22} = 1; // 64-bit size flag
|
|
}
|
|
}
|
|
|
|
multiclass TwoOperandFPDataNeg<bits<4> opcode, string asm, SDNode node> {
|
|
def Srr : BaseTwoOperandFPData<opcode, FPR32, asm,
|
|
[(set FPR32:$Rd, (fneg (node FPR32:$Rn, (f32 FPR32:$Rm))))]> {
|
|
let Inst{22} = 0; // 32-bit size flag
|
|
}
|
|
|
|
def Drr : BaseTwoOperandFPData<opcode, FPR64, asm,
|
|
[(set FPR64:$Rd, (fneg (node FPR64:$Rn, (f64 FPR64:$Rm))))]> {
|
|
let Inst{22} = 1; // 64-bit size flag
|
|
}
|
|
}
|
|
|
|
|
|
//---
|
|
// Three operand floating point data processing
|
|
//---
|
|
|
|
class BaseThreeOperandFPData<bit isNegated, bit isSub,
|
|
RegisterClass regtype, string asm, list<dag> pat>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm, regtype: $Ra),
|
|
asm, "\t$Rd, $Rn, $Rm, $Ra", "", pat>,
|
|
Sched<[WriteFMul]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<5> Ra;
|
|
let Inst{31-23} = 0b000111110;
|
|
let Inst{21} = isNegated;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15} = isSub;
|
|
let Inst{14-10} = Ra;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass ThreeOperandFPData<bit isNegated, bit isSub,string asm,
|
|
SDPatternOperator node> {
|
|
def Srrr : BaseThreeOperandFPData<isNegated, isSub, FPR32, asm,
|
|
[(set FPR32:$Rd,
|
|
(node (f32 FPR32:$Rn), (f32 FPR32:$Rm), (f32 FPR32:$Ra)))]> {
|
|
let Inst{22} = 0; // 32-bit size flag
|
|
}
|
|
|
|
def Drrr : BaseThreeOperandFPData<isNegated, isSub, FPR64, asm,
|
|
[(set FPR64:$Rd,
|
|
(node (f64 FPR64:$Rn), (f64 FPR64:$Rm), (f64 FPR64:$Ra)))]> {
|
|
let Inst{22} = 1; // 64-bit size flag
|
|
}
|
|
}
|
|
|
|
//---
|
|
// Floating point data comparisons
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseOneOperandFPComparison<bit signalAllNans,
|
|
RegisterClass regtype, string asm,
|
|
list<dag> pat>
|
|
: I<(outs), (ins regtype:$Rn), asm, "\t$Rn, #0.0", "", pat>,
|
|
Sched<[WriteFCmp]> {
|
|
bits<5> Rn;
|
|
let Inst{31-23} = 0b000111100;
|
|
let Inst{21} = 1;
|
|
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{15-10} = 0b001000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4} = signalAllNans;
|
|
let Inst{3-0} = 0b1000;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseTwoOperandFPComparison<bit signalAllNans, RegisterClass regtype,
|
|
string asm, list<dag> pat>
|
|
: I<(outs), (ins regtype:$Rn, regtype:$Rm), asm, "\t$Rn, $Rm", "", pat>,
|
|
Sched<[WriteFCmp]> {
|
|
bits<5> Rm;
|
|
bits<5> Rn;
|
|
let Inst{31-23} = 0b000111100;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-10} = 0b001000;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4} = signalAllNans;
|
|
let Inst{3-0} = 0b0000;
|
|
}
|
|
|
|
multiclass FPComparison<bit signalAllNans, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
let Defs = [CPSR] in {
|
|
def Srr : BaseTwoOperandFPComparison<signalAllNans, FPR32, asm,
|
|
[(OpNode FPR32:$Rn, (f32 FPR32:$Rm)), (implicit CPSR)]> {
|
|
let Inst{22} = 0;
|
|
}
|
|
|
|
def Sri : BaseOneOperandFPComparison<signalAllNans, FPR32, asm,
|
|
[(OpNode (f32 FPR32:$Rn), fpimm0), (implicit CPSR)]> {
|
|
let Inst{22} = 0;
|
|
}
|
|
|
|
def Drr : BaseTwoOperandFPComparison<signalAllNans, FPR64, asm,
|
|
[(OpNode FPR64:$Rn, (f64 FPR64:$Rm)), (implicit CPSR)]> {
|
|
let Inst{22} = 1;
|
|
}
|
|
|
|
def Dri : BaseOneOperandFPComparison<signalAllNans, FPR64, asm,
|
|
[(OpNode (f64 FPR64:$Rn), fpimm0), (implicit CPSR)]> {
|
|
let Inst{22} = 1;
|
|
}
|
|
} // Defs = [CPSR]
|
|
}
|
|
|
|
//---
|
|
// Floating point conditional comparisons
|
|
//---
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseFPCondComparison<bit signalAllNans,
|
|
RegisterClass regtype, string asm>
|
|
: I<(outs), (ins regtype:$Rn, regtype:$Rm, imm0_15:$nzcv, ccode:$cond),
|
|
asm, "\t$Rn, $Rm, $nzcv, $cond", "", []>,
|
|
Sched<[WriteFCmp]> {
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<4> nzcv;
|
|
bits<4> cond;
|
|
|
|
let Inst{31-23} = 0b000111100;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = cond;
|
|
let Inst{11-10} = 0b01;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4} = signalAllNans;
|
|
let Inst{3-0} = nzcv;
|
|
}
|
|
|
|
multiclass FPCondComparison<bit signalAllNans, string asm> {
|
|
let Defs = [CPSR], Uses = [CPSR] in {
|
|
def Srr : BaseFPCondComparison<signalAllNans, FPR32, asm> {
|
|
let Inst{22} = 0;
|
|
}
|
|
|
|
def Drr : BaseFPCondComparison<signalAllNans, FPR64, asm> {
|
|
let Inst{22} = 1;
|
|
}
|
|
} // Defs = [CPSR], Uses = [CPSR]
|
|
}
|
|
|
|
//---
|
|
// Floating point conditional select
|
|
//---
|
|
|
|
class BaseFPCondSelect<RegisterClass regtype, ValueType vt, string asm>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm, ccode:$cond),
|
|
asm, "\t$Rd, $Rn, $Rm, $cond", "",
|
|
[(set regtype:$Rd,
|
|
(ARM64csel (vt regtype:$Rn), regtype:$Rm,
|
|
(i32 imm:$cond), CPSR))]>,
|
|
Sched<[WriteF]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<4> cond;
|
|
|
|
let Inst{31-23} = 0b000111100;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = cond;
|
|
let Inst{11-10} = 0b11;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass FPCondSelect<string asm> {
|
|
let Uses = [CPSR] in {
|
|
def Srrr : BaseFPCondSelect<FPR32, f32, asm> {
|
|
let Inst{22} = 0;
|
|
}
|
|
|
|
def Drrr : BaseFPCondSelect<FPR64, f64, asm> {
|
|
let Inst{22} = 1;
|
|
}
|
|
} // Uses = [CPSR]
|
|
}
|
|
|
|
//---
|
|
// Floating move immediate
|
|
//---
|
|
|
|
class BaseFPMoveImmediate<RegisterClass regtype, Operand fpimmtype, string asm>
|
|
: I<(outs regtype:$Rd), (ins fpimmtype:$imm), asm, "\t$Rd, $imm", "",
|
|
[(set regtype:$Rd, fpimmtype:$imm)]>,
|
|
Sched<[WriteFImm]> {
|
|
bits<5> Rd;
|
|
bits<8> imm;
|
|
let Inst{31-23} = 0b000111100;
|
|
let Inst{21} = 1;
|
|
let Inst{20-13} = imm;
|
|
let Inst{12-5} = 0b10000000;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass FPMoveImmediate<string asm> {
|
|
def Si : BaseFPMoveImmediate<FPR32, fpimm32, asm> {
|
|
let Inst{22} = 0;
|
|
}
|
|
|
|
def Di : BaseFPMoveImmediate<FPR64, fpimm64, asm> {
|
|
let Inst{22} = 1;
|
|
}
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD
|
|
//----------------------------------------------------------------------------
|
|
|
|
def VectorIndexBOperand : AsmOperandClass { let Name = "VectorIndexB"; }
|
|
def VectorIndexHOperand : AsmOperandClass { let Name = "VectorIndexH"; }
|
|
def VectorIndexSOperand : AsmOperandClass { let Name = "VectorIndexS"; }
|
|
def VectorIndexDOperand : AsmOperandClass { let Name = "VectorIndexD"; }
|
|
def VectorIndexB : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 16;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndexBOperand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i64imm);
|
|
}
|
|
def VectorIndexH : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 8;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndexHOperand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i64imm);
|
|
}
|
|
def VectorIndexS : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 4;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndexSOperand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i64imm);
|
|
}
|
|
def VectorIndexD : Operand<i64>, ImmLeaf<i64, [{
|
|
return ((uint64_t)Imm) < 2;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndexDOperand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i64imm);
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD three register vector instructions
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDThreeSameVector<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand regtype, string asm, string kind,
|
|
list<dag> pattern>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm), asm,
|
|
"{\t$Rd" # kind # ", $Rn" # kind # ", $Rm" # kind #
|
|
"|" # kind # "\t$Rd, $Rn, $Rm|}", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-11} = opcode;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDThreeSameVectorTied<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand regtype, string asm, string kind,
|
|
list<dag> pattern>
|
|
: I<(outs regtype:$dst), (ins regtype:$Rd, regtype:$Rn, regtype:$Rm), asm,
|
|
"{\t$Rd" # kind # ", $Rn" # kind # ", $Rm" # kind #
|
|
"|" # kind # "\t$Rd, $Rn, $Rm}", "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-11} = opcode;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
// All operand sizes distinguished in the encoding.
|
|
multiclass SIMDThreeSameVector<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDThreeSameVector<0, U, 0b00, opc, V64,
|
|
asm, ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i8 V64:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8 : BaseSIMDThreeSameVector<1, U, 0b00, opc, V128,
|
|
asm, ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode (v16i8 V128:$Rn), (v16i8 V128:$Rm)))]>;
|
|
def v4i16 : BaseSIMDThreeSameVector<0, U, 0b01, opc, V64,
|
|
asm, ".4h",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i16 V64:$Rn), (v4i16 V64:$Rm)))]>;
|
|
def v8i16 : BaseSIMDThreeSameVector<1, U, 0b01, opc, V128,
|
|
asm, ".8h",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn), (v8i16 V128:$Rm)))]>;
|
|
def v2i32 : BaseSIMDThreeSameVector<0, U, 0b10, opc, V64,
|
|
asm, ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i32 V64:$Rn), (v2i32 V64:$Rm)))]>;
|
|
def v4i32 : BaseSIMDThreeSameVector<1, U, 0b10, opc, V128,
|
|
asm, ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn), (v4i32 V128:$Rm)))]>;
|
|
def v2i64 : BaseSIMDThreeSameVector<1, U, 0b11, opc, V128,
|
|
asm, ".2d",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i64 V128:$Rn), (v2i64 V128:$Rm)))]>;
|
|
}
|
|
|
|
// As above, but D sized elements unsupported.
|
|
multiclass SIMDThreeSameVectorBHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDThreeSameVector<0, U, 0b00, opc, V64,
|
|
asm, ".8b",
|
|
[(set V64:$Rd, (v8i8 (OpNode (v8i8 V64:$Rn), (v8i8 V64:$Rm))))]>;
|
|
def v16i8 : BaseSIMDThreeSameVector<1, U, 0b00, opc, V128,
|
|
asm, ".16b",
|
|
[(set V128:$Rd, (v16i8 (OpNode (v16i8 V128:$Rn), (v16i8 V128:$Rm))))]>;
|
|
def v4i16 : BaseSIMDThreeSameVector<0, U, 0b01, opc, V64,
|
|
asm, ".4h",
|
|
[(set V64:$Rd, (v4i16 (OpNode (v4i16 V64:$Rn), (v4i16 V64:$Rm))))]>;
|
|
def v8i16 : BaseSIMDThreeSameVector<1, U, 0b01, opc, V128,
|
|
asm, ".8h",
|
|
[(set V128:$Rd, (v8i16 (OpNode (v8i16 V128:$Rn), (v8i16 V128:$Rm))))]>;
|
|
def v2i32 : BaseSIMDThreeSameVector<0, U, 0b10, opc, V64,
|
|
asm, ".2s",
|
|
[(set V64:$Rd, (v2i32 (OpNode (v2i32 V64:$Rn), (v2i32 V64:$Rm))))]>;
|
|
def v4i32 : BaseSIMDThreeSameVector<1, U, 0b10, opc, V128,
|
|
asm, ".4s",
|
|
[(set V128:$Rd, (v4i32 (OpNode (v4i32 V128:$Rn), (v4i32 V128:$Rm))))]>;
|
|
}
|
|
|
|
multiclass SIMDThreeSameVectorBHSTied<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDThreeSameVectorTied<0, U, 0b00, opc, V64,
|
|
asm, ".8b",
|
|
[(set (v8i8 V64:$dst),
|
|
(OpNode (v8i8 V64:$Rd), (v8i8 V64:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8 : BaseSIMDThreeSameVectorTied<1, U, 0b00, opc, V128,
|
|
asm, ".16b",
|
|
[(set (v16i8 V128:$dst),
|
|
(OpNode (v16i8 V128:$Rd), (v16i8 V128:$Rn), (v16i8 V128:$Rm)))]>;
|
|
def v4i16 : BaseSIMDThreeSameVectorTied<0, U, 0b01, opc, V64,
|
|
asm, ".4h",
|
|
[(set (v4i16 V64:$dst),
|
|
(OpNode (v4i16 V64:$Rd), (v4i16 V64:$Rn), (v4i16 V64:$Rm)))]>;
|
|
def v8i16 : BaseSIMDThreeSameVectorTied<1, U, 0b01, opc, V128,
|
|
asm, ".8h",
|
|
[(set (v8i16 V128:$dst),
|
|
(OpNode (v8i16 V128:$Rd), (v8i16 V128:$Rn), (v8i16 V128:$Rm)))]>;
|
|
def v2i32 : BaseSIMDThreeSameVectorTied<0, U, 0b10, opc, V64,
|
|
asm, ".2s",
|
|
[(set (v2i32 V64:$dst),
|
|
(OpNode (v2i32 V64:$Rd), (v2i32 V64:$Rn), (v2i32 V64:$Rm)))]>;
|
|
def v4i32 : BaseSIMDThreeSameVectorTied<1, U, 0b10, opc, V128,
|
|
asm, ".4s",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i32 V128:$Rn), (v4i32 V128:$Rm)))]>;
|
|
}
|
|
|
|
// As above, but only B sized elements supported.
|
|
multiclass SIMDThreeSameVectorB<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDThreeSameVector<0, U, 0b00, opc, V64,
|
|
asm, ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i8 V64:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8 : BaseSIMDThreeSameVector<1, U, 0b00, opc, V128,
|
|
asm, ".16b",
|
|
[(set (v16i8 V128:$Rd),
|
|
(OpNode (v16i8 V128:$Rn), (v16i8 V128:$Rm)))]>;
|
|
}
|
|
|
|
// As above, but only S and D sized floating point elements supported.
|
|
multiclass SIMDThreeSameVectorFP<bit U, bit S, bits<5> opc,
|
|
string asm, SDPatternOperator OpNode> {
|
|
def v2f32 : BaseSIMDThreeSameVector<0, U, {S,0}, opc, V64,
|
|
asm, ".2s",
|
|
[(set (v2f32 V64:$Rd), (OpNode (v2f32 V64:$Rn), (v2f32 V64:$Rm)))]>;
|
|
def v4f32 : BaseSIMDThreeSameVector<1, U, {S,0}, opc, V128,
|
|
asm, ".4s",
|
|
[(set (v4f32 V128:$Rd), (OpNode (v4f32 V128:$Rn), (v4f32 V128:$Rm)))]>;
|
|
def v2f64 : BaseSIMDThreeSameVector<1, U, {S,1}, opc, V128,
|
|
asm, ".2d",
|
|
[(set (v2f64 V128:$Rd), (OpNode (v2f64 V128:$Rn), (v2f64 V128:$Rm)))]>;
|
|
}
|
|
|
|
multiclass SIMDThreeSameVectorFPCmp<bit U, bit S, bits<5> opc,
|
|
string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v2f32 : BaseSIMDThreeSameVector<0, U, {S,0}, opc, V64,
|
|
asm, ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2f32 V64:$Rn), (v2f32 V64:$Rm)))]>;
|
|
def v4f32 : BaseSIMDThreeSameVector<1, U, {S,0}, opc, V128,
|
|
asm, ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4f32 V128:$Rn), (v4f32 V128:$Rm)))]>;
|
|
def v2f64 : BaseSIMDThreeSameVector<1, U, {S,1}, opc, V128,
|
|
asm, ".2d",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2f64 V128:$Rn), (v2f64 V128:$Rm)))]>;
|
|
}
|
|
|
|
multiclass SIMDThreeSameVectorFPTied<bit U, bit S, bits<5> opc,
|
|
string asm, SDPatternOperator OpNode> {
|
|
def v2f32 : BaseSIMDThreeSameVectorTied<0, U, {S,0}, opc, V64,
|
|
asm, ".2s",
|
|
[(set (v2f32 V64:$dst),
|
|
(OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn), (v2f32 V64:$Rm)))]>;
|
|
def v4f32 : BaseSIMDThreeSameVectorTied<1, U, {S,0}, opc, V128,
|
|
asm, ".4s",
|
|
[(set (v4f32 V128:$dst),
|
|
(OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn), (v4f32 V128:$Rm)))]>;
|
|
def v2f64 : BaseSIMDThreeSameVectorTied<1, U, {S,1}, opc, V128,
|
|
asm, ".2d",
|
|
[(set (v2f64 V128:$dst),
|
|
(OpNode (v2f64 V128:$Rd), (v2f64 V128:$Rn), (v2f64 V128:$Rm)))]>;
|
|
}
|
|
|
|
// As above, but D and B sized elements unsupported.
|
|
multiclass SIMDThreeSameVectorHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v4i16 : BaseSIMDThreeSameVector<0, U, 0b01, opc, V64,
|
|
asm, ".4h",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i16 V64:$Rn), (v4i16 V64:$Rm)))]>;
|
|
def v8i16 : BaseSIMDThreeSameVector<1, U, 0b01, opc, V128,
|
|
asm, ".8h",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn), (v8i16 V128:$Rm)))]>;
|
|
def v2i32 : BaseSIMDThreeSameVector<0, U, 0b10, opc, V64,
|
|
asm, ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i32 V64:$Rn), (v2i32 V64:$Rm)))]>;
|
|
def v4i32 : BaseSIMDThreeSameVector<1, U, 0b10, opc, V128,
|
|
asm, ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn), (v4i32 V128:$Rm)))]>;
|
|
}
|
|
|
|
// Logical three vector ops share opcode bits, and only use B sized elements.
|
|
multiclass SIMDLogicalThreeVector<bit U, bits<2> size, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v8i8 : BaseSIMDThreeSameVector<0, U, size, 0b00011, V64,
|
|
asm, ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode V64:$Rn, V64:$Rm))]>;
|
|
def v16i8 : BaseSIMDThreeSameVector<1, U, size, 0b00011, V128,
|
|
asm, ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode V128:$Rn, V128:$Rm))]>;
|
|
|
|
def : Pat<(v4i16 (OpNode V64:$LHS, V64:$RHS)),
|
|
(!cast<Instruction>(NAME#"v8i8") V64:$LHS, V64:$RHS)>;
|
|
def : Pat<(v2i32 (OpNode V64:$LHS, V64:$RHS)),
|
|
(!cast<Instruction>(NAME#"v8i8") V64:$LHS, V64:$RHS)>;
|
|
def : Pat<(v1i64 (OpNode V64:$LHS, V64:$RHS)),
|
|
(!cast<Instruction>(NAME#"v8i8") V64:$LHS, V64:$RHS)>;
|
|
|
|
def : Pat<(v8i16 (OpNode V128:$LHS, V128:$RHS)),
|
|
(!cast<Instruction>(NAME#"v16i8") V128:$LHS, V128:$RHS)>;
|
|
def : Pat<(v4i32 (OpNode V128:$LHS, V128:$RHS)),
|
|
(!cast<Instruction>(NAME#"v16i8") V128:$LHS, V128:$RHS)>;
|
|
def : Pat<(v2i64 (OpNode V128:$LHS, V128:$RHS)),
|
|
(!cast<Instruction>(NAME#"v16i8") V128:$LHS, V128:$RHS)>;
|
|
}
|
|
|
|
multiclass SIMDLogicalThreeVectorTied<bit U, bits<2> size,
|
|
string asm, SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDThreeSameVectorTied<0, U, size, 0b00011, V64,
|
|
asm, ".8b",
|
|
[(set (v8i8 V64:$dst),
|
|
(OpNode (v8i8 V64:$Rd), (v8i8 V64:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8 : BaseSIMDThreeSameVectorTied<1, U, size, 0b00011, V128,
|
|
asm, ".16b",
|
|
[(set (v16i8 V128:$dst),
|
|
(OpNode (v16i8 V128:$Rd), (v16i8 V128:$Rn),
|
|
(v16i8 V128:$Rm)))]>;
|
|
|
|
def : Pat<(v4i16 (OpNode (v4i16 V64:$LHS), (v4i16 V64:$MHS),
|
|
(v4i16 V64:$RHS))),
|
|
(!cast<Instruction>(NAME#"v8i8")
|
|
V64:$LHS, V64:$MHS, V64:$RHS)>;
|
|
def : Pat<(v2i32 (OpNode (v2i32 V64:$LHS), (v2i32 V64:$MHS),
|
|
(v2i32 V64:$RHS))),
|
|
(!cast<Instruction>(NAME#"v8i8")
|
|
V64:$LHS, V64:$MHS, V64:$RHS)>;
|
|
def : Pat<(v1i64 (OpNode (v1i64 V64:$LHS), (v1i64 V64:$MHS),
|
|
(v1i64 V64:$RHS))),
|
|
(!cast<Instruction>(NAME#"v8i8")
|
|
V64:$LHS, V64:$MHS, V64:$RHS)>;
|
|
|
|
def : Pat<(v8i16 (OpNode (v8i16 V128:$LHS), (v8i16 V128:$MHS),
|
|
(v8i16 V128:$RHS))),
|
|
(!cast<Instruction>(NAME#"v16i8")
|
|
V128:$LHS, V128:$MHS, V128:$RHS)>;
|
|
def : Pat<(v4i32 (OpNode (v4i32 V128:$LHS), (v4i32 V128:$MHS),
|
|
(v4i32 V128:$RHS))),
|
|
(!cast<Instruction>(NAME#"v16i8")
|
|
V128:$LHS, V128:$MHS, V128:$RHS)>;
|
|
def : Pat<(v2i64 (OpNode (v2i64 V128:$LHS), (v2i64 V128:$MHS),
|
|
(v2i64 V128:$RHS))),
|
|
(!cast<Instruction>(NAME#"v16i8")
|
|
V128:$LHS, V128:$MHS, V128:$RHS)>;
|
|
}
|
|
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD two register vector instructions.
