forked from OSchip/llvm-project
528 lines
24 KiB
TableGen
528 lines
24 KiB
TableGen
//===-- X86InstrFragmentsSIMD.td - x86 SIMD ISA ------------*- tablegen -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file provides pattern fragments useful for SIMD instructions.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// MMX Pattern Fragments
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def load_mmx : PatFrag<(ops node:$ptr), (x86mmx (load node:$ptr))>;
|
|
def bc_mmx : PatFrag<(ops node:$in), (x86mmx (bitconvert node:$in))>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE specific DAG Nodes.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def SDTX86FPShiftOp : SDTypeProfile<1, 2, [ SDTCisSameAs<0, 1>,
|
|
SDTCisFP<0>, SDTCisInt<2> ]>;
|
|
def SDTX86VFCMP : SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisSameAs<1, 2>,
|
|
SDTCisFP<1>, SDTCisVT<3, i8>]>;
|
|
|
|
def X86umin : SDNode<"X86ISD::UMIN", SDTIntBinOp>;
|
|
def X86umax : SDNode<"X86ISD::UMAX", SDTIntBinOp>;
|
|
def X86smin : SDNode<"X86ISD::SMIN", SDTIntBinOp>;
|
|
def X86smax : SDNode<"X86ISD::SMAX", SDTIntBinOp>;
|
|
|
|
def X86fmin : SDNode<"X86ISD::FMIN", SDTFPBinOp>;
|
|
def X86fmax : SDNode<"X86ISD::FMAX", SDTFPBinOp>;
|
|
|
|
// Commutative and Associative FMIN and FMAX.
|
|
def X86fminc : SDNode<"X86ISD::FMINC", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86fmaxc : SDNode<"X86ISD::FMAXC", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
|
|
def X86fand : SDNode<"X86ISD::FAND", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86for : SDNode<"X86ISD::FOR", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86fxor : SDNode<"X86ISD::FXOR", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86fandn : SDNode<"X86ISD::FANDN", SDTFPBinOp,
|
|
[SDNPCommutative, SDNPAssociative]>;
|
|
def X86frsqrt : SDNode<"X86ISD::FRSQRT", SDTFPUnaryOp>;
|
|
def X86frcp : SDNode<"X86ISD::FRCP", SDTFPUnaryOp>;
|
|
def X86fsrl : SDNode<"X86ISD::FSRL", SDTX86FPShiftOp>;
|
|
def X86fgetsign: SDNode<"X86ISD::FGETSIGNx86",SDTFPToIntOp>;
|
|
def X86fhadd : SDNode<"X86ISD::FHADD", SDTFPBinOp>;
|
|
def X86fhsub : SDNode<"X86ISD::FHSUB", SDTFPBinOp>;
|
|
def X86hadd : SDNode<"X86ISD::HADD", SDTIntBinOp>;
|
|
def X86hsub : SDNode<"X86ISD::HSUB", SDTIntBinOp>;
|
|
def X86comi : SDNode<"X86ISD::COMI", SDTX86CmpTest>;
|
|
def X86ucomi : SDNode<"X86ISD::UCOMI", SDTX86CmpTest>;
|
|
def X86cmpss : SDNode<"X86ISD::FSETCCss", SDTX86Cmpss>;
|
|
def X86cmpsd : SDNode<"X86ISD::FSETCCsd", SDTX86Cmpsd>;
|
|
