llvm-project/llvm/lib/Target/X86/X86InstrXOP.td

401 lines
20 KiB
TableGen
Raw Normal View History

//===-- X86InstrXOP.td - XOP Instruction Set ---------------*- 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 XOP (eXtended OPerations)
//
//===----------------------------------------------------------------------===//
multiclass xop2op<bits<8> opc, string OpcodeStr, Intrinsic Int, PatFrag memop> {
def rr : IXOP<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (Int VR128:$src))]>, XOP, Sched<[WritePHAdd]>;
def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst), (ins i128mem:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (Int (bitconvert (memop addr:$src))))]>, XOP,
Sched<[WritePHAddLd, ReadAfterLd]>;
}
let ExeDomain = SSEPackedInt in {
defm VPHSUBWD : xop2op<0xE2, "vphsubwd", int_x86_xop_vphsubwd, loadv2i64>;
defm VPHSUBDQ : xop2op<0xE3, "vphsubdq", int_x86_xop_vphsubdq, loadv2i64>;
defm VPHSUBBW : xop2op<0xE1, "vphsubbw", int_x86_xop_vphsubbw, loadv2i64>;
defm VPHADDWQ : xop2op<0xC7, "vphaddwq", int_x86_xop_vphaddwq, loadv2i64>;
defm VPHADDWD : xop2op<0xC6, "vphaddwd", int_x86_xop_vphaddwd, loadv2i64>;
defm VPHADDUWQ : xop2op<0xD7, "vphadduwq", int_x86_xop_vphadduwq, loadv2i64>;
defm VPHADDUWD : xop2op<0xD6, "vphadduwd", int_x86_xop_vphadduwd, loadv2i64>;
defm VPHADDUDQ : xop2op<0xDB, "vphaddudq", int_x86_xop_vphaddudq, loadv2i64>;
defm VPHADDUBW : xop2op<0xD1, "vphaddubw", int_x86_xop_vphaddubw, loadv2i64>;
defm VPHADDUBQ : xop2op<0xD3, "vphaddubq", int_x86_xop_vphaddubq, loadv2i64>;
defm VPHADDUBD : xop2op<0xD2, "vphaddubd", int_x86_xop_vphaddubd, loadv2i64>;
defm VPHADDDQ : xop2op<0xCB, "vphadddq", int_x86_xop_vphadddq, loadv2i64>;
defm VPHADDBW : xop2op<0xC1, "vphaddbw", int_x86_xop_vphaddbw, loadv2i64>;
defm VPHADDBQ : xop2op<0xC3, "vphaddbq", int_x86_xop_vphaddbq, loadv2i64>;
defm VPHADDBD : xop2op<0xC2, "vphaddbd", int_x86_xop_vphaddbd, loadv2i64>;
}
// Scalar load 2 addr operand instructions
multiclass xop2opsld<bits<8> opc, string OpcodeStr, Intrinsic Int,
Operand memop, ComplexPattern mem_cpat> {
def rr : IXOP<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (Int VR128:$src))]>, XOP, Sched<[WriteFAdd]>;
def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst), (ins memop:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (Int (bitconvert mem_cpat:$src)))]>, XOP,
Sched<[WriteFAddLd, ReadAfterLd]>;
}
multiclass xop2op128<bits<8> opc, string OpcodeStr, Intrinsic Int,
PatFrag memop> {
def rr : IXOP<opc, MRMSrcReg, (outs VR128:$dst), (ins VR128:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (Int VR128:$src))]>, XOP, Sched<[WriteFAdd]>;
def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst), (ins f128mem:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR128:$dst, (Int (bitconvert (memop addr:$src))))]>, XOP,
Sched<[WriteFAddLd, ReadAfterLd]>;
}
multiclass xop2op256<bits<8> opc, string OpcodeStr, Intrinsic Int,
PatFrag memop> {
def Yrr : IXOP<opc, MRMSrcReg, (outs VR256:$dst), (ins VR256:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR256:$dst, (Int VR256:$src))]>, XOP, VEX_L, Sched<[WriteFAdd]>;
def Yrm : IXOP<opc, MRMSrcMem, (outs VR256:$dst), (ins f256mem:$src),