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDTwoSameVector<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand regtype, string asm, string dstkind,
|
|
string srckind, list<dag> pattern>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn), asm,
|
|
"{\t$Rd" # dstkind # ", $Rn" # srckind #
|
|
"|" # dstkind # "\t$Rd, $Rn}", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDTwoSameVectorTied<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand regtype, string asm, string dstkind,
|
|
string srckind, list<dag> pattern>
|
|
: I<(outs regtype:$dst), (ins regtype:$Rd, regtype:$Rn), asm,
|
|
"{\t$Rd" # dstkind # ", $Rn" # srckind #
|
|
"|" # dstkind # "\t$Rd, $Rn}", "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
// Supports B, H, and S element sizes.
|
|
multiclass SIMDTwoVectorBHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDTwoSameVector<0, U, 0b00, opc, V64,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i8 V64:$Rn)))]>;
|
|
def v16i8 : BaseSIMDTwoSameVector<1, U, 0b00, opc, V128,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode (v16i8 V128:$Rn)))]>;
|
|
def v4i16 : BaseSIMDTwoSameVector<0, U, 0b01, opc, V64,
|
|
asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i16 V64:$Rn)))]>;
|
|
def v8i16 : BaseSIMDTwoSameVector<1, U, 0b01, opc, V128,
|
|
asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn)))]>;
|
|
def v2i32 : BaseSIMDTwoSameVector<0, U, 0b10, opc, V64,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i32 V64:$Rn)))]>;
|
|
def v4i32 : BaseSIMDTwoSameVector<1, U, 0b10, opc, V128,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn)))]>;
|
|
}
|
|
|
|
class BaseSIMDVectorLShiftLongBySize<bit Q, bits<2> size,
|
|
RegisterOperand regtype, string asm, string dstkind,
|
|
string srckind, string amount>
|
|
: I<(outs V128:$Rd), (ins regtype:$Rn), asm,
|
|
"{\t$Rd" # dstkind # ", $Rn" # srckind # ", #" # amount #
|
|
"|" # dstkind # "\t$Rd, $Rn, #" # amount # "}", "", []>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29-24} = 0b101110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-10} = 0b100001001110;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDVectorLShiftLongBySizeBHS {
|
|
let neverHasSideEffects = 1 in {
|
|
def v8i8 : BaseSIMDVectorLShiftLongBySize<0, 0b00, V64,
|
|
"shll", ".8h", ".8b", "8">;
|
|
def v16i8 : BaseSIMDVectorLShiftLongBySize<1, 0b00, V128,
|
|
"shll2", ".8h", ".16b", "8">;
|
|
def v4i16 : BaseSIMDVectorLShiftLongBySize<0, 0b01, V64,
|
|
"shll", ".4s", ".4h", "16">;
|
|
def v8i16 : BaseSIMDVectorLShiftLongBySize<1, 0b01, V128,
|
|
"shll2", ".4s", ".8h", "16">;
|
|
def v2i32 : BaseSIMDVectorLShiftLongBySize<0, 0b10, V64,
|
|
"shll", ".2d", ".2s", "32">;
|
|
def v4i32 : BaseSIMDVectorLShiftLongBySize<1, 0b10, V128,
|
|
"shll2", ".2d", ".4s", "32">;
|
|
}
|
|
}
|
|
|
|
// Supports all element sizes.
|
|
multiclass SIMDLongTwoVector<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_v4i16 : BaseSIMDTwoSameVector<0, U, 0b00, opc, V64,
|
|
asm, ".4h", ".8b",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v8i8 V64:$Rn)))]>;
|
|
def v16i8_v8i16 : BaseSIMDTwoSameVector<1, U, 0b00, opc, V128,
|
|
asm, ".8h", ".16b",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v16i8 V128:$Rn)))]>;
|
|
def v4i16_v2i32 : BaseSIMDTwoSameVector<0, U, 0b01, opc, V64,
|
|
asm, ".2s", ".4h",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v4i16 V64:$Rn)))]>;
|
|
def v8i16_v4i32 : BaseSIMDTwoSameVector<1, U, 0b01, opc, V128,
|
|
asm, ".4s", ".8h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v8i16 V128:$Rn)))]>;
|
|
def v2i32_v1i64 : BaseSIMDTwoSameVector<0, U, 0b10, opc, V64,
|
|
asm, ".1d", ".2s",
|
|
[(set (v1i64 V64:$Rd), (OpNode (v2i32 V64:$Rn)))]>;
|
|
def v4i32_v2i64 : BaseSIMDTwoSameVector<1, U, 0b10, opc, V128,
|
|
asm, ".2d", ".4s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v4i32 V128:$Rn)))]>;
|
|
}
|
|
|
|
multiclass SIMDLongTwoVectorTied<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_v4i16 : BaseSIMDTwoSameVectorTied<0, U, 0b00, opc, V64,
|
|
asm, ".4h", ".8b",
|
|
[(set (v4i16 V64:$dst), (OpNode (v4i16 V64:$Rd),
|
|
(v8i8 V64:$Rn)))]>;
|
|
def v16i8_v8i16 : BaseSIMDTwoSameVectorTied<1, U, 0b00, opc, V128,
|
|
asm, ".8h", ".16b",
|
|
[(set (v8i16 V128:$dst), (OpNode (v8i16 V128:$Rd),
|
|
(v16i8 V128:$Rn)))]>;
|
|
def v4i16_v2i32 : BaseSIMDTwoSameVectorTied<0, U, 0b01, opc, V64,
|
|
asm, ".2s", ".4h",
|
|
[(set (v2i32 V64:$dst), (OpNode (v2i32 V64:$Rd),
|
|
(v4i16 V64:$Rn)))]>;
|
|
def v8i16_v4i32 : BaseSIMDTwoSameVectorTied<1, U, 0b01, opc, V128,
|
|
asm, ".4s", ".8h",
|
|
[(set (v4i32 V128:$dst), (OpNode (v4i32 V128:$Rd),
|
|
(v8i16 V128:$Rn)))]>;
|
|
def v2i32_v1i64 : BaseSIMDTwoSameVectorTied<0, U, 0b10, opc, V64,
|
|
asm, ".1d", ".2s",
|
|
[(set (v1i64 V64:$dst), (OpNode (v1i64 V64:$Rd),
|
|
(v2i32 V64:$Rn)))]>;
|
|
def v4i32_v2i64 : BaseSIMDTwoSameVectorTied<1, U, 0b10, opc, V128,
|
|
asm, ".2d", ".4s",
|
|
[(set (v2i64 V128:$dst), (OpNode (v2i64 V128:$Rd),
|
|
(v4i32 V128:$Rn)))]>;
|
|
}
|
|
|
|
// Supports all element sizes, except 1xD.
|
|
multiclass SIMDTwoVectorBHSDTied<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDTwoSameVectorTied<0, U, 0b00, opc, V64,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$dst), (OpNode (v8i8 V64:$Rd), (v8i8 V64:$Rn)))]>;
|
|
def v16i8 : BaseSIMDTwoSameVectorTied<1, U, 0b00, opc, V128,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$dst), (OpNode (v16i8 V128:$Rd), (v16i8 V128:$Rn)))]>;
|
|
def v4i16 : BaseSIMDTwoSameVectorTied<0, U, 0b01, opc, V64,
|
|
asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$dst), (OpNode (v4i16 V64:$Rd), (v4i16 V64:$Rn)))]>;
|
|
def v8i16 : BaseSIMDTwoSameVectorTied<1, U, 0b01, opc, V128,
|
|
asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$dst), (OpNode (v8i16 V128:$Rd), (v8i16 V128:$Rn)))]>;
|
|
def v2i32 : BaseSIMDTwoSameVectorTied<0, U, 0b10, opc, V64,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$dst), (OpNode (v2i32 V64:$Rd), (v2i32 V64:$Rn)))]>;
|
|
def v4i32 : BaseSIMDTwoSameVectorTied<1, U, 0b10, opc, V128,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$dst), (OpNode (v4i32 V128:$Rd), (v4i32 V128:$Rn)))]>;
|
|
def v2i64 : BaseSIMDTwoSameVectorTied<1, U, 0b11, opc, V128,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2i64 V128:$dst), (OpNode (v2i64 V128:$Rd), (v2i64 V128:$Rn)))]>;
|
|
}
|
|
|
|
multiclass SIMDTwoVectorBHSD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v8i8 : BaseSIMDTwoSameVector<0, U, 0b00, opc, V64,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i8 V64:$Rn)))]>;
|
|
def v16i8 : BaseSIMDTwoSameVector<1, U, 0b00, opc, V128,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode (v16i8 V128:$Rn)))]>;
|
|
def v4i16 : BaseSIMDTwoSameVector<0, U, 0b01, opc, V64,
|
|
asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i16 V64:$Rn)))]>;
|
|
def v8i16 : BaseSIMDTwoSameVector<1, U, 0b01, opc, V128,
|
|
asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn)))]>;
|
|
def v2i32 : BaseSIMDTwoSameVector<0, U, 0b10, opc, V64,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i32 V64:$Rn)))]>;
|
|
def v4i32 : BaseSIMDTwoSameVector<1, U, 0b10, opc, V128,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn)))]>;
|
|
def v2i64 : BaseSIMDTwoSameVector<1, U, 0b11, opc, V128,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i64 V128:$Rn)))]>;
|
|
}
|
|
|
|
|
|
// Supports only B element sizes.
|
|
multiclass SIMDTwoVectorB<bit U, bits<2> size, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDTwoSameVector<0, U, size, opc, V64,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i8 V64:$Rn)))]>;
|
|
def v16i8 : BaseSIMDTwoSameVector<1, U, size, opc, V128,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode (v16i8 V128:$Rn)))]>;
|
|
|
|
}
|
|
|
|
// Supports only B and H element sizes.
|
|
multiclass SIMDTwoVectorBH<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDTwoSameVector<0, U, 0b00, opc, V64,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode V64:$Rn))]>;
|
|
def v16i8 : BaseSIMDTwoSameVector<1, U, 0b00, opc, V128,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode V128:$Rn))]>;
|
|
def v4i16 : BaseSIMDTwoSameVector<0, U, 0b01, opc, V64,
|
|
asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$Rd), (OpNode V64:$Rn))]>;
|
|
def v8i16 : BaseSIMDTwoSameVector<1, U, 0b01, opc, V128,
|
|
asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$Rd), (OpNode V128:$Rn))]>;
|
|
}
|
|
|
|
// Supports only S and D element sizes, uses high bit of the size field
|
|
// as an extra opcode bit.
|
|
multiclass SIMDTwoVectorFP<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v2f32 : BaseSIMDTwoSameVector<0, U, {S,0}, opc, V64,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2f32 V64:$Rd), (OpNode (v2f32 V64:$Rn)))]>;
|
|
def v4f32 : BaseSIMDTwoSameVector<1, U, {S,0}, opc, V128,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4f32 V128:$Rd), (OpNode (v4f32 V128:$Rn)))]>;
|
|
def v2f64 : BaseSIMDTwoSameVector<1, U, {S,1}, opc, V128,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2f64 V128:$Rd), (OpNode (v2f64 V128:$Rn)))]>;
|
|
}
|
|
|
|
// Supports only S element size.
|
|
multiclass SIMDTwoVectorS<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v2i32 : BaseSIMDTwoSameVector<0, U, {S,0}, opc, V64,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i32 V64:$Rn)))]>;
|
|
def v4i32 : BaseSIMDTwoSameVector<1, U, {S,0}, opc, V128,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn)))]>;
|
|
}
|
|
|
|
|
|
multiclass SIMDTwoVectorFPToInt<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v2f32 : BaseSIMDTwoSameVector<0, U, {S,0}, opc, V64,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2f32 V64:$Rn)))]>;
|
|
def v4f32 : BaseSIMDTwoSameVector<1, U, {S,0}, opc, V128,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4f32 V128:$Rn)))]>;
|
|
def v2f64 : BaseSIMDTwoSameVector<1, U, {S,1}, opc, V128,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2f64 V128:$Rn)))]>;
|
|
}
|
|
|
|
multiclass SIMDTwoVectorIntToFP<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v2f32 : BaseSIMDTwoSameVector<0, U, {S,0}, opc, V64,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2f32 V64:$Rd), (OpNode (v2i32 V64:$Rn)))]>;
|
|
def v4f32 : BaseSIMDTwoSameVector<1, U, {S,0}, opc, V128,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4f32 V128:$Rd), (OpNode (v4i32 V128:$Rn)))]>;
|
|
def v2f64 : BaseSIMDTwoSameVector<1, U, {S,1}, opc, V128,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2f64 V128:$Rd), (OpNode (v2i64 V128:$Rn)))]>;
|
|
}
|
|
|
|
|
|
class BaseSIMDMixedTwoVector<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand inreg, RegisterOperand outreg,
|
|
string asm, string outkind, string inkind,
|
|
list<dag> pattern>
|
|
: I<(outs outreg:$Rd), (ins inreg:$Rn), asm,
|
|
"{\t$Rd" # outkind # ", $Rn" # inkind #
|
|
"|" # outkind # "\t$Rd, $Rn}", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class BaseSIMDMixedTwoVectorTied<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand inreg, RegisterOperand outreg,
|
|
string asm, string outkind, string inkind,
|
|
list<dag> pattern>
|
|
: I<(outs outreg:$dst), (ins outreg:$Rd, inreg:$Rn), asm,
|
|
"{\t$Rd" # outkind # ", $Rn" # inkind #
|
|
"|" # outkind # "\t$Rd, $Rn}", "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDMixedTwoVector<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : BaseSIMDMixedTwoVector<0, U, 0b00, opc, V128, V64,
|
|
asm, ".8b", ".8h",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i16 V128:$Rn)))]>;
|
|
def v16i8 : BaseSIMDMixedTwoVectorTied<1, U, 0b00, opc, V128, V128,
|
|
asm#"2", ".16b", ".8h", []>;
|
|
def v4i16 : BaseSIMDMixedTwoVector<0, U, 0b01, opc, V128, V64,
|
|
asm, ".4h", ".4s",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i32 V128:$Rn)))]>;
|
|
def v8i16 : BaseSIMDMixedTwoVectorTied<1, U, 0b01, opc, V128, V128,
|
|
asm#"2", ".8h", ".4s", []>;
|
|
def v2i32 : BaseSIMDMixedTwoVector<0, U, 0b10, opc, V128, V64,
|
|
asm, ".2s", ".2d",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i64 V128:$Rn)))]>;
|
|
def v4i32 : BaseSIMDMixedTwoVectorTied<1, U, 0b10, opc, V128, V128,
|
|
asm#"2", ".4s", ".2d", []>;
|
|
|
|
def : Pat<(concat_vectors (v8i8 V64:$Rd), (OpNode (v8i16 V128:$Rn))),
|
|
(!cast<Instruction>(NAME # "v16i8")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
|
|
def : Pat<(concat_vectors (v4i16 V64:$Rd), (OpNode (v4i32 V128:$Rn))),
|
|
(!cast<Instruction>(NAME # "v8i16")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
|
|
def : Pat<(concat_vectors (v2i32 V64:$Rd), (OpNode (v2i64 V128:$Rn))),
|
|
(!cast<Instruction>(NAME # "v4i32")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
|
|
}
|
|
|
|
class BaseSIMDCmpTwoVector<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand regtype, string asm, string kind,
|
|
ValueType dty, ValueType sty, SDNode OpNode>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn), asm,
|
|
"{\t$Rd" # kind # ", $Rn" # kind # ", #0" #
|
|
"|" # kind # "\t$Rd, $Rn, #0}", "",
|
|
[(set (dty regtype:$Rd), (OpNode (sty regtype:$Rn)))]>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
// Comparisons support all element sizes, except 1xD.
|
|
multiclass SIMDCmpTwoVector<bit U, bits<5> opc, string asm,
|
|
SDNode OpNode> {
|
|
def v8i8rz : BaseSIMDCmpTwoVector<0, U, 0b00, opc, V64,
|
|
asm, ".8b",
|
|
v8i8, v8i8, OpNode>;
|
|
def v16i8rz : BaseSIMDCmpTwoVector<1, U, 0b00, opc, V128,
|
|
asm, ".16b",
|
|
v16i8, v16i8, OpNode>;
|
|
def v4i16rz : BaseSIMDCmpTwoVector<0, U, 0b01, opc, V64,
|
|
asm, ".4h",
|
|
v4i16, v4i16, OpNode>;
|
|
def v8i16rz : BaseSIMDCmpTwoVector<1, U, 0b01, opc, V128,
|
|
asm, ".8h",
|
|
v8i16, v8i16, OpNode>;
|
|
def v2i32rz : BaseSIMDCmpTwoVector<0, U, 0b10, opc, V64,
|
|
asm, ".2s",
|
|
v2i32, v2i32, OpNode>;
|
|
def v4i32rz : BaseSIMDCmpTwoVector<1, U, 0b10, opc, V128,
|
|
asm, ".4s",
|
|
v4i32, v4i32, OpNode>;
|
|
def v2i64rz : BaseSIMDCmpTwoVector<1, U, 0b11, opc, V128,
|
|
asm, ".2d",
|
|
v2i64, v2i64, OpNode>;
|
|
}
|
|
|
|
// FP Comparisons support only S and D element sizes.
|
|
multiclass SIMDFPCmpTwoVector<bit U, bit S, bits<5> opc,
|
|
string asm, SDNode OpNode> {
|
|
def v2i32rz : BaseSIMDCmpTwoVector<0, U, {S,0}, opc, V64,
|
|
asm, ".2s",
|
|
v2i32, v2f32, OpNode>;
|
|
def v4i32rz : BaseSIMDCmpTwoVector<1, U, {S,0}, opc, V128,
|
|
asm, ".4s",
|
|
v4i32, v4f32, OpNode>;
|
|
def v2i64rz : BaseSIMDCmpTwoVector<1, U, {S,1}, opc, V128,
|
|
asm, ".2d",
|
|
v2i64, v2f64, OpNode>;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDFPCvtTwoVector<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand outtype, RegisterOperand intype,
|
|
string asm, string VdTy, string VnTy,
|
|
list<dag> pattern>
|
|
: I<(outs outtype:$Rd), (ins intype:$Rn), asm,
|
|
!strconcat("\t$Rd", VdTy, ", $Rn", VnTy), "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class BaseSIMDFPCvtTwoVectorTied<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand outtype, RegisterOperand intype,
|
|
string asm, string VdTy, string VnTy,
|
|
list<dag> pattern>
|
|
: I<(outs outtype:$dst), (ins outtype:$Rd, intype:$Rn), asm,
|
|
!strconcat("\t$Rd", VdTy, ", $Rn", VnTy), "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDFPWidenTwoVector<bit U, bit S, bits<5> opc, string asm> {
|
|
def v4i16 : BaseSIMDFPCvtTwoVector<0, U, {S,0}, opc, V128, V64,
|
|
asm, ".4s", ".4h", []>;
|
|
def v8i16 : BaseSIMDFPCvtTwoVector<1, U, {S,0}, opc, V128, V128,
|
|
asm#"2", ".4s", ".8h", []>;
|
|
def v2i32 : BaseSIMDFPCvtTwoVector<0, U, {S,1}, opc, V128, V64,
|
|
asm, ".2d", ".2s", []>;
|
|
def v4i32 : BaseSIMDFPCvtTwoVector<1, U, {S,1}, opc, V128, V128,
|
|
asm#"2", ".2d", ".4s", []>;
|
|
}
|
|
|
|
multiclass SIMDFPNarrowTwoVector<bit U, bit S, bits<5> opc, string asm> {
|
|
def v4i16 : BaseSIMDFPCvtTwoVector<0, U, {S,0}, opc, V64, V128,
|
|
asm, ".4h", ".4s", []>;
|
|
def v8i16 : BaseSIMDFPCvtTwoVectorTied<1, U, {S,0}, opc, V128, V128,
|
|
asm#"2", ".8h", ".4s", []>;
|
|
def v2i32 : BaseSIMDFPCvtTwoVector<0, U, {S,1}, opc, V64, V128,
|
|
asm, ".2s", ".2d", []>;
|
|
def v4i32 : BaseSIMDFPCvtTwoVectorTied<1, U, {S,1}, opc, V128, V128,
|
|
asm#"2", ".4s", ".2d", []>;
|
|
}
|
|
|
|
multiclass SIMDFPInexactCvtTwoVector<bit U, bit S, bits<5> opc, string asm,
|
|
Intrinsic OpNode> {
|
|
def v2f32 : BaseSIMDFPCvtTwoVector<0, U, {S,1}, opc, V64, V128,
|
|
asm, ".2s", ".2d",
|
|
[(set (v2f32 V64:$Rd), (OpNode (v2f64 V128:$Rn)))]>;
|
|
def v4f32 : BaseSIMDFPCvtTwoVectorTied<1, U, {S,1}, opc, V128, V128,
|
|
asm#"2", ".4s", ".2d", []>;
|
|
|
|
def : Pat<(concat_vectors (v2f32 V64:$Rd), (OpNode (v2f64 V128:$Rn))),
|
|
(!cast<Instruction>(NAME # "v4f32")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD three register different-size vector instructions.
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDDifferentThreeVector<bit U, bits<3> size, bits<4> opcode,
|
|
RegisterOperand outtype, RegisterOperand intype1,
|
|
RegisterOperand intype2, string asm,
|
|
string outkind, string inkind1, string inkind2,
|
|
list<dag> pattern>
|
|
: I<(outs outtype:$Rd), (ins intype1:$Rn, intype2:$Rm), asm,
|
|
"{\t$Rd" # outkind # ", $Rn" # inkind1 # ", $Rm" # inkind2 #
|
|
"|" # outkind # "\t$Rd, $Rn, $Rm}", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = size{0};
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size{2-1};
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = opcode;
|
|
let Inst{11-10} = 0b00;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDDifferentThreeVectorTied<bit U, bits<3> size, bits<4> opcode,
|
|
RegisterOperand outtype, RegisterOperand intype1,
|
|
RegisterOperand intype2, string asm,
|
|
string outkind, string inkind1, string inkind2,
|
|
list<dag> pattern>
|
|
: I<(outs outtype:$dst), (ins outtype:$Rd, intype1:$Rn, intype2:$Rm), asm,
|
|
"{\t$Rd" # outkind # ", $Rn" # inkind1 # ", $Rm" # inkind2 #
|
|
"|" # outkind # "\t$Rd, $Rn, $Rm}", "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = size{0};
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size{2-1};
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = opcode;
|
|
let Inst{11-10} = 0b00;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
// FIXME: TableGen doesn't know how to deal with expanded types that also
|
|
// change the element count (in this case, placing the results in
|
|
// the high elements of the result register rather than the low
|
|
// elements). Until that's fixed, we can't code-gen those.
|
|
multiclass SIMDNarrowThreeVectorBHS<bit U, bits<4> opc, string asm,
|
|
Intrinsic IntOp> {
|
|
def v8i16_v8i8 : BaseSIMDDifferentThreeVector<U, 0b000, opc,
|
|
V64, V128, V128,
|
|
asm, ".8b", ".8h", ".8h",
|
|
[(set (v8i8 V64:$Rd), (IntOp (v8i16 V128:$Rn), (v8i16 V128:$Rm)))]>;
|
|
def v8i16_v16i8 : BaseSIMDDifferentThreeVectorTied<U, 0b001, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".16b", ".8h", ".8h",
|
|
[]>;
|
|
def v4i32_v4i16 : BaseSIMDDifferentThreeVector<U, 0b010, opc,
|
|
V64, V128, V128,
|
|
asm, ".4h", ".4s", ".4s",
|
|
[(set (v4i16 V64:$Rd), (IntOp (v4i32 V128:$Rn), (v4i32 V128:$Rm)))]>;
|
|
def v4i32_v8i16 : BaseSIMDDifferentThreeVectorTied<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".8h", ".4s", ".4s",
|
|
[]>;
|
|
def v2i64_v2i32 : BaseSIMDDifferentThreeVector<U, 0b100, opc,
|
|
V64, V128, V128,
|
|
asm, ".2s", ".2d", ".2d",
|
|
[(set (v2i32 V64:$Rd), (IntOp (v2i64 V128:$Rn), (v2i64 V128:$Rm)))]>;
|
|
def v2i64_v4i32 : BaseSIMDDifferentThreeVectorTied<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".2d", ".2d",
|
|
[]>;
|
|
|
|
|
|
// Patterns for the '2' variants involve INSERT_SUBREG, which you can't put in
|
|
// a version attached to an instruction.