def X86pshufb : SDNode<"X86ISD::PSHUFB",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<0,2>]>>;
|
|
def X86andnp : SDNode<"X86ISD::ANDNP",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<0,2>]>>;
|
|
def X86psign : SDNode<"X86ISD::PSIGN",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<0,2>]>>;
|
|
def X86pextrb : SDNode<"X86ISD::PEXTRB",
|
|
SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<2>]>>;
|
|
def X86pextrw : SDNode<"X86ISD::PEXTRW",
|
|
SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<2>]>>;
|
|
def X86pinsrb : SDNode<"X86ISD::PINSRB",
|
|
SDTypeProfile<1, 3, [SDTCisVT<0, v16i8>, SDTCisSameAs<0,1>,
|
|
SDTCisVT<2, i32>, SDTCisPtrTy<3>]>>;
|
|
def X86pinsrw : SDNode<"X86ISD::PINSRW",
|
|
SDTypeProfile<1, 3, [SDTCisVT<0, v8i16>, SDTCisSameAs<0,1>,
|
|
SDTCisVT<2, i32>, SDTCisPtrTy<3>]>>;
|
|
def X86insrtps : SDNode<"X86ISD::INSERTPS",
|
|
SDTypeProfile<1, 3, [SDTCisVT<0, v4f32>, SDTCisSameAs<0,1>,
|
|
SDTCisVT<2, v4f32>, SDTCisPtrTy<3>]>>;
|
|
def X86vzmovl : SDNode<"X86ISD::VZEXT_MOVL",
|
|
SDTypeProfile<1, 1, [SDTCisSameAs<0,1>]>>;
|
|
|
|
def X86vzmovly : SDNode<"X86ISD::VZEXT_MOVL",
|
|
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
|
|
SDTCisOpSmallerThanOp<1, 0> ]>>;
|
|
|
|
def X86vsmovl : SDNode<"X86ISD::VSEXT_MOVL",
|
|
SDTypeProfile<1, 1,
|
|
[SDTCisVec<0>, SDTCisInt<1>, SDTCisInt<0>]>>;
|
|
|
|
def X86vzload : SDNode<"X86ISD::VZEXT_LOAD", SDTLoad,
|
|
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
|
|
|
|
def X86vzext : SDNode<"X86ISD::VZEXT",
|
|
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
|
|
SDTCisInt<0>, SDTCisInt<1>]>>;
|
|
|
|
def X86vsext : SDNode<"X86ISD::VSEXT",
|
|
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
|
|
SDTCisInt<0>, SDTCisInt<1>]>>;
|
|
|
|
def X86vfpext : SDNode<"X86ISD::VFPEXT",
|
|
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
|
|
SDTCisFP<0>, SDTCisFP<1>]>>;
|
|
def X86vfpround: SDNode<"X86ISD::VFPROUND",
|
|
SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVec<1>,
|
|
SDTCisFP<0>, SDTCisFP<1>]>>;
|
|
|
|
def X86vshldq : SDNode<"X86ISD::VSHLDQ", SDTIntShiftOp>;
|
|
def X86vshrdq : SDNode<"X86ISD::VSRLDQ", SDTIntShiftOp>;
|
|
def X86cmpp : SDNode<"X86ISD::CMPP", SDTX86VFCMP>;
|
|
def X86pcmpeq : SDNode<"X86ISD::PCMPEQ", SDTIntBinOp, [SDNPCommutative]>;
|
|
def X86pcmpgt : SDNode<"X86ISD::PCMPGT", SDTIntBinOp>;
|
|
|
|
def X86IntCmpMask : SDTypeProfile<1, 2,
|
|
[SDTCisVec<0>, SDTCisSameAs<1, 2>, SDTCisInt<1>]>;
|
|
def X86pcmpeqm : SDNode<"X86ISD::PCMPEQM", X86IntCmpMask, [SDNPCommutative]>;
|
|
