llvm-project/llvm/lib/Target/X86/X86InstrCompiler.td

1863 lines
83 KiB
TableGen

//===- X86InstrCompiler.td - Compiler Pseudos and Patterns -*- 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 various pseudo instructions used by the compiler,
// as well as Pat patterns used during instruction selection.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// Pattern Matching Support
def GetLo32XForm : SDNodeXForm<imm, [{
// Transformation function: get the low 32 bits.
return getI32Imm((unsigned)N->getZExtValue());
}]>;
def GetLo8XForm : SDNodeXForm<imm, [{
// Transformation function: get the low 8 bits.
return getI8Imm((uint8_t)N->getZExtValue());
}]>;
//===----------------------------------------------------------------------===//
// Random Pseudo Instructions.
// PIC base construction. This expands to code that looks like this:
// call $next_inst
// popl %destreg"
let hasSideEffects = 0, isNotDuplicable = 1, Uses = [ESP] in
def MOVPC32r : Ii32<0xE8, Pseudo, (outs GR32:$reg), (ins i32imm:$label),
"", []>;
// ADJCALLSTACKDOWN/UP implicitly use/def ESP because they may be expanded into
// a stack adjustment and the codegen must know that they may modify the stack
// pointer before prolog-epilog rewriting occurs.
// Pessimistically assume ADJCALLSTACKDOWN / ADJCALLSTACKUP will become
// sub / add which can clobber EFLAGS.
let Defs = [ESP, EFLAGS], Uses = [ESP] in {
def ADJCALLSTACKDOWN32 : I<0, Pseudo, (outs), (ins i32imm:$amt),
"#ADJCALLSTACKDOWN",
[(X86callseq_start timm:$amt)]>,
Requires<[NotLP64]>;
def ADJCALLSTACKUP32 : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2),
"#ADJCALLSTACKUP",
[(X86callseq_end timm:$amt1, timm:$amt2)]>,
Requires<[NotLP64]>;
}
// ADJCALLSTACKDOWN/UP implicitly use/def RSP because they may be expanded into
// a stack adjustment and the codegen must know that they may modify the stack
// pointer before prolog-epilog rewriting occurs.
// Pessimistically assume ADJCALLSTACKDOWN / ADJCALLSTACKUP will become
// sub / add which can clobber EFLAGS.
let Defs = [RSP, EFLAGS], Uses = [RSP] in {
def ADJCALLSTACKDOWN64 : I<0, Pseudo, (outs), (ins i32imm:$amt),
"#ADJCALLSTACKDOWN",
[(X86callseq_start timm:$amt)]>,
Requires<[IsLP64]>;
def ADJCALLSTACKUP64 : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2),
"#ADJCALLSTACKUP",
[(X86callseq_end timm:$amt1, timm:$amt2)]>,
Requires<[IsLP64]>;
}
// x86-64 va_start lowering magic.
let usesCustomInserter = 1, Defs = [EFLAGS] in {
def VASTART_SAVE_XMM_REGS : I<0, Pseudo,
(outs),
(ins GR8:$al,
i64imm:$regsavefi, i64imm:$offset,
variable_ops),
"#VASTART_SAVE_XMM_REGS $al, $regsavefi, $offset",
[(X86vastart_save_xmm_regs GR8:$al,
imm:$regsavefi,
imm:$offset),
(implicit EFLAGS)]>;
// The VAARG_64 pseudo-instruction takes the address of the va_list,
// and places the address of the next argument into a register.
let Defs = [EFLAGS] in
def VAARG_64 : I<0, Pseudo,
(outs GR64:$dst),
(ins i8mem:$ap, i32imm:$size, i8imm:$mode, i32imm:$align),
"#VAARG_64 $dst, $ap, $size, $mode, $align",
[(set GR64:$dst,
(X86vaarg64 addr:$ap, imm:$size, imm:$mode, imm:$align)),
(implicit EFLAGS)]>;
// Dynamic stack allocation yields a _chkstk or _alloca call for all Windows
// targets. These calls are needed to probe the stack when allocating more than
// 4k bytes in one go. Touching the stack at 4K increments is necessary to
// ensure that the guard pages used by the OS virtual memory manager are
// allocated in correct sequence.
// The main point of having separate instruction are extra unmodelled effects
// (compared to ordinary calls) like stack pointer change.
let Defs = [EAX, ESP, EFLAGS], Uses = [ESP] in
def WIN_ALLOCA : I<0, Pseudo, (outs), (ins),
"# dynamic stack allocation",
[(X86WinAlloca)]>;
// When using segmented stacks these are lowered into instructions which first
// check if the current stacklet has enough free memory. If it does, memory is
// allocated by bumping the stack pointer. Otherwise memory is allocated from
// the heap.
let Defs = [EAX, ESP, EFLAGS], Uses = [ESP] in
def SEG_ALLOCA_32 : I<0, Pseudo, (outs GR32:$dst), (ins GR32:$size),
"# variable sized alloca for segmented stacks",
[(set GR32:$dst,
(X86SegAlloca GR32:$size))]>,
Requires<[NotLP64]>;
let Defs = [RAX, RSP, EFLAGS], Uses = [RSP] in
def SEG_ALLOCA_64 : I<0, Pseudo, (outs GR64:$dst), (ins GR64:$size),
"# variable sized alloca for segmented stacks",
[(set GR64:$dst,
(X86SegAlloca GR64:$size))]>,
Requires<[In64BitMode]>;
}
// The MSVC runtime contains an _ftol2 routine for converting floating-point
// to integer values. It has a strange calling convention: the input is
// popped from the x87 stack, and the return value is given in EDX:EAX. ECX is
// used as a temporary register. No other registers (aside from flags) are
// touched.
// Microsoft toolchains do not support 80-bit precision, so a WIN_FTOL_80
// variant is unnecessary.
let Defs = [EAX, EDX, ECX, EFLAGS], FPForm = SpecialFP in {
def WIN_FTOL_32 : I<0, Pseudo, (outs), (ins RFP32:$src),
"# win32 fptoui",
[(X86WinFTOL RFP32:$src)]>,
Requires<[Not64BitMode]>;
def WIN_FTOL_64 : I<0, Pseudo, (outs), (ins RFP64:$src),
"# win32 fptoui",
[(X86WinFTOL RFP64:$src)]>,
Requires<[Not64BitMode]>;
}
//===----------------------------------------------------------------------===//
// EH Pseudo Instructions
//
let SchedRW = [WriteSystem] in {
let isTerminator = 1, isReturn = 1, isBarrier = 1,
hasCtrlDep = 1, isCodeGenOnly = 1 in {
def EH_RETURN : I<0xC3, RawFrm, (outs), (ins GR32:$addr),
"ret\t#eh_return, addr: $addr",
[(X86ehret GR32:$addr)], IIC_RET>, Sched<[WriteJumpLd]>;
}
let isTerminator = 1, isReturn = 1, isBarrier = 1,
hasCtrlDep = 1, isCodeGenOnly = 1 in {
def EH_RETURN64 : I<0xC3, RawFrm, (outs), (ins GR64:$addr),
"ret\t#eh_return, addr: $addr",
[(X86ehret GR64:$addr)], IIC_RET>, Sched<[WriteJumpLd]>;
}
let hasSideEffects = 1, isBarrier = 1, isCodeGenOnly = 1,
usesCustomInserter = 1 in {
def EH_SjLj_SetJmp32 : I<0, Pseudo, (outs GR32:$dst), (ins i32mem:$buf),
"#EH_SJLJ_SETJMP32",
[(set GR32:$dst, (X86eh_sjlj_setjmp addr:$buf))]>,
Requires<[Not64BitMode]>;
def EH_SjLj_SetJmp64 : I<0, Pseudo, (outs GR32:$dst), (ins i64mem:$buf),
"#EH_SJLJ_SETJMP64",
[(set GR32:$dst, (X86eh_sjlj_setjmp addr:$buf))]>,
Requires<[In64BitMode]>;
let isTerminator = 1 in {
def EH_SjLj_LongJmp32 : I<0, Pseudo, (outs), (ins i32mem:$buf),
"#EH_SJLJ_LONGJMP32",
[(X86eh_sjlj_longjmp addr:$buf)]>,
Requires<[Not64BitMode]>;
def EH_SjLj_LongJmp64 : I<0, Pseudo, (outs), (ins i64mem:$buf),
"#EH_SJLJ_LONGJMP64",
[(X86eh_sjlj_longjmp addr:$buf)]>,
Requires<[In64BitMode]>;
}
}
} // SchedRW
let isBranch = 1, isTerminator = 1, isCodeGenOnly = 1 in {
def EH_SjLj_Setup : I<0, Pseudo, (outs), (ins brtarget:$dst),
"#EH_SjLj_Setup\t$dst", []>;
}
//===----------------------------------------------------------------------===//
// Pseudo instructions used by unwind info.
//
let isPseudo = 1 in {
def SEH_PushReg : I<0, Pseudo, (outs), (ins i32imm:$reg),
"#SEH_PushReg $reg", []>;
def SEH_SaveReg : I<0, Pseudo, (outs), (ins i32imm:$reg, i32imm:$dst),
"#SEH_SaveReg $reg, $dst", []>;
def SEH_SaveXMM : I<0, Pseudo, (outs), (ins i32imm:$reg, i32imm:$dst),
"#SEH_SaveXMM $reg, $dst", []>;
def SEH_StackAlloc : I<0, Pseudo, (outs), (ins i32imm:$size),
"#SEH_StackAlloc $size", []>;
def SEH_SetFrame : I<0, Pseudo, (outs), (ins i32imm:$reg, i32imm:$offset),
"#SEH_SetFrame $reg, $offset", []>;
def SEH_PushFrame : I<0, Pseudo, (outs), (ins i1imm:$mode),
"#SEH_PushFrame $mode", []>;
def SEH_EndPrologue : I<0, Pseudo, (outs), (ins),
"#SEH_EndPrologue", []>;
def SEH_Epilogue : I<0, Pseudo, (outs), (ins),
"#SEH_Epilogue", []>;
}
//===----------------------------------------------------------------------===//
// Pseudo instructions used by segmented stacks.
//
// This is lowered into a RET instruction by MCInstLower. We need
// this so that we don't have to have a MachineBasicBlock which ends
// with a RET and also has successors.
let isPseudo = 1 in {
def MORESTACK_RET: I<0, Pseudo, (outs), (ins),
"", []>;
// This instruction is lowered to a RET followed by a MOV. The two
// instructions are not generated on a higher level since then the
// verifier sees a MachineBasicBlock ending with a non-terminator.
def MORESTACK_RET_RESTORE_R10 : I<0, Pseudo, (outs), (ins),
"", []>;
}
//===----------------------------------------------------------------------===//
// Alias Instructions
//===----------------------------------------------------------------------===//
// Alias instruction mapping movr0 to xor.
// FIXME: remove when we can teach regalloc that xor reg, reg is ok.
let Defs = [EFLAGS], isReMaterializable = 1, isAsCheapAsAMove = 1,
isPseudo = 1 in
def MOV32r0 : I<0, Pseudo, (outs GR32:$dst), (ins), "",
[(set GR32:$dst, 0)], IIC_ALU_NONMEM>, Sched<[WriteZero]>;
// Other widths can also make use of the 32-bit xor, which may have a smaller
// encoding and avoid partial register updates.
def : Pat<(i8 0), (EXTRACT_SUBREG (MOV32r0), sub_8bit)>;
def : Pat<(i16 0), (EXTRACT_SUBREG (MOV32r0), sub_16bit)>;
def : Pat<(i64 0), (SUBREG_TO_REG (i64 0), (MOV32r0), sub_32bit)> {
let AddedComplexity = 20;
}
// Materialize i64 constant where top 32-bits are zero. This could theoretically
// use MOV32ri with a SUBREG_TO_REG to represent the zero-extension, however
// that would make it more difficult to rematerialize.
let AddedComplexity = 1, isReMaterializable = 1, isAsCheapAsAMove = 1,
isCodeGenOnly = 1, hasSideEffects = 0 in
def MOV32ri64 : Ii32<0xb8, AddRegFrm, (outs GR32:$dst), (ins i64i32imm:$src),
"", [], IIC_ALU_NONMEM>, Sched<[WriteALU]>;
// This 64-bit pseudo-move can be used for both a 64-bit constant that is
// actually the zero-extension of a 32-bit constant, and for labels in the
// x86-64 small code model.
def mov64imm32 : ComplexPattern<i64, 1, "SelectMOV64Imm32", [imm, X86Wrapper]>;
let AddedComplexity = 1 in
def : Pat<(i64 mov64imm32:$src),
(SUBREG_TO_REG (i64 0), (MOV32ri64 mov64imm32:$src), sub_32bit)>;
// Use sbb to materialize carry bit.
let Uses = [EFLAGS], Defs = [EFLAGS], isPseudo = 1, SchedRW = [WriteALU] in {
// FIXME: These are pseudo ops that should be replaced with Pat<> patterns.