|
|
def : Pat<(concat_vectors (v8i8 V64:$Rd), (IntOp (v8i16 V128:$Rn),
|
|
(v8i16 V128:$Rm))),
|
|
(!cast<Instruction>(NAME # "v8i16_v16i8")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
|
|
V128:$Rn, V128:$Rm)>;
|
|
def : Pat<(concat_vectors (v4i16 V64:$Rd), (IntOp (v4i32 V128:$Rn),
|
|
(v4i32 V128:$Rm))),
|
|
(!cast<Instruction>(NAME # "v4i32_v8i16")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
|
|
V128:$Rn, V128:$Rm)>;
|
|
def : Pat<(concat_vectors (v2i32 V64:$Rd), (IntOp (v2i64 V128:$Rn),
|
|
(v2i64 V128:$Rm))),
|
|
(!cast<Instruction>(NAME # "v2i64_v4i32")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
|
|
V128:$Rn, V128:$Rm)>;
|
|
}
|
|
|
|
multiclass SIMDDifferentThreeVectorBD<bit U, bits<4> opc, string asm,
|
|
Intrinsic IntOp> {
|
|
def v8i8 : BaseSIMDDifferentThreeVector<U, 0b000, opc,
|
|
V128, V64, V64,
|
|
asm, ".8h", ".8b", ".8b",
|
|
[(set (v8i16 V128:$Rd), (IntOp (v8i8 V64:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8 : BaseSIMDDifferentThreeVector<U, 0b001, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".8h", ".16b", ".16b", []>;
|
|
def v1i64 : BaseSIMDDifferentThreeVector<U, 0b110, opc,
|
|
V128, V64, V64,
|
|
asm, ".1q", ".1d", ".1d", []>;
|
|
def v2i64 : BaseSIMDDifferentThreeVector<U, 0b111, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".1q", ".2d", ".2d", []>;
|
|
|
|
def : Pat<(v8i16 (IntOp (v8i8 (extract_high_v16i8 V128:$Rn)),
|
|
(v8i8 (extract_high_v16i8 V128:$Rm)))),
|
|
(!cast<Instruction>(NAME#"v16i8") V128:$Rn, V128:$Rm)>;
|
|
}
|
|
|
|
multiclass SIMDLongThreeVectorHS<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v4i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b010, opc,
|
|
V128, V64, V64,
|
|
asm, ".4s", ".4h", ".4h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i16 V64:$Rn), (v4i16 V64:$Rm)))]>;
|
|
def v8i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".8h", ".8h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 V128:$Rm)))]>;
|
|
def v2i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b100, opc,
|
|
V128, V64, V64,
|
|
asm, ".2d", ".2s", ".2s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i32 V64:$Rn), (v2i32 V64:$Rm)))]>;
|
|
def v4i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".2d", ".4s", ".4s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 V128:$Rm)))]>;
|
|
}
|
|
|
|
multiclass SIMDLongThreeVectorBHSabdl<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v8i8_v8i16 : BaseSIMDDifferentThreeVector<U, 0b000, opc,
|
|
V128, V64, V64,
|
|
asm, ".8h", ".8b", ".8b",
|
|
[(set (v8i16 V128:$Rd),
|
|
(zext (v8i8 (OpNode (v8i8 V64:$Rn), (v8i8 V64:$Rm)))))]>;
|
|
def v16i8_v8i16 : BaseSIMDDifferentThreeVector<U, 0b001, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".8h", ".16b", ".16b",
|
|
[(set (v8i16 V128:$Rd),
|
|
(zext (v8i8 (OpNode (extract_high_v16i8 V128:$Rn),
|
|
(extract_high_v16i8 V128:$Rm)))))]>;
|
|
def v4i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b010, opc,
|
|
V128, V64, V64,
|
|
asm, ".4s", ".4h", ".4h",
|
|
[(set (v4i32 V128:$Rd),
|
|
(zext (v4i16 (OpNode (v4i16 V64:$Rn), (v4i16 V64:$Rm)))))]>;
|
|
def v8i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".8h", ".8h",
|
|
[(set (v4i32 V128:$Rd),
|
|
(zext (v4i16 (OpNode (extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 V128:$Rm)))))]>;
|
|
def v2i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b100, opc,
|
|
V128, V64, V64,
|
|
asm, ".2d", ".2s", ".2s",
|
|
[(set (v2i64 V128:$Rd),
|
|
(zext (v2i32 (OpNode (v2i32 V64:$Rn), (v2i32 V64:$Rm)))))]>;
|
|
def v4i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".2d", ".4s", ".4s",
|
|
[(set (v2i64 V128:$Rd),
|
|
(zext (v2i32 (OpNode (extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 V128:$Rm)))))]>;
|
|
}
|
|
|
|
multiclass SIMDLongThreeVectorTiedBHSabal<bit U, bits<4> opc,
|
|
string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_v8i16 : BaseSIMDDifferentThreeVectorTied<U, 0b000, opc,
|
|
V128, V64, V64,
|
|
asm, ".8h", ".8b", ".8b",
|
|
[(set (v8i16 V128:$dst),
|
|
(add (v8i16 V128:$Rd),
|
|
(zext (v8i8 (OpNode (v8i8 V64:$Rn), (v8i8 V64:$Rm))))))]>;
|
|
def v16i8_v8i16 : BaseSIMDDifferentThreeVectorTied<U, 0b001, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".8h", ".16b", ".16b",
|
|
[(set (v8i16 V128:$dst),
|
|
(add (v8i16 V128:$Rd),
|
|
(zext (v8i8 (OpNode (extract_high_v16i8 V128:$Rn),
|
|
(extract_high_v16i8 V128:$Rm))))))]>;
|
|
def v4i16_v4i32 : BaseSIMDDifferentThreeVectorTied<U, 0b010, opc,
|
|
V128, V64, V64,
|
|
asm, ".4s", ".4h", ".4h",
|
|
[(set (v4i32 V128:$dst),
|
|
(add (v4i32 V128:$Rd),
|
|
(zext (v4i16 (OpNode (v4i16 V64:$Rn), (v4i16 V64:$Rm))))))]>;
|
|
def v8i16_v4i32 : BaseSIMDDifferentThreeVectorTied<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".8h", ".8h",
|
|
[(set (v4i32 V128:$dst),
|
|
(add (v4i32 V128:$Rd),
|
|
(zext (v4i16 (OpNode (extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 V128:$Rm))))))]>;
|
|
def v2i32_v2i64 : BaseSIMDDifferentThreeVectorTied<U, 0b100, opc,
|
|
V128, V64, V64,
|
|
asm, ".2d", ".2s", ".2s",
|
|
[(set (v2i64 V128:$dst),
|
|
(add (v2i64 V128:$Rd),
|
|
(zext (v2i32 (OpNode (v2i32 V64:$Rn), (v2i32 V64:$Rm))))))]>;
|
|
def v4i32_v2i64 : BaseSIMDDifferentThreeVectorTied<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".2d", ".4s", ".4s",
|
|
[(set (v2i64 V128:$dst),
|
|
(add (v2i64 V128:$Rd),
|
|
(zext (v2i32 (OpNode (extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 V128:$Rm))))))]>;
|
|
}
|
|
|
|
multiclass SIMDLongThreeVectorBHS<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v8i8_v8i16 : BaseSIMDDifferentThreeVector<U, 0b000, opc,
|
|
V128, V64, V64,
|
|
asm, ".8h", ".8b", ".8b",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i8 V64:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8_v8i16 : BaseSIMDDifferentThreeVector<U, 0b001, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".8h", ".16b", ".16b",
|
|
[(set (v8i16 V128:$Rd), (OpNode (extract_high_v16i8 V128:$Rn),
|
|
(extract_high_v16i8 V128:$Rm)))]>;
|
|
def v4i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b010, opc,
|
|
V128, V64, V64,
|
|
asm, ".4s", ".4h", ".4h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i16 V64:$Rn), (v4i16 V64:$Rm)))]>;
|
|
def v8i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".8h", ".8h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 V128:$Rm)))]>;
|
|
def v2i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b100, opc,
|
|
V128, V64, V64,
|
|
asm, ".2d", ".2s", ".2s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i32 V64:$Rn), (v2i32 V64:$Rm)))]>;
|
|
def v4i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".2d", ".4s", ".4s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 V128:$Rm)))]>;
|
|
}
|
|
|
|
multiclass SIMDLongThreeVectorTiedBHS<bit U, bits<4> opc,
|
|
string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_v8i16 : BaseSIMDDifferentThreeVectorTied<U, 0b000, opc,
|
|
V128, V64, V64,
|
|
asm, ".8h", ".8b", ".8b",
|
|
[(set (v8i16 V128:$dst),
|
|
(OpNode (v8i16 V128:$Rd), (v8i8 V64:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8_v8i16 : BaseSIMDDifferentThreeVectorTied<U, 0b001, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".8h", ".16b", ".16b",
|
|
[(set (v8i16 V128:$dst),
|
|
(OpNode (v8i16 V128:$Rd),
|
|
(extract_high_v16i8 V128:$Rn),
|
|
(extract_high_v16i8 V128:$Rm)))]>;
|
|
def v4i16_v4i32 : BaseSIMDDifferentThreeVectorTied<U, 0b010, opc,
|
|
V128, V64, V64,
|
|
asm, ".4s", ".4h", ".4h",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i16 V64:$Rn), (v4i16 V64:$Rm)))]>;
|
|
def v8i16_v4i32 : BaseSIMDDifferentThreeVectorTied<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".8h", ".8h",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd),
|
|
(extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 V128:$Rm)))]>;
|
|
def v2i32_v2i64 : BaseSIMDDifferentThreeVectorTied<U, 0b100, opc,
|
|
V128, V64, V64,
|
|
asm, ".2d", ".2s", ".2s",
|
|
[(set (v2i64 V128:$dst),
|
|
(OpNode (v2i64 V128:$Rd), (v2i32 V64:$Rn), (v2i32 V64:$Rm)))]>;
|
|
def v4i32_v2i64 : BaseSIMDDifferentThreeVectorTied<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".2d", ".4s", ".4s",
|
|
[(set (v2i64 V128:$dst),
|
|
(OpNode (v2i64 V128:$Rd),
|
|
(extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 V128:$Rm)))]>;
|
|
}
|
|
|
|
multiclass SIMDLongThreeVectorSQDMLXTiedHS<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator Accum> {
|
|
def v4i16_v4i32 : BaseSIMDDifferentThreeVectorTied<U, 0b010, opc,
|
|
V128, V64, V64,
|
|
asm, ".4s", ".4h", ".4h",
|
|
[(set (v4i32 V128:$dst),
|
|
(Accum (v4i32 V128:$Rd),
|
|
(v4i32 (int_arm64_neon_sqdmull (v4i16 V64:$Rn),
|
|
(v4i16 V64:$Rm)))))]>;
|
|
def v8i16_v4i32 : BaseSIMDDifferentThreeVectorTied<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".8h", ".8h",
|
|
[(set (v4i32 V128:$dst),
|
|
(Accum (v4i32 V128:$Rd),
|
|
(v4i32 (int_arm64_neon_sqdmull (extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 V128:$Rm)))))]>;
|
|
def v2i32_v2i64 : BaseSIMDDifferentThreeVectorTied<U, 0b100, opc,
|
|
V128, V64, V64,
|
|
asm, ".2d", ".2s", ".2s",
|
|
[(set (v2i64 V128:$dst),
|
|
(Accum (v2i64 V128:$Rd),
|
|
(v2i64 (int_arm64_neon_sqdmull (v2i32 V64:$Rn),
|
|
(v2i32 V64:$Rm)))))]>;
|
|
def v4i32_v2i64 : BaseSIMDDifferentThreeVectorTied<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".2d", ".4s", ".4s",
|
|
[(set (v2i64 V128:$dst),
|
|
(Accum (v2i64 V128:$Rd),
|
|
(v2i64 (int_arm64_neon_sqdmull (extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 V128:$Rm)))))]>;
|
|
}
|
|
|
|
multiclass SIMDWideThreeVectorBHS<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_v8i16 : BaseSIMDDifferentThreeVector<U, 0b000, opc,
|
|
V128, V128, V64,
|
|
asm, ".8h", ".8h", ".8b",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn), (v8i8 V64:$Rm)))]>;
|
|
def v16i8_v8i16 : BaseSIMDDifferentThreeVector<U, 0b001, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".8h", ".8h", ".16b",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn),
|
|
(extract_high_v16i8 V128:$Rm)))]>;
|
|
def v4i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b010, opc,
|
|
V128, V128, V64,
|
|
asm, ".4s", ".4s", ".4h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn), (v4i16 V64:$Rm)))]>;
|
|
def v8i16_v4i32 : BaseSIMDDifferentThreeVector<U, 0b011, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".4s", ".4s", ".8h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn),
|
|
(extract_high_v8i16 V128:$Rm)))]>;
|
|
def v2i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b100, opc,
|
|
V128, V128, V64,
|
|
asm, ".2d", ".2d", ".2s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i64 V128:$Rn), (v2i32 V64:$Rm)))]>;
|
|
def v4i32_v2i64 : BaseSIMDDifferentThreeVector<U, 0b101, opc,
|
|
V128, V128, V128,
|
|
asm#"2", ".2d", ".2d", ".4s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i64 V128:$Rn),
|
|
(extract_high_v4i32 V128:$Rm)))]>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD bitwise extract from vector
|
|
//----------------------------------------------------------------------------
|
|
|
|
class BaseSIMDBitwiseExtract<bit size, RegisterOperand regtype, ValueType vty,
|
|
string asm, string kind>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm, i32imm:$imm), asm,
|
|
"{\t$Rd" # kind # ", $Rn" # kind # ", $Rm" # kind # ", $imm" #
|
|
"|" # kind # "\t$Rd, $Rn, $Rm, $imm}", "",
|
|
[(set (vty regtype:$Rd),
|
|
(ARM64ext regtype:$Rn, regtype:$Rm, (i32 imm:$imm)))]>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
bits<4> imm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = size;
|
|
let Inst{29-21} = 0b101110000;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15} = 0;
|
|
let Inst{14-11} = imm;
|
|
let Inst{10} = 0;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
|
|
multiclass SIMDBitwiseExtract<string asm> {
|
|
def v8i8 : BaseSIMDBitwiseExtract<0, V64, v8i8, asm, ".8b">;
|
|
def v16i8 : BaseSIMDBitwiseExtract<1, V128, v16i8, asm, ".16b">;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD zip vector
|
|
//----------------------------------------------------------------------------
|
|
|
|
class BaseSIMDZipVector<bits<3> size, bits<3> opc, RegisterOperand regtype,
|
|
string asm, string kind, SDNode OpNode, ValueType valty>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm), asm,
|
|
"{\t$Rd" # kind # ", $Rn" # kind # ", $Rm" # kind #
|
|
"|" # kind # "\t$Rd, $Rn, $Rm}", "",
|
|
[(set (valty regtype:$Rd), (OpNode regtype:$Rn, regtype:$Rm))]>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = size{0};
|
|
let Inst{29-24} = 0b001110;
|
|
let Inst{23-22} = size{2-1};
|
|
let Inst{21} = 0;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15} = 0;
|
|
let Inst{14-12} = opc;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDZipVector<bits<3>opc, string asm,
|
|
SDNode OpNode> {
|
|
def v8i8 : BaseSIMDZipVector<0b000, opc, V64,
|
|
asm, ".8b", OpNode, v8i8>;
|
|
def v16i8 : BaseSIMDZipVector<0b001, opc, V128,
|
|
asm, ".16b", OpNode, v16i8>;
|
|
def v4i16 : BaseSIMDZipVector<0b010, opc, V64,
|
|
asm, ".4h", OpNode, v4i16>;
|
|
def v8i16 : BaseSIMDZipVector<0b011, opc, V128,
|
|
asm, ".8h", OpNode, v8i16>;
|
|
def v2i32 : BaseSIMDZipVector<0b100, opc, V64,
|
|
asm, ".2s", OpNode, v2i32>;
|
|
def v4i32 : BaseSIMDZipVector<0b101, opc, V128,
|
|
asm, ".4s", OpNode, v4i32>;
|
|
def v2i64 : BaseSIMDZipVector<0b111, opc, V128,
|
|
asm, ".2d", OpNode, v2i64>;
|
|
|
|
def : Pat<(v2f32 (OpNode V64:$Rn, V64:$Rm)),
|
|
(!cast<Instruction>(NAME#"v2i32") V64:$Rn, V64:$Rm)>;
|
|
def : Pat<(v4f32 (OpNode V128:$Rn, V128:$Rm)),
|
|
(!cast<Instruction>(NAME#"v4i32") V128:$Rn, V128:$Rm)>;
|
|
def : Pat<(v2f64 (OpNode V128:$Rn, V128:$Rm)),
|
|
(!cast<Instruction>(NAME#"v2i64") V128:$Rn, V128:$Rm)>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD three register scalar instructions
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseSIMDThreeScalar<bit U, bits<2> size, bits<5> opcode,
|
|
RegisterClass regtype, string asm,
|
|
list<dag> pattern>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn, regtype:$Rm), asm,
|
|
"\t$Rd, $Rn, $Rm", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-11} = opcode;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDThreeScalarD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v1i64 : BaseSIMDThreeScalar<U, 0b11, opc, FPR64, asm,
|
|
[(set (v1i64 FPR64:$Rd), (OpNode (v1i64 FPR64:$Rn), (v1i64 FPR64:$Rm)))]>;
|
|
}
|
|
|
|
multiclass SIMDThreeScalarBHSD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v1i64 : BaseSIMDThreeScalar<U, 0b11, opc, FPR64, asm,
|
|
[(set (v1i64 FPR64:$Rd), (OpNode (v1i64 FPR64:$Rn), (v1i64 FPR64:$Rm)))]>;
|
|
def v1i32 : BaseSIMDThreeScalar<U, 0b10, opc, FPR32, asm, []>;
|
|
def v1i16 : BaseSIMDThreeScalar<U, 0b01, opc, FPR16, asm, []>;
|
|
def v1i8 : BaseSIMDThreeScalar<U, 0b00, opc, FPR8 , asm, []>;
|
|
|
|
def : Pat<(i64 (OpNode (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
|
|
(!cast<Instruction>(NAME#"v1i64") FPR64:$Rn, FPR64:$Rm)>;
|
|
def : Pat<(i32 (OpNode (i32 FPR32:$Rn), (i32 FPR32:$Rm))),
|
|
(!cast<Instruction>(NAME#"v1i32") FPR32:$Rn, FPR32:$Rm)>;
|
|
}
|
|
|
|
multiclass SIMDThreeScalarHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v1i32 : BaseSIMDThreeScalar<U, 0b10, opc, FPR32, asm,
|
|
[(set FPR32:$Rd, (OpNode FPR32:$Rn, FPR32:$Rm))]>;
|
|
def v1i16 : BaseSIMDThreeScalar<U, 0b01, opc, FPR16, asm, []>;
|
|
}
|
|
|
|
multiclass SIMDThreeScalarSD<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in {
|
|
def #NAME#64 : BaseSIMDThreeScalar<U, {S,1}, opc, FPR64, asm,
|
|
[(set (f64 FPR64:$Rd), (OpNode (f64 FPR64:$Rn), (f64 FPR64:$Rm)))]>;
|
|
def #NAME#32 : BaseSIMDThreeScalar<U, {S,0}, opc, FPR32, asm,
|
|
[(set FPR32:$Rd, (OpNode FPR32:$Rn, FPR32:$Rm))]>;
|
|
}
|
|
|
|
def : Pat<(v1f64 (OpNode (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
|
|
(!cast<Instruction>(NAME # "64") FPR64:$Rn, FPR64:$Rm)>;
|
|
}
|
|
|
|
multiclass SIMDThreeScalarFPCmp<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in {
|
|
def #NAME#64 : BaseSIMDThreeScalar<U, {S,1}, opc, FPR64, asm,
|
|
[(set (i64 FPR64:$Rd), (OpNode (f64 FPR64:$Rn), (f64 FPR64:$Rm)))]>;
|
|
def #NAME#32 : BaseSIMDThreeScalar<U, {S,0}, opc, FPR32, asm,
|
|
[(set (i32 FPR32:$Rd), (OpNode (f32 FPR32:$Rn), (f32 FPR32:$Rm)))]>;
|
|
}
|
|
|
|
def : Pat<(v1i64 (OpNode (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
|
|
(!cast<Instruction>(NAME # "64") FPR64:$Rn, FPR64:$Rm)>;
|
|
}
|
|
|
|
class BaseSIMDThreeScalarMixed<bit U, bits<2> size, bits<5> opcode,
|
|
dag oops, dag iops, string asm, string cstr, list<dag> pat>
|
|
: I<oops, iops, asm,
|
|
"\t$Rd, $Rn, $Rm", cstr, pat>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21} = 1;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-11} = opcode;
|
|
let Inst{10} = 0;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDThreeScalarMixedHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def i16 : BaseSIMDThreeScalarMixed<U, 0b01, opc,
|
|
(outs FPR32:$Rd),
|
|
(ins FPR16:$Rn, FPR16:$Rm), asm, "", []>;
|
|
def i32 : BaseSIMDThreeScalarMixed<U, 0b10, opc,
|
|
(outs FPR64:$Rd),
|
|
(ins FPR32:$Rn, FPR32:$Rm), asm, "",
|
|
[(set (i64 FPR64:$Rd), (OpNode (i32 FPR32:$Rn), (i32 FPR32:$Rm)))]>;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDThreeScalarMixedTiedHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def i16 : BaseSIMDThreeScalarMixed<U, 0b01, opc,
|
|
(outs FPR32:$dst),
|
|
(ins FPR32:$Rd, FPR16:$Rn, FPR16:$Rm),
|
|
asm, "$Rd = $dst", []>;
|
|
def i32 : BaseSIMDThreeScalarMixed<U, 0b10, opc,
|
|
(outs FPR64:$dst),
|
|
(ins FPR64:$Rd, FPR32:$Rn, FPR32:$Rm),
|
|
asm, "$Rd = $dst",
|
|
[(set (i64 FPR64:$dst),
|
|
(OpNode (i64 FPR64:$Rd), (i32 FPR32:$Rn), (i32 FPR32:$Rm)))]>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD two register scalar instructions
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDTwoScalar<bit U, bits<2> size, bits<5> opcode,
|
|
RegisterClass regtype, RegisterClass regtype2,
|
|
string asm, list<dag> pat>
|
|
: I<(outs regtype:$Rd), (ins regtype2:$Rn), asm,
|
|
"\t$Rd, $Rn", "", pat>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDTwoScalarTied<bit U, bits<2> size, bits<5> opcode,
|
|
RegisterClass regtype, RegisterClass regtype2,
|
|
string asm, list<dag> pat>
|
|
: I<(outs regtype:$dst), (ins regtype:$Rd, regtype2:$Rn), asm,
|
|
"\t$Rd, $Rn", "$Rd = $dst", pat>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDCmpTwoScalar<bit U, bits<2> size, bits<5> opcode,
|
|
RegisterClass regtype, string asm>
|
|
: I<(outs regtype:$Rd), (ins regtype:$Rn), asm,
|
|
"\t$Rd, $Rn, #0", "", []>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b10000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class SIMDInexactCvtTwoScalar<bits<5> opcode, string asm>
|
|
: I<(outs FPR32:$Rd), (ins FPR64:$Rn), asm, "\t$Rd, $Rn", "",
|
|
[(set (f32 FPR32:$Rd), (int_arm64_sisd_fcvtxn (f64 FPR64:$Rn)))]>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-17} = 0b011111100110000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDCmpTwoScalarD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v1i64rz : BaseSIMDCmpTwoScalar<U, 0b11, opc, FPR64, asm>;
|
|
|
|
def : Pat<(v1i64 (OpNode FPR64:$Rn)),
|
|
(!cast<Instruction>(NAME # v1i64rz) FPR64:$Rn)>;
|
|
}
|
|
|
|
multiclass SIMDCmpTwoScalarSD<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v1i64rz : BaseSIMDCmpTwoScalar<U, {S,1}, opc, FPR64, asm>;
|
|
def v1i32rz : BaseSIMDCmpTwoScalar<U, {S,0}, opc, FPR32, asm>;
|
|
|
|
def : Pat<(v1i64 (OpNode (v1f64 FPR64:$Rn))),
|
|
(!cast<Instruction>(NAME # v1i64rz) FPR64:$Rn)>;
|
|
}
|
|
|
|
multiclass SIMDTwoScalarD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v1i64 : BaseSIMDTwoScalar<U, 0b11, opc, FPR64, FPR64, asm,
|
|
[(set (v1i64 FPR64:$Rd), (OpNode (v1i64 FPR64:$Rn)))]>;
|
|
|
|
def : Pat<(i64 (OpNode (i64 FPR64:$Rn))),
|
|
(!cast<Instruction>(NAME # "v1i64") FPR64:$Rn)>;
|
|
}
|
|
|
|
multiclass SIMDTwoScalarSD<bit U, bit S, bits<5> opc, string asm> {
|
|
def v1i64 : BaseSIMDTwoScalar<U, {S,1}, opc, FPR64, FPR64, asm,[]>;
|
|
def v1i32 : BaseSIMDTwoScalar<U, {S,0}, opc, FPR32, FPR32, asm,[]>;
|
|
}
|
|
|
|
multiclass SIMDTwoScalarCVTSD<bit U, bit S, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v1i64 : BaseSIMDTwoScalar<U, {S,1}, opc, FPR64, FPR64, asm,
|
|
[(set FPR64:$Rd, (OpNode (f64 FPR64:$Rn)))]>;
|
|
def v1i32 : BaseSIMDTwoScalar<U, {S,0}, opc, FPR32, FPR32, asm,
|
|
[(set FPR32:$Rd, (OpNode (f32 FPR32:$Rn)))]>;
|
|
}
|
|
|
|
multiclass SIMDTwoScalarBHSD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in {
|
|
def v1i64 : BaseSIMDTwoScalar<U, 0b11, opc, FPR64, FPR64, asm,
|
|
[(set (i64 FPR64:$Rd), (OpNode (i64 FPR64:$Rn)))]>;
|
|
def v1i32 : BaseSIMDTwoScalar<U, 0b10, opc, FPR32, FPR32, asm,
|
|
[(set (i32 FPR32:$Rd), (OpNode (i32 FPR32:$Rn)))]>;
|
|
def v1i16 : BaseSIMDTwoScalar<U, 0b01, opc, FPR16, FPR16, asm, []>;
|
|
def v1i8 : BaseSIMDTwoScalar<U, 0b00, opc, FPR8 , FPR8 , asm, []>;
|
|
}
|
|
|
|
def : Pat<(v1i64 (OpNode (v1i64 FPR64:$Rn))),
|
|
(!cast<Instruction>(NAME # v1i64) FPR64:$Rn)>;
|
|
}
|
|
|
|
multiclass SIMDTwoScalarBHSDTied<bit U, bits<5> opc, string asm,
|
|
Intrinsic OpNode> {
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in {
|
|
def v1i64 : BaseSIMDTwoScalarTied<U, 0b11, opc, FPR64, FPR64, asm,
|
|
[(set (i64 FPR64:$dst), (OpNode (i64 FPR64:$Rd), (i64 FPR64:$Rn)))]>;
|
|
def v1i32 : BaseSIMDTwoScalarTied<U, 0b10, opc, FPR32, FPR32, asm,
|
|
[(set (i32 FPR32:$dst), (OpNode (i32 FPR32:$Rd), (i32 FPR32:$Rn)))]>;
|
|
def v1i16 : BaseSIMDTwoScalarTied<U, 0b01, opc, FPR16, FPR16, asm, []>;
|
|
def v1i8 : BaseSIMDTwoScalarTied<U, 0b00, opc, FPR8 , FPR8 , asm, []>;
|
|
}
|
|
|
|
def : Pat<(v1i64 (OpNode (v1i64 FPR64:$Rd), (v1i64 FPR64:$Rn))),
|
|
(!cast<Instruction>(NAME # v1i64) FPR64:$Rd, FPR64:$Rn)>;
|
|
}
|
|
|
|
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDTwoScalarMixedBHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v1i32 : BaseSIMDTwoScalar<U, 0b10, opc, FPR32, FPR64, asm,
|
|
[(set (i32 FPR32:$Rd), (OpNode (i64 FPR64:$Rn)))]>;
|
|
def v1i16 : BaseSIMDTwoScalar<U, 0b01, opc, FPR16, FPR32, asm, []>;
|
|
def v1i8 : BaseSIMDTwoScalar<U, 0b00, opc, FPR8 , FPR16, asm, []>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD scalar pairwise instructions
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDPairwiseScalar<bit U, bits<2> size, bits<5> opcode,
|
|
RegisterOperand regtype, RegisterOperand vectype,
|
|
string asm, string kind>
|
|
: I<(outs regtype:$Rd), (ins vectype:$Rn), asm,
|
|
"{\t$Rd, $Rn" # kind # "|" # kind # "\t$Rd, $Rn}", "", []>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b11110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b11000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDPairwiseScalarD<bit U, bits<5> opc, string asm> {
|
|
def v2i64p : BaseSIMDPairwiseScalar<U, 0b11, opc, FPR64Op, V128,
|
|
asm, ".2d">;
|
|
}
|
|
|
|
multiclass SIMDPairwiseScalarSD<bit U, bit S, bits<5> opc, string asm> {
|
|
def v2i32p : BaseSIMDPairwiseScalar<U, {S,0}, opc, FPR32Op, V64,
|
|
asm, ".2s">;
|
|
def v2i64p : BaseSIMDPairwiseScalar<U, {S,1}, opc, FPR64Op, V128,
|
|
asm, ".2d">;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD across lanes instructions
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDAcrossLanes<bit Q, bit U, bits<2> size, bits<5> opcode,
|
|
RegisterClass regtype, RegisterOperand vectype,
|
|
string asm, string kind, list<dag> pattern>
|
|
: I<(outs regtype:$Rd), (ins vectype:$Rn), asm,
|
|
"{\t$Rd, $Rn" # kind # "|" # kind # "\t$Rd, $Rn}", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-24} = 0b01110;
|
|
let Inst{23-22} = size;
|
|
let Inst{21-17} = 0b11000;
|
|
let Inst{16-12} = opcode;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDAcrossLanesBHS<bit U, bits<5> opcode,
|
|
string asm> {
|
|
def v8i8v : BaseSIMDAcrossLanes<0, U, 0b00, opcode, FPR8, V64,
|
|
asm, ".8b", []>;
|
|
def v16i8v : BaseSIMDAcrossLanes<1, U, 0b00, opcode, FPR8, V128,
|
|
asm, ".16b", []>;
|
|
def v4i16v : BaseSIMDAcrossLanes<0, U, 0b01, opcode, FPR16, V64,
|
|
asm, ".4h", []>;
|
|
def v8i16v : BaseSIMDAcrossLanes<1, U, 0b01, opcode, FPR16, V128,
|
|
asm, ".8h", []>;
|
|
def v4i32v : BaseSIMDAcrossLanes<1, U, 0b10, opcode, FPR32, V128,
|
|
asm, ".4s", []>;
|
|
}
|
|
|
|
multiclass SIMDAcrossLanesHSD<bit U, bits<5> opcode, string asm> {
|
|
def v8i8v : BaseSIMDAcrossLanes<0, U, 0b00, opcode, FPR16, V64,
|
|
asm, ".8b", []>;
|
|
def v16i8v : BaseSIMDAcrossLanes<1, U, 0b00, opcode, FPR16, V128,
|
|
asm, ".16b", []>;
|
|
def v4i16v : BaseSIMDAcrossLanes<0, U, 0b01, opcode, FPR32, V64,
|
|
asm, ".4h", []>;
|
|
def v8i16v : BaseSIMDAcrossLanes<1, U, 0b01, opcode, FPR32, V128,
|
|
asm, ".8h", []>;
|
|
def v4i32v : BaseSIMDAcrossLanes<1, U, 0b10, opcode, FPR64, V128,
|
|
asm, ".4s", []>;
|
|
}
|
|
|
|
multiclass SIMDAcrossLanesS<bits<5> opcode, bit sz1, string asm,
|
|
Intrinsic intOp> {
|
|
def v4i32v : BaseSIMDAcrossLanes<1, 1, {sz1, 0}, opcode, FPR32, V128,
|
|
asm, ".4s",
|
|
[(set FPR32:$Rd, (intOp (v4f32 V128:$Rn)))]>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD INS/DUP instructions
|
|
//----------------------------------------------------------------------------
|
|
|
|
// FIXME: There has got to be a better way to factor these. ugh.
