forked from OSchip/llvm-project
8629 lines
414 KiB
TableGen
8629 lines
414 KiB
TableGen
//===-- ARMInstrNEON.td - NEON support for ARM -------------*- 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 ARM NEON instruction set.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// NEON-specific Operands.
|
|
//===----------------------------------------------------------------------===//
|
|
def nModImm : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
}
|
|
|
|
def nImmSplatI8AsmOperand : AsmOperandClass { let Name = "NEONi8splat"; }
|
|
def nImmSplatI8 : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmSplatI8AsmOperand;
|
|
}
|
|
def nImmSplatI16AsmOperand : AsmOperandClass { let Name = "NEONi16splat"; }
|
|
def nImmSplatI16 : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmSplatI16AsmOperand;
|
|
}
|
|
def nImmSplatI32AsmOperand : AsmOperandClass { let Name = "NEONi32splat"; }
|
|
def nImmSplatI32 : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmSplatI32AsmOperand;
|
|
}
|
|
def nImmSplatNotI16AsmOperand : AsmOperandClass { let Name = "NEONi16splatNot"; }
|
|
def nImmSplatNotI16 : Operand<i32> {
|
|
let ParserMatchClass = nImmSplatNotI16AsmOperand;
|
|
}
|
|
def nImmSplatNotI32AsmOperand : AsmOperandClass { let Name = "NEONi32splatNot"; }
|
|
def nImmSplatNotI32 : Operand<i32> {
|
|
let ParserMatchClass = nImmSplatNotI32AsmOperand;
|
|
}
|
|
def nImmVMOVI32AsmOperand : AsmOperandClass { let Name = "NEONi32vmov"; }
|
|
def nImmVMOVI32 : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmVMOVI32AsmOperand;
|
|
}
|
|
|
|
class nImmVMOVIAsmOperandReplicate<ValueType From, ValueType To>
|
|
: AsmOperandClass {
|
|
let Name = "NEONi" # To.Size # "vmovi" # From.Size # "Replicate";
|
|
let PredicateMethod = "isNEONmovReplicate<" # From.Size # ", " # To.Size # ">";
|
|
let RenderMethod = "addNEONvmovi" # From.Size # "ReplicateOperands";
|
|
}
|
|
|
|
class nImmVINVIAsmOperandReplicate<ValueType From, ValueType To>
|
|
: AsmOperandClass {
|
|
let Name = "NEONi" # To.Size # "invi" # From.Size # "Replicate";
|
|
let PredicateMethod = "isNEONinvReplicate<" # From.Size # ", " # To.Size # ">";
|
|
let RenderMethod = "addNEONinvi" # From.Size # "ReplicateOperands";
|
|
}
|
|
|
|
class nImmVMOVIReplicate<ValueType From, ValueType To> : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmVMOVIAsmOperandReplicate<From, To>;
|
|
}
|
|
|
|
class nImmVINVIReplicate<ValueType From, ValueType To> : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmVINVIAsmOperandReplicate<From, To>;
|
|
}
|
|
|
|
def nImmVMOVI32NegAsmOperand : AsmOperandClass { let Name = "NEONi32vmovNeg"; }
|
|
def nImmVMOVI32Neg : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmVMOVI32NegAsmOperand;
|
|
}
|
|
def nImmVMOVF32 : Operand<i32> {
|
|
let PrintMethod = "printFPImmOperand";
|
|
let ParserMatchClass = FPImmOperand;
|
|
}
|
|
def nImmSplatI64AsmOperand : AsmOperandClass { let Name = "NEONi64splat"; }
|
|
def nImmSplatI64 : Operand<i32> {
|
|
let PrintMethod = "printNEONModImmOperand";
|
|
let ParserMatchClass = nImmSplatI64AsmOperand;
|
|
}
|
|
|
|
def VectorIndex8Operand : AsmOperandClass { let Name = "VectorIndex8"; }
|
|
def VectorIndex16Operand : AsmOperandClass { let Name = "VectorIndex16"; }
|
|
def VectorIndex32Operand : AsmOperandClass { let Name = "VectorIndex32"; }
|
|
def VectorIndex64Operand : AsmOperandClass { let Name = "VectorIndex64"; }
|
|
def VectorIndex8 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint64_t)Imm) < 8;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndex8Operand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i32imm);
|
|
}
|
|
def VectorIndex16 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint64_t)Imm) < 4;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndex16Operand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i32imm);
|
|
}
|
|
def VectorIndex32 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint64_t)Imm) < 2;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndex32Operand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i32imm);
|
|
}
|
|
def VectorIndex64 : Operand<i32>, ImmLeaf<i32, [{
|
|
return ((uint64_t)Imm) < 1;
|
|
}]> {
|
|
let ParserMatchClass = VectorIndex64Operand;
|
|
let PrintMethod = "printVectorIndex";
|
|
let MIOperandInfo = (ops i32imm);
|
|
}
|
|
|
|
// Register list of one D register.
|
|
def VecListOneDAsmOperand : AsmOperandClass {
|
|
let Name = "VecListOneD";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListOneD : RegisterOperand<DPR, "printVectorListOne"> {
|
|
let ParserMatchClass = VecListOneDAsmOperand;
|
|
}
|
|
// Register list of two sequential D registers.
|
|
def VecListDPairAsmOperand : AsmOperandClass {
|
|
let Name = "VecListDPair";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListDPair : RegisterOperand<DPair, "printVectorListTwo"> {
|
|
let ParserMatchClass = VecListDPairAsmOperand;
|
|
}
|
|
// Register list of three sequential D registers.
|
|
def VecListThreeDAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeD";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListThreeD : RegisterOperand<DPR, "printVectorListThree"> {
|
|
let ParserMatchClass = VecListThreeDAsmOperand;
|
|
}
|
|
// Register list of four sequential D registers.
|
|
def VecListFourDAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourD";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListFourD : RegisterOperand<DPR, "printVectorListFour"> {
|
|
let ParserMatchClass = VecListFourDAsmOperand;
|
|
}
|
|
// Register list of two D registers spaced by 2 (two sequential Q registers).
|
|
def VecListDPairSpacedAsmOperand : AsmOperandClass {
|
|
let Name = "VecListDPairSpaced";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListDPairSpaced : RegisterOperand<DPair, "printVectorListTwoSpaced"> {
|
|
let ParserMatchClass = VecListDPairSpacedAsmOperand;
|
|
}
|
|
// Register list of three D registers spaced by 2 (three Q registers).
|
|
def VecListThreeQAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeQ";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListThreeQ : RegisterOperand<DPR, "printVectorListThreeSpaced"> {
|
|
let ParserMatchClass = VecListThreeQAsmOperand;
|
|
}
|
|
// Register list of three D registers spaced by 2 (three Q registers).
|
|
def VecListFourQAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourQ";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListFourQ : RegisterOperand<DPR, "printVectorListFourSpaced"> {
|
|
let ParserMatchClass = VecListFourQAsmOperand;
|
|
}
|
|
|
|
// Register list of one D register, with "all lanes" subscripting.
|
|
def VecListOneDAllLanesAsmOperand : AsmOperandClass {
|
|
let Name = "VecListOneDAllLanes";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListOneDAllLanes : RegisterOperand<DPR, "printVectorListOneAllLanes"> {
|
|
let ParserMatchClass = VecListOneDAllLanesAsmOperand;
|
|
}
|
|
// Register list of two D registers, with "all lanes" subscripting.
|
|
def VecListDPairAllLanesAsmOperand : AsmOperandClass {
|
|
let Name = "VecListDPairAllLanes";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListDPairAllLanes : RegisterOperand<DPair,
|
|
"printVectorListTwoAllLanes"> {
|
|
let ParserMatchClass = VecListDPairAllLanesAsmOperand;
|
|
}
|
|
// Register list of two D registers spaced by 2 (two sequential Q registers).
|
|
def VecListDPairSpacedAllLanesAsmOperand : AsmOperandClass {
|
|
let Name = "VecListDPairSpacedAllLanes";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListDPairSpacedAllLanes : RegisterOperand<DPairSpc,
|
|
"printVectorListTwoSpacedAllLanes"> {
|
|
let ParserMatchClass = VecListDPairSpacedAllLanesAsmOperand;
|
|
}
|
|
// Register list of three D registers, with "all lanes" subscripting.
|
|
def VecListThreeDAllLanesAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeDAllLanes";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListThreeDAllLanes : RegisterOperand<DPR,
|
|
"printVectorListThreeAllLanes"> {
|
|
let ParserMatchClass = VecListThreeDAllLanesAsmOperand;
|
|
}
|
|
// Register list of three D registers spaced by 2 (three sequential Q regs).
|
|
def VecListThreeQAllLanesAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeQAllLanes";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListThreeQAllLanes : RegisterOperand<DPR,
|
|
"printVectorListThreeSpacedAllLanes"> {
|
|
let ParserMatchClass = VecListThreeQAllLanesAsmOperand;
|
|
}
|
|
// Register list of four D registers, with "all lanes" subscripting.
|
|
def VecListFourDAllLanesAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourDAllLanes";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListFourDAllLanes : RegisterOperand<DPR, "printVectorListFourAllLanes"> {
|
|
let ParserMatchClass = VecListFourDAllLanesAsmOperand;
|
|
}
|
|
// Register list of four D registers spaced by 2 (four sequential Q regs).
|
|
def VecListFourQAllLanesAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourQAllLanes";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListOperands";
|
|
}
|
|
def VecListFourQAllLanes : RegisterOperand<DPR,
|
|
"printVectorListFourSpacedAllLanes"> {
|
|
let ParserMatchClass = VecListFourQAllLanesAsmOperand;
|
|
}
|
|
|
|
|
|
// Register list of one D register, with byte lane subscripting.
|
|
def VecListOneDByteIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListOneDByteIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListOneDByteIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListOneDByteIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with half-word lane subscripting.
|
|
def VecListOneDHWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListOneDHWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListOneDHWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListOneDHWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with word lane subscripting.
|
|
def VecListOneDWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListOneDWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListOneDWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListOneDWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
|
|
// Register list of two D registers with byte lane subscripting.
|
|
def VecListTwoDByteIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListTwoDByteIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListTwoDByteIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListTwoDByteIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with half-word lane subscripting.
|
|
def VecListTwoDHWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListTwoDHWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListTwoDHWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListTwoDHWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with word lane subscripting.
|
|
def VecListTwoDWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListTwoDWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListTwoDWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListTwoDWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// Register list of two Q registers with half-word lane subscripting.
|
|
def VecListTwoQHWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListTwoQHWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListTwoQHWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListTwoQHWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with word lane subscripting.
|
|
def VecListTwoQWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListTwoQWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListTwoQWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListTwoQWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
|
|
|
|
// Register list of three D registers with byte lane subscripting.
|
|
def VecListThreeDByteIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeDByteIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListThreeDByteIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListThreeDByteIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with half-word lane subscripting.
|
|
def VecListThreeDHWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeDHWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListThreeDHWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListThreeDHWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with word lane subscripting.
|
|
def VecListThreeDWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeDWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListThreeDWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListThreeDWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// Register list of three Q registers with half-word lane subscripting.
|
|
def VecListThreeQHWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeQHWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListThreeQHWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListThreeQHWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with word lane subscripting.
|
|
def VecListThreeQWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListThreeQWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListThreeQWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListThreeQWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
|
|
// Register list of four D registers with byte lane subscripting.
|
|
def VecListFourDByteIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourDByteIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListFourDByteIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListFourDByteIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with half-word lane subscripting.
|
|
def VecListFourDHWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourDHWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListFourDHWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListFourDHWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with word lane subscripting.
|
|
def VecListFourDWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourDWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListFourDWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListFourDWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// Register list of four Q registers with half-word lane subscripting.
|
|
def VecListFourQHWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourQHWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListFourQHWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListFourQHWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
// ...with word lane subscripting.
|
|
def VecListFourQWordIndexAsmOperand : AsmOperandClass {
|
|
let Name = "VecListFourQWordIndexed";
|
|
let ParserMethod = "parseVectorList";
|
|
let RenderMethod = "addVecListIndexedOperands";
|
|
}
|
|
def VecListFourQWordIndexed : Operand<i32> {
|
|
let ParserMatchClass = VecListFourQWordIndexAsmOperand;
|
|
let MIOperandInfo = (ops DPR:$Vd, i32imm:$idx);
|
|
}
|
|
|
|
def dword_alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() >= 8;
|
|
}]>;
|
|
def dword_alignedstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() >= 8;
|
|
}]>;
|
|
def word_alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() == 4;
|
|
}]>;
|
|
def word_alignedstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() == 4;
|
|
}]>;
|
|
def hword_alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() == 2;
|
|
}]>;
|
|
def hword_alignedstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() == 2;
|
|
}]>;
|
|
def byte_alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() == 1;
|
|
}]>;
|
|
def byte_alignedstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() == 1;
|
|
}]>;
|
|
def non_word_alignedload : PatFrag<(ops node:$ptr), (load node:$ptr), [{
|
|
return cast<LoadSDNode>(N)->getAlignment() < 4;
|
|
}]>;
|
|
def non_word_alignedstore : PatFrag<(ops node:$val, node:$ptr),
|
|
(store node:$val, node:$ptr), [{
|
|
return cast<StoreSDNode>(N)->getAlignment() < 4;
|
|
}]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// NEON-specific DAG Nodes.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def SDTARMVCMP : SDTypeProfile<1, 2, [SDTCisInt<0>, SDTCisSameAs<1, 2>]>;
|
|
def SDTARMVCMPZ : SDTypeProfile<1, 1, []>;
|
|
|
|
def NEONvceq : SDNode<"ARMISD::VCEQ", SDTARMVCMP>;
|
|
def NEONvceqz : SDNode<"ARMISD::VCEQZ", SDTARMVCMPZ>;
|
|
def NEONvcge : SDNode<"ARMISD::VCGE", SDTARMVCMP>;
|
|
def NEONvcgez : SDNode<"ARMISD::VCGEZ", SDTARMVCMPZ>;
|
|
def NEONvclez : SDNode<"ARMISD::VCLEZ", SDTARMVCMPZ>;
|
|
def NEONvcgeu : SDNode<"ARMISD::VCGEU", SDTARMVCMP>;
|
|
def NEONvcgt : SDNode<"ARMISD::VCGT", SDTARMVCMP>;
|
|
def NEONvcgtz : SDNode<"ARMISD::VCGTZ", SDTARMVCMPZ>;
|
|
def NEONvcltz : SDNode<"ARMISD::VCLTZ", SDTARMVCMPZ>;
|
|
def NEONvcgtu : SDNode<"ARMISD::VCGTU", SDTARMVCMP>;
|
|
def NEONvtst : SDNode<"ARMISD::VTST", SDTARMVCMP>;
|
|
|
|
// Types for vector shift by immediates. The "SHX" version is for long and
|
|
// narrow operations where the source and destination vectors have different
|
|
// types. The "SHINS" version is for shift and insert operations.
|
|
def SDTARMVSH : SDTypeProfile<1, 2, [SDTCisInt<0>, SDTCisSameAs<0, 1>,
|
|
SDTCisVT<2, i32>]>;
|
|
def SDTARMVSHX : SDTypeProfile<1, 2, [SDTCisInt<0>, SDTCisInt<1>,
|
|
SDTCisVT<2, i32>]>;
|
|
def SDTARMVSHINS : SDTypeProfile<1, 3, [SDTCisInt<0>, SDTCisSameAs<0, 1>,
|
|
SDTCisSameAs<0, 2>, SDTCisVT<3, i32>]>;
|
|
|
|
def NEONvshl : SDNode<"ARMISD::VSHL", SDTARMVSH>;
|
|
def NEONvshrs : SDNode<"ARMISD::VSHRs", SDTARMVSH>;
|
|
def NEONvshru : SDNode<"ARMISD::VSHRu", SDTARMVSH>;
|
|
def NEONvshrn : SDNode<"ARMISD::VSHRN", SDTARMVSHX>;
|
|
|
|
def NEONvrshrs : SDNode<"ARMISD::VRSHRs", SDTARMVSH>;
|
|
def NEONvrshru : SDNode<"ARMISD::VRSHRu", SDTARMVSH>;
|
|
def NEONvrshrn : SDNode<"ARMISD::VRSHRN", SDTARMVSHX>;
|
|
|
|
def NEONvqshls : SDNode<"ARMISD::VQSHLs", SDTARMVSH>;
|
|
def NEONvqshlu : SDNode<"ARMISD::VQSHLu", SDTARMVSH>;
|
|
def NEONvqshlsu : SDNode<"ARMISD::VQSHLsu", SDTARMVSH>;
|
|
def NEONvqshrns : SDNode<"ARMISD::VQSHRNs", SDTARMVSHX>;
|
|
def NEONvqshrnu : SDNode<"ARMISD::VQSHRNu", SDTARMVSHX>;
|
|
def NEONvqshrnsu : SDNode<"ARMISD::VQSHRNsu", SDTARMVSHX>;
|
|
|
|
def NEONvqrshrns : SDNode<"ARMISD::VQRSHRNs", SDTARMVSHX>;
|
|
def NEONvqrshrnu : SDNode<"ARMISD::VQRSHRNu", SDTARMVSHX>;
|
|
def NEONvqrshrnsu : SDNode<"ARMISD::VQRSHRNsu", SDTARMVSHX>;
|
|
|
|
def NEONvsli : SDNode<"ARMISD::VSLI", SDTARMVSHINS>;
|
|
def NEONvsri : SDNode<"ARMISD::VSRI", SDTARMVSHINS>;
|
|
|
|
def SDTARMVGETLN : SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisInt<1>,
|
|
SDTCisVT<2, i32>]>;
|
|
def NEONvgetlaneu : SDNode<"ARMISD::VGETLANEu", SDTARMVGETLN>;
|
|
def NEONvgetlanes : SDNode<"ARMISD::VGETLANEs", SDTARMVGETLN>;
|
|
|
|
def SDTARMVMOVIMM : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisVT<1, i32>]>;
|
|
def NEONvmovImm : SDNode<"ARMISD::VMOVIMM", SDTARMVMOVIMM>;
|
|
def NEONvmvnImm : SDNode<"ARMISD::VMVNIMM", SDTARMVMOVIMM>;
|
|
def NEONvmovFPImm : SDNode<"ARMISD::VMOVFPIMM", SDTARMVMOVIMM>;
|
|
|
|
def SDTARMVORRIMM : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0, 1>,
|
|
SDTCisVT<2, i32>]>;
|
|
def NEONvorrImm : SDNode<"ARMISD::VORRIMM", SDTARMVORRIMM>;
|
|
def NEONvbicImm : SDNode<"ARMISD::VBICIMM", SDTARMVORRIMM>;
|
|
|
|
def NEONvbsl : SDNode<"ARMISD::VBSL",
|
|
SDTypeProfile<1, 3, [SDTCisVec<0>,
|
|
SDTCisSameAs<0, 1>,
|
|
SDTCisSameAs<0, 2>,
|
|
SDTCisSameAs<0, 3>]>>;
|
|
|
|
def NEONvdup : SDNode<"ARMISD::VDUP", SDTypeProfile<1, 1, [SDTCisVec<0>]>>;
|
|
|
|
// VDUPLANE can produce a quad-register result from a double-register source,
|
|
// so the result is not constrained to match the source.
|
|
def NEONvduplane : SDNode<"ARMISD::VDUPLANE",
|
|
SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisVec<1>,
|
|
SDTCisVT<2, i32>]>>;
|
|
|
|
def SDTARMVEXT : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0, 1>,
|
|
SDTCisSameAs<0, 2>, SDTCisVT<3, i32>]>;
|
|
def NEONvext : SDNode<"ARMISD::VEXT", SDTARMVEXT>;
|
|
|
|
def SDTARMVSHUF : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0, 1>]>;
|
|
def NEONvrev64 : SDNode<"ARMISD::VREV64", SDTARMVSHUF>;
|
|
def NEONvrev32 : SDNode<"ARMISD::VREV32", SDTARMVSHUF>;
|
|
def NEONvrev16 : SDNode<"ARMISD::VREV16", SDTARMVSHUF>;
|
|
|
|
def SDTARMVSHUF2 : SDTypeProfile<2, 2, [SDTCisVec<0>, SDTCisSameAs<0, 1>,
|
|
SDTCisSameAs<0, 2>,
|
|
SDTCisSameAs<0, 3>]>;
|
|
def NEONzip : SDNode<"ARMISD::VZIP", SDTARMVSHUF2>;
|
|
def NEONuzp : SDNode<"ARMISD::VUZP", SDTARMVSHUF2>;
|
|
def NEONtrn : SDNode<"ARMISD::VTRN", SDTARMVSHUF2>;
|
|
|
|
def SDTARMVMULL : SDTypeProfile<1, 2, [SDTCisInt<0>, SDTCisInt<1>,
|
|
SDTCisSameAs<1, 2>]>;
|
|
def NEONvmulls : SDNode<"ARMISD::VMULLs", SDTARMVMULL>;
|
|
def NEONvmullu : SDNode<"ARMISD::VMULLu", SDTARMVMULL>;
|
|
|
|
def SDTARMVTBL1 : SDTypeProfile<1, 2, [SDTCisVT<0, v8i8>, SDTCisVT<1, v8i8>,
|
|
SDTCisVT<2, v8i8>]>;
|
|
def SDTARMVTBL2 : SDTypeProfile<1, 3, [SDTCisVT<0, v8i8>, SDTCisVT<1, v8i8>,
|
|
SDTCisVT<2, v8i8>, SDTCisVT<3, v8i8>]>;
|
|
def NEONvtbl1 : SDNode<"ARMISD::VTBL1", SDTARMVTBL1>;
|
|
def NEONvtbl2 : SDNode<"ARMISD::VTBL2", SDTARMVTBL2>;
|
|
|
|
|
|
def NEONimmAllZerosV: PatLeaf<(NEONvmovImm (i32 timm)), [{
|
|
ConstantSDNode *ConstVal = cast<ConstantSDNode>(N->getOperand(0));
|
|
unsigned EltBits = 0;
|
|
uint64_t EltVal = ARM_AM::decodeNEONModImm(ConstVal->getZExtValue(), EltBits);
|
|
return (EltBits == 32 && EltVal == 0);
|
|
}]>;
|
|
|
|
def NEONimmAllOnesV: PatLeaf<(NEONvmovImm (i32 timm)), [{
|
|
ConstantSDNode *ConstVal = cast<ConstantSDNode>(N->getOperand(0));
|
|
unsigned EltBits = 0;
|
|
uint64_t EltVal = ARM_AM::decodeNEONModImm(ConstVal->getZExtValue(), EltBits);
|
|
return (EltBits == 8 && EltVal == 0xff);
|
|
}]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// NEON load / store instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Use VLDM to load a Q register as a D register pair.
|
|
// This is a pseudo instruction that is expanded to VLDMD after reg alloc.
|
|
def VLDMQIA
|
|
: PseudoVFPLdStM<(outs DPair:$dst), (ins GPR:$Rn),
|
|
IIC_fpLoad_m, "",
|
|
[(set DPair:$dst, (v2f64 (word_alignedload GPR:$Rn)))]>;
|
|
|
|
// Use VSTM to store a Q register as a D register pair.
|
|
// This is a pseudo instruction that is expanded to VSTMD after reg alloc.
|
|
def VSTMQIA
|
|
: PseudoVFPLdStM<(outs), (ins DPair:$src, GPR:$Rn),
|
|
IIC_fpStore_m, "",
|
|
[(word_alignedstore (v2f64 DPair:$src), GPR:$Rn)]>;
|
|
|
|
// Classes for VLD* pseudo-instructions with multi-register operands.
|
|
// These are expanded to real instructions after register allocation.