!strconcat(OpcodeStr, "\t{$src, $dst|$dst, $src}"),
[(set VR256:$dst, (Int (bitconvert (memop addr:$src))))]>, XOP, VEX_L,
Sched<[WriteFAddLd, ReadAfterLd]>;
}
let ExeDomain = SSEPackedSingle in {
defm VFRCZSS : xop2opsld<0x82, "vfrczss", int_x86_xop_vfrcz_ss,
ssmem, sse_load_f32>;
defm VFRCZPS : xop2op128<0x80, "vfrczps", int_x86_xop_vfrcz_ps, loadv4f32>;
defm VFRCZPS : xop2op256<0x80, "vfrczps", int_x86_xop_vfrcz_ps_256, loadv8f32>;
}
let ExeDomain = SSEPackedDouble in {
defm VFRCZSD : xop2opsld<0x83, "vfrczsd", int_x86_xop_vfrcz_sd,
sdmem, sse_load_f64>;
defm VFRCZPD : xop2op128<0x81, "vfrczpd", int_x86_xop_vfrcz_pd, loadv2f64>;
defm VFRCZPD : xop2op256<0x81, "vfrczpd", int_x86_xop_vfrcz_pd_256, loadv4f64>;
}
multiclass xop3op<bits<8> opc, string OpcodeStr, SDNode OpNode,
ValueType vt128> {
def rr : IXOP<opc, MRMSrcReg4VOp3, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2))))]>,
XOP, Sched<[WriteVarVecShift]>;
def rm : IXOP<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, i128mem:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 VR128:$src1),
(vt128 (bitconvert (loadv2i64 addr:$src2))))))]>,
XOP_4V, VEX_W, Sched<[WriteVarVecShiftLd, ReadAfterLd]>;
def mr : IXOP<opc, MRMSrcMem4VOp3, (outs VR128:$dst),
(ins i128mem:$src1, VR128:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 (bitconvert (loadv2i64 addr:$src1))),
(vt128 VR128:$src2))))]>,
XOP, Sched<[WriteVarVecShiftLd, ReadAfterLd]>;
// For disassembler
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
def rr_REV : IXOP<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[]>,
[X86] Adding FoldGenRegForm helper field (for memory folding tables tableGen backend) to X86Inst class and set its value for the relevant instructions. Some register-register instructions can be encoded in 2 different ways, this happens when 2 register operands can be folded (separately). For example if we look at the MOV8rr and MOV8rr_REV, both instructions perform exactly the same operation, but are encoded differently. Here is the relevant information about these instructions from Intel's 64-ia-32-architectures-software-developer-manual: Opcode Instruction Op/En 64-Bit Mode Compat/Leg Mode Description 8A /r MOV r8,r/m8 RM Valid Valid Move r/m8 to r8. 88 /r MOV r/m8,r8 MR Valid Valid Move r8 to r/m8. Here we can see that in order to enable the folding of the output and input registers, we had to define 2 "encodings", and as a result we got 2 move 8-bit register-register instructions. In the X86 backend, we define both of these instructions, usually one has a regular name (MOV8rr) while the other has "_REV" suffix (MOV8rr_REV), must be marked with isCodeGenOnly flag and is not emitted from CodeGen. Automatically generating the memory folding tables relies on matching encodings of instructions, but in these cases where we want to map both memory forms of the mov 8-bit (MOV8rm & MOV8mr) to MOV8rr (not to MOV8rr_REV) we have to somehow point from the MOV8rr_REV to the "regular" appropriate instruction which in this case is MOV8rr. This field enable this "pointing" mechanism - which is used in the TableGen backend for generating memory folding tables. Differential Revision: https://reviews.llvm.org/D32683 llvm-svn: 304087