|
|
|
|
class BaseSIMDInsDup<bit Q, bit op, dag outs, dag ins, string asm,
|
|
string operands, string constraints, list<dag> pattern>
|
|
: I<outs, ins, asm, operands, constraints, pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = op;
|
|
let Inst{28-21} = 0b01110000;
|
|
let Inst{15} = 0;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class SIMDDupFromMain<bit Q, bits<5> imm5, string size, ValueType vectype,
|
|
RegisterOperand vecreg, RegisterClass regtype>
|
|
: BaseSIMDInsDup<Q, 0, (outs vecreg:$Rd), (ins regtype:$Rn), "dup",
|
|
"{\t$Rd" # size # ", $Rn" #
|
|
"|" # size # "\t$Rd, $Rn}", "",
|
|
[(set (vectype vecreg:$Rd), (ARM64dup regtype:$Rn))]> {
|
|
let Inst{20-16} = imm5;
|
|
let Inst{14-11} = 0b0001;
|
|
}
|
|
|
|
class SIMDDupFromElement<bit Q, string dstkind, string srckind,
|
|
ValueType vectype, ValueType insreg,
|
|
RegisterOperand vecreg, Operand idxtype,
|
|
ValueType elttype, SDNode OpNode>
|
|
: BaseSIMDInsDup<Q, 0, (outs vecreg:$Rd), (ins V128:$Rn, idxtype:$idx), "dup",
|
|
"{\t$Rd" # dstkind # ", $Rn" # srckind # "$idx" #
|
|
"|" # dstkind # "\t$Rd, $Rn$idx}", "",
|
|
[(set (vectype vecreg:$Rd),
|
|
(OpNode (insreg V128:$Rn), idxtype:$idx))]> {
|
|
let Inst{14-11} = 0b0000;
|
|
}
|
|
|
|
class SIMDDup64FromElement
|
|
: SIMDDupFromElement<1, ".2d", ".d", v2i64, v2i64, V128,
|
|
VectorIndexD, i64, ARM64duplane64> {
|
|
bits<1> idx;
|
|
let Inst{20} = idx;
|
|
let Inst{19-16} = 0b1000;
|
|
}
|
|
|
|
class SIMDDup32FromElement<bit Q, string size, ValueType vectype,
|
|
RegisterOperand vecreg>
|
|
: SIMDDupFromElement<Q, size, ".s", vectype, v4i32, vecreg,
|
|
VectorIndexS, i64, ARM64duplane32> {
|
|
bits<2> idx;
|
|
let Inst{20-19} = idx;
|
|
let Inst{18-16} = 0b100;
|
|
}
|
|
|
|
class SIMDDup16FromElement<bit Q, string size, ValueType vectype,
|
|
RegisterOperand vecreg>
|
|
: SIMDDupFromElement<Q, size, ".h", vectype, v8i16, vecreg,
|
|
VectorIndexH, i64, ARM64duplane16> {
|
|
bits<3> idx;
|
|
let Inst{20-18} = idx;
|
|
let Inst{17-16} = 0b10;
|
|
}
|
|
|
|
class SIMDDup8FromElement<bit Q, string size, ValueType vectype,
|
|
RegisterOperand vecreg>
|
|
: SIMDDupFromElement<Q, size, ".b", vectype, v16i8, vecreg,
|
|
VectorIndexB, i64, ARM64duplane8> {
|
|
bits<4> idx;
|
|
let Inst{20-17} = idx;
|
|
let Inst{16} = 1;
|
|
}
|
|
|
|
class BaseSIMDMov<bit Q, string size, bits<4> imm4, RegisterClass regtype,
|
|
Operand idxtype, string asm, list<dag> pattern>
|
|
: BaseSIMDInsDup<Q, 0, (outs regtype:$Rd), (ins V128:$Rn, idxtype:$idx), asm,
|
|
"{\t$Rd, $Rn" # size # "$idx" #
|
|
"|" # size # "\t$Rd, $Rn$idx}", "", pattern> {
|
|
let Inst{14-11} = imm4;
|
|
}
|
|
|
|
class SIMDSMov<bit Q, string size, RegisterClass regtype,
|
|
Operand idxtype>
|
|
: BaseSIMDMov<Q, size, 0b0101, regtype, idxtype, "smov", []>;
|
|
class SIMDUMov<bit Q, string size, ValueType vectype, RegisterClass regtype,
|
|
Operand idxtype>
|
|
: BaseSIMDMov<Q, size, 0b0111, regtype, idxtype, "umov",
|
|
[(set regtype:$Rd, (vector_extract (vectype V128:$Rn), idxtype:$idx))]>;
|
|
|
|
class SIMDMovAlias<string asm, string size, Instruction inst,
|
|
RegisterClass regtype, Operand idxtype>
|
|
: InstAlias<asm#"{\t$dst, $src"#size#"$idx" #
|
|
"|" # size # "\t$dst, $src$idx}",
|
|
(inst regtype:$dst, V128:$src, idxtype:$idx)>;
|
|
|
|
multiclass SMov {
|
|
def vi8to32 : SIMDSMov<0, ".b", GPR32, VectorIndexB> {
|
|
bits<4> idx;
|
|
let Inst{20-17} = idx;
|
|
let Inst{16} = 1;
|
|
}
|
|
def vi8to64 : SIMDSMov<1, ".b", GPR64, VectorIndexB> {
|
|
bits<4> idx;
|
|
let Inst{20-17} = idx;
|
|
let Inst{16} = 1;
|
|
}
|
|
def vi16to32 : SIMDSMov<0, ".h", GPR32, VectorIndexH> {
|
|
bits<3> idx;
|
|
let Inst{20-18} = idx;
|
|
let Inst{17-16} = 0b10;
|
|
}
|
|
def vi16to64 : SIMDSMov<1, ".h", GPR64, VectorIndexH> {
|
|
bits<3> idx;
|
|
let Inst{20-18} = idx;
|
|
let Inst{17-16} = 0b10;
|
|
}
|
|
def vi32to64 : SIMDSMov<1, ".s", GPR64, VectorIndexS> {
|
|
bits<2> idx;
|
|
let Inst{20-19} = idx;
|
|
let Inst{18-16} = 0b100;
|
|
}
|
|
}
|
|
|
|
multiclass UMov {
|
|
def vi8 : SIMDUMov<0, ".b", v16i8, GPR32, VectorIndexB> {
|
|
bits<4> idx;
|
|
let Inst{20-17} = idx;
|
|
let Inst{16} = 1;
|
|
}
|
|
def vi16 : SIMDUMov<0, ".h", v8i16, GPR32, VectorIndexH> {
|
|
bits<3> idx;
|
|
let Inst{20-18} = idx;
|
|
let Inst{17-16} = 0b10;
|
|
}
|
|
def vi32 : SIMDUMov<0, ".s", v4i32, GPR32, VectorIndexS> {
|
|
bits<2> idx;
|
|
let Inst{20-19} = idx;
|
|
let Inst{18-16} = 0b100;
|
|
}
|
|
def vi64 : SIMDUMov<1, ".d", v2i64, GPR64, VectorIndexD> {
|
|
bits<1> idx;
|
|
let Inst{20} = idx;
|
|
let Inst{19-16} = 0b1000;
|
|
}
|
|
def : SIMDMovAlias<"mov", ".s",
|
|
!cast<Instruction>(NAME#"vi32"),
|
|
GPR32, VectorIndexS>;
|
|
def : SIMDMovAlias<"mov", ".d",
|
|
!cast<Instruction>(NAME#"vi64"),
|
|
GPR64, VectorIndexD>;
|
|
}
|
|
|
|
class SIMDInsFromMain<string size, ValueType vectype,
|
|
RegisterClass regtype, Operand idxtype>
|
|
: BaseSIMDInsDup<1, 0, (outs V128:$dst),
|
|
(ins V128:$Rd, idxtype:$idx, regtype:$Rn), "ins",
|
|
"{\t$Rd" # size # "$idx, $Rn" #
|
|
"|" # size # "\t$Rd$idx, $Rn}",
|
|
"$Rd = $dst",
|
|
[(set V128:$dst,
|
|
(vector_insert (vectype V128:$Rd), regtype:$Rn, idxtype:$idx))]> {
|
|
let Inst{14-11} = 0b0011;
|
|
}
|
|
|
|
class SIMDInsFromElement<string size, ValueType vectype,
|
|
ValueType elttype, Operand idxtype>
|
|
: BaseSIMDInsDup<1, 1, (outs V128:$dst),
|
|
(ins V128:$Rd, idxtype:$idx, V128:$Rn, idxtype:$idx2), "ins",
|
|
"{\t$Rd" # size # "$idx, $Rn" # size # "$idx2" #
|
|
"|" # size # "\t$Rd$idx, $Rn$idx2}",
|
|
"$Rd = $dst",
|
|
[(set V128:$dst,
|
|
(vector_insert
|
|
(vectype V128:$Rd),
|
|
(elttype (vector_extract (vectype V128:$Rn), idxtype:$idx2)),
|
|
idxtype:$idx))]>;
|
|
|
|
class SIMDInsMainMovAlias<string size, Instruction inst,
|
|
RegisterClass regtype, Operand idxtype>
|
|
: InstAlias<"mov" # "{\t$dst" # size # "$idx, $src" #
|
|
"|" # size #"\t$dst$idx, $src}",
|
|
(inst V128:$dst, idxtype:$idx, regtype:$src)>;
|
|
class SIMDInsElementMovAlias<string size, Instruction inst,
|
|
Operand idxtype>
|
|
: InstAlias<"mov" # "{\t$dst" # size # "$idx, $src" # size # "$idx2" #
|
|
# "|" # size #" $dst$idx, $src$idx2}",
|
|
(inst V128:$dst, idxtype:$idx, V128:$src, idxtype:$idx2)>;
|
|
|
|
|
|
multiclass SIMDIns {
|
|
def vi8gpr : SIMDInsFromMain<".b", v16i8, GPR32, VectorIndexB> {
|
|
bits<4> idx;
|
|
let Inst{20-17} = idx;
|
|
let Inst{16} = 1;
|
|
}
|
|
def vi16gpr : SIMDInsFromMain<".h", v8i16, GPR32, VectorIndexH> {
|
|
bits<3> idx;
|
|
let Inst{20-18} = idx;
|
|
let Inst{17-16} = 0b10;
|
|
}
|
|
def vi32gpr : SIMDInsFromMain<".s", v4i32, GPR32, VectorIndexS> {
|
|
bits<2> idx;
|
|
let Inst{20-19} = idx;
|
|
let Inst{18-16} = 0b100;
|
|
}
|
|
def vi64gpr : SIMDInsFromMain<".d", v2i64, GPR64, VectorIndexD> {
|
|
bits<1> idx;
|
|
let Inst{20} = idx;
|
|
let Inst{19-16} = 0b1000;
|
|
}
|
|
|
|
def vi8lane : SIMDInsFromElement<".b", v16i8, i32, VectorIndexB> {
|
|
bits<4> idx;
|
|
bits<4> idx2;
|
|
let Inst{20-17} = idx;
|
|
let Inst{16} = 1;
|
|
let Inst{14-11} = idx2;
|
|
}
|
|
def vi16lane : SIMDInsFromElement<".h", v8i16, i32, VectorIndexH> {
|
|
bits<3> idx;
|
|
bits<3> idx2;
|
|
let Inst{20-18} = idx;
|
|
let Inst{17-16} = 0b10;
|
|
let Inst{14-12} = idx2;
|
|
let Inst{11} = 0;
|
|
}
|
|
def vi32lane : SIMDInsFromElement<".s", v4i32, i32, VectorIndexS> {
|
|
bits<2> idx;
|
|
bits<2> idx2;
|
|
let Inst{20-19} = idx;
|
|
let Inst{18-16} = 0b100;
|
|
let Inst{14-13} = idx2;
|
|
let Inst{12-11} = 0;
|
|
}
|
|
def vi64lane : SIMDInsFromElement<".d", v2i64, i64, VectorIndexD> {
|
|
bits<1> idx;
|
|
bits<1> idx2;
|
|
let Inst{20} = idx;
|
|
let Inst{19-16} = 0b1000;
|
|
let Inst{14} = idx2;
|
|
let Inst{13-11} = 0;
|
|
}
|
|
|
|
// For all forms of the INS instruction, the "mov" mnemonic is the
|
|
// preferred alias. Why they didn't just call the instruction "mov" in
|
|
// the first place is a very good question indeed...
|
|
def : SIMDInsMainMovAlias<".b", !cast<Instruction>(NAME#"vi8gpr"),
|
|
GPR32, VectorIndexB>;
|
|
def : SIMDInsMainMovAlias<".h", !cast<Instruction>(NAME#"vi16gpr"),
|
|
GPR32, VectorIndexH>;
|
|
def : SIMDInsMainMovAlias<".s", !cast<Instruction>(NAME#"vi32gpr"),
|
|
GPR32, VectorIndexS>;
|
|
def : SIMDInsMainMovAlias<".d", !cast<Instruction>(NAME#"vi64gpr"),
|
|
GPR64, VectorIndexD>;
|
|
|
|
def : SIMDInsElementMovAlias<".b", !cast<Instruction>(NAME#"vi8lane"),
|
|
VectorIndexB>;
|
|
def : SIMDInsElementMovAlias<".h", !cast<Instruction>(NAME#"vi16lane"),
|
|
VectorIndexH>;
|
|
def : SIMDInsElementMovAlias<".s", !cast<Instruction>(NAME#"vi32lane"),
|
|
VectorIndexS>;
|
|
def : SIMDInsElementMovAlias<".d", !cast<Instruction>(NAME#"vi64lane"),
|
|
VectorIndexD>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD TBL/TBX
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseSIMDTableLookup<bit Q, bits<2> len, bit op, RegisterOperand vectype,
|
|
RegisterOperand listtype, string asm, string kind>
|
|
: I<(outs vectype:$Vd), (ins listtype:$Vn, vectype:$Vm), asm,
|
|
"\t$Vd" # kind # ", $Vn, $Vm" # kind, "", []>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Vd;
|
|
bits<5> Vn;
|
|
bits<5> Vm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29-21} = 0b001110000;
|
|
let Inst{20-16} = Vm;
|
|
let Inst{15} = 0;
|
|
let Inst{14-13} = len;
|
|
let Inst{12} = op;
|
|
let Inst{11-10} = 0b00;
|
|
let Inst{9-5} = Vn;
|
|
let Inst{4-0} = Vd;
|
|
}
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseSIMDTableLookupTied<bit Q, bits<2> len, bit op, RegisterOperand vectype,
|
|
RegisterOperand listtype, string asm, string kind>
|
|
: I<(outs vectype:$dst), (ins vectype:$Vd, listtype:$Vn, vectype:$Vm), asm,
|
|
"\t$Vd" # kind # ", $Vn, $Vm" # kind, "$Vd = $dst", []>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Vd;
|
|
bits<5> Vn;
|
|
bits<5> Vm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29-21} = 0b001110000;
|
|
let Inst{20-16} = Vm;
|
|
let Inst{15} = 0;
|
|
let Inst{14-13} = len;
|
|
let Inst{12} = op;
|
|
let Inst{11-10} = 0b00;
|
|
let Inst{9-5} = Vn;
|
|
let Inst{4-0} = Vd;
|
|
}
|
|
|
|
class SIMDTableLookupAlias<string asm, Instruction inst,
|
|
RegisterOperand vectype, RegisterOperand listtype>
|
|
: InstAlias<!strconcat(asm, "\t$dst, $lst, $index"),
|
|
(inst vectype:$dst, listtype:$lst, vectype:$index), 0>;
|
|
|
|
multiclass SIMDTableLookup<bit op, string asm> {
|
|
def v8i8One : BaseSIMDTableLookup<0, 0b00, op, V64, VecListOne16b,
|
|
asm, ".8b">;
|
|
def v8i8Two : BaseSIMDTableLookup<0, 0b01, op, V64, VecListTwo16b,
|
|
asm, ".8b">;
|
|
def v8i8Three : BaseSIMDTableLookup<0, 0b10, op, V64, VecListThree16b,
|
|
asm, ".8b">;
|
|
def v8i8Four : BaseSIMDTableLookup<0, 0b11, op, V64, VecListFour16b,
|
|
asm, ".8b">;
|
|
def v16i8One : BaseSIMDTableLookup<1, 0b00, op, V128, VecListOne16b,
|
|
asm, ".16b">;
|
|
def v16i8Two : BaseSIMDTableLookup<1, 0b01, op, V128, VecListTwo16b,
|
|
asm, ".16b">;
|
|
def v16i8Three: BaseSIMDTableLookup<1, 0b10, op, V128, VecListThree16b,
|
|
asm, ".16b">;
|
|
def v16i8Four : BaseSIMDTableLookup<1, 0b11, op, V128, VecListFour16b,
|
|
asm, ".16b">;
|
|
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8One"),
|
|
V64, VecListOne128>;
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8Two"),
|
|
V64, VecListTwo128>;
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8Three"),
|
|
V64, VecListThree128>;
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8Four"),
|
|
V64, VecListFour128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8One"),
|
|
V128, VecListOne128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8Two"),
|
|
V128, VecListTwo128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8Three"),
|
|
V128, VecListThree128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8Four"),
|
|
V128, VecListFour128>;
|
|
}
|
|
|
|
multiclass SIMDTableLookupTied<bit op, string asm> {
|
|
def v8i8One : BaseSIMDTableLookupTied<0, 0b00, op, V64, VecListOne16b,
|
|
asm, ".8b">;
|
|
def v8i8Two : BaseSIMDTableLookupTied<0, 0b01, op, V64, VecListTwo16b,
|
|
asm, ".8b">;
|
|
def v8i8Three : BaseSIMDTableLookupTied<0, 0b10, op, V64, VecListThree16b,
|
|
asm, ".8b">;
|
|
def v8i8Four : BaseSIMDTableLookupTied<0, 0b11, op, V64, VecListFour16b,
|
|
asm, ".8b">;
|
|
def v16i8One : BaseSIMDTableLookupTied<1, 0b00, op, V128, VecListOne16b,
|
|
asm, ".16b">;
|
|
def v16i8Two : BaseSIMDTableLookupTied<1, 0b01, op, V128, VecListTwo16b,
|
|
asm, ".16b">;
|
|
def v16i8Three: BaseSIMDTableLookupTied<1, 0b10, op, V128, VecListThree16b,
|
|
asm, ".16b">;
|
|
def v16i8Four : BaseSIMDTableLookupTied<1, 0b11, op, V128, VecListFour16b,
|
|
asm, ".16b">;
|
|
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8One"),
|
|
V64, VecListOne128>;
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8Two"),
|
|
V64, VecListTwo128>;
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8Three"),
|
|
V64, VecListThree128>;
|
|
def : SIMDTableLookupAlias<asm # ".8b",
|
|
!cast<Instruction>(NAME#"v8i8Four"),
|
|
V64, VecListFour128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8One"),
|
|
V128, VecListOne128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8Two"),
|
|
V128, VecListTwo128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8Three"),
|
|
V128, VecListThree128>;
|
|
def : SIMDTableLookupAlias<asm # ".16b",
|
|
!cast<Instruction>(NAME#"v16i8Four"),
|
|
V128, VecListFour128>;
|
|
}
|
|
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD scalar CPY
|
|
//----------------------------------------------------------------------------
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDScalarCPY<RegisterClass regtype, RegisterOperand vectype,
|
|
string kind, Operand idxtype>
|
|
: I<(outs regtype:$dst), (ins vectype:$src, idxtype:$idx), "mov",
|
|
"{\t$dst, $src" # kind # "$idx" #
|
|
"|\t$dst, $src$idx}", "", []>,
|
|
Sched<[WriteV]> {
|
|
bits<5> dst;
|
|
bits<5> src;
|
|
let Inst{31-21} = 0b01011110000;
|
|
let Inst{15-10} = 0b000001;
|
|
let Inst{9-5} = src;
|
|
let Inst{4-0} = dst;
|
|
}
|
|
|
|
class SIMDScalarCPYAlias<string asm, string size, Instruction inst,
|
|
RegisterClass regtype, RegisterOperand vectype, Operand idxtype>
|
|
: InstAlias<asm # "{\t$dst, $src" # size # "$index" #
|
|
# "|\t$dst, $src$index}",
|
|
(inst regtype:$dst, vectype:$src, idxtype:$index)>;
|
|
|
|
|
|
multiclass SIMDScalarCPY<string asm> {
|
|
def i8 : BaseSIMDScalarCPY<FPR8, V128, ".b", VectorIndexB> {
|
|
bits<4> idx;
|
|
let Inst{20-17} = idx;
|
|
let Inst{16} = 1;
|
|
}
|
|
def i16 : BaseSIMDScalarCPY<FPR16, V128, ".h", VectorIndexH> {
|
|
bits<3> idx;
|
|
let Inst{20-18} = idx;
|
|
let Inst{17-16} = 0b10;
|
|
}
|
|
def i32 : BaseSIMDScalarCPY<FPR32, V128, ".s", VectorIndexS> {
|
|
bits<2> idx;
|
|
let Inst{20-19} = idx;
|
|
let Inst{18-16} = 0b100;
|
|
}
|
|
def i64 : BaseSIMDScalarCPY<FPR64, V128, ".d", VectorIndexD> {
|
|
bits<1> idx;
|
|
let Inst{20} = idx;
|
|
let Inst{19-16} = 0b1000;
|
|
}
|
|
|
|
// 'DUP' mnemonic aliases.