|
|
class VLDQPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QPR:$dst), (ins addrmode6:$addr), itin, "">;
|
|
class VLDQWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset), itin,
|
|
"$addr.addr = $wb">;
|
|
class VLDQWBfixedPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr), itin,
|
|
"$addr.addr = $wb">;
|
|
class VLDQWBregisterPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, rGPR:$offset), itin,
|
|
"$addr.addr = $wb">;
|
|
|
|
class VLDQQPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQPR:$dst), (ins addrmode6:$addr), itin, "">;
|
|
class VLDQQWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset), itin,
|
|
"$addr.addr = $wb">;
|
|
class VLDQQWBfixedPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr), itin,
|
|
"$addr.addr = $wb">;
|
|
class VLDQQWBregisterPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, rGPR:$offset), itin,
|
|
"$addr.addr = $wb">;
|
|
|
|
|
|
class VLDQQQQPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQQQPR:$dst), (ins addrmode6:$addr, QQQQPR:$src),itin,
|
|
"$src = $dst">;
|
|
class VLDQQQQWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQQQPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QQQQPR:$src), itin,
|
|
"$addr.addr = $wb, $src = $dst">;
|
|
|
|
let mayLoad = 1, hasSideEffects = 0, hasExtraDefRegAllocReq = 1 in {
|
|
|
|
// VLD1 : Vector Load (multiple single elements)
|
|
class VLD1D<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0,0b10,0b0111,op7_4, (outs VecListOneD:$Vd),
|
|
(ins AddrMode:$Rn), IIC_VLD1,
|
|
"vld1", Dt, "$Vd, $Rn", "", []>, Sched<[WriteVLD1]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
class VLD1Q<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0,0b10,0b1010,op7_4, (outs VecListDPair:$Vd),
|
|
(ins AddrMode:$Rn), IIC_VLD1x2,
|
|
"vld1", Dt, "$Vd, $Rn", "", []>, Sched<[WriteVLD2]> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
|
|
def VLD1d8 : VLD1D<{0,0,0,?}, "8", addrmode6align64>;
|
|
def VLD1d16 : VLD1D<{0,1,0,?}, "16", addrmode6align64>;
|
|
def VLD1d32 : VLD1D<{1,0,0,?}, "32", addrmode6align64>;
|
|
def VLD1d64 : VLD1D<{1,1,0,?}, "64", addrmode6align64>;
|
|
|
|
def VLD1q8 : VLD1Q<{0,0,?,?}, "8", addrmode6align64or128>;
|
|
def VLD1q16 : VLD1Q<{0,1,?,?}, "16", addrmode6align64or128>;
|
|
def VLD1q32 : VLD1Q<{1,0,?,?}, "32", addrmode6align64or128>;
|
|
def VLD1q64 : VLD1Q<{1,1,?,?}, "64", addrmode6align64or128>;
|
|
|
|
// ...with address register writeback:
|
|
multiclass VLD1DWB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b10, 0b0111,op7_4, (outs VecListOneD:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), IIC_VLD1u,
|
|
"vld1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD1]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b10,0b0111,op7_4, (outs VecListOneD:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), IIC_VLD1u,
|
|
"vld1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD1]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
multiclass VLD1QWB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b10,0b1010,op7_4, (outs VecListDPair:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), IIC_VLD1x2u,
|
|
"vld1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD2]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b10,0b1010,op7_4, (outs VecListDPair:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), IIC_VLD1x2u,
|
|
"vld1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD2]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
|
|
defm VLD1d8wb : VLD1DWB<{0,0,0,?}, "8", addrmode6align64>;
|
|
defm VLD1d16wb : VLD1DWB<{0,1,0,?}, "16", addrmode6align64>;
|
|
defm VLD1d32wb : VLD1DWB<{1,0,0,?}, "32", addrmode6align64>;
|
|
defm VLD1d64wb : VLD1DWB<{1,1,0,?}, "64", addrmode6align64>;
|
|
defm VLD1q8wb : VLD1QWB<{0,0,?,?}, "8", addrmode6align64or128>;
|
|
defm VLD1q16wb : VLD1QWB<{0,1,?,?}, "16", addrmode6align64or128>;
|
|
defm VLD1q32wb : VLD1QWB<{1,0,?,?}, "32", addrmode6align64or128>;
|
|
defm VLD1q64wb : VLD1QWB<{1,1,?,?}, "64", addrmode6align64or128>;
|
|
|
|
// ...with 3 registers
|
|
class VLD1D3<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0,0b10,0b0110,op7_4, (outs VecListThreeD:$Vd),
|
|
(ins AddrMode:$Rn), IIC_VLD1x3, "vld1", Dt,
|
|
"$Vd, $Rn", "", []>, Sched<[WriteVLD3]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
multiclass VLD1D3WB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b10,0b0110, op7_4, (outs VecListThreeD:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), IIC_VLD1x2u,
|
|
"vld1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD3]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b10,0b0110,op7_4, (outs VecListThreeD:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), IIC_VLD1x2u,
|
|
"vld1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD3]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
|
|
def VLD1d8T : VLD1D3<{0,0,0,?}, "8", addrmode6align64>;
|
|
def VLD1d16T : VLD1D3<{0,1,0,?}, "16", addrmode6align64>;
|
|
def VLD1d32T : VLD1D3<{1,0,0,?}, "32", addrmode6align64>;
|
|
def VLD1d64T : VLD1D3<{1,1,0,?}, "64", addrmode6align64>;
|
|
|
|
defm VLD1d8Twb : VLD1D3WB<{0,0,0,?}, "8", addrmode6align64>;
|
|
defm VLD1d16Twb : VLD1D3WB<{0,1,0,?}, "16", addrmode6align64>;
|
|
defm VLD1d32Twb : VLD1D3WB<{1,0,0,?}, "32", addrmode6align64>;
|
|
defm VLD1d64Twb : VLD1D3WB<{1,1,0,?}, "64", addrmode6align64>;
|
|
|
|
def VLD1d8TPseudo : VLDQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1d16TPseudo : VLDQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1d32TPseudo : VLDQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1d64TPseudo : VLDQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1d64TPseudoWB_fixed : VLDQQWBfixedPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1d64TPseudoWB_register : VLDQQWBregisterPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
|
|
def VLD1q8HighTPseudo : VLDQQQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1q8LowTPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1q16HighTPseudo : VLDQQQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1q16LowTPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1q32HighTPseudo : VLDQQQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1q32LowTPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1q64HighTPseudo : VLDQQQQPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
def VLD1q64LowTPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x3>, Sched<[WriteVLD3]>;
|
|
|
|
// ...with 4 registers
|
|
class VLD1D4<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0, 0b10, 0b0010, op7_4, (outs VecListFourD:$Vd),
|
|
(ins AddrMode:$Rn), IIC_VLD1x4, "vld1", Dt,
|
|
"$Vd, $Rn", "", []>, Sched<[WriteVLD4]> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
multiclass VLD1D4WB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b10,0b0010, op7_4, (outs VecListFourD:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), IIC_VLD1x2u,
|
|
"vld1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD4]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b10,0b0010,op7_4, (outs VecListFourD:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), IIC_VLD1x2u,
|
|
"vld1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD4]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
|
|
def VLD1d8Q : VLD1D4<{0,0,?,?}, "8", addrmode6align64or128or256>;
|
|
def VLD1d16Q : VLD1D4<{0,1,?,?}, "16", addrmode6align64or128or256>;
|
|
def VLD1d32Q : VLD1D4<{1,0,?,?}, "32", addrmode6align64or128or256>;
|
|
def VLD1d64Q : VLD1D4<{1,1,?,?}, "64", addrmode6align64or128or256>;
|
|
|
|
defm VLD1d8Qwb : VLD1D4WB<{0,0,?,?}, "8", addrmode6align64or128or256>;
|
|
defm VLD1d16Qwb : VLD1D4WB<{0,1,?,?}, "16", addrmode6align64or128or256>;
|
|
defm VLD1d32Qwb : VLD1D4WB<{1,0,?,?}, "32", addrmode6align64or128or256>;
|
|
defm VLD1d64Qwb : VLD1D4WB<{1,1,?,?}, "64", addrmode6align64or128or256>;
|
|
|
|
def VLD1d8QPseudo : VLDQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1d16QPseudo : VLDQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1d32QPseudo : VLDQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1d64QPseudo : VLDQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1d64QPseudoWB_fixed : VLDQQWBfixedPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1d64QPseudoWB_register : VLDQQWBregisterPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
|
|
def VLD1q8LowQPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1q8HighQPseudo : VLDQQQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1q16LowQPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1q16HighQPseudo : VLDQQQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1q32LowQPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1q32HighQPseudo : VLDQQQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1q64LowQPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
def VLD1q64HighQPseudo : VLDQQQQPseudo<IIC_VLD1x4>, Sched<[WriteVLD4]>;
|
|
|
|
// VLD2 : Vector Load (multiple 2-element structures)
|
|
class VLD2<bits<4> op11_8, bits<4> op7_4, string Dt, RegisterOperand VdTy,
|
|
InstrItinClass itin, Operand AddrMode>
|
|
: NLdSt<0, 0b10, op11_8, op7_4, (outs VdTy:$Vd),
|
|
(ins AddrMode:$Rn), itin,
|
|
"vld2", Dt, "$Vd, $Rn", "", []> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
|
|
def VLD2d8 : VLD2<0b1000, {0,0,?,?}, "8", VecListDPair, IIC_VLD2,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
def VLD2d16 : VLD2<0b1000, {0,1,?,?}, "16", VecListDPair, IIC_VLD2,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
def VLD2d32 : VLD2<0b1000, {1,0,?,?}, "32", VecListDPair, IIC_VLD2,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
|
|
def VLD2q8 : VLD2<0b0011, {0,0,?,?}, "8", VecListFourD, IIC_VLD2x2,
|
|
addrmode6align64or128or256>, Sched<[WriteVLD4]>;
|
|
def VLD2q16 : VLD2<0b0011, {0,1,?,?}, "16", VecListFourD, IIC_VLD2x2,
|
|
addrmode6align64or128or256>, Sched<[WriteVLD4]>;
|
|
def VLD2q32 : VLD2<0b0011, {1,0,?,?}, "32", VecListFourD, IIC_VLD2x2,
|
|
addrmode6align64or128or256>, Sched<[WriteVLD4]>;
|
|
|
|
def VLD2q8Pseudo : VLDQQPseudo<IIC_VLD2x2>, Sched<[WriteVLD4]>;
|
|
def VLD2q16Pseudo : VLDQQPseudo<IIC_VLD2x2>, Sched<[WriteVLD4]>;
|
|
def VLD2q32Pseudo : VLDQQPseudo<IIC_VLD2x2>, Sched<[WriteVLD4]>;
|
|
|
|
// ...with address register writeback:
|
|
multiclass VLD2WB<bits<4> op11_8, bits<4> op7_4, string Dt,
|
|
RegisterOperand VdTy, InstrItinClass itin, Operand AddrMode> {
|
|
def _fixed : NLdSt<0, 0b10, op11_8, op7_4, (outs VdTy:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), itin,
|
|
"vld2", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
def _register : NLdSt<0, 0b10, op11_8, op7_4, (outs VdTy:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), itin,
|
|
"vld2", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
}
|
|
|
|
defm VLD2d8wb : VLD2WB<0b1000, {0,0,?,?}, "8", VecListDPair, IIC_VLD2u,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
defm VLD2d16wb : VLD2WB<0b1000, {0,1,?,?}, "16", VecListDPair, IIC_VLD2u,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
defm VLD2d32wb : VLD2WB<0b1000, {1,0,?,?}, "32", VecListDPair, IIC_VLD2u,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
|
|
defm VLD2q8wb : VLD2WB<0b0011, {0,0,?,?}, "8", VecListFourD, IIC_VLD2x2u,
|
|
addrmode6align64or128or256>, Sched<[WriteVLD4]>;
|
|
defm VLD2q16wb : VLD2WB<0b0011, {0,1,?,?}, "16", VecListFourD, IIC_VLD2x2u,
|
|
addrmode6align64or128or256>, Sched<[WriteVLD4]>;
|
|
defm VLD2q32wb : VLD2WB<0b0011, {1,0,?,?}, "32", VecListFourD, IIC_VLD2x2u,
|
|
addrmode6align64or128or256>, Sched<[WriteVLD4]>;
|
|
|
|
def VLD2q8PseudoWB_fixed : VLDQQWBfixedPseudo<IIC_VLD2x2u>, Sched<[WriteVLD4]>;
|
|
def VLD2q16PseudoWB_fixed : VLDQQWBfixedPseudo<IIC_VLD2x2u>, Sched<[WriteVLD4]>;
|
|
def VLD2q32PseudoWB_fixed : VLDQQWBfixedPseudo<IIC_VLD2x2u>, Sched<[WriteVLD4]>;
|
|
def VLD2q8PseudoWB_register : VLDQQWBregisterPseudo<IIC_VLD2x2u>, Sched<[WriteVLD4]>;
|
|
def VLD2q16PseudoWB_register : VLDQQWBregisterPseudo<IIC_VLD2x2u>, Sched<[WriteVLD4]>;
|
|
def VLD2q32PseudoWB_register : VLDQQWBregisterPseudo<IIC_VLD2x2u>, Sched<[WriteVLD4]>;
|
|
|
|
// ...with double-spaced registers
|
|
def VLD2b8 : VLD2<0b1001, {0,0,?,?}, "8", VecListDPairSpaced, IIC_VLD2,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
def VLD2b16 : VLD2<0b1001, {0,1,?,?}, "16", VecListDPairSpaced, IIC_VLD2,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
def VLD2b32 : VLD2<0b1001, {1,0,?,?}, "32", VecListDPairSpaced, IIC_VLD2,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
defm VLD2b8wb : VLD2WB<0b1001, {0,0,?,?}, "8", VecListDPairSpaced, IIC_VLD2u,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
defm VLD2b16wb : VLD2WB<0b1001, {0,1,?,?}, "16", VecListDPairSpaced, IIC_VLD2u,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
defm VLD2b32wb : VLD2WB<0b1001, {1,0,?,?}, "32", VecListDPairSpaced, IIC_VLD2u,
|
|
addrmode6align64or128>, Sched<[WriteVLD2]>;
|
|
|
|
// VLD3 : Vector Load (multiple 3-element structures)
|
|
class VLD3D<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b10, op11_8, op7_4, (outs DPR:$Vd, DPR:$dst2, DPR:$dst3),
|
|
(ins addrmode6:$Rn), IIC_VLD3,
|
|
"vld3", Dt, "\\{$Vd, $dst2, $dst3\\}, $Rn", "", []>, Sched<[WriteVLD3]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST3Instruction";
|
|
}
|
|
|
|
def VLD3d8 : VLD3D<0b0100, {0,0,0,?}, "8">;
|
|
def VLD3d16 : VLD3D<0b0100, {0,1,0,?}, "16">;
|
|
def VLD3d32 : VLD3D<0b0100, {1,0,0,?}, "32">;
|
|
|
|
def VLD3d8Pseudo : VLDQQPseudo<IIC_VLD3>, Sched<[WriteVLD3]>;
|
|
def VLD3d16Pseudo : VLDQQPseudo<IIC_VLD3>, Sched<[WriteVLD3]>;
|
|
def VLD3d32Pseudo : VLDQQPseudo<IIC_VLD3>, Sched<[WriteVLD3]>;
|
|
|
|
// ...with address register writeback:
|
|
class VLD3DWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b10, op11_8, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm), IIC_VLD3u,
|
|
"vld3", Dt, "\\{$Vd, $dst2, $dst3\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD3]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST3Instruction";
|
|
}
|
|
|
|
def VLD3d8_UPD : VLD3DWB<0b0100, {0,0,0,?}, "8">;
|
|
def VLD3d16_UPD : VLD3DWB<0b0100, {0,1,0,?}, "16">;
|
|
def VLD3d32_UPD : VLD3DWB<0b0100, {1,0,0,?}, "32">;
|
|
|
|
def VLD3d8Pseudo_UPD : VLDQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
def VLD3d16Pseudo_UPD : VLDQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
def VLD3d32Pseudo_UPD : VLDQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VLD3q8 : VLD3D<0b0101, {0,0,0,?}, "8">;
|
|
def VLD3q16 : VLD3D<0b0101, {0,1,0,?}, "16">;
|
|
def VLD3q32 : VLD3D<0b0101, {1,0,0,?}, "32">;
|
|
def VLD3q8_UPD : VLD3DWB<0b0101, {0,0,0,?}, "8">;
|
|
def VLD3q16_UPD : VLD3DWB<0b0101, {0,1,0,?}, "16">;
|
|
def VLD3q32_UPD : VLD3DWB<0b0101, {1,0,0,?}, "32">;
|
|
|
|
def VLD3q8Pseudo_UPD : VLDQQQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
def VLD3q16Pseudo_UPD : VLDQQQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
def VLD3q32Pseudo_UPD : VLDQQQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
|
|
// ...alternate versions to be allocated odd register numbers:
|
|
def VLD3q8oddPseudo : VLDQQQQPseudo<IIC_VLD3>, Sched<[WriteVLD3]>;
|
|
def VLD3q16oddPseudo : VLDQQQQPseudo<IIC_VLD3>, Sched<[WriteVLD3]>;
|
|
def VLD3q32oddPseudo : VLDQQQQPseudo<IIC_VLD3>, Sched<[WriteVLD3]>;
|
|
|
|
def VLD3q8oddPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
def VLD3q16oddPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
def VLD3q32oddPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD3u>, Sched<[WriteVLD3]>;
|
|
|
|
// VLD4 : Vector Load (multiple 4-element structures)
|
|
class VLD4D<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b10, op11_8, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, DPR:$dst4),
|
|
(ins addrmode6:$Rn), IIC_VLD4,
|
|
"vld4", Dt, "\\{$Vd, $dst2, $dst3, $dst4\\}, $Rn", "", []>,
|
|
Sched<[WriteVLD4]> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST4Instruction";
|
|
}
|
|
|
|
def VLD4d8 : VLD4D<0b0000, {0,0,?,?}, "8">;
|
|
def VLD4d16 : VLD4D<0b0000, {0,1,?,?}, "16">;
|
|
def VLD4d32 : VLD4D<0b0000, {1,0,?,?}, "32">;
|
|
|
|
def VLD4d8Pseudo : VLDQQPseudo<IIC_VLD4>, Sched<[WriteVLD4]>;
|
|
def VLD4d16Pseudo : VLDQQPseudo<IIC_VLD4>, Sched<[WriteVLD4]>;
|
|
def VLD4d32Pseudo : VLDQQPseudo<IIC_VLD4>, Sched<[WriteVLD4]>;
|
|
|
|
// ...with address register writeback:
|
|
class VLD4DWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b10, op11_8, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, DPR:$dst4, GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm), IIC_VLD4u,
|
|
"vld4", Dt, "\\{$Vd, $dst2, $dst3, $dst4\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD4]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST4Instruction";
|
|
}
|
|
|
|
def VLD4d8_UPD : VLD4DWB<0b0000, {0,0,?,?}, "8">;
|
|
def VLD4d16_UPD : VLD4DWB<0b0000, {0,1,?,?}, "16">;
|
|
def VLD4d32_UPD : VLD4DWB<0b0000, {1,0,?,?}, "32">;
|
|
|
|
def VLD4d8Pseudo_UPD : VLDQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
def VLD4d16Pseudo_UPD : VLDQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
def VLD4d32Pseudo_UPD : VLDQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VLD4q8 : VLD4D<0b0001, {0,0,?,?}, "8">;
|
|
def VLD4q16 : VLD4D<0b0001, {0,1,?,?}, "16">;
|
|
def VLD4q32 : VLD4D<0b0001, {1,0,?,?}, "32">;
|
|
def VLD4q8_UPD : VLD4DWB<0b0001, {0,0,?,?}, "8">;
|
|
def VLD4q16_UPD : VLD4DWB<0b0001, {0,1,?,?}, "16">;
|
|
def VLD4q32_UPD : VLD4DWB<0b0001, {1,0,?,?}, "32">;
|
|
|
|
def VLD4q8Pseudo_UPD : VLDQQQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
def VLD4q16Pseudo_UPD : VLDQQQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
def VLD4q32Pseudo_UPD : VLDQQQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
|
|
// ...alternate versions to be allocated odd register numbers:
|
|
def VLD4q8oddPseudo : VLDQQQQPseudo<IIC_VLD4>, Sched<[WriteVLD4]>;
|
|
def VLD4q16oddPseudo : VLDQQQQPseudo<IIC_VLD4>, Sched<[WriteVLD4]>;
|
|
def VLD4q32oddPseudo : VLDQQQQPseudo<IIC_VLD4>, Sched<[WriteVLD4]>;
|
|
|
|
def VLD4q8oddPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
def VLD4q16oddPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
def VLD4q32oddPseudo_UPD : VLDQQQQWBPseudo<IIC_VLD4u>, Sched<[WriteVLD4]>;
|
|
|
|
} // mayLoad = 1, hasSideEffects = 0, hasExtraDefRegAllocReq = 1
|
|
|
|
// Classes for VLD*LN pseudo-instructions with multi-register operands.
|
|
// These are expanded to real instructions after register allocation.
|
|
class VLDQLNPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QPR:$dst),
|
|
(ins addrmode6:$addr, QPR:$src, nohash_imm:$lane),
|
|
itin, "$src = $dst">;
|
|
class VLDQLNWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QPR:$src,
|
|
nohash_imm:$lane), itin, "$addr.addr = $wb, $src = $dst">;
|
|
class VLDQQLNPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQPR:$dst),
|
|
(ins addrmode6:$addr, QQPR:$src, nohash_imm:$lane),
|
|
itin, "$src = $dst">;
|
|
class VLDQQLNWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QQPR:$src,
|
|
nohash_imm:$lane), itin, "$addr.addr = $wb, $src = $dst">;
|
|
class VLDQQQQLNPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQQQPR:$dst),
|
|
(ins addrmode6:$addr, QQQQPR:$src, nohash_imm:$lane),
|
|
itin, "$src = $dst">;
|
|
class VLDQQQQLNWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs QQQQPR:$dst, GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QQQQPR:$src,
|
|
nohash_imm:$lane), itin, "$addr.addr = $wb, $src = $dst">;
|
|
|
|
// VLD1LN : Vector Load (single element to one lane)
|
|
class VLD1LN<bits<4> op11_8, bits<4> op7_4, string Dt, ValueType Ty,
|
|
PatFrag LoadOp>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4, (outs DPR:$Vd),
|
|
(ins addrmode6:$Rn, DPR:$src, nohash_imm:$lane),
|
|
IIC_VLD1ln, "vld1", Dt, "\\{$Vd[$lane]\\}, $Rn",
|
|
"$src = $Vd",
|
|
[(set DPR:$Vd, (vector_insert (Ty DPR:$src),
|
|
(i32 (LoadOp addrmode6:$Rn)),
|
|
imm:$lane))]> {
|
|
let Rm = 0b1111;
|
|
let DecoderMethod = "DecodeVLD1LN";
|
|
}
|
|
class VLD1LN32<bits<4> op11_8, bits<4> op7_4, string Dt, ValueType Ty,
|
|
PatFrag LoadOp>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4, (outs DPR:$Vd),
|
|
(ins addrmode6oneL32:$Rn, DPR:$src, nohash_imm:$lane),
|
|
IIC_VLD1ln, "vld1", Dt, "\\{$Vd[$lane]\\}, $Rn",
|
|
"$src = $Vd",
|
|
[(set DPR:$Vd, (vector_insert (Ty DPR:$src),
|
|
(i32 (LoadOp addrmode6oneL32:$Rn)),
|
|
imm:$lane))]>, Sched<[WriteVLD1]> {
|
|
let Rm = 0b1111;
|
|
let DecoderMethod = "DecodeVLD1LN";
|
|
}
|
|
class VLD1QLNPseudo<ValueType Ty, PatFrag LoadOp> : VLDQLNPseudo<IIC_VLD1ln>,
|
|
Sched<[WriteVLD1]> {
|
|
let Pattern = [(set QPR:$dst, (vector_insert (Ty QPR:$src),
|
|
(i32 (LoadOp addrmode6:$addr)),
|
|
imm:$lane))];
|
|
}
|
|
|
|
def VLD1LNd8 : VLD1LN<0b0000, {?,?,?,0}, "8", v8i8, extloadi8> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD1LNd16 : VLD1LN<0b0100, {?,?,0,?}, "16", v4i16, extloadi16> {
|
|
let Inst{7-6} = lane{1-0};
|
|
let Inst{5-4} = Rn{5-4};
|
|
}
|
|
def VLD1LNd32 : VLD1LN32<0b1000, {?,0,?,?}, "32", v2i32, load> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5-4} = Rn{5-4};
|
|
}
|
|
|
|
def VLD1LNq8Pseudo : VLD1QLNPseudo<v16i8, extloadi8>;
|
|
def VLD1LNq16Pseudo : VLD1QLNPseudo<v8i16, extloadi16>;
|
|
def VLD1LNq32Pseudo : VLD1QLNPseudo<v4i32, load>;
|
|
|
|
def : Pat<(vector_insert (v2f32 DPR:$src),
|
|
(f32 (load addrmode6:$addr)), imm:$lane),
|
|
(VLD1LNd32 addrmode6:$addr, DPR:$src, imm:$lane)>;
|
|
def : Pat<(vector_insert (v4f32 QPR:$src),
|
|
(f32 (load addrmode6:$addr)), imm:$lane),
|
|
(VLD1LNq32Pseudo addrmode6:$addr, QPR:$src, imm:$lane)>;
|
|
|
|
// A 64-bit subvector insert to the first 128-bit vector position
|
|
// is a subregister copy that needs no instruction.
|
|
def : Pat<(insert_subvector undef, (v1i64 DPR:$src), (i32 0)),
|
|
(INSERT_SUBREG (v2i64 (IMPLICIT_DEF)), DPR:$src, dsub_0)>;
|
|
def : Pat<(insert_subvector undef, (v2i32 DPR:$src), (i32 0)),
|
|
(INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), DPR:$src, dsub_0)>;
|
|
def : Pat<(insert_subvector undef, (v2f32 DPR:$src), (i32 0)),
|
|
(INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), DPR:$src, dsub_0)>;
|
|
def : Pat<(insert_subvector undef, (v4i16 DPR:$src), (i32 0)),
|
|
(INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), DPR:$src, dsub_0)>;
|
|
def : Pat<(insert_subvector undef, (v4f16 DPR:$src), (i32 0)),
|
|
(INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), DPR:$src, dsub_0)>;
|
|
def : Pat<(insert_subvector (v16i8 undef), (v8i8 DPR:$src), (i32 0)),
|
|
(INSERT_SUBREG (v16i8 (IMPLICIT_DEF)), DPR:$src, dsub_0)>;
|
|
|
|
|
|
let mayLoad = 1, hasSideEffects = 0, hasExtraDefRegAllocReq = 1 in {
|
|
|
|
// ...with address register writeback:
|
|
class VLD1LNWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4, (outs DPR:$Vd, GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$src, nohash_imm:$lane), IIC_VLD1lnu, "vld1", Dt,
|
|
"\\{$Vd[$lane]\\}, $Rn$Rm",
|
|
"$src = $Vd, $Rn.addr = $wb", []>, Sched<[WriteVLD1]> {
|
|
let DecoderMethod = "DecodeVLD1LN";
|
|
}
|
|
|
|
def VLD1LNd8_UPD : VLD1LNWB<0b0000, {?,?,?,0}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD1LNd16_UPD : VLD1LNWB<0b0100, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
let Inst{4} = Rn{4};
|
|
}
|
|
def VLD1LNd32_UPD : VLD1LNWB<0b1000, {?,0,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{4};
|
|
let Inst{4} = Rn{4};
|
|
}
|
|
|
|
def VLD1LNq8Pseudo_UPD : VLDQLNWBPseudo<IIC_VLD1lnu>, Sched<[WriteVLD1]>;
|
|
def VLD1LNq16Pseudo_UPD : VLDQLNWBPseudo<IIC_VLD1lnu>, Sched<[WriteVLD1]>;
|
|
def VLD1LNq32Pseudo_UPD : VLDQLNWBPseudo<IIC_VLD1lnu>, Sched<[WriteVLD1]>;
|
|
|
|
// VLD2LN : Vector Load (single 2-element structure to one lane)
|
|
class VLD2LN<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4, (outs DPR:$Vd, DPR:$dst2),
|
|
(ins addrmode6:$Rn, DPR:$src1, DPR:$src2, nohash_imm:$lane),
|
|
IIC_VLD2ln, "vld2", Dt, "\\{$Vd[$lane], $dst2[$lane]\\}, $Rn",
|
|
"$src1 = $Vd, $src2 = $dst2", []>, Sched<[WriteVLD1]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD2LN";
|
|
}
|
|
|
|
def VLD2LNd8 : VLD2LN<0b0001, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD2LNd16 : VLD2LN<0b0101, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD2LNd32 : VLD2LN<0b1001, {?,0,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD2LNd8Pseudo : VLDQLNPseudo<IIC_VLD2ln>, Sched<[WriteVLD1]>;
|
|
def VLD2LNd16Pseudo : VLDQLNPseudo<IIC_VLD2ln>, Sched<[WriteVLD1]>;
|
|
def VLD2LNd32Pseudo : VLDQLNPseudo<IIC_VLD2ln>, Sched<[WriteVLD1]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VLD2LNq16 : VLD2LN<0b0101, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD2LNq32 : VLD2LN<0b1001, {?,1,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD2LNq16Pseudo : VLDQQLNPseudo<IIC_VLD2ln>, Sched<[WriteVLD1]>;
|
|
def VLD2LNq32Pseudo : VLDQQLNPseudo<IIC_VLD2ln>, Sched<[WriteVLD1]>;
|
|
|
|
// ...with address register writeback:
|
|
class VLD2LNWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4, (outs DPR:$Vd, DPR:$dst2, GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$src1, DPR:$src2, nohash_imm:$lane), IIC_VLD2lnu, "vld2", Dt,
|
|
"\\{$Vd[$lane], $dst2[$lane]\\}, $Rn$Rm",
|
|
"$src1 = $Vd, $src2 = $dst2, $Rn.addr = $wb", []> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD2LN";
|
|
}
|
|
|
|
def VLD2LNd8_UPD : VLD2LNWB<0b0001, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD2LNd16_UPD : VLD2LNWB<0b0101, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD2LNd32_UPD : VLD2LNWB<0b1001, {?,0,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD2LNd8Pseudo_UPD : VLDQLNWBPseudo<IIC_VLD2lnu>, Sched<[WriteVLD1]>;
|
|
def VLD2LNd16Pseudo_UPD : VLDQLNWBPseudo<IIC_VLD2lnu>, Sched<[WriteVLD1]>;
|
|
def VLD2LNd32Pseudo_UPD : VLDQLNWBPseudo<IIC_VLD2lnu>, Sched<[WriteVLD1]>;
|
|
|
|
def VLD2LNq16_UPD : VLD2LNWB<0b0101, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD2LNq32_UPD : VLD2LNWB<0b1001, {?,1,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD2LNq16Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD2lnu>, Sched<[WriteVLD1]>;
|
|
def VLD2LNq32Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD2lnu>, Sched<[WriteVLD1]>;
|
|
|
|
// VLD3LN : Vector Load (single 3-element structure to one lane)
|
|
class VLD3LN<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4, (outs DPR:$Vd, DPR:$dst2, DPR:$dst3),
|
|
(ins addrmode6:$Rn, DPR:$src1, DPR:$src2, DPR:$src3,
|
|
nohash_imm:$lane), IIC_VLD3ln, "vld3", Dt,
|
|
"\\{$Vd[$lane], $dst2[$lane], $dst3[$lane]\\}, $Rn",
|
|
"$src1 = $Vd, $src2 = $dst2, $src3 = $dst3", []>, Sched<[WriteVLD2]> {
|
|
let Rm = 0b1111;
|
|
let DecoderMethod = "DecodeVLD3LN";
|
|
}
|
|
|
|
def VLD3LNd8 : VLD3LN<0b0010, {?,?,?,0}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD3LNd16 : VLD3LN<0b0110, {?,?,0,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD3LNd32 : VLD3LN<0b1010, {?,0,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD3LNd8Pseudo : VLDQQLNPseudo<IIC_VLD3ln>, Sched<[WriteVLD2]>;
|
|
def VLD3LNd16Pseudo : VLDQQLNPseudo<IIC_VLD3ln>, Sched<[WriteVLD2]>;
|
|
def VLD3LNd32Pseudo : VLDQQLNPseudo<IIC_VLD3ln>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VLD3LNq16 : VLD3LN<0b0110, {?,?,1,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD3LNq32 : VLD3LN<0b1010, {?,1,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD3LNq16Pseudo : VLDQQQQLNPseudo<IIC_VLD3ln>, Sched<[WriteVLD2]>;
|
|
def VLD3LNq32Pseudo : VLDQQQQLNPseudo<IIC_VLD3ln>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with address register writeback:
|
|
class VLD3LNWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$src1, DPR:$src2, DPR:$src3, nohash_imm:$lane),
|
|
IIC_VLD3lnu, "vld3", Dt,
|
|
"\\{$Vd[$lane], $dst2[$lane], $dst3[$lane]\\}, $Rn$Rm",
|
|
"$src1 = $Vd, $src2 = $dst2, $src3 = $dst3, $Rn.addr = $wb",
|
|
[]>, Sched<[WriteVLD2]> {
|
|
let DecoderMethod = "DecodeVLD3LN";
|
|
}
|
|
|
|
def VLD3LNd8_UPD : VLD3LNWB<0b0010, {?,?,?,0}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD3LNd16_UPD : VLD3LNWB<0b0110, {?,?,0,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD3LNd32_UPD : VLD3LNWB<0b1010, {?,0,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD3LNd8Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD3lnu>, Sched<[WriteVLD2]>;
|
|
def VLD3LNd16Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD3lnu>, Sched<[WriteVLD2]>;
|
|
def VLD3LNd32Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD3lnu>, Sched<[WriteVLD2]>;
|
|
|
|
def VLD3LNq16_UPD : VLD3LNWB<0b0110, {?,?,1,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD3LNq32_UPD : VLD3LNWB<0b1010, {?,1,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VLD3LNq16Pseudo_UPD : VLDQQQQLNWBPseudo<IIC_VLD3lnu>, Sched<[WriteVLD2]>;
|
|
def VLD3LNq32Pseudo_UPD : VLDQQQQLNWBPseudo<IIC_VLD3lnu>, Sched<[WriteVLD2]>;
|
|
|
|
// VLD4LN : Vector Load (single 4-element structure to one lane)
|
|
class VLD4LN<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, DPR:$dst4),
|
|
(ins addrmode6:$Rn, DPR:$src1, DPR:$src2, DPR:$src3, DPR:$src4,
|
|
nohash_imm:$lane), IIC_VLD4ln, "vld4", Dt,
|
|
"\\{$Vd[$lane], $dst2[$lane], $dst3[$lane], $dst4[$lane]\\}, $Rn",
|
|
"$src1 = $Vd, $src2 = $dst2, $src3 = $dst3, $src4 = $dst4", []>,
|
|
Sched<[WriteVLD2]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD4LN";
|
|
}
|
|
|
|
def VLD4LNd8 : VLD4LN<0b0011, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD4LNd16 : VLD4LN<0b0111, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD4LNd32 : VLD4LN<0b1011, {?,0,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VLD4LNd8Pseudo : VLDQQLNPseudo<IIC_VLD4ln>, Sched<[WriteVLD2]>;
|
|
def VLD4LNd16Pseudo : VLDQQLNPseudo<IIC_VLD4ln>, Sched<[WriteVLD2]>;
|
|
def VLD4LNd32Pseudo : VLDQQLNPseudo<IIC_VLD4ln>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VLD4LNq16 : VLD4LN<0b0111, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD4LNq32 : VLD4LN<0b1011, {?,1,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VLD4LNq16Pseudo : VLDQQQQLNPseudo<IIC_VLD4ln>, Sched<[WriteVLD2]>;
|
|
def VLD4LNq32Pseudo : VLDQQQQLNPseudo<IIC_VLD4ln>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with address register writeback:
|
|
class VLD4LNWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b10, op11_8, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, DPR:$dst4, GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$src1, DPR:$src2, DPR:$src3, DPR:$src4, nohash_imm:$lane),
|
|
IIC_VLD4lnu, "vld4", Dt,
|
|
"\\{$Vd[$lane], $dst2[$lane], $dst3[$lane], $dst4[$lane]\\}, $Rn$Rm",
|
|
"$src1 = $Vd, $src2 = $dst2, $src3 = $dst3, $src4 = $dst4, $Rn.addr = $wb",
|
|
[]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD4LN" ;
|
|
}
|
|
|
|
def VLD4LNd8_UPD : VLD4LNWB<0b0011, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VLD4LNd16_UPD : VLD4LNWB<0b0111, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD4LNd32_UPD : VLD4LNWB<0b1011, {?,0,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VLD4LNd8Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD4lnu>, Sched<[WriteVLD2]>;
|
|
def VLD4LNd16Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD4lnu>, Sched<[WriteVLD2]>;
|
|
def VLD4LNd32Pseudo_UPD : VLDQQLNWBPseudo<IIC_VLD4lnu>, Sched<[WriteVLD2]>;
|
|
|
|
def VLD4LNq16_UPD : VLD4LNWB<0b0111, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VLD4LNq32_UPD : VLD4LNWB<0b1011, {?,1,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VLD4LNq16Pseudo_UPD : VLDQQQQLNWBPseudo<IIC_VLD4lnu>, Sched<[WriteVLD2]>;
|
|
def VLD4LNq32Pseudo_UPD : VLDQQQQLNWBPseudo<IIC_VLD4lnu>, Sched<[WriteVLD2]>;
|
|
|
|
} // mayLoad = 1, hasSideEffects = 0, hasExtraDefRegAllocReq = 1
|
|
|
|
// VLD1DUP : Vector Load (single element to all lanes)
|
|
class VLD1DUP<bits<4> op7_4, string Dt, ValueType Ty, PatFrag LoadOp,
|
|
Operand AddrMode>
|
|
: NLdSt<1, 0b10, 0b1100, op7_4, (outs VecListOneDAllLanes:$Vd),
|
|
(ins AddrMode:$Rn),
|
|
IIC_VLD1dup, "vld1", Dt, "$Vd, $Rn", "",
|
|
[(set VecListOneDAllLanes:$Vd,
|
|
(Ty (NEONvdup (i32 (LoadOp AddrMode:$Rn)))))]>,
|
|
Sched<[WriteVLD2]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD1DupInstruction";
|
|
}
|
|
def VLD1DUPd8 : VLD1DUP<{0,0,0,?}, "8", v8i8, extloadi8,
|
|
addrmode6dupalignNone>;
|
|
def VLD1DUPd16 : VLD1DUP<{0,1,0,?}, "16", v4i16, extloadi16,
|
|
addrmode6dupalign16>;
|
|
def VLD1DUPd32 : VLD1DUP<{1,0,0,?}, "32", v2i32, load,
|
|
addrmode6dupalign32>;
|
|
|
|
def : Pat<(v2f32 (NEONvdup (f32 (load addrmode6dup:$addr)))),
|
|
(VLD1DUPd32 addrmode6:$addr)>;
|
|
|
|
class VLD1QDUP<bits<4> op7_4, string Dt, ValueType Ty, PatFrag LoadOp,
|
|
Operand AddrMode>
|
|
: NLdSt<1, 0b10, 0b1100, op7_4, (outs VecListDPairAllLanes:$Vd),
|
|
(ins AddrMode:$Rn), IIC_VLD1dup,
|
|
"vld1", Dt, "$Vd, $Rn", "",
|
|
[(set VecListDPairAllLanes:$Vd,
|
|
(Ty (NEONvdup (i32 (LoadOp AddrMode:$Rn)))))]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD1DupInstruction";
|
|
}
|
|
|
|
def VLD1DUPq8 : VLD1QDUP<{0,0,1,0}, "8", v16i8, extloadi8,
|
|
addrmode6dupalignNone>;
|
|
def VLD1DUPq16 : VLD1QDUP<{0,1,1,?}, "16", v8i16, extloadi16,
|
|
addrmode6dupalign16>;
|
|
def VLD1DUPq32 : VLD1QDUP<{1,0,1,?}, "32", v4i32, load,
|
|
addrmode6dupalign32>;
|
|
|
|
def : Pat<(v4f32 (NEONvdup (f32 (load addrmode6dup:$addr)))),
|
|
(VLD1DUPq32 addrmode6:$addr)>;
|
|
|
|
let mayLoad = 1, hasSideEffects = 0, hasExtraDefRegAllocReq = 1 in {
|
|
// ...with address register writeback:
|
|
multiclass VLD1DUPWB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<1, 0b10, 0b1100, op7_4,
|
|
(outs VecListOneDAllLanes:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), IIC_VLD1dupu,
|
|
"vld1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD1DupInstruction";
|
|
}
|
|
def _register : NLdSt<1, 0b10, 0b1100, op7_4,
|
|
(outs VecListOneDAllLanes:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), IIC_VLD1dupu,
|
|
"vld1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD1DupInstruction";
|
|
}
|
|
}
|
|
multiclass VLD1QDUPWB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<1, 0b10, 0b1100, op7_4,
|
|
(outs VecListDPairAllLanes:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), IIC_VLD1dupu,
|
|
"vld1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD1]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD1DupInstruction";
|
|
}
|
|
def _register : NLdSt<1, 0b10, 0b1100, op7_4,
|
|
(outs VecListDPairAllLanes:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), IIC_VLD1dupu,
|
|
"vld1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD1DupInstruction";
|
|
}
|
|
}
|
|
|
|
defm VLD1DUPd8wb : VLD1DUPWB<{0,0,0,0}, "8", addrmode6dupalignNone>;
|
|
defm VLD1DUPd16wb : VLD1DUPWB<{0,1,0,?}, "16", addrmode6dupalign16>;
|
|
defm VLD1DUPd32wb : VLD1DUPWB<{1,0,0,?}, "32", addrmode6dupalign32>;
|
|
|
|
defm VLD1DUPq8wb : VLD1QDUPWB<{0,0,1,0}, "8", addrmode6dupalignNone>;
|
|
defm VLD1DUPq16wb : VLD1QDUPWB<{0,1,1,?}, "16", addrmode6dupalign16>;
|
|
defm VLD1DUPq32wb : VLD1QDUPWB<{1,0,1,?}, "32", addrmode6dupalign32>;
|
|
|
|
// VLD2DUP : Vector Load (single 2-element structure to all lanes)
|
|
class VLD2DUP<bits<4> op7_4, string Dt, RegisterOperand VdTy, Operand AddrMode>
|
|
: NLdSt<1, 0b10, 0b1101, op7_4, (outs VdTy:$Vd),
|
|
(ins AddrMode:$Rn), IIC_VLD2dup,
|
|
"vld2", Dt, "$Vd, $Rn", "", []> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD2DupInstruction";
|
|
}
|
|
|
|
def VLD2DUPd8 : VLD2DUP<{0,0,0,?}, "8", VecListDPairAllLanes,
|
|
addrmode6dupalign16>;
|
|
def VLD2DUPd16 : VLD2DUP<{0,1,0,?}, "16", VecListDPairAllLanes,
|
|
addrmode6dupalign32>;
|
|
def VLD2DUPd32 : VLD2DUP<{1,0,0,?}, "32", VecListDPairAllLanes,
|
|
addrmode6dupalign64>;
|
|
|
|
// HACK this one, VLD2DUPd8x2 must be changed at the same time with VLD2b8 or
|
|
// "vld2.8 {d0[], d2[]}, [r4:32]" will become "vld2.8 {d0, d2}, [r4:32]".