2017-05-28 20:39:37 +08:00
XOP_4V, VEX_W, Sched<[WriteVarVecShift]>, FoldGenData<NAME#rr>;
}
let ExeDomain = SSEPackedInt in {
defm VPROTB : xop3op<0x90, "vprotb", rotl, v16i8>;
defm VPROTD : xop3op<0x92, "vprotd", rotl, v4i32>;
defm VPROTQ : xop3op<0x93, "vprotq", rotl, v2i64>;
defm VPROTW : xop3op<0x91, "vprotw", rotl, v8i16>;
defm VPSHAB : xop3op<0x98, "vpshab", X86vpsha, v16i8>;
defm VPSHAD : xop3op<0x9A, "vpshad", X86vpsha, v4i32>;
defm VPSHAQ : xop3op<0x9B, "vpshaq", X86vpsha, v2i64>;
defm VPSHAW : xop3op<0x99, "vpshaw", X86vpsha, v8i16>;
defm VPSHLB : xop3op<0x94, "vpshlb", X86vpshl, v16i8>;
defm VPSHLD : xop3op<0x96, "vpshld", X86vpshl, v4i32>;
defm VPSHLQ : xop3op<0x97, "vpshlq", X86vpshl, v2i64>;
defm VPSHLW : xop3op<0x95, "vpshlw", X86vpshl, v8i16>;
}
multiclass xop3opimm<bits<8> opc, string OpcodeStr, SDNode OpNode,
ValueType vt128> {
def ri : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, u8imm:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 VR128:$src1), imm:$src2)))]>,
XOP, Sched<[WriteVecShift]>;
def mi : IXOPi8<opc, MRMSrcMem, (outs VR128:$dst),
(ins i128mem:$src1, u8imm:$src2),
!strconcat(OpcodeStr, "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 (bitconvert (loadv2i64 addr:$src1))), imm:$src2)))]>,
XOP, Sched<[WriteVecShiftLd, ReadAfterLd]>;
}
let ExeDomain = SSEPackedInt in {
defm VPROTB : xop3opimm<0xC0, "vprotb", X86vrotli, v16i8>;
defm VPROTD : xop3opimm<0xC2, "vprotd", X86vrotli, v4i32>;
defm VPROTQ : xop3opimm<0xC3, "vprotq", X86vrotli, v2i64>;
defm VPROTW : xop3opimm<0xC1, "vprotw", X86vrotli, v8i16>;
}
// Instruction where second source can be memory, but third must be register
multiclass xop4opm2<bits<8> opc, string OpcodeStr, Intrinsic Int> {
let isCommutable = 1 in
def rr : IXOPi8Reg<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set VR128:$dst,
(Int VR128:$src1, VR128:$src2, VR128:$src3))]>, XOP_4V,
Sched<[WriteVecIMul]>;
def rm : IXOPi8Reg<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, i128mem:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set VR128:$dst,
(Int VR128:$src1, (bitconvert (loadv2i64 addr:$src2)),
VR128:$src3))]>, XOP_4V, Sched<[WriteVecIMulLd, ReadAfterLd]>;
}
let ExeDomain = SSEPackedInt in {
defm VPMADCSWD : xop4opm2<0xB6, "vpmadcswd", int_x86_xop_vpmadcswd>;
defm VPMADCSSWD : xop4opm2<0xA6, "vpmadcsswd", int_x86_xop_vpmadcsswd>;
defm VPMACSWW : xop4opm2<0x95, "vpmacsww", int_x86_xop_vpmacsww>;
defm VPMACSWD : xop4opm2<0x96, "vpmacswd", int_x86_xop_vpmacswd>;
defm VPMACSSWW : xop4opm2<0x85, "vpmacssww", int_x86_xop_vpmacssww>;
defm VPMACSSWD : xop4opm2<0x86, "vpmacsswd", int_x86_xop_vpmacsswd>;
defm VPMACSSDQL : xop4opm2<0x87, "vpmacssdql", int_x86_xop_vpmacssdql>;
defm VPMACSSDQH : xop4opm2<0x8F, "vpmacssdqh", int_x86_xop_vpmacssdqh>;
defm VPMACSSDD : xop4opm2<0x8E, "vpmacssdd", int_x86_xop_vpmacssdd>;
defm VPMACSDQL : xop4opm2<0x97, "vpmacsdql", int_x86_xop_vpmacsdql>;
defm VPMACSDQH : xop4opm2<0x9F, "vpmacsdqh", int_x86_xop_vpmacsdqh>;
defm VPMACSDD : xop4opm2<0x9E, "vpmacsdd", int_x86_xop_vpmacsdd>;
}
// IFMA patterns - for cases where we can safely ignore the overflow bits from
// the multiply or easily match with existing intrinsics.