// However, Pat<> can't replicate the destination reg into the inputs of the
// result.
def SETB_C8r : I<0, Pseudo, (outs GR8:$dst), (ins), "",
[(set GR8:$dst, (X86setcc_c X86_COND_B, EFLAGS))]>;
def SETB_C16r : I<0, Pseudo, (outs GR16:$dst), (ins), "",
[(set GR16:$dst, (X86setcc_c X86_COND_B, EFLAGS))]>;
def SETB_C32r : I<0, Pseudo, (outs GR32:$dst), (ins), "",
[(set GR32:$dst, (X86setcc_c X86_COND_B, EFLAGS))]>;
def SETB_C64r : I<0, Pseudo, (outs GR64:$dst), (ins), "",
[(set GR64:$dst, (X86setcc_c X86_COND_B, EFLAGS))]>;
} // isCodeGenOnly
def : Pat<(i16 (anyext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C16r)>;
def : Pat<(i32 (anyext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C32r)>;
def : Pat<(i64 (anyext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C64r)>;
def : Pat<(i16 (sext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C16r)>;
def : Pat<(i32 (sext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C32r)>;
def : Pat<(i64 (sext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C64r)>;
// We canonicalize 'setb' to "(and (sbb reg,reg), 1)" on the hope that the and
// will be eliminated and that the sbb can be extended up to a wider type. When
// this happens, it is great. However, if we are left with an 8-bit sbb and an
// and, we might as well just match it as a setb.
def : Pat<(and (i8 (X86setcc_c X86_COND_B, EFLAGS)), 1),
(SETBr)>;
// (add OP, SETB) -> (adc OP, 0)
def : Pat<(add (and (i8 (X86setcc_c X86_COND_B, EFLAGS)), 1), GR8:$op),
(ADC8ri GR8:$op, 0)>;
def : Pat<(add (and (i32 (X86setcc_c X86_COND_B, EFLAGS)), 1), GR32:$op),
(ADC32ri8 GR32:$op, 0)>;
def : Pat<(add (and (i64 (X86setcc_c X86_COND_B, EFLAGS)), 1), GR64:$op),
(ADC64ri8 GR64:$op, 0)>;
// (sub OP, SETB) -> (sbb OP, 0)
def : Pat<(sub GR8:$op, (and (i8 (X86setcc_c X86_COND_B, EFLAGS)), 1)),
(SBB8ri GR8:$op, 0)>;
def : Pat<(sub GR32:$op, (and (i32 (X86setcc_c X86_COND_B, EFLAGS)), 1)),
(SBB32ri8 GR32:$op, 0)>;
def : Pat<(sub GR64:$op, (and (i64 (X86setcc_c X86_COND_B, EFLAGS)), 1)),
(SBB64ri8 GR64:$op, 0)>;
// (sub OP, SETCC_CARRY) -> (adc OP, 0)
def : Pat<(sub GR8:$op, (i8 (X86setcc_c X86_COND_B, EFLAGS))),
(ADC8ri GR8:$op, 0)>;
def : Pat<(sub GR32:$op, (i32 (X86setcc_c X86_COND_B, EFLAGS))),
(ADC32ri8 GR32:$op, 0)>;
def : Pat<(sub GR64:$op, (i64 (X86setcc_c X86_COND_B, EFLAGS))),
(ADC64ri8 GR64:$op, 0)>;
//===----------------------------------------------------------------------===//
// String Pseudo Instructions
//
let SchedRW = [WriteMicrocoded] in {
let Defs = [ECX,EDI,ESI], Uses = [ECX,EDI,ESI], isCodeGenOnly = 1 in {
def REP_MOVSB_32 : I<0xA4, RawFrm, (outs), (ins), "{rep;movsb|rep movsb}",
[(X86rep_movs i8)], IIC_REP_MOVS>, REP,
Requires<[Not64BitMode]>;
def REP_MOVSW_32 : I<0xA5, RawFrm, (outs), (ins), "{rep;movsw|rep movsw}",
[(X86rep_movs i16)], IIC_REP_MOVS>, REP, OpSize16,
Requires<[Not64BitMode]>;
def REP_MOVSD_32 : I<0xA5, RawFrm, (outs), (ins), "{rep;movsl|rep movsd}",
[(X86rep_movs i32)], IIC_REP_MOVS>, REP, OpSize32,
Requires<[Not64BitMode]>;
}
let Defs = [RCX,RDI,RSI], Uses = [RCX,RDI,RSI], isCodeGenOnly = 1 in {
def REP_MOVSB_64 : I<0xA4, RawFrm, (outs), (ins), "{rep;movsb|rep movsb}",
[(X86rep_movs i8)], IIC_REP_MOVS>, REP,
Requires<[In64BitMode]>;
def REP_MOVSW_64 : I<0xA5, RawFrm, (outs), (ins), "{rep;movsw|rep movsw}",
[(X86rep_movs i16)], IIC_REP_MOVS>, REP, OpSize16,
Requires<[In64BitMode]>;
def REP_MOVSD_64 : I<0xA5, RawFrm, (outs), (ins), "{rep;movsl|rep movsd}",
[(X86rep_movs i32)], IIC_REP_MOVS>, REP, OpSize32,
Requires<[In64BitMode]>;
def REP_MOVSQ_64 : RI<0xA5, RawFrm, (outs), (ins), "{rep;movsq|rep movsq}",
[(X86rep_movs i64)], IIC_REP_MOVS>, REP,
Requires<[In64BitMode]>;
}
// FIXME: Should use "(X86rep_stos AL)" as the pattern.
let Defs = [ECX,EDI], isCodeGenOnly = 1 in {
let Uses = [AL,ECX,EDI] in
def REP_STOSB_32 : I<0xAA, RawFrm, (outs), (ins), "{rep;stosb|rep stosb}",
[(X86rep_stos i8)], IIC_REP_STOS>, REP,
Requires<[Not64BitMode]>;
let Uses = [AX,ECX,EDI] in
def REP_STOSW_32 : I<0xAB, RawFrm, (outs), (ins), "{rep;stosw|rep stosw}",
[(X86rep_stos i16)], IIC_REP_STOS>, REP, OpSize16,
Requires<[Not64BitMode]>;
let Uses = [EAX,ECX,EDI] in
def REP_STOSD_32 : I<0xAB, RawFrm, (outs), (ins), "{rep;stosl|rep stosd}",
[(X86rep_stos i32)], IIC_REP_STOS>, REP, OpSize32,
Requires<[Not64BitMode]>;
}
let Defs = [RCX,RDI], isCodeGenOnly = 1 in {
let Uses = [AL,RCX,RDI] in
def REP_STOSB_64 : I<0xAA, RawFrm, (outs), (ins), "{rep;stosb|rep stosb}",
[(X86rep_stos i8)], IIC_REP_STOS>, REP,
Requires<[In64BitMode]>;
let Uses = [AX,RCX,RDI] in
def REP_STOSW_64 : I<0xAB, RawFrm, (outs), (ins), "{rep;stosw|rep stosw}",
[(X86rep_stos i16)], IIC_REP_STOS>, REP, OpSize16,
Requires<[In64BitMode]>;
let Uses = [RAX,RCX,RDI] in
def REP_STOSD_64 : I<0xAB, RawFrm, (outs), (ins), "{rep;stosl|rep stosd}",
[(X86rep_stos i32)], IIC_REP_STOS>, REP, OpSize32,
Requires<[In64BitMode]>;
let Uses = [RAX,RCX,RDI] in
def REP_STOSQ_64 : RI<0xAB, RawFrm, (outs), (ins), "{rep;stosq|rep stosq}",
[(X86rep_stos i64)], IIC_REP_STOS>, REP,
Requires<[In64BitMode]>;
}
} // SchedRW
//===----------------------------------------------------------------------===//
// Thread Local Storage Instructions
//
// ELF TLS Support
// 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.
let Defs = [EAX, ECX, EDX, FP0, FP1, FP2, FP3, FP4, FP5, FP6, FP7,
ST0, ST1, ST2, ST3, ST4, ST5, ST6, ST7,
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 TLS_addr32 : I<0, Pseudo, (outs), (ins i32mem:$sym),
"# TLS_addr32",
[(X86tlsaddr tls32addr:$sym)]>,
Requires<[Not64BitMode]>;
def TLS_base_addr32 : I<0, Pseudo, (outs), (ins i32mem:$sym),
"# TLS_base_addr32",
[(X86tlsbaseaddr tls32baseaddr:$sym)]>,
Requires<[Not64BitMode]>;
}
// All calls clobber the non-callee saved registers. RSP is marked as
// a use to prevent stack-pointer assignments that appear immediately
// before calls from potentially appearing dead.
let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
FP0, FP1, FP2, FP3, FP4, FP5, FP6, FP7,
ST0, ST1, ST2, ST3, ST4, ST5, ST6, ST7,
MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
Uses = [RSP] in {
def TLS_addr64 : I<0, Pseudo, (outs), (ins i64mem:$sym),
"# TLS_addr64",
[(X86tlsaddr tls64addr:$sym)]>,
Requires<[In64BitMode]>;
def TLS_base_addr64 : I<0, Pseudo, (outs), (ins i64mem:$sym),
"# TLS_base_addr64",
[(X86tlsbaseaddr tls64baseaddr:$sym)]>,
Requires<[In64BitMode]>;
}
// Darwin TLS Support
// For i386, the address of the thunk is passed on the stack, on return the
// address of the variable is in %eax. %ecx is trashed during the function
// call. All other registers are preserved.
let Defs = [EAX, ECX, EFLAGS],
Uses = [ESP],
usesCustomInserter = 1 in
def TLSCall_32 : I<0, Pseudo, (outs), (ins i32mem:$sym),
"# TLSCall_32",
[(X86TLSCall addr:$sym)]>,
Requires<[Not64BitMode]>;
// For x86_64, the address of the thunk is passed in %rdi, on return
// the address of the variable is in %rax. All other registers are preserved.
let Defs = [RAX, EFLAGS],
Uses = [RSP, RDI],
usesCustomInserter = 1 in
def TLSCall_64 : I<0, Pseudo, (outs), (ins i64mem:$sym),
"# TLSCall_64",
[(X86TLSCall addr:$sym)]>,
Requires<[In64BitMode]>;
//===----------------------------------------------------------------------===//
// Conditional Move Pseudo Instructions
// X86 doesn't have 8-bit conditional moves. Use a customInserter to
// emit control flow. An alternative to this is to mark i8 SELECT as Promote,
// however that requires promoting the operands, and can induce additional
// i8 register pressure.
let usesCustomInserter = 1, Uses = [EFLAGS] in {
def CMOV_GR8 : I<0, Pseudo,
(outs GR8:$dst), (ins GR8:$src1, GR8:$src2, i8imm:$cond),
"#CMOV_GR8 PSEUDO!",
[(set GR8:$dst, (X86cmov GR8:$src1, GR8:$src2,
imm:$cond, EFLAGS))]>;
let Predicates = [NoCMov] in {
def CMOV_GR32 : I<0, Pseudo,
(outs GR32:$dst), (ins GR32:$src1, GR32:$src2, i8imm:$cond),
"#CMOV_GR32* PSEUDO!",
[(set GR32:$dst,
(X86cmov GR32:$src1, GR32:$src2, imm:$cond, EFLAGS))]>;
def CMOV_GR16 : I<0, Pseudo,
(outs GR16:$dst), (ins GR16:$src1, GR16:$src2, i8imm:$cond),
"#CMOV_GR16* PSEUDO!",
[(set GR16:$dst,
(X86cmov GR16:$src1, GR16:$src2, imm:$cond, EFLAGS))]>;
} // Predicates = [NoCMov]
// fcmov doesn't handle all possible EFLAGS, provide a fallback if there is no
// SSE1.
let Predicates = [FPStackf32] in
def CMOV_RFP32 : I<0, Pseudo,
(outs RFP32:$dst),
(ins RFP32:$src1, RFP32:$src2, i8imm:$cond),
"#CMOV_RFP32 PSEUDO!",
[(set RFP32:$dst,
(X86cmov RFP32:$src1, RFP32:$src2, imm:$cond,
EFLAGS))]>;
// fcmov doesn't handle all possible EFLAGS, provide a fallback if there is no
// SSE2.
let Predicates = [FPStackf64] in
def CMOV_RFP64 : I<0, Pseudo,
(outs RFP64:$dst),
(ins RFP64:$src1, RFP64:$src2, i8imm:$cond),
"#CMOV_RFP64 PSEUDO!",
[(set RFP64:$dst,
(X86cmov RFP64:$src1, RFP64:$src2, imm:$cond,
EFLAGS))]>;
def CMOV_RFP80 : I<0, Pseudo,
(outs RFP80:$dst),
(ins RFP80:$src1, RFP80:$src2, i8imm:$cond),
"#CMOV_RFP80 PSEUDO!",
[(set RFP80:$dst,
(X86cmov RFP80:$src1, RFP80:$src2, imm:$cond,
EFLAGS))]>;
} // UsesCustomInserter = 1, Uses = [EFLAGS]
//===----------------------------------------------------------------------===//
// Normal-Instructions-With-Lock-Prefix Pseudo Instructions
//===----------------------------------------------------------------------===//
// FIXME: Use normal instructions and add lock prefix dynamically.