def X86pcmpgtm : SDNode<"X86ISD::PCMPGTM", X86IntCmpMask>;
|
|
|
|
def X86CmpMaskCC : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<1, 2>, SDTCisVT<3, i8>]>;
|
|
def X86cmpm : SDNode<"X86ISD::CMPM", X86CmpMaskCC>;
|
|
def X86cmpmu : SDNode<"X86ISD::CMPMU", X86CmpMaskCC>;
|
|
|
|
def X86vshl : SDNode<"X86ISD::VSHL",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisVec<2>]>>;
|
|
def X86vsrl : SDNode<"X86ISD::VSRL",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisVec<2>]>>;
|
|
def X86vsra : SDNode<"X86ISD::VSRA",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisVec<2>]>>;
|
|
|
|
def X86vshli : SDNode<"X86ISD::VSHLI", SDTIntShiftOp>;
|
|
def X86vsrli : SDNode<"X86ISD::VSRLI", SDTIntShiftOp>;
|
|
def X86vsrai : SDNode<"X86ISD::VSRAI", SDTIntShiftOp>;
|
|
|
|
def SDTX86CmpPTest : SDTypeProfile<1, 2, [SDTCisVT<0, i32>,
|
|
SDTCisVec<1>,
|
|
SDTCisSameAs<2, 1>]>;
|
|
def X86subus : SDNode<"X86ISD::SUBUS", SDTIntBinOp>;
|
|
def X86ptest : SDNode<"X86ISD::PTEST", SDTX86CmpPTest>;
|
|
def X86testp : SDNode<"X86ISD::TESTP", SDTX86CmpPTest>;
|
|
def X86kortest : SDNode<"X86ISD::KORTEST", SDTX86CmpPTest>;
|
|
def X86ktest : SDNode<"X86ISD::KTEST", SDTX86CmpPTest>;
|
|
def X86testm : SDNode<"X86ISD::TESTM", SDTypeProfile<1, 2, [SDTCisVec<0>,
|
|
SDTCisVec<1>,
|
|
SDTCisSameAs<2, 1>]>>;
|
|
|
|
def X86pmuludq : SDNode<"X86ISD::PMULUDQ",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
|
|
SDTCisSameAs<1,2>]>>;
|
|
|
|
// Specific shuffle nodes - At some point ISD::VECTOR_SHUFFLE will always get
|
|
// translated into one of the target nodes below during lowering.
|
|
// Note: this is a work in progress...
|
|
def SDTShuff1Op : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
|
|
def SDTShuff2Op : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<0,2>]>;
|
|
def SDTShuff3Op : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<0,2>, SDTCisSameAs<0,3>]>;
|
|
|
|
def SDTShuff2OpI : SDTypeProfile<1, 2, [SDTCisVec<0>,
|
|
SDTCisSameAs<0,1>, SDTCisInt<2>]>;
|
|
def SDTShuff3OpI : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<0,2>, SDTCisInt<3>]>;
|
|
|
|
def SDTVBroadcast : SDTypeProfile<1, 1, [SDTCisVec<0>]>;
|
|
def SDTVBroadcastm : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>]>;
|
|
|
|
def SDTBlend : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<1,2>, SDTCisVT<3, i32>]>;
|
|
|
|
def SDTFma : SDTypeProfile<1, 3, [SDTCisSameAs<0,1>,
|
|
SDTCisSameAs<1,2>, SDTCisSameAs<1,3>]>;
|
|
|
|
def X86PAlignr : SDNode<"X86ISD::PALIGNR", SDTShuff3OpI>;
|
|
|
|
def X86PShufd : SDNode<"X86ISD::PSHUFD", SDTShuff2OpI>;