|
|
def : SIMDScalarCPYAlias<"dup", ".b",
|
|
!cast<Instruction>(NAME#"i8"),
|
|
FPR8, V128, VectorIndexB>;
|
|
def : SIMDScalarCPYAlias<"dup", ".h",
|
|
!cast<Instruction>(NAME#"i16"),
|
|
FPR16, V128, VectorIndexH>;
|
|
def : SIMDScalarCPYAlias<"dup", ".s",
|
|
!cast<Instruction>(NAME#"i32"),
|
|
FPR32, V128, VectorIndexS>;
|
|
def : SIMDScalarCPYAlias<"dup", ".d",
|
|
!cast<Instruction>(NAME#"i64"),
|
|
FPR64, V128, VectorIndexD>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD modified immediate instructions
|
|
//----------------------------------------------------------------------------
|
|
|
|
class BaseSIMDModifiedImm<bit Q, bit op, dag oops, dag iops,
|
|
string asm, string op_string,
|
|
string cstr, list<dag> pattern>
|
|
: I<oops, iops, asm, op_string, cstr, pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<8> imm8;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = op;
|
|
let Inst{28-19} = 0b0111100000;
|
|
let Inst{18-16} = imm8{7-5};
|
|
let Inst{11-10} = 0b01;
|
|
let Inst{9-5} = imm8{4-0};
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class BaseSIMDModifiedImmVector<bit Q, bit op, RegisterOperand vectype,
|
|
Operand immtype, dag opt_shift_iop,
|
|
string opt_shift, string asm, string kind,
|
|
list<dag> pattern>
|
|
: BaseSIMDModifiedImm<Q, op, (outs vectype:$Rd),
|
|
!con((ins immtype:$imm8), opt_shift_iop), asm,
|
|
"{\t$Rd" # kind # ", $imm8" # opt_shift #
|
|
"|" # kind # "\t$Rd, $imm8" # opt_shift # "}",
|
|
"", pattern> {
|
|
let DecoderMethod = "DecodeModImmInstruction";
|
|
}
|
|
|
|
class BaseSIMDModifiedImmVectorTied<bit Q, bit op, RegisterOperand vectype,
|
|
Operand immtype, dag opt_shift_iop,
|
|
string opt_shift, string asm, string kind,
|
|
list<dag> pattern>
|
|
: BaseSIMDModifiedImm<Q, op, (outs vectype:$dst),
|
|
!con((ins vectype:$Rd, immtype:$imm8), opt_shift_iop),
|
|
asm, "{\t$Rd" # kind # ", $imm8" # opt_shift #
|
|
"|" # kind # "\t$Rd, $imm8" # opt_shift # "}",
|
|
"$Rd = $dst", pattern> {
|
|
let DecoderMethod = "DecodeModImmTiedInstruction";
|
|
}
|
|
|
|
class BaseSIMDModifiedImmVectorShift<bit Q, bit op, bits<2> b15_b12,
|
|
RegisterOperand vectype, string asm,
|
|
string kind, list<dag> pattern>
|
|
: BaseSIMDModifiedImmVector<Q, op, vectype, imm0_255,
|
|
(ins logical_vec_shift:$shift),
|
|
"$shift", asm, kind, pattern> {
|
|
bits<2> shift;
|
|
let Inst{15} = b15_b12{1};
|
|
let Inst{14-13} = shift;
|
|
let Inst{12} = b15_b12{0};
|
|
}
|
|
|
|
class BaseSIMDModifiedImmVectorShiftTied<bit Q, bit op, bits<2> b15_b12,
|
|
RegisterOperand vectype, string asm,
|
|
string kind, list<dag> pattern>
|
|
: BaseSIMDModifiedImmVectorTied<Q, op, vectype, imm0_255,
|
|
(ins logical_vec_shift:$shift),
|
|
"$shift", asm, kind, pattern> {
|
|
bits<2> shift;
|
|
let Inst{15} = b15_b12{1};
|
|
let Inst{14-13} = shift;
|
|
let Inst{12} = b15_b12{0};
|
|
}
|
|
|
|
|
|
class BaseSIMDModifiedImmVectorShiftHalf<bit Q, bit op, bits<2> b15_b12,
|
|
RegisterOperand vectype, string asm,
|
|
string kind, list<dag> pattern>
|
|
: BaseSIMDModifiedImmVector<Q, op, vectype, imm0_255,
|
|
(ins logical_vec_hw_shift:$shift),
|
|
"$shift", asm, kind, pattern> {
|
|
bits<2> shift;
|
|
let Inst{15} = b15_b12{1};
|
|
let Inst{14} = 0;
|
|
let Inst{13} = shift{0};
|
|
let Inst{12} = b15_b12{0};
|
|
}
|
|
|
|
class BaseSIMDModifiedImmVectorShiftHalfTied<bit Q, bit op, bits<2> b15_b12,
|
|
RegisterOperand vectype, string asm,
|
|
string kind, list<dag> pattern>
|
|
: BaseSIMDModifiedImmVectorTied<Q, op, vectype, imm0_255,
|
|
(ins logical_vec_hw_shift:$shift),
|
|
"$shift", asm, kind, pattern> {
|
|
bits<2> shift;
|
|
let Inst{15} = b15_b12{1};
|
|
let Inst{14} = 0;
|
|
let Inst{13} = shift{0};
|
|
let Inst{12} = b15_b12{0};
|
|
}
|
|
|
|
multiclass SIMDModifiedImmVectorShift<bit op, bits<2> hw_cmode, bits<2> w_cmode,
|
|
string asm> {
|
|
def v4i16 : BaseSIMDModifiedImmVectorShiftHalf<0, op, hw_cmode, V64,
|
|
asm, ".4h", []>;
|
|
def v8i16 : BaseSIMDModifiedImmVectorShiftHalf<1, op, hw_cmode, V128,
|
|
asm, ".8h", []>;
|
|
|
|
def v2i32 : BaseSIMDModifiedImmVectorShift<0, op, w_cmode, V64,
|
|
asm, ".2s", []>;
|
|
def v4i32 : BaseSIMDModifiedImmVectorShift<1, op, w_cmode, V128,
|
|
asm, ".4s", []>;
|
|
}
|
|
|
|
multiclass SIMDModifiedImmVectorShiftTied<bit op, bits<2> hw_cmode,
|
|
bits<2> w_cmode, string asm,
|
|
SDNode OpNode> {
|
|
def v4i16 : BaseSIMDModifiedImmVectorShiftHalfTied<0, op, hw_cmode, V64,
|
|
asm, ".4h",
|
|
[(set (v4i16 V64:$dst), (OpNode V64:$Rd,
|
|
imm0_255:$imm8,
|
|
(i32 imm:$shift)))]>;
|
|
def v8i16 : BaseSIMDModifiedImmVectorShiftHalfTied<1, op, hw_cmode, V128,
|
|
asm, ".8h",
|
|
[(set (v8i16 V128:$dst), (OpNode V128:$Rd,
|
|
imm0_255:$imm8,
|
|
(i32 imm:$shift)))]>;
|
|
|
|
def v2i32 : BaseSIMDModifiedImmVectorShiftTied<0, op, w_cmode, V64,
|
|
asm, ".2s",
|
|
[(set (v2i32 V64:$dst), (OpNode V64:$Rd,
|
|
imm0_255:$imm8,
|
|
(i32 imm:$shift)))]>;
|
|
def v4i32 : BaseSIMDModifiedImmVectorShiftTied<1, op, w_cmode, V128,
|
|
asm, ".4s",
|
|
[(set (v4i32 V128:$dst), (OpNode V128:$Rd,
|
|
imm0_255:$imm8,
|
|
(i32 imm:$shift)))]>;
|
|
}
|
|
|
|
class SIMDModifiedImmMoveMSL<bit Q, bit op, bits<4> cmode,
|
|
RegisterOperand vectype, string asm,
|
|
string kind, list<dag> pattern>
|
|
: BaseSIMDModifiedImmVector<Q, op, vectype, imm0_255,
|
|
(ins move_vec_shift:$shift),
|
|
"$shift", asm, kind, pattern> {
|
|
bits<1> shift;
|
|
let Inst{15-13} = cmode{3-1};
|
|
let Inst{12} = shift;
|
|
}
|
|
|
|
class SIMDModifiedImmVectorNoShift<bit Q, bit op, bits<4> cmode,
|
|
RegisterOperand vectype,
|
|
Operand imm_type, string asm,
|
|
string kind, list<dag> pattern>
|
|
: BaseSIMDModifiedImmVector<Q, op, vectype, imm_type, (ins), "",
|
|
asm, kind, pattern> {
|
|
let Inst{15-12} = cmode;
|
|
}
|
|
|
|
class SIMDModifiedImmScalarNoShift<bit Q, bit op, bits<4> cmode, string asm,
|
|
list<dag> pattern>
|
|
: BaseSIMDModifiedImm<Q, op, (outs FPR64:$Rd), (ins simdimmtype10:$imm8), asm,
|
|
"\t$Rd, $imm8", "", pattern> {
|
|
let Inst{15-12} = cmode;
|
|
let DecoderMethod = "DecodeModImmInstruction";
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD indexed element
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDIndexed<bit Q, bit U, bit Scalar, bits<2> size, bits<4> opc,
|
|
RegisterOperand dst_reg, RegisterOperand lhs_reg,
|
|
RegisterOperand rhs_reg, Operand vec_idx, string asm,
|
|
string apple_kind, string dst_kind, string lhs_kind,
|
|
string rhs_kind, list<dag> pattern>
|
|
: I<(outs dst_reg:$Rd), (ins lhs_reg:$Rn, rhs_reg:$Rm, vec_idx:$idx),
|
|
asm,
|
|
"{\t$Rd" # dst_kind # ", $Rn" # lhs_kind # ", $Rm" # rhs_kind # "$idx" #
|
|
"|" # apple_kind # "\t$Rd, $Rn, $Rm$idx}", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28} = Scalar;
|
|
let Inst{27-24} = 0b1111;
|
|
let Inst{23-22} = size;
|
|
// Bit 21 must be set by the derived class.
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = opc;
|
|
// Bit 11 must be set by the derived class.
|
|
let Inst{10} = 0;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDIndexedTied<bit Q, bit U, bit Scalar, bits<2> size, bits<4> opc,
|
|
RegisterOperand dst_reg, RegisterOperand lhs_reg,
|
|
RegisterOperand rhs_reg, Operand vec_idx, string asm,
|
|
string apple_kind, string dst_kind, string lhs_kind,
|
|
string rhs_kind, list<dag> pattern>
|
|
: I<(outs dst_reg:$dst),
|
|
(ins dst_reg:$Rd, lhs_reg:$Rn, rhs_reg:$Rm, vec_idx:$idx), asm,
|
|
"{\t$Rd" # dst_kind # ", $Rn" # lhs_kind # ", $Rm" # rhs_kind # "$idx" #
|
|
"|" # apple_kind # "\t$Rd, $Rn, $Rm$idx}", "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28} = Scalar;
|
|
let Inst{27-24} = 0b1111;
|
|
let Inst{23-22} = size;
|
|
// Bit 21 must be set by the derived class.
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15-12} = opc;
|
|
// Bit 11 must be set by the derived class.
|
|
let Inst{10} = 0;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDFPIndexedSD<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v2i32_indexed : BaseSIMDIndexed<0, U, 0, 0b10, opc,
|
|
V64, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2s", ".2s", ".2s", ".s",
|
|
[(set (v2f32 V64:$Rd),
|
|
(OpNode (v2f32 V64:$Rn),
|
|
(v2f32 (ARM64duplane32 (v4f32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexed<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm, ".4s", ".4s", ".4s", ".s",
|
|
[(set (v4f32 V128:$Rd),
|
|
(OpNode (v4f32 V128:$Rn),
|
|
(v4f32 (ARM64duplane32 (v4f32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v2i64_indexed : BaseSIMDIndexed<1, U, 0, 0b11, opc,
|
|
V128, V128,
|
|
V128, VectorIndexD,
|
|
asm, ".2d", ".2d", ".2d", ".d",
|
|
[(set (v2f64 V128:$Rd),
|
|
(OpNode (v2f64 V128:$Rn),
|
|
(v2f64 (ARM64duplane64 (v2f64 V128:$Rm), VectorIndexD:$idx))))]> {
|
|
bits<1> idx;
|
|
let Inst{11} = idx{0};
|
|
let Inst{21} = 0;
|
|
}
|
|
|
|
def v1i32_indexed : BaseSIMDIndexed<1, U, 1, 0b10, opc,
|
|
FPR32Op, FPR32Op, V128, VectorIndexS,
|
|
asm, ".s", "", "", ".s",
|
|
[(set (f32 FPR32Op:$Rd),
|
|
(OpNode (f32 FPR32Op:$Rn),
|
|
(f32 (vector_extract (v4f32 V128:$Rm),
|
|
VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v1i64_indexed : BaseSIMDIndexed<1, U, 1, 0b11, opc,
|
|
FPR64Op, FPR64Op, V128, VectorIndexD,
|
|
asm, ".d", "", "", ".d",
|
|
[(set (f64 FPR64Op:$Rd),
|
|
(OpNode (f64 FPR64Op:$Rn),
|
|
(f64 (vector_extract (v2f64 V128:$Rm),
|
|
VectorIndexD:$idx))))]> {
|
|
bits<1> idx;
|
|
let Inst{11} = idx{0};
|
|
let Inst{21} = 0;
|
|
}
|
|
}
|
|
|
|
multiclass SIMDFPIndexedSDTiedPatterns<string INST, SDPatternOperator OpNode> {
|
|
// 2 variants for the .2s version: DUPLANE from 128-bit and DUP scalar.
|
|
def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
|
|
(ARM64duplane32 (v4f32 V128:$Rm),
|
|
VectorIndexS:$idx))),
|
|
(!cast<Instruction>(INST # v2i32_indexed)
|
|
V64:$Rd, V64:$Rn, V128:$Rm, VectorIndexS:$idx)>;
|
|
def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
|
|
(ARM64dup (f32 FPR32Op:$Rm)))),
|
|
(!cast<Instruction>(INST # "v2i32_indexed") V64:$Rd, V64:$Rn,
|
|
(SUBREG_TO_REG (i32 0), FPR32Op:$Rm, ssub), (i64 0))>;
|
|
|
|
|
|
// 2 variants for the .4s version: DUPLANE from 128-bit and DUP scalar.
|
|
def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
|
|
(ARM64duplane32 (v4f32 V128:$Rm),
|
|
VectorIndexS:$idx))),
|
|
(!cast<Instruction>(INST # "v4i32_indexed")
|
|
V128:$Rd, V128:$Rn, V128:$Rm, VectorIndexS:$idx)>;
|
|
def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
|
|
(ARM64dup (f32 FPR32Op:$Rm)))),
|
|
(!cast<Instruction>(INST # "v4i32_indexed") V128:$Rd, V128:$Rn,
|
|
(SUBREG_TO_REG (i32 0), FPR32Op:$Rm, ssub), (i64 0))>;
|
|
|
|
// 2 variants for the .2d version: DUPLANE from 128-bit and DUP scalar.
|
|
def : Pat<(v2f64 (OpNode (v2f64 V128:$Rd), (v2f64 V128:$Rn),
|
|
(ARM64duplane64 (v2f64 V128:$Rm),
|
|
VectorIndexD:$idx))),
|
|
(!cast<Instruction>(INST # "v2i64_indexed")
|
|
V128:$Rd, V128:$Rn, V128:$Rm, VectorIndexS:$idx)>;
|
|
def : Pat<(v2f64 (OpNode (v2f64 V128:$Rd), (v2f64 V128:$Rn),
|
|
(ARM64dup (f64 FPR64Op:$Rm)))),
|
|
(!cast<Instruction>(INST # "v2i64_indexed") V128:$Rd, V128:$Rn,
|
|
(SUBREG_TO_REG (i32 0), FPR64Op:$Rm, dsub), (i64 0))>;
|
|
|
|
// 2 variants for 32-bit scalar version: extract from .2s or from .4s
|
|
def : Pat<(f32 (OpNode (f32 FPR32:$Rd), (f32 FPR32:$Rn),
|
|
(vector_extract (v4f32 V128:$Rm), VectorIndexS:$idx))),
|
|
(!cast<Instruction>(INST # "v1i32_indexed") FPR32:$Rd, FPR32:$Rn,
|
|
V128:$Rm, VectorIndexS:$idx)>;
|
|
def : Pat<(f32 (OpNode (f32 FPR32:$Rd), (f32 FPR32:$Rn),
|
|
(vector_extract (v2f32 V64:$Rm), VectorIndexS:$idx))),
|
|
(!cast<Instruction>(INST # "v1i32_indexed") FPR32:$Rd, FPR32:$Rn,
|
|
(SUBREG_TO_REG (i32 0), V64:$Rm, dsub), VectorIndexS:$idx)>;
|
|
|
|
// 1 variant for 64-bit scalar version: extract from .1d or from .2d
|
|
def : Pat<(f64 (OpNode (f64 FPR64:$Rd), (f64 FPR64:$Rn),
|
|
(vector_extract (v2f64 V128:$Rm), VectorIndexD:$idx))),
|
|
(!cast<Instruction>(INST # "v1i64_indexed") FPR64:$Rd, FPR64:$Rn,
|
|
V128:$Rm, VectorIndexD:$idx)>;
|
|
}
|
|
|
|
multiclass SIMDFPIndexedSDTied<bit U, bits<4> opc, string asm> {
|
|
def v2i32_indexed : BaseSIMDIndexedTied<0, U, 0, 0b10, opc, V64, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2s", ".2s", ".2s", ".s", []> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexedTied<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm, ".4s", ".4s", ".4s", ".s", []> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v2i64_indexed : BaseSIMDIndexedTied<1, U, 0, 0b11, opc,
|
|
V128, V128,
|
|
V128, VectorIndexD,
|
|
asm, ".2d", ".2d", ".2d", ".d", []> {
|
|
bits<1> idx;
|
|
let Inst{11} = idx{0};
|
|
let Inst{21} = 0;
|
|
}
|
|
|
|
|
|
def v1i32_indexed : BaseSIMDIndexedTied<1, U, 1, 0b10, opc,
|
|
FPR32Op, FPR32Op, V128, VectorIndexS,
|
|
asm, ".s", "", "", ".s", []> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v1i64_indexed : BaseSIMDIndexedTied<1, U, 1, 0b11, opc,
|
|
FPR64Op, FPR64Op, V128, VectorIndexD,
|
|
asm, ".d", "", "", ".d", []> {
|
|
bits<1> idx;
|
|
let Inst{11} = idx{0};
|
|
let Inst{21} = 0;
|
|
}
|
|
}
|
|
|
|
multiclass SIMDIndexedHS<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v4i16_indexed : BaseSIMDIndexed<0, U, 0, 0b01, opc, V64, V64,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".4h", ".4h", ".4h", ".h",
|
|
[(set (v4i16 V64:$Rd),
|
|
(OpNode (v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v8i16_indexed : BaseSIMDIndexed<1, U, 0, 0b01, opc,
|
|
V128, V128,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".8h", ".8h", ".8h", ".h",
|
|
[(set (v8i16 V128:$Rd),
|
|
(OpNode (v8i16 V128:$Rn),
|
|
(v8i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v2i32_indexed : BaseSIMDIndexed<0, U, 0, 0b10, opc,
|
|
V64, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2s", ".2s", ".2s", ".s",
|
|
[(set (v2i32 V64:$Rd),
|
|
(OpNode (v2i32 V64:$Rn),
|
|
(v2i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexed<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm, ".4s", ".4s", ".4s", ".s",
|
|
[(set (v4i32 V128:$Rd),
|
|
(OpNode (v4i32 V128:$Rn),
|
|
(v4i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v1i16_indexed : BaseSIMDIndexed<1, U, 1, 0b01, opc,
|
|
FPR16Op, FPR16Op, V128_lo, VectorIndexH,
|
|
asm, ".h", "", "", ".h", []> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v1i32_indexed : BaseSIMDIndexed<1, U, 1, 0b10, opc,
|
|
FPR32Op, FPR32Op, V128, VectorIndexS,
|
|
asm, ".s", "", "", ".s",
|
|
[(set (i32 FPR32Op:$Rd),
|
|
(OpNode FPR32Op:$Rn,
|
|
(i32 (vector_extract (v4i32 V128:$Rm),
|
|
VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorIndexedHS<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v4i16_indexed : BaseSIMDIndexed<0, U, 0, 0b01, opc,
|
|
V64, V64,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".4h", ".4h", ".4h", ".h",
|
|
[(set (v4i16 V64:$Rd),
|
|
(OpNode (v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v8i16_indexed : BaseSIMDIndexed<1, U, 0, 0b01, opc,
|
|
V128, V128,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".8h", ".8h", ".8h", ".h",
|
|
[(set (v8i16 V128:$Rd),
|
|
(OpNode (v8i16 V128:$Rn),
|
|
(v8i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v2i32_indexed : BaseSIMDIndexed<0, U, 0, 0b10, opc,
|
|
V64, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2s", ".2s", ".2s", ".s",
|
|
[(set (v2i32 V64:$Rd),
|
|
(OpNode (v2i32 V64:$Rn),
|
|
(v2i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexed<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm, ".4s", ".4s", ".4s", ".s",
|
|
[(set (v4i32 V128:$Rd),
|
|
(OpNode (v4i32 V128:$Rn),
|
|
(v4i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorIndexedHSTied<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v4i16_indexed : BaseSIMDIndexedTied<0, U, 0, 0b01, opc, V64, V64,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".4h", ".4h", ".4h", ".h",
|
|
[(set (v4i16 V64:$dst),
|
|
(OpNode (v4i16 V64:$Rd),(v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v8i16_indexed : BaseSIMDIndexedTied<1, U, 0, 0b01, opc,
|
|
V128, V128,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".8h", ".8h", ".8h", ".h",
|
|
[(set (v8i16 V128:$dst),
|
|
(OpNode (v8i16 V128:$Rd), (v8i16 V128:$Rn),
|
|
(v8i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v2i32_indexed : BaseSIMDIndexedTied<0, U, 0, 0b10, opc,
|
|
V64, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2s", ".2s", ".2s", ".s",
|
|
[(set (v2i32 V64:$dst),
|
|
(OpNode (v2i32 V64:$Rd), (v2i32 V64:$Rn),
|
|
(v2i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexedTied<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm, ".4s", ".4s", ".4s", ".s",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i32 V128:$Rn),
|
|
(v4i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDIndexedLongSD<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v4i16_indexed : BaseSIMDIndexed<0, U, 0, 0b01, opc,
|
|
V128, V64,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".4s", ".4s", ".4h", ".h",
|
|
[(set (v4i32 V128:$Rd),
|
|
(OpNode (v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v8i16_indexed : BaseSIMDIndexed<1, U, 0, 0b01, opc,
|
|
V128, V128,
|
|
V128_lo, VectorIndexH,
|
|
asm#"2", ".4s", ".4s", ".8h", ".h",
|
|
[(set (v4i32 V128:$Rd),
|
|
(OpNode (extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 (ARM64duplane16 (v8i16 V128_lo:$Rm),
|
|
VectorIndexH:$idx))))]> {
|
|
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v2i32_indexed : BaseSIMDIndexed<0, U, 0, 0b10, opc,
|
|
V128, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2d", ".2d", ".2s", ".s",
|
|
[(set (v2i64 V128:$Rd),
|
|
(OpNode (v2i32 V64:$Rn),
|
|
(v2i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexed<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm#"2", ".2d", ".2d", ".4s", ".s",
|
|
[(set (v2i64 V128:$Rd),
|
|
(OpNode (extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 (ARM64duplane32 (v4i32 V128:$Rm),
|
|
VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v1i32_indexed : BaseSIMDIndexed<1, U, 1, 0b01, opc,
|
|
FPR32Op, FPR16Op, V128_lo, VectorIndexH,
|
|
asm, ".h", "", "", ".h", []> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v1i64_indexed : BaseSIMDIndexed<1, U, 1, 0b10, opc,
|
|
FPR64Op, FPR32Op, V128, VectorIndexS,
|
|
asm, ".s", "", "", ".s", []> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDIndexedLongSQDMLXSDTied<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator Accum> {
|
|
def v4i16_indexed : BaseSIMDIndexedTied<0, U, 0, 0b01, opc,
|
|
V128, V64,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".4s", ".4s", ".4h", ".h",
|
|
[(set (v4i32 V128:$dst),
|
|
(Accum (v4i32 V128:$Rd),
|
|
(v4i32 (int_arm64_neon_sqdmull
|
|
(v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm),
|
|
VectorIndexH:$idx))))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
// FIXME: it would be nice to use the scalar (v1i32) instruction here, but an
|
|
// intermediate EXTRACT_SUBREG would be untyped.