// Memory barriers
// TODO: Get this to fold the constant into the instruction.
let isCodeGenOnly = 1, Defs = [EFLAGS] in
def OR32mrLocked : I<0x09, MRMDestMem, (outs), (ins i32mem:$dst, GR32:$zero),
"or{l}\t{$zero, $dst|$dst, $zero}",
[], IIC_ALU_MEM>, Requires<[Not64BitMode]>, LOCK,
Sched<[WriteALULd, WriteRMW]>;
let hasSideEffects = 1 in
def Int_MemBarrier : I<0, Pseudo, (outs), (ins),
"#MEMBARRIER",
[(X86MemBarrier)]>, Sched<[WriteLoad]>;
// RegOpc corresponds to the mr version of the instruction
// ImmOpc corresponds to the mi version of the instruction
// ImmOpc8 corresponds to the mi8 version of the instruction
// ImmMod corresponds to the instruction format of the mi and mi8 versions
multiclass LOCK_ArithBinOp<bits<8> RegOpc, bits<8> ImmOpc, bits<8> ImmOpc8,
Format ImmMod, string mnemonic> {
let Defs = [EFLAGS], mayLoad = 1, mayStore = 1, isCodeGenOnly = 1,
SchedRW = [WriteALULd, WriteRMW] in {
def NAME#8mr : I<{RegOpc{7}, RegOpc{6}, RegOpc{5}, RegOpc{4},
RegOpc{3}, RegOpc{2}, RegOpc{1}, 0 },
MRMDestMem, (outs), (ins i8mem:$dst, GR8:$src2),
!strconcat(mnemonic, "{b}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_NONMEM>, LOCK;
def NAME#16mr : I<{RegOpc{7}, RegOpc{6}, RegOpc{5}, RegOpc{4},
RegOpc{3}, RegOpc{2}, RegOpc{1}, 1 },
MRMDestMem, (outs), (ins i16mem:$dst, GR16:$src2),
!strconcat(mnemonic, "{w}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_NONMEM>, OpSize16, LOCK;
def NAME#32mr : I<{RegOpc{7}, RegOpc{6}, RegOpc{5}, RegOpc{4},
RegOpc{3}, RegOpc{2}, RegOpc{1}, 1 },
MRMDestMem, (outs), (ins i32mem:$dst, GR32:$src2),
!strconcat(mnemonic, "{l}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_NONMEM>, OpSize32, LOCK;
def NAME#64mr : RI<{RegOpc{7}, RegOpc{6}, RegOpc{5}, RegOpc{4},
RegOpc{3}, RegOpc{2}, RegOpc{1}, 1 },
MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
!strconcat(mnemonic, "{q}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_NONMEM>, LOCK;
def NAME#8mi : Ii8<{ImmOpc{7}, ImmOpc{6}, ImmOpc{5}, ImmOpc{4},
ImmOpc{3}, ImmOpc{2}, ImmOpc{1}, 0 },
ImmMod, (outs), (ins i8mem :$dst, i8imm :$src2),
!strconcat(mnemonic, "{b}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_MEM>, LOCK;
def NAME#16mi : Ii16<{ImmOpc{7}, ImmOpc{6}, ImmOpc{5}, ImmOpc{4},
ImmOpc{3}, ImmOpc{2}, ImmOpc{1}, 1 },
ImmMod, (outs), (ins i16mem :$dst, i16imm :$src2),
!strconcat(mnemonic, "{w}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_MEM>, OpSize16, LOCK;
def NAME#32mi : Ii32<{ImmOpc{7}, ImmOpc{6}, ImmOpc{5}, ImmOpc{4},
ImmOpc{3}, ImmOpc{2}, ImmOpc{1}, 1 },
ImmMod, (outs), (ins i32mem :$dst, i32imm :$src2),
!strconcat(mnemonic, "{l}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_MEM>, OpSize32, LOCK;
def NAME#64mi32 : RIi32<{ImmOpc{7}, ImmOpc{6}, ImmOpc{5}, ImmOpc{4},
ImmOpc{3}, ImmOpc{2}, ImmOpc{1}, 1 },
ImmMod, (outs), (ins i64mem :$dst, i64i32imm :$src2),
!strconcat(mnemonic, "{q}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_MEM>, LOCK;
def NAME#16mi8 : Ii8<{ImmOpc8{7}, ImmOpc8{6}, ImmOpc8{5}, ImmOpc8{4},
ImmOpc8{3}, ImmOpc8{2}, ImmOpc8{1}, 1 },
ImmMod, (outs), (ins i16mem :$dst, i16i8imm :$src2),
!strconcat(mnemonic, "{w}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_MEM>, OpSize16, LOCK;
def NAME#32mi8 : Ii8<{ImmOpc8{7}, ImmOpc8{6}, ImmOpc8{5}, ImmOpc8{4},
ImmOpc8{3}, ImmOpc8{2}, ImmOpc8{1}, 1 },
ImmMod, (outs), (ins i32mem :$dst, i32i8imm :$src2),
!strconcat(mnemonic, "{l}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_MEM>, OpSize32, LOCK;
def NAME#64mi8 : RIi8<{ImmOpc8{7}, ImmOpc8{6}, ImmOpc8{5}, ImmOpc8{4},
ImmOpc8{3}, ImmOpc8{2}, ImmOpc8{1}, 1 },
ImmMod, (outs), (ins i64mem :$dst, i64i8imm :$src2),
!strconcat(mnemonic, "{q}\t",
"{$src2, $dst|$dst, $src2}"),
[], IIC_ALU_MEM>, LOCK;
}
}
defm LOCK_ADD : LOCK_ArithBinOp<0x00, 0x80, 0x83, MRM0m, "add">;
defm LOCK_SUB : LOCK_ArithBinOp<0x28, 0x80, 0x83, MRM5m, "sub">;
defm LOCK_OR : LOCK_ArithBinOp<0x08, 0x80, 0x83, MRM1m, "or">;
defm LOCK_AND : LOCK_ArithBinOp<0x20, 0x80, 0x83, MRM4m, "and">;
defm LOCK_XOR : LOCK_ArithBinOp<0x30, 0x80, 0x83, MRM6m, "xor">;
// Optimized codegen when the non-memory output is not used.
multiclass LOCK_ArithUnOp<bits<8> Opc8, bits<8> Opc, Format Form,
string mnemonic> {
let Defs = [EFLAGS], mayLoad = 1, mayStore = 1, isCodeGenOnly = 1,
SchedRW = [WriteALULd, WriteRMW] in {
def NAME#8m : I<Opc8, Form, (outs), (ins i8mem :$dst),
!strconcat(mnemonic, "{b}\t$dst"),
[], IIC_UNARY_MEM>, LOCK;
def NAME#16m : I<Opc, Form, (outs), (ins i16mem:$dst),
!strconcat(mnemonic, "{w}\t$dst"),
[], IIC_UNARY_MEM>, OpSize16, LOCK;
def NAME#32m : I<Opc, Form, (outs), (ins i32mem:$dst),
!strconcat(mnemonic, "{l}\t$dst"),
[], IIC_UNARY_MEM>, OpSize32, LOCK;
def NAME#64m : RI<Opc, Form, (outs), (ins i64mem:$dst),
!strconcat(mnemonic, "{q}\t$dst"),
[], IIC_UNARY_MEM>, LOCK;
}
}
defm LOCK_INC : LOCK_ArithUnOp<0xFE, 0xFF, MRM0m, "inc">;
defm LOCK_DEC : LOCK_ArithUnOp<0xFE, 0xFF, MRM1m, "dec">;
// Atomic compare and swap.
multiclass LCMPXCHG_UnOp<bits<8> Opc, Format Form, string mnemonic,
SDPatternOperator frag, X86MemOperand x86memop,
InstrItinClass itin> {
let isCodeGenOnly = 1 in {
def NAME : I<Opc, Form, (outs), (ins x86memop:$ptr),
!strconcat(mnemonic, "\t$ptr"),
[(frag addr:$ptr)], itin>, TB, LOCK;
}
}
multiclass LCMPXCHG_BinOp<bits<8> Opc8, bits<8> Opc, Format Form,
string mnemonic, SDPatternOperator frag,
InstrItinClass itin8, InstrItinClass itin> {
let isCodeGenOnly = 1, SchedRW = [WriteALULd, WriteRMW] in {
let Defs = [AL, EFLAGS], Uses = [AL] in
def NAME#8 : I<Opc8, Form, (outs), (ins i8mem:$ptr, GR8:$swap),
!strconcat(mnemonic, "{b}\t{$swap, $ptr|$ptr, $swap}"),
[(frag addr:$ptr, GR8:$swap, 1)], itin8>, TB, LOCK;
let Defs = [AX, EFLAGS], Uses = [AX] in
def NAME#16 : I<Opc, Form, (outs), (ins i16mem:$ptr, GR16:$swap),
!strconcat(mnemonic, "{w}\t{$swap, $ptr|$ptr, $swap}"),
[(frag addr:$ptr, GR16:$swap, 2)], itin>, TB, OpSize16, LOCK;
let Defs = [EAX, EFLAGS], Uses = [EAX] in
def NAME#32 : I<Opc, Form, (outs), (ins i32mem:$ptr, GR32:$swap),
!strconcat(mnemonic, "{l}\t{$swap, $ptr|$ptr, $swap}"),
[(frag addr:$ptr, GR32:$swap, 4)], itin>, TB, OpSize32, LOCK;
let Defs = [RAX, EFLAGS], Uses = [RAX] in
def NAME#64 : RI<Opc, Form, (outs), (ins i64mem:$ptr, GR64:$swap),
!strconcat(mnemonic, "{q}\t{$swap, $ptr|$ptr, $swap}"),
[(frag addr:$ptr, GR64:$swap, 8)], itin>, TB, LOCK;
}
}
let Defs = [EAX, EDX, EFLAGS], Uses = [EAX, EBX, ECX, EDX],
SchedRW = [WriteALULd, WriteRMW] in {
defm LCMPXCHG8B : LCMPXCHG_UnOp<0xC7, MRM1m, "cmpxchg8b",
X86cas8, i64mem,
IIC_CMPX_LOCK_8B>;
}
let Defs = [RAX, RDX, EFLAGS], Uses = [RAX, RBX, RCX, RDX],
Predicates = [HasCmpxchg16b], SchedRW = [WriteALULd, WriteRMW] in {
defm LCMPXCHG16B : LCMPXCHG_UnOp<0xC7, MRM1m, "cmpxchg16b",
X86cas16, i128mem,
IIC_CMPX_LOCK_16B>, REX_W;
}
defm LCMPXCHG : LCMPXCHG_BinOp<0xB0, 0xB1, MRMDestMem, "cmpxchg",
X86cas, IIC_CMPX_LOCK_8, IIC_CMPX_LOCK>;
// Atomic exchange and add
multiclass ATOMIC_LOAD_BINOP<bits<8> opc8, bits<8> opc, string mnemonic,
string frag,
InstrItinClass itin8, InstrItinClass itin> {
let Constraints = "$val = $dst", Defs = [EFLAGS], isCodeGenOnly = 1,
SchedRW = [WriteALULd, WriteRMW] in {
def NAME#8 : I<opc8, MRMSrcMem, (outs GR8:$dst),
(ins GR8:$val, i8mem:$ptr),
!strconcat(mnemonic, "{b}\t{$val, $ptr|$ptr, $val}"),
[(set GR8:$dst,
(!cast<PatFrag>(frag # "_8") addr:$ptr, GR8:$val))],
itin8>;
def NAME#16 : I<opc, MRMSrcMem, (outs GR16:$dst),
(ins GR16:$val, i16mem:$ptr),
!strconcat(mnemonic, "{w}\t{$val, $ptr|$ptr, $val}"),
[(set
GR16:$dst,
(!cast<PatFrag>(frag # "_16") addr:$ptr, GR16:$val))],
itin>, OpSize16;
def NAME#32 : I<opc, MRMSrcMem, (outs GR32:$dst),
(ins GR32:$val, i32mem:$ptr),
!strconcat(mnemonic, "{l}\t{$val, $ptr|$ptr, $val}"),
[(set
GR32:$dst,
(!cast<PatFrag>(frag # "_32") addr:$ptr, GR32:$val))],
itin>, OpSize32;
def NAME#64 : RI<opc, MRMSrcMem, (outs GR64:$dst),
(ins GR64:$val, i64mem:$ptr),
!strconcat(mnemonic, "{q}\t{$val, $ptr|$ptr, $val}"),
[(set
GR64:$dst,
(!cast<PatFrag>(frag # "_64") addr:$ptr, GR64:$val))],
itin>;
}
}
defm LXADD : ATOMIC_LOAD_BINOP<0xc0, 0xc1, "xadd", "atomic_load_add",
IIC_XADD_LOCK_MEM8, IIC_XADD_LOCK_MEM>,
TB, LOCK;
/* The following multiclass tries to make sure that in code like
* x.store (immediate op x.load(acquire), release)
* an operation directly on memory is generated instead of wasting a register.