|
|
def X86PShufhw : SDNode<"X86ISD::PSHUFHW", SDTShuff2OpI>;
|
|
def X86PShuflw : SDNode<"X86ISD::PSHUFLW", SDTShuff2OpI>;
|
|
|
|
def X86Shufp : SDNode<"X86ISD::SHUFP", SDTShuff3OpI>;
|
|
|
|
def X86Movddup : SDNode<"X86ISD::MOVDDUP", SDTShuff1Op>;
|
|
def X86Movshdup : SDNode<"X86ISD::MOVSHDUP", SDTShuff1Op>;
|
|
def X86Movsldup : SDNode<"X86ISD::MOVSLDUP", SDTShuff1Op>;
|
|
|
|
def X86Movsd : SDNode<"X86ISD::MOVSD", SDTShuff2Op>;
|
|
def X86Movss : SDNode<"X86ISD::MOVSS", SDTShuff2Op>;
|
|
|
|
def X86Movlhps : SDNode<"X86ISD::MOVLHPS", SDTShuff2Op>;
|
|
def X86Movlhpd : SDNode<"X86ISD::MOVLHPD", SDTShuff2Op>;
|
|
def X86Movhlps : SDNode<"X86ISD::MOVHLPS", SDTShuff2Op>;
|
|
|
|
def X86Movlps : SDNode<"X86ISD::MOVLPS", SDTShuff2Op>;
|
|
def X86Movlpd : SDNode<"X86ISD::MOVLPD", SDTShuff2Op>;
|
|
|
|
def X86Unpckl : SDNode<"X86ISD::UNPCKL", SDTShuff2Op>;
|
|
def X86Unpckh : SDNode<"X86ISD::UNPCKH", SDTShuff2Op>;
|
|
|
|
def X86VPermilp : SDNode<"X86ISD::VPERMILP", SDTShuff2OpI>;
|
|
def X86VPermv : SDNode<"X86ISD::VPERMV", SDTShuff2Op>;
|
|
def X86VPermi : SDNode<"X86ISD::VPERMI", SDTShuff2OpI>;
|
|
def X86VPermv3 : SDNode<"X86ISD::VPERMV3", SDTShuff3Op>;
|
|
|
|
def X86VPerm2x128 : SDNode<"X86ISD::VPERM2X128", SDTShuff3OpI>;
|
|
|
|
def X86VBroadcast : SDNode<"X86ISD::VBROADCAST", SDTVBroadcast>;
|
|
def X86VBroadcastm : SDNode<"X86ISD::VBROADCASTM", SDTVBroadcastm>;
|
|
|
|
def X86Blendi : SDNode<"X86ISD::BLENDI", SDTBlend>;
|
|
def X86Fmadd : SDNode<"X86ISD::FMADD", SDTFma>;
|
|
def X86Fnmadd : SDNode<"X86ISD::FNMADD", SDTFma>;
|
|
def X86Fmsub : SDNode<"X86ISD::FMSUB", SDTFma>;
|
|
def X86Fnmsub : SDNode<"X86ISD::FNMSUB", SDTFma>;
|
|
def X86Fmaddsub : SDNode<"X86ISD::FMADDSUB", SDTFma>;
|
|
def X86Fmsubadd : SDNode<"X86ISD::FMSUBADD", SDTFma>;
|
|
|
|
def SDT_PCMPISTRI : SDTypeProfile<2, 3, [SDTCisVT<0, i32>, SDTCisVT<1, i32>,
|
|
SDTCisVT<2, v16i8>, SDTCisVT<3, v16i8>,
|
|
SDTCisVT<4, i8>]>;
|
|
def SDT_PCMPESTRI : SDTypeProfile<2, 5, [SDTCisVT<0, i32>, SDTCisVT<1, i32>,
|
|
SDTCisVT<2, v16i8>, SDTCisVT<3, i32>,
|
|
SDTCisVT<4, v16i8>, SDTCisVT<5, i32>,
|
|
SDTCisVT<6, i8>]>;
|
|
|
|
def X86pcmpistri : SDNode<"X86ISD::PCMPISTRI", SDT_PCMPISTRI>;
|
|
def X86pcmpestri : SDNode<"X86ISD::PCMPESTRI", SDT_PCMPESTRI>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE Complex Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// These are 'extloads' from a scalar to the low element of a vector, zeroing
|
|
// the top elements. These are used for the SSE 'ss' and 'sd' instruction
|
|
// forms.