|
|
// ...with double-spaced registers
|
|
def VLD2DUPd8x2 : VLD2DUP<{0,0,1,?}, "8", VecListDPairSpacedAllLanes,
|
|
addrmode6dupalign16>;
|
|
def VLD2DUPd16x2 : VLD2DUP<{0,1,1,?}, "16", VecListDPairSpacedAllLanes,
|
|
addrmode6dupalign32>;
|
|
def VLD2DUPd32x2 : VLD2DUP<{1,0,1,?}, "32", VecListDPairSpacedAllLanes,
|
|
addrmode6dupalign64>;
|
|
|
|
def VLD2DUPq8EvenPseudo : VLDQQPseudo<IIC_VLD2dup>, Sched<[WriteVLD2]>;
|
|
def VLD2DUPq8OddPseudo : VLDQQPseudo<IIC_VLD2dup>, Sched<[WriteVLD2]>;
|
|
def VLD2DUPq16EvenPseudo : VLDQQPseudo<IIC_VLD2dup>, Sched<[WriteVLD2]>;
|
|
def VLD2DUPq16OddPseudo : VLDQQPseudo<IIC_VLD2dup>, Sched<[WriteVLD2]>;
|
|
def VLD2DUPq32EvenPseudo : VLDQQPseudo<IIC_VLD2dup>, Sched<[WriteVLD2]>;
|
|
def VLD2DUPq32OddPseudo : VLDQQPseudo<IIC_VLD2dup>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with address register writeback:
|
|
multiclass VLD2DUPWB<bits<4> op7_4, string Dt, RegisterOperand VdTy,
|
|
Operand AddrMode> {
|
|
def _fixed : NLdSt<1, 0b10, 0b1101, op7_4,
|
|
(outs VdTy:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn), IIC_VLD2dupu,
|
|
"vld2", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD1]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD2DupInstruction";
|
|
}
|
|
def _register : NLdSt<1, 0b10, 0b1101, op7_4,
|
|
(outs VdTy:$Vd, GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm), IIC_VLD2dupu,
|
|
"vld2", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD1]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD2DupInstruction";
|
|
}
|
|
}
|
|
|
|
defm VLD2DUPd8wb : VLD2DUPWB<{0,0,0,0}, "8", VecListDPairAllLanes,
|
|
addrmode6dupalign16>;
|
|
defm VLD2DUPd16wb : VLD2DUPWB<{0,1,0,?}, "16", VecListDPairAllLanes,
|
|
addrmode6dupalign32>;
|
|
defm VLD2DUPd32wb : VLD2DUPWB<{1,0,0,?}, "32", VecListDPairAllLanes,
|
|
addrmode6dupalign64>;
|
|
|
|
defm VLD2DUPd8x2wb : VLD2DUPWB<{0,0,1,0}, "8", VecListDPairSpacedAllLanes,
|
|
addrmode6dupalign16>;
|
|
defm VLD2DUPd16x2wb : VLD2DUPWB<{0,1,1,?}, "16", VecListDPairSpacedAllLanes,
|
|
addrmode6dupalign32>;
|
|
defm VLD2DUPd32x2wb : VLD2DUPWB<{1,0,1,?}, "32", VecListDPairSpacedAllLanes,
|
|
addrmode6dupalign64>;
|
|
|
|
// VLD3DUP : Vector Load (single 3-element structure to all lanes)
|
|
class VLD3DUP<bits<4> op7_4, string Dt>
|
|
: NLdSt<1, 0b10, 0b1110, op7_4, (outs DPR:$Vd, DPR:$dst2, DPR:$dst3),
|
|
(ins addrmode6dup:$Rn), IIC_VLD3dup,
|
|
"vld3", Dt, "\\{$Vd[], $dst2[], $dst3[]\\}, $Rn", "", []>,
|
|
Sched<[WriteVLD2]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = 0;
|
|
let DecoderMethod = "DecodeVLD3DupInstruction";
|
|
}
|
|
|
|
def VLD3DUPd8 : VLD3DUP<{0,0,0,?}, "8">;
|
|
def VLD3DUPd16 : VLD3DUP<{0,1,0,?}, "16">;
|
|
def VLD3DUPd32 : VLD3DUP<{1,0,0,?}, "32">;
|
|
|
|
def VLD3DUPd8Pseudo : VLDQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPd16Pseudo : VLDQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPd32Pseudo : VLDQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with double-spaced registers (not used for codegen):
|
|
def VLD3DUPq8 : VLD3DUP<{0,0,1,?}, "8">;
|
|
def VLD3DUPq16 : VLD3DUP<{0,1,1,?}, "16">;
|
|
def VLD3DUPq32 : VLD3DUP<{1,0,1,?}, "32">;
|
|
|
|
def VLD3DUPq8EvenPseudo : VLDQQQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPq8OddPseudo : VLDQQQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPq16EvenPseudo : VLDQQQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPq16OddPseudo : VLDQQQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPq32EvenPseudo : VLDQQQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPq32OddPseudo : VLDQQQQPseudo<IIC_VLD3dup>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with address register writeback:
|
|
class VLD3DUPWB<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<1, 0b10, 0b1110, op7_4, (outs DPR:$Vd, DPR:$dst2, DPR:$dst3, GPR:$wb),
|
|
(ins AddrMode:$Rn, am6offset:$Rm), IIC_VLD3dupu,
|
|
"vld3", Dt, "\\{$Vd[], $dst2[], $dst3[]\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD2]> {
|
|
let Inst{4} = 0;
|
|
let DecoderMethod = "DecodeVLD3DupInstruction";
|
|
}
|
|
|
|
def VLD3DUPd8_UPD : VLD3DUPWB<{0,0,0,0}, "8", addrmode6dupalign64>;
|
|
def VLD3DUPd16_UPD : VLD3DUPWB<{0,1,0,?}, "16", addrmode6dupalign64>;
|
|
def VLD3DUPd32_UPD : VLD3DUPWB<{1,0,0,?}, "32", addrmode6dupalign64>;
|
|
|
|
def VLD3DUPq8_UPD : VLD3DUPWB<{0,0,1,0}, "8", addrmode6dupalign64>;
|
|
def VLD3DUPq16_UPD : VLD3DUPWB<{0,1,1,?}, "16", addrmode6dupalign64>;
|
|
def VLD3DUPq32_UPD : VLD3DUPWB<{1,0,1,?}, "32", addrmode6dupalign64>;
|
|
|
|
def VLD3DUPd8Pseudo_UPD : VLDQQWBPseudo<IIC_VLD3dupu>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPd16Pseudo_UPD : VLDQQWBPseudo<IIC_VLD3dupu>, Sched<[WriteVLD2]>;
|
|
def VLD3DUPd32Pseudo_UPD : VLDQQWBPseudo<IIC_VLD3dupu>, Sched<[WriteVLD2]>;
|
|
|
|
// VLD4DUP : Vector Load (single 4-element structure to all lanes)
|
|
class VLD4DUP<bits<4> op7_4, string Dt>
|
|
: NLdSt<1, 0b10, 0b1111, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, DPR:$dst4),
|
|
(ins addrmode6dup:$Rn), IIC_VLD4dup,
|
|
"vld4", Dt, "\\{$Vd[], $dst2[], $dst3[], $dst4[]\\}, $Rn", "", []> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD4DupInstruction";
|
|
}
|
|
|
|
def VLD4DUPd8 : VLD4DUP<{0,0,0,?}, "8">;
|
|
def VLD4DUPd16 : VLD4DUP<{0,1,0,?}, "16">;
|
|
def VLD4DUPd32 : VLD4DUP<{1,?,0,?}, "32"> { let Inst{6} = Rn{5}; }
|
|
|
|
def VLD4DUPd8Pseudo : VLDQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPd16Pseudo : VLDQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPd32Pseudo : VLDQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with double-spaced registers (not used for codegen):
|
|
def VLD4DUPq8 : VLD4DUP<{0,0,1,?}, "8">;
|
|
def VLD4DUPq16 : VLD4DUP<{0,1,1,?}, "16">;
|
|
def VLD4DUPq32 : VLD4DUP<{1,?,1,?}, "32"> { let Inst{6} = Rn{5}; }
|
|
|
|
def VLD4DUPq8EvenPseudo : VLDQQQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPq8OddPseudo : VLDQQQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPq16EvenPseudo : VLDQQQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPq16OddPseudo : VLDQQQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPq32EvenPseudo : VLDQQQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPq32OddPseudo : VLDQQQQPseudo<IIC_VLD4dup>, Sched<[WriteVLD2]>;
|
|
|
|
// ...with address register writeback:
|
|
class VLD4DUPWB<bits<4> op7_4, string Dt>
|
|
: NLdSt<1, 0b10, 0b1111, op7_4,
|
|
(outs DPR:$Vd, DPR:$dst2, DPR:$dst3, DPR:$dst4, GPR:$wb),
|
|
(ins addrmode6dup:$Rn, am6offset:$Rm), IIC_VLD4dupu,
|
|
"vld4", Dt, "\\{$Vd[], $dst2[], $dst3[], $dst4[]\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVLD2]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLD4DupInstruction";
|
|
}
|
|
|
|
def VLD4DUPd8_UPD : VLD4DUPWB<{0,0,0,0}, "8">;
|
|
def VLD4DUPd16_UPD : VLD4DUPWB<{0,1,0,?}, "16">;
|
|
def VLD4DUPd32_UPD : VLD4DUPWB<{1,?,0,?}, "32"> { let Inst{6} = Rn{5}; }
|
|
|
|
def VLD4DUPq8_UPD : VLD4DUPWB<{0,0,1,0}, "8">;
|
|
def VLD4DUPq16_UPD : VLD4DUPWB<{0,1,1,?}, "16">;
|
|
def VLD4DUPq32_UPD : VLD4DUPWB<{1,?,1,?}, "32"> { let Inst{6} = Rn{5}; }
|
|
|
|
def VLD4DUPd8Pseudo_UPD : VLDQQWBPseudo<IIC_VLD4dupu>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPd16Pseudo_UPD : VLDQQWBPseudo<IIC_VLD4dupu>, Sched<[WriteVLD2]>;
|
|
def VLD4DUPd32Pseudo_UPD : VLDQQWBPseudo<IIC_VLD4dupu>, Sched<[WriteVLD2]>;
|
|
|
|
} // mayLoad = 1, hasSideEffects = 0, hasExtraDefRegAllocReq = 1
|
|
|
|
let mayStore = 1, hasSideEffects = 0, hasExtraSrcRegAllocReq = 1 in {
|
|
|
|
// Classes for VST* pseudo-instructions with multi-register operands.
|
|
// These are expanded to real instructions after register allocation.
|
|
class VSTQPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs), (ins addrmode6:$addr, QPR:$src), itin, "">;
|
|
class VSTQWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QPR:$src), itin,
|
|
"$addr.addr = $wb">;
|
|
class VSTQWBfixedPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, QPR:$src), itin,
|
|
"$addr.addr = $wb">;
|
|
class VSTQWBregisterPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, rGPR:$offset, QPR:$src), itin,
|
|
"$addr.addr = $wb">;
|
|
class VSTQQPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs), (ins addrmode6:$addr, QQPR:$src), itin, "">;
|
|
class VSTQQWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QQPR:$src), itin,
|
|
"$addr.addr = $wb">;
|
|
class VSTQQWBfixedPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, QQPR:$src), itin,
|
|
"$addr.addr = $wb">;
|
|
class VSTQQWBregisterPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, rGPR:$offset, QQPR:$src), itin,
|
|
"$addr.addr = $wb">;
|
|
|
|
class VSTQQQQPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs), (ins addrmode6:$addr, QQQQPR:$src), itin, "">;
|
|
class VSTQQQQWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QQQQPR:$src), itin,
|
|
"$addr.addr = $wb">;
|
|
|
|
// VST1 : Vector Store (multiple single elements)
|
|
class VST1D<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0,0b00,0b0111,op7_4, (outs), (ins AddrMode:$Rn, VecListOneD:$Vd),
|
|
IIC_VST1, "vst1", Dt, "$Vd, $Rn", "", []>, Sched<[WriteVST1]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
class VST1Q<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0,0b00,0b1010,op7_4, (outs), (ins AddrMode:$Rn, VecListDPair:$Vd),
|
|
IIC_VST1x2, "vst1", Dt, "$Vd, $Rn", "", []>, Sched<[WriteVST2]> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
|
|
def VST1d8 : VST1D<{0,0,0,?}, "8", addrmode6align64>;
|
|
def VST1d16 : VST1D<{0,1,0,?}, "16", addrmode6align64>;
|
|
def VST1d32 : VST1D<{1,0,0,?}, "32", addrmode6align64>;
|
|
def VST1d64 : VST1D<{1,1,0,?}, "64", addrmode6align64>;
|
|
|
|
def VST1q8 : VST1Q<{0,0,?,?}, "8", addrmode6align64or128>;
|
|
def VST1q16 : VST1Q<{0,1,?,?}, "16", addrmode6align64or128>;
|
|
def VST1q32 : VST1Q<{1,0,?,?}, "32", addrmode6align64or128>;
|
|
def VST1q64 : VST1Q<{1,1,?,?}, "64", addrmode6align64or128>;
|
|
|
|
// ...with address register writeback:
|
|
multiclass VST1DWB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b00, 0b0111,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, VecListOneD:$Vd), IIC_VLD1u,
|
|
"vst1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST1]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b00,0b0111,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm, VecListOneD:$Vd),
|
|
IIC_VLD1u,
|
|
"vst1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST1]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
multiclass VST1QWB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b00,0b1010,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, VecListDPair:$Vd), IIC_VLD1x2u,
|
|
"vst1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST2]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b00,0b1010,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm, VecListDPair:$Vd),
|
|
IIC_VLD1x2u,
|
|
"vst1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST2]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
|
|
defm VST1d8wb : VST1DWB<{0,0,0,?}, "8", addrmode6align64>;
|
|
defm VST1d16wb : VST1DWB<{0,1,0,?}, "16", addrmode6align64>;
|
|
defm VST1d32wb : VST1DWB<{1,0,0,?}, "32", addrmode6align64>;
|
|
defm VST1d64wb : VST1DWB<{1,1,0,?}, "64", addrmode6align64>;
|
|
|
|
defm VST1q8wb : VST1QWB<{0,0,?,?}, "8", addrmode6align64or128>;
|
|
defm VST1q16wb : VST1QWB<{0,1,?,?}, "16", addrmode6align64or128>;
|
|
defm VST1q32wb : VST1QWB<{1,0,?,?}, "32", addrmode6align64or128>;
|
|
defm VST1q64wb : VST1QWB<{1,1,?,?}, "64", addrmode6align64or128>;
|
|
|
|
// ...with 3 registers
|
|
class VST1D3<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0, 0b00, 0b0110, op7_4, (outs),
|
|
(ins AddrMode:$Rn, VecListThreeD:$Vd),
|
|
IIC_VST1x3, "vst1", Dt, "$Vd, $Rn", "", []>, Sched<[WriteVST3]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
multiclass VST1D3WB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b00,0b0110,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, VecListThreeD:$Vd), IIC_VLD1x3u,
|
|
"vst1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST3]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b00,0b0110,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm, VecListThreeD:$Vd),
|
|
IIC_VLD1x3u,
|
|
"vst1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST3]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
|
|
def VST1d8T : VST1D3<{0,0,0,?}, "8", addrmode6align64>;
|
|
def VST1d16T : VST1D3<{0,1,0,?}, "16", addrmode6align64>;
|
|
def VST1d32T : VST1D3<{1,0,0,?}, "32", addrmode6align64>;
|
|
def VST1d64T : VST1D3<{1,1,0,?}, "64", addrmode6align64>;
|
|
|
|
defm VST1d8Twb : VST1D3WB<{0,0,0,?}, "8", addrmode6align64>;
|
|
defm VST1d16Twb : VST1D3WB<{0,1,0,?}, "16", addrmode6align64>;
|
|
defm VST1d32Twb : VST1D3WB<{1,0,0,?}, "32", addrmode6align64>;
|
|
defm VST1d64Twb : VST1D3WB<{1,1,0,?}, "64", addrmode6align64>;
|
|
|
|
def VST1d8TPseudo : VSTQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1d16TPseudo : VSTQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1d32TPseudo : VSTQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1d64TPseudo : VSTQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1d64TPseudoWB_fixed : VSTQQWBfixedPseudo<IIC_VST1x3u>, Sched<[WriteVST3]>;
|
|
def VST1d64TPseudoWB_register : VSTQQWBPseudo<IIC_VST1x3u>, Sched<[WriteVST3]>;
|
|
|
|
def VST1q8HighTPseudo : VSTQQQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1q8LowTPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1q16HighTPseudo : VSTQQQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1q16LowTPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1q32HighTPseudo : VSTQQQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1q32LowTPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1q64HighTPseudo : VSTQQQQPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
def VST1q64LowTPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x3>, Sched<[WriteVST3]>;
|
|
|
|
// ...with 4 registers
|
|
class VST1D4<bits<4> op7_4, string Dt, Operand AddrMode>
|
|
: NLdSt<0, 0b00, 0b0010, op7_4, (outs),
|
|
(ins AddrMode:$Rn, VecListFourD:$Vd),
|
|
IIC_VST1x4, "vst1", Dt, "$Vd, $Rn", "",
|
|
[]>, Sched<[WriteVST4]> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
multiclass VST1D4WB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0,0b00,0b0010,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, VecListFourD:$Vd), IIC_VLD1x4u,
|
|
"vst1", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST4]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
def _register : NLdSt<0,0b00,0b0010,op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm, VecListFourD:$Vd),
|
|
IIC_VLD1x4u,
|
|
"vst1", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST4]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST1Instruction";
|
|
}
|
|
}
|
|
|
|
def VST1d8Q : VST1D4<{0,0,?,?}, "8", addrmode6align64or128or256>;
|
|
def VST1d16Q : VST1D4<{0,1,?,?}, "16", addrmode6align64or128or256>;
|
|
def VST1d32Q : VST1D4<{1,0,?,?}, "32", addrmode6align64or128or256>;
|
|
def VST1d64Q : VST1D4<{1,1,?,?}, "64", addrmode6align64or128or256>;
|
|
|
|
defm VST1d8Qwb : VST1D4WB<{0,0,?,?}, "8", addrmode6align64or128or256>;
|
|
defm VST1d16Qwb : VST1D4WB<{0,1,?,?}, "16", addrmode6align64or128or256>;
|
|
defm VST1d32Qwb : VST1D4WB<{1,0,?,?}, "32", addrmode6align64or128or256>;
|
|
defm VST1d64Qwb : VST1D4WB<{1,1,?,?}, "64", addrmode6align64or128or256>;
|
|
|
|
def VST1d8QPseudo : VSTQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1d16QPseudo : VSTQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1d32QPseudo : VSTQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1d64QPseudo : VSTQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1d64QPseudoWB_fixed : VSTQQWBfixedPseudo<IIC_VST1x4u>, Sched<[WriteVST4]>;
|
|
def VST1d64QPseudoWB_register : VSTQQWBPseudo<IIC_VST1x4u>, Sched<[WriteVST4]>;
|
|
|
|
def VST1q8HighQPseudo : VSTQQQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1q8LowQPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1q16HighQPseudo : VSTQQQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1q16LowQPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1q32HighQPseudo : VSTQQQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1q32LowQPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1q64HighQPseudo : VSTQQQQPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
def VST1q64LowQPseudo_UPD : VSTQQQQWBPseudo<IIC_VST1x4>, Sched<[WriteVST4]>;
|
|
|
|
// VST2 : Vector Store (multiple 2-element structures)
|
|
class VST2<bits<4> op11_8, bits<4> op7_4, string Dt, RegisterOperand VdTy,
|
|
InstrItinClass itin, Operand AddrMode>
|
|
: NLdSt<0, 0b00, op11_8, op7_4, (outs), (ins AddrMode:$Rn, VdTy:$Vd),
|
|
itin, "vst2", Dt, "$Vd, $Rn", "", []> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
|
|
def VST2d8 : VST2<0b1000, {0,0,?,?}, "8", VecListDPair, IIC_VST2,
|
|
addrmode6align64or128>, Sched<[WriteVST2]>;
|
|
def VST2d16 : VST2<0b1000, {0,1,?,?}, "16", VecListDPair, IIC_VST2,
|
|
addrmode6align64or128>, Sched<[WriteVST2]>;
|
|
def VST2d32 : VST2<0b1000, {1,0,?,?}, "32", VecListDPair, IIC_VST2,
|
|
addrmode6align64or128>, Sched<[WriteVST2]>;
|
|
|
|
def VST2q8 : VST2<0b0011, {0,0,?,?}, "8", VecListFourD, IIC_VST2x2,
|
|
addrmode6align64or128or256>, Sched<[WriteVST4]>;
|
|
def VST2q16 : VST2<0b0011, {0,1,?,?}, "16", VecListFourD, IIC_VST2x2,
|
|
addrmode6align64or128or256>, Sched<[WriteVST4]>;
|
|
def VST2q32 : VST2<0b0011, {1,0,?,?}, "32", VecListFourD, IIC_VST2x2,
|
|
addrmode6align64or128or256>, Sched<[WriteVST4]>;
|
|
|
|
def VST2q8Pseudo : VSTQQPseudo<IIC_VST2x2>, Sched<[WriteVST4]>;
|
|
def VST2q16Pseudo : VSTQQPseudo<IIC_VST2x2>, Sched<[WriteVST4]>;
|
|
def VST2q32Pseudo : VSTQQPseudo<IIC_VST2x2>, Sched<[WriteVST4]>;
|
|
|
|
// ...with address register writeback:
|
|
multiclass VST2DWB<bits<4> op11_8, bits<4> op7_4, string Dt,
|
|
RegisterOperand VdTy, Operand AddrMode> {
|
|
def _fixed : NLdSt<0, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, VdTy:$Vd), IIC_VLD1u,
|
|
"vst2", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST2]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
def _register : NLdSt<0, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm, VdTy:$Vd), IIC_VLD1u,
|
|
"vst2", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST2]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
}
|
|
multiclass VST2QWB<bits<4> op7_4, string Dt, Operand AddrMode> {
|
|
def _fixed : NLdSt<0, 0b00, 0b0011, op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, VecListFourD:$Vd), IIC_VLD1u,
|
|
"vst2", Dt, "$Vd, $Rn!",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST4]> {
|
|
let Rm = 0b1101; // NLdSt will assign to the right encoding bits.
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
def _register : NLdSt<0, 0b00, 0b0011, op7_4, (outs GPR:$wb),
|
|
(ins AddrMode:$Rn, rGPR:$Rm, VecListFourD:$Vd),
|
|
IIC_VLD1u,
|
|
"vst2", Dt, "$Vd, $Rn, $Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST4]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST2Instruction";
|
|
}
|
|
}
|
|
|
|
defm VST2d8wb : VST2DWB<0b1000, {0,0,?,?}, "8", VecListDPair,
|
|
addrmode6align64or128>;
|
|
defm VST2d16wb : VST2DWB<0b1000, {0,1,?,?}, "16", VecListDPair,
|
|
addrmode6align64or128>;
|
|
defm VST2d32wb : VST2DWB<0b1000, {1,0,?,?}, "32", VecListDPair,
|
|
addrmode6align64or128>;
|
|
|
|
defm VST2q8wb : VST2QWB<{0,0,?,?}, "8", addrmode6align64or128or256>;
|
|
defm VST2q16wb : VST2QWB<{0,1,?,?}, "16", addrmode6align64or128or256>;
|
|
defm VST2q32wb : VST2QWB<{1,0,?,?}, "32", addrmode6align64or128or256>;
|
|
|
|
def VST2q8PseudoWB_fixed : VSTQQWBfixedPseudo<IIC_VST2x2u>, Sched<[WriteVST4]>;
|
|
def VST2q16PseudoWB_fixed : VSTQQWBfixedPseudo<IIC_VST2x2u>, Sched<[WriteVST4]>;
|
|
def VST2q32PseudoWB_fixed : VSTQQWBfixedPseudo<IIC_VST2x2u>, Sched<[WriteVST4]>;
|
|
def VST2q8PseudoWB_register : VSTQQWBregisterPseudo<IIC_VST2x2u>, Sched<[WriteVST4]>;
|
|
def VST2q16PseudoWB_register : VSTQQWBregisterPseudo<IIC_VST2x2u>, Sched<[WriteVST4]>;
|
|
def VST2q32PseudoWB_register : VSTQQWBregisterPseudo<IIC_VST2x2u>, Sched<[WriteVST4]>;
|
|
|
|
// ...with double-spaced registers
|
|
def VST2b8 : VST2<0b1001, {0,0,?,?}, "8", VecListDPairSpaced, IIC_VST2,
|
|
addrmode6align64or128>;
|
|
def VST2b16 : VST2<0b1001, {0,1,?,?}, "16", VecListDPairSpaced, IIC_VST2,
|
|
addrmode6align64or128>;
|
|
def VST2b32 : VST2<0b1001, {1,0,?,?}, "32", VecListDPairSpaced, IIC_VST2,
|
|
addrmode6align64or128>;
|
|
defm VST2b8wb : VST2DWB<0b1001, {0,0,?,?}, "8", VecListDPairSpaced,
|
|
addrmode6align64or128>;
|
|
defm VST2b16wb : VST2DWB<0b1001, {0,1,?,?}, "16", VecListDPairSpaced,
|
|
addrmode6align64or128>;
|
|
defm VST2b32wb : VST2DWB<0b1001, {1,0,?,?}, "32", VecListDPairSpaced,
|
|
addrmode6align64or128>;
|
|
|
|
// VST3 : Vector Store (multiple 3-element structures)
|
|
class VST3D<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b00, op11_8, op7_4, (outs),
|
|
(ins addrmode6:$Rn, DPR:$Vd, DPR:$src2, DPR:$src3), IIC_VST3,
|
|
"vst3", Dt, "\\{$Vd, $src2, $src3\\}, $Rn", "", []>, Sched<[WriteVST3]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST3Instruction";
|
|
}
|
|
|
|
def VST3d8 : VST3D<0b0100, {0,0,0,?}, "8">;
|
|
def VST3d16 : VST3D<0b0100, {0,1,0,?}, "16">;
|
|
def VST3d32 : VST3D<0b0100, {1,0,0,?}, "32">;
|
|
|
|
def VST3d8Pseudo : VSTQQPseudo<IIC_VST3>, Sched<[WriteVST3]>;
|
|
def VST3d16Pseudo : VSTQQPseudo<IIC_VST3>, Sched<[WriteVST3]>;
|
|
def VST3d32Pseudo : VSTQQPseudo<IIC_VST3>, Sched<[WriteVST3]>;
|
|
|
|
// ...with address register writeback:
|
|
class VST3DWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$Vd, DPR:$src2, DPR:$src3), IIC_VST3u,
|
|
"vst3", Dt, "\\{$Vd, $src2, $src3\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST3]> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVLDST3Instruction";
|
|
}
|
|
|
|
def VST3d8_UPD : VST3DWB<0b0100, {0,0,0,?}, "8">;
|
|
def VST3d16_UPD : VST3DWB<0b0100, {0,1,0,?}, "16">;
|
|
def VST3d32_UPD : VST3DWB<0b0100, {1,0,0,?}, "32">;
|
|
|
|
def VST3d8Pseudo_UPD : VSTQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
def VST3d16Pseudo_UPD : VSTQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
def VST3d32Pseudo_UPD : VSTQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VST3q8 : VST3D<0b0101, {0,0,0,?}, "8">;
|
|
def VST3q16 : VST3D<0b0101, {0,1,0,?}, "16">;
|
|
def VST3q32 : VST3D<0b0101, {1,0,0,?}, "32">;
|
|
def VST3q8_UPD : VST3DWB<0b0101, {0,0,0,?}, "8">;
|
|
def VST3q16_UPD : VST3DWB<0b0101, {0,1,0,?}, "16">;
|
|
def VST3q32_UPD : VST3DWB<0b0101, {1,0,0,?}, "32">;
|
|
|
|
def VST3q8Pseudo_UPD : VSTQQQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
def VST3q16Pseudo_UPD : VSTQQQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
def VST3q32Pseudo_UPD : VSTQQQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
|
|
// ...alternate versions to be allocated odd register numbers:
|
|
def VST3q8oddPseudo : VSTQQQQPseudo<IIC_VST3>, Sched<[WriteVST3]>;
|
|
def VST3q16oddPseudo : VSTQQQQPseudo<IIC_VST3>, Sched<[WriteVST3]>;
|
|
def VST3q32oddPseudo : VSTQQQQPseudo<IIC_VST3>, Sched<[WriteVST3]>;
|
|
|
|
def VST3q8oddPseudo_UPD : VSTQQQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
def VST3q16oddPseudo_UPD : VSTQQQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
def VST3q32oddPseudo_UPD : VSTQQQQWBPseudo<IIC_VST3u>, Sched<[WriteVST3]>;
|
|
|
|
// VST4 : Vector Store (multiple 4-element structures)
|
|
class VST4D<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b00, op11_8, op7_4, (outs),
|
|
(ins addrmode6:$Rn, DPR:$Vd, DPR:$src2, DPR:$src3, DPR:$src4),
|
|
IIC_VST4, "vst4", Dt, "\\{$Vd, $src2, $src3, $src4\\}, $Rn",
|
|
"", []>, Sched<[WriteVST4]> {
|
|
let Rm = 0b1111;
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST4Instruction";
|
|
}
|
|
|
|
def VST4d8 : VST4D<0b0000, {0,0,?,?}, "8">;
|
|
def VST4d16 : VST4D<0b0000, {0,1,?,?}, "16">;
|
|
def VST4d32 : VST4D<0b0000, {1,0,?,?}, "32">;
|
|
|
|
def VST4d8Pseudo : VSTQQPseudo<IIC_VST4>, Sched<[WriteVST4]>;
|
|
def VST4d16Pseudo : VSTQQPseudo<IIC_VST4>, Sched<[WriteVST4]>;
|
|
def VST4d32Pseudo : VSTQQPseudo<IIC_VST4>, Sched<[WriteVST4]>;
|
|
|
|
// ...with address register writeback:
|
|
class VST4DWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdSt<0, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$Vd, DPR:$src2, DPR:$src3, DPR:$src4), IIC_VST4u,
|
|
"vst4", Dt, "\\{$Vd, $src2, $src3, $src4\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []>, Sched<[WriteVST4]> {
|
|
let Inst{5-4} = Rn{5-4};
|
|
let DecoderMethod = "DecodeVLDST4Instruction";
|
|
}
|
|
|
|
def VST4d8_UPD : VST4DWB<0b0000, {0,0,?,?}, "8">;
|
|
def VST4d16_UPD : VST4DWB<0b0000, {0,1,?,?}, "16">;
|
|
def VST4d32_UPD : VST4DWB<0b0000, {1,0,?,?}, "32">;
|
|
|
|
def VST4d8Pseudo_UPD : VSTQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
def VST4d16Pseudo_UPD : VSTQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
def VST4d32Pseudo_UPD : VSTQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VST4q8 : VST4D<0b0001, {0,0,?,?}, "8">;
|
|
def VST4q16 : VST4D<0b0001, {0,1,?,?}, "16">;
|
|
def VST4q32 : VST4D<0b0001, {1,0,?,?}, "32">;
|
|
def VST4q8_UPD : VST4DWB<0b0001, {0,0,?,?}, "8">;
|
|
def VST4q16_UPD : VST4DWB<0b0001, {0,1,?,?}, "16">;
|
|
def VST4q32_UPD : VST4DWB<0b0001, {1,0,?,?}, "32">;
|
|
|
|
def VST4q8Pseudo_UPD : VSTQQQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
def VST4q16Pseudo_UPD : VSTQQQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
def VST4q32Pseudo_UPD : VSTQQQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
|
|
// ...alternate versions to be allocated odd register numbers:
|
|
def VST4q8oddPseudo : VSTQQQQPseudo<IIC_VST4>, Sched<[WriteVST4]>;
|
|
def VST4q16oddPseudo : VSTQQQQPseudo<IIC_VST4>, Sched<[WriteVST4]>;
|
|
def VST4q32oddPseudo : VSTQQQQPseudo<IIC_VST4>, Sched<[WriteVST4]>;
|
|
|
|
def VST4q8oddPseudo_UPD : VSTQQQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
def VST4q16oddPseudo_UPD : VSTQQQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
def VST4q32oddPseudo_UPD : VSTQQQQWBPseudo<IIC_VST4u>, Sched<[WriteVST4]>;
|
|
|
|
} // mayStore = 1, hasSideEffects = 0, hasExtraSrcRegAllocReq = 1
|
|
|
|
// Classes for VST*LN pseudo-instructions with multi-register operands.