* It is not automatic as atomic_store/load are only lowered to MOV instructions
* extremely late to prevent them from being accidentally reordered in the backend
* (see below the RELEASE_MOV* / ACQUIRE_MOV* pseudo-instructions)
*/
multiclass RELEASE_BINOP_MI<string op> {
def NAME#8mi : I<0, Pseudo, (outs), (ins i8mem:$dst, i8imm:$src),
"#RELEASE_BINOP PSEUDO!",
[(atomic_store_8 addr:$dst, (!cast<PatFrag>(op)
(atomic_load_8 addr:$dst), (i8 imm:$src)))]>;
// NAME#16 is not generated as 16-bit arithmetic instructions are considered
// costly and avoided as far as possible by this backend anyway
def NAME#32mi : I<0, Pseudo, (outs), (ins i32mem:$dst, i32imm:$src),
"#RELEASE_BINOP PSEUDO!",
[(atomic_store_32 addr:$dst, (!cast<PatFrag>(op)
(atomic_load_32 addr:$dst), (i32 imm:$src)))]>;
def NAME#64mi32 : I<0, Pseudo, (outs), (ins i64mem:$dst, i64i32imm:$src),
"#RELEASE_BINOP PSEUDO!",
[(atomic_store_64 addr:$dst, (!cast<PatFrag>(op)
(atomic_load_64 addr:$dst), (i64immSExt32:$src)))]>;
}
defm RELEASE_ADD : RELEASE_BINOP_MI<"add">;
defm RELEASE_AND : RELEASE_BINOP_MI<"and">;
defm RELEASE_OR : RELEASE_BINOP_MI<"or">;
defm RELEASE_XOR : RELEASE_BINOP_MI<"xor">;
// Note: we don't deal with sub, because substractions of constants are
// optimized into additions before this code can run
multiclass RELEASE_UNOP<dag dag8, dag dag16, dag dag32, dag dag64> {
def NAME#8m : I<0, Pseudo, (outs), (ins i8mem:$dst),
"#RELEASE_UNOP PSEUDO!",
[(atomic_store_8 addr:$dst, dag8)]>;
def NAME#16m : I<0, Pseudo, (outs), (ins i16mem:$dst),
"#RELEASE_UNOP PSEUDO!",
[(atomic_store_16 addr:$dst, dag16)]>;
def NAME#32m : I<0, Pseudo, (outs), (ins i32mem:$dst),
"#RELEASE_UNOP PSEUDO!",
[(atomic_store_32 addr:$dst, dag32)]>;
def NAME#64m : I<0, Pseudo, (outs), (ins i64mem:$dst),
"#RELEASE_UNOP PSEUDO!",
[(atomic_store_64 addr:$dst, dag64)]>;
}
defm RELEASE_INC : RELEASE_UNOP<
(add (atomic_load_8 addr:$dst), (i8 1)),
(add (atomic_load_16 addr:$dst), (i16 1)),
(add (atomic_load_32 addr:$dst), (i32 1)),
(add (atomic_load_64 addr:$dst), (i64 1))>, Requires<[NotSlowIncDec]>;
defm RELEASE_DEC : RELEASE_UNOP<
(add (atomic_load_8 addr:$dst), (i8 -1)),
(add (atomic_load_16 addr:$dst), (i16 -1)),
(add (atomic_load_32 addr:$dst), (i32 -1)),
(add (atomic_load_64 addr:$dst), (i64 -1))>, Requires<[NotSlowIncDec]>;
/*
TODO: These don't work because the type inference of TableGen fails.
TODO: find a way to fix it.
defm RELEASE_NEG : RELEASE_UNOP<
(ineg (atomic_load_8 addr:$dst)),
(ineg (atomic_load_16 addr:$dst)),
(ineg (atomic_load_32 addr:$dst)),
(ineg (atomic_load_64 addr:$dst))>;
defm RELEASE_NOT : RELEASE_UNOP<
(not (atomic_load_8 addr:$dst)),
(not (atomic_load_16 addr:$dst)),
(not (atomic_load_32 addr:$dst)),
(not (atomic_load_64 addr:$dst))>;
*/
def RELEASE_MOV8mi : I<0, Pseudo, (outs), (ins i8mem:$dst, i8imm:$src),
"#RELEASE_MOV PSEUDO !",
[(atomic_store_8 addr:$dst, (i8 imm:$src))]>;
def RELEASE_MOV16mi : I<0, Pseudo, (outs), (ins i16mem:$dst, i16imm:$src),
"#RELEASE_MOV PSEUDO !",
[(atomic_store_16 addr:$dst, (i16 imm:$src))]>;
def RELEASE_MOV32mi : I<0, Pseudo, (outs), (ins i32mem:$dst, i32imm:$src),
"#RELEASE_MOV PSEUDO !",
[(atomic_store_32 addr:$dst, (i32 imm:$src))]>;
def RELEASE_MOV64mi32 : I<0, Pseudo, (outs), (ins i64mem:$dst, i64i32imm:$src),
"#RELEASE_MOV PSEUDO !",
[(atomic_store_64 addr:$dst, i64immSExt32:$src)]>;
def RELEASE_MOV8mr : I<0, Pseudo, (outs), (ins i8mem :$dst, GR8 :$src),
"#RELEASE_MOV PSEUDO!",
[(atomic_store_8 addr:$dst, GR8 :$src)]>;
def RELEASE_MOV16mr : I<0, Pseudo, (outs), (ins i16mem:$dst, GR16:$src),
"#RELEASE_MOV PSEUDO!",
[(atomic_store_16 addr:$dst, GR16:$src)]>;
def RELEASE_MOV32mr : I<0, Pseudo, (outs), (ins i32mem:$dst, GR32:$src),
"#RELEASE_MOV PSEUDO!",
[(atomic_store_32 addr:$dst, GR32:$src)]>;
def RELEASE_MOV64mr : I<0, Pseudo, (outs), (ins i64mem:$dst, GR64:$src),
"#RELEASE_MOV PSEUDO!",
[(atomic_store_64 addr:$dst, GR64:$src)]>;
def ACQUIRE_MOV8rm : I<0, Pseudo, (outs GR8 :$dst), (ins i8mem :$src),
"#ACQUIRE_MOV PSEUDO!",
[(set GR8:$dst, (atomic_load_8 addr:$src))]>;
def ACQUIRE_MOV16rm : I<0, Pseudo, (outs GR16:$dst), (ins i16mem:$src),
"#ACQUIRE_MOV PSEUDO!",
[(set GR16:$dst, (atomic_load_16 addr:$src))]>;
def ACQUIRE_MOV32rm : I<0, Pseudo, (outs GR32:$dst), (ins i32mem:$src),
"#ACQUIRE_MOV PSEUDO!",
[(set GR32:$dst, (atomic_load_32 addr:$src))]>;
def ACQUIRE_MOV64rm : I<0, Pseudo, (outs GR64:$dst), (ins i64mem:$src),
"#ACQUIRE_MOV PSEUDO!",
[(set GR64:$dst, (atomic_load_64 addr:$src))]>;
//===----------------------------------------------------------------------===//
// Conditional Move Pseudo Instructions.
//===----------------------------------------------------------------------===//
// CMOV* - Used to implement the SSE SELECT DAG operation. Expanded after
// instruction selection into a branch sequence.
let Uses = [EFLAGS], usesCustomInserter = 1 in {
def CMOV_FR32 : I<0, Pseudo,
(outs FR32:$dst), (ins FR32:$t, FR32:$f, i8imm:$cond),
"#CMOV_FR32 PSEUDO!",
[(set FR32:$dst, (X86cmov FR32:$t, FR32:$f, imm:$cond,
EFLAGS))]>;
def CMOV_FR64 : I<0, Pseudo,
(outs FR64:$dst), (ins FR64:$t, FR64:$f, i8imm:$cond),
"#CMOV_FR64 PSEUDO!",
[(set FR64:$dst, (X86cmov FR64:$t, FR64:$f, imm:$cond,
EFLAGS))]>;
def CMOV_V4F32 : I<0, Pseudo,
(outs VR128:$dst), (ins VR128:$t, VR128:$f, i8imm:$cond),
"#CMOV_V4F32 PSEUDO!",
[(set VR128:$dst,
(v4f32 (X86cmov VR128:$t, VR128:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V2F64 : I<0, Pseudo,
(outs VR128:$dst), (ins VR128:$t, VR128:$f, i8imm:$cond),
"#CMOV_V2F64 PSEUDO!",
[(set VR128:$dst,
(v2f64 (X86cmov VR128:$t, VR128:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V2I64 : I<0, Pseudo,
(outs VR128:$dst), (ins VR128:$t, VR128:$f, i8imm:$cond),
"#CMOV_V2I64 PSEUDO!",
[(set VR128:$dst,
(v2i64 (X86cmov VR128:$t, VR128:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V8F32 : I<0, Pseudo,
(outs VR256:$dst), (ins VR256:$t, VR256:$f, i8imm:$cond),
"#CMOV_V8F32 PSEUDO!",
[(set VR256:$dst,
(v8f32 (X86cmov VR256:$t, VR256:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V4F64 : I<0, Pseudo,
(outs VR256:$dst), (ins VR256:$t, VR256:$f, i8imm:$cond),
"#CMOV_V4F64 PSEUDO!",
[(set VR256:$dst,
(v4f64 (X86cmov VR256:$t, VR256:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V4I64 : I<0, Pseudo,
(outs VR256:$dst), (ins VR256:$t, VR256:$f, i8imm:$cond),
"#CMOV_V4I64 PSEUDO!",
[(set VR256:$dst,
(v4i64 (X86cmov VR256:$t, VR256:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V8I64 : I<0, Pseudo,
(outs VR512:$dst), (ins VR512:$t, VR512:$f, i8imm:$cond),
"#CMOV_V8I64 PSEUDO!",
[(set VR512:$dst,
(v8i64 (X86cmov VR512:$t, VR512:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V8F64 : I<0, Pseudo,
(outs VR512:$dst), (ins VR512:$t, VR512:$f, i8imm:$cond),
"#CMOV_V8F64 PSEUDO!",
[(set VR512:$dst,
(v8f64 (X86cmov VR512:$t, VR512:$f, imm:$cond,
EFLAGS)))]>;
def CMOV_V16F32 : I<0, Pseudo,
(outs VR512:$dst), (ins VR512:$t, VR512:$f, i8imm:$cond),
"#CMOV_V16F32 PSEUDO!",
[(set VR512:$dst,
(v16f32 (X86cmov VR512:$t, VR512:$f, imm:$cond,
EFLAGS)))]>;
}
//===----------------------------------------------------------------------===//
// DAG Pattern Matching Rules
//===----------------------------------------------------------------------===//
// ConstantPool GlobalAddress, ExternalSymbol, and JumpTable
def : Pat<(i32 (X86Wrapper tconstpool :$dst)), (MOV32ri tconstpool :$dst)>;
def : Pat<(i32 (X86Wrapper tjumptable :$dst)), (MOV32ri tjumptable :$dst)>;
def : Pat<(i32 (X86Wrapper tglobaltlsaddr:$dst)),(MOV32ri tglobaltlsaddr:$dst)>;
def : Pat<(i32 (X86Wrapper tglobaladdr :$dst)), (MOV32ri tglobaladdr :$dst)>;
def : Pat<(i32 (X86Wrapper texternalsym:$dst)), (MOV32ri texternalsym:$dst)>;
def : Pat<(i32 (X86Wrapper tblockaddress:$dst)), (MOV32ri tblockaddress:$dst)>;
def : Pat<(add GR32:$src1, (X86Wrapper tconstpool:$src2)),
(ADD32ri GR32:$src1, tconstpool:$src2)>;
def : Pat<(add GR32:$src1, (X86Wrapper tjumptable:$src2)),
(ADD32ri GR32:$src1, tjumptable:$src2)>;
def : Pat<(add GR32:$src1, (X86Wrapper tglobaladdr :$src2)),
(ADD32ri GR32:$src1, tglobaladdr:$src2)>;
def : Pat<(add GR32:$src1, (X86Wrapper texternalsym:$src2)),
(ADD32ri GR32:$src1, texternalsym:$src2)>;
def : Pat<(add GR32:$src1, (X86Wrapper tblockaddress:$src2)),
(ADD32ri GR32:$src1, tblockaddress:$src2)>;
def : Pat<(store (i32 (X86Wrapper tglobaladdr:$src)), addr:$dst),
(MOV32mi addr:$dst, tglobaladdr:$src)>;
def : Pat<(store (i32 (X86Wrapper texternalsym:$src)), addr:$dst),
(MOV32mi addr:$dst, texternalsym:$src)>;
def : Pat<(store (i32 (X86Wrapper tblockaddress:$src)), addr:$dst),
(MOV32mi addr:$dst, tblockaddress:$src)>;
// ConstantPool GlobalAddress, ExternalSymbol, and JumpTable when not in small
// code model mode, should use 'movabs'. FIXME: This is really a hack, the
// 'movabs' predicate should handle this sort of thing.