|
|
def : Pat<(i32 (Accum (i32 FPR32Op:$Rd),
|
|
(i32 (vector_extract (v4i32
|
|
(int_arm64_neon_sqdmull (v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm),
|
|
VectorIndexH:$idx)))),
|
|
(i64 0))))),
|
|
(EXTRACT_SUBREG
|
|
(!cast<Instruction>(NAME # v4i16_indexed)
|
|
(SUBREG_TO_REG (i32 0), FPR32Op:$Rd, ssub), V64:$Rn,
|
|
V128_lo:$Rm, VectorIndexH:$idx),
|
|
ssub)>;
|
|
|
|
def v8i16_indexed : BaseSIMDIndexedTied<1, U, 0, 0b01, opc,
|
|
V128, V128,
|
|
V128_lo, VectorIndexH,
|
|
asm#"2", ".4s", ".4s", ".8h", ".h",
|
|
[(set (v4i32 V128:$dst),
|
|
(Accum (v4i32 V128:$Rd),
|
|
(v4i32 (int_arm64_neon_sqdmull
|
|
(extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16
|
|
(ARM64duplane16 (v8i16 V128_lo:$Rm),
|
|
VectorIndexH:$idx))))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v2i32_indexed : BaseSIMDIndexedTied<0, U, 0, 0b10, opc,
|
|
V128, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2d", ".2d", ".2s", ".s",
|
|
[(set (v2i64 V128:$dst),
|
|
(Accum (v2i64 V128:$Rd),
|
|
(v2i64 (int_arm64_neon_sqdmull
|
|
(v2i32 V64:$Rn),
|
|
(v2i32 (ARM64duplane32 (v4i32 V128:$Rm),
|
|
VectorIndexS:$idx))))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexedTied<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm#"2", ".2d", ".2d", ".4s", ".s",
|
|
[(set (v2i64 V128:$dst),
|
|
(Accum (v2i64 V128:$Rd),
|
|
(v2i64 (int_arm64_neon_sqdmull
|
|
(extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32
|
|
(ARM64duplane32 (v4i32 V128:$Rm),
|
|
VectorIndexS:$idx))))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v1i32_indexed : BaseSIMDIndexedTied<1, U, 1, 0b01, opc,
|
|
FPR32Op, FPR16Op, V128_lo, VectorIndexH,
|
|
asm, ".h", "", "", ".h", []> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
|
|
def v1i64_indexed : BaseSIMDIndexedTied<1, U, 1, 0b10, opc,
|
|
FPR64Op, FPR32Op, V128, VectorIndexS,
|
|
asm, ".s", "", "", ".s",
|
|
[(set (i64 FPR64Op:$dst),
|
|
(Accum (i64 FPR64Op:$Rd),
|
|
(i64 (int_arm64_neon_sqdmulls_scalar
|
|
(i32 FPR32Op:$Rn),
|
|
(i32 (vector_extract (v4i32 V128:$Rm),
|
|
VectorIndexS:$idx))))))]> {
|
|
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorIndexedLongSD<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in {
|
|
def v4i16_indexed : BaseSIMDIndexed<0, U, 0, 0b01, opc,
|
|
V128, V64,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".4s", ".4s", ".4h", ".h",
|
|
[(set (v4i32 V128:$Rd),
|
|
(OpNode (v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v8i16_indexed : BaseSIMDIndexed<1, U, 0, 0b01, opc,
|
|
V128, V128,
|
|
V128_lo, VectorIndexH,
|
|
asm#"2", ".4s", ".4s", ".8h", ".h",
|
|
[(set (v4i32 V128:$Rd),
|
|
(OpNode (extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 (ARM64duplane16 (v8i16 V128_lo:$Rm),
|
|
VectorIndexH:$idx))))]> {
|
|
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v2i32_indexed : BaseSIMDIndexed<0, U, 0, 0b10, opc,
|
|
V128, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2d", ".2d", ".2s", ".s",
|
|
[(set (v2i64 V128:$Rd),
|
|
(OpNode (v2i32 V64:$Rn),
|
|
(v2i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexed<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm#"2", ".2d", ".2d", ".4s", ".s",
|
|
[(set (v2i64 V128:$Rd),
|
|
(OpNode (extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 (ARM64duplane32 (v4i32 V128:$Rm),
|
|
VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorIndexedLongSDTied<bit U, bits<4> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in {
|
|
def v4i16_indexed : BaseSIMDIndexedTied<0, U, 0, 0b01, opc,
|
|
V128, V64,
|
|
V128_lo, VectorIndexH,
|
|
asm, ".4s", ".4s", ".4h", ".h",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i16 V64:$Rn),
|
|
(v4i16 (ARM64duplane16 (v8i16 V128_lo:$Rm), VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v8i16_indexed : BaseSIMDIndexedTied<1, U, 0, 0b01, opc,
|
|
V128, V128,
|
|
V128_lo, VectorIndexH,
|
|
asm#"2", ".4s", ".4s", ".8h", ".h",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd),
|
|
(extract_high_v8i16 V128:$Rn),
|
|
(extract_high_v8i16 (ARM64duplane16 (v8i16 V128_lo:$Rm),
|
|
VectorIndexH:$idx))))]> {
|
|
bits<3> idx;
|
|
let Inst{11} = idx{2};
|
|
let Inst{21} = idx{1};
|
|
let Inst{20} = idx{0};
|
|
}
|
|
|
|
def v2i32_indexed : BaseSIMDIndexedTied<0, U, 0, 0b10, opc,
|
|
V128, V64,
|
|
V128, VectorIndexS,
|
|
asm, ".2d", ".2d", ".2s", ".s",
|
|
[(set (v2i64 V128:$dst),
|
|
(OpNode (v2i64 V128:$Rd), (v2i32 V64:$Rn),
|
|
(v2i32 (ARM64duplane32 (v4i32 V128:$Rm), VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
|
|
def v4i32_indexed : BaseSIMDIndexedTied<1, U, 0, 0b10, opc,
|
|
V128, V128,
|
|
V128, VectorIndexS,
|
|
asm#"2", ".2d", ".2d", ".4s", ".s",
|
|
[(set (v2i64 V128:$dst),
|
|
(OpNode (v2i64 V128:$Rd),
|
|
(extract_high_v4i32 V128:$Rn),
|
|
(extract_high_v4i32 (ARM64duplane32 (v4i32 V128:$Rm),
|
|
VectorIndexS:$idx))))]> {
|
|
bits<2> idx;
|
|
let Inst{11} = idx{1};
|
|
let Inst{21} = idx{0};
|
|
}
|
|
}
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD scalar shift by immediate
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseSIMDScalarShift<bit U, bits<5> opc, bits<7> fixed_imm,
|
|
RegisterClass regtype1, RegisterClass regtype2,
|
|
Operand immtype, string asm, list<dag> pattern>
|
|
: I<(outs regtype1:$Rd), (ins regtype2:$Rn, immtype:$imm),
|
|
asm, "\t$Rd, $Rn, $imm", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<7> imm;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-23} = 0b111110;
|
|
let Inst{22-16} = fixed_imm;
|
|
let Inst{15-11} = opc;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseSIMDScalarShiftTied<bit U, bits<5> opc, bits<7> fixed_imm,
|
|
RegisterClass regtype1, RegisterClass regtype2,
|
|
Operand immtype, string asm, list<dag> pattern>
|
|
: I<(outs regtype1:$dst), (ins regtype1:$Rd, regtype2:$Rn, immtype:$imm),
|
|
asm, "\t$Rd, $Rn, $imm", "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<7> imm;
|
|
let Inst{31-30} = 0b01;
|
|
let Inst{29} = U;
|
|
let Inst{28-23} = 0b111110;
|
|
let Inst{22-16} = fixed_imm;
|
|
let Inst{15-11} = opc;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
|
|
multiclass SIMDScalarRShiftSD<bit U, bits<5> opc, string asm> {
|
|
def s : BaseSIMDScalarShift<U, opc, {0,1,?,?,?,?,?},
|
|
FPR32, FPR32, vecshiftR32, asm, []> {
|
|
let Inst{20-16} = imm{4-0};
|
|
}
|
|
|
|
def d : BaseSIMDScalarShift<U, opc, {1,?,?,?,?,?,?},
|
|
FPR64, FPR64, vecshiftR64, asm, []> {
|
|
let Inst{21-16} = imm{5-0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDScalarRShiftD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def d : BaseSIMDScalarShift<U, opc, {1,?,?,?,?,?,?},
|
|
FPR64, FPR64, vecshiftR64, asm,
|
|
[(set (i64 FPR64:$Rd),
|
|
(OpNode (i64 FPR64:$Rn), (i32 vecshiftR64:$imm)))]> {
|
|
let Inst{21-16} = imm{5-0};
|
|
}
|
|
|
|
def : Pat<(v1i64 (OpNode (v1i64 FPR64:$Rn), (i32 vecshiftR64:$imm))),
|
|
(!cast<Instruction>(NAME # "d") FPR64:$Rn, vecshiftR64:$imm)>;
|
|
}
|
|
|
|
multiclass SIMDScalarRShiftDTied<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def d : BaseSIMDScalarShiftTied<U, opc, {1,?,?,?,?,?,?},
|
|
FPR64, FPR64, vecshiftR64, asm,
|
|
[(set (i64 FPR64:$dst), (OpNode (i64 FPR64:$Rd), (i64 FPR64:$Rn),
|
|
(i32 vecshiftR64:$imm)))]> {
|
|
let Inst{21-16} = imm{5-0};
|
|
}
|
|
|
|
def : Pat<(v1i64 (OpNode (v1i64 FPR64:$Rd), (v1i64 FPR64:$Rn),
|
|
(i32 vecshiftR64:$imm))),
|
|
(!cast<Instruction>(NAME # "d") FPR64:$Rd, FPR64:$Rn,
|
|
vecshiftR64:$imm)>;
|
|
}
|
|
|
|
multiclass SIMDScalarLShiftD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def d : BaseSIMDScalarShift<U, opc, {1,?,?,?,?,?,?},
|
|
FPR64, FPR64, vecshiftL64, asm,
|
|
[(set (v1i64 FPR64:$Rd),
|
|
(OpNode (v1i64 FPR64:$Rn), (i32 vecshiftL64:$imm)))]> {
|
|
let Inst{21-16} = imm{5-0};
|
|
}
|
|
}
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
multiclass SIMDScalarLShiftDTied<bit U, bits<5> opc, string asm> {
|
|
def d : BaseSIMDScalarShiftTied<U, opc, {1,?,?,?,?,?,?},
|
|
FPR64, FPR64, vecshiftL64, asm, []> {
|
|
let Inst{21-16} = imm{5-0};
|
|
}
|
|
}
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
multiclass SIMDScalarRShiftBHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def b : BaseSIMDScalarShift<U, opc, {0,0,0,1,?,?,?},
|
|
FPR8, FPR16, vecshiftR8, asm, []> {
|
|
let Inst{18-16} = imm{2-0};
|
|
}
|
|
|
|
def h : BaseSIMDScalarShift<U, opc, {0,0,1,?,?,?,?},
|
|
FPR16, FPR32, vecshiftR16, asm, []> {
|
|
let Inst{19-16} = imm{3-0};
|
|
}
|
|
|
|
def s : BaseSIMDScalarShift<U, opc, {0,1,?,?,?,?,?},
|
|
FPR32, FPR64, vecshiftR32, asm,
|
|
[(set (i32 FPR32:$Rd), (OpNode (i64 FPR64:$Rn), vecshiftR32:$imm))]> {
|
|
let Inst{20-16} = imm{4-0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDScalarLShiftBHSD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def b : BaseSIMDScalarShift<U, opc, {0,0,0,1,?,?,?},
|
|
FPR8, FPR8, vecshiftL8, asm, []> {
|
|
let Inst{18-16} = imm{2-0};
|
|
}
|
|
|
|
def h : BaseSIMDScalarShift<U, opc, {0,0,1,?,?,?,?},
|
|
FPR16, FPR16, vecshiftL16, asm, []> {
|
|
let Inst{19-16} = imm{3-0};
|
|
}
|
|
|
|
def s : BaseSIMDScalarShift<U, opc, {0,1,?,?,?,?,?},
|
|
FPR32, FPR32, vecshiftL32, asm,
|
|
[(set (i32 FPR32:$Rd), (OpNode (i32 FPR32:$Rn), (i32 vecshiftL32:$imm)))]> {
|
|
let Inst{20-16} = imm{4-0};
|
|
}
|
|
|
|
def d : BaseSIMDScalarShift<U, opc, {1,?,?,?,?,?,?},
|
|
FPR64, FPR64, vecshiftL64, asm,
|
|
[(set (v1i64 FPR64:$Rd), (OpNode (v1i64 FPR64:$Rn),
|
|
(i32 vecshiftL64:$imm)))]> {
|
|
let Inst{21-16} = imm{5-0};
|
|
}
|
|
}
|
|
|
|
multiclass SIMDScalarRShiftBHSD<bit U, bits<5> opc, string asm> {
|
|
def b : BaseSIMDScalarShift<U, opc, {0,0,0,1,?,?,?},
|
|
FPR8, FPR8, vecshiftR8, asm, []> {
|
|
let Inst{18-16} = imm{2-0};
|
|
}
|
|
|
|
def h : BaseSIMDScalarShift<U, opc, {0,0,1,?,?,?,?},
|
|
FPR16, FPR16, vecshiftR16, asm, []> {
|
|
let Inst{19-16} = imm{3-0};
|
|
}
|
|
|
|
def s : BaseSIMDScalarShift<U, opc, {0,1,?,?,?,?,?},
|
|
FPR32, FPR32, vecshiftR32, asm, []> {
|
|
let Inst{20-16} = imm{4-0};
|
|
}
|
|
|
|
def d : BaseSIMDScalarShift<U, opc, {1,?,?,?,?,?,?},
|
|
FPR64, FPR64, vecshiftR64, asm, []> {
|
|
let Inst{21-16} = imm{5-0};
|
|
}
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// AdvSIMD vector x indexed element
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseSIMDVectorShift<bit Q, bit U, bits<5> opc, bits<7> fixed_imm,
|
|
RegisterOperand dst_reg, RegisterOperand src_reg,
|
|
Operand immtype,
|
|
string asm, string dst_kind, string src_kind,
|
|
list<dag> pattern>
|
|
: I<(outs dst_reg:$Rd), (ins src_reg:$Rn, immtype:$imm),
|
|
asm, "{\t$Rd" # dst_kind # ", $Rn" # src_kind # ", $imm" #
|
|
"|" # dst_kind # "\t$Rd, $Rn, $imm}", "", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-23} = 0b011110;
|
|
let Inst{22-16} = fixed_imm;
|
|
let Inst{15-11} = opc;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let mayStore = 0, mayLoad = 0, hasSideEffects = 0 in
|
|
class BaseSIMDVectorShiftTied<bit Q, bit U, bits<5> opc, bits<7> fixed_imm,
|
|
RegisterOperand vectype1, RegisterOperand vectype2,
|
|
Operand immtype,
|
|
string asm, string dst_kind, string src_kind,
|
|
list<dag> pattern>
|
|
: I<(outs vectype1:$dst), (ins vectype1:$Rd, vectype2:$Rn, immtype:$imm),
|
|
asm, "{\t$Rd" # dst_kind # ", $Rn" # src_kind # ", $imm" #
|
|
"|" # dst_kind # "\t$Rd, $Rn, $imm}", "$Rd = $dst", pattern>,
|
|
Sched<[WriteV]> {
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29} = U;
|
|
let Inst{28-23} = 0b011110;
|
|
let Inst{22-16} = fixed_imm;
|
|
let Inst{15-11} = opc;
|
|
let Inst{10} = 1;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
multiclass SIMDVectorRShiftSD<bit U, bits<5> opc, string asm,
|
|
Intrinsic OpNode> {
|
|
def v2i32_shift : BaseSIMDVectorShift<0, U, opc, {0,1,?,?,?,?,?},
|
|
V64, V64, vecshiftR32,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2f32 V64:$Rn), (i32 imm:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShift<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftR32,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4f32 V128:$Rn), (i32 imm:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v2i64_shift : BaseSIMDVectorShift<1, U, opc, {1,?,?,?,?,?,?},
|
|
V128, V128, vecshiftR64,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2f64 V128:$Rn), (i32 imm:$imm)))]> {
|
|
bits<6> imm;
|
|
let Inst{21-16} = imm;
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorRShiftSDToFP<bit U, bits<5> opc, string asm,
|
|
Intrinsic OpNode> {
|
|
def v2i32_shift : BaseSIMDVectorShift<0, U, opc, {0,1,?,?,?,?,?},
|
|
V64, V64, vecshiftR32,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2f32 V64:$Rd), (OpNode (v2i32 V64:$Rn), (i32 imm:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShift<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftR32,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4f32 V128:$Rd), (OpNode (v4i32 V128:$Rn), (i32 imm:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v2i64_shift : BaseSIMDVectorShift<1, U, opc, {1,?,?,?,?,?,?},
|
|
V128, V128, vecshiftR64,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2f64 V128:$Rd), (OpNode (v2i64 V128:$Rn), (i32 imm:$imm)))]> {
|
|
bits<6> imm;
|
|
let Inst{21-16} = imm;
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorRShiftNarrowBHS<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_shift : BaseSIMDVectorShift<0, U, opc, {0,0,0,1,?,?,?},
|
|
V64, V128, vecshiftR16Narrow,
|
|
asm, ".8b", ".8h",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i16 V128:$Rn), vecshiftR16Narrow:$imm))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v16i8_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,0,0,1,?,?,?},
|
|
V128, V128, vecshiftR16Narrow,
|
|
asm#"2", ".16b", ".8h", []> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
def v4i16_shift : BaseSIMDVectorShift<0, U, opc, {0,0,1,?,?,?,?},
|
|
V64, V128, vecshiftR32Narrow,
|
|
asm, ".4h", ".4s",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i32 V128:$Rn), vecshiftR32Narrow:$imm))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v8i16_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,0,1,?,?,?,?},
|
|
V128, V128, vecshiftR32Narrow,
|
|
asm#"2", ".8h", ".4s", []> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
def v2i32_shift : BaseSIMDVectorShift<0, U, opc, {0,1,?,?,?,?,?},
|
|
V64, V128, vecshiftR64Narrow,
|
|
asm, ".2s", ".2d",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i64 V128:$Rn), vecshiftR64Narrow:$imm))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftR64Narrow,
|
|
asm#"2", ".4s", ".2d", []> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
// TableGen doesn't like patters w/ INSERT_SUBREG on the instructions
|
|
// themselves, so put them here instead.
|
|
|
|
// Patterns involving what's effectively an insert high and a normal
|
|
// intrinsic, represented by CONCAT_VECTORS.
