mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-28 19:31:58 +00:00
53fa56e8dc
The Win64 calling convention has xmm6-15 as callee-saved while still clobbering all ymm registers. Add a YMM_HI_6_15 pseudo-register that aliases the clobbered part of the ymm registers, and mark that as call-clobbered. This allows live xmm registers across calls. This hack wouldn't be necessary with RegisterMask operands representing the call clobbers, but they are not quite operational yet. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149088 91177308-0d34-0410-b5e6-96231b3b80d8
307 lines
14 KiB
TableGen
307 lines
14 KiB
TableGen
//===- X86InstrControl.td - Control Flow Instructions ------*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file describes the X86 jump, return, call, and related instructions.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Control Flow Instructions.
|
|
//
|
|
|
|
// Return instructions.
|
|
let isTerminator = 1, isReturn = 1, isBarrier = 1,
|
|
hasCtrlDep = 1, FPForm = SpecialFP in {
|
|
def RET : I <0xC3, RawFrm, (outs), (ins variable_ops),
|
|
"ret",
|
|
[(X86retflag 0)]>;
|
|
def RETI : Ii16<0xC2, RawFrm, (outs), (ins i16imm:$amt, variable_ops),
|
|
"ret\t$amt",
|
|
[(X86retflag timm:$amt)]>;
|
|
def RETIW : Ii16<0xC2, RawFrm, (outs), (ins i16imm:$amt, variable_ops),
|
|
"retw\t$amt",
|
|
[]>, OpSize;
|
|
def LRETL : I <0xCB, RawFrm, (outs), (ins),
|
|
"lretl", []>;
|
|
def LRETQ : RI <0xCB, RawFrm, (outs), (ins),
|
|
"lretq", []>;
|
|
def LRETI : Ii16<0xCA, RawFrm, (outs), (ins i16imm:$amt),
|
|
"lret\t$amt", []>;
|
|
def LRETIW : Ii16<0xCA, RawFrm, (outs), (ins i16imm:$amt),
|
|
"lretw\t$amt", []>, OpSize;
|
|
}
|
|
|
|
// Unconditional branches.
|
|
let isBarrier = 1, isBranch = 1, isTerminator = 1 in {
|
|
def JMP_4 : Ii32PCRel<0xE9, RawFrm, (outs), (ins brtarget:$dst),
|
|
"jmp\t$dst", [(br bb:$dst)]>;
|
|
def JMP_1 : Ii8PCRel<0xEB, RawFrm, (outs), (ins brtarget8:$dst),
|
|
"jmp\t$dst", []>;
|
|
// FIXME : Intel syntax for JMP64pcrel32 such that it is not ambiguious
|
|
// with JMP_1.
|
|
def JMP64pcrel32 : I<0xE9, RawFrm, (outs), (ins brtarget:$dst),
|
|
"jmpq\t$dst", []>;
|
|
}
|
|
|
|
// Conditional Branches.
|
|
let isBranch = 1, isTerminator = 1, Uses = [EFLAGS] in {
|
|
multiclass ICBr<bits<8> opc1, bits<8> opc4, string asm, PatFrag Cond> {
|
|
def _1 : Ii8PCRel <opc1, RawFrm, (outs), (ins brtarget8:$dst), asm, []>;
|
|
def _4 : Ii32PCRel<opc4, RawFrm, (outs), (ins brtarget:$dst), asm,
|
|
[(X86brcond bb:$dst, Cond, EFLAGS)]>, TB;
|
|
}
|
|
}
|
|
|
|
defm JO : ICBr<0x70, 0x80, "jo\t$dst" , X86_COND_O>;
|
|
defm JNO : ICBr<0x71, 0x81, "jno\t$dst" , X86_COND_NO>;
|
|
defm JB : ICBr<0x72, 0x82, "jb\t$dst" , X86_COND_B>;
|
|
defm JAE : ICBr<0x73, 0x83, "jae\t$dst", X86_COND_AE>;
|
|
defm JE : ICBr<0x74, 0x84, "je\t$dst" , X86_COND_E>;
|
|
defm JNE : ICBr<0x75, 0x85, "jne\t$dst", X86_COND_NE>;
|
|
defm JBE : ICBr<0x76, 0x86, "jbe\t$dst", X86_COND_BE>;
|
|
defm JA : ICBr<0x77, 0x87, "ja\t$dst" , X86_COND_A>;
|
|
defm JS : ICBr<0x78, 0x88, "js\t$dst" , X86_COND_S>;
|
|
defm JNS : ICBr<0x79, 0x89, "jns\t$dst", X86_COND_NS>;
|
|
defm JP : ICBr<0x7A, 0x8A, "jp\t$dst" , X86_COND_P>;
|
|
defm JNP : ICBr<0x7B, 0x8B, "jnp\t$dst", X86_COND_NP>;
|
|
defm JL : ICBr<0x7C, 0x8C, "jl\t$dst" , X86_COND_L>;
|
|
defm JGE : ICBr<0x7D, 0x8D, "jge\t$dst", X86_COND_GE>;
|
|
defm JLE : ICBr<0x7E, 0x8E, "jle\t$dst", X86_COND_LE>;
|
|
defm JG : ICBr<0x7F, 0x8F, "jg\t$dst" , X86_COND_G>;
|
|
|
|
// jcx/jecx/jrcx instructions.