def : Pat<(i64 (X86Wrapper tconstpool :$dst)),
(MOV64ri tconstpool :$dst)>, Requires<[FarData]>;
def : Pat<(i64 (X86Wrapper tjumptable :$dst)),
(MOV64ri tjumptable :$dst)>, Requires<[FarData]>;
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
(MOV64ri tglobaladdr :$dst)>, Requires<[FarData]>;
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
(MOV64ri texternalsym:$dst)>, Requires<[FarData]>;
def : Pat<(i64 (X86Wrapper tblockaddress:$dst)),
(MOV64ri tblockaddress:$dst)>, Requires<[FarData]>;
// In kernel code model, we can get the address of a label
// into a register with 'movq'. FIXME: This is a hack, the 'imm' predicate of
// the MOV64ri32 should accept these.
def : Pat<(i64 (X86Wrapper tconstpool :$dst)),
(MOV64ri32 tconstpool :$dst)>, Requires<[KernelCode]>;
def : Pat<(i64 (X86Wrapper tjumptable :$dst)),
(MOV64ri32 tjumptable :$dst)>, Requires<[KernelCode]>;
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
(MOV64ri32 tglobaladdr :$dst)>, Requires<[KernelCode]>;
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
(MOV64ri32 texternalsym:$dst)>, Requires<[KernelCode]>;
def : Pat<(i64 (X86Wrapper tblockaddress:$dst)),
(MOV64ri32 tblockaddress:$dst)>, Requires<[KernelCode]>;
// If we have small model and -static mode, it is safe to store global addresses
// directly as immediates. FIXME: This is really a hack, the 'imm' predicate
// for MOV64mi32 should handle this sort of thing.
def : Pat<(store (i64 (X86Wrapper tconstpool:$src)), addr:$dst),
(MOV64mi32 addr:$dst, tconstpool:$src)>,
Requires<[NearData, IsStatic]>;
def : Pat<(store (i64 (X86Wrapper tjumptable:$src)), addr:$dst),
(MOV64mi32 addr:$dst, tjumptable:$src)>,
Requires<[NearData, IsStatic]>;
def : Pat<(store (i64 (X86Wrapper tglobaladdr:$src)), addr:$dst),
(MOV64mi32 addr:$dst, tglobaladdr:$src)>,
Requires<[NearData, IsStatic]>;
def : Pat<(store (i64 (X86Wrapper texternalsym:$src)), addr:$dst),
(MOV64mi32 addr:$dst, texternalsym:$src)>,
Requires<[NearData, IsStatic]>;
def : Pat<(store (i64 (X86Wrapper tblockaddress:$src)), addr:$dst),
(MOV64mi32 addr:$dst, tblockaddress:$src)>,
Requires<[NearData, IsStatic]>;
// Calls
// tls has some funny stuff here...
// This corresponds to movabs $foo@tpoff, %rax
def : Pat<(i64 (X86Wrapper tglobaltlsaddr :$dst)),
(MOV64ri32 tglobaltlsaddr :$dst)>;
// This corresponds to add $foo@tpoff, %rax
def : Pat<(add GR64:$src1, (X86Wrapper tglobaltlsaddr :$dst)),
(ADD64ri32 GR64:$src1, tglobaltlsaddr :$dst)>;
// Direct PC relative function call for small code model. 32-bit displacement
// sign extended to 64-bit.
def : Pat<(X86call (i64 tglobaladdr:$dst)),
(CALL64pcrel32 tglobaladdr:$dst)>;
def : Pat<(X86call (i64 texternalsym:$dst)),
(CALL64pcrel32 texternalsym:$dst)>;
// Tailcall stuff. The TCRETURN instructions execute after the epilog, so they
// can never use callee-saved registers. That is the purpose of the GR64_TC
// register classes.
//
// The only volatile register that is never used by the calling convention is
// %r11. This happens when calling a vararg function with 6 arguments.
//
// Match an X86tcret that uses less than 7 volatile registers.
def X86tcret_6regs : PatFrag<(ops node:$ptr, node:$off),
(X86tcret node:$ptr, node:$off), [{
// X86tcret args: (*chain, ptr, imm, regs..., glue)
unsigned NumRegs = 0;
for (unsigned i = 3, e = N->getNumOperands(); i != e; ++i)
if (isa<RegisterSDNode>(N->getOperand(i)) && ++NumRegs > 6)
return false;
return true;
}]>;
def : Pat<(X86tcret ptr_rc_tailcall:$dst, imm:$off),
(TCRETURNri ptr_rc_tailcall:$dst, imm:$off)>,
Requires<[Not64BitMode]>;
// FIXME: This is disabled for 32-bit PIC mode because the global base
// register which is part of the address mode may be assigned a
// callee-saved register.
def : Pat<(X86tcret (load addr:$dst), imm:$off),
(TCRETURNmi addr:$dst, imm:$off)>,
Requires<[Not64BitMode, IsNotPIC]>;
def : Pat<(X86tcret (i32 tglobaladdr:$dst), imm:$off),
(TCRETURNdi texternalsym:$dst, imm:$off)>,
Requires<[Not64BitMode]>;
def : Pat<(X86tcret (i32 texternalsym:$dst), imm:$off),
(TCRETURNdi texternalsym:$dst, imm:$off)>,
Requires<[Not64BitMode]>;
def : Pat<(X86tcret ptr_rc_tailcall:$dst, imm:$off),
(TCRETURNri64 ptr_rc_tailcall:$dst, imm:$off)>,
Requires<[In64BitMode]>;
// Don't fold loads into X86tcret requiring more than 6 regs.
// There wouldn't be enough scratch registers for base+index.
def : Pat<(X86tcret_6regs (load addr:$dst), imm:$off),
(TCRETURNmi64 addr:$dst, imm:$off)>,
Requires<[In64BitMode]>;
def : Pat<(X86tcret (i64 tglobaladdr:$dst), imm:$off),
(TCRETURNdi64 tglobaladdr:$dst, imm:$off)>,
Requires<[In64BitMode]>;
def : Pat<(X86tcret (i64 texternalsym:$dst), imm:$off),
(TCRETURNdi64 texternalsym:$dst, imm:$off)>,
Requires<[In64BitMode]>;
// Normal calls, with various flavors of addresses.
def : Pat<(X86call (i32 tglobaladdr:$dst)),
(CALLpcrel32 tglobaladdr:$dst)>;
def : Pat<(X86call (i32 texternalsym:$dst)),
(CALLpcrel32 texternalsym:$dst)>;
def : Pat<(X86call (i32 imm:$dst)),
(CALLpcrel32 imm:$dst)>, Requires<[CallImmAddr]>;
// Comparisons.
// TEST R,R is smaller than CMP R,0
def : Pat<(X86cmp GR8:$src1, 0),
(TEST8rr GR8:$src1, GR8:$src1)>;
def : Pat<(X86cmp GR16:$src1, 0),
(TEST16rr GR16:$src1, GR16:$src1)>;
def : Pat<(X86cmp GR32:$src1, 0),
(TEST32rr GR32:$src1, GR32:$src1)>;
def : Pat<(X86cmp GR64:$src1, 0),
(TEST64rr GR64:$src1, GR64:$src1)>;
// Conditional moves with folded loads with operands swapped and conditions
// inverted.
multiclass CMOVmr<PatLeaf InvertedCond, Instruction Inst16, Instruction Inst32,
Instruction Inst64> {
let Predicates = [HasCMov] in {
def : Pat<(X86cmov (loadi16 addr:$src1), GR16:$src2, InvertedCond, EFLAGS),
(Inst16 GR16:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi32 addr:$src1), GR32:$src2, InvertedCond, EFLAGS),
(Inst32 GR32:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, InvertedCond, EFLAGS),
(Inst64 GR64:$src2, addr:$src1)>;
}
}
defm : CMOVmr<X86_COND_B , CMOVAE16rm, CMOVAE32rm, CMOVAE64rm>;
defm : CMOVmr<X86_COND_AE, CMOVB16rm , CMOVB32rm , CMOVB64rm>;
defm : CMOVmr<X86_COND_E , CMOVNE16rm, CMOVNE32rm, CMOVNE64rm>;
defm : CMOVmr<X86_COND_NE, CMOVE16rm , CMOVE32rm , CMOVE64rm>;
defm : CMOVmr<X86_COND_BE, CMOVA16rm , CMOVA32rm , CMOVA64rm>;
defm : CMOVmr<X86_COND_A , CMOVBE16rm, CMOVBE32rm, CMOVBE64rm>;
defm : CMOVmr<X86_COND_L , CMOVGE16rm, CMOVGE32rm, CMOVGE64rm>;
defm : CMOVmr<X86_COND_GE, CMOVL16rm , CMOVL32rm , CMOVL64rm>;
defm : CMOVmr<X86_COND_LE, CMOVG16rm , CMOVG32rm , CMOVG64rm>;
defm : CMOVmr<X86_COND_G , CMOVLE16rm, CMOVLE32rm, CMOVLE64rm>;
defm : CMOVmr<X86_COND_P , CMOVNP16rm, CMOVNP32rm, CMOVNP64rm>;
defm : CMOVmr<X86_COND_NP, CMOVP16rm , CMOVP32rm , CMOVP64rm>;
defm : CMOVmr<X86_COND_S , CMOVNS16rm, CMOVNS32rm, CMOVNS64rm>;
defm : CMOVmr<X86_COND_NS, CMOVS16rm , CMOVS32rm , CMOVS64rm>;
defm : CMOVmr<X86_COND_O , CMOVNO16rm, CMOVNO32rm, CMOVNO64rm>;
defm : CMOVmr<X86_COND_NO, CMOVO16rm , CMOVO32rm , CMOVO64rm>;
// zextload bool -> zextload byte
def : Pat<(zextloadi8i1 addr:$src), (MOV8rm addr:$src)>;
def : Pat<(zextloadi16i1 addr:$src), (MOVZX16rm8 addr:$src)>;
def : Pat<(zextloadi32i1 addr:$src), (MOVZX32rm8 addr:$src)>;
def : Pat<(zextloadi64i1 addr:$src),
(SUBREG_TO_REG (i64 0), (MOVZX32rm8 addr:$src), sub_32bit)>;
// extload bool -> extload byte
// When extloading from 16-bit and smaller memory locations into 64-bit
// registers, use zero-extending loads so that the entire 64-bit register is
// defined, avoiding partial-register updates.