|
|
// These are expanded to real instructions after register allocation.
|
|
class VSTQLNPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs), (ins addrmode6:$addr, QPR:$src, nohash_imm:$lane),
|
|
itin, "">;
|
|
class VSTQLNWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QPR:$src,
|
|
nohash_imm:$lane), itin, "$addr.addr = $wb">;
|
|
class VSTQQLNPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs), (ins addrmode6:$addr, QQPR:$src, nohash_imm:$lane),
|
|
itin, "">;
|
|
class VSTQQLNWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QQPR:$src,
|
|
nohash_imm:$lane), itin, "$addr.addr = $wb">;
|
|
class VSTQQQQLNPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs), (ins addrmode6:$addr, QQQQPR:$src, nohash_imm:$lane),
|
|
itin, "">;
|
|
class VSTQQQQLNWBPseudo<InstrItinClass itin>
|
|
: PseudoNLdSt<(outs GPR:$wb),
|
|
(ins addrmode6:$addr, am6offset:$offset, QQQQPR:$src,
|
|
nohash_imm:$lane), itin, "$addr.addr = $wb">;
|
|
|
|
// VST1LN : Vector Store (single element from one lane)
|
|
class VST1LN<bits<4> op11_8, bits<4> op7_4, string Dt, ValueType Ty,
|
|
PatFrag StoreOp, SDNode ExtractOp, Operand AddrMode>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs),
|
|
(ins AddrMode:$Rn, DPR:$Vd, nohash_imm:$lane),
|
|
IIC_VST1ln, "vst1", Dt, "\\{$Vd[$lane]\\}, $Rn", "",
|
|
[(StoreOp (ExtractOp (Ty DPR:$Vd), imm:$lane), AddrMode:$Rn)]>,
|
|
Sched<[WriteVST1]> {
|
|
let Rm = 0b1111;
|
|
let DecoderMethod = "DecodeVST1LN";
|
|
}
|
|
class VST1QLNPseudo<ValueType Ty, PatFrag StoreOp, SDNode ExtractOp>
|
|
: VSTQLNPseudo<IIC_VST1ln>, Sched<[WriteVST1]> {
|
|
let Pattern = [(StoreOp (ExtractOp (Ty QPR:$src), imm:$lane),
|
|
addrmode6:$addr)];
|
|
}
|
|
|
|
def VST1LNd8 : VST1LN<0b0000, {?,?,?,0}, "8", v8i8, truncstorei8,
|
|
NEONvgetlaneu, addrmode6> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST1LNd16 : VST1LN<0b0100, {?,?,0,?}, "16", v4i16, truncstorei16,
|
|
NEONvgetlaneu, addrmode6> {
|
|
let Inst{7-6} = lane{1-0};
|
|
let Inst{4} = Rn{4};
|
|
}
|
|
|
|
def VST1LNd32 : VST1LN<0b1000, {?,0,?,?}, "32", v2i32, store, extractelt,
|
|
addrmode6oneL32> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5-4} = Rn{5-4};
|
|
}
|
|
|
|
def VST1LNq8Pseudo : VST1QLNPseudo<v16i8, truncstorei8, NEONvgetlaneu>;
|
|
def VST1LNq16Pseudo : VST1QLNPseudo<v8i16, truncstorei16, NEONvgetlaneu>;
|
|
def VST1LNq32Pseudo : VST1QLNPseudo<v4i32, store, extractelt>;
|
|
|
|
def : Pat<(store (extractelt (v2f32 DPR:$src), imm:$lane), addrmode6:$addr),
|
|
(VST1LNd32 addrmode6:$addr, DPR:$src, imm:$lane)>;
|
|
def : Pat<(store (extractelt (v4f32 QPR:$src), imm:$lane), addrmode6:$addr),
|
|
(VST1LNq32Pseudo addrmode6:$addr, QPR:$src, imm:$lane)>;
|
|
|
|
// ...with address register writeback:
|
|
class VST1LNWB<bits<4> op11_8, bits<4> op7_4, string Dt, ValueType Ty,
|
|
PatFrag StoreOp, SDNode ExtractOp, Operand AdrMode>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins AdrMode:$Rn, am6offset:$Rm,
|
|
DPR:$Vd, nohash_imm:$lane), IIC_VST1lnu, "vst1", Dt,
|
|
"\\{$Vd[$lane]\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb",
|
|
[(set GPR:$wb, (StoreOp (ExtractOp (Ty DPR:$Vd), imm:$lane),
|
|
AdrMode:$Rn, am6offset:$Rm))]>,
|
|
Sched<[WriteVST1]> {
|
|
let DecoderMethod = "DecodeVST1LN";
|
|
}
|
|
class VST1QLNWBPseudo<ValueType Ty, PatFrag StoreOp, SDNode ExtractOp>
|
|
: VSTQLNWBPseudo<IIC_VST1lnu>, Sched<[WriteVST1]> {
|
|
let Pattern = [(set GPR:$wb, (StoreOp (ExtractOp (Ty QPR:$src), imm:$lane),
|
|
addrmode6:$addr, am6offset:$offset))];
|
|
}
|
|
|
|
def VST1LNd8_UPD : VST1LNWB<0b0000, {?,?,?,0}, "8", v8i8, post_truncsti8,
|
|
NEONvgetlaneu, addrmode6> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST1LNd16_UPD : VST1LNWB<0b0100, {?,?,0,?}, "16", v4i16, post_truncsti16,
|
|
NEONvgetlaneu, addrmode6> {
|
|
let Inst{7-6} = lane{1-0};
|
|
let Inst{4} = Rn{4};
|
|
}
|
|
def VST1LNd32_UPD : VST1LNWB<0b1000, {?,0,?,?}, "32", v2i32, post_store,
|
|
extractelt, addrmode6oneL32> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5-4} = Rn{5-4};
|
|
}
|
|
|
|
def VST1LNq8Pseudo_UPD : VST1QLNWBPseudo<v16i8, post_truncsti8, NEONvgetlaneu>;
|
|
def VST1LNq16Pseudo_UPD : VST1QLNWBPseudo<v8i16, post_truncsti16,NEONvgetlaneu>;
|
|
def VST1LNq32Pseudo_UPD : VST1QLNWBPseudo<v4i32, post_store, extractelt>;
|
|
|
|
let mayStore = 1, hasSideEffects = 0, hasExtraSrcRegAllocReq = 1 in {
|
|
|
|
// VST2LN : Vector Store (single 2-element structure from one lane)
|
|
class VST2LN<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs),
|
|
(ins addrmode6:$Rn, DPR:$Vd, DPR:$src2, nohash_imm:$lane),
|
|
IIC_VST2ln, "vst2", Dt, "\\{$Vd[$lane], $src2[$lane]\\}, $Rn",
|
|
"", []>, Sched<[WriteVST1]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVST2LN";
|
|
}
|
|
|
|
def VST2LNd8 : VST2LN<0b0001, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST2LNd16 : VST2LN<0b0101, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST2LNd32 : VST2LN<0b1001, {?,0,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VST2LNd8Pseudo : VSTQLNPseudo<IIC_VST2ln>, Sched<[WriteVST1]>;
|
|
def VST2LNd16Pseudo : VSTQLNPseudo<IIC_VST2ln>, Sched<[WriteVST1]>;
|
|
def VST2LNd32Pseudo : VSTQLNPseudo<IIC_VST2ln>, Sched<[WriteVST1]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VST2LNq16 : VST2LN<0b0101, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
let Inst{4} = Rn{4};
|
|
}
|
|
def VST2LNq32 : VST2LN<0b1001, {?,1,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{4} = Rn{4};
|
|
}
|
|
|
|
def VST2LNq16Pseudo : VSTQQLNPseudo<IIC_VST2ln>, Sched<[WriteVST1]>;
|
|
def VST2LNq32Pseudo : VSTQQLNPseudo<IIC_VST2ln>, Sched<[WriteVST1]>;
|
|
|
|
// ...with address register writeback:
|
|
class VST2LNWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$Vd, DPR:$src2, nohash_imm:$lane), IIC_VST2lnu, "vst2", Dt,
|
|
"\\{$Vd[$lane], $src2[$lane]\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVST2LN";
|
|
}
|
|
|
|
def VST2LNd8_UPD : VST2LNWB<0b0001, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST2LNd16_UPD : VST2LNWB<0b0101, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST2LNd32_UPD : VST2LNWB<0b1001, {?,0,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VST2LNd8Pseudo_UPD : VSTQLNWBPseudo<IIC_VST2lnu>, Sched<[WriteVST1]>;
|
|
def VST2LNd16Pseudo_UPD : VSTQLNWBPseudo<IIC_VST2lnu>, Sched<[WriteVST1]>;
|
|
def VST2LNd32Pseudo_UPD : VSTQLNWBPseudo<IIC_VST2lnu>, Sched<[WriteVST1]>;
|
|
|
|
def VST2LNq16_UPD : VST2LNWB<0b0101, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST2LNq32_UPD : VST2LNWB<0b1001, {?,1,0,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VST2LNq16Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST2lnu>, Sched<[WriteVST1]>;
|
|
def VST2LNq32Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST2lnu>, Sched<[WriteVST1]>;
|
|
|
|
// VST3LN : Vector Store (single 3-element structure from one lane)
|
|
class VST3LN<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs),
|
|
(ins addrmode6:$Rn, DPR:$Vd, DPR:$src2, DPR:$src3,
|
|
nohash_imm:$lane), IIC_VST3ln, "vst3", Dt,
|
|
"\\{$Vd[$lane], $src2[$lane], $src3[$lane]\\}, $Rn", "", []>,
|
|
Sched<[WriteVST2]> {
|
|
let Rm = 0b1111;
|
|
let DecoderMethod = "DecodeVST3LN";
|
|
}
|
|
|
|
def VST3LNd8 : VST3LN<0b0010, {?,?,?,0}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST3LNd16 : VST3LN<0b0110, {?,?,0,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST3LNd32 : VST3LN<0b1010, {?,0,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VST3LNd8Pseudo : VSTQQLNPseudo<IIC_VST3ln>, Sched<[WriteVST2]>;
|
|
def VST3LNd16Pseudo : VSTQQLNPseudo<IIC_VST3ln>, Sched<[WriteVST2]>;
|
|
def VST3LNd32Pseudo : VSTQQLNPseudo<IIC_VST3ln>, Sched<[WriteVST2]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VST3LNq16 : VST3LN<0b0110, {?,?,1,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST3LNq32 : VST3LN<0b1010, {?,1,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VST3LNq16Pseudo : VSTQQQQLNPseudo<IIC_VST3ln>;
|
|
def VST3LNq32Pseudo : VSTQQQQLNPseudo<IIC_VST3ln>;
|
|
|
|
// ...with address register writeback:
|
|
class VST3LNWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$Vd, DPR:$src2, DPR:$src3, nohash_imm:$lane),
|
|
IIC_VST3lnu, "vst3", Dt,
|
|
"\\{$Vd[$lane], $src2[$lane], $src3[$lane]\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []> {
|
|
let DecoderMethod = "DecodeVST3LN";
|
|
}
|
|
|
|
def VST3LNd8_UPD : VST3LNWB<0b0010, {?,?,?,0}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST3LNd16_UPD : VST3LNWB<0b0110, {?,?,0,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST3LNd32_UPD : VST3LNWB<0b1010, {?,0,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VST3LNd8Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST3lnu>, Sched<[WriteVST2]>;
|
|
def VST3LNd16Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST3lnu>, Sched<[WriteVST2]>;
|
|
def VST3LNd32Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST3lnu>, Sched<[WriteVST2]>;
|
|
|
|
def VST3LNq16_UPD : VST3LNWB<0b0110, {?,?,1,0}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST3LNq32_UPD : VST3LNWB<0b1010, {?,1,0,0}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
}
|
|
|
|
def VST3LNq16Pseudo_UPD : VSTQQQQLNWBPseudo<IIC_VST3lnu>, Sched<[WriteVST2]>;
|
|
def VST3LNq32Pseudo_UPD : VSTQQQQLNWBPseudo<IIC_VST3lnu>, Sched<[WriteVST2]>;
|
|
|
|
// VST4LN : Vector Store (single 4-element structure from one lane)
|
|
class VST4LN<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs),
|
|
(ins addrmode6:$Rn, DPR:$Vd, DPR:$src2, DPR:$src3, DPR:$src4,
|
|
nohash_imm:$lane), IIC_VST4ln, "vst4", Dt,
|
|
"\\{$Vd[$lane], $src2[$lane], $src3[$lane], $src4[$lane]\\}, $Rn",
|
|
"", []>, Sched<[WriteVST2]> {
|
|
let Rm = 0b1111;
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVST4LN";
|
|
}
|
|
|
|
def VST4LNd8 : VST4LN<0b0011, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST4LNd16 : VST4LN<0b0111, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST4LNd32 : VST4LN<0b1011, {?,0,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VST4LNd8Pseudo : VSTQQLNPseudo<IIC_VST4ln>, Sched<[WriteVST2]>;
|
|
def VST4LNd16Pseudo : VSTQQLNPseudo<IIC_VST4ln>, Sched<[WriteVST2]>;
|
|
def VST4LNd32Pseudo : VSTQQLNPseudo<IIC_VST4ln>, Sched<[WriteVST2]>;
|
|
|
|
// ...with double-spaced registers:
|
|
def VST4LNq16 : VST4LN<0b0111, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST4LNq32 : VST4LN<0b1011, {?,1,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VST4LNq16Pseudo : VSTQQQQLNPseudo<IIC_VST4ln>, Sched<[WriteVST2]>;
|
|
def VST4LNq32Pseudo : VSTQQQQLNPseudo<IIC_VST4ln>, Sched<[WriteVST2]>;
|
|
|
|
// ...with address register writeback:
|
|
class VST4LNWB<bits<4> op11_8, bits<4> op7_4, string Dt>
|
|
: NLdStLn<1, 0b00, op11_8, op7_4, (outs GPR:$wb),
|
|
(ins addrmode6:$Rn, am6offset:$Rm,
|
|
DPR:$Vd, DPR:$src2, DPR:$src3, DPR:$src4, nohash_imm:$lane),
|
|
IIC_VST4lnu, "vst4", Dt,
|
|
"\\{$Vd[$lane], $src2[$lane], $src3[$lane], $src4[$lane]\\}, $Rn$Rm",
|
|
"$Rn.addr = $wb", []> {
|
|
let Inst{4} = Rn{4};
|
|
let DecoderMethod = "DecodeVST4LN";
|
|
}
|
|
|
|
def VST4LNd8_UPD : VST4LNWB<0b0011, {?,?,?,?}, "8"> {
|
|
let Inst{7-5} = lane{2-0};
|
|
}
|
|
def VST4LNd16_UPD : VST4LNWB<0b0111, {?,?,0,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST4LNd32_UPD : VST4LNWB<0b1011, {?,0,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VST4LNd8Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST4lnu>, Sched<[WriteVST2]>;
|
|
def VST4LNd16Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST4lnu>, Sched<[WriteVST2]>;
|
|
def VST4LNd32Pseudo_UPD : VSTQQLNWBPseudo<IIC_VST4lnu>, Sched<[WriteVST2]>;
|
|
|
|
def VST4LNq16_UPD : VST4LNWB<0b0111, {?,?,1,?}, "16"> {
|
|
let Inst{7-6} = lane{1-0};
|
|
}
|
|
def VST4LNq32_UPD : VST4LNWB<0b1011, {?,1,?,?}, "32"> {
|
|
let Inst{7} = lane{0};
|
|
let Inst{5} = Rn{5};
|
|
}
|
|
|
|
def VST4LNq16Pseudo_UPD : VSTQQQQLNWBPseudo<IIC_VST4lnu>, Sched<[WriteVST2]>;
|
|
def VST4LNq32Pseudo_UPD : VSTQQQQLNWBPseudo<IIC_VST4lnu>, Sched<[WriteVST2]>;
|
|
|
|
} // mayStore = 1, hasSideEffects = 0, hasExtraSrcRegAllocReq = 1
|
|
|
|
// Use vld1/vst1 for unaligned f64 load / store
|
|
def : Pat<(f64 (hword_alignedload addrmode6:$addr)),
|
|
(VLD1d16 addrmode6:$addr)>, Requires<[IsLE]>;
|
|
def : Pat<(hword_alignedstore (f64 DPR:$value), addrmode6:$addr),
|
|
(VST1d16 addrmode6:$addr, DPR:$value)>, Requires<[IsLE]>;
|
|
def : Pat<(f64 (byte_alignedload addrmode6:$addr)),
|
|
(VLD1d8 addrmode6:$addr)>, Requires<[IsLE]>;
|
|
def : Pat<(byte_alignedstore (f64 DPR:$value), addrmode6:$addr),
|
|
(VST1d8 addrmode6:$addr, DPR:$value)>, Requires<[IsLE]>;
|
|
def : Pat<(f64 (non_word_alignedload addrmode6:$addr)),
|
|
(VLD1d64 addrmode6:$addr)>, Requires<[IsBE]>;
|
|
def : Pat<(non_word_alignedstore (f64 DPR:$value), addrmode6:$addr),
|
|
(VST1d64 addrmode6:$addr, DPR:$value)>, Requires<[IsBE]>;
|
|
|
|
// Use vld1/vst1 for Q and QQ. Also use them for unaligned v2f64
|
|
// load / store if it's legal.
|
|
def : Pat<(v2f64 (dword_alignedload addrmode6:$addr)),
|
|
(VLD1q64 addrmode6:$addr)>;
|
|
def : Pat<(dword_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
|
|
(VST1q64 addrmode6:$addr, QPR:$value)>;
|
|
def : Pat<(v2f64 (word_alignedload addrmode6:$addr)),
|
|
(VLD1q32 addrmode6:$addr)>, Requires<[IsLE]>;
|
|
def : Pat<(word_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
|
|
(VST1q32 addrmode6:$addr, QPR:$value)>, Requires<[IsLE]>;
|
|
def : Pat<(v2f64 (hword_alignedload addrmode6:$addr)),
|
|
(VLD1q16 addrmode6:$addr)>, Requires<[IsLE]>;
|
|
def : Pat<(hword_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
|
|
(VST1q16 addrmode6:$addr, QPR:$value)>, Requires<[IsLE]>;
|
|
def : Pat<(v2f64 (byte_alignedload addrmode6:$addr)),
|
|
(VLD1q8 addrmode6:$addr)>, Requires<[IsLE]>;
|
|
def : Pat<(byte_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
|
|
(VST1q8 addrmode6:$addr, QPR:$value)>, Requires<[IsLE]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// NEON pattern fragments
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Extract D sub-registers of Q registers.
|
|
def DSubReg_i8_reg : SDNodeXForm<imm, [{
|
|
assert(ARM::dsub_7 == ARM::dsub_0+7 && "Unexpected subreg numbering");
|
|
return CurDAG->getTargetConstant(ARM::dsub_0 + N->getZExtValue()/8, SDLoc(N),
|
|
MVT::i32);
|
|
}]>;
|
|
def DSubReg_i16_reg : SDNodeXForm<imm, [{
|
|
assert(ARM::dsub_7 == ARM::dsub_0+7 && "Unexpected subreg numbering");
|
|
return CurDAG->getTargetConstant(ARM::dsub_0 + N->getZExtValue()/4, SDLoc(N),
|
|
MVT::i32);
|
|
}]>;
|
|
def DSubReg_i32_reg : SDNodeXForm<imm, [{
|
|
assert(ARM::dsub_7 == ARM::dsub_0+7 && "Unexpected subreg numbering");
|
|
return CurDAG->getTargetConstant(ARM::dsub_0 + N->getZExtValue()/2, SDLoc(N),
|
|
MVT::i32);
|
|
}]>;
|
|
def DSubReg_f64_reg : SDNodeXForm<imm, [{
|
|
assert(ARM::dsub_7 == ARM::dsub_0+7 && "Unexpected subreg numbering");
|
|
return CurDAG->getTargetConstant(ARM::dsub_0 + N->getZExtValue(), SDLoc(N),
|
|
MVT::i32);
|
|
}]>;
|
|
|
|
// Extract S sub-registers of Q/D registers.
|
|
def SSubReg_f32_reg : SDNodeXForm<imm, [{
|
|
assert(ARM::ssub_3 == ARM::ssub_0+3 && "Unexpected subreg numbering");
|
|
return CurDAG->getTargetConstant(ARM::ssub_0 + N->getZExtValue(), SDLoc(N),
|
|
MVT::i32);
|
|
}]>;
|
|
|
|
// Translate lane numbers from Q registers to D subregs.
|
|
def SubReg_i8_lane : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(N->getZExtValue() & 7, SDLoc(N), MVT::i32);
|
|
}]>;
|
|
def SubReg_i16_lane : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(N->getZExtValue() & 3, SDLoc(N), MVT::i32);
|
|
}]>;
|
|
def SubReg_i32_lane : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(N->getZExtValue() & 1, SDLoc(N), MVT::i32);
|
|
}]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Instruction Classes
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Basic 2-register operations: double- and quad-register.
|
|
class N2VD<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4, string OpcodeStr,
|
|
string Dt, ValueType ResTy, ValueType OpTy, SDNode OpNode>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 0, op4, (outs DPR:$Vd),
|
|
(ins DPR:$Vm), IIC_VUNAD, OpcodeStr, Dt,"$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (ResTy (OpNode (OpTy DPR:$Vm))))]>;
|
|
class N2VQ<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4, string OpcodeStr,
|
|
string Dt, ValueType ResTy, ValueType OpTy, SDNode OpNode>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 1, op4, (outs QPR:$Vd),
|
|
(ins QPR:$Vm), IIC_VUNAQ, OpcodeStr, Dt,"$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (ResTy (OpNode (OpTy QPR:$Vm))))]>;
|
|
|
|
// Basic 2-register intrinsics, both double- and quad-register.
|
|
class N2VDInt<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 0, op4, (outs DPR:$Vd),
|
|
(ins DPR:$Vm), itin, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vm))))]>;
|
|
class N2VQInt<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 1, op4, (outs QPR:$Vd),
|
|
(ins QPR:$Vm), itin, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm))))]>;
|
|
|
|
// Same as above, but not predicated.
|
|
class N2VDIntnp<bits<2> op19_18, bits<2> op17_16, bits<3> op10_8, bit op7,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2Vnp<op19_18, op17_16, op10_8, op7, 0, (outs DPR:$Vd), (ins DPR:$Vm),
|
|
itin, OpcodeStr, Dt,
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vm))))]>;
|
|
|
|
class N2VQIntnp<bits<2> op19_18, bits<2> op17_16, bits<3> op10_8, bit op7,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2Vnp<op19_18, op17_16, op10_8, op7, 1, (outs QPR:$Vd), (ins QPR:$Vm),
|
|
itin, OpcodeStr, Dt,
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm))))]>;
|
|
|
|
// Similar to NV2VQIntnp with some more encoding bits exposed (crypto).
|
|
class N2VQIntXnp<bits<2> op19_18, bits<2> op17_16, bits<3> op10_8, bit op6,
|
|
bit op7, InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2Vnp<op19_18, op17_16, op10_8, op7, op6, (outs QPR:$Vd), (ins QPR:$Vm),
|
|
itin, OpcodeStr, Dt,
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm))))]>;
|
|
|
|
// Same as N2VQIntXnp but with Vd as a src register.
|
|
class N2VQIntX2np<bits<2> op19_18, bits<2> op17_16, bits<3> op10_8, bit op6,
|
|
bit op7, InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2Vnp<op19_18, op17_16, op10_8, op7, op6,
|
|
(outs QPR:$Vd), (ins QPR:$src, QPR:$Vm),
|
|
itin, OpcodeStr, Dt,
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$src), (OpTy QPR:$Vm))))]> {
|
|
let Constraints = "$src = $Vd";
|
|
}
|
|
|
|
// Narrow 2-register operations.
|
|
class N2VN<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op6, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyD, ValueType TyQ, SDNode OpNode>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, op6, op4, (outs DPR:$Vd),
|
|
(ins QPR:$Vm), itin, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (TyD (OpNode (TyQ QPR:$Vm))))]>;
|
|
|
|
// Narrow 2-register intrinsics.
|
|
class N2VNInt<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op6, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyD, ValueType TyQ, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, op6, op4, (outs DPR:$Vd),
|
|
(ins QPR:$Vm), itin, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (TyD (IntOp (TyQ QPR:$Vm))))]>;
|
|
|
|
// Long 2-register operations (currently only used for VMOVL).
|
|
class N2VL<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op6, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode OpNode>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, op6, op4, (outs QPR:$Vd),
|
|
(ins DPR:$Vm), itin, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (TyQ (OpNode (TyD DPR:$Vm))))]>;
|
|
|
|
// Long 2-register intrinsics.
|
|
class N2VLInt<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op6, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, op6, op4, (outs QPR:$Vd),
|
|
(ins DPR:$Vm), itin, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (TyQ (IntOp (TyD DPR:$Vm))))]>;
|
|
|
|
// 2-register shuffles (VTRN/VZIP/VUZP), both double- and quad-register.
|
|
class N2VDShuffle<bits<2> op19_18, bits<5> op11_7, string OpcodeStr, string Dt>
|
|
: N2V<0b11, 0b11, op19_18, 0b10, op11_7, 0, 0, (outs DPR:$Vd, DPR:$Vm),
|
|
(ins DPR:$src1, DPR:$src2), IIC_VPERMD,
|
|
OpcodeStr, Dt, "$Vd, $Vm",
|
|
"$src1 = $Vd, $src2 = $Vm", []>;
|
|
class N2VQShuffle<bits<2> op19_18, bits<5> op11_7,
|
|
InstrItinClass itin, string OpcodeStr, string Dt>
|
|
: N2V<0b11, 0b11, op19_18, 0b10, op11_7, 1, 0, (outs QPR:$Vd, QPR:$Vm),
|
|
(ins QPR:$src1, QPR:$src2), itin, OpcodeStr, Dt, "$Vd, $Vm",
|
|
"$src1 = $Vd, $src2 = $Vm", []>;
|
|
|
|
// Basic 3-register operations: double- and quad-register.
|
|
class N3VD<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDNode OpNode, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set DPR:$Vd, (ResTy (OpNode (OpTy DPR:$Vn), (OpTy DPR:$Vm))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = Commutable;
|
|
}
|
|
// Same as N3VD but no data type.
|
|
class N3VDX<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr,
|
|
ValueType ResTy, ValueType OpTy,
|
|
SDNode OpNode, bit Commutable>
|
|
: N3VX<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, "$Vd, $Vn, $Vm", "",
|
|
[(set DPR:$Vd, (ResTy (OpNode (OpTy DPR:$Vn), (OpTy DPR:$Vm))))]>{
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
class N3VDSL<bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType Ty, SDNode ShOp>
|
|
: N3VLane32<0, 1, op21_20, op11_8, 1, 0,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (Ty DPR:$Vd),
|
|
(Ty (ShOp (Ty DPR:$Vn),
|
|
(Ty (NEONvduplane (Ty DPR_VFP2:$Vm),imm:$lane)))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = 0;
|
|
}
|
|
class N3VDSL16<bits<2> op21_20, bits<4> op11_8,
|
|
string OpcodeStr, string Dt, ValueType Ty, SDNode ShOp>
|
|
: N3VLane16<0, 1, op21_20, op11_8, 1, 0,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, IIC_VMULi16D, OpcodeStr, Dt,"$Vd, $Vn, $Vm$lane","",
|
|
[(set (Ty DPR:$Vd),
|
|
(Ty (ShOp (Ty DPR:$Vn),
|
|
(Ty (NEONvduplane (Ty DPR_8:$Vm), imm:$lane)))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = 0;
|
|
}
|
|
|
|
class N3VQ<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDNode OpNode, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, QPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (ResTy (OpNode (OpTy QPR:$Vn), (OpTy QPR:$Vm))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = Commutable;
|
|
}
|
|
class N3VQX<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr,
|
|
ValueType ResTy, ValueType OpTy, SDNode OpNode, bit Commutable>
|
|
: N3VX<op24, op23, op21_20, op11_8, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, QPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (ResTy (OpNode (OpTy QPR:$Vn), (OpTy QPR:$Vm))))]>{
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = Commutable;
|
|
}
|
|
class N3VQSL<bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDNode ShOp>
|
|
: N3VLane32<1, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (ShOp (ResTy QPR:$Vn),
|
|
(ResTy (NEONvduplane (OpTy DPR_VFP2:$Vm),
|
|
imm:$lane)))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = 0;
|
|
}
|
|
class N3VQSL16<bits<2> op21_20, bits<4> op11_8, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDNode ShOp>
|
|
: N3VLane16<1, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, IIC_VMULi16Q, OpcodeStr, Dt,"$Vd, $Vn, $Vm$lane", "",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (ShOp (ResTy QPR:$Vn),
|
|
(ResTy (NEONvduplane (OpTy DPR_8:$Vm),
|
|
imm:$lane)))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = 0;
|
|
}
|
|
|
|
// Basic 3-register intrinsics, both double- and quad-register.
|
|
class N3VDInt<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
Format f, InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR:$Vm), f, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vn), (OpTy DPR:$Vm))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
class N3VDIntnp<bits<5> op27_23, bits<2> op21_20, bits<4> op11_8, bit op6,
|
|
bit op4, Format f, InstrItinClass itin, string OpcodeStr,
|
|
string Dt, ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator IntOp, bit Commutable>
|
|
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin, OpcodeStr, Dt,
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vn), (OpTy DPR:$Vm))))]>;
|
|
|
|
class N3VDIntSL<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt, ValueType Ty, SDPatternOperator IntOp>
|
|
: N3VLane32<0, 1, op21_20, op11_8, 1, 0,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (Ty DPR:$Vd),
|
|
(Ty (IntOp (Ty DPR:$Vn),
|
|
(Ty (NEONvduplane (Ty DPR_VFP2:$Vm),
|
|
imm:$lane)))))]> {
|
|
let isCommutable = 0;
|
|
}
|
|
|
|
class N3VDIntSL16<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt, ValueType Ty, SDPatternOperator IntOp>
|
|
: N3VLane16<0, 1, op21_20, op11_8, 1, 0,
|
|
(outs DPR:$Vd), (ins DPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (Ty DPR:$Vd),
|
|
(Ty (IntOp (Ty DPR:$Vn),
|
|
(Ty (NEONvduplane (Ty DPR_8:$Vm), imm:$lane)))))]> {
|
|
let isCommutable = 0;
|
|
}
|
|
class N3VDIntSh<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
Format f, InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm, DPR:$Vn), f, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $Vn", "",
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vm), (OpTy DPR:$Vn))))]> {
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd";
|
|
let isCommutable = 0;
|
|
}
|
|
|
|
class N3VQInt<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
Format f, InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, QPR:$Vm), f, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vn), (OpTy QPR:$Vm))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
class N3VQIntnp<bits<5> op27_23, bits<2> op21_20, bits<4> op11_8, bit op6,
|
|
bit op4, Format f, InstrItinClass itin, string OpcodeStr,
|
|
string Dt, ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator IntOp, bit Commutable>
|
|
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, QPR:$Vm), f, itin, OpcodeStr, Dt,
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vn), (OpTy QPR:$Vm))))]>;
|
|
|
|
// Same as N3VQIntnp but with Vd as a src register.