|
|
let isAsmParserOnly = 1, isBranch = 1, isTerminator = 1 in {
|
|
// These are the 32-bit versions of this instruction for the asmparser. In
|
|
// 32-bit mode, the address size prefix is jcxz and the unprefixed version is
|
|
// jecxz.
|
|
let Uses = [CX] in
|
|
def JCXZ : Ii8PCRel<0xE3, RawFrm, (outs), (ins brtarget8:$dst),
|
|
"jcxz\t$dst", []>, AdSize, Requires<[In32BitMode]>;
|
|
let Uses = [ECX] in
|
|
def JECXZ_32 : Ii8PCRel<0xE3, RawFrm, (outs), (ins brtarget8:$dst),
|
|
"jecxz\t$dst", []>, Requires<[In32BitMode]>;
|
|
|
|
// J*CXZ instruction: 64-bit versions of this instruction for the asmparser.
|
|
// In 64-bit mode, the address size prefix is jecxz and the unprefixed version
|
|
// is jrcxz.
|
|
let Uses = [ECX] in
|
|
def JECXZ_64 : Ii8PCRel<0xE3, RawFrm, (outs), (ins brtarget8:$dst),
|
|
"jecxz\t$dst", []>, AdSize, Requires<[In64BitMode]>;
|
|
let Uses = [RCX] in
|
|
def JRCXZ : Ii8PCRel<0xE3, RawFrm, (outs), (ins brtarget8:$dst),
|
|
"jrcxz\t$dst", []>, Requires<[In64BitMode]>;
|
|
}
|
|
|
|
// Indirect branches
|
|
let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in {
|
|
def JMP32r : I<0xFF, MRM4r, (outs), (ins GR32:$dst), "jmp{l}\t{*}$dst",
|
|
[(brind GR32:$dst)]>, Requires<[In32BitMode]>;
|
|
def JMP32m : I<0xFF, MRM4m, (outs), (ins i32mem:$dst), "jmp{l}\t{*}$dst",
|
|
[(brind (loadi32 addr:$dst))]>, Requires<[In32BitMode]>;
|
|
|
|
def JMP64r : I<0xFF, MRM4r, (outs), (ins GR64:$dst), "jmp{q}\t{*}$dst",
|
|
[(brind GR64:$dst)]>, Requires<[In64BitMode]>;
|
|
def JMP64m : I<0xFF, MRM4m, (outs), (ins i64mem:$dst), "jmp{q}\t{*}$dst",
|
|
[(brind (loadi64 addr:$dst))]>, Requires<[In64BitMode]>;
|
|
|
|
def FARJMP16i : Iseg16<0xEA, RawFrmImm16, (outs),
|
|
(ins i16imm:$off, i16imm:$seg),
|
|
"ljmp{w}\t{$seg, $off|$off, $seg}", []>, OpSize;
|
|
def FARJMP32i : Iseg32<0xEA, RawFrmImm16, (outs),
|
|
(ins i32imm:$off, i16imm:$seg),
|
|
"ljmp{l}\t{$seg, $off|$off, $seg}", []>;
|
|
def FARJMP64 : RI<0xFF, MRM5m, (outs), (ins opaque80mem:$dst),
|
|
"ljmp{q}\t{*}$dst", []>;
|
|
|
|
def FARJMP16m : I<0xFF, MRM5m, (outs), (ins opaque32mem:$dst),
|
|
"ljmp{w}\t{*}$dst", []>, OpSize;
|
|
def FARJMP32m : I<0xFF, MRM5m, (outs), (ins opaque48mem:$dst),
|
|
"ljmp{l}\t{*}$dst", []>;
|
|
}
|
|
|
|
|
|
// Loop instructions
|
|
|
|
def LOOP : Ii8PCRel<0xE2, RawFrm, (outs), (ins brtarget8:$dst), "loop\t$dst", []>;
|
|
def LOOPE : Ii8PCRel<0xE1, RawFrm, (outs), (ins brtarget8:$dst), "loope\t$dst", []>;
|
|
def LOOPNE : Ii8PCRel<0xE0, RawFrm, (outs), (ins brtarget8:$dst), "loopne\t$dst", []>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Call Instructions...