def : Pat<(extloadi8i1 addr:$src), (MOV8rm addr:$src)>;
def : Pat<(extloadi16i1 addr:$src), (MOVZX16rm8 addr:$src)>;
def : Pat<(extloadi32i1 addr:$src), (MOVZX32rm8 addr:$src)>;
def : Pat<(extloadi16i8 addr:$src), (MOVZX16rm8 addr:$src)>;
def : Pat<(extloadi32i8 addr:$src), (MOVZX32rm8 addr:$src)>;
def : Pat<(extloadi32i16 addr:$src), (MOVZX32rm16 addr:$src)>;
// For other extloads, use subregs, since the high contents of the register are
// defined after an extload.
def : Pat<(extloadi64i1 addr:$src),
(SUBREG_TO_REG (i64 0), (MOVZX32rm8 addr:$src), sub_32bit)>;
def : Pat<(extloadi64i8 addr:$src),
(SUBREG_TO_REG (i64 0), (MOVZX32rm8 addr:$src), sub_32bit)>;
def : Pat<(extloadi64i16 addr:$src),
(SUBREG_TO_REG (i64 0), (MOVZX32rm16 addr:$src), sub_32bit)>;
def : Pat<(extloadi64i32 addr:$src),
(SUBREG_TO_REG (i64 0), (MOV32rm addr:$src), sub_32bit)>;
// anyext. Define these to do an explicit zero-extend to
// avoid partial-register updates.
def : Pat<(i16 (anyext GR8 :$src)), (EXTRACT_SUBREG
(MOVZX32rr8 GR8 :$src), sub_16bit)>;
def : Pat<(i32 (anyext GR8 :$src)), (MOVZX32rr8 GR8 :$src)>;
// Except for i16 -> i32 since isel expect i16 ops to be promoted to i32.
def : Pat<(i32 (anyext GR16:$src)),
(INSERT_SUBREG (i32 (IMPLICIT_DEF)), GR16:$src, sub_16bit)>;
def : Pat<(i64 (anyext GR8 :$src)),
(SUBREG_TO_REG (i64 0), (MOVZX32rr8 GR8 :$src), sub_32bit)>;
def : Pat<(i64 (anyext GR16:$src)),
(SUBREG_TO_REG (i64 0), (MOVZX32rr16 GR16 :$src), sub_32bit)>;
def : Pat<(i64 (anyext GR32:$src)),
(SUBREG_TO_REG (i64 0), GR32:$src, sub_32bit)>;
// Any instruction that defines a 32-bit result leaves the high half of the
// register. Truncate can be lowered to EXTRACT_SUBREG. CopyFromReg may
// be copying from a truncate. And x86's cmov doesn't do anything if the
// condition is false. But any other 32-bit operation will zero-extend
// up to 64 bits.
def def32 : PatLeaf<(i32 GR32:$src), [{
return N->getOpcode() != ISD::TRUNCATE &&
N->getOpcode() != TargetOpcode::EXTRACT_SUBREG &&
N->getOpcode() != ISD::CopyFromReg &&
N->getOpcode() != ISD::AssertSext &&
N->getOpcode() != X86ISD::CMOV;
}]>;
// In the case of a 32-bit def that is known to implicitly zero-extend,
// we can use a SUBREG_TO_REG.
def : Pat<(i64 (zext def32:$src)),
(SUBREG_TO_REG (i64 0), GR32:$src, sub_32bit)>;
//===----------------------------------------------------------------------===//
// Pattern match OR as ADD
//===----------------------------------------------------------------------===//
// If safe, we prefer to pattern match OR as ADD at isel time. ADD can be
// 3-addressified into an LEA instruction to avoid copies. However, we also
// want to finally emit these instructions as an or at the end of the code
// generator to make the generated code easier to read. To do this, we select
// into "disjoint bits" pseudo ops.
// Treat an 'or' node is as an 'add' if the or'ed bits are known to be zero.
def or_is_add : PatFrag<(ops node:$lhs, node:$rhs), (or node:$lhs, node:$rhs),[{
if (ConstantSDNode *CN = dyn_cast<ConstantSDNode>(N->getOperand(1)))
return CurDAG->MaskedValueIsZero(N->getOperand(0), CN->getAPIntValue());
APInt KnownZero0, KnownOne0;
CurDAG->computeKnownBits(N->getOperand(0), KnownZero0, KnownOne0, 0);
APInt KnownZero1, KnownOne1;
CurDAG->computeKnownBits(N->getOperand(1), KnownZero1, KnownOne1, 0);
return (~KnownZero0 & ~KnownZero1) == 0;
}]>;
// (or x1, x2) -> (add x1, x2) if two operands are known not to share bits.
// Try this before the selecting to OR.
let AddedComplexity = 5, SchedRW = [WriteALU] in {
let isConvertibleToThreeAddress = 1,
Constraints = "$src1 = $dst", Defs = [EFLAGS] in {
let isCommutable = 1 in {
def ADD16rr_DB : I<0, Pseudo, (outs GR16:$dst), (ins GR16:$src1, GR16:$src2),
"", // orw/addw REG, REG
[(set GR16:$dst, (or_is_add GR16:$src1, GR16:$src2))]>;
def ADD32rr_DB : I<0, Pseudo, (outs GR32:$dst), (ins GR32:$src1, GR32:$src2),
"", // orl/addl REG, REG
[(set GR32:$dst, (or_is_add GR32:$src1, GR32:$src2))]>;
def ADD64rr_DB : I<0, Pseudo, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
"", // orq/addq REG, REG
[(set GR64:$dst, (or_is_add GR64:$src1, GR64:$src2))]>;
} // isCommutable
// NOTE: These are order specific, we want the ri8 forms to be listed
// first so that they are slightly preferred to the ri forms.
def ADD16ri8_DB : I<0, Pseudo,
(outs GR16:$dst), (ins GR16:$src1, i16i8imm:$src2),
"", // orw/addw REG, imm8
[(set GR16:$dst,(or_is_add GR16:$src1,i16immSExt8:$src2))]>;
def ADD16ri_DB : I<0, Pseudo, (outs GR16:$dst), (ins GR16:$src1, i16imm:$src2),
"", // orw/addw REG, imm
[(set GR16:$dst, (or_is_add GR16:$src1, imm:$src2))]>;
def ADD32ri8_DB : I<0, Pseudo,
(outs GR32:$dst), (ins GR32:$src1, i32i8imm:$src2),
"", // orl/addl REG, imm8
[(set GR32:$dst,(or_is_add GR32:$src1,i32immSExt8:$src2))]>;
def ADD32ri_DB : I<0, Pseudo, (outs GR32:$dst), (ins GR32:$src1, i32imm:$src2),
"", // orl/addl REG, imm
[(set GR32:$dst, (or_is_add GR32:$src1, imm:$src2))]>;
def ADD64ri8_DB : I<0, Pseudo,
(outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
"", // orq/addq REG, imm8
[(set GR64:$dst, (or_is_add GR64:$src1,
i64immSExt8:$src2))]>;
def ADD64ri32_DB : I<0, Pseudo,
(outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
"", // orq/addq REG, imm
[(set GR64:$dst, (or_is_add GR64:$src1,
i64immSExt32:$src2))]>;
}
} // AddedComplexity, SchedRW
//===----------------------------------------------------------------------===//
// Some peepholes
//===----------------------------------------------------------------------===//
// Odd encoding trick: -128 fits into an 8-bit immediate field while
// +128 doesn't, so in this special case use a sub instead of an add.
def : Pat<(add GR16:$src1, 128),
(SUB16ri8 GR16:$src1, -128)>;
def : Pat<(store (add (loadi16 addr:$dst), 128), addr:$dst),
(SUB16mi8 addr:$dst, -128)>;
def : Pat<(add GR32:$src1, 128),
(SUB32ri8 GR32:$src1, -128)>;
def : Pat<(store (add (loadi32 addr:$dst), 128), addr:$dst),
(SUB32mi8 addr:$dst, -128)>;
def : Pat<(add GR64:$src1, 128),
(SUB64ri8 GR64:$src1, -128)>;
def : Pat<(store (add (loadi64 addr:$dst), 128), addr:$dst),
(SUB64mi8 addr:$dst, -128)>;
// The same trick applies for 32-bit immediate fields in 64-bit
// instructions.
def : Pat<(add GR64:$src1, 0x0000000080000000),
(SUB64ri32 GR64:$src1, 0xffffffff80000000)>;
def : Pat<(store (add (loadi64 addr:$dst), 0x00000000800000000), addr:$dst),
(SUB64mi32 addr:$dst, 0xffffffff80000000)>;
// To avoid needing to materialize an immediate in a register, use a 32-bit and
// with implicit zero-extension instead of a 64-bit and if the immediate has at
// least 32 bits of leading zeros. If in addition the last 32 bits can be
// represented with a sign extension of a 8 bit constant, use that.
def : Pat<(and GR64:$src, i64immZExt32SExt8:$imm),
(SUBREG_TO_REG
(i64 0),
(AND32ri8
(EXTRACT_SUBREG GR64:$src, sub_32bit),
(i32 (GetLo8XForm imm:$imm))),
sub_32bit)>;
def : Pat<(and GR64:$src, i64immZExt32:$imm),
(SUBREG_TO_REG
(i64 0),
(AND32ri
(EXTRACT_SUBREG GR64:$src, sub_32bit),
(i32 (GetLo32XForm imm:$imm))),
sub_32bit)>;
// r & (2^16-1) ==> movz
def : Pat<(and GR32:$src1, 0xffff),
(MOVZX32rr16 (EXTRACT_SUBREG GR32:$src1, sub_16bit))>;
// r & (2^8-1) ==> movz
def : Pat<(and GR32:$src1, 0xff),
(MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src1,
GR32_ABCD)),
sub_8bit))>,
Requires<[Not64BitMode]>;
// r & (2^8-1) ==> movz
def : Pat<(and GR16:$src1, 0xff),
(EXTRACT_SUBREG (MOVZX32rr8 (EXTRACT_SUBREG
(i16 (COPY_TO_REGCLASS GR16:$src1, GR16_ABCD)), sub_8bit)),
sub_16bit)>,
Requires<[Not64BitMode]>;
// r & (2^32-1) ==> movz
def : Pat<(and GR64:$src, 0x00000000FFFFFFFF),
(SUBREG_TO_REG (i64 0),
(MOV32rr (EXTRACT_SUBREG GR64:$src, sub_32bit)),
sub_32bit)>;
// r & (2^16-1) ==> movz
def : Pat<(and GR64:$src, 0xffff),
(SUBREG_TO_REG (i64 0),
(MOVZX32rr16 (i16 (EXTRACT_SUBREG GR64:$src, sub_16bit))),
sub_32bit)>;
// r & (2^8-1) ==> movz
def : Pat<(and GR64:$src, 0xff),
(SUBREG_TO_REG (i64 0),
(MOVZX32rr8 (i8 (EXTRACT_SUBREG GR64:$src, sub_8bit))),
sub_32bit)>;
// r & (2^8-1) ==> movz
def : Pat<(and GR32:$src1, 0xff),
(MOVZX32rr8 (EXTRACT_SUBREG GR32:$src1, sub_8bit))>,
Requires<[In64BitMode]>;
// r & (2^8-1) ==> movz
def : Pat<(and GR16:$src1, 0xff),
(EXTRACT_SUBREG (MOVZX32rr8 (i8
(EXTRACT_SUBREG GR16:$src1, sub_8bit))), sub_16bit)>,
Requires<[In64BitMode]>;
// sext_inreg patterns
def : Pat<(sext_inreg GR32:$src, i16),
(MOVSX32rr16 (EXTRACT_SUBREG GR32:$src, sub_16bit))>;
def : Pat<(sext_inreg GR32:$src, i8),
(MOVSX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src,
GR32_ABCD)),
sub_8bit))>,
Requires<[Not64BitMode]>;
def : Pat<(sext_inreg GR16:$src, i8),
(EXTRACT_SUBREG (i32 (MOVSX32rr8 (EXTRACT_SUBREG
(i32 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)), sub_8bit))),
sub_16bit)>,
Requires<[Not64BitMode]>;
def : Pat<(sext_inreg GR64:$src, i32),
(MOVSX64rr32 (EXTRACT_SUBREG GR64:$src, sub_32bit))>;
def : Pat<(sext_inreg GR64:$src, i16),
(MOVSX64rr16 (EXTRACT_SUBREG GR64:$src, sub_16bit))>;
def : Pat<(sext_inreg GR64:$src, i8),
(MOVSX64rr8 (EXTRACT_SUBREG GR64:$src, sub_8bit))>;
def : Pat<(sext_inreg GR32:$src, i8),
(MOVSX32rr8 (EXTRACT_SUBREG GR32:$src, sub_8bit))>,
Requires<[In64BitMode]>;
def : Pat<(sext_inreg GR16:$src, i8),
(EXTRACT_SUBREG (MOVSX32rr8
(EXTRACT_SUBREG GR16:$src, sub_8bit)), sub_16bit)>,
Requires<[In64BitMode]>;
// sext, sext_load, zext, zext_load
def: Pat<(i16 (sext GR8:$src)),
(EXTRACT_SUBREG (MOVSX32rr8 GR8:$src), sub_16bit)>;
def: Pat<(sextloadi16i8 addr:$src),
(EXTRACT_SUBREG (MOVSX32rm8 addr:$src), sub_16bit)>;
def: Pat<(i16 (zext GR8:$src)),
(EXTRACT_SUBREG (MOVZX32rr8 GR8:$src), sub_16bit)>;
def: Pat<(zextloadi16i8 addr:$src),
(EXTRACT_SUBREG (MOVZX32rm8 addr:$src), sub_16bit)>;
// trunc patterns
def : Pat<(i16 (trunc GR32:$src)),
(EXTRACT_SUBREG GR32:$src, sub_16bit)>;
def : Pat<(i8 (trunc GR32:$src)),
(EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)),
sub_8bit)>,
Requires<[Not64BitMode]>;
def : Pat<(i8 (trunc GR16:$src)),
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit)>,
Requires<[Not64BitMode]>;
def : Pat<(i32 (trunc GR64:$src)),
(EXTRACT_SUBREG GR64:$src, sub_32bit)>;
def : Pat<(i16 (trunc GR64:$src)),
(EXTRACT_SUBREG GR64:$src, sub_16bit)>;
def : Pat<(i8 (trunc GR64:$src)),
(EXTRACT_SUBREG GR64:$src, sub_8bit)>;
def : Pat<(i8 (trunc GR32:$src)),
(EXTRACT_SUBREG GR32:$src, sub_8bit)>,
Requires<[In64BitMode]>;
def : Pat<(i8 (trunc GR16:$src)),
(EXTRACT_SUBREG GR16:$src, sub_8bit)>,
Requires<[In64BitMode]>;
// h-register tricks
def : Pat<(i8 (trunc (srl_su GR16:$src, (i8 8)))),
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi)>,
Requires<[Not64BitMode]>;
def : Pat<(i8 (trunc (srl_su GR32:$src, (i8 8)))),
(EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)),
sub_8bit_hi)>,
Requires<[Not64BitMode]>;
def : Pat<(srl GR16:$src, (i8 8)),
(EXTRACT_SUBREG
(MOVZX32rr8
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi)),
sub_16bit)>,
Requires<[Not64BitMode]>;
def : Pat<(i32 (zext (srl_su GR16:$src, (i8 8)))),
(MOVZX32rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src,
GR16_ABCD)),
sub_8bit_hi))>,
Requires<[Not64BitMode]>;
def : Pat<(i32 (anyext (srl_su GR16:$src, (i8 8)))),
(MOVZX32rr8 (EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src,
GR16_ABCD)),
sub_8bit_hi))>,
Requires<[Not64BitMode]>;
def : Pat<(and (srl_su GR32:$src, (i8 8)), (i32 255)),
(MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src,
GR32_ABCD)),
sub_8bit_hi))>,
Requires<[Not64BitMode]>;
def : Pat<(srl (and_su GR32:$src, 0xff00), (i8 8)),
(MOVZX32rr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src,
GR32_ABCD)),
sub_8bit_hi))>,
Requires<[Not64BitMode]>;
// h-register tricks.