|
|
def sse_load_f32 : ComplexPattern<v4f32, 5, "SelectScalarSSELoad", [],
|
|
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand,
|
|
SDNPWantRoot]>;
|
|
def sse_load_f64 : ComplexPattern<v2f64, 5, "SelectScalarSSELoad", [],
|
|
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand,
|
|
SDNPWantRoot]>;
|
|
|
|
def ssmem : Operand<v4f32> {
|
|
let PrintMethod = "printf32mem";
|
|
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
|
|
let ParserMatchClass = X86MemAsmOperand;
|
|
let OperandType = "OPERAND_MEMORY";
|
|
}
|
|
def sdmem : Operand<v2f64> {
|
|
let PrintMethod = "printf64mem";
|
|
let MIOperandInfo = (ops ptr_rc, i8imm, ptr_rc_nosp, i32imm, i8imm);
|
|
let ParserMatchClass = X86MemAsmOperand;
|
|
let OperandType = "OPERAND_MEMORY";
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SSE pattern fragments
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// 128-bit load pattern fragments
|
|
// NOTE: all 128-bit integer vector loads are promoted to v2i64
|
|
def loadv4f32 : PatFrag<(ops node:$ptr), (v4f32 (load node:$ptr))>;
|
|
def loadv2f64 : PatFrag<(ops node:$ptr), (v2f64 (load node:$ptr))>;
|
|
def loadv2i64 : PatFrag<(ops node:$ptr), (v2i64 (load node:$ptr))>;
|
|
|
|
// 256-bit load pattern fragments
|
|
// NOTE: all 256-bit integer vector loads are promoted to v4i64
|
|
def loadv8f32 : PatFrag<(ops node:$ptr), (v8f32 (load node:$ptr))>;
|
|
def loadv4f64 : PatFrag<(ops node:$ptr), (v4f64 (load node:$ptr))>;
|
|
def loadv4i64 : PatFrag<(ops node:$ptr), (v4i64 (load node:$ptr))>;
|
|
|
|
// 512-bit load pattern fragments
|
|
def loadv16f32 : PatFrag<(ops node:$ptr), (v16f32 (load node:$ptr))>;
|
|
def loadv8f64 : PatFrag<(ops node:$ptr), (v8f64 (load node:$ptr))>;
|
|
def loadv8i64 : PatFrag<(ops node:$ptr), (v8i64 (load node:$ptr))>;
|
|
|
|
// 128-/256-/512-bit extload pattern fragments
|
|
def extloadv2f32 : PatFrag<(ops node:$ptr), (v2f64 (extloadvf32 node:$ptr))>;
|
|
def extloadv4f32 : PatFrag<(ops node:$ptr), (v4f64 (extloadvf32 node:$ptr))>;
|
|
def extloadv8f32 : PatFrag<(ops node:$ptr), (v8f64 (extloadvf32 node:$ptr))>;
|
|
|
|
// Like 'store', but always requires 128-bit vector alignment.
|
|
def alignedstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() >= 16;
|
|
}]>;
|
|
|
|
// Like 'store', but always requires 256-bit vector alignment.
|
|
def alignedstore256 : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() >= 32;
|
|
}]>;
|
|
|
|
// Like 'store', but always requires 512-bit vector alignment.
|
|
def alignedstore512 : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() >= 64;
|
|
}]>;
|
|
|
|
// Like 'load', but always requires 128-bit vector alignment.
|
|
def alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() >= 16;
|
|
}]>;
|
|
|
|
// Like 'X86vzload', but always requires 128-bit vector alignment.
|
|
def alignedX86vzload : PatFrag<(ops node:$ptr), (X86vzload node:$ptr), [{
|
|
return cast<MemSDNode>(N)->getAlignment() >= 16;
|
|
}]>;
|
|
|
|
// Like 'load', but always requires 256-bit vector alignment.
|
|
def alignedload256 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() >= 32;
|
|
}]>;
|
|
|
|
// Like 'load', but always requires 512-bit vector alignment.