|
|
def : Pat<(concat_vectors (v8i8 V64:$Rd),(OpNode (v8i16 V128:$Rn),
|
|
vecshiftR16Narrow:$imm)),
|
|
(!cast<Instruction>(NAME # "v16i8_shift")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
|
|
V128:$Rn, vecshiftR16Narrow:$imm)>;
|
|
def : Pat<(concat_vectors (v4i16 V64:$Rd), (OpNode (v4i32 V128:$Rn),
|
|
vecshiftR32Narrow:$imm)),
|
|
(!cast<Instruction>(NAME # "v8i16_shift")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
|
|
V128:$Rn, vecshiftR32Narrow:$imm)>;
|
|
def : Pat<(concat_vectors (v2i32 V64:$Rd), (OpNode (v2i64 V128:$Rn),
|
|
vecshiftR64Narrow:$imm)),
|
|
(!cast<Instruction>(NAME # "v4i32_shift")
|
|
(INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
|
|
V128:$Rn, vecshiftR64Narrow:$imm)>;
|
|
}
|
|
|
|
multiclass SIMDVectorLShiftBHSD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_shift : BaseSIMDVectorShift<0, U, opc, {0,0,0,1,?,?,?},
|
|
V64, V64, vecshiftL8,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i8 V64:$Rn),
|
|
(i32 vecshiftL8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v16i8_shift : BaseSIMDVectorShift<1, U, opc, {0,0,0,1,?,?,?},
|
|
V128, V128, vecshiftL8,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode (v16i8 V128:$Rn),
|
|
(i32 vecshiftL8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v4i16_shift : BaseSIMDVectorShift<0, U, opc, {0,0,1,?,?,?,?},
|
|
V64, V64, vecshiftL16,
|
|
asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i16 V64:$Rn),
|
|
(i32 vecshiftL16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v8i16_shift : BaseSIMDVectorShift<1, U, opc, {0,0,1,?,?,?,?},
|
|
V128, V128, vecshiftL16,
|
|
asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn),
|
|
(i32 vecshiftL16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v2i32_shift : BaseSIMDVectorShift<0, U, opc, {0,1,?,?,?,?,?},
|
|
V64, V64, vecshiftL32,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i32 V64:$Rn),
|
|
(i32 vecshiftL32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShift<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftL32,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn),
|
|
(i32 vecshiftL32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v2i64_shift : BaseSIMDVectorShift<1, U, opc, {1,?,?,?,?,?,?},
|
|
V128, V128, vecshiftL64,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i64 V128:$Rn),
|
|
(i32 vecshiftL64:$imm)))]> {
|
|
bits<6> imm;
|
|
let Inst{21-16} = imm;
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorRShiftBHSD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_shift : BaseSIMDVectorShift<0, U, opc, {0,0,0,1,?,?,?},
|
|
V64, V64, vecshiftR8,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$Rd), (OpNode (v8i8 V64:$Rn),
|
|
(i32 vecshiftR8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v16i8_shift : BaseSIMDVectorShift<1, U, opc, {0,0,0,1,?,?,?},
|
|
V128, V128, vecshiftR8,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$Rd), (OpNode (v16i8 V128:$Rn),
|
|
(i32 vecshiftR8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v4i16_shift : BaseSIMDVectorShift<0, U, opc, {0,0,1,?,?,?,?},
|
|
V64, V64, vecshiftR16,
|
|
asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$Rd), (OpNode (v4i16 V64:$Rn),
|
|
(i32 vecshiftR16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v8i16_shift : BaseSIMDVectorShift<1, U, opc, {0,0,1,?,?,?,?},
|
|
V128, V128, vecshiftR16,
|
|
asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i16 V128:$Rn),
|
|
(i32 vecshiftR16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v2i32_shift : BaseSIMDVectorShift<0, U, opc, {0,1,?,?,?,?,?},
|
|
V64, V64, vecshiftR32,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$Rd), (OpNode (v2i32 V64:$Rn),
|
|
(i32 vecshiftR32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShift<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftR32,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i32 V128:$Rn),
|
|
(i32 vecshiftR32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v2i64_shift : BaseSIMDVectorShift<1, U, opc, {1,?,?,?,?,?,?},
|
|
V128, V128, vecshiftR64,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i64 V128:$Rn),
|
|
(i32 vecshiftR64:$imm)))]> {
|
|
bits<6> imm;
|
|
let Inst{21-16} = imm;
|
|
}
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDVectorRShiftBHSDTied<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v8i8_shift : BaseSIMDVectorShiftTied<0, U, opc, {0,0,0,1,?,?,?},
|
|
V64, V64, vecshiftR8, asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$dst),
|
|
(OpNode (v8i8 V64:$Rd), (v8i8 V64:$Rn),
|
|
(i32 vecshiftR8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v16i8_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,0,0,1,?,?,?},
|
|
V128, V128, vecshiftR8, asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$dst),
|
|
(OpNode (v16i8 V128:$Rd), (v16i8 V128:$Rn),
|
|
(i32 vecshiftR8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v4i16_shift : BaseSIMDVectorShiftTied<0, U, opc, {0,0,1,?,?,?,?},
|
|
V64, V64, vecshiftR16, asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$dst),
|
|
(OpNode (v4i16 V64:$Rd), (v4i16 V64:$Rn),
|
|
(i32 vecshiftR16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v8i16_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,0,1,?,?,?,?},
|
|
V128, V128, vecshiftR16, asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$dst),
|
|
(OpNode (v8i16 V128:$Rd), (v8i16 V128:$Rn),
|
|
(i32 vecshiftR16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v2i32_shift : BaseSIMDVectorShiftTied<0, U, opc, {0,1,?,?,?,?,?},
|
|
V64, V64, vecshiftR32, asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$dst),
|
|
(OpNode (v2i32 V64:$Rd), (v2i32 V64:$Rn),
|
|
(i32 vecshiftR32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftR32, asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i32 V128:$Rn),
|
|
(i32 vecshiftR32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v2i64_shift : BaseSIMDVectorShiftTied<1, U, opc, {1,?,?,?,?,?,?},
|
|
V128, V128, vecshiftR64,
|
|
asm, ".2d", ".2d", [(set (v2i64 V128:$dst),
|
|
(OpNode (v2i64 V128:$Rd), (v2i64 V128:$Rn),
|
|
(i32 vecshiftR64:$imm)))]> {
|
|
bits<6> imm;
|
|
let Inst{21-16} = imm;
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorLShiftBHSDTied<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode = null_frag> {
|
|
def v8i8_shift : BaseSIMDVectorShiftTied<0, U, opc, {0,0,0,1,?,?,?},
|
|
V64, V64, vecshiftL8,
|
|
asm, ".8b", ".8b",
|
|
[(set (v8i8 V64:$dst),
|
|
(OpNode (v8i8 V64:$Rd), (v8i8 V64:$Rn),
|
|
(i32 vecshiftL8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v16i8_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,0,0,1,?,?,?},
|
|
V128, V128, vecshiftL8,
|
|
asm, ".16b", ".16b",
|
|
[(set (v16i8 V128:$dst),
|
|
(OpNode (v16i8 V128:$Rd), (v16i8 V128:$Rn),
|
|
(i32 vecshiftL8:$imm)))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v4i16_shift : BaseSIMDVectorShiftTied<0, U, opc, {0,0,1,?,?,?,?},
|
|
V64, V64, vecshiftL16,
|
|
asm, ".4h", ".4h",
|
|
[(set (v4i16 V64:$dst),
|
|
(OpNode (v4i16 V64:$Rd), (v4i16 V64:$Rn),
|
|
(i32 vecshiftL16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v8i16_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,0,1,?,?,?,?},
|
|
V128, V128, vecshiftL16,
|
|
asm, ".8h", ".8h",
|
|
[(set (v8i16 V128:$dst),
|
|
(OpNode (v8i16 V128:$Rd), (v8i16 V128:$Rn),
|
|
(i32 vecshiftL16:$imm)))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v2i32_shift : BaseSIMDVectorShiftTied<0, U, opc, {0,1,?,?,?,?,?},
|
|
V64, V64, vecshiftL32,
|
|
asm, ".2s", ".2s",
|
|
[(set (v2i32 V64:$dst),
|
|
(OpNode (v2i32 V64:$Rd), (v2i32 V64:$Rn),
|
|
(i32 vecshiftL32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShiftTied<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftL32,
|
|
asm, ".4s", ".4s",
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i32 V128:$Rn),
|
|
(i32 vecshiftL32:$imm)))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v2i64_shift : BaseSIMDVectorShiftTied<1, U, opc, {1,?,?,?,?,?,?},
|
|
V128, V128, vecshiftL64,
|
|
asm, ".2d", ".2d",
|
|
[(set (v2i64 V128:$dst),
|
|
(OpNode (v2i64 V128:$Rd), (v2i64 V128:$Rn),
|
|
(i32 vecshiftL64:$imm)))]> {
|
|
bits<6> imm;
|
|
let Inst{21-16} = imm;
|
|
}
|
|
}
|
|
|
|
multiclass SIMDVectorLShiftLongBHSD<bit U, bits<5> opc, string asm,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8_shift : BaseSIMDVectorShift<0, U, opc, {0,0,0,1,?,?,?},
|
|
V128, V64, vecshiftL8, asm, ".8h", ".8b",
|
|
[(set (v8i16 V128:$Rd), (OpNode (v8i8 V64:$Rn), vecshiftL8:$imm))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v16i8_shift : BaseSIMDVectorShift<1, U, opc, {0,0,0,1,?,?,?},
|
|
V128, V128, vecshiftL8,
|
|
asm#"2", ".8h", ".16b",
|
|
[(set (v8i16 V128:$Rd),
|
|
(OpNode (extract_high_v16i8 V128:$Rn), vecshiftL8:$imm))]> {
|
|
bits<3> imm;
|
|
let Inst{18-16} = imm;
|
|
}
|
|
|
|
def v4i16_shift : BaseSIMDVectorShift<0, U, opc, {0,0,1,?,?,?,?},
|
|
V128, V64, vecshiftL16, asm, ".4s", ".4h",
|
|
[(set (v4i32 V128:$Rd), (OpNode (v4i16 V64:$Rn), vecshiftL16:$imm))]> {
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v8i16_shift : BaseSIMDVectorShift<1, U, opc, {0,0,1,?,?,?,?},
|
|
V128, V128, vecshiftL16,
|
|
asm#"2", ".4s", ".8h",
|
|
[(set (v4i32 V128:$Rd),
|
|
(OpNode (extract_high_v8i16 V128:$Rn), vecshiftL16:$imm))]> {
|
|
|
|
bits<4> imm;
|
|
let Inst{19-16} = imm;
|
|
}
|
|
|
|
def v2i32_shift : BaseSIMDVectorShift<0, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V64, vecshiftL32, asm, ".2d", ".2s",
|
|
[(set (v2i64 V128:$Rd), (OpNode (v2i32 V64:$Rn), vecshiftL32:$imm))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
|
|
def v4i32_shift : BaseSIMDVectorShift<1, U, opc, {0,1,?,?,?,?,?},
|
|
V128, V128, vecshiftL32,
|
|
asm#"2", ".2d", ".4s",
|
|
[(set (v2i64 V128:$Rd),
|
|
(OpNode (extract_high_v4i32 V128:$Rn), vecshiftL32:$imm))]> {
|
|
bits<5> imm;
|
|
let Inst{20-16} = imm;
|
|
}
|
|
}
|
|
|
|
|
|
//---
|
|
// Vector load/store
|
|
//---
|
|
// SIMD ldX/stX no-index memory references don't allow the optional
|
|
// ", #0" constant and handle post-indexing explicitly, so we use
|
|
// a more specialized parse method for them. Otherwise, it's the same as
|
|
// the general am_noindex handling.
|
|
def MemorySIMDNoIndexOperand : AsmOperandClass {
|
|
let Name = "MemorySIMDNoIndex";
|
|
let ParserMethod = "tryParseNoIndexMemory";
|
|
}
|
|
def am_simdnoindex : Operand<i64>,
|
|
ComplexPattern<i64, 1, "SelectAddrModeNoIndex", []> {
|
|
let PrintMethod = "printAMNoIndex";
|
|
let ParserMatchClass = MemorySIMDNoIndexOperand;
|
|
let MIOperandInfo = (ops GPR64sp:$base);
|
|
let DecoderMethod = "DecodeGPR64spRegisterClass";
|
|
}
|
|
|
|
class BaseSIMDLdSt<bit Q, bit L, bits<4> opcode, bits<2> size,
|
|
string asm, dag oops, dag iops, list<dag> pattern>
|
|
: I<oops, iops, asm, "\t$Vt, $vaddr", "", pattern> {
|
|
bits<5> Vt;
|
|
bits<5> vaddr;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29-23} = 0b0011000;
|
|
let Inst{22} = L;
|
|
let Inst{21-16} = 0b000000;
|
|
let Inst{15-12} = opcode;
|
|
let Inst{11-10} = size;
|
|
let Inst{9-5} = vaddr;
|
|
let Inst{4-0} = Vt;
|
|
}
|
|
|
|
class BaseSIMDLdStPost<bit Q, bit L, bits<4> opcode, bits<2> size,
|
|
string asm, dag oops, dag iops>
|
|
: I<oops, iops, asm, "\t$Vt, $vaddr, $Xm", "", []> {
|
|
bits<5> Vt;
|
|
bits<5> vaddr;
|
|
bits<5> Xm;
|
|
let Inst{31} = 0;
|
|
let Inst{30} = Q;
|
|
let Inst{29-23} = 0b0011001;
|
|
let Inst{22} = L;
|
|
let Inst{21} = 0;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{15-12} = opcode;
|
|
let Inst{11-10} = size;
|
|
let Inst{9-5} = vaddr;
|
|
let Inst{4-0} = Vt;
|
|
let DecoderMethod = "DecodeSIMDLdStPost";
|
|
}
|
|
|
|
// The immediate form of AdvSIMD post-indexed addressing is encoded with
|
|
// register post-index addressing from the zero register.
|
|
multiclass SIMDLdStAliases<string asm, string layout, string Count,
|
|
int Offset, int Size> {
|
|
// E.g. "ld1 { v0.8b, v1.8b }, [x1], #16"
|
|
// "ld1\t$Vt, $vaddr, #16"
|
|
// may get mapped to
|
|
// (LD1Twov8b_POST VecListTwo8b:$Vt, am_simdnoindex:$vaddr, XZR)
|
|
def : InstAlias<asm # "\t$Vt, $vaddr, #" # Offset,
|
|
(!cast<Instruction>(NAME # Count # "v" # layout # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # layout):$Vt,
|
|
am_simdnoindex:$vaddr, XZR), 1>;
|
|
|
|
// E.g. "ld1.8b { v0, v1 }, [x1], #16"
|
|
// "ld1.8b\t$Vt, $vaddr, #16"
|
|
// may get mapped to
|
|
// (LD1Twov8b_POST VecListTwo64:$Vt, am_simdnoindex:$vaddr, XZR)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt, $vaddr, #" # Offset,
|
|
(!cast<Instruction>(NAME # Count # "v" # layout # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # Size):$Vt,
|
|
am_simdnoindex:$vaddr, XZR), 0>;
|
|
|
|
// E.g. "ld1.8b { v0, v1 }, [x1]"
|
|
// "ld1\t$Vt, $vaddr"
|
|
// may get mapped to
|
|
// (LD1Twov8b VecListTwo64:$Vt, am_simdnoindex:$vaddr)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt, $vaddr",
|
|
(!cast<Instruction>(NAME # Count # "v" # layout)
|
|
!cast<RegisterOperand>("VecList" # Count # Size):$Vt,
|
|
am_simdnoindex:$vaddr), 0>;
|
|
|
|
// E.g. "ld1.8b { v0, v1 }, [x1], x2"
|
|
// "ld1\t$Vt, $vaddr, $Xm"
|
|
// may get mapped to
|
|
// (LD1Twov8b_POST VecListTwo64:$Vt, am_simdnoindex:$vaddr, GPR64pi8:$Xm)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt, $vaddr, $Xm",
|
|
(!cast<Instruction>(NAME # Count # "v" # layout # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # Size):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset):$Xm), 0>;
|
|
}
|
|
|
|
multiclass BaseSIMDLdN<string Count, string asm, string veclist, int Offset128,
|
|
int Offset64, bits<4> opcode> {
|
|
let hasSideEffects = 0, mayLoad = 1, mayStore = 0 in {
|
|
def v16b: BaseSIMDLdSt<1, 1, opcode, 0b00, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "16b"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
def v8h : BaseSIMDLdSt<1, 1, opcode, 0b01, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "8h"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
def v4s : BaseSIMDLdSt<1, 1, opcode, 0b10, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "4s"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
def v2d : BaseSIMDLdSt<1, 1, opcode, 0b11, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "2d"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
def v8b : BaseSIMDLdSt<0, 1, opcode, 0b00, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "8b"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
def v4h : BaseSIMDLdSt<0, 1, opcode, 0b01, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "4h"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
def v2s : BaseSIMDLdSt<0, 1, opcode, 0b10, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "2s"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
|
|
|
|
def v16b_POST: BaseSIMDLdStPost<1, 1, opcode, 0b00, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "16b"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v8h_POST : BaseSIMDLdStPost<1, 1, opcode, 0b01, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "8h"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v4s_POST : BaseSIMDLdStPost<1, 1, opcode, 0b10, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "4s"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v2d_POST : BaseSIMDLdStPost<1, 1, opcode, 0b11, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "2d"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v8b_POST : BaseSIMDLdStPost<0, 1, opcode, 0b00, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "8b"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
def v4h_POST : BaseSIMDLdStPost<0, 1, opcode, 0b01, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "4h"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
def v2s_POST : BaseSIMDLdStPost<0, 1, opcode, 0b10, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "2s"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
}
|
|
|
|
defm : SIMDLdStAliases<asm, "16b", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "8h", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "4s", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "2d", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "8b", Count, Offset64, 64>;
|
|
defm : SIMDLdStAliases<asm, "4h", Count, Offset64, 64>;
|
|
defm : SIMDLdStAliases<asm, "2s", Count, Offset64, 64>;
|
|
}
|
|
|
|
// Only ld1/st1 has a v1d version.
|
|
multiclass BaseSIMDStN<string Count, string asm, string veclist, int Offset128,
|
|
int Offset64, bits<4> opcode> {
|
|
let hasSideEffects = 0, mayStore = 1, mayLoad = 0 in {
|
|
def v16b : BaseSIMDLdSt<1, 0, opcode, 0b00, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "16b"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
def v8h : BaseSIMDLdSt<1, 0, opcode, 0b01, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "8h"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
def v4s : BaseSIMDLdSt<1, 0, opcode, 0b10, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "4s"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
def v2d : BaseSIMDLdSt<1, 0, opcode, 0b11, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "2d"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
def v8b : BaseSIMDLdSt<0, 0, opcode, 0b00, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "8b"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
def v4h : BaseSIMDLdSt<0, 0, opcode, 0b01, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "4h"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
def v2s : BaseSIMDLdSt<0, 0, opcode, 0b10, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "2s"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
|
|
def v16b_POST : BaseSIMDLdStPost<1, 0, opcode, 0b00, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "16b"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v8h_POST : BaseSIMDLdStPost<1, 0, opcode, 0b01, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "8h"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v4s_POST : BaseSIMDLdStPost<1, 0, opcode, 0b10, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "4s"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v2d_POST : BaseSIMDLdStPost<1, 0, opcode, 0b11, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "2d"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset128):$Xm)>;
|
|
def v8b_POST : BaseSIMDLdStPost<0, 0, opcode, 0b00, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "8b"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
def v4h_POST : BaseSIMDLdStPost<0, 0, opcode, 0b01, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "4h"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
def v2s_POST : BaseSIMDLdStPost<0, 0, opcode, 0b10, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "2s"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
}
|
|
|
|
defm : SIMDLdStAliases<asm, "16b", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "8h", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "4s", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "2d", Count, Offset128, 128>;
|
|
defm : SIMDLdStAliases<asm, "8b", Count, Offset64, 64>;
|
|
defm : SIMDLdStAliases<asm, "4h", Count, Offset64, 64>;
|
|
defm : SIMDLdStAliases<asm, "2s", Count, Offset64, 64>;
|
|
}
|
|
|
|
multiclass BaseSIMDLd1<string Count, string asm, string veclist,
|
|
int Offset128, int Offset64, bits<4> opcode>
|
|
: BaseSIMDLdN<Count, asm, veclist, Offset128, Offset64, opcode> {
|
|
|
|
// LD1 instructions have extra "1d" variants.
|
|
let hasSideEffects = 0, mayLoad = 1, mayStore = 0 in {
|
|
def v1d : BaseSIMDLdSt<0, 1, opcode, 0b11, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "1d"):$Vt),
|
|
(ins am_simdnoindex:$vaddr), []>;
|
|
|
|
def v1d_POST : BaseSIMDLdStPost<0, 1, opcode, 0b11, asm,
|
|
(outs !cast<RegisterOperand>(veclist # "1d"):$Vt),
|
|
(ins am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
}
|
|
|
|
defm : SIMDLdStAliases<asm, "1d", Count, Offset64, 64>;
|
|
}
|
|
|
|
multiclass BaseSIMDSt1<string Count, string asm, string veclist,
|
|
int Offset128, int Offset64, bits<4> opcode>
|
|
: BaseSIMDStN<Count, asm, veclist, Offset128, Offset64, opcode> {
|
|
|
|
// ST1 instructions have extra "1d" variants.
|
|
let hasSideEffects = 0, mayLoad = 0, mayStore = 1 in {
|
|
def v1d : BaseSIMDLdSt<0, 0, opcode, 0b11, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "1d"):$Vt,
|
|
am_simdnoindex:$vaddr), []>;
|
|
|
|
def v1d_POST : BaseSIMDLdStPost<0, 0, opcode, 0b11, asm, (outs),
|
|
(ins !cast<RegisterOperand>(veclist # "1d"):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset64):$Xm)>;
|
|
}
|
|
|
|
defm : SIMDLdStAliases<asm, "1d", Count, Offset64, 64>;
|
|
}
|
|
|
|
multiclass SIMDLd1Multiple<string asm> {
|
|
defm One : BaseSIMDLd1<"One", asm, "VecListOne", 16, 8, 0b0111>;
|
|
defm Two : BaseSIMDLd1<"Two", asm, "VecListTwo", 32, 16, 0b1010>;
|
|
defm Three : BaseSIMDLd1<"Three", asm, "VecListThree", 48, 24, 0b0110>;
|
|
defm Four : BaseSIMDLd1<"Four", asm, "VecListFour", 64, 32, 0b0010>;
|
|
}
|
|
|
|
multiclass SIMDSt1Multiple<string asm> {
|
|
defm One : BaseSIMDSt1<"One", asm, "VecListOne", 16, 8, 0b0111>;
|
|
defm Two : BaseSIMDSt1<"Two", asm, "VecListTwo", 32, 16, 0b1010>;
|
|
defm Three : BaseSIMDSt1<"Three", asm, "VecListThree", 48, 24, 0b0110>;
|
|
defm Four : BaseSIMDSt1<"Four", asm, "VecListFour", 64, 32, 0b0010>;
|
|
}
|
|
|
|
multiclass SIMDLd2Multiple<string asm> {
|
|
defm Two : BaseSIMDLdN<"Two", asm, "VecListTwo", 32, 16, 0b1000>;
|
|
}
|
|
|
|
multiclass SIMDSt2Multiple<string asm> {
|
|
defm Two : BaseSIMDStN<"Two", asm, "VecListTwo", 32, 16, 0b1000>;
|
|
}
|
|
|
|
multiclass SIMDLd3Multiple<string asm> {
|
|
defm Three : BaseSIMDLdN<"Three", asm, "VecListThree", 48, 24, 0b0100>;
|
|
}
|
|
|
|
multiclass SIMDSt3Multiple<string asm> {
|
|
defm Three : BaseSIMDStN<"Three", asm, "VecListThree", 48, 24, 0b0100>;
|
|
}
|
|
|
|
multiclass SIMDLd4Multiple<string asm> {
|
|
defm Four : BaseSIMDLdN<"Four", asm, "VecListFour", 64, 32, 0b0000>;
|
|
}
|
|
|
|
multiclass SIMDSt4Multiple<string asm> {
|
|
defm Four : BaseSIMDStN<"Four", asm, "VecListFour", 64, 32, 0b0000>;
|
|
}
|
|
|
|
//---
|
|
// AdvSIMD Load/store single-element
|
|
//---
|
|
|
|
class BaseSIMDLdStSingle<bit L, bit R, bits<3> opcode,
|
|
string asm, string operands, dag oops, dag iops,
|
|
list<dag> pattern>
|
|
: I<oops, iops, asm, operands, "", pattern> {
|
|
bits<5> Vt;
|
|
bits<5> vaddr;
|
|
let Inst{31} = 0;
|
|
let Inst{29-24} = 0b001101;
|
|
let Inst{22} = L;
|
|
let Inst{21} = R;
|
|
let Inst{15-13} = opcode;
|
|
let Inst{9-5} = vaddr;
|
|
let Inst{4-0} = Vt;
|
|
let DecoderMethod = "DecodeSIMDLdStSingle";
|
|
}
|
|
|
|
class BaseSIMDLdStSingleTied<bit L, bit R, bits<3> opcode,
|
|
string asm, string operands, dag oops, dag iops,
|
|
list<dag> pattern>
|
|
: I<oops, iops, asm, operands, "$Vt = $dst", pattern> {
|
|
bits<5> Vt;
|
|
bits<5> vaddr;
|
|
let Inst{31} = 0;
|
|
let Inst{29-24} = 0b001101;
|
|
let Inst{22} = L;
|
|
let Inst{21} = R;
|
|
let Inst{15-13} = opcode;
|
|
let Inst{9-5} = vaddr;
|
|
let Inst{4-0} = Vt;
|
|
let DecoderMethod = "DecodeSIMDLdStSingleTied";
|
|
}
|
|
|
|
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDLdR<bit Q, bit R, bits<3> opcode, bit S, bits<2> size, string asm,
|
|
Operand listtype>
|
|
: BaseSIMDLdStSingle<1, R, opcode, asm, "\t$Vt, $vaddr",
|
|
(outs listtype:$Vt), (ins am_simdnoindex:$vaddr), []> {
|
|
let Inst{30} = Q;
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = S;
|
|
let Inst{11-10} = size;
|
|
}
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
class BaseSIMDLdRPost<bit Q, bit R, bits<3> opcode, bit S, bits<2> size,
|
|
string asm, Operand listtype, Operand GPR64pi>
|
|
: BaseSIMDLdStSingle<1, R, opcode, asm, "\t$Vt, $vaddr, $Xm",
|
|
(outs listtype:$Vt),
|
|
(ins am_simdnoindex:$vaddr, GPR64pi:$Xm), []> {
|
|
bits<5> Xm;
|
|
let Inst{30} = Q;
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = S;
|
|
let Inst{11-10} = size;
|
|
}
|
|
|
|
multiclass SIMDLdrAliases<string asm, string layout, string Count,
|
|
int Offset, int Size> {
|
|
// E.g. "ld1r { v0.8b }, [x1], #1"
|
|
// "ld1r.8b\t$Vt, $vaddr, #1"
|
|
// may get mapped to
|
|
// (LD1Rv8b_POST VecListOne8b:$Vt, am_simdnoindex:$vaddr, XZR)
|
|
def : InstAlias<asm # "\t$Vt, $vaddr, #" # Offset,
|
|
(!cast<Instruction>(NAME # "v" # layout # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # layout):$Vt,
|
|
am_simdnoindex:$vaddr, XZR), 1>;
|
|
|
|
// E.g. "ld1r.8b { v0 }, [x1], #1"
|
|
// "ld1r.8b\t$Vt, $vaddr, #1"
|
|
// may get mapped to
|
|
// (LD1Rv8b_POST VecListOne64:$Vt, am_simdnoindex:$vaddr, XZR)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt, $vaddr, #" # Offset,
|
|
(!cast<Instruction>(NAME # "v" # layout # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # Size):$Vt,
|
|
am_simdnoindex:$vaddr, XZR), 0>;
|
|
|
|
// E.g. "ld1r.8b { v0 }, [x1]"
|
|
// "ld1r.8b\t$Vt, $vaddr"
|
|
// may get mapped to
|
|
// (LD1Rv8b VecListOne64:$Vt, am_simdnoindex:$vaddr)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt, $vaddr",
|
|
(!cast<Instruction>(NAME # "v" # layout)
|
|
!cast<RegisterOperand>("VecList" # Count # Size):$Vt,
|
|
am_simdnoindex:$vaddr), 0>;
|
|
|
|
// E.g. "ld1r.8b { v0 }, [x1], x2"
|
|
// "ld1r.8b\t$Vt, $vaddr, $Xm"
|
|
// may get mapped to
|
|
// (LD1Rv8b_POST VecListOne64:$Vt, am_simdnoindex:$vaddr, GPR64pi1:$Xm)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt, $vaddr, $Xm",
|
|
(!cast<Instruction>(NAME # "v" # layout # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # Size):$Vt,
|
|
am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset):$Xm), 0>;
|
|
}
|
|
|
|
multiclass SIMDLdR<bit R, bits<3> opcode, bit S, string asm, string Count,
|
|
int Offset1, int Offset2, int Offset4, int Offset8> {
|
|
def v8b : BaseSIMDLdR<0, R, opcode, S, 0b00, asm,
|
|
!cast<Operand>("VecList" # Count # "8b")>;
|
|
def v16b: BaseSIMDLdR<1, R, opcode, S, 0b00, asm,
|
|
!cast<Operand>("VecList" # Count #"16b")>;
|
|
def v4h : BaseSIMDLdR<0, R, opcode, S, 0b01, asm,
|
|
!cast<Operand>("VecList" # Count #"4h")>;
|
|
def v8h : BaseSIMDLdR<1, R, opcode, S, 0b01, asm,
|
|
!cast<Operand>("VecList" # Count #"8h")>;
|
|
def v2s : BaseSIMDLdR<0, R, opcode, S, 0b10, asm,
|
|
!cast<Operand>("VecList" # Count #"2s")>;
|
|
def v4s : BaseSIMDLdR<1, R, opcode, S, 0b10, asm,
|
|
!cast<Operand>("VecList" # Count #"4s")>;
|
|
def v1d : BaseSIMDLdR<0, R, opcode, S, 0b11, asm,
|
|
!cast<Operand>("VecList" # Count #"1d")>;
|
|
def v2d : BaseSIMDLdR<1, R, opcode, S, 0b11, asm,
|
|
!cast<Operand>("VecList" # Count #"2d")>;
|
|
|
|
def v8b_POST : BaseSIMDLdRPost<0, R, opcode, S, 0b00, asm,
|
|
!cast<Operand>("VecList" # Count # "8b"),
|
|
!cast<Operand>("GPR64pi" # Offset1)>;
|
|
def v16b_POST: BaseSIMDLdRPost<1, R, opcode, S, 0b00, asm,
|
|
!cast<Operand>("VecList" # Count # "16b"),
|
|
!cast<Operand>("GPR64pi" # Offset1)>;
|
|
def v4h_POST : BaseSIMDLdRPost<0, R, opcode, S, 0b01, asm,
|
|
!cast<Operand>("VecList" # Count # "4h"),
|
|
!cast<Operand>("GPR64pi" # Offset2)>;
|
|
def v8h_POST : BaseSIMDLdRPost<1, R, opcode, S, 0b01, asm,
|
|
!cast<Operand>("VecList" # Count # "8h"),
|
|
!cast<Operand>("GPR64pi" # Offset2)>;
|
|
def v2s_POST : BaseSIMDLdRPost<0, R, opcode, S, 0b10, asm,
|
|
!cast<Operand>("VecList" # Count # "2s"),
|
|
!cast<Operand>("GPR64pi" # Offset4)>;
|
|
def v4s_POST : BaseSIMDLdRPost<1, R, opcode, S, 0b10, asm,
|
|
!cast<Operand>("VecList" # Count # "4s"),
|
|
!cast<Operand>("GPR64pi" # Offset4)>;
|
|
def v1d_POST : BaseSIMDLdRPost<0, R, opcode, S, 0b11, asm,
|
|
!cast<Operand>("VecList" # Count # "1d"),
|
|
!cast<Operand>("GPR64pi" # Offset8)>;
|
|
def v2d_POST : BaseSIMDLdRPost<1, R, opcode, S, 0b11, asm,
|
|
!cast<Operand>("VecList" # Count # "2d"),
|
|
!cast<Operand>("GPR64pi" # Offset8)>;
|
|
|
|
defm : SIMDLdrAliases<asm, "8b", Count, Offset1, 64>;
|
|
defm : SIMDLdrAliases<asm, "16b", Count, Offset1, 128>;
|
|
defm : SIMDLdrAliases<asm, "4h", Count, Offset2, 64>;
|
|
defm : SIMDLdrAliases<asm, "8h", Count, Offset2, 128>;
|
|
defm : SIMDLdrAliases<asm, "2s", Count, Offset4, 64>;
|
|
defm : SIMDLdrAliases<asm, "4s", Count, Offset4, 128>;
|
|
defm : SIMDLdrAliases<asm, "1d", Count, Offset8, 64>;
|
|
defm : SIMDLdrAliases<asm, "2d", Count, Offset8, 128>;
|
|
}
|
|
|
|
class SIMDLdStSingleB<bit L, bit R, bits<3> opcode, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q:S:size fields.