// For now, be conservative on x86-64 and use an h-register extract only if the
// value is immediately zero-extended or stored, which are somewhat common
// cases. This uses a bunch of code to prevent a register requiring a REX prefix
// from being allocated in the same instruction as the h register, as there's
// currently no way to describe this requirement to the register allocator.
// h-register extract and zero-extend.
def : Pat<(and (srl_su GR64:$src, (i8 8)), (i64 255)),
(SUBREG_TO_REG
(i64 0),
(MOVZX32_NOREXrr8
(EXTRACT_SUBREG (i64 (COPY_TO_REGCLASS GR64:$src, GR64_ABCD)),
sub_8bit_hi)),
sub_32bit)>;
def : Pat<(and (srl_su GR32:$src, (i8 8)), (i32 255)),
(MOVZX32_NOREXrr8
(EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)),
sub_8bit_hi))>,
Requires<[In64BitMode]>;
def : Pat<(srl (and_su GR32:$src, 0xff00), (i8 8)),
(MOVZX32_NOREXrr8 (EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src,
GR32_ABCD)),
sub_8bit_hi))>,
Requires<[In64BitMode]>;
def : Pat<(srl GR16:$src, (i8 8)),
(EXTRACT_SUBREG
(MOVZX32_NOREXrr8
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi)),
sub_16bit)>,
Requires<[In64BitMode]>;
def : Pat<(i32 (zext (srl_su GR16:$src, (i8 8)))),
(MOVZX32_NOREXrr8
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi))>,
Requires<[In64BitMode]>;
def : Pat<(i32 (anyext (srl_su GR16:$src, (i8 8)))),
(MOVZX32_NOREXrr8
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi))>,
Requires<[In64BitMode]>;
def : Pat<(i64 (zext (srl_su GR16:$src, (i8 8)))),
(SUBREG_TO_REG
(i64 0),
(MOVZX32_NOREXrr8
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi)),
sub_32bit)>;
def : Pat<(i64 (anyext (srl_su GR16:$src, (i8 8)))),
(SUBREG_TO_REG
(i64 0),
(MOVZX32_NOREXrr8
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi)),
sub_32bit)>;
// h-register extract and store.
def : Pat<(store (i8 (trunc_su (srl_su GR64:$src, (i8 8)))), addr:$dst),
(MOV8mr_NOREX
addr:$dst,
(EXTRACT_SUBREG (i64 (COPY_TO_REGCLASS GR64:$src, GR64_ABCD)),
sub_8bit_hi))>;
def : Pat<(store (i8 (trunc_su (srl_su GR32:$src, (i8 8)))), addr:$dst),
(MOV8mr_NOREX
addr:$dst,
(EXTRACT_SUBREG (i32 (COPY_TO_REGCLASS GR32:$src, GR32_ABCD)),
sub_8bit_hi))>,
Requires<[In64BitMode]>;
def : Pat<(store (i8 (trunc_su (srl_su GR16:$src, (i8 8)))), addr:$dst),
(MOV8mr_NOREX
addr:$dst,
(EXTRACT_SUBREG (i16 (COPY_TO_REGCLASS GR16:$src, GR16_ABCD)),
sub_8bit_hi))>,
Requires<[In64BitMode]>;
// (shl x, 1) ==> (add x, x)
// Note that if x is undef (immediate or otherwise), we could theoretically
// end up with the two uses of x getting different values, producing a result
// where the least significant bit is not 0. However, the probability of this
// happening is considered low enough that this is officially not a
// "real problem".
def : Pat<(shl GR8 :$src1, (i8 1)), (ADD8rr GR8 :$src1, GR8 :$src1)>;
def : Pat<(shl GR16:$src1, (i8 1)), (ADD16rr GR16:$src1, GR16:$src1)>;
def : Pat<(shl GR32:$src1, (i8 1)), (ADD32rr GR32:$src1, GR32:$src1)>;
def : Pat<(shl GR64:$src1, (i8 1)), (ADD64rr GR64:$src1, GR64:$src1)>;
// Helper imms that check if a mask doesn't change significant shift bits.
def immShift32 : ImmLeaf<i8, [{ return CountTrailingOnes_32(Imm) >= 5; }]>;
def immShift64 : ImmLeaf<i8, [{ return CountTrailingOnes_32(Imm) >= 6; }]>;
// Shift amount is implicitly masked.
multiclass MaskedShiftAmountPats<SDNode frag, string name> {
// (shift x (and y, 31)) ==> (shift x, y)
def : Pat<(frag GR8:$src1, (and CL, immShift32)),
(!cast<Instruction>(name # "8rCL") GR8:$src1)>;
def : Pat<(frag GR16:$src1, (and CL, immShift32)),
(!cast<Instruction>(name # "16rCL") GR16:$src1)>;
def : Pat<(frag GR32:$src1, (and CL, immShift32)),
(!cast<Instruction>(name # "32rCL") GR32:$src1)>;
def : Pat<(store (frag (loadi8 addr:$dst), (and CL, immShift32)), addr:$dst),
(!cast<Instruction>(name # "8mCL") addr:$dst)>;
def : Pat<(store (frag (loadi16 addr:$dst), (and CL, immShift32)), addr:$dst),
(!cast<Instruction>(name # "16mCL") addr:$dst)>;
def : Pat<(store (frag (loadi32 addr:$dst), (and CL, immShift32)), addr:$dst),
(!cast<Instruction>(name # "32mCL") addr:$dst)>;
// (shift x (and y, 63)) ==> (shift x, y)
def : Pat<(frag GR64:$src1, (and CL, immShift64)),
(!cast<Instruction>(name # "64rCL") GR64:$src1)>;
def : Pat<(store (frag (loadi64 addr:$dst), (and CL, 63)), addr:$dst),
(!cast<Instruction>(name # "64mCL") addr:$dst)>;
}
defm : MaskedShiftAmountPats<shl, "SHL">;
defm : MaskedShiftAmountPats<srl, "SHR">;
defm : MaskedShiftAmountPats<sra, "SAR">;
defm : MaskedShiftAmountPats<rotl, "ROL">;
defm : MaskedShiftAmountPats<rotr, "ROR">;
// (anyext (setcc_carry)) -> (setcc_carry)
def : Pat<(i16 (anyext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C16r)>;
def : Pat<(i32 (anyext (i8 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C32r)>;
def : Pat<(i32 (anyext (i16 (X86setcc_c X86_COND_B, EFLAGS)))),
(SETB_C32r)>;
//===----------------------------------------------------------------------===//
// EFLAGS-defining Patterns
//===----------------------------------------------------------------------===//
// add reg, reg
def : Pat<(add GR8 :$src1, GR8 :$src2), (ADD8rr GR8 :$src1, GR8 :$src2)>;
def : Pat<(add GR16:$src1, GR16:$src2), (ADD16rr GR16:$src1, GR16:$src2)>;
def : Pat<(add GR32:$src1, GR32:$src2), (ADD32rr GR32:$src1, GR32:$src2)>;
// add reg, mem
def : Pat<(add GR8:$src1, (loadi8 addr:$src2)),
(ADD8rm GR8:$src1, addr:$src2)>;
def : Pat<(add GR16:$src1, (loadi16 addr:$src2)),
(ADD16rm GR16:$src1, addr:$src2)>;
def : Pat<(add GR32:$src1, (loadi32 addr:$src2)),
(ADD32rm GR32:$src1, addr:$src2)>;
// add reg, imm
def : Pat<(add GR8 :$src1, imm:$src2), (ADD8ri GR8:$src1 , imm:$src2)>;
def : Pat<(add GR16:$src1, imm:$src2), (ADD16ri GR16:$src1, imm:$src2)>;
def : Pat<(add GR32:$src1, imm:$src2), (ADD32ri GR32:$src1, imm:$src2)>;
def : Pat<(add GR16:$src1, i16immSExt8:$src2),
(ADD16ri8 GR16:$src1, i16immSExt8:$src2)>;
def : Pat<(add GR32:$src1, i32immSExt8:$src2),
(ADD32ri8 GR32:$src1, i32immSExt8:$src2)>;
// sub reg, reg
def : Pat<(sub GR8 :$src1, GR8 :$src2), (SUB8rr GR8 :$src1, GR8 :$src2)>;
def : Pat<(sub GR16:$src1, GR16:$src2), (SUB16rr GR16:$src1, GR16:$src2)>;
def : Pat<(sub GR32:$src1, GR32:$src2), (SUB32rr GR32:$src1, GR32:$src2)>;
// sub reg, mem
def : Pat<(sub GR8:$src1, (loadi8 addr:$src2)),
(SUB8rm GR8:$src1, addr:$src2)>;
def : Pat<(sub GR16:$src1, (loadi16 addr:$src2)),
(SUB16rm GR16:$src1, addr:$src2)>;
def : Pat<(sub GR32:$src1, (loadi32 addr:$src2)),
(SUB32rm GR32:$src1, addr:$src2)>;
// sub reg, imm
def : Pat<(sub GR8:$src1, imm:$src2),
(SUB8ri GR8:$src1, imm:$src2)>;
def : Pat<(sub GR16:$src1, imm:$src2),
(SUB16ri GR16:$src1, imm:$src2)>;
def : Pat<(sub GR32:$src1, imm:$src2),
(SUB32ri GR32:$src1, imm:$src2)>;
def : Pat<(sub GR16:$src1, i16immSExt8:$src2),
(SUB16ri8 GR16:$src1, i16immSExt8:$src2)>;
def : Pat<(sub GR32:$src1, i32immSExt8:$src2),
(SUB32ri8 GR32:$src1, i32immSExt8:$src2)>;
// sub 0, reg
def : Pat<(X86sub_flag 0, GR8 :$src), (NEG8r GR8 :$src)>;
def : Pat<(X86sub_flag 0, GR16:$src), (NEG16r GR16:$src)>;
def : Pat<(X86sub_flag 0, GR32:$src), (NEG32r GR32:$src)>;
def : Pat<(X86sub_flag 0, GR64:$src), (NEG64r GR64:$src)>;
// mul reg, reg
def : Pat<(mul GR16:$src1, GR16:$src2),
(IMUL16rr GR16:$src1, GR16:$src2)>;
def : Pat<(mul GR32:$src1, GR32:$src2),
(IMUL32rr GR32:$src1, GR32:$src2)>;
// mul reg, mem
def : Pat<(mul GR16:$src1, (loadi16 addr:$src2)),
(IMUL16rm GR16:$src1, addr:$src2)>;
def : Pat<(mul GR32:$src1, (loadi32 addr:$src2)),
(IMUL32rm GR32:$src1, addr:$src2)>;
// mul reg, imm
def : Pat<(mul GR16:$src1, imm:$src2),
(IMUL16rri GR16:$src1, imm:$src2)>;
def : Pat<(mul GR32:$src1, imm:$src2),
(IMUL32rri GR32:$src1, imm:$src2)>;
def : Pat<(mul GR16:$src1, i16immSExt8:$src2),
(IMUL16rri8 GR16:$src1, i16immSExt8:$src2)>;
def : Pat<(mul GR32:$src1, i32immSExt8:$src2),
(IMUL32rri8 GR32:$src1, i32immSExt8:$src2)>;
// reg = mul mem, imm
def : Pat<(mul (loadi16 addr:$src1), imm:$src2),
(IMUL16rmi addr:$src1, imm:$src2)>;
def : Pat<(mul (loadi32 addr:$src1), imm:$src2),
(IMUL32rmi addr:$src1, imm:$src2)>;
def : Pat<(mul (loadi16 addr:$src1), i16immSExt8:$src2),
(IMUL16rmi8 addr:$src1, i16immSExt8:$src2)>;
def : Pat<(mul (loadi32 addr:$src1), i32immSExt8:$src2),
(IMUL32rmi8 addr:$src1, i32immSExt8:$src2)>;
// Patterns for nodes that do not produce flags, for instructions that do.