|
|
def alignedload512 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() >= 64;
|
|
}]>;
|
|
|
|
def alignedloadfsf32 : PatFrag<(ops node:$ptr),
|
|
(f32 (alignedload node:$ptr))>;
|
|
def alignedloadfsf64 : PatFrag<(ops node:$ptr),
|
|
(f64 (alignedload node:$ptr))>;
|
|
|
|
// 128-bit aligned load pattern fragments
|
|
// NOTE: all 128-bit integer vector loads are promoted to v2i64
|
|
def alignedloadv4f32 : PatFrag<(ops node:$ptr),
|
|
(v4f32 (alignedload node:$ptr))>;
|
|
def alignedloadv2f64 : PatFrag<(ops node:$ptr),
|
|
(v2f64 (alignedload node:$ptr))>;
|
|
def alignedloadv2i64 : PatFrag<(ops node:$ptr),
|
|
(v2i64 (alignedload node:$ptr))>;
|
|
|
|
// 256-bit aligned load pattern fragments
|
|
// NOTE: all 256-bit integer vector loads are promoted to v4i64
|
|
def alignedloadv8f32 : PatFrag<(ops node:$ptr),
|
|
(v8f32 (alignedload256 node:$ptr))>;
|
|
def alignedloadv4f64 : PatFrag<(ops node:$ptr),
|
|
(v4f64 (alignedload256 node:$ptr))>;
|
|
def alignedloadv4i64 : PatFrag<(ops node:$ptr),
|
|
(v4i64 (alignedload256 node:$ptr))>;
|
|
|
|
// 512-bit aligned load pattern fragments
|
|
def alignedloadv16f32 : PatFrag<(ops node:$ptr),
|
|
(v16f32 (alignedload512 node:$ptr))>;
|
|
def alignedloadv16i32 : PatFrag<(ops node:$ptr),
|
|
(v16i32 (alignedload512 node:$ptr))>;
|
|
def alignedloadv8f64 : PatFrag<(ops node:$ptr),
|
|
(v8f64 (alignedload512 node:$ptr))>;
|
|
def alignedloadv8i64 : PatFrag<(ops node:$ptr),
|
|
(v8i64 (alignedload512 node:$ptr))>;
|
|
|
|
// Like 'load', but uses special alignment checks suitable for use in
|
|
// memory operands in most SSE instructions, which are required to
|
|
// be naturally aligned on some targets but not on others. If the subtarget
|
|
// allows unaligned accesses, match any load, though this may require
|
|
// setting a feature bit in the processor (on startup, for example).
|
|
// Opteron 10h and later implement such a feature.
|
|
def memop : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return Subtarget->hasVectorUAMem()
|
|
|| cast<LoadSDNode>(N)->getAlignment() >= 16;
|
|
}]>;
|
|
|
|
def memop4 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return Subtarget->hasVectorUAMem()
|
|
|| cast<LoadSDNode>(N)->getAlignment() >= 4;
|
|
}]>;
|
|
|
|
def memop8 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return Subtarget->hasVectorUAMem()
|
|
|| cast<LoadSDNode>(N)->getAlignment() >= 8;
|
|
}]>;
|
|
|
|
def memopfsf32 : PatFrag<(ops node:$ptr), (f32 (memop node:$ptr))>;
|
|
def memopfsf64 : PatFrag<(ops node:$ptr), (f64 (memop node:$ptr))>;
|
|
|
|
// 128-bit memop pattern fragments
|
|
// NOTE: all 128-bit integer vector loads are promoted to v2i64
|
|
def memopv4f32 : PatFrag<(ops node:$ptr), (v4f32 (memop node:$ptr))>;
|
|
def memopv2f64 : PatFrag<(ops node:$ptr), (v2f64 (memop node:$ptr))>;
|
|
def memopv2i64 : PatFrag<(ops node:$ptr), (v2i64 (memop node:$ptr))>;
|
|
|
|
// 256-bit memop pattern fragments
|
|
// NOTE: all 256-bit integer vector loads are promoted to v4i64
|
|
def memopv8f32 : PatFrag<(ops node:$ptr), (v8f32 (memop node:$ptr))>;
|
|
def memopv4f64 : PatFrag<(ops node:$ptr), (v4f64 (memop node:$ptr))>;
|
|
def memopv4i64 : PatFrag<(ops node:$ptr), (v4i64 (memop node:$ptr))>;
|
|
|
|
// 512-bit memop pattern fragments
|
|
def memopv16f32 : PatFrag<(ops node:$ptr), (v16f32 (memop4 node:$ptr))>;
|
|
def memopv8f64 : PatFrag<(ops node:$ptr), (v8f64 (memop8 node:$ptr))>;
|
|
def memopv16i32 : PatFrag<(ops node:$ptr), (v16i32 (memop4 node:$ptr))>;
|
|
def memopv8i64 : PatFrag<(ops node:$ptr), (v8i64 (memop8 node:$ptr))>;
|
|
|
|
// SSSE3 uses MMX registers for some instructions. They aren't aligned on a
|
|
// 16-byte boundary.
