llvm-project/llvm/lib/CodeGen/MIRParser/MILexer.h

208 lines
4.8 KiB
C
Raw Normal View History

//===- MILexer.h - Lexer for machine instructions ---------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file declares the function that lexes the machine instruction source
// string.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_CODEGEN_MIRPARSER_MILEXER_H
#define LLVM_LIB_CODEGEN_MIRPARSER_MILEXER_H
#include "llvm/ADT/APSInt.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include <string>
namespace llvm {
class Twine;
/// A token produced by the machine instruction lexer.
struct MIToken {
enum TokenKind {
// Markers
Eof,
Error,
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
Newline,
// Tokens with no info.
comma,
equal,
underscore,
colon,
coloncolon,
dot,
exclaim,
lparen,
rparen,
lbrace,
rbrace,
plus,
minus,
less,
greater,
// Keywords
kw_implicit,
kw_implicit_define,
kw_def,
kw_dead,
kw_dereferenceable,
kw_killed,
kw_undef,
kw_internal,
kw_early_clobber,
kw_debug_use,
kw_tied_def,
kw_frame_setup,
kw_debug_location,
kw_cfi_same_value,
kw_cfi_offset,
kw_cfi_def_cfa_register,
kw_cfi_def_cfa_offset,
kw_cfi_def_cfa,
kw_blockaddress,
kw_intrinsic,
kw_target_index,
kw_half,
kw_float,
kw_double,
kw_x86_fp80,
kw_fp128,
kw_ppc_fp128,
kw_target_flags,
kw_volatile,
kw_non_temporal,
kw_invariant,
kw_align,
kw_stack,
kw_got,
kw_jump_table,
kw_constant_pool,
kw_call_entry,
kw_liveout,
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
kw_address_taken,
kw_landing_pad,
kw_liveins,
kw_successors,
kw_floatpred,
kw_intpred,
// Named metadata keywords
md_tbaa,
md_alias_scope,
md_noalias,
md_range,
md_diexpr,
// Identifier tokens
Identifier,
IntegerType,
NamedRegister,
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
MachineBasicBlockLabel,
MachineBasicBlock,
PointerType,
ScalarType,
StackObject,
FixedStackObject,
NamedGlobalValue,
GlobalValue,
ExternalSymbol,
// Other tokens
IntegerLiteral,
FloatingPointLiteral,
HexLiteral,
VirtualRegister,
ConstantPoolItem,
JumpTableIndex,
NamedIRBlock,
IRBlock,
NamedIRValue,
IRValue,
QuotedIRValue, // `<constant value>`
SubRegisterIndex,
StringConstant
};
private:
TokenKind Kind = Error;
StringRef Range;
StringRef StringValue;
std::string StringValueStorage;
APSInt IntVal;
public:
MIToken() = default;
MIToken &reset(TokenKind Kind, StringRef Range);
MIToken &setStringValue(StringRef StrVal);
MIToken &setOwnedStringValue(std::string StrVal);
MIToken &setIntegerValue(APSInt IntVal);
TokenKind kind() const { return Kind; }
bool isError() const { return Kind == Error; }
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
bool isNewlineOrEOF() const { return Kind == Newline || Kind == Eof; }
bool isErrorOrEOF() const { return Kind == Error || Kind == Eof; }
bool isRegister() const {
return Kind == NamedRegister || Kind == underscore ||
Kind == VirtualRegister;
}
bool isRegisterFlag() const {
return Kind == kw_implicit || Kind == kw_implicit_define ||
Kind == kw_def || Kind == kw_dead || Kind == kw_killed ||
Kind == kw_undef || Kind == kw_internal ||
Kind == kw_early_clobber || Kind == kw_debug_use;
}
bool isMemoryOperandFlag() const {
return Kind == kw_volatile || Kind == kw_non_temporal ||
Kind == kw_dereferenceable || Kind == kw_invariant ||
Kind == StringConstant;
}
bool is(TokenKind K) const { return Kind == K; }
bool isNot(TokenKind K) const { return Kind != K; }
StringRef::iterator location() const { return Range.begin(); }
StringRef range() const { return Range; }
/// Return the token's string value.
StringRef stringValue() const { return StringValue; }
const APSInt &integerValue() const { return IntVal; }
bool hasIntegerValue() const {
return Kind == IntegerLiteral || Kind == MachineBasicBlock ||
MIR Serialization: Change MIR syntax - use custom syntax for MBBs. This commit modifies the way the machine basic blocks are serialized - now the machine basic blocks are serialized using a custom syntax instead of relying on YAML primitives. Instead of using YAML mappings to represent the individual machine basic blocks in a machine function's body, the new syntax uses a single YAML block scalar which contains all of the machine basic blocks and instructions for that function. This is an example of a function's body that uses the old syntax: body: - id: 0 name: entry instructions: - '%eax = MOV32r0 implicit-def %eflags' - 'RETQ %eax' ... The same body is now written like this: body: | bb.0.entry: %eax = MOV32r0 implicit-def %eflags RETQ %eax ... This syntax change is motivated by the fact that the bundled machine instructions didn't map that well to the old syntax which was using a single YAML sequence to store all of the machine instructions in a block. The bundled machine instructions internally use flags like BundledPred and BundledSucc to determine the bundles, and serializing them as MI flags using the old syntax would have had a negative impact on the readability and the ease of editing for MIR files. The new syntax allows me to serialize the bundled machine instructions using a block construct without relying on the internal flags, for example: BUNDLE implicit-def dead %itstate, implicit-def %s1 ... { t2IT 1, 24, implicit-def %itstate %s1 = VMOVS killed %s0, 1, killed %cpsr, implicit killed %itstate } This commit also converts the MIR testcases to the new syntax. I developed a script that can convert from the old syntax to the new one. I will post the script on the llvm-commits mailing list in the thread for this commit. llvm-svn: 244982
2015-08-14 07:10:16 +08:00
Kind == MachineBasicBlockLabel || Kind == StackObject ||
Kind == FixedStackObject || Kind == GlobalValue ||
Kind == VirtualRegister || Kind == ConstantPoolItem ||
Kind == JumpTableIndex || Kind == IRBlock || Kind == IRValue;
}
};
/// Consume a single machine instruction token in the given source and return
/// the remaining source string.
StringRef lexMIToken(
StringRef Source, MIToken &Token,
function_ref<void(StringRef::iterator, const Twine &)> ErrorCallback);
} // end namespace llvm
#endif // LLVM_LIB_CODEGEN_MIRPARSER_MILEXER_H