// addition
def : Pat<(add GR64:$src1, GR64:$src2),
(ADD64rr GR64:$src1, GR64:$src2)>;
def : Pat<(add GR64:$src1, i64immSExt8:$src2),
(ADD64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(add GR64:$src1, i64immSExt32:$src2),
(ADD64ri32 GR64:$src1, i64immSExt32:$src2)>;
def : Pat<(add GR64:$src1, (loadi64 addr:$src2)),
(ADD64rm GR64:$src1, addr:$src2)>;
// subtraction
def : Pat<(sub GR64:$src1, GR64:$src2),
(SUB64rr GR64:$src1, GR64:$src2)>;
def : Pat<(sub GR64:$src1, (loadi64 addr:$src2)),
(SUB64rm GR64:$src1, addr:$src2)>;
def : Pat<(sub GR64:$src1, i64immSExt8:$src2),
(SUB64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(sub GR64:$src1, i64immSExt32:$src2),
(SUB64ri32 GR64:$src1, i64immSExt32:$src2)>;
// Multiply
def : Pat<(mul GR64:$src1, GR64:$src2),
(IMUL64rr GR64:$src1, GR64:$src2)>;
def : Pat<(mul GR64:$src1, (loadi64 addr:$src2)),
(IMUL64rm GR64:$src1, addr:$src2)>;
def : Pat<(mul GR64:$src1, i64immSExt8:$src2),
(IMUL64rri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(mul GR64:$src1, i64immSExt32:$src2),
(IMUL64rri32 GR64:$src1, i64immSExt32:$src2)>;
def : Pat<(mul (loadi64 addr:$src1), i64immSExt8:$src2),
(IMUL64rmi8 addr:$src1, i64immSExt8:$src2)>;
def : Pat<(mul (loadi64 addr:$src1), i64immSExt32:$src2),
(IMUL64rmi32 addr:$src1, i64immSExt32:$src2)>;
// Increment reg.
// Do not make INC if it is slow
def : Pat<(add GR8:$src, 1),
(INC8r GR8:$src)>, Requires<[NotSlowIncDec]>;
def : Pat<(add GR16:$src, 1),
(INC16r GR16:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR16:$src, 1),
(INC64_16r GR16:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR32:$src, 1),
(INC32r GR32:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR32:$src, 1),
(INC64_32r GR32:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR64:$src, 1),
(INC64r GR64:$src)>, Requires<[NotSlowIncDec]>;
// Decrement reg.
// Do not make DEC if it is slow
def : Pat<(add GR8:$src, -1),
(DEC8r GR8:$src)>, Requires<[NotSlowIncDec]>;
def : Pat<(add GR16:$src, -1),
(DEC16r GR16:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR16:$src, -1),
(DEC64_16r GR16:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR32:$src, -1),
(DEC32r GR32:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR32:$src, -1),
(DEC64_32r GR32:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR64:$src, -1),
(DEC64r GR64:$src)>, Requires<[NotSlowIncDec]>;
// or reg/reg.
def : Pat<(or GR8 :$src1, GR8 :$src2), (OR8rr GR8 :$src1, GR8 :$src2)>;
def : Pat<(or GR16:$src1, GR16:$src2), (OR16rr GR16:$src1, GR16:$src2)>;
def : Pat<(or GR32:$src1, GR32:$src2), (OR32rr GR32:$src1, GR32:$src2)>;
def : Pat<(or GR64:$src1, GR64:$src2), (OR64rr GR64:$src1, GR64:$src2)>;
// or reg/mem
def : Pat<(or GR8:$src1, (loadi8 addr:$src2)),
(OR8rm GR8:$src1, addr:$src2)>;
def : Pat<(or GR16:$src1, (loadi16 addr:$src2)),
(OR16rm GR16:$src1, addr:$src2)>;
def : Pat<(or GR32:$src1, (loadi32 addr:$src2)),
(OR32rm GR32:$src1, addr:$src2)>;
def : Pat<(or GR64:$src1, (loadi64 addr:$src2)),
(OR64rm GR64:$src1, addr:$src2)>;
// or reg/imm
def : Pat<(or GR8:$src1 , imm:$src2), (OR8ri GR8 :$src1, imm:$src2)>;
def : Pat<(or GR16:$src1, imm:$src2), (OR16ri GR16:$src1, imm:$src2)>;
def : Pat<(or GR32:$src1, imm:$src2), (OR32ri GR32:$src1, imm:$src2)>;
def : Pat<(or GR16:$src1, i16immSExt8:$src2),
(OR16ri8 GR16:$src1, i16immSExt8:$src2)>;
def : Pat<(or GR32:$src1, i32immSExt8:$src2),
(OR32ri8 GR32:$src1, i32immSExt8:$src2)>;
def : Pat<(or GR64:$src1, i64immSExt8:$src2),
(OR64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(or GR64:$src1, i64immSExt32:$src2),
(OR64ri32 GR64:$src1, i64immSExt32:$src2)>;
// xor reg/reg
def : Pat<(xor GR8 :$src1, GR8 :$src2), (XOR8rr GR8 :$src1, GR8 :$src2)>;
def : Pat<(xor GR16:$src1, GR16:$src2), (XOR16rr GR16:$src1, GR16:$src2)>;
def : Pat<(xor GR32:$src1, GR32:$src2), (XOR32rr GR32:$src1, GR32:$src2)>;
def : Pat<(xor GR64:$src1, GR64:$src2), (XOR64rr GR64:$src1, GR64:$src2)>;
// xor reg/mem
def : Pat<(xor GR8:$src1, (loadi8 addr:$src2)),
(XOR8rm GR8:$src1, addr:$src2)>;
def : Pat<(xor GR16:$src1, (loadi16 addr:$src2)),
(XOR16rm GR16:$src1, addr:$src2)>;
def : Pat<(xor GR32:$src1, (loadi32 addr:$src2)),
(XOR32rm GR32:$src1, addr:$src2)>;
def : Pat<(xor GR64:$src1, (loadi64 addr:$src2)),
(XOR64rm GR64:$src1, addr:$src2)>;
// xor reg/imm
def : Pat<(xor GR8:$src1, imm:$src2),
(XOR8ri GR8:$src1, imm:$src2)>;
def : Pat<(xor GR16:$src1, imm:$src2),
(XOR16ri GR16:$src1, imm:$src2)>;
def : Pat<(xor GR32:$src1, imm:$src2),
(XOR32ri GR32:$src1, imm:$src2)>;
def : Pat<(xor GR16:$src1, i16immSExt8:$src2),
(XOR16ri8 GR16:$src1, i16immSExt8:$src2)>;
def : Pat<(xor GR32:$src1, i32immSExt8:$src2),
(XOR32ri8 GR32:$src1, i32immSExt8:$src2)>;
def : Pat<(xor GR64:$src1, i64immSExt8:$src2),
(XOR64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(xor GR64:$src1, i64immSExt32:$src2),
(XOR64ri32 GR64:$src1, i64immSExt32:$src2)>;
// and reg/reg
def : Pat<(and GR8 :$src1, GR8 :$src2), (AND8rr GR8 :$src1, GR8 :$src2)>;
def : Pat<(and GR16:$src1, GR16:$src2), (AND16rr GR16:$src1, GR16:$src2)>;
def : Pat<(and GR32:$src1, GR32:$src2), (AND32rr GR32:$src1, GR32:$src2)>;
def : Pat<(and GR64:$src1, GR64:$src2), (AND64rr GR64:$src1, GR64:$src2)>;
// and reg/mem
def : Pat<(and GR8:$src1, (loadi8 addr:$src2)),
(AND8rm GR8:$src1, addr:$src2)>;
def : Pat<(and GR16:$src1, (loadi16 addr:$src2)),
(AND16rm GR16:$src1, addr:$src2)>;
def : Pat<(and GR32:$src1, (loadi32 addr:$src2)),
(AND32rm GR32:$src1, addr:$src2)>;
def : Pat<(and GR64:$src1, (loadi64 addr:$src2)),
(AND64rm GR64:$src1, addr:$src2)>;
// and reg/imm
def : Pat<(and GR8:$src1, imm:$src2),
(AND8ri GR8:$src1, imm:$src2)>;
def : Pat<(and GR16:$src1, imm:$src2),
(AND16ri GR16:$src1, imm:$src2)>;
def : Pat<(and GR32:$src1, imm:$src2),
(AND32ri GR32:$src1, imm:$src2)>;
def : Pat<(and GR16:$src1, i16immSExt8:$src2),
(AND16ri8 GR16:$src1, i16immSExt8:$src2)>;
def : Pat<(and GR32:$src1, i32immSExt8:$src2),
(AND32ri8 GR32:$src1, i32immSExt8:$src2)>;
def : Pat<(and GR64:$src1, i64immSExt8:$src2),
(AND64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(and GR64:$src1, i64immSExt32:$src2),
(AND64ri32 GR64:$src1, i64immSExt32:$src2)>;
// Bit scan instruction patterns to match explicit zero-undef behavior.
def : Pat<(cttz_zero_undef GR16:$src), (BSF16rr GR16:$src)>;
def : Pat<(cttz_zero_undef GR32:$src), (BSF32rr GR32:$src)>;
def : Pat<(cttz_zero_undef GR64:$src), (BSF64rr GR64:$src)>;
def : Pat<(cttz_zero_undef (loadi16 addr:$src)), (BSF16rm addr:$src)>;
def : Pat<(cttz_zero_undef (loadi32 addr:$src)), (BSF32rm addr:$src)>;
def : Pat<(cttz_zero_undef (loadi64 addr:$src)), (BSF64rm addr:$src)>;
// When HasMOVBE is enabled it is possible to get a non-legalized
// register-register 16 bit bswap. This maps it to a ROL instruction.
let Predicates = [HasMOVBE] in {
def : Pat<(bswap GR16:$src), (ROL16ri GR16:$src, (i8 8))>;
}