|
|
// FIXME: 8 byte alignment for mmx reads is not required
|
|
def memop64 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() >= 8;
|
|
}]>;
|
|
|
|
def memopmmx : PatFrag<(ops node:$ptr), (x86mmx (memop64 node:$ptr))>;
|
|
|
|
// MOVNT Support
|
|
// Like 'store', but requires the non-temporal bit to be set
|
|
def nontemporalstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(st node:$val, node:$ptr), [{
|
|
if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
|
|
return ST->isNonTemporal();
|
|
return false;
|
|
}]>;
|
|
|
|
def alignednontemporalstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(st node:$val, node:$ptr), [{
|
|
if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
|
|
return ST->isNonTemporal() && !ST->isTruncatingStore() &&
|
|
ST->getAddressingMode() == ISD::UNINDEXED &&
|
|
ST->getAlignment() >= 16;
|
|
return false;
|
|
}]>;
|
|
|
|
def unalignednontemporalstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(st node:$val, node:$ptr), [{
|
|
if (StoreSDNode *ST = dyn_cast<StoreSDNode>(N))
|
|
return ST->isNonTemporal() &&
|
|
ST->getAlignment() < 16;
|
|
return false;
|
|
}]>;
|
|
|
|
// 128-bit bitconvert pattern fragments
|
|
def bc_v4f32 : PatFrag<(ops node:$in), (v4f32 (bitconvert node:$in))>;
|
|
def bc_v2f64 : PatFrag<(ops node:$in), (v2f64 (bitconvert node:$in))>;
|
|
def bc_v16i8 : PatFrag<(ops node:$in), (v16i8 (bitconvert node:$in))>;
|
|
def bc_v8i16 : PatFrag<(ops node:$in), (v8i16 (bitconvert node:$in))>;
|
|
def bc_v4i32 : PatFrag<(ops node:$in), (v4i32 (bitconvert node:$in))>;
|
|
def bc_v2i64 : PatFrag<(ops node:$in), (v2i64 (bitconvert node:$in))>;
|
|
|
|
// 256-bit bitconvert pattern fragments
|
|
def bc_v32i8 : PatFrag<(ops node:$in), (v32i8 (bitconvert node:$in))>;
|
|
def bc_v16i16 : PatFrag<(ops node:$in), (v16i16 (bitconvert node:$in))>;
|
|
def bc_v8i32 : PatFrag<(ops node:$in), (v8i32 (bitconvert node:$in))>;
|
|
def bc_v4i64 : PatFrag<(ops node:$in), (v4i64 (bitconvert node:$in))>;
|
|
|
|
// 512-bit bitconvert pattern fragments
|
|
def bc_v16i32 : PatFrag<(ops node:$in), (v16i32 (bitconvert node:$in))>;
|
|
def bc_v8i64 : PatFrag<(ops node:$in), (v8i64 (bitconvert node:$in))>;
|
|
|
|
def vzmovl_v2i64 : PatFrag<(ops node:$src),
|
|
(bitconvert (v2i64 (X86vzmovl
|
|
(v2i64 (scalar_to_vector (loadi64 node:$src))))))>;
|
|
def vzmovl_v4i32 : PatFrag<(ops node:$src),
|
|
(bitconvert (v4i32 (X86vzmovl
|
|
(v4i32 (scalar_to_vector (loadi32 node:$src))))))>;
|
|
|
|
def vzload_v2i64 : PatFrag<(ops node:$src),
|
|
(bitconvert (v2i64 (X86vzload node:$src)))>;
|
|
|
|
|
|
def fp32imm0 : PatLeaf<(f32 fpimm), [{
|
|
return N->isExactlyValue(+0.0);
|
|
}]>;
|
|
|
|
// BYTE_imm - Transform bit immediates into byte immediates.