|
|
class N3VQInt3np<bits<5> op27_23, bits<2> op21_20, bits<4> op11_8, bit op6,
|
|
bit op4, Format f, InstrItinClass itin, string OpcodeStr,
|
|
string Dt, ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator IntOp, bit Commutable>
|
|
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src, QPR:$Vn, QPR:$Vm),
|
|
f, itin, OpcodeStr, Dt,
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$src), (OpTy QPR:$Vn),
|
|
(OpTy QPR:$Vm))))]> {
|
|
let Constraints = "$src = $Vd";
|
|
}
|
|
|
|
class N3VQIntSL<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3VLane32<1, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (IntOp (ResTy QPR:$Vn),
|
|
(ResTy (NEONvduplane (OpTy DPR_VFP2:$Vm),
|
|
imm:$lane)))))]> {
|
|
let isCommutable = 0;
|
|
}
|
|
class N3VQIntSL16<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3VLane16<1, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (IntOp (ResTy QPR:$Vn),
|
|
(ResTy (NEONvduplane (OpTy DPR_8:$Vm),
|
|
imm:$lane)))))]> {
|
|
let isCommutable = 0;
|
|
}
|
|
class N3VQIntSh<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
Format f, InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3V<op24, op23, op21_20, op11_8, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm, QPR:$Vn), f, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $Vn", "",
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm), (OpTy QPR:$Vn))))]> {
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd";
|
|
let isCommutable = 0;
|
|
}
|
|
|
|
// Multiply-Add/Sub operations: double- and quad-register.
|
|
class N3VDMulOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType Ty, SDPatternOperator MulOp, SDPatternOperator OpNode>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set DPR:$Vd, (Ty (OpNode DPR:$src1,
|
|
(Ty (MulOp DPR:$Vn, DPR:$Vm)))))]>;
|
|
|
|
class N3VDMulOpSL<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt,
|
|
ValueType Ty, SDPatternOperator MulOp, SDPatternOperator ShOp>
|
|
: N3VLane32<0, 1, op21_20, op11_8, 1, 0,
|
|
(outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set (Ty DPR:$Vd),
|
|
(Ty (ShOp (Ty DPR:$src1),
|
|
(Ty (MulOp DPR:$Vn,
|
|
(Ty (NEONvduplane (Ty DPR_VFP2:$Vm),
|
|
imm:$lane)))))))]>;
|
|
class N3VDMulOpSL16<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt,
|
|
ValueType Ty, SDPatternOperator MulOp, SDPatternOperator ShOp>
|
|
: N3VLane16<0, 1, op21_20, op11_8, 1, 0,
|
|
(outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set (Ty DPR:$Vd),
|
|
(Ty (ShOp (Ty DPR:$src1),
|
|
(Ty (MulOp DPR:$Vn,
|
|
(Ty (NEONvduplane (Ty DPR_8:$Vm),
|
|
imm:$lane)))))))]>;
|
|
|
|
class N3VQMulOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt, ValueType Ty,
|
|
SDPatternOperator MulOp, SDPatternOperator OpNode>
|
|
: N3V<op24, op23, op21_20, op11_8, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src1, QPR:$Vn, QPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (Ty (OpNode QPR:$src1,
|
|
(Ty (MulOp QPR:$Vn, QPR:$Vm)))))]>;
|
|
class N3VQMulOpSL<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt, ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator MulOp, SDPatternOperator ShOp>
|
|
: N3VLane32<1, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (ShOp (ResTy QPR:$src1),
|
|
(ResTy (MulOp QPR:$Vn,
|
|
(ResTy (NEONvduplane (OpTy DPR_VFP2:$Vm),
|
|
imm:$lane)))))))]>;
|
|
class N3VQMulOpSL16<bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator MulOp, SDPatternOperator ShOp>
|
|
: N3VLane16<1, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (ShOp (ResTy QPR:$src1),
|
|
(ResTy (MulOp QPR:$Vn,
|
|
(ResTy (NEONvduplane (OpTy DPR_8:$Vm),
|
|
imm:$lane)))))))]>;
|
|
|
|
// Neon Intrinsic-Op instructions (VABA): double- and quad-register.
|
|
class N3VDIntOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType Ty, SDPatternOperator IntOp, SDNode OpNode>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set DPR:$Vd, (Ty (OpNode DPR:$src1,
|
|
(Ty (IntOp (Ty DPR:$Vn), (Ty DPR:$Vm))))))]>;
|
|
class N3VQIntOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType Ty, SDPatternOperator IntOp, SDNode OpNode>
|
|
: N3V<op24, op23, op21_20, op11_8, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src1, QPR:$Vn, QPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (Ty (OpNode QPR:$src1,
|
|
(Ty (IntOp (Ty QPR:$Vn), (Ty QPR:$Vm))))))]>;
|
|
|
|
// Neon 3-argument intrinsics, both double- and quad-register.
|
|
// The destination register is also used as the first source operand register.
|
|
class N3VDInt3<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$src1),
|
|
(OpTy DPR:$Vn), (OpTy DPR:$Vm))))]>;
|
|
class N3VQInt3<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3V<op24, op23, op21_20, op11_8, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src1, QPR:$Vn, QPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$src1),
|
|
(OpTy QPR:$Vn), (OpTy QPR:$Vm))))]>;
|
|
|
|
// Long Multiply-Add/Sub operations.
|
|
class N3VLMulOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode MulOp, SDNode OpNode>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (OpNode (TyQ QPR:$src1),
|
|
(TyQ (MulOp (TyD DPR:$Vn),
|
|
(TyD DPR:$Vm)))))]>;
|
|
class N3VLMulOpSL<bit op24, bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode MulOp, SDNode OpNode>
|
|
: N3VLane32<op24, 1, op21_20, op11_8, 1, 0, (outs QPR:$Vd),
|
|
(ins QPR:$src1, DPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set QPR:$Vd,
|
|
(OpNode (TyQ QPR:$src1),
|
|
(TyQ (MulOp (TyD DPR:$Vn),
|
|
(TyD (NEONvduplane (TyD DPR_VFP2:$Vm),
|
|
imm:$lane))))))]>;
|
|
class N3VLMulOpSL16<bit op24, bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode MulOp, SDNode OpNode>
|
|
: N3VLane16<op24, 1, op21_20, op11_8, 1, 0, (outs QPR:$Vd),
|
|
(ins QPR:$src1, DPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set QPR:$Vd,
|
|
(OpNode (TyQ QPR:$src1),
|
|
(TyQ (MulOp (TyD DPR:$Vn),
|
|
(TyD (NEONvduplane (TyD DPR_8:$Vm),
|
|
imm:$lane))))))]>;
|
|
|
|
// Long Intrinsic-Op vector operations with explicit extend (VABAL).
|
|
class N3VLIntExtOp<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDPatternOperator IntOp, SDNode ExtOp,
|
|
SDNode OpNode>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (OpNode (TyQ QPR:$src1),
|
|
(TyQ (ExtOp (TyD (IntOp (TyD DPR:$Vn),
|
|
(TyD DPR:$Vm)))))))]>;
|
|
|
|
// Neon Long 3-argument intrinsic. The destination register is
|
|
// a quad-register and is also used as the first source operand register.
|
|
class N3VLInt3<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDPatternOperator IntOp>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src1, DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd,
|
|
(TyQ (IntOp (TyQ QPR:$src1), (TyD DPR:$Vn), (TyD DPR:$Vm))))]>;
|
|
class N3VLInt3SL<bit op24, bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3VLane32<op24, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$src1, DPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (IntOp (ResTy QPR:$src1),
|
|
(OpTy DPR:$Vn),
|
|
(OpTy (NEONvduplane (OpTy DPR_VFP2:$Vm),
|
|
imm:$lane)))))]>;
|
|
class N3VLInt3SL16<bit op24, bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3VLane16<op24, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$src1, DPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "$src1 = $Vd",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (IntOp (ResTy QPR:$src1),
|
|
(OpTy DPR:$Vn),
|
|
(OpTy (NEONvduplane (OpTy DPR_8:$Vm),
|
|
imm:$lane)))))]>;
|
|
|
|
// Narrowing 3-register intrinsics.
|
|
class N3VNInt<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
string OpcodeStr, string Dt, ValueType TyD, ValueType TyQ,
|
|
SDPatternOperator IntOp, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs DPR:$Vd), (ins QPR:$Vn, QPR:$Vm), N3RegFrm, IIC_VBINi4D,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set DPR:$Vd, (TyD (IntOp (TyQ QPR:$Vn), (TyQ QPR:$Vm))))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Long 3-register operations.
|
|
class N3VL<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode OpNode, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (TyQ (OpNode (TyD DPR:$Vn), (TyD DPR:$Vm))))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
class N3VLSL<bit op24, bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode OpNode>
|
|
: N3VLane32<op24, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set QPR:$Vd,
|
|
(TyQ (OpNode (TyD DPR:$Vn),
|
|
(TyD (NEONvduplane (TyD DPR_VFP2:$Vm),imm:$lane)))))]>;
|
|
class N3VLSL16<bit op24, bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode OpNode>
|
|
: N3VLane16<op24, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set QPR:$Vd,
|
|
(TyQ (OpNode (TyD DPR:$Vn),
|
|
(TyD (NEONvduplane (TyD DPR_8:$Vm), imm:$lane)))))]>;
|
|
|
|
// Long 3-register operations with explicitly extended operands.
|
|
class N3VLExt<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDNode OpNode, SDNode ExtOp,
|
|
bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (OpNode (TyQ (ExtOp (TyD DPR:$Vn))),
|
|
(TyQ (ExtOp (TyD DPR:$Vm)))))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Long 3-register intrinsics with explicit extend (VABDL).
|
|
class N3VLIntExt<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDPatternOperator IntOp, SDNode ExtOp,
|
|
bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (TyQ (ExtOp (TyD (IntOp (TyD DPR:$Vn),
|
|
(TyD DPR:$Vm))))))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Long 3-register intrinsics.
|
|
class N3VLInt<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType TyQ, ValueType TyD, SDPatternOperator IntOp, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (TyQ (IntOp (TyD DPR:$Vn), (TyD DPR:$Vm))))]> {
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Same as above, but not predicated.
|
|
class N3VLIntnp<bits<5> op27_23, bits<2> op21_20, bits<4> op11_8, bit op6,
|
|
bit op4, InstrItinClass itin, string OpcodeStr,
|
|
string Dt, ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator IntOp, bit Commutable>
|
|
: N3Vnp<op27_23, op21_20, op11_8, op6, op4,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR:$Vm), N3RegFrm, itin, OpcodeStr, Dt,
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vn), (OpTy DPR:$Vm))))]>;
|
|
|
|
class N3VLIntSL<bit op24, bits<2> op21_20, bits<4> op11_8, InstrItinClass itin,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3VLane32<op24, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (IntOp (OpTy DPR:$Vn),
|
|
(OpTy (NEONvduplane (OpTy DPR_VFP2:$Vm),
|
|
imm:$lane)))))]>;
|
|
class N3VLIntSL16<bit op24, bits<2> op21_20, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N3VLane16<op24, 1, op21_20, op11_8, 1, 0,
|
|
(outs QPR:$Vd), (ins DPR:$Vn, DPR_8:$Vm, VectorIndex16:$lane),
|
|
NVMulSLFrm, itin, OpcodeStr, Dt, "$Vd, $Vn, $Vm$lane", "",
|
|
[(set (ResTy QPR:$Vd),
|
|
(ResTy (IntOp (OpTy DPR:$Vn),
|
|
(OpTy (NEONvduplane (OpTy DPR_8:$Vm),
|
|
imm:$lane)))))]>;
|
|
|
|
// Wide 3-register operations.
|
|
class N3VW<bit op24, bit op23, bits<2> op21_20, bits<4> op11_8, bit op4,
|
|
string OpcodeStr, string Dt, ValueType TyQ, ValueType TyD,
|
|
SDNode OpNode, SDNode ExtOp, bit Commutable>
|
|
: N3V<op24, op23, op21_20, op11_8, 0, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vn, DPR:$Vm), N3RegFrm, IIC_VSUBiD,
|
|
OpcodeStr, Dt, "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (OpNode (TyQ QPR:$Vn),
|
|
(TyQ (ExtOp (TyD DPR:$Vm)))))]> {
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd";
|
|
let isCommutable = Commutable;
|
|
}
|
|
|
|
// Pairwise long 2-register intrinsics, both double- and quad-register.
|
|
class N2VDPLInt<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 0, op4, (outs DPR:$Vd),
|
|
(ins DPR:$Vm), IIC_VSHLiD, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vm))))]>;
|
|
class N2VQPLInt<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 1, op4, (outs QPR:$Vd),
|
|
(ins QPR:$Vm), IIC_VSHLiD, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm))))]>;
|
|
|
|
// Pairwise long 2-register accumulate intrinsics,
|
|
// both double- and quad-register.
|
|
// The destination register is also used as the first source operand register.
|
|
class N2VDPLInt2<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$src1, DPR:$Vm), IIC_VPALiD,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "$src1 = $Vd",
|
|
[(set DPR:$Vd, (ResTy (IntOp (ResTy DPR:$src1), (OpTy DPR:$Vm))))]>;
|
|
class N2VQPLInt2<bits<2> op24_23, bits<2> op21_20, bits<2> op19_18,
|
|
bits<2> op17_16, bits<5> op11_7, bit op4,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, SDPatternOperator IntOp>
|
|
: N2V<op24_23, op21_20, op19_18, op17_16, op11_7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$src1, QPR:$Vm), IIC_VPALiQ,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (ResTy (IntOp (ResTy QPR:$src1), (OpTy QPR:$Vm))))]>;
|
|
|
|
// Shift by immediate,
|
|
// both double- and quad-register.
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd" in {
|
|
class N2VDSh<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
Format f, InstrItinClass itin, Operand ImmTy,
|
|
string OpcodeStr, string Dt, ValueType Ty, SDNode OpNode>
|
|
: N2VImm<op24, op23, op11_8, op7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm, ImmTy:$SIMM), f, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "",
|
|
[(set DPR:$Vd, (Ty (OpNode (Ty DPR:$Vm), (i32 imm:$SIMM))))]>;
|
|
class N2VQSh<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
Format f, InstrItinClass itin, Operand ImmTy,
|
|
string OpcodeStr, string Dt, ValueType Ty, SDNode OpNode>
|
|
: N2VImm<op24, op23, op11_8, op7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm, ImmTy:$SIMM), f, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "",
|
|
[(set QPR:$Vd, (Ty (OpNode (Ty QPR:$Vm), (i32 imm:$SIMM))))]>;
|
|
}
|
|
|
|
// Long shift by immediate.
|
|
class N2VLSh<bit op24, bit op23, bits<4> op11_8, bit op7, bit op6, bit op4,
|
|
string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, Operand ImmTy,
|
|
SDPatternOperator OpNode>
|
|
: N2VImm<op24, op23, op11_8, op7, op6, op4,
|
|
(outs QPR:$Vd), (ins DPR:$Vm, ImmTy:$SIMM), N2RegVShLFrm,
|
|
IIC_VSHLiD, OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "",
|
|
[(set QPR:$Vd, (ResTy (OpNode (OpTy DPR:$Vm), ImmTy:$SIMM)))]>;
|
|
|
|
// Narrow shift by immediate.
|
|
class N2VNSh<bit op24, bit op23, bits<4> op11_8, bit op7, bit op6, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, Operand ImmTy,
|
|
SDPatternOperator OpNode>
|
|
: N2VImm<op24, op23, op11_8, op7, op6, op4,
|
|
(outs DPR:$Vd), (ins QPR:$Vm, ImmTy:$SIMM), N2RegVShRFrm, itin,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "",
|
|
[(set DPR:$Vd, (ResTy (OpNode (OpTy QPR:$Vm),
|
|
(i32 ImmTy:$SIMM))))]>;
|
|
|
|
// Shift right by immediate and accumulate,
|
|
// both double- and quad-register.
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd" in {
|
|
class N2VDShAdd<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
Operand ImmTy, string OpcodeStr, string Dt,
|
|
ValueType Ty, SDNode ShOp>
|
|
: N2VImm<op24, op23, op11_8, op7, 0, op4, (outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vm, ImmTy:$SIMM), N2RegVShRFrm, IIC_VPALiD,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "$src1 = $Vd",
|
|
[(set DPR:$Vd, (Ty (add DPR:$src1,
|
|
(Ty (ShOp DPR:$Vm, (i32 imm:$SIMM))))))]>;
|
|
class N2VQShAdd<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
Operand ImmTy, string OpcodeStr, string Dt,
|
|
ValueType Ty, SDNode ShOp>
|
|
: N2VImm<op24, op23, op11_8, op7, 1, op4, (outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vm, ImmTy:$SIMM), N2RegVShRFrm, IIC_VPALiD,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (Ty (add QPR:$src1,
|
|
(Ty (ShOp QPR:$Vm, (i32 imm:$SIMM))))))]>;
|
|
}
|
|
|
|
// Shift by immediate and insert,
|
|
// both double- and quad-register.
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd" in {
|
|
class N2VDShIns<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
Operand ImmTy, Format f, string OpcodeStr, string Dt,
|
|
ValueType Ty,SDNode ShOp>
|
|
: N2VImm<op24, op23, op11_8, op7, 0, op4, (outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vm, ImmTy:$SIMM), f, IIC_VSHLiD,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "$src1 = $Vd",
|
|
[(set DPR:$Vd, (Ty (ShOp DPR:$src1, DPR:$Vm, (i32 imm:$SIMM))))]>;
|
|
class N2VQShIns<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
Operand ImmTy, Format f, string OpcodeStr, string Dt,
|
|
ValueType Ty,SDNode ShOp>
|
|
: N2VImm<op24, op23, op11_8, op7, 1, op4, (outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vm, ImmTy:$SIMM), f, IIC_VSHLiQ,
|
|
OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "$src1 = $Vd",
|
|
[(set QPR:$Vd, (Ty (ShOp QPR:$src1, QPR:$Vm, (i32 imm:$SIMM))))]>;
|
|
}
|
|
|
|
// Convert, with fractional bits immediate,
|
|
// both double- and quad-register.
|
|
class N2VCvtD<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
string OpcodeStr, string Dt, ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator IntOp>
|
|
: N2VImm<op24, op23, op11_8, op7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm, neon_vcvt_imm32:$SIMM), NVCVTFrm,
|
|
IIC_VUNAD, OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "",
|
|
[(set DPR:$Vd, (ResTy (IntOp (OpTy DPR:$Vm), (i32 imm:$SIMM))))]>;
|
|
class N2VCvtQ<bit op24, bit op23, bits<4> op11_8, bit op7, bit op4,
|
|
string OpcodeStr, string Dt, ValueType ResTy, ValueType OpTy,
|
|
SDPatternOperator IntOp>
|
|
: N2VImm<op24, op23, op11_8, op7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm, neon_vcvt_imm32:$SIMM), NVCVTFrm,
|
|
IIC_VUNAQ, OpcodeStr, Dt, "$Vd, $Vm, $SIMM", "",
|
|
[(set QPR:$Vd, (ResTy (IntOp (OpTy QPR:$Vm), (i32 imm:$SIMM))))]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Multiclasses
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Abbreviations used in multiclass suffixes:
|
|
// Q = quarter int (8 bit) elements
|
|
// H = half int (16 bit) elements
|
|
// S = single int (32 bit) elements
|
|
// D = double int (64 bit) elements
|
|
|
|
// Neon 2-register vector operations and intrinsics.
|
|
|
|
// Neon 2-register comparisons.
|
|
// source operand element sizes of 8, 16 and 32 bits:
|
|
multiclass N2V_QHS_cmp<bits<2> op24_23, bits<2> op21_20, bits<2> op17_16,
|
|
bits<5> op11_7, bit op4, string opc, string Dt,
|
|
string asm, SDNode OpNode> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2V<op24_23, op21_20, 0b00, op17_16, op11_7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), NoItinerary,
|
|
opc, !strconcat(Dt, "8"), asm, "",
|
|
[(set DPR:$Vd, (v8i8 (OpNode (v8i8 DPR:$Vm))))]>;
|
|
def v4i16 : N2V<op24_23, op21_20, 0b01, op17_16, op11_7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), NoItinerary,
|
|
opc, !strconcat(Dt, "16"), asm, "",
|
|
[(set DPR:$Vd, (v4i16 (OpNode (v4i16 DPR:$Vm))))]>;
|
|
def v2i32 : N2V<op24_23, op21_20, 0b10, op17_16, op11_7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), NoItinerary,
|
|
opc, !strconcat(Dt, "32"), asm, "",
|
|
[(set DPR:$Vd, (v2i32 (OpNode (v2i32 DPR:$Vm))))]>;
|
|
def v2f32 : N2V<op24_23, op21_20, 0b10, op17_16, op11_7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), NoItinerary,
|
|
opc, "f32", asm, "",
|
|
[(set DPR:$Vd, (v2i32 (OpNode (v2f32 DPR:$Vm))))]> {
|
|
let Inst{10} = 1; // overwrite F = 1
|
|
}
|
|
def v4f16 : N2V<op24_23, op21_20, 0b01, op17_16, op11_7, 0, op4,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), NoItinerary,
|
|
opc, "f16", asm, "",
|
|
[(set DPR:$Vd, (v4i16 (OpNode (v4f16 DPR:$Vm))))]>,
|
|
Requires<[HasNEON,HasFullFP16]> {
|
|
let Inst{10} = 1; // overwrite F = 1
|
|
}
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2V<op24_23, op21_20, 0b00, op17_16, op11_7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), NoItinerary,
|
|
opc, !strconcat(Dt, "8"), asm, "",
|
|
[(set QPR:$Vd, (v16i8 (OpNode (v16i8 QPR:$Vm))))]>;
|
|
def v8i16 : N2V<op24_23, op21_20, 0b01, op17_16, op11_7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), NoItinerary,
|
|
opc, !strconcat(Dt, "16"), asm, "",
|
|
[(set QPR:$Vd, (v8i16 (OpNode (v8i16 QPR:$Vm))))]>;
|
|
def v4i32 : N2V<op24_23, op21_20, 0b10, op17_16, op11_7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), NoItinerary,
|
|
opc, !strconcat(Dt, "32"), asm, "",
|
|
[(set QPR:$Vd, (v4i32 (OpNode (v4i32 QPR:$Vm))))]>;
|
|
def v4f32 : N2V<op24_23, op21_20, 0b10, op17_16, op11_7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), NoItinerary,
|
|
opc, "f32", asm, "",
|
|
[(set QPR:$Vd, (v4i32 (OpNode (v4f32 QPR:$Vm))))]> {
|
|
let Inst{10} = 1; // overwrite F = 1
|
|
}
|
|
def v8f16 : N2V<op24_23, op21_20, 0b01, op17_16, op11_7, 1, op4,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), NoItinerary,
|
|
opc, "f16", asm, "",
|
|
[(set QPR:$Vd, (v8i16 (OpNode (v8f16 QPR:$Vm))))]>,
|
|
Requires<[HasNEON,HasFullFP16]> {
|
|
let Inst{10} = 1; // overwrite F = 1
|
|
}
|
|
}
|
|
|
|
|
|
// Neon 2-register vector intrinsics,
|
|
// element sizes of 8, 16 and 32 bits:
|
|
multiclass N2VInt_QHS<bits<2> op24_23, bits<2> op21_20, bits<2> op17_16,
|
|
bits<5> op11_7, bit op4,
|
|
InstrItinClass itinD, InstrItinClass itinQ,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDInt<op24_23, op21_20, 0b00, op17_16, op11_7, op4,
|
|
itinD, OpcodeStr, !strconcat(Dt, "8"), v8i8, v8i8, IntOp>;
|
|
def v4i16 : N2VDInt<op24_23, op21_20, 0b01, op17_16, op11_7, op4,
|
|
itinD, OpcodeStr, !strconcat(Dt, "16"),v4i16,v4i16,IntOp>;
|
|
def v2i32 : N2VDInt<op24_23, op21_20, 0b10, op17_16, op11_7, op4,
|
|
itinD, OpcodeStr, !strconcat(Dt, "32"),v2i32,v2i32,IntOp>;
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQInt<op24_23, op21_20, 0b00, op17_16, op11_7, op4,
|
|
itinQ, OpcodeStr, !strconcat(Dt, "8"), v16i8,v16i8,IntOp>;
|
|
def v8i16 : N2VQInt<op24_23, op21_20, 0b01, op17_16, op11_7, op4,
|
|
itinQ, OpcodeStr, !strconcat(Dt, "16"),v8i16,v8i16,IntOp>;
|
|
def v4i32 : N2VQInt<op24_23, op21_20, 0b10, op17_16, op11_7, op4,
|
|
itinQ, OpcodeStr, !strconcat(Dt, "32"),v4i32,v4i32,IntOp>;
|
|
}
|
|
|
|
|
|
// Neon Narrowing 2-register vector operations,
|
|
// source operand element sizes of 16, 32 and 64 bits:
|
|
multiclass N2VN_HSD<bits<2> op24_23, bits<2> op21_20, bits<2> op17_16,
|
|
bits<5> op11_7, bit op6, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDNode OpNode> {
|
|
def v8i8 : N2VN<op24_23, op21_20, 0b00, op17_16, op11_7, op6, op4,
|
|
itin, OpcodeStr, !strconcat(Dt, "16"),
|
|
v8i8, v8i16, OpNode>;
|
|
def v4i16 : N2VN<op24_23, op21_20, 0b01, op17_16, op11_7, op6, op4,
|
|
itin, OpcodeStr, !strconcat(Dt, "32"),
|
|
v4i16, v4i32, OpNode>;
|
|
def v2i32 : N2VN<op24_23, op21_20, 0b10, op17_16, op11_7, op6, op4,
|
|
itin, OpcodeStr, !strconcat(Dt, "64"),
|
|
v2i32, v2i64, OpNode>;
|
|
}
|
|
|
|
// Neon Narrowing 2-register vector intrinsics,
|
|
// source operand element sizes of 16, 32 and 64 bits:
|
|
multiclass N2VNInt_HSD<bits<2> op24_23, bits<2> op21_20, bits<2> op17_16,
|
|
bits<5> op11_7, bit op6, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp> {
|
|
def v8i8 : N2VNInt<op24_23, op21_20, 0b00, op17_16, op11_7, op6, op4,
|
|
itin, OpcodeStr, !strconcat(Dt, "16"),
|
|
v8i8, v8i16, IntOp>;
|
|
def v4i16 : N2VNInt<op24_23, op21_20, 0b01, op17_16, op11_7, op6, op4,
|
|
itin, OpcodeStr, !strconcat(Dt, "32"),
|
|
v4i16, v4i32, IntOp>;
|
|
def v2i32 : N2VNInt<op24_23, op21_20, 0b10, op17_16, op11_7, op6, op4,
|
|
itin, OpcodeStr, !strconcat(Dt, "64"),
|
|
v2i32, v2i64, IntOp>;
|
|
}
|
|
|
|
|
|
// Neon Lengthening 2-register vector intrinsic (currently specific to VMOVL).
|
|
// source operand element sizes of 16, 32 and 64 bits:
|
|
multiclass N2VL_QHS<bits<2> op24_23, bits<5> op11_7, bit op6, bit op4,
|
|
string OpcodeStr, string Dt, SDNode OpNode> {
|
|
def v8i16 : N2VL<op24_23, 0b00, 0b10, 0b00, op11_7, op6, op4, IIC_VQUNAiD,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i16, v8i8, OpNode>;
|
|
def v4i32 : N2VL<op24_23, 0b01, 0b00, 0b00, op11_7, op6, op4, IIC_VQUNAiD,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i32, v4i16, OpNode>;
|
|
def v2i64 : N2VL<op24_23, 0b10, 0b00, 0b00, op11_7, op6, op4, IIC_VQUNAiD,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v2i32, OpNode>;
|
|
}
|
|
|
|
|
|
// Neon 3-register vector operations.
|
|
|
|
// First with only element sizes of 8, 16 and 32 bits:
|
|
multiclass N3V_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt,
|
|
SDNode OpNode, bit Commutable = 0> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N3VD<op24, op23, 0b00, op11_8, op4, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i8, v8i8, OpNode, Commutable>;
|
|
def v4i16 : N3VD<op24, op23, 0b01, op11_8, op4, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i16, v4i16, OpNode, Commutable>;
|
|
def v2i32 : N3VD<op24, op23, 0b10, op11_8, op4, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i32, v2i32, OpNode, Commutable>;
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N3VQ<op24, op23, 0b00, op11_8, op4, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v16i8, v16i8, OpNode, Commutable>;
|
|
def v8i16 : N3VQ<op24, op23, 0b01, op11_8, op4, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v8i16, v8i16, OpNode, Commutable>;
|
|
def v4i32 : N3VQ<op24, op23, 0b10, op11_8, op4, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v4i32, v4i32, OpNode, Commutable>;
|
|
}
|
|
|
|
multiclass N3VSL_HS<bits<4> op11_8, string OpcodeStr, SDNode ShOp> {
|
|
def v4i16 : N3VDSL16<0b01, op11_8, OpcodeStr, "i16", v4i16, ShOp>;
|
|
def v2i32 : N3VDSL<0b10, op11_8, IIC_VMULi32D, OpcodeStr, "i32", v2i32, ShOp>;
|
|
def v8i16 : N3VQSL16<0b01, op11_8, OpcodeStr, "i16", v8i16, v4i16, ShOp>;
|
|
def v4i32 : N3VQSL<0b10, op11_8, IIC_VMULi32Q, OpcodeStr, "i32",
|
|
v4i32, v2i32, ShOp>;
|
|
}
|
|
|
|
// ....then also with element size 64 bits:
|
|
multiclass N3V_QHSD<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itinD, InstrItinClass itinQ,
|
|
string OpcodeStr, string Dt,
|
|
SDNode OpNode, bit Commutable = 0>
|
|
: N3V_QHS<op24, op23, op11_8, op4, itinD, itinD, itinQ, itinQ,
|
|
OpcodeStr, Dt, OpNode, Commutable> {
|
|
def v1i64 : N3VD<op24, op23, 0b11, op11_8, op4, itinD,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v1i64, v1i64, OpNode, Commutable>;
|
|
def v2i64 : N3VQ<op24, op23, 0b11, op11_8, op4, itinQ,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v2i64, v2i64, OpNode, Commutable>;
|
|
}
|
|
|
|
|
|
// Neon 3-register vector intrinsics.
|
|
|
|
// First with only element sizes of 16 and 32 bits:
|
|
multiclass N3VInt_HS<bit op24, bit op23, bits<4> op11_8, bit op4, Format f,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, bit Commutable = 0> {
|
|
// 64-bit vector types.
|
|
def v4i16 : N3VDInt<op24, op23, 0b01, op11_8, op4, f, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i16, v4i16, IntOp, Commutable>;
|
|
def v2i32 : N3VDInt<op24, op23, 0b10, op11_8, op4, f, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i32, v2i32, IntOp, Commutable>;
|
|
|
|
// 128-bit vector types.
|
|
def v8i16 : N3VQInt<op24, op23, 0b01, op11_8, op4, f, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v8i16, v8i16, IntOp, Commutable>;
|
|
def v4i32 : N3VQInt<op24, op23, 0b10, op11_8, op4, f, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v4i32, v4i32, IntOp, Commutable>;
|
|
}
|
|
multiclass N3VInt_HSSh<bit op24, bit op23, bits<4> op11_8, bit op4, Format f,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp> {
|
|
// 64-bit vector types.
|
|
def v4i16 : N3VDIntSh<op24, op23, 0b01, op11_8, op4, f, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i16, v4i16, IntOp>;
|
|
def v2i32 : N3VDIntSh<op24, op23, 0b10, op11_8, op4, f, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i32, v2i32, IntOp>;
|
|
|
|
// 128-bit vector types.