let Predicates = [HasXOP] in {
def : Pat<(v8i16 (add (mul (v8i16 VR128:$src1), (v8i16 VR128:$src2)),
(v8i16 VR128:$src3))),
(VPMACSWWrr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(v4i32 (add (mul (v4i32 VR128:$src1), (v4i32 VR128:$src2)),
(v4i32 VR128:$src3))),
(VPMACSDDrr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(v2i64 (add (X86pmuldq (bc_v2i64 (X86PShufd (v4i32 VR128:$src1), (i8 -11))),
(bc_v2i64 (X86PShufd (v4i32 VR128:$src2), (i8 -11)))),
(v2i64 VR128:$src3))),
(VPMACSDQHrr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(v2i64 (add (X86pmuldq (v2i64 VR128:$src1), (v2i64 VR128:$src2)),
(v2i64 VR128:$src3))),
(VPMACSDQLrr VR128:$src1, VR128:$src2, VR128:$src3)>;
def : Pat<(v4i32 (add (X86vpmaddwd (v8i16 VR128:$src1), (v8i16 VR128:$src2)),
(v4i32 VR128:$src3))),
(VPMADCSWDrr VR128:$src1, VR128:$src2, VR128:$src3)>;
}
// Transforms to swizzle an immediate to help matching memory operand in first
// operand.
def CommuteVPCOMCC : SDNodeXForm<imm, [{
uint8_t Imm = N->getZExtValue() & 0x7;
Imm = X86::getSwappedVPCOMImm(Imm);
return getI8Imm(Imm, SDLoc(N));
}]>;
// Instruction where second source can be memory, third must be imm8
multiclass xopvpcom<bits<8> opc, string Suffix, SDNode OpNode, ValueType vt128> {
let ExeDomain = SSEPackedInt in { // SSE integer instructions
let isCommutable = 1 in
def ri : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, XOPCC:$cc),
!strconcat("vpcom${cc}", Suffix,
"\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
imm:$cc)))]>,
XOP_4V, Sched<[WriteVecALULd, ReadAfterLd]>;
def mi : IXOPi8<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, i128mem:$src2, XOPCC:$cc),
!strconcat("vpcom${cc}", Suffix,
"\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 VR128:$src1),
(vt128 (bitconvert (loadv2i64 addr:$src2))),
imm:$cc)))]>,
XOP_4V, Sched<[WriteVecALULd, ReadAfterLd]>;
let isAsmParserOnly = 1, hasSideEffects = 0 in {
def ri_alt : IXOPi8<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, u8imm:$src3),
!strconcat("vpcom", Suffix,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_4V, Sched<[WriteVecALULd, ReadAfterLd]>;
let mayLoad = 1 in
def mi_alt : IXOPi8<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, i128mem:$src2, u8imm:$src3),
!strconcat("vpcom", Suffix,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_4V, Sched<[WriteVecALULd, ReadAfterLd]>;
}
}
def : Pat<(OpNode (bitconvert (loadv2i64 addr:$src2)),
(vt128 VR128:$src1), imm:$cc),
(!cast<Instruction>(NAME#"mi") VR128:$src1, addr:$src2,
(CommuteVPCOMCC imm:$cc))>;
}