|
|
def BYTE_imm : SDNodeXForm<imm, [{
|
|
// Transformation function: imm >> 3
|
|
return getI32Imm(N->getZExtValue() >> 3);
|
|
}]>;
|
|
|
|
// EXTRACT_get_vextract128_imm xform function: convert extract_subvector index
|
|
// to VEXTRACTF128/VEXTRACTI128 imm.
|
|
def EXTRACT_get_vextract128_imm : SDNodeXForm<extract_subvector, [{
|
|
return getI8Imm(X86::getExtractVEXTRACT128Immediate(N));
|
|
}]>;
|
|
|
|
// INSERT_get_vinsert128_imm xform function: convert insert_subvector index to
|
|
// VINSERTF128/VINSERTI128 imm.
|
|
def INSERT_get_vinsert128_imm : SDNodeXForm<insert_subvector, [{
|
|
return getI8Imm(X86::getInsertVINSERT128Immediate(N));
|
|
}]>;
|
|
|
|
// EXTRACT_get_vextract256_imm xform function: convert extract_subvector index
|
|
// to VEXTRACTF64x4 imm.
|
|
def EXTRACT_get_vextract256_imm : SDNodeXForm<extract_subvector, [{
|
|
return getI8Imm(X86::getExtractVEXTRACT256Immediate(N));
|
|
}]>;
|
|
|
|
// INSERT_get_vinsert256_imm xform function: convert insert_subvector index to
|
|
// VINSERTF64x4 imm.
|
|
def INSERT_get_vinsert256_imm : SDNodeXForm<insert_subvector, [{
|
|
return getI8Imm(X86::getInsertVINSERT256Immediate(N));
|
|
}]>;
|
|
|
|
def vextract128_extract : PatFrag<(ops node:$bigvec, node:$index),
|
|
(extract_subvector node:$bigvec,
|
|
node:$index), [{
|
|
return X86::isVEXTRACT128Index(N);
|
|
}], EXTRACT_get_vextract128_imm>;
|
|
|
|
def vinsert128_insert : PatFrag<(ops node:$bigvec, node:$smallvec,
|
|
node:$index),
|
|
(insert_subvector node:$bigvec, node:$smallvec,
|
|
node:$index), [{
|
|
return X86::isVINSERT128Index(N);
|
|
}], INSERT_get_vinsert128_imm>;
|
|
|
|
|
|
def vextract256_extract : PatFrag<(ops node:$bigvec, node:$index),
|
|
(extract_subvector node:$bigvec,
|
|
node:$index), [{
|
|
return X86::isVEXTRACT256Index(N);
|
|
}], EXTRACT_get_vextract256_imm>;
|
|
|
|
def vinsert256_insert : PatFrag<(ops node:$bigvec, node:$smallvec,
|
|
node:$index),
|
|
(insert_subvector node:$bigvec, node:$smallvec,
|
|
node:$index), [{
|
|
return X86::isVINSERT256Index(N);
|
|
}], INSERT_get_vinsert256_imm>;
|
|
|