|
|
def v8i16 : N3VQIntSh<op24, op23, 0b01, op11_8, op4, f, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v8i16, v8i16, IntOp>;
|
|
def v4i32 : N3VQIntSh<op24, op23, 0b10, op11_8, op4, f, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v4i32, v4i32, IntOp>;
|
|
}
|
|
|
|
multiclass N3VIntSL_HS<bits<4> op11_8,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp> {
|
|
def v4i16 : N3VDIntSL16<0b01, op11_8, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, IntOp>;
|
|
def v2i32 : N3VDIntSL<0b10, op11_8, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, IntOp>;
|
|
def v8i16 : N3VQIntSL16<0b01, op11_8, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, v4i16, IntOp>;
|
|
def v4i32 : N3VQIntSL<0b10, op11_8, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, v2i32, IntOp>;
|
|
}
|
|
|
|
// ....then also with element size of 8 bits:
|
|
multiclass N3VInt_QHS<bit op24, bit op23, bits<4> op11_8, bit op4, Format f,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, bit Commutable = 0>
|
|
: N3VInt_HS<op24, op23, op11_8, op4, f, itinD16, itinD32, itinQ16, itinQ32,
|
|
OpcodeStr, Dt, IntOp, Commutable> {
|
|
def v8i8 : N3VDInt<op24, op23, 0b00, op11_8, op4, f, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i8, v8i8, IntOp, Commutable>;
|
|
def v16i8 : N3VQInt<op24, op23, 0b00, op11_8, op4, f, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v16i8, v16i8, IntOp, Commutable>;
|
|
}
|
|
multiclass N3VInt_QHSSh<bit op24, bit op23, bits<4> op11_8, bit op4, Format f,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp>
|
|
: N3VInt_HSSh<op24, op23, op11_8, op4, f, itinD16, itinD32, itinQ16, itinQ32,
|
|
OpcodeStr, Dt, IntOp> {
|
|
def v8i8 : N3VDIntSh<op24, op23, 0b00, op11_8, op4, f, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i8, v8i8, IntOp>;
|
|
def v16i8 : N3VQIntSh<op24, op23, 0b00, op11_8, op4, f, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v16i8, v16i8, IntOp>;
|
|
}
|
|
|
|
|
|
// ....then also with element size of 64 bits:
|
|
multiclass N3VInt_QHSD<bit op24, bit op23, bits<4> op11_8, bit op4, Format f,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, bit Commutable = 0>
|
|
: N3VInt_QHS<op24, op23, op11_8, op4, f, itinD16, itinD32, itinQ16, itinQ32,
|
|
OpcodeStr, Dt, IntOp, Commutable> {
|
|
def v1i64 : N3VDInt<op24, op23, 0b11, op11_8, op4, f, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v1i64, v1i64, IntOp, Commutable>;
|
|
def v2i64 : N3VQInt<op24, op23, 0b11, op11_8, op4, f, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v2i64, v2i64, IntOp, Commutable>;
|
|
}
|
|
multiclass N3VInt_QHSDSh<bit op24, bit op23, bits<4> op11_8, bit op4, Format f,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp>
|
|
: N3VInt_QHSSh<op24, op23, op11_8, op4, f, itinD16, itinD32, itinQ16, itinQ32,
|
|
OpcodeStr, Dt, IntOp> {
|
|
def v1i64 : N3VDIntSh<op24, op23, 0b11, op11_8, op4, f, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v1i64, v1i64, IntOp>;
|
|
def v2i64 : N3VQIntSh<op24, op23, 0b11, op11_8, op4, f, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v2i64, v2i64, IntOp>;
|
|
}
|
|
|
|
// Neon Narrowing 3-register vector intrinsics,
|
|
// source operand element sizes of 16, 32 and 64 bits:
|
|
multiclass N3VNInt_HSD<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, bit Commutable = 0> {
|
|
def v8i8 : N3VNInt<op24, op23, 0b00, op11_8, op4,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v8i8, v8i16, IntOp, Commutable>;
|
|
def v4i16 : N3VNInt<op24, op23, 0b01, op11_8, op4,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v4i16, v4i32, IntOp, Commutable>;
|
|
def v2i32 : N3VNInt<op24, op23, 0b10, op11_8, op4,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v2i32, v2i64, IntOp, Commutable>;
|
|
}
|
|
|
|
|
|
// Neon Long 3-register vector operations.
|
|
|
|
multiclass N3VL_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin16, InstrItinClass itin32,
|
|
string OpcodeStr, string Dt,
|
|
SDNode OpNode, bit Commutable = 0> {
|
|
def v8i16 : N3VL<op24, op23, 0b00, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i16, v8i8, OpNode, Commutable>;
|
|
def v4i32 : N3VL<op24, op23, 0b01, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i32, v4i16, OpNode, Commutable>;
|
|
def v2i64 : N3VL<op24, op23, 0b10, op11_8, op4, itin32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i64, v2i32, OpNode, Commutable>;
|
|
}
|
|
|
|
multiclass N3VLSL_HS<bit op24, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDNode OpNode> {
|
|
def v4i16 : N3VLSL16<op24, 0b01, op11_8, itin, OpcodeStr,
|
|
!strconcat(Dt, "16"), v4i32, v4i16, OpNode>;
|
|
def v2i32 : N3VLSL<op24, 0b10, op11_8, itin, OpcodeStr,
|
|
!strconcat(Dt, "32"), v2i64, v2i32, OpNode>;
|
|
}
|
|
|
|
multiclass N3VLExt_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin16, InstrItinClass itin32,
|
|
string OpcodeStr, string Dt,
|
|
SDNode OpNode, SDNode ExtOp, bit Commutable = 0> {
|
|
def v8i16 : N3VLExt<op24, op23, 0b00, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i16, v8i8, OpNode, ExtOp, Commutable>;
|
|
def v4i32 : N3VLExt<op24, op23, 0b01, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i32, v4i16, OpNode, ExtOp, Commutable>;
|
|
def v2i64 : N3VLExt<op24, op23, 0b10, op11_8, op4, itin32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i64, v2i32, OpNode, ExtOp, Commutable>;
|
|
}
|
|
|
|
// Neon Long 3-register vector intrinsics.
|
|
|
|
// First with only element sizes of 16 and 32 bits:
|
|
multiclass N3VLInt_HS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin16, InstrItinClass itin32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, bit Commutable = 0> {
|
|
def v4i32 : N3VLInt<op24, op23, 0b01, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i32, v4i16, IntOp, Commutable>;
|
|
def v2i64 : N3VLInt<op24, op23, 0b10, op11_8, op4, itin32,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i64, v2i32, IntOp, Commutable>;
|
|
}
|
|
|
|
multiclass N3VLIntSL_HS<bit op24, bits<4> op11_8,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp> {
|
|
def v4i16 : N3VLIntSL16<op24, 0b01, op11_8, itin,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i32, v4i16, IntOp>;
|
|
def v2i32 : N3VLIntSL<op24, 0b10, op11_8, itin,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v2i32, IntOp>;
|
|
}
|
|
|
|
// ....then also with element size of 8 bits:
|
|
multiclass N3VLInt_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin16, InstrItinClass itin32,
|
|
string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, bit Commutable = 0>
|
|
: N3VLInt_HS<op24, op23, op11_8, op4, itin16, itin32, OpcodeStr, Dt,
|
|
IntOp, Commutable> {
|
|
def v8i16 : N3VLInt<op24, op23, 0b00, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i16, v8i8, IntOp, Commutable>;
|
|
}
|
|
|
|
// ....with explicit extend (VABDL).
|
|
multiclass N3VLIntExt_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, SDNode ExtOp, bit Commutable = 0> {
|
|
def v8i16 : N3VLIntExt<op24, op23, 0b00, op11_8, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i16, v8i8, IntOp, ExtOp, Commutable>;
|
|
def v4i32 : N3VLIntExt<op24, op23, 0b01, op11_8, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i32, v4i16, IntOp, ExtOp, Commutable>;
|
|
def v2i64 : N3VLIntExt<op24, op23, 0b10, op11_8, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i64, v2i32, IntOp, ExtOp, Commutable>;
|
|
}
|
|
|
|
|
|
// Neon Wide 3-register vector intrinsics,
|
|
// source operand element sizes of 8, 16 and 32 bits:
|
|
multiclass N3VW_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
string OpcodeStr, string Dt,
|
|
SDNode OpNode, SDNode ExtOp, bit Commutable = 0> {
|
|
def v8i16 : N3VW<op24, op23, 0b00, op11_8, op4,
|
|
OpcodeStr, !strconcat(Dt, "8"),
|
|
v8i16, v8i8, OpNode, ExtOp, Commutable>;
|
|
def v4i32 : N3VW<op24, op23, 0b01, op11_8, op4,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v4i32, v4i16, OpNode, ExtOp, Commutable>;
|
|
def v2i64 : N3VW<op24, op23, 0b10, op11_8, op4,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v2i64, v2i32, OpNode, ExtOp, Commutable>;
|
|
}
|
|
|
|
|
|
// Neon Multiply-Op vector operations,
|
|
// element sizes of 8, 16 and 32 bits:
|
|
multiclass N3VMulOp_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt, SDNode OpNode> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N3VDMulOp<op24, op23, 0b00, op11_8, op4, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i8, mul, OpNode>;
|
|
def v4i16 : N3VDMulOp<op24, op23, 0b01, op11_8, op4, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, mul, OpNode>;
|
|
def v2i32 : N3VDMulOp<op24, op23, 0b10, op11_8, op4, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, mul, OpNode>;
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N3VQMulOp<op24, op23, 0b00, op11_8, op4, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "8"), v16i8, mul, OpNode>;
|
|
def v8i16 : N3VQMulOp<op24, op23, 0b01, op11_8, op4, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, mul, OpNode>;
|
|
def v4i32 : N3VQMulOp<op24, op23, 0b10, op11_8, op4, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, mul, OpNode>;
|
|
}
|
|
|
|
multiclass N3VMulOpSL_HS<bits<4> op11_8,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt, SDPatternOperator ShOp> {
|
|
def v4i16 : N3VDMulOpSL16<0b01, op11_8, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, mul, ShOp>;
|
|
def v2i32 : N3VDMulOpSL<0b10, op11_8, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, mul, ShOp>;
|
|
def v8i16 : N3VQMulOpSL16<0b01, op11_8, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, v4i16,
|
|
mul, ShOp>;
|
|
def v4i32 : N3VQMulOpSL<0b10, op11_8, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, v2i32,
|
|
mul, ShOp>;
|
|
}
|
|
|
|
// Neon Intrinsic-Op vector operations,
|
|
// element sizes of 8, 16 and 32 bits:
|
|
multiclass N3VIntOp_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itinD, InstrItinClass itinQ,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp,
|
|
SDNode OpNode> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N3VDIntOp<op24, op23, 0b00, op11_8, op4, itinD,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i8, IntOp, OpNode>;
|
|
def v4i16 : N3VDIntOp<op24, op23, 0b01, op11_8, op4, itinD,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, IntOp, OpNode>;
|
|
def v2i32 : N3VDIntOp<op24, op23, 0b10, op11_8, op4, itinD,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, IntOp, OpNode>;
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N3VQIntOp<op24, op23, 0b00, op11_8, op4, itinQ,
|
|
OpcodeStr, !strconcat(Dt, "8"), v16i8, IntOp, OpNode>;
|
|
def v8i16 : N3VQIntOp<op24, op23, 0b01, op11_8, op4, itinQ,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, IntOp, OpNode>;
|
|
def v4i32 : N3VQIntOp<op24, op23, 0b10, op11_8, op4, itinQ,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, IntOp, OpNode>;
|
|
}
|
|
|
|
// Neon 3-argument intrinsics,
|
|
// element sizes of 16 and 32 bits:
|
|
multiclass N3VInt3_HS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp> {
|
|
// 64-bit vector types.
|
|
def v4i16 : N3VDInt3<op24, op23, 0b01, op11_8, op4, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, v4i16, IntOp>;
|
|
def v2i32 : N3VDInt3<op24, op23, 0b10, op11_8, op4, itinD32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, v2i32, IntOp>;
|
|
|
|
// 128-bit vector types.
|
|
def v8i16 : N3VQInt3<op24, op23, 0b01, op11_8, op4, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, v8i16, IntOp>;
|
|
def v4i32 : N3VQInt3<op24, op23, 0b10, op11_8, op4, itinQ32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, v4i32, IntOp>;
|
|
}
|
|
|
|
// element sizes of 8, 16 and 32 bits:
|
|
multiclass N3VInt3_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itinD16, InstrItinClass itinD32,
|
|
InstrItinClass itinQ16, InstrItinClass itinQ32,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp>
|
|
:N3VInt3_HS <op24, op23, op11_8, op4, itinD16, itinD32,
|
|
itinQ16, itinQ32, OpcodeStr, Dt, IntOp>{
|
|
// 64-bit vector types.
|
|
def v8i8 : N3VDInt3<op24, op23, 0b00, op11_8, op4, itinD16,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i8, v8i8, IntOp>;
|
|
// 128-bit vector types.
|
|
def v16i8 : N3VQInt3<op24, op23, 0b00, op11_8, op4, itinQ16,
|
|
OpcodeStr, !strconcat(Dt, "8"), v16i8, v16i8, IntOp>;
|
|
}
|
|
|
|
// Neon Long Multiply-Op vector operations,
|
|
// element sizes of 8, 16 and 32 bits:
|
|
multiclass N3VLMulOp_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin16, InstrItinClass itin32,
|
|
string OpcodeStr, string Dt, SDNode MulOp,
|
|
SDNode OpNode> {
|
|
def v8i16 : N3VLMulOp<op24, op23, 0b00, op11_8, op4, itin16, OpcodeStr,
|
|
!strconcat(Dt, "8"), v8i16, v8i8, MulOp, OpNode>;
|
|
def v4i32 : N3VLMulOp<op24, op23, 0b01, op11_8, op4, itin16, OpcodeStr,
|
|
!strconcat(Dt, "16"), v4i32, v4i16, MulOp, OpNode>;
|
|
def v2i64 : N3VLMulOp<op24, op23, 0b10, op11_8, op4, itin32, OpcodeStr,
|
|
!strconcat(Dt, "32"), v2i64, v2i32, MulOp, OpNode>;
|
|
}
|
|
|
|
multiclass N3VLMulOpSL_HS<bit op24, bits<4> op11_8, string OpcodeStr,
|
|
string Dt, SDNode MulOp, SDNode OpNode> {
|
|
def v4i16 : N3VLMulOpSL16<op24, 0b01, op11_8, IIC_VMACi16D, OpcodeStr,
|
|
!strconcat(Dt,"16"), v4i32, v4i16, MulOp, OpNode>;
|
|
def v2i32 : N3VLMulOpSL<op24, 0b10, op11_8, IIC_VMACi32D, OpcodeStr,
|
|
!strconcat(Dt, "32"), v2i64, v2i32, MulOp, OpNode>;
|
|
}
|
|
|
|
|
|
// Neon Long 3-argument intrinsics.
|
|
|
|
// First with only element sizes of 16 and 32 bits:
|
|
multiclass N3VLInt3_HS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin16, InstrItinClass itin32,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp> {
|
|
def v4i32 : N3VLInt3<op24, op23, 0b01, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i32, v4i16, IntOp>;
|
|
def v2i64 : N3VLInt3<op24, op23, 0b10, op11_8, op4, itin32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v2i32, IntOp>;
|
|
}
|
|
|
|
multiclass N3VLInt3SL_HS<bit op24, bits<4> op11_8,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp> {
|
|
def v4i16 : N3VLInt3SL16<op24, 0b01, op11_8, IIC_VMACi16D,
|
|
OpcodeStr, !strconcat(Dt,"16"), v4i32, v4i16, IntOp>;
|
|
def v2i32 : N3VLInt3SL<op24, 0b10, op11_8, IIC_VMACi32D,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v2i32, IntOp>;
|
|
}
|
|
|
|
// ....then also with element size of 8 bits:
|
|
multiclass N3VLInt3_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin16, InstrItinClass itin32,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp>
|
|
: N3VLInt3_HS<op24, op23, op11_8, op4, itin16, itin32, OpcodeStr, Dt, IntOp> {
|
|
def v8i16 : N3VLInt3<op24, op23, 0b00, op11_8, op4, itin16,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i16, v8i8, IntOp>;
|
|
}
|
|
|
|
// ....with explicit extend (VABAL).
|
|
multiclass N3VLIntExtOp_QHS<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDPatternOperator IntOp, SDNode ExtOp, SDNode OpNode> {
|
|
def v8i16 : N3VLIntExtOp<op24, op23, 0b00, op11_8, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i16, v8i8,
|
|
IntOp, ExtOp, OpNode>;
|
|
def v4i32 : N3VLIntExtOp<op24, op23, 0b01, op11_8, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i32, v4i16,
|
|
IntOp, ExtOp, OpNode>;
|
|
def v2i64 : N3VLIntExtOp<op24, op23, 0b10, op11_8, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v2i32,
|
|
IntOp, ExtOp, OpNode>;
|
|
}
|
|
|
|
|
|
// Neon Pairwise long 2-register intrinsics,
|
|
// element sizes of 8, 16 and 32 bits:
|
|
multiclass N2VPLInt_QHS<bits<2> op24_23, bits<2> op21_20, bits<2> op17_16,
|
|
bits<5> op11_7, bit op4,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDPLInt<op24_23, op21_20, 0b00, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "8"), v4i16, v8i8, IntOp>;
|
|
def v4i16 : N2VDPLInt<op24_23, op21_20, 0b01, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "16"), v2i32, v4i16, IntOp>;
|
|
def v2i32 : N2VDPLInt<op24_23, op21_20, 0b10, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "32"), v1i64, v2i32, IntOp>;
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQPLInt<op24_23, op21_20, 0b00, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i16, v16i8, IntOp>;
|
|
def v8i16 : N2VQPLInt<op24_23, op21_20, 0b01, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i32, v8i16, IntOp>;
|
|
def v4i32 : N2VQPLInt<op24_23, op21_20, 0b10, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v4i32, IntOp>;
|
|
}
|
|
|
|
|
|
// Neon Pairwise long 2-register accumulate intrinsics,
|
|
// element sizes of 8, 16 and 32 bits:
|
|
multiclass N2VPLInt2_QHS<bits<2> op24_23, bits<2> op21_20, bits<2> op17_16,
|
|
bits<5> op11_7, bit op4,
|
|
string OpcodeStr, string Dt, SDPatternOperator IntOp> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDPLInt2<op24_23, op21_20, 0b00, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "8"), v4i16, v8i8, IntOp>;
|
|
def v4i16 : N2VDPLInt2<op24_23, op21_20, 0b01, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "16"), v2i32, v4i16, IntOp>;
|
|
def v2i32 : N2VDPLInt2<op24_23, op21_20, 0b10, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "32"), v1i64, v2i32, IntOp>;
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQPLInt2<op24_23, op21_20, 0b00, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i16, v16i8, IntOp>;
|
|
def v8i16 : N2VQPLInt2<op24_23, op21_20, 0b01, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i32, v8i16, IntOp>;
|
|
def v4i32 : N2VQPLInt2<op24_23, op21_20, 0b10, op17_16, op11_7, op4,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v4i32, IntOp>;
|
|
}
|
|
|
|
|
|
// Neon 2-register vector shift by immediate,
|
|
// with f of either N2RegVShLFrm or N2RegVShRFrm
|
|
// element sizes of 8, 16, 32 and 64 bits:
|
|
multiclass N2VShL_QHSD<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDNode OpNode> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDSh<op24, op23, op11_8, 0, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i8, OpNode> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v4i16 : N2VDSh<op24, op23, op11_8, 0, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, OpNode> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v2i32 : N2VDSh<op24, op23, op11_8, 0, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, OpNode> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v1i64 : N2VDSh<op24, op23, op11_8, 1, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "64"), v1i64, OpNode>;
|
|
// imm6 = xxxxxx
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQSh<op24, op23, op11_8, 0, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "8"), v16i8, OpNode> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v8i16 : N2VQSh<op24, op23, op11_8, 0, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, OpNode> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v4i32 : N2VQSh<op24, op23, op11_8, 0, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, OpNode> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v2i64 : N2VQSh<op24, op23, op11_8, 1, op4, N2RegVShLFrm, itin, i32imm,
|
|
OpcodeStr, !strconcat(Dt, "64"), v2i64, OpNode>;
|
|
// imm6 = xxxxxx
|
|
}
|
|
multiclass N2VShR_QHSD<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
InstrItinClass itin, string OpcodeStr, string Dt,
|
|
string baseOpc, SDNode OpNode> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDSh<op24, op23, op11_8, 0, op4, N2RegVShRFrm, itin, shr_imm8,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i8, OpNode> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v4i16 : N2VDSh<op24, op23, op11_8, 0, op4, N2RegVShRFrm, itin, shr_imm16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, OpNode> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v2i32 : N2VDSh<op24, op23, op11_8, 0, op4, N2RegVShRFrm, itin, shr_imm32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, OpNode> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v1i64 : N2VDSh<op24, op23, op11_8, 1, op4, N2RegVShRFrm, itin, shr_imm64,
|
|
OpcodeStr, !strconcat(Dt, "64"), v1i64, OpNode>;
|
|
// imm6 = xxxxxx
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQSh<op24, op23, op11_8, 0, op4, N2RegVShRFrm, itin, shr_imm8,
|
|
OpcodeStr, !strconcat(Dt, "8"), v16i8, OpNode> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v8i16 : N2VQSh<op24, op23, op11_8, 0, op4, N2RegVShRFrm, itin, shr_imm16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, OpNode> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v4i32 : N2VQSh<op24, op23, op11_8, 0, op4, N2RegVShRFrm, itin, shr_imm32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, OpNode> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v2i64 : N2VQSh<op24, op23, op11_8, 1, op4, N2RegVShRFrm, itin, shr_imm64,
|
|
OpcodeStr, !strconcat(Dt, "64"), v2i64, OpNode>;
|
|
// imm6 = xxxxxx
|
|
}
|
|
|
|
// Neon Shift-Accumulate vector operations,
|
|
// element sizes of 8, 16, 32 and 64 bits:
|
|
multiclass N2VShAdd_QHSD<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
string OpcodeStr, string Dt, SDNode ShOp> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDShAdd<op24, op23, op11_8, 0, op4, shr_imm8,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i8, ShOp> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v4i16 : N2VDShAdd<op24, op23, op11_8, 0, op4, shr_imm16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i16, ShOp> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v2i32 : N2VDShAdd<op24, op23, op11_8, 0, op4, shr_imm32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i32, ShOp> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v1i64 : N2VDShAdd<op24, op23, op11_8, 1, op4, shr_imm64,
|
|
OpcodeStr, !strconcat(Dt, "64"), v1i64, ShOp>;
|
|
// imm6 = xxxxxx
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQShAdd<op24, op23, op11_8, 0, op4, shr_imm8,
|
|
OpcodeStr, !strconcat(Dt, "8"), v16i8, ShOp> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v8i16 : N2VQShAdd<op24, op23, op11_8, 0, op4, shr_imm16,
|
|
OpcodeStr, !strconcat(Dt, "16"), v8i16, ShOp> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v4i32 : N2VQShAdd<op24, op23, op11_8, 0, op4, shr_imm32,
|
|
OpcodeStr, !strconcat(Dt, "32"), v4i32, ShOp> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v2i64 : N2VQShAdd<op24, op23, op11_8, 1, op4, shr_imm64,
|
|
OpcodeStr, !strconcat(Dt, "64"), v2i64, ShOp>;
|
|
// imm6 = xxxxxx
|
|
}
|
|
|
|
// Neon Shift-Insert vector operations,
|
|
// with f of either N2RegVShLFrm or N2RegVShRFrm
|
|
// element sizes of 8, 16, 32 and 64 bits:
|
|
multiclass N2VShInsL_QHSD<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
string OpcodeStr> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDShIns<op24, op23, op11_8, 0, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "8", v8i8, NEONvsli> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v4i16 : N2VDShIns<op24, op23, op11_8, 0, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "16", v4i16, NEONvsli> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v2i32 : N2VDShIns<op24, op23, op11_8, 0, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "32", v2i32, NEONvsli> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v1i64 : N2VDShIns<op24, op23, op11_8, 1, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "64", v1i64, NEONvsli>;
|
|
// imm6 = xxxxxx
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQShIns<op24, op23, op11_8, 0, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "8", v16i8, NEONvsli> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v8i16 : N2VQShIns<op24, op23, op11_8, 0, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "16", v8i16, NEONvsli> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v4i32 : N2VQShIns<op24, op23, op11_8, 0, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "32", v4i32, NEONvsli> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v2i64 : N2VQShIns<op24, op23, op11_8, 1, op4, i32imm,
|
|
N2RegVShLFrm, OpcodeStr, "64", v2i64, NEONvsli>;
|
|
// imm6 = xxxxxx
|
|
}
|
|
multiclass N2VShInsR_QHSD<bit op24, bit op23, bits<4> op11_8, bit op4,
|
|
string OpcodeStr> {
|
|
// 64-bit vector types.
|
|
def v8i8 : N2VDShIns<op24, op23, op11_8, 0, op4, shr_imm8,
|
|
N2RegVShRFrm, OpcodeStr, "8", v8i8, NEONvsri> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v4i16 : N2VDShIns<op24, op23, op11_8, 0, op4, shr_imm16,
|
|
N2RegVShRFrm, OpcodeStr, "16", v4i16, NEONvsri> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v2i32 : N2VDShIns<op24, op23, op11_8, 0, op4, shr_imm32,
|
|
N2RegVShRFrm, OpcodeStr, "32", v2i32, NEONvsri> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v1i64 : N2VDShIns<op24, op23, op11_8, 1, op4, shr_imm64,
|
|
N2RegVShRFrm, OpcodeStr, "64", v1i64, NEONvsri>;
|
|
// imm6 = xxxxxx
|
|
|
|
// 128-bit vector types.
|
|
def v16i8 : N2VQShIns<op24, op23, op11_8, 0, op4, shr_imm8,
|
|
N2RegVShRFrm, OpcodeStr, "8", v16i8, NEONvsri> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v8i16 : N2VQShIns<op24, op23, op11_8, 0, op4, shr_imm16,
|
|
N2RegVShRFrm, OpcodeStr, "16", v8i16, NEONvsri> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v4i32 : N2VQShIns<op24, op23, op11_8, 0, op4, shr_imm32,
|
|
N2RegVShRFrm, OpcodeStr, "32", v4i32, NEONvsri> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
def v2i64 : N2VQShIns<op24, op23, op11_8, 1, op4, shr_imm64,
|
|
N2RegVShRFrm, OpcodeStr, "64", v2i64, NEONvsri>;
|
|
// imm6 = xxxxxx
|
|
}
|
|
|
|
// Neon Shift Long operations,
|
|
// element sizes of 8, 16, 32 bits:
|
|
multiclass N2VLSh_QHS<bit op24, bit op23, bits<4> op11_8, bit op7, bit op6,
|
|
bit op4, string OpcodeStr, string Dt,
|
|
SDPatternOperator OpNode> {
|
|
def v8i16 : N2VLSh<op24, op23, op11_8, op7, op6, op4,
|
|
OpcodeStr, !strconcat(Dt, "8"), v8i16, v8i8, imm1_7, OpNode> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v4i32 : N2VLSh<op24, op23, op11_8, op7, op6, op4,
|
|
OpcodeStr, !strconcat(Dt, "16"), v4i32, v4i16, imm1_15, OpNode> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v2i64 : N2VLSh<op24, op23, op11_8, op7, op6, op4,
|
|
OpcodeStr, !strconcat(Dt, "32"), v2i64, v2i32, imm1_31, OpNode> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
}
|
|
|
|
// Neon Shift Narrow operations,
|
|
// element sizes of 16, 32, 64 bits:
|
|
multiclass N2VNSh_HSD<bit op24, bit op23, bits<4> op11_8, bit op7, bit op6,
|
|
bit op4, InstrItinClass itin, string OpcodeStr, string Dt,
|
|
SDPatternOperator OpNode> {
|
|
def v8i8 : N2VNSh<op24, op23, op11_8, op7, op6, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "16"),
|
|
v8i8, v8i16, shr_imm8, OpNode> {
|
|
let Inst{21-19} = 0b001; // imm6 = 001xxx
|
|
}
|
|
def v4i16 : N2VNSh<op24, op23, op11_8, op7, op6, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "32"),
|
|
v4i16, v4i32, shr_imm16, OpNode> {
|
|
let Inst{21-20} = 0b01; // imm6 = 01xxxx
|
|
}
|
|
def v2i32 : N2VNSh<op24, op23, op11_8, op7, op6, op4, itin,
|
|
OpcodeStr, !strconcat(Dt, "64"),
|
|
v2i32, v2i64, shr_imm32, OpNode> {
|
|
let Inst{21} = 0b1; // imm6 = 1xxxxx
|
|
}
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Instruction Definitions.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Vector Add Operations.
|
|
|
|
// VADD : Vector Add (integer and floating-point)
|
|
defm VADD : N3V_QHSD<0, 0, 0b1000, 0, IIC_VBINiD, IIC_VBINiQ, "vadd", "i",
|
|
add, 1>;
|
|
def VADDfd : N3VD<0, 0, 0b00, 0b1101, 0, IIC_VBIND, "vadd", "f32",
|
|
v2f32, v2f32, fadd, 1>;
|
|
def VADDfq : N3VQ<0, 0, 0b00, 0b1101, 0, IIC_VBINQ, "vadd", "f32",
|
|
v4f32, v4f32, fadd, 1>;
|
|
def VADDhd : N3VD<0, 0, 0b01, 0b1101, 0, IIC_VBIND, "vadd", "f16",
|
|
v4f16, v4f16, fadd, 1>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
def VADDhq : N3VQ<0, 0, 0b01, 0b1101, 0, IIC_VBINQ, "vadd", "f16",
|
|
v8f16, v8f16, fadd, 1>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
// VADDL : Vector Add Long (Q = D + D)
|
|
defm VADDLs : N3VLExt_QHS<0,1,0b0000,0, IIC_VSHLiD, IIC_VSHLiD,
|
|
"vaddl", "s", add, sext, 1>;
|
|
defm VADDLu : N3VLExt_QHS<1,1,0b0000,0, IIC_VSHLiD, IIC_VSHLiD,
|
|
"vaddl", "u", add, zext, 1>;
|
|
// VADDW : Vector Add Wide (Q = Q + D)
|
|
defm VADDWs : N3VW_QHS<0,1,0b0001,0, "vaddw", "s", add, sext, 0>;
|
|
defm VADDWu : N3VW_QHS<1,1,0b0001,0, "vaddw", "u", add, zext, 0>;
|
|
// VHADD : Vector Halving Add
|
|
defm VHADDs : N3VInt_QHS<0, 0, 0b0000, 0, N3RegFrm,
|
|
IIC_VBINi4D, IIC_VBINi4D, IIC_VBINi4Q, IIC_VBINi4Q,
|
|
"vhadd", "s", int_arm_neon_vhadds, 1>;
|
|
defm VHADDu : N3VInt_QHS<1, 0, 0b0000, 0, N3RegFrm,
|
|
IIC_VBINi4D, IIC_VBINi4D, IIC_VBINi4Q, IIC_VBINi4Q,
|
|
"vhadd", "u", int_arm_neon_vhaddu, 1>;
|
|
// VRHADD : Vector Rounding Halving Add
|
|
defm VRHADDs : N3VInt_QHS<0, 0, 0b0001, 0, N3RegFrm,
|
|
IIC_VBINi4D, IIC_VBINi4D, IIC_VBINi4Q, IIC_VBINi4Q,
|
|
"vrhadd", "s", int_arm_neon_vrhadds, 1>;
|
|
defm VRHADDu : N3VInt_QHS<1, 0, 0b0001, 0, N3RegFrm,
|
|
IIC_VBINi4D, IIC_VBINi4D, IIC_VBINi4Q, IIC_VBINi4Q,
|
|
"vrhadd", "u", int_arm_neon_vrhaddu, 1>;
|
|
// VQADD : Vector Saturating Add
|
|
defm VQADDs : N3VInt_QHSD<0, 0, 0b0000, 1, N3RegFrm,
|
|
IIC_VBINi4D, IIC_VBINi4D, IIC_VBINi4Q, IIC_VBINi4Q,
|
|
"vqadd", "s", int_arm_neon_vqadds, 1>;
|
|
defm VQADDu : N3VInt_QHSD<1, 0, 0b0000, 1, N3RegFrm,
|
|
IIC_VBINi4D, IIC_VBINi4D, IIC_VBINi4Q, IIC_VBINi4Q,
|
|
"vqadd", "u", int_arm_neon_vqaddu, 1>;
|
|
// VADDHN : Vector Add and Narrow Returning High Half (D = Q + Q)
|
|
defm VADDHN : N3VNInt_HSD<0,1,0b0100,0, "vaddhn", "i", null_frag, 1>;
|
|
// VRADDHN : Vector Rounding Add and Narrow Returning High Half (D = Q + Q)
|
|
defm VRADDHN : N3VNInt_HSD<1,1,0b0100,0, "vraddhn", "i",
|
|
int_arm_neon_vraddhn, 1>;
|
|
|
|
def : Pat<(v8i8 (trunc (NEONvshru (add (v8i16 QPR:$Vn), QPR:$Vm), 8))),
|
|
(VADDHNv8i8 QPR:$Vn, QPR:$Vm)>;
|
|
def : Pat<(v4i16 (trunc (NEONvshru (add (v4i32 QPR:$Vn), QPR:$Vm), 16))),
|
|
(VADDHNv4i16 QPR:$Vn, QPR:$Vm)>;
|
|
def : Pat<(v2i32 (trunc (NEONvshru (add (v2i64 QPR:$Vn), QPR:$Vm), 32))),
|
|
(VADDHNv2i32 QPR:$Vn, QPR:$Vm)>;
|
|
|
|
// Vector Multiply Operations.