defm VPCOMB : xopvpcom<0xCC, "b", X86vpcom, v16i8>;
defm VPCOMW : xopvpcom<0xCD, "w", X86vpcom, v8i16>;
defm VPCOMD : xopvpcom<0xCE, "d", X86vpcom, v4i32>;
defm VPCOMQ : xopvpcom<0xCF, "q", X86vpcom, v2i64>;
defm VPCOMUB : xopvpcom<0xEC, "ub", X86vpcomu, v16i8>;
defm VPCOMUW : xopvpcom<0xED, "uw", X86vpcomu, v8i16>;
defm VPCOMUD : xopvpcom<0xEE, "ud", X86vpcomu, v4i32>;
defm VPCOMUQ : xopvpcom<0xEF, "uq", X86vpcomu, v2i64>;
multiclass xop4op<bits<8> opc, string OpcodeStr, SDNode OpNode,
ValueType vt128> {
def rrr : IXOPi8Reg<opc, MRMSrcReg, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
(vt128 VR128:$src3))))]>,
XOP_4V, Sched<[WriteShuffle]>;
def rrm : IXOPi8Reg<opc, MRMSrcMemOp4, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, i128mem:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set VR128:$dst,
(vt128 (OpNode (vt128 VR128:$src1), (vt128 VR128:$src2),
(vt128 (bitconvert (loadv2i64 addr:$src3))))))]>,
XOP_4V, VEX_W, Sched<[WriteShuffleLd, ReadAfterLd]>;
def rmr : IXOPi8Reg<opc, MRMSrcMem, (outs VR128:$dst),
(ins VR128:$src1, i128mem:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set VR128:$dst,
(v16i8 (OpNode (vt128 VR128:$src1), (vt128 (bitconvert (loadv2i64 addr:$src2))),
(vt128 VR128:$src3))))]>,
XOP_4V, Sched<[WriteShuffleLd, ReadAfterLd]>;
// For disassembler
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
def rrr_REV : IXOPi8Reg<opc, MRMSrcRegOp4, (outs VR128:$dst),
(ins VR128:$src1, VR128:$src2, VR128:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_4V, VEX_W, Sched<[WriteShuffle]>, FoldGenData<NAME#rrr>;
}
let ExeDomain = SSEPackedInt in {
defm VPPERM : xop4op<0xA3, "vpperm", X86vpperm, v16i8>;
}
// Instruction where either second or third source can be memory
multiclass xop4op_int<bits<8> opc, string OpcodeStr, RegisterClass RC,
X86MemOperand x86memop, ValueType VT> {
def rrr : IXOPi8Reg<opc, MRMSrcReg, (outs RC:$dst),
(ins RC:$src1, RC:$src2, RC:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set RC:$dst, (VT (or (and RC:$src3, RC:$src1),
(X86andnp RC:$src3, RC:$src2))))]>, XOP_4V,
Sched<[WriteShuffle]>;
def rrm : IXOPi8Reg<opc, MRMSrcMemOp4, (outs RC:$dst),
(ins RC:$src1, RC:$src2, x86memop:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set RC:$dst, (VT (or (and (load addr:$src3), RC:$src1),
(X86andnp (load addr:$src3), RC:$src2))))]>,
XOP_4V, VEX_W, Sched<[WriteShuffleLd, ReadAfterLd]>;
def rmr : IXOPi8Reg<opc, MRMSrcMem, (outs RC:$dst),
(ins RC:$src1, x86memop:$src2, RC:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[(set RC:$dst, (VT (or (and RC:$src3, RC:$src1),