|
|
//
|
|
let isCall = 1 in
|
|
// All calls clobber the non-callee saved registers. ESP is marked as
|
|
// a use to prevent stack-pointer assignments that appear immediately
|
|
// before calls from potentially appearing dead. Uses for argument
|
|
// registers are added manually.
|
|
let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
|
|
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
|
|
Uses = [ESP] in {
|
|
def CALLpcrel32 : Ii32PCRel<0xE8, RawFrm,
|
|
(outs), (ins i32imm_pcrel:$dst,variable_ops),
|
|
"call{l}\t$dst", []>, Requires<[In32BitMode]>;
|
|
def CALL32r : I<0xFF, MRM2r, (outs), (ins GR32:$dst, variable_ops),
|
|
"call{l}\t{*}$dst", [(X86call GR32:$dst)]>,
|
|
Requires<[In32BitMode]>;
|
|
def CALL32m : I<0xFF, MRM2m, (outs), (ins i32mem:$dst, variable_ops),
|
|
"call{l}\t{*}$dst", [(X86call (loadi32 addr:$dst))]>,
|
|
Requires<[In32BitMode]>;
|
|
|
|
def FARCALL16i : Iseg16<0x9A, RawFrmImm16, (outs),
|
|
(ins i16imm:$off, i16imm:$seg),
|
|
"lcall{w}\t{$seg, $off|$off, $seg}", []>, OpSize;
|
|
def FARCALL32i : Iseg32<0x9A, RawFrmImm16, (outs),
|
|
(ins i32imm:$off, i16imm:$seg),
|
|
"lcall{l}\t{$seg, $off|$off, $seg}", []>;
|
|
|
|
def FARCALL16m : I<0xFF, MRM3m, (outs), (ins opaque32mem:$dst),
|
|
"lcall{w}\t{*}$dst", []>, OpSize;
|
|
def FARCALL32m : I<0xFF, MRM3m, (outs), (ins opaque48mem:$dst),
|
|
"lcall{l}\t{*}$dst", []>;
|
|
|
|
// callw for 16 bit code for the assembler.
|
|
let isAsmParserOnly = 1 in
|
|
def CALLpcrel16 : Ii16PCRel<0xE8, RawFrm,
|
|
(outs), (ins i16imm_pcrel:$dst, variable_ops),
|
|
"callw\t$dst", []>, OpSize;
|
|
}
|
|
|
|
|
|
// Tail call stuff.
|
|
|
|
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1,
|
|
isCodeGenOnly = 1 in
|
|
let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
|
|
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
|
|
Uses = [ESP] in {
|
|
def TCRETURNdi : PseudoI<(outs),
|
|
(ins i32imm_pcrel:$dst, i32imm:$offset, variable_ops), []>;
|
|
def TCRETURNri : PseudoI<(outs),
|
|
(ins GR32_TC:$dst, i32imm:$offset, variable_ops), []>;
|
|
let mayLoad = 1 in
|
|
def TCRETURNmi : PseudoI<(outs),
|
|
(ins i32mem_TC:$dst, i32imm:$offset, variable_ops), []>;
|
|
|
|
// FIXME: The should be pseudo instructions that are lowered when going to
|
|
// mcinst.
|
|
def TAILJMPd : Ii32PCRel<0xE9, RawFrm, (outs),
|
|
(ins i32imm_pcrel:$dst, variable_ops),
|
|
"jmp\t$dst # TAILCALL",
|
|
[]>;
|
|
def TAILJMPr : I<0xFF, MRM4r, (outs), (ins GR32_TC:$dst, variable_ops),
|
|
"", []>; // FIXME: Remove encoding when JIT is dead.
|
|
let mayLoad = 1 in
|
|
def TAILJMPm : I<0xFF, MRM4m, (outs), (ins i32mem_TC:$dst, variable_ops),
|
|
"jmp{l}\t{*}$dst # TAILCALL", []>;
|
|
}
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Call Instructions...
|
|
//
|
|
let isCall = 1 in
|
|
// All calls clobber the non-callee saved registers. RSP is marked as
|
|
// a use to prevent stack-pointer assignments that appear immediately
|
|
// before calls from potentially appearing dead. Uses for argument
|
|
// registers are added manually.
|
|
let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
|
|
FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
|
|
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
|
|
Uses = [RSP] in {
|
|
|
|
// NOTE: this pattern doesn't match "X86call imm", because we do not know
|
|
// that the offset between an arbitrary immediate and the call will fit in
|
|
// the 32-bit pcrel field that we have.