|
|
bits<4> idx;
|
|
let Inst{30} = idx{3};
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = idx{2};
|
|
let Inst{11-10} = idx{1-0};
|
|
}
|
|
class SIMDLdStSingleBTied<bit L, bit R, bits<3> opcode, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q:S:size fields.
|
|
bits<4> idx;
|
|
let Inst{30} = idx{3};
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = idx{2};
|
|
let Inst{11-10} = idx{1-0};
|
|
}
|
|
class SIMDLdStSingleBPost<bit L, bit R, bits<3> opcode, string asm,
|
|
dag oops, dag iops>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q:S:size fields.
|
|
bits<4> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx{3};
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = idx{2};
|
|
let Inst{11-10} = idx{1-0};
|
|
}
|
|
class SIMDLdStSingleBTiedPost<bit L, bit R, bits<3> opcode, string asm,
|
|
dag oops, dag iops>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q:S:size fields.
|
|
bits<4> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx{3};
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = idx{2};
|
|
let Inst{11-10} = idx{1-0};
|
|
}
|
|
|
|
class SIMDLdStSingleH<bit L, bit R, bits<3> opcode, bit size, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q:S:size<1> fields.
|
|
bits<3> idx;
|
|
let Inst{30} = idx{2};
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = idx{1};
|
|
let Inst{11} = idx{0};
|
|
let Inst{10} = size;
|
|
}
|
|
class SIMDLdStSingleHTied<bit L, bit R, bits<3> opcode, bit size, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q:S:size<1> fields.
|
|
bits<3> idx;
|
|
let Inst{30} = idx{2};
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = idx{1};
|
|
let Inst{11} = idx{0};
|
|
let Inst{10} = size;
|
|
}
|
|
|
|
class SIMDLdStSingleHPost<bit L, bit R, bits<3> opcode, bit size, string asm,
|
|
dag oops, dag iops>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q:S:size<1> fields.
|
|
bits<3> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx{2};
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = idx{1};
|
|
let Inst{11} = idx{0};
|
|
let Inst{10} = size;
|
|
}
|
|
class SIMDLdStSingleHTiedPost<bit L, bit R, bits<3> opcode, bit size, string asm,
|
|
dag oops, dag iops>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q:S:size<1> fields.
|
|
bits<3> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx{2};
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = idx{1};
|
|
let Inst{11} = idx{0};
|
|
let Inst{10} = size;
|
|
}
|
|
class SIMDLdStSingleS<bit L, bit R, bits<3> opcode, bits<2> size, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q:S fields.
|
|
bits<2> idx;
|
|
let Inst{30} = idx{1};
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = idx{0};
|
|
let Inst{11-10} = size;
|
|
}
|
|
class SIMDLdStSingleSTied<bit L, bit R, bits<3> opcode, bits<2> size, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q:S fields.
|
|
bits<2> idx;
|
|
let Inst{30} = idx{1};
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = idx{0};
|
|
let Inst{11-10} = size;
|
|
}
|
|
class SIMDLdStSingleSPost<bit L, bit R, bits<3> opcode, bits<2> size,
|
|
string asm, dag oops, dag iops>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q:S fields.
|
|
bits<2> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx{1};
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = idx{0};
|
|
let Inst{11-10} = size;
|
|
}
|
|
class SIMDLdStSingleSTiedPost<bit L, bit R, bits<3> opcode, bits<2> size,
|
|
string asm, dag oops, dag iops>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q:S fields.
|
|
bits<2> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx{1};
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = idx{0};
|
|
let Inst{11-10} = size;
|
|
}
|
|
class SIMDLdStSingleD<bit L, bit R, bits<3> opcode, bits<2> size, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q field.
|
|
bits<1> idx;
|
|
let Inst{30} = idx;
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = 0;
|
|
let Inst{11-10} = size;
|
|
}
|
|
class SIMDLdStSingleDTied<bit L, bit R, bits<3> opcode, bits<2> size, string asm,
|
|
dag oops, dag iops, list<dag> pattern>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr", oops, iops,
|
|
pattern> {
|
|
// idx encoded in Q field.
|
|
bits<1> idx;
|
|
let Inst{30} = idx;
|
|
let Inst{23} = 0;
|
|
let Inst{20-16} = 0b00000;
|
|
let Inst{12} = 0;
|
|
let Inst{11-10} = size;
|
|
}
|
|
class SIMDLdStSingleDPost<bit L, bit R, bits<3> opcode, bits<2> size,
|
|
string asm, dag oops, dag iops>
|
|
: BaseSIMDLdStSingle<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q field.
|
|
bits<1> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx;
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = 0;
|
|
let Inst{11-10} = size;
|
|
}
|
|
class SIMDLdStSingleDTiedPost<bit L, bit R, bits<3> opcode, bits<2> size,
|
|
string asm, dag oops, dag iops>
|
|
: BaseSIMDLdStSingleTied<L, R, opcode, asm, "\t$Vt$idx, $vaddr, $Xm",
|
|
oops, iops, []> {
|
|
// idx encoded in Q field.
|
|
bits<1> idx;
|
|
bits<5> Xm;
|
|
let Inst{30} = idx;
|
|
let Inst{23} = 1;
|
|
let Inst{20-16} = Xm;
|
|
let Inst{12} = 0;
|
|
let Inst{11-10} = size;
|
|
}
|
|
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDLdSingleBTied<bit R, bits<3> opcode, string asm,
|
|
RegisterOperand listtype,
|
|
RegisterOperand GPR64pi> {
|
|
def i8 : SIMDLdStSingleBTied<1, R, opcode, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexB:$idx,
|
|
am_simdnoindex:$vaddr), []>;
|
|
|
|
def i8_POST : SIMDLdStSingleBTiedPost<1, R, opcode, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexB:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDLdSingleHTied<bit R, bits<3> opcode, bit size, string asm,
|
|
RegisterOperand listtype,
|
|
RegisterOperand GPR64pi> {
|
|
def i16 : SIMDLdStSingleHTied<1, R, opcode, size, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexH:$idx,
|
|
am_simdnoindex:$vaddr), []>;
|
|
|
|
def i16_POST : SIMDLdStSingleHTiedPost<1, R, opcode, size, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexH:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDLdSingleSTied<bit R, bits<3> opcode, bits<2> size,string asm,
|
|
RegisterOperand listtype,
|
|
RegisterOperand GPR64pi> {
|
|
def i32 : SIMDLdStSingleSTied<1, R, opcode, size, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexS:$idx,
|
|
am_simdnoindex:$vaddr), []>;
|
|
|
|
def i32_POST : SIMDLdStSingleSTiedPost<1, R, opcode, size, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexS:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
let mayLoad = 1, mayStore = 0, hasSideEffects = 0 in
|
|
multiclass SIMDLdSingleDTied<bit R, bits<3> opcode, bits<2> size, string asm,
|
|
RegisterOperand listtype,
|
|
RegisterOperand GPR64pi> {
|
|
def i64 : SIMDLdStSingleDTied<1, R, opcode, size, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexD:$idx,
|
|
am_simdnoindex:$vaddr), []>;
|
|
|
|
def i64_POST : SIMDLdStSingleDTiedPost<1, R, opcode, size, asm,
|
|
(outs listtype:$dst),
|
|
(ins listtype:$Vt, VectorIndexD:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
let mayLoad = 0, mayStore = 1, hasSideEffects = 0 in
|
|
multiclass SIMDStSingleB<bit R, bits<3> opcode, string asm,
|
|
RegisterOperand listtype, list<dag> pattern,
|
|
RegisterOperand GPR64pi> {
|
|
def i8 : SIMDLdStSingleB<0, R, opcode, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexB:$idx,
|
|
am_simdnoindex:$vaddr),
|
|
pattern>;
|
|
|
|
def i8_POST : SIMDLdStSingleBPost<0, R, opcode, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexB:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
let mayLoad = 0, mayStore = 1, hasSideEffects = 0 in
|
|
multiclass SIMDStSingleH<bit R, bits<3> opcode, bit size, string asm,
|
|
RegisterOperand listtype, list<dag> pattern,
|
|
RegisterOperand GPR64pi> {
|
|
def i16 : SIMDLdStSingleH<0, R, opcode, size, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexH:$idx,
|
|
am_simdnoindex:$vaddr),
|
|
pattern>;
|
|
|
|
def i16_POST : SIMDLdStSingleHPost<0, R, opcode, size, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexH:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
let mayLoad = 0, mayStore = 1, hasSideEffects = 0 in
|
|
multiclass SIMDStSingleS<bit R, bits<3> opcode, bits<2> size,string asm,
|
|
RegisterOperand listtype, list<dag> pattern,
|
|
RegisterOperand GPR64pi> {
|
|
def i32 : SIMDLdStSingleS<0, R, opcode, size, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexS:$idx,
|
|
am_simdnoindex:$vaddr),
|
|
pattern>;
|
|
|
|
def i32_POST : SIMDLdStSingleSPost<0, R, opcode, size, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexS:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
let mayLoad = 0, mayStore = 1, hasSideEffects = 0 in
|
|
multiclass SIMDStSingleD<bit R, bits<3> opcode, bits<2> size, string asm,
|
|
RegisterOperand listtype, list<dag> pattern,
|
|
RegisterOperand GPR64pi> {
|
|
def i64 : SIMDLdStSingleD<0, R, opcode, size, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexD:$idx,
|
|
am_simdnoindex:$vaddr), pattern>;
|
|
|
|
def i64_POST : SIMDLdStSingleDPost<0, R, opcode, size, asm,
|
|
(outs), (ins listtype:$Vt, VectorIndexD:$idx,
|
|
am_simdnoindex:$vaddr, GPR64pi:$Xm)>;
|
|
}
|
|
|
|
multiclass SIMDLdStSingleAliases<string asm, string layout, string Type,
|
|
string Count, int Offset, Operand idxtype> {
|
|
// E.g. "ld1 { v0.8b }[0], [x1], #1"
|
|
// "ld1\t$Vt, $vaddr, #1"
|
|
// may get mapped to
|
|
// (LD1Rv8b_POST VecListOne8b:$Vt, am_simdnoindex:$vaddr, XZR)
|
|
def : InstAlias<asm # "\t$Vt$idx, $vaddr, #" # Offset,
|
|
(!cast<Instruction>(NAME # Type # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # layout):$Vt,
|
|
idxtype:$idx, am_simdnoindex:$vaddr, XZR), 1>;
|
|
|
|
// E.g. "ld1.8b { v0 }[0], [x1], #1"
|
|
// "ld1.8b\t$Vt, $vaddr, #1"
|
|
// may get mapped to
|
|
// (LD1Rv8b_POST VecListOne64:$Vt, am_simdnoindex:$vaddr, XZR)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt$idx, $vaddr, #" # Offset,
|
|
(!cast<Instruction>(NAME # Type # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # "128"):$Vt,
|
|
idxtype:$idx, am_simdnoindex:$vaddr, XZR), 0>;
|
|
|
|
// E.g. "ld1.8b { v0 }[0], [x1]"
|
|
// "ld1.8b\t$Vt, $vaddr"
|
|
// may get mapped to
|
|
// (LD1Rv8b VecListOne64:$Vt, am_simdnoindex:$vaddr)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt$idx, $vaddr",
|
|
(!cast<Instruction>(NAME # Type)
|
|
!cast<RegisterOperand>("VecList" # Count # "128"):$Vt,
|
|
idxtype:$idx, am_simdnoindex:$vaddr), 0>;
|
|
|
|
// E.g. "ld1.8b { v0 }[0], [x1], x2"
|
|
// "ld1.8b\t$Vt, $vaddr, $Xm"
|
|
// may get mapped to
|
|
// (LD1Rv8b_POST VecListOne64:$Vt, am_simdnoindex:$vaddr, GPR64pi1:$Xm)
|
|
def : InstAlias<asm # "." # layout # "\t$Vt$idx, $vaddr, $Xm",
|
|
(!cast<Instruction>(NAME # Type # "_POST")
|
|
!cast<RegisterOperand>("VecList" # Count # "128"):$Vt,
|
|
idxtype:$idx, am_simdnoindex:$vaddr,
|
|
!cast<RegisterOperand>("GPR64pi" # Offset):$Xm), 0>;
|
|
}
|
|
|
|
multiclass SIMDLdSt1SingleAliases<string asm> {
|
|
defm : SIMDLdStSingleAliases<asm, "b", "i8", "One", 1, VectorIndexB>;
|
|
defm : SIMDLdStSingleAliases<asm, "h", "i16", "One", 2, VectorIndexH>;
|
|
defm : SIMDLdStSingleAliases<asm, "s", "i32", "One", 4, VectorIndexS>;
|
|
defm : SIMDLdStSingleAliases<asm, "d", "i64", "One", 8, VectorIndexD>;
|
|
}
|
|
|
|
multiclass SIMDLdSt2SingleAliases<string asm> {
|
|
defm : SIMDLdStSingleAliases<asm, "b", "i8", "Two", 2, VectorIndexB>;
|
|
defm : SIMDLdStSingleAliases<asm, "h", "i16", "Two", 4, VectorIndexH>;
|
|
defm : SIMDLdStSingleAliases<asm, "s", "i32", "Two", 8, VectorIndexS>;
|
|
defm : SIMDLdStSingleAliases<asm, "d", "i64", "Two", 16, VectorIndexD>;
|
|
}
|
|
|
|
multiclass SIMDLdSt3SingleAliases<string asm> {
|
|
defm : SIMDLdStSingleAliases<asm, "b", "i8", "Three", 3, VectorIndexB>;
|
|
defm : SIMDLdStSingleAliases<asm, "h", "i16", "Three", 6, VectorIndexH>;
|
|
defm : SIMDLdStSingleAliases<asm, "s", "i32", "Three", 12, VectorIndexS>;
|
|
defm : SIMDLdStSingleAliases<asm, "d", "i64", "Three", 24, VectorIndexD>;
|
|
}
|
|
|
|
multiclass SIMDLdSt4SingleAliases<string asm> {
|
|
defm : SIMDLdStSingleAliases<asm, "b", "i8", "Four", 4, VectorIndexB>;
|
|
defm : SIMDLdStSingleAliases<asm, "h", "i16", "Four", 8, VectorIndexH>;
|
|
defm : SIMDLdStSingleAliases<asm, "s", "i32", "Four", 16, VectorIndexS>;
|
|
defm : SIMDLdStSingleAliases<asm, "d", "i64", "Four", 32, VectorIndexD>;
|
|
}
|
|
|
|
//----------------------------------------------------------------------------
|
|
// Crypto extensions
|
|
//----------------------------------------------------------------------------
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class AESBase<bits<4> opc, string asm, dag outs, dag ins, string cstr,
|
|
list<dag> pat>
|
|
: I<outs, ins, asm, "{\t$Rd.16b, $Rn.16b|.16b\t$Rd, $Rn}", cstr, pat>,
|
|
Sched<[WriteV]>{
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-16} = 0b0100111000101000;
|
|
let Inst{15-12} = opc;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class AESInst<bits<4> opc, string asm, Intrinsic OpNode>
|
|
: AESBase<opc, asm, (outs V128:$Rd), (ins V128:$Rn), "",
|
|
[(set (v16i8 V128:$Rd), (OpNode (v16i8 V128:$Rn)))]>;
|
|
|
|
class AESTiedInst<bits<4> opc, string asm, Intrinsic OpNode>
|
|
: AESBase<opc, asm, (outs V128:$dst), (ins V128:$Rd, V128:$Rn),
|
|
"$Rd = $dst",
|
|
[(set (v16i8 V128:$dst),
|
|
(OpNode (v16i8 V128:$Rd), (v16i8 V128:$Rn)))]>;
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class SHA3OpTiedInst<bits<3> opc, string asm, string dst_lhs_kind,
|
|
dag oops, dag iops, list<dag> pat>
|
|
: I<oops, iops, asm,
|
|
"{\t$Rd" # dst_lhs_kind # ", $Rn" # dst_lhs_kind # ", $Rm.4s" #
|
|
"|.4s\t$Rd, $Rn, $Rm}", "$Rd = $dst", pat>,
|
|
Sched<[WriteV]>{
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
bits<5> Rm;
|
|
let Inst{31-21} = 0b01011110000;
|
|
let Inst{20-16} = Rm;
|
|
let Inst{15} = 0;
|
|
let Inst{14-12} = opc;
|
|
let Inst{11-10} = 0b00;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class SHATiedInstQSV<bits<3> opc, string asm, Intrinsic OpNode>
|
|
: SHA3OpTiedInst<opc, asm, "", (outs FPR128:$dst),
|
|
(ins FPR128:$Rd, FPR32:$Rn, V128:$Rm),
|
|
[(set (v4i32 FPR128:$dst),
|
|
(OpNode (v4i32 FPR128:$Rd), (i32 FPR32:$Rn),
|
|
(v4i32 V128:$Rm)))]>;
|
|
|
|
class SHATiedInstVVV<bits<3> opc, string asm, Intrinsic OpNode>
|
|
: SHA3OpTiedInst<opc, asm, ".4s", (outs V128:$dst),
|
|
(ins V128:$Rd, V128:$Rn, V128:$Rm),
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i32 V128:$Rn),
|
|
(v4i32 V128:$Rm)))]>;
|
|
|
|
class SHATiedInstQQV<bits<3> opc, string asm, Intrinsic OpNode>
|
|
: SHA3OpTiedInst<opc, asm, "", (outs FPR128:$dst),
|
|
(ins FPR128:$Rd, FPR128:$Rn, V128:$Rm),
|
|
[(set (v4i32 FPR128:$dst),
|
|
(OpNode (v4i32 FPR128:$Rd), (v4i32 FPR128:$Rn),
|
|
(v4i32 V128:$Rm)))]>;
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 0 in
|
|
class SHA2OpInst<bits<4> opc, string asm, string kind,
|
|
string cstr, dag oops, dag iops,
|
|
list<dag> pat>
|
|
: I<oops, iops, asm, "{\t$Rd" # kind # ", $Rn" # kind #
|
|
"|" # kind # "\t$Rd, $Rn}", cstr, pat>,
|
|
Sched<[WriteV]>{
|
|
bits<5> Rd;
|
|
bits<5> Rn;
|
|
let Inst{31-16} = 0b0101111000101000;
|
|
let Inst{15-12} = opc;
|
|
let Inst{11-10} = 0b10;
|
|
let Inst{9-5} = Rn;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
class SHATiedInstVV<bits<4> opc, string asm, Intrinsic OpNode>
|
|
: SHA2OpInst<opc, asm, ".4s", "$Rd = $dst", (outs V128:$dst),
|
|
(ins V128:$Rd, V128:$Rn),
|
|
[(set (v4i32 V128:$dst),
|
|
(OpNode (v4i32 V128:$Rd), (v4i32 V128:$Rn)))]>;
|
|
|
|
class SHAInstSS<bits<4> opc, string asm, Intrinsic OpNode>
|
|
: SHA2OpInst<opc, asm, "", "", (outs FPR32:$Rd), (ins FPR32:$Rn),
|
|
[(set (i32 FPR32:$Rd), (OpNode (i32 FPR32:$Rn)))]>;
|
|
|
|
// Allow the size specifier tokens to be upper case, not just lower.
|
|
def : TokenAlias<".8B", ".8b">;
|
|
def : TokenAlias<".4H", ".4h">;
|
|
def : TokenAlias<".2S", ".2s">;
|
|
def : TokenAlias<".1D", ".1d">;
|
|
def : TokenAlias<".16B", ".16b">;
|
|
def : TokenAlias<".8H", ".8h">;
|
|
def : TokenAlias<".4S", ".4s">;
|
|
def : TokenAlias<".2D", ".2d">;
|
|
def : TokenAlias<".B", ".b">;
|
|
def : TokenAlias<".H", ".h">;
|
|
def : TokenAlias<".S", ".s">;
|
|
def : TokenAlias<".D", ".d">;
|