(X86andnp RC:$src3, (load addr:$src2)))))]>,
XOP_4V, Sched<[WriteShuffleLd, ReadAfterLd]>;
// For disassembler
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
def rrr_REV : IXOPi8Reg<opc, MRMSrcRegOp4, (outs RC:$dst),
(ins RC:$src1, RC:$src2, RC:$src3),
!strconcat(OpcodeStr,
"\t{$src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3}"),
[]>, XOP_4V, VEX_W, Sched<[WriteShuffle]>, FoldGenData<NAME#rrr>;
}
let ExeDomain = SSEPackedInt in {
defm VPCMOV : xop4op_int<0xA2, "vpcmov", VR128, i128mem, v2i64>;
defm VPCMOVY : xop4op_int<0xA2, "vpcmov", VR256, i256mem, v4i64>, VEX_L;
}
multiclass xop_vpermil2<bits<8> Opc, string OpcodeStr, RegisterClass RC,
X86MemOperand intmemop, X86MemOperand fpmemop,
ValueType VT, PatFrag FPLdFrag,
PatFrag IntLdFrag> {
def rr : IXOP5<Opc, MRMSrcReg, (outs RC:$dst),
(ins RC:$src1, RC:$src2, RC:$src3, u8imm:$src4),
!strconcat(OpcodeStr,
"\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
[(set RC:$dst,
(VT (X86vpermil2 RC:$src1, RC:$src2, RC:$src3, (i8 imm:$src4))))]>,
Sched<[WriteFShuffle]>;
def rm : IXOP5<Opc, MRMSrcMemOp4, (outs RC:$dst),
(ins RC:$src1, RC:$src2, intmemop:$src3, u8imm:$src4),
!strconcat(OpcodeStr,
"\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
[(set RC:$dst,
(VT (X86vpermil2 RC:$src1, RC:$src2,
(bitconvert (IntLdFrag addr:$src3)),
(i8 imm:$src4))))]>, VEX_W,
Sched<[WriteFShuffleLd, ReadAfterLd]>;
def mr : IXOP5<Opc, MRMSrcMem, (outs RC:$dst),
(ins RC:$src1, fpmemop:$src2, RC:$src3, u8imm:$src4),
!strconcat(OpcodeStr,
"\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
[(set RC:$dst,
(VT (X86vpermil2 RC:$src1, (FPLdFrag addr:$src2),
RC:$src3, (i8 imm:$src4))))]>,
Sched<[WriteFShuffleLd, ReadAfterLd]>;
// For disassembler
let isCodeGenOnly = 1, ForceDisassemble = 1, hasSideEffects = 0 in
def rr_REV : IXOP5<Opc, MRMSrcRegOp4, (outs RC:$dst),
(ins RC:$src1, RC:$src2, RC:$src3, u8imm:$src4),
!strconcat(OpcodeStr,
"\t{$src4, $src3, $src2, $src1, $dst|$dst, $src1, $src2, $src3, $src4}"),
[]>, VEX_W, Sched<[WriteFShuffle]>, FoldGenData<NAME#rr>;
}
let ExeDomain = SSEPackedDouble in {
defm VPERMIL2PD : xop_vpermil2<0x49, "vpermil2pd", VR128, i128mem, f128mem,
v2f64, loadv2f64, loadv2i64>;
defm VPERMIL2PDY : xop_vpermil2<0x49, "vpermil2pd", VR256, i256mem, f256mem,
v4f64, loadv4f64, loadv4i64>, VEX_L;
}
let ExeDomain = SSEPackedSingle in {
defm VPERMIL2PS : xop_vpermil2<0x48, "vpermil2ps", VR128, i128mem, f128mem,
v4f32, loadv4f32, loadv2i64>;
defm VPERMIL2PSY : xop_vpermil2<0x48, "vpermil2ps", VR256, i256mem, f256mem,
v8f32, loadv8f32, loadv4i64>, VEX_L;
}