|
|
|
|
// VMUL : Vector Multiply (integer, polynomial and floating-point)
|
|
defm VMUL : N3V_QHS<0, 0, 0b1001, 1, IIC_VMULi16D, IIC_VMULi32D,
|
|
IIC_VMULi16Q, IIC_VMULi32Q, "vmul", "i", mul, 1>;
|
|
def VMULpd : N3VDInt<1, 0, 0b00, 0b1001, 1, N3RegFrm, IIC_VMULi16D, "vmul",
|
|
"p8", v8i8, v8i8, int_arm_neon_vmulp, 1>;
|
|
def VMULpq : N3VQInt<1, 0, 0b00, 0b1001, 1, N3RegFrm, IIC_VMULi16Q, "vmul",
|
|
"p8", v16i8, v16i8, int_arm_neon_vmulp, 1>;
|
|
def VMULfd : N3VD<1, 0, 0b00, 0b1101, 1, IIC_VFMULD, "vmul", "f32",
|
|
v2f32, v2f32, fmul, 1>;
|
|
def VMULfq : N3VQ<1, 0, 0b00, 0b1101, 1, IIC_VFMULQ, "vmul", "f32",
|
|
v4f32, v4f32, fmul, 1>;
|
|
def VMULhd : N3VD<1, 0, 0b01, 0b1101, 1, IIC_VFMULD, "vmul", "f16",
|
|
v4f16, v4f16, fmul, 1>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
def VMULhq : N3VQ<1, 0, 0b01, 0b1101, 1, IIC_VFMULQ, "vmul", "f16",
|
|
v8f16, v8f16, fmul, 1>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
defm VMULsl : N3VSL_HS<0b1000, "vmul", mul>;
|
|
def VMULslfd : N3VDSL<0b10, 0b1001, IIC_VBIND, "vmul", "f32", v2f32, fmul>;
|
|
def VMULslfq : N3VQSL<0b10, 0b1001, IIC_VBINQ, "vmul", "f32", v4f32,
|
|
v2f32, fmul>;
|
|
def VMULslhd : N3VDSL16<0b01, 0b1001, "vmul", "f16", v4f16, fmul>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
def VMULslhq : N3VQSL16<0b01, 0b1001, "vmul", "f16", v8f16,
|
|
v4f16, fmul>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
|
|
def : Pat<(v8i16 (mul (v8i16 QPR:$src1),
|
|
(v8i16 (NEONvduplane (v8i16 QPR:$src2), imm:$lane)))),
|
|
(v8i16 (VMULslv8i16 (v8i16 QPR:$src1),
|
|
(v4i16 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
def : Pat<(v4i32 (mul (v4i32 QPR:$src1),
|
|
(v4i32 (NEONvduplane (v4i32 QPR:$src2), imm:$lane)))),
|
|
(v4i32 (VMULslv4i32 (v4i32 QPR:$src1),
|
|
(v2i32 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
def : Pat<(v4f32 (fmul (v4f32 QPR:$src1),
|
|
(v4f32 (NEONvduplane (v4f32 QPR:$src2), imm:$lane)))),
|
|
(v4f32 (VMULslfq (v4f32 QPR:$src1),
|
|
(v2f32 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
def : Pat<(v8f16 (fmul (v8f16 QPR:$src1),
|
|
(v8f16 (NEONvduplane (v8f16 QPR:$src2), imm:$lane)))),
|
|
(v8f16 (VMULslhq(v8f16 QPR:$src1),
|
|
(v4f16 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
|
|
def : Pat<(v2f32 (fmul DPR:$Rn, (NEONvdup (f32 SPR:$Rm)))),
|
|
(VMULslfd DPR:$Rn,
|
|
(INSERT_SUBREG (v2f32 (IMPLICIT_DEF)), SPR:$Rm, ssub_0),
|
|
(i32 0))>;
|
|
def : Pat<(v4f16 (fmul DPR:$Rn, (NEONvdup (f16 HPR:$Rm)))),
|
|
(VMULslhd DPR:$Rn,
|
|
(INSERT_SUBREG (v4f16 (IMPLICIT_DEF)), HPR:$Rm, ssub_0),
|
|
(i32 0))>;
|
|
def : Pat<(v4f32 (fmul QPR:$Rn, (NEONvdup (f32 SPR:$Rm)))),
|
|
(VMULslfq QPR:$Rn,
|
|
(INSERT_SUBREG (v2f32 (IMPLICIT_DEF)), SPR:$Rm, ssub_0),
|
|
(i32 0))>;
|
|
def : Pat<(v8f16 (fmul QPR:$Rn, (NEONvdup (f16 HPR:$Rm)))),
|
|
(VMULslhq QPR:$Rn,
|
|
(INSERT_SUBREG (v4f16 (IMPLICIT_DEF)), HPR:$Rm, ssub_0),
|
|
(i32 0))>;
|
|
|
|
// VQDMULH : Vector Saturating Doubling Multiply Returning High Half
|
|
defm VQDMULH : N3VInt_HS<0, 0, 0b1011, 0, N3RegFrm, IIC_VMULi16D, IIC_VMULi32D,
|
|
IIC_VMULi16Q, IIC_VMULi32Q,
|
|
"vqdmulh", "s", int_arm_neon_vqdmulh, 1>;
|
|
defm VQDMULHsl: N3VIntSL_HS<0b1100, IIC_VMULi16D, IIC_VMULi32D,
|
|
IIC_VMULi16Q, IIC_VMULi32Q,
|
|
"vqdmulh", "s", int_arm_neon_vqdmulh>;
|
|
def : Pat<(v8i16 (int_arm_neon_vqdmulh (v8i16 QPR:$src1),
|
|
(v8i16 (NEONvduplane (v8i16 QPR:$src2),
|
|
imm:$lane)))),
|
|
(v8i16 (VQDMULHslv8i16 (v8i16 QPR:$src1),
|
|
(v4i16 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqdmulh (v4i32 QPR:$src1),
|
|
(v4i32 (NEONvduplane (v4i32 QPR:$src2),
|
|
imm:$lane)))),
|
|
(v4i32 (VQDMULHslv4i32 (v4i32 QPR:$src1),
|
|
(v2i32 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
|
|
// VQRDMULH : Vector Rounding Saturating Doubling Multiply Returning High Half
|
|
defm VQRDMULH : N3VInt_HS<1, 0, 0b1011, 0, N3RegFrm,
|
|
IIC_VMULi16D,IIC_VMULi32D,IIC_VMULi16Q,IIC_VMULi32Q,
|
|
"vqrdmulh", "s", int_arm_neon_vqrdmulh, 1>;
|
|
defm VQRDMULHsl : N3VIntSL_HS<0b1101, IIC_VMULi16D, IIC_VMULi32D,
|
|
IIC_VMULi16Q, IIC_VMULi32Q,
|
|
"vqrdmulh", "s", int_arm_neon_vqrdmulh>;
|
|
def : Pat<(v8i16 (int_arm_neon_vqrdmulh (v8i16 QPR:$src1),
|
|
(v8i16 (NEONvduplane (v8i16 QPR:$src2),
|
|
imm:$lane)))),
|
|
(v8i16 (VQRDMULHslv8i16 (v8i16 QPR:$src1),
|
|
(v4i16 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqrdmulh (v4i32 QPR:$src1),
|
|
(v4i32 (NEONvduplane (v4i32 QPR:$src2),
|
|
imm:$lane)))),
|
|
(v4i32 (VQRDMULHslv4i32 (v4i32 QPR:$src1),
|
|
(v2i32 (EXTRACT_SUBREG QPR:$src2,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
|
|
// VMULL : Vector Multiply Long (integer and polynomial) (Q = D * D)
|
|
let PostEncoderMethod = "NEONThumb2DataIPostEncoder",
|
|
DecoderNamespace = "NEONData" in {
|
|
defm VMULLs : N3VL_QHS<0,1,0b1100,0, IIC_VMULi16D, IIC_VMULi32D,
|
|
"vmull", "s", NEONvmulls, 1>;
|
|
defm VMULLu : N3VL_QHS<1,1,0b1100,0, IIC_VMULi16D, IIC_VMULi32D,
|
|
"vmull", "u", NEONvmullu, 1>;
|
|
def VMULLp8 : N3VLInt<0, 1, 0b00, 0b1110, 0, IIC_VMULi16D, "vmull", "p8",
|
|
v8i16, v8i8, int_arm_neon_vmullp, 1>;
|
|
def VMULLp64 : N3VLIntnp<0b00101, 0b10, 0b1110, 0, 0, NoItinerary,
|
|
"vmull", "p64", v2i64, v1i64, int_arm_neon_vmullp, 1>,
|
|
Requires<[HasV8, HasCrypto]>;
|
|
}
|
|
defm VMULLsls : N3VLSL_HS<0, 0b1010, IIC_VMULi16D, "vmull", "s", NEONvmulls>;
|
|
defm VMULLslu : N3VLSL_HS<1, 0b1010, IIC_VMULi16D, "vmull", "u", NEONvmullu>;
|
|
|
|
// VQDMULL : Vector Saturating Doubling Multiply Long (Q = D * D)
|
|
defm VQDMULL : N3VLInt_HS<0,1,0b1101,0, IIC_VMULi16D, IIC_VMULi32D,
|
|
"vqdmull", "s", int_arm_neon_vqdmull, 1>;
|
|
defm VQDMULLsl: N3VLIntSL_HS<0, 0b1011, IIC_VMULi16D,
|
|
"vqdmull", "s", int_arm_neon_vqdmull>;
|
|
|
|
// Vector Multiply-Accumulate and Multiply-Subtract Operations.
|
|
|
|
// VMLA : Vector Multiply Accumulate (integer and floating-point)
|
|
defm VMLA : N3VMulOp_QHS<0, 0, 0b1001, 0, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vmla", "i", add>;
|
|
def VMLAfd : N3VDMulOp<0, 0, 0b00, 0b1101, 1, IIC_VMACD, "vmla", "f32",
|
|
v2f32, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx, DontUseFusedMAC]>;
|
|
def VMLAfq : N3VQMulOp<0, 0, 0b00, 0b1101, 1, IIC_VMACQ, "vmla", "f32",
|
|
v4f32, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx, DontUseFusedMAC]>;
|
|
def VMLAhd : N3VDMulOp<0, 0, 0b01, 0b1101, 1, IIC_VMACD, "vmla", "f16",
|
|
v4f16, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx, DontUseFusedMAC]>;
|
|
def VMLAhq : N3VQMulOp<0, 0, 0b01, 0b1101, 1, IIC_VMACQ, "vmla", "f16",
|
|
v8f16, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx, DontUseFusedMAC]>;
|
|
defm VMLAsl : N3VMulOpSL_HS<0b0000, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vmla", "i", add>;
|
|
def VMLAslfd : N3VDMulOpSL<0b10, 0b0001, IIC_VMACD, "vmla", "f32",
|
|
v2f32, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx]>;
|
|
def VMLAslfq : N3VQMulOpSL<0b10, 0b0001, IIC_VMACQ, "vmla", "f32",
|
|
v4f32, v2f32, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx]>;
|
|
def VMLAslhd : N3VDMulOpSL16<0b01, 0b0001, IIC_VMACD, "vmla", "f16",
|
|
v4f16, fmul, fadd>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx]>;
|
|
def VMLAslhq : N3VQMulOpSL16<0b01, 0b0001, IIC_VMACQ, "vmla", "f16",
|
|
v8f16, v4f16, fmul, fadd>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx]>;
|
|
|
|
def : Pat<(v8i16 (add (v8i16 QPR:$src1),
|
|
(mul (v8i16 QPR:$src2),
|
|
(v8i16 (NEONvduplane (v8i16 QPR:$src3), imm:$lane))))),
|
|
(v8i16 (VMLAslv8i16 (v8i16 QPR:$src1), (v8i16 QPR:$src2),
|
|
(v4i16 (EXTRACT_SUBREG QPR:$src3,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
|
|
def : Pat<(v4i32 (add (v4i32 QPR:$src1),
|
|
(mul (v4i32 QPR:$src2),
|
|
(v4i32 (NEONvduplane (v4i32 QPR:$src3), imm:$lane))))),
|
|
(v4i32 (VMLAslv4i32 (v4i32 QPR:$src1), (v4i32 QPR:$src2),
|
|
(v2i32 (EXTRACT_SUBREG QPR:$src3,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
|
|
def : Pat<(v4f32 (fadd_mlx (v4f32 QPR:$src1),
|
|
(fmul_su (v4f32 QPR:$src2),
|
|
(v4f32 (NEONvduplane (v4f32 QPR:$src3), imm:$lane))))),
|
|
(v4f32 (VMLAslfq (v4f32 QPR:$src1),
|
|
(v4f32 QPR:$src2),
|
|
(v2f32 (EXTRACT_SUBREG QPR:$src3,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>,
|
|
Requires<[HasNEON, UseFPVMLx]>;
|
|
|
|
// VMLAL : Vector Multiply Accumulate Long (Q += D * D)
|
|
defm VMLALs : N3VLMulOp_QHS<0,1,0b1000,0, IIC_VMACi16D, IIC_VMACi32D,
|
|
"vmlal", "s", NEONvmulls, add>;
|
|
defm VMLALu : N3VLMulOp_QHS<1,1,0b1000,0, IIC_VMACi16D, IIC_VMACi32D,
|
|
"vmlal", "u", NEONvmullu, add>;
|
|
|
|
defm VMLALsls : N3VLMulOpSL_HS<0, 0b0010, "vmlal", "s", NEONvmulls, add>;
|
|
defm VMLALslu : N3VLMulOpSL_HS<1, 0b0010, "vmlal", "u", NEONvmullu, add>;
|
|
|
|
let Predicates = [HasNEON, HasV8_1a] in {
|
|
// v8.1a Neon Rounding Double Multiply-Op vector operations,
|
|
// VQRDMLAH : Vector Saturating Rounding Doubling Multiply Accumulate Long
|
|
// (Q += D * D)
|
|
defm VQRDMLAH : N3VInt3_HS<1, 0, 0b1011, 1, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vqrdmlah", "s",
|
|
null_frag>;
|
|
def : Pat<(v4i16 (int_arm_neon_vqadds
|
|
(v4i16 DPR:$src1),
|
|
(v4i16 (int_arm_neon_vqrdmulh (v4i16 DPR:$Vn),
|
|
(v4i16 DPR:$Vm))))),
|
|
(v4i16 (VQRDMLAHv4i16 DPR:$src1, DPR:$Vn, DPR:$Vm))>;
|
|
def : Pat<(v2i32 (int_arm_neon_vqadds
|
|
(v2i32 DPR:$src1),
|
|
(v2i32 (int_arm_neon_vqrdmulh (v2i32 DPR:$Vn),
|
|
(v2i32 DPR:$Vm))))),
|
|
(v2i32 (VQRDMLAHv2i32 DPR:$src1, DPR:$Vn, DPR:$Vm))>;
|
|
def : Pat<(v8i16 (int_arm_neon_vqadds
|
|
(v8i16 QPR:$src1),
|
|
(v8i16 (int_arm_neon_vqrdmulh (v8i16 QPR:$Vn),
|
|
(v8i16 QPR:$Vm))))),
|
|
(v8i16 (VQRDMLAHv8i16 QPR:$src1, QPR:$Vn, QPR:$Vm))>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqadds
|
|
(v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqrdmulh (v4i32 QPR:$Vn),
|
|
(v4i32 QPR:$Vm))))),
|
|
(v4i32 (VQRDMLAHv4i32 QPR:$src1, QPR:$Vn, QPR:$Vm))>;
|
|
|
|
defm VQRDMLAHsl : N3VMulOpSL_HS<0b1110, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vqrdmlah", "s",
|
|
null_frag>;
|
|
def : Pat<(v4i16 (int_arm_neon_vqadds
|
|
(v4i16 DPR:$src1),
|
|
(v4i16 (int_arm_neon_vqrdmulh
|
|
(v4i16 DPR:$Vn),
|
|
(v4i16 (NEONvduplane (v4i16 DPR_8:$Vm),
|
|
imm:$lane)))))),
|
|
(v4i16 (VQRDMLAHslv4i16 DPR:$src1, DPR:$Vn, DPR_8:$Vm,
|
|
imm:$lane))>;
|
|
def : Pat<(v2i32 (int_arm_neon_vqadds
|
|
(v2i32 DPR:$src1),
|
|
(v2i32 (int_arm_neon_vqrdmulh
|
|
(v2i32 DPR:$Vn),
|
|
(v2i32 (NEONvduplane (v2i32 DPR_VFP2:$Vm),
|
|
imm:$lane)))))),
|
|
(v2i32 (VQRDMLAHslv2i32 DPR:$src1, DPR:$Vn, DPR_VFP2:$Vm,
|
|
imm:$lane))>;
|
|
def : Pat<(v8i16 (int_arm_neon_vqadds
|
|
(v8i16 QPR:$src1),
|
|
(v8i16 (int_arm_neon_vqrdmulh
|
|
(v8i16 QPR:$src2),
|
|
(v8i16 (NEONvduplane (v8i16 QPR:$src3),
|
|
imm:$lane)))))),
|
|
(v8i16 (VQRDMLAHslv8i16 (v8i16 QPR:$src1),
|
|
(v8i16 QPR:$src2),
|
|
(v4i16 (EXTRACT_SUBREG
|
|
QPR:$src3,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqadds
|
|
(v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqrdmulh
|
|
(v4i32 QPR:$src2),
|
|
(v4i32 (NEONvduplane (v4i32 QPR:$src3),
|
|
imm:$lane)))))),
|
|
(v4i32 (VQRDMLAHslv4i32 (v4i32 QPR:$src1),
|
|
(v4i32 QPR:$src2),
|
|
(v2i32 (EXTRACT_SUBREG
|
|
QPR:$src3,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
|
|
// VQRDMLSH : Vector Saturating Rounding Doubling Multiply Subtract Long
|
|
// (Q -= D * D)
|
|
defm VQRDMLSH : N3VInt3_HS<1, 0, 0b1100, 1, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vqrdmlsh", "s",
|
|
null_frag>;
|
|
def : Pat<(v4i16 (int_arm_neon_vqsubs
|
|
(v4i16 DPR:$src1),
|
|
(v4i16 (int_arm_neon_vqrdmulh (v4i16 DPR:$Vn),
|
|
(v4i16 DPR:$Vm))))),
|
|
(v4i16 (VQRDMLSHv4i16 DPR:$src1, DPR:$Vn, DPR:$Vm))>;
|
|
def : Pat<(v2i32 (int_arm_neon_vqsubs
|
|
(v2i32 DPR:$src1),
|
|
(v2i32 (int_arm_neon_vqrdmulh (v2i32 DPR:$Vn),
|
|
(v2i32 DPR:$Vm))))),
|
|
(v2i32 (VQRDMLSHv2i32 DPR:$src1, DPR:$Vn, DPR:$Vm))>;
|
|
def : Pat<(v8i16 (int_arm_neon_vqsubs
|
|
(v8i16 QPR:$src1),
|
|
(v8i16 (int_arm_neon_vqrdmulh (v8i16 QPR:$Vn),
|
|
(v8i16 QPR:$Vm))))),
|
|
(v8i16 (VQRDMLSHv8i16 QPR:$src1, QPR:$Vn, QPR:$Vm))>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqsubs
|
|
(v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqrdmulh (v4i32 QPR:$Vn),
|
|
(v4i32 QPR:$Vm))))),
|
|
(v4i32 (VQRDMLSHv4i32 QPR:$src1, QPR:$Vn, QPR:$Vm))>;
|
|
|
|
defm VQRDMLSHsl : N3VMulOpSL_HS<0b1111, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vqrdmlsh", "s",
|
|
null_frag>;
|
|
def : Pat<(v4i16 (int_arm_neon_vqsubs
|
|
(v4i16 DPR:$src1),
|
|
(v4i16 (int_arm_neon_vqrdmulh
|
|
(v4i16 DPR:$Vn),
|
|
(v4i16 (NEONvduplane (v4i16 DPR_8:$Vm),
|
|
imm:$lane)))))),
|
|
(v4i16 (VQRDMLSHslv4i16 DPR:$src1, DPR:$Vn, DPR_8:$Vm, imm:$lane))>;
|
|
def : Pat<(v2i32 (int_arm_neon_vqsubs
|
|
(v2i32 DPR:$src1),
|
|
(v2i32 (int_arm_neon_vqrdmulh
|
|
(v2i32 DPR:$Vn),
|
|
(v2i32 (NEONvduplane (v2i32 DPR_VFP2:$Vm),
|
|
imm:$lane)))))),
|
|
(v2i32 (VQRDMLSHslv2i32 DPR:$src1, DPR:$Vn, DPR_VFP2:$Vm,
|
|
imm:$lane))>;
|
|
def : Pat<(v8i16 (int_arm_neon_vqsubs
|
|
(v8i16 QPR:$src1),
|
|
(v8i16 (int_arm_neon_vqrdmulh
|
|
(v8i16 QPR:$src2),
|
|
(v8i16 (NEONvduplane (v8i16 QPR:$src3),
|
|
imm:$lane)))))),
|
|
(v8i16 (VQRDMLSHslv8i16 (v8i16 QPR:$src1),
|
|
(v8i16 QPR:$src2),
|
|
(v4i16 (EXTRACT_SUBREG
|
|
QPR:$src3,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqsubs
|
|
(v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqrdmulh
|
|
(v4i32 QPR:$src2),
|
|
(v4i32 (NEONvduplane (v4i32 QPR:$src3),
|
|
imm:$lane)))))),
|
|
(v4i32 (VQRDMLSHslv4i32 (v4i32 QPR:$src1),
|
|
(v4i32 QPR:$src2),
|
|
(v2i32 (EXTRACT_SUBREG
|
|
QPR:$src3,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
}
|
|
// VQDMLAL : Vector Saturating Doubling Multiply Accumulate Long (Q += D * D)
|
|
defm VQDMLAL : N3VLInt3_HS<0, 1, 0b1001, 0, IIC_VMACi16D, IIC_VMACi32D,
|
|
"vqdmlal", "s", null_frag>;
|
|
defm VQDMLALsl: N3VLInt3SL_HS<0, 0b0011, "vqdmlal", "s", null_frag>;
|
|
|
|
def : Pat<(v4i32 (int_arm_neon_vqadds (v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqdmull (v4i16 DPR:$Vn),
|
|
(v4i16 DPR:$Vm))))),
|
|
(VQDMLALv4i32 QPR:$src1, DPR:$Vn, DPR:$Vm)>;
|
|
def : Pat<(v2i64 (int_arm_neon_vqadds (v2i64 QPR:$src1),
|
|
(v2i64 (int_arm_neon_vqdmull (v2i32 DPR:$Vn),
|
|
(v2i32 DPR:$Vm))))),
|
|
(VQDMLALv2i64 QPR:$src1, DPR:$Vn, DPR:$Vm)>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqadds (v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqdmull (v4i16 DPR:$Vn),
|
|
(v4i16 (NEONvduplane (v4i16 DPR_8:$Vm),
|
|
imm:$lane)))))),
|
|
(VQDMLALslv4i16 QPR:$src1, DPR:$Vn, DPR_8:$Vm, imm:$lane)>;
|
|
def : Pat<(v2i64 (int_arm_neon_vqadds (v2i64 QPR:$src1),
|
|
(v2i64 (int_arm_neon_vqdmull (v2i32 DPR:$Vn),
|
|
(v2i32 (NEONvduplane (v2i32 DPR_VFP2:$Vm),
|
|
imm:$lane)))))),
|
|
(VQDMLALslv2i32 QPR:$src1, DPR:$Vn, DPR_VFP2:$Vm, imm:$lane)>;
|
|
|
|
// VMLS : Vector Multiply Subtract (integer and floating-point)
|
|
defm VMLS : N3VMulOp_QHS<1, 0, 0b1001, 0, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vmls", "i", sub>;
|
|
def VMLSfd : N3VDMulOp<0, 0, 0b10, 0b1101, 1, IIC_VMACD, "vmls", "f32",
|
|
v2f32, fmul_su, fsub_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx, DontUseFusedMAC]>;
|
|
def VMLSfq : N3VQMulOp<0, 0, 0b10, 0b1101, 1, IIC_VMACQ, "vmls", "f32",
|
|
v4f32, fmul_su, fsub_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx, DontUseFusedMAC]>;
|
|
def VMLShd : N3VDMulOp<0, 0, 0b11, 0b1101, 1, IIC_VMACD, "vmls", "f16",
|
|
v4f16, fmul, fsub>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx, DontUseFusedMAC]>;
|
|
def VMLShq : N3VQMulOp<0, 0, 0b11, 0b1101, 1, IIC_VMACQ, "vmls", "f16",
|
|
v8f16, fmul, fsub>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx, DontUseFusedMAC]>;
|
|
defm VMLSsl : N3VMulOpSL_HS<0b0100, IIC_VMACi16D, IIC_VMACi32D,
|
|
IIC_VMACi16Q, IIC_VMACi32Q, "vmls", "i", sub>;
|
|
def VMLSslfd : N3VDMulOpSL<0b10, 0b0101, IIC_VMACD, "vmls", "f32",
|
|
v2f32, fmul_su, fsub_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx]>;
|
|
def VMLSslfq : N3VQMulOpSL<0b10, 0b0101, IIC_VMACQ, "vmls", "f32",
|
|
v4f32, v2f32, fmul_su, fsub_mlx>,
|
|
Requires<[HasNEON, UseFPVMLx]>;
|
|
def VMLSslhd : N3VDMulOpSL16<0b01, 0b0101, IIC_VMACD, "vmls", "f16",
|
|
v4f16, fmul, fsub>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx]>;
|
|
def VMLSslhq : N3VQMulOpSL16<0b01, 0b0101, IIC_VMACQ, "vmls", "f16",
|
|
v8f16, v4f16, fmul, fsub>,
|
|
Requires<[HasNEON, HasFullFP16, UseFPVMLx]>;
|
|
|
|
def : Pat<(v8i16 (sub (v8i16 QPR:$src1),
|
|
(mul (v8i16 QPR:$src2),
|
|
(v8i16 (NEONvduplane (v8i16 QPR:$src3), imm:$lane))))),
|
|
(v8i16 (VMLSslv8i16 (v8i16 QPR:$src1), (v8i16 QPR:$src2),
|
|
(v4i16 (EXTRACT_SUBREG QPR:$src3,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
|
|
def : Pat<(v4i32 (sub (v4i32 QPR:$src1),
|
|
(mul (v4i32 QPR:$src2),
|
|
(v4i32 (NEONvduplane (v4i32 QPR:$src3), imm:$lane))))),
|
|
(v4i32 (VMLSslv4i32 (v4i32 QPR:$src1), (v4i32 QPR:$src2),
|
|
(v2i32 (EXTRACT_SUBREG QPR:$src3,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
|
|
def : Pat<(v4f32 (fsub_mlx (v4f32 QPR:$src1),
|
|
(fmul_su (v4f32 QPR:$src2),
|
|
(v4f32 (NEONvduplane (v4f32 QPR:$src3), imm:$lane))))),
|
|
(v4f32 (VMLSslfq (v4f32 QPR:$src1), (v4f32 QPR:$src2),
|
|
(v2f32 (EXTRACT_SUBREG QPR:$src3,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>,
|
|
Requires<[HasNEON, UseFPVMLx]>;
|
|
|
|
// VMLSL : Vector Multiply Subtract Long (Q -= D * D)
|
|
defm VMLSLs : N3VLMulOp_QHS<0,1,0b1010,0, IIC_VMACi16D, IIC_VMACi32D,
|
|
"vmlsl", "s", NEONvmulls, sub>;
|
|
defm VMLSLu : N3VLMulOp_QHS<1,1,0b1010,0, IIC_VMACi16D, IIC_VMACi32D,
|
|
"vmlsl", "u", NEONvmullu, sub>;
|
|
|
|
defm VMLSLsls : N3VLMulOpSL_HS<0, 0b0110, "vmlsl", "s", NEONvmulls, sub>;
|
|
defm VMLSLslu : N3VLMulOpSL_HS<1, 0b0110, "vmlsl", "u", NEONvmullu, sub>;
|
|
|
|
// VQDMLSL : Vector Saturating Doubling Multiply Subtract Long (Q -= D * D)
|
|
defm VQDMLSL : N3VLInt3_HS<0, 1, 0b1011, 0, IIC_VMACi16D, IIC_VMACi32D,
|
|
"vqdmlsl", "s", null_frag>;
|
|
defm VQDMLSLsl: N3VLInt3SL_HS<0, 0b0111, "vqdmlsl", "s", null_frag>;
|
|
|
|
def : Pat<(v4i32 (int_arm_neon_vqsubs (v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqdmull (v4i16 DPR:$Vn),
|
|
(v4i16 DPR:$Vm))))),
|
|
(VQDMLSLv4i32 QPR:$src1, DPR:$Vn, DPR:$Vm)>;
|
|
def : Pat<(v2i64 (int_arm_neon_vqsubs (v2i64 QPR:$src1),
|
|
(v2i64 (int_arm_neon_vqdmull (v2i32 DPR:$Vn),
|
|
(v2i32 DPR:$Vm))))),
|
|
(VQDMLSLv2i64 QPR:$src1, DPR:$Vn, DPR:$Vm)>;
|
|
def : Pat<(v4i32 (int_arm_neon_vqsubs (v4i32 QPR:$src1),
|
|
(v4i32 (int_arm_neon_vqdmull (v4i16 DPR:$Vn),
|
|
(v4i16 (NEONvduplane (v4i16 DPR_8:$Vm),
|
|
imm:$lane)))))),
|
|
(VQDMLSLslv4i16 QPR:$src1, DPR:$Vn, DPR_8:$Vm, imm:$lane)>;
|
|
def : Pat<(v2i64 (int_arm_neon_vqsubs (v2i64 QPR:$src1),
|
|
(v2i64 (int_arm_neon_vqdmull (v2i32 DPR:$Vn),
|
|
(v2i32 (NEONvduplane (v2i32 DPR_VFP2:$Vm),
|
|
imm:$lane)))))),
|
|
(VQDMLSLslv2i32 QPR:$src1, DPR:$Vn, DPR_VFP2:$Vm, imm:$lane)>;
|
|
|
|
// Fused Vector Multiply-Accumulate and Fused Multiply-Subtract Operations.
|
|
def VFMAfd : N3VDMulOp<0, 0, 0b00, 0b1100, 1, IIC_VFMACD, "vfma", "f32",
|
|
v2f32, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON,HasVFP4,UseFusedMAC]>;
|
|
|
|
def VFMAfq : N3VQMulOp<0, 0, 0b00, 0b1100, 1, IIC_VFMACQ, "vfma", "f32",
|
|
v4f32, fmul_su, fadd_mlx>,
|
|
Requires<[HasNEON,HasVFP4,UseFusedMAC]>;
|
|
def VFMAhd : N3VDMulOp<0, 0, 0b01, 0b1100, 1, IIC_VFMACD, "vfma", "f16",
|
|
v4f16, fmul, fadd>,
|
|
Requires<[HasNEON,HasFullFP16,UseFusedMAC]>;
|
|
|
|
def VFMAhq : N3VQMulOp<0, 0, 0b01, 0b1100, 1, IIC_VFMACQ, "vfma", "f16",
|
|
v8f16, fmul, fadd>,
|
|
Requires<[HasNEON,HasFullFP16,UseFusedMAC]>;
|
|
|
|
// Fused Vector Multiply Subtract (floating-point)
|
|
def VFMSfd : N3VDMulOp<0, 0, 0b10, 0b1100, 1, IIC_VFMACD, "vfms", "f32",
|
|
v2f32, fmul_su, fsub_mlx>,
|
|
Requires<[HasNEON,HasVFP4,UseFusedMAC]>;
|
|
def VFMSfq : N3VQMulOp<0, 0, 0b10, 0b1100, 1, IIC_VFMACQ, "vfms", "f32",
|
|
v4f32, fmul_su, fsub_mlx>,
|
|
Requires<[HasNEON,HasVFP4,UseFusedMAC]>;
|
|
def VFMShd : N3VDMulOp<0, 0, 0b11, 0b1100, 1, IIC_VFMACD, "vfms", "f16",
|
|
v4f16, fmul, fsub>,
|
|
Requires<[HasNEON,HasFullFP16,UseFusedMAC]>;
|
|
def VFMShq : N3VQMulOp<0, 0, 0b11, 0b1100, 1, IIC_VFMACQ, "vfms", "f16",
|
|
v8f16, fmul, fsub>,
|
|
Requires<[HasNEON,HasFullFP16,UseFusedMAC]>;
|
|
|
|
// Match @llvm.fma.* intrinsics
|
|
def : Pat<(v4f16 (fma DPR:$Vn, DPR:$Vm, DPR:$src1)),
|
|
(VFMAhd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
def : Pat<(v8f16 (fma QPR:$Vn, QPR:$Vm, QPR:$src1)),
|
|
(VFMAhq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
def : Pat<(v2f32 (fma DPR:$Vn, DPR:$Vm, DPR:$src1)),
|
|
(VFMAfd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasVFP4]>;
|
|
def : Pat<(v4f32 (fma QPR:$Vn, QPR:$Vm, QPR:$src1)),
|
|
(VFMAfq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasVFP4]>;
|
|
def : Pat<(v2f32 (fma (fneg DPR:$Vn), DPR:$Vm, DPR:$src1)),
|
|
(VFMSfd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasVFP4]>;
|
|
def : Pat<(v4f32 (fma (fneg QPR:$Vn), QPR:$Vm, QPR:$src1)),
|
|
(VFMSfq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasVFP4]>;
|
|
|
|
// ARMv8.2a dot product instructions.