|
|
def CALL64pcrel32 : Ii32PCRel<0xE8, RawFrm,
|
|
(outs), (ins i64i32imm_pcrel:$dst, variable_ops),
|
|
"call{q}\t$dst", []>,
|
|
Requires<[In64BitMode, NotWin64]>;
|
|
def CALL64r : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
|
|
"call{q}\t{*}$dst", [(X86call GR64:$dst)]>,
|
|
Requires<[In64BitMode, NotWin64]>;
|
|
def CALL64m : I<0xFF, MRM2m, (outs), (ins i64mem:$dst, variable_ops),
|
|
"call{q}\t{*}$dst", [(X86call (loadi64 addr:$dst))]>,
|
|
Requires<[In64BitMode, NotWin64]>;
|
|
|
|
def FARCALL64 : RI<0xFF, MRM3m, (outs), (ins opaque80mem:$dst),
|
|
"lcall{q}\t{*}$dst", []>;
|
|
}
|
|
|
|
// FIXME: We need to teach codegen about single list of call-clobbered
|
|
// registers.
|
|
let isCall = 1, isCodeGenOnly = 1 in
|
|
// All calls clobber the non-callee saved registers. RSP is marked as
|
|
// a use to prevent stack-pointer assignments that appear immediately
|
|
// before calls from potentially appearing dead. Uses for argument
|
|
// registers are added manually.
|
|
let Defs = [RAX, RCX, RDX, R8, R9, R10, R11,
|
|
FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, YMM_HI_6_15, EFLAGS],
|
|
Uses = [RSP] in {
|
|
def WINCALL64pcrel32 : Ii32PCRel<0xE8, RawFrm,
|
|
(outs), (ins i64i32imm_pcrel:$dst, variable_ops),
|
|
"call{q}\t$dst", []>,
|
|
Requires<[IsWin64]>;
|
|
def WINCALL64r : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
|
|
"call{q}\t{*}$dst",
|
|
[(X86call GR64:$dst)]>, Requires<[IsWin64]>;
|
|
def WINCALL64m : I<0xFF, MRM2m, (outs),
|
|
(ins i64mem:$dst,variable_ops),
|
|
"call{q}\t{*}$dst",
|
|
[(X86call (loadi64 addr:$dst))]>,
|
|
Requires<[IsWin64]>;
|
|
}
|
|
|
|
let isCall = 1, isCodeGenOnly = 1 in
|
|
// __chkstk(MSVC): clobber R10, R11 and EFLAGS.
|
|
// ___chkstk(Mingw64): clobber R10, R11, RAX and EFLAGS, and update RSP.
|
|
let Defs = [RAX, R10, R11, RSP, EFLAGS],
|
|
Uses = [RSP] in {
|
|
def W64ALLOCA : Ii32PCRel<0xE8, RawFrm,
|
|
(outs), (ins i64i32imm_pcrel:$dst, variable_ops),
|
|
"call{q}\t$dst", []>,
|
|
Requires<[IsWin64]>;
|
|
}
|
|
|
|
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1,
|
|
isCodeGenOnly = 1 in
|
|
// AMD64 cc clobbers RSI, RDI, XMM6-XMM15.
|
|
let Defs = [RAX, RCX, RDX, R8, R9, R10, R11,
|
|
FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
|
|
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
|
|
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, EFLAGS],
|
|
Uses = [RSP],
|
|
usesCustomInserter = 1 in {
|
|
def TCRETURNdi64 : PseudoI<(outs),
|
|
(ins i64i32imm_pcrel:$dst, i32imm:$offset, variable_ops),
|
|
[]>;
|
|
def TCRETURNri64 : PseudoI<(outs),
|
|
(ins ptr_rc_tailcall:$dst, i32imm:$offset, variable_ops), []>;
|
|
let mayLoad = 1 in
|
|
def TCRETURNmi64 : PseudoI<(outs),
|
|
(ins i64mem_TC:$dst, i32imm:$offset, variable_ops), []>;
|
|
|
|
def TAILJMPd64 : Ii32PCRel<0xE9, RawFrm, (outs),
|
|
(ins i64i32imm_pcrel:$dst, variable_ops),
|
|
"jmp\t$dst # TAILCALL", []>;
|
|
def TAILJMPr64 : I<0xFF, MRM4r, (outs), (ins ptr_rc_tailcall:$dst, variable_ops),
|
|
"jmp{q}\t{*}$dst # TAILCALL", []>;
|
|
|
|
let mayLoad = 1 in
|
|
def TAILJMPm64 : I<0xFF, MRM4m, (outs), (ins i64mem_TC:$dst, variable_ops),
|
|
"jmp{q}\t{*}$dst # TAILCALL", []>;
|
|
}
|