|
|
// We put them in the VFPV8 decoder namespace because the ARM and Thumb
|
|
// encodings are the same and thus no further bit twiddling is necessary
|
|
// in the disassembler.
|
|
class VDOT<bit op6, bit op4, RegisterClass RegTy, string Asm, string AsmTy,
|
|
ValueType AccumTy, ValueType InputTy,
|
|
SDPatternOperator OpNode> :
|
|
N3Vnp<0b11000, 0b10, 0b1101, op6, op4, (outs RegTy:$dst),
|
|
(ins RegTy:$Vd, RegTy:$Vn, RegTy:$Vm), N3RegFrm, IIC_VDOTPROD,
|
|
Asm, AsmTy,
|
|
[(set (AccumTy RegTy:$dst),
|
|
(OpNode (AccumTy RegTy:$Vd),
|
|
(InputTy RegTy:$Vn),
|
|
(InputTy RegTy:$Vm)))]> {
|
|
let Predicates = [HasDotProd];
|
|
let DecoderNamespace = "VFPV8";
|
|
let Constraints = "$dst = $Vd";
|
|
}
|
|
|
|
def VUDOTD : VDOT<0, 1, DPR, "vudot", "u8", v2i32, v8i8, int_arm_neon_udot>;
|
|
def VSDOTD : VDOT<0, 0, DPR, "vsdot", "s8", v2i32, v8i8, int_arm_neon_sdot>;
|
|
def VUDOTQ : VDOT<1, 1, QPR, "vudot", "u8", v4i32, v16i8, int_arm_neon_udot>;
|
|
def VSDOTQ : VDOT<1, 0, QPR, "vsdot", "s8", v4i32, v16i8, int_arm_neon_sdot>;
|
|
|
|
// Indexed dot product instructions:
|
|
multiclass DOTI<string opc, string dt, bit Q, bit U, RegisterClass Ty,
|
|
ValueType AccumType, ValueType InputType, SDPatternOperator OpNode,
|
|
dag RHS> {
|
|
def "" : N3Vnp<0b11100, 0b10, 0b1101, Q, U, (outs Ty:$dst),
|
|
(ins Ty:$Vd, Ty:$Vn, DPR_VFP2:$Vm, VectorIndex32:$lane),
|
|
N3RegFrm, IIC_VDOTPROD, opc, dt, []> {
|
|
bit lane;
|
|
let Inst{5} = lane;
|
|
let AsmString = !strconcat(opc, ".", dt, "\t$Vd, $Vn, $Vm$lane");
|
|
let Constraints = "$dst = $Vd";
|
|
let Predicates = [HasDotProd];
|
|
let DecoderNamespace = "VFPV8";
|
|
}
|
|
|
|
def : Pat<
|
|
(AccumType (OpNode (AccumType Ty:$Vd),
|
|
(InputType Ty:$Vn),
|
|
(InputType (bitconvert (AccumType
|
|
(NEONvduplane (AccumType Ty:$Vm),
|
|
VectorIndex32:$lane)))))),
|
|
(!cast<Instruction>(NAME) Ty:$Vd, Ty:$Vn, RHS, VectorIndex32:$lane)>;
|
|
}
|
|
|
|
defm VUDOTDI : DOTI<"vudot", "u8", 0b0, 0b1, DPR, v2i32, v8i8,
|
|
int_arm_neon_udot, (v2i32 DPR_VFP2:$Vm)>;
|
|
defm VSDOTDI : DOTI<"vsdot", "s8", 0b0, 0b0, DPR, v2i32, v8i8,
|
|
int_arm_neon_sdot, (v2i32 DPR_VFP2:$Vm)>;
|
|
defm VUDOTQI : DOTI<"vudot", "u8", 0b1, 0b1, QPR, v4i32, v16i8,
|
|
int_arm_neon_udot, (EXTRACT_SUBREG QPR:$Vm, dsub_0)>;
|
|
defm VSDOTQI : DOTI<"vsdot", "s8", 0b1, 0b0, QPR, v4i32, v16i8,
|
|
int_arm_neon_sdot, (EXTRACT_SUBREG QPR:$Vm, dsub_0)>;
|
|
|
|
|
|
// ARMv8.3 complex operations
|
|
class BaseN3VCP8ComplexTied<bit op21, bit op4, bit s, bit q,
|
|
InstrItinClass itin, dag oops, dag iops,
|
|
string opc, string dt, list<dag> pattern>
|
|
: N3VCP8<{?,?}, {op21,s}, q, op4, oops,
|
|
iops, itin, opc, dt, "$Vd, $Vn, $Vm, $rot", "$src1 = $Vd", pattern>{
|
|
bits<2> rot;
|
|
let Inst{24-23} = rot;
|
|
}
|
|
|
|
class BaseN3VCP8ComplexOdd<bit op23, bit op21, bit op4, bit s, bit q,
|
|
InstrItinClass itin, dag oops, dag iops, string opc,
|
|
string dt, list<dag> pattern>
|
|
: N3VCP8<{?,op23}, {op21,s}, q, op4, oops,
|
|
iops, itin, opc, dt, "$Vd, $Vn, $Vm, $rot", "", pattern> {
|
|
bits<1> rot;
|
|
let Inst{24} = rot;
|
|
}
|
|
|
|
class BaseN3VCP8ComplexTiedLane32<bit op4, bit s, bit q, InstrItinClass itin,
|
|
dag oops, dag iops, string opc, string dt,
|
|
list<dag> pattern>
|
|
: N3VLaneCP8<s, {?,?}, q, op4, oops, iops, itin, opc, dt,
|
|
"$Vd, $Vn, $Vm$lane, $rot", "$src1 = $Vd", pattern> {
|
|
bits<2> rot;
|
|
bit lane;
|
|
|
|
let Inst{21-20} = rot;
|
|
let Inst{5} = lane;
|
|
}
|
|
|
|
class BaseN3VCP8ComplexTiedLane64<bit op4, bit s, bit q, InstrItinClass itin,
|
|
dag oops, dag iops, string opc, string dt,
|
|
list<dag> pattern>
|
|
: N3VLaneCP8<s, {?,?}, q, op4, oops, iops, itin, opc, dt,
|
|
"$Vd, $Vn, $Vm$lane, $rot", "$src1 = $Vd", pattern> {
|
|
bits<2> rot;
|
|
bit lane;
|
|
|
|
let Inst{21-20} = rot;
|
|
let Inst{5} = Vm{4};
|
|
// This is needed because the lane operand does not have any bits in the
|
|
// encoding (it only has one possible value), so we need to manually set it
|
|
// to it's default value.
|
|
let DecoderMethod = "DecodeNEONComplexLane64Instruction";
|
|
}
|
|
|
|
multiclass N3VCP8ComplexTied<bit op21, bit op4,
|
|
string OpcodeStr, SDPatternOperator Op> {
|
|
let Predicates = [HasNEON,HasV8_3a,HasFullFP16] in {
|
|
def v4f16 : BaseN3VCP8ComplexTied<op21, op4, 0, 0, IIC_VMACD, (outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vn, DPR:$Vm, complexrotateop:$rot),
|
|
OpcodeStr, "f16", []>;
|
|
def v8f16 : BaseN3VCP8ComplexTied<op21, op4, 0, 1, IIC_VMACQ, (outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vn, QPR:$Vm, complexrotateop:$rot),
|
|
OpcodeStr, "f16", []>;
|
|
}
|
|
let Predicates = [HasNEON,HasV8_3a] in {
|
|
def v2f32 : BaseN3VCP8ComplexTied<op21, op4, 1, 0, IIC_VMACD, (outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vn, DPR:$Vm, complexrotateop:$rot),
|
|
OpcodeStr, "f32", []>;
|
|
def v4f32 : BaseN3VCP8ComplexTied<op21, op4, 1, 1, IIC_VMACQ, (outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vn, QPR:$Vm, complexrotateop:$rot),
|
|
OpcodeStr, "f32", []>;
|
|
}
|
|
}
|
|
|
|
multiclass N3VCP8ComplexOdd<bit op23, bit op21, bit op4,
|
|
string OpcodeStr, SDPatternOperator Op> {
|
|
let Predicates = [HasNEON,HasV8_3a,HasFullFP16] in {
|
|
def v4f16 : BaseN3VCP8ComplexOdd<op23, op21, op4, 0, 0, IIC_VMACD,
|
|
(outs DPR:$Vd),
|
|
(ins DPR:$Vn, DPR:$Vm, complexrotateopodd:$rot),
|
|
OpcodeStr, "f16", []>;
|
|
def v8f16 : BaseN3VCP8ComplexOdd<op23, op21, op4, 0, 1, IIC_VMACQ,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$Vn, QPR:$Vm, complexrotateopodd:$rot),
|
|
OpcodeStr, "f16", []>;
|
|
}
|
|
let Predicates = [HasNEON,HasV8_3a] in {
|
|
def v2f32 : BaseN3VCP8ComplexOdd<op23, op21, op4, 1, 0, IIC_VMACD,
|
|
(outs DPR:$Vd),
|
|
(ins DPR:$Vn, DPR:$Vm, complexrotateopodd:$rot),
|
|
OpcodeStr, "f32", []>;
|
|
def v4f32 : BaseN3VCP8ComplexOdd<op23, op21, op4, 1, 1, IIC_VMACQ,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$Vn, QPR:$Vm, complexrotateopodd:$rot),
|
|
OpcodeStr, "f32", []>;
|
|
}
|
|
}
|
|
|
|
// These instructions index by pairs of lanes, so the VectorIndexes are twice
|
|
// as wide as the data types.
|
|
multiclass N3VCP8ComplexTiedLane<bit op4, string OpcodeStr,
|
|
SDPatternOperator Op> {
|
|
let Predicates = [HasNEON,HasV8_3a,HasFullFP16] in {
|
|
def v4f16_indexed : BaseN3VCP8ComplexTiedLane32<op4, 0, 0, IIC_VMACD,
|
|
(outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vn, DPR_VFP2:$Vm,
|
|
VectorIndex32:$lane, complexrotateop:$rot),
|
|
OpcodeStr, "f16", []>;
|
|
def v8f16_indexed : BaseN3VCP8ComplexTiedLane32<op4, 0, 1, IIC_VMACQ,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vn, DPR_VFP2:$Vm,
|
|
VectorIndex32:$lane, complexrotateop:$rot),
|
|
OpcodeStr, "f16", []>;
|
|
}
|
|
let Predicates = [HasNEON,HasV8_3a] in {
|
|
def v2f32_indexed : BaseN3VCP8ComplexTiedLane64<op4, 1, 0, IIC_VMACD,
|
|
(outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vn, DPR:$Vm, VectorIndex64:$lane,
|
|
complexrotateop:$rot),
|
|
OpcodeStr, "f32", []>;
|
|
def v4f32_indexed : BaseN3VCP8ComplexTiedLane64<op4, 1, 1, IIC_VMACQ,
|
|
(outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vn, DPR:$Vm, VectorIndex64:$lane,
|
|
complexrotateop:$rot),
|
|
OpcodeStr, "f32", []>;
|
|
}
|
|
}
|
|
|
|
defm VCMLA : N3VCP8ComplexTied<1, 0, "vcmla", null_frag>;
|
|
defm VCADD : N3VCP8ComplexOdd<1, 0, 0, "vcadd", null_frag>;
|
|
defm VCMLA : N3VCP8ComplexTiedLane<0, "vcmla", null_frag>;
|
|
|
|
// Vector Subtract Operations.
|
|
|
|
// VSUB : Vector Subtract (integer and floating-point)
|
|
defm VSUB : N3V_QHSD<1, 0, 0b1000, 0, IIC_VSUBiD, IIC_VSUBiQ,
|
|
"vsub", "i", sub, 0>;
|
|
def VSUBfd : N3VD<0, 0, 0b10, 0b1101, 0, IIC_VBIND, "vsub", "f32",
|
|
v2f32, v2f32, fsub, 0>;
|
|
def VSUBfq : N3VQ<0, 0, 0b10, 0b1101, 0, IIC_VBINQ, "vsub", "f32",
|
|
v4f32, v4f32, fsub, 0>;
|
|
def VSUBhd : N3VD<0, 0, 0b11, 0b1101, 0, IIC_VBIND, "vsub", "f16",
|
|
v4f16, v4f16, fsub, 0>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
def VSUBhq : N3VQ<0, 0, 0b11, 0b1101, 0, IIC_VBINQ, "vsub", "f16",
|
|
v8f16, v8f16, fsub, 0>,
|
|
Requires<[HasNEON,HasFullFP16]>;
|
|
// VSUBL : Vector Subtract Long (Q = D - D)
|
|
defm VSUBLs : N3VLExt_QHS<0,1,0b0010,0, IIC_VSHLiD, IIC_VSHLiD,
|
|
"vsubl", "s", sub, sext, 0>;
|
|
defm VSUBLu : N3VLExt_QHS<1,1,0b0010,0, IIC_VSHLiD, IIC_VSHLiD,
|
|
"vsubl", "u", sub, zext, 0>;
|
|
// VSUBW : Vector Subtract Wide (Q = Q - D)
|
|
defm VSUBWs : N3VW_QHS<0,1,0b0011,0, "vsubw", "s", sub, sext, 0>;
|
|
defm VSUBWu : N3VW_QHS<1,1,0b0011,0, "vsubw", "u", sub, zext, 0>;
|
|
// VHSUB : Vector Halving Subtract
|
|
defm VHSUBs : N3VInt_QHS<0, 0, 0b0010, 0, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vhsub", "s", int_arm_neon_vhsubs, 0>;
|
|
defm VHSUBu : N3VInt_QHS<1, 0, 0b0010, 0, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vhsub", "u", int_arm_neon_vhsubu, 0>;
|
|
// VQSUB : Vector Saturing Subtract
|
|
defm VQSUBs : N3VInt_QHSD<0, 0, 0b0010, 1, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vqsub", "s", int_arm_neon_vqsubs, 0>;
|
|
defm VQSUBu : N3VInt_QHSD<1, 0, 0b0010, 1, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vqsub", "u", int_arm_neon_vqsubu, 0>;
|
|
// VSUBHN : Vector Subtract and Narrow Returning High Half (D = Q - Q)
|
|
defm VSUBHN : N3VNInt_HSD<0,1,0b0110,0, "vsubhn", "i", null_frag, 0>;
|
|
// VRSUBHN : Vector Rounding Subtract and Narrow Returning High Half (D=Q-Q)
|
|
defm VRSUBHN : N3VNInt_HSD<1,1,0b0110,0, "vrsubhn", "i",
|
|
int_arm_neon_vrsubhn, 0>;
|
|
|
|
def : Pat<(v8i8 (trunc (NEONvshru (sub (v8i16 QPR:$Vn), QPR:$Vm), 8))),
|
|
(VSUBHNv8i8 QPR:$Vn, QPR:$Vm)>;
|
|
def : Pat<(v4i16 (trunc (NEONvshru (sub (v4i32 QPR:$Vn), QPR:$Vm), 16))),
|
|
(VSUBHNv4i16 QPR:$Vn, QPR:$Vm)>;
|
|
def : Pat<(v2i32 (trunc (NEONvshru (sub (v2i64 QPR:$Vn), QPR:$Vm), 32))),
|
|
(VSUBHNv2i32 QPR:$Vn, QPR:$Vm)>;
|
|
|
|
// Vector Comparisons.
|
|
|
|
// VCEQ : Vector Compare Equal
|
|
defm VCEQ : N3V_QHS<1, 0, 0b1000, 1, IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q,
|
|
IIC_VSUBi4Q, "vceq", "i", NEONvceq, 1>;
|
|
def VCEQfd : N3VD<0,0,0b00,0b1110,0, IIC_VBIND, "vceq", "f32", v2i32, v2f32,
|
|
NEONvceq, 1>;
|
|
def VCEQfq : N3VQ<0,0,0b00,0b1110,0, IIC_VBINQ, "vceq", "f32", v4i32, v4f32,
|
|
NEONvceq, 1>;
|
|
def VCEQhd : N3VD<0,0,0b01,0b1110,0, IIC_VBIND, "vceq", "f16", v4i16, v4f16,
|
|
NEONvceq, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCEQhq : N3VQ<0,0,0b01,0b1110,0, IIC_VBINQ, "vceq", "f16", v8i16, v8f16,
|
|
NEONvceq, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd" in
|
|
defm VCEQz : N2V_QHS_cmp<0b11, 0b11, 0b01, 0b00010, 0, "vceq", "i",
|
|
"$Vd, $Vm, #0", NEONvceqz>;
|
|
|
|
// VCGE : Vector Compare Greater Than or Equal
|
|
defm VCGEs : N3V_QHS<0, 0, 0b0011, 1, IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q,
|
|
IIC_VSUBi4Q, "vcge", "s", NEONvcge, 0>;
|
|
defm VCGEu : N3V_QHS<1, 0, 0b0011, 1, IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q,
|
|
IIC_VSUBi4Q, "vcge", "u", NEONvcgeu, 0>;
|
|
def VCGEfd : N3VD<1,0,0b00,0b1110,0, IIC_VBIND, "vcge", "f32", v2i32, v2f32,
|
|
NEONvcge, 0>;
|
|
def VCGEfq : N3VQ<1,0,0b00,0b1110,0, IIC_VBINQ, "vcge", "f32", v4i32, v4f32,
|
|
NEONvcge, 0>;
|
|
def VCGEhd : N3VD<1,0,0b01,0b1110,0, IIC_VBIND, "vcge", "f16", v4i16, v4f16,
|
|
NEONvcge, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCGEhq : N3VQ<1,0,0b01,0b1110,0, IIC_VBINQ, "vcge", "f16", v8i16, v8f16,
|
|
NEONvcge, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd" in {
|
|
defm VCGEz : N2V_QHS_cmp<0b11, 0b11, 0b01, 0b00001, 0, "vcge", "s",
|
|
"$Vd, $Vm, #0", NEONvcgez>;
|
|
defm VCLEz : N2V_QHS_cmp<0b11, 0b11, 0b01, 0b00011, 0, "vcle", "s",
|
|
"$Vd, $Vm, #0", NEONvclez>;
|
|
}
|
|
|
|
// VCGT : Vector Compare Greater Than
|
|
defm VCGTs : N3V_QHS<0, 0, 0b0011, 0, IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q,
|
|
IIC_VSUBi4Q, "vcgt", "s", NEONvcgt, 0>;
|
|
defm VCGTu : N3V_QHS<1, 0, 0b0011, 0, IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q,
|
|
IIC_VSUBi4Q, "vcgt", "u", NEONvcgtu, 0>;
|
|
def VCGTfd : N3VD<1,0,0b10,0b1110,0, IIC_VBIND, "vcgt", "f32", v2i32, v2f32,
|
|
NEONvcgt, 0>;
|
|
def VCGTfq : N3VQ<1,0,0b10,0b1110,0, IIC_VBINQ, "vcgt", "f32", v4i32, v4f32,
|
|
NEONvcgt, 0>;
|
|
def VCGThd : N3VD<1,0,0b11,0b1110,0, IIC_VBIND, "vcgt", "f16", v4i16, v4f16,
|
|
NEONvcgt, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCGThq : N3VQ<1,0,0b11,0b1110,0, IIC_VBINQ, "vcgt", "f16", v8i16, v8f16,
|
|
NEONvcgt, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
let TwoOperandAliasConstraint = "$Vm = $Vd" in {
|
|
defm VCGTz : N2V_QHS_cmp<0b11, 0b11, 0b01, 0b00000, 0, "vcgt", "s",
|
|
"$Vd, $Vm, #0", NEONvcgtz>;
|
|
defm VCLTz : N2V_QHS_cmp<0b11, 0b11, 0b01, 0b00100, 0, "vclt", "s",
|
|
"$Vd, $Vm, #0", NEONvcltz>;
|
|
}
|
|
|
|
// VACGE : Vector Absolute Compare Greater Than or Equal (aka VCAGE)
|
|
def VACGEfd : N3VDInt<1, 0, 0b00, 0b1110, 1, N3RegFrm, IIC_VBIND, "vacge",
|
|
"f32", v2i32, v2f32, int_arm_neon_vacge, 0>;
|
|
def VACGEfq : N3VQInt<1, 0, 0b00, 0b1110, 1, N3RegFrm, IIC_VBINQ, "vacge",
|
|
"f32", v4i32, v4f32, int_arm_neon_vacge, 0>;
|
|
def VACGEhd : N3VDInt<1, 0, 0b01, 0b1110, 1, N3RegFrm, IIC_VBIND, "vacge",
|
|
"f16", v4i16, v4f16, int_arm_neon_vacge, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VACGEhq : N3VQInt<1, 0, 0b01, 0b1110, 1, N3RegFrm, IIC_VBINQ, "vacge",
|
|
"f16", v8i16, v8f16, int_arm_neon_vacge, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
// VACGT : Vector Absolute Compare Greater Than (aka VCAGT)
|
|
def VACGTfd : N3VDInt<1, 0, 0b10, 0b1110, 1, N3RegFrm, IIC_VBIND, "vacgt",
|
|
"f32", v2i32, v2f32, int_arm_neon_vacgt, 0>;
|
|
def VACGTfq : N3VQInt<1, 0, 0b10, 0b1110, 1, N3RegFrm, IIC_VBINQ, "vacgt",
|
|
"f32", v4i32, v4f32, int_arm_neon_vacgt, 0>;
|
|
def VACGThd : N3VDInt<1, 0, 0b11, 0b1110, 1, N3RegFrm, IIC_VBIND, "vacgt",
|
|
"f16", v4i16, v4f16, int_arm_neon_vacgt, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VACGThq : N3VQInt<1, 0, 0b11, 0b1110, 1, N3RegFrm, IIC_VBINQ, "vacgt",
|
|
"f16", v8i16, v8f16, int_arm_neon_vacgt, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
// VTST : Vector Test Bits
|
|
defm VTST : N3V_QHS<0, 0, 0b1000, 1, IIC_VBINi4D, IIC_VBINi4D, IIC_VBINi4Q,
|
|
IIC_VBINi4Q, "vtst", "", NEONvtst, 1>;
|
|
|
|
def: NEONInstAlias<"vaclt${p}.f32 $Vd, $Vn, $Vm",
|
|
(VACGTfd DPR:$Vd, DPR:$Vm, DPR:$Vn, pred:$p)>;
|
|
def: NEONInstAlias<"vaclt${p}.f32 $Vd, $Vn, $Vm",
|
|
(VACGTfq QPR:$Vd, QPR:$Vm, QPR:$Vn, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f32 $Vd, $Vn, $Vm",
|
|
(VACGEfd DPR:$Vd, DPR:$Vm, DPR:$Vn, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f32 $Vd, $Vn, $Vm",
|
|
(VACGEfq QPR:$Vd, QPR:$Vm, QPR:$Vn, pred:$p)>;
|
|
let Predicates = [HasNEON, HasFullFP16] in {
|
|
def: NEONInstAlias<"vaclt${p}.f16 $Vd, $Vn, $Vm",
|
|
(VACGThd DPR:$Vd, DPR:$Vm, DPR:$Vn, pred:$p)>;
|
|
def: NEONInstAlias<"vaclt${p}.f16 $Vd, $Vn, $Vm",
|
|
(VACGThq QPR:$Vd, QPR:$Vm, QPR:$Vn, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f16 $Vd, $Vn, $Vm",
|
|
(VACGEhd DPR:$Vd, DPR:$Vm, DPR:$Vn, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f16 $Vd, $Vn, $Vm",
|
|
(VACGEhq QPR:$Vd, QPR:$Vm, QPR:$Vn, pred:$p)>;
|
|
}
|
|
|
|
// +fp16fml Floating Point Multiplication Variants
|
|
let Predicates = [HasNEON, HasFP16FML], DecoderNamespace= "VFPV8" in {
|
|
|
|
class N3VCP8F16Q1<string asm, RegisterClass Td, RegisterClass Tn,
|
|
RegisterClass Tm, bits<2> op1, bits<2> op2, bit op3>
|
|
: N3VCP8<op1, op2, 1, op3, (outs Td:$Vd), (ins Tn:$Vn, Tm:$Vm), NoItinerary,
|
|
asm, "f16", "$Vd, $Vn, $Vm", "", []>;
|
|
|
|
class N3VCP8F16Q0<string asm, RegisterClass Td, RegisterClass Tn,
|
|
RegisterClass Tm, bits<2> op1, bits<2> op2, bit op3>
|
|
: N3VCP8Q0<op1, op2, 0, op3, (outs Td:$Vd), (ins Tn:$Vn, Tm:$Vm), NoItinerary,
|
|
asm, "f16", "$Vd, $Vn, $Vm", "", []>;
|
|
|
|
class VFMQ0<string opc, bits<2> S>
|
|
: N3VLaneCP8<0, S, 0, 1, (outs DPR:$Vd),
|
|
(ins SPR:$Vn, SPR:$Vm, VectorIndex32:$idx),
|
|
IIC_VMACD, opc, "f16", "$Vd, $Vn, $Vm$idx", "", []> {
|
|
bit idx;
|
|
let Inst{3} = idx;
|
|
let Inst{19-16} = Vn{4-1};
|
|
let Inst{7} = Vn{0};
|
|
let Inst{5} = Vm{0};
|
|
let Inst{2-0} = Vm{3-1};
|
|
}
|
|
|
|
class VFMQ1<string opc, bits<2> S>
|
|
: N3VLaneCP8<0, S, 1, 1, (outs QPR:$Vd),
|
|
(ins DPR:$Vn, DPR:$Vm, VectorIndex16:$idx),
|
|
IIC_VMACD, opc, "f16", "$Vd, $Vn, $Vm$idx", "", []> {
|
|
bits<2> idx;
|
|
let Inst{5} = idx{1};
|
|
let Inst{3} = idx{0};
|
|
}
|
|
|
|
let hasNoSchedulingInfo = 1 in {
|
|
// op1 op2 op3
|
|
def VFMALD : N3VCP8F16Q0<"vfmal", DPR, SPR, SPR, 0b00, 0b10, 1>;
|
|
def VFMSLD : N3VCP8F16Q0<"vfmsl", DPR, SPR, SPR, 0b01, 0b10, 1>;
|
|
def VFMALQ : N3VCP8F16Q1<"vfmal", QPR, DPR, DPR, 0b00, 0b10, 1>;
|
|
def VFMSLQ : N3VCP8F16Q1<"vfmsl", QPR, DPR, DPR, 0b01, 0b10, 1>;
|
|
def VFMALDI : VFMQ0<"vfmal", 0b00>;
|
|
def VFMSLDI : VFMQ0<"vfmsl", 0b01>;
|
|
def VFMALQI : VFMQ1<"vfmal", 0b00>;
|
|
def VFMSLQI : VFMQ1<"vfmsl", 0b01>;
|
|
}
|
|
} // HasNEON, HasFP16FML
|
|
|
|
|
|
def: NEONInstAlias<"vaclt${p}.f32 $Vd, $Vm",
|
|
(VACGTfd DPR:$Vd, DPR:$Vm, DPR:$Vd, pred:$p)>;
|
|
def: NEONInstAlias<"vaclt${p}.f32 $Vd, $Vm",
|
|
(VACGTfq QPR:$Vd, QPR:$Vm, QPR:$Vd, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f32 $Vd, $Vm",
|
|
(VACGEfd DPR:$Vd, DPR:$Vm, DPR:$Vd, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f32 $Vd, $Vm",
|
|
(VACGEfq QPR:$Vd, QPR:$Vm, QPR:$Vd, pred:$p)>;
|
|
let Predicates = [HasNEON, HasFullFP16] in {
|
|
def: NEONInstAlias<"vaclt${p}.f16 $Vd, $Vm",
|
|
(VACGThd DPR:$Vd, DPR:$Vm, DPR:$Vd, pred:$p)>;
|
|
def: NEONInstAlias<"vaclt${p}.f16 $Vd, $Vm",
|
|
(VACGThq QPR:$Vd, QPR:$Vm, QPR:$Vd, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f16 $Vd, $Vm",
|
|
(VACGEhd DPR:$Vd, DPR:$Vm, DPR:$Vd, pred:$p)>;
|
|
def: NEONInstAlias<"vacle${p}.f16 $Vd, $Vm",
|
|
(VACGEhq QPR:$Vd, QPR:$Vm, QPR:$Vd, pred:$p)>;
|
|
}
|
|
|
|
// Vector Bitwise Operations.
|
|
|
|
def vnotd : PatFrag<(ops node:$in),
|
|
(xor node:$in, (bitconvert (v8i8 NEONimmAllOnesV)))>;
|
|
def vnotq : PatFrag<(ops node:$in),
|
|
(xor node:$in, (bitconvert (v16i8 NEONimmAllOnesV)))>;
|
|
|
|
|
|
// VAND : Vector Bitwise AND
|
|
def VANDd : N3VDX<0, 0, 0b00, 0b0001, 1, IIC_VBINiD, "vand",
|
|
v2i32, v2i32, and, 1>;
|
|
def VANDq : N3VQX<0, 0, 0b00, 0b0001, 1, IIC_VBINiQ, "vand",
|
|
v4i32, v4i32, and, 1>;
|
|
|
|
// VEOR : Vector Bitwise Exclusive OR
|
|
def VEORd : N3VDX<1, 0, 0b00, 0b0001, 1, IIC_VBINiD, "veor",
|
|
v2i32, v2i32, xor, 1>;
|
|
def VEORq : N3VQX<1, 0, 0b00, 0b0001, 1, IIC_VBINiQ, "veor",
|
|
v4i32, v4i32, xor, 1>;
|
|
|
|
// VORR : Vector Bitwise OR
|
|
def VORRd : N3VDX<0, 0, 0b10, 0b0001, 1, IIC_VBINiD, "vorr",
|
|
v2i32, v2i32, or, 1>;
|
|
def VORRq : N3VQX<0, 0, 0b10, 0b0001, 1, IIC_VBINiQ, "vorr",
|
|
v4i32, v4i32, or, 1>;
|
|
|
|
def VORRiv4i16 : N1ModImm<1, 0b000, {1,0,?,1}, 0, 0, 0, 1,
|
|
(outs DPR:$Vd), (ins nImmSplatI16:$SIMM, DPR:$src),
|
|
IIC_VMOVImm,
|
|
"vorr", "i16", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set DPR:$Vd,
|
|
(v4i16 (NEONvorrImm DPR:$src, timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VORRiv2i32 : N1ModImm<1, 0b000, {0,?,?,1}, 0, 0, 0, 1,
|
|
(outs DPR:$Vd), (ins nImmSplatI32:$SIMM, DPR:$src),
|
|
IIC_VMOVImm,
|
|
"vorr", "i32", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set DPR:$Vd,
|
|
(v2i32 (NEONvorrImm DPR:$src, timm:$SIMM)))]> {
|
|
let Inst{10-9} = SIMM{10-9};
|
|
}
|
|
|
|
def VORRiv8i16 : N1ModImm<1, 0b000, {1,0,?,1}, 0, 1, 0, 1,
|
|
(outs QPR:$Vd), (ins nImmSplatI16:$SIMM, QPR:$src),
|
|
IIC_VMOVImm,
|
|
"vorr", "i16", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set QPR:$Vd,
|
|
(v8i16 (NEONvorrImm QPR:$src, timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VORRiv4i32 : N1ModImm<1, 0b000, {0,?,?,1}, 0, 1, 0, 1,
|
|
(outs QPR:$Vd), (ins nImmSplatI32:$SIMM, QPR:$src),
|
|
IIC_VMOVImm,
|
|
"vorr", "i32", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set QPR:$Vd,
|
|
(v4i32 (NEONvorrImm QPR:$src, timm:$SIMM)))]> {
|
|
let Inst{10-9} = SIMM{10-9};
|
|
}
|
|
|
|
|
|
// VBIC : Vector Bitwise Bit Clear (AND NOT)
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd" in {
|
|
def VBICd : N3VX<0, 0, 0b01, 0b0001, 0, 1, (outs DPR:$Vd),
|
|
(ins DPR:$Vn, DPR:$Vm), N3RegFrm, IIC_VBINiD,
|
|
"vbic", "$Vd, $Vn, $Vm", "",
|
|
[(set DPR:$Vd, (v2i32 (and DPR:$Vn,
|
|
(vnotd DPR:$Vm))))]>;
|
|
def VBICq : N3VX<0, 0, 0b01, 0b0001, 1, 1, (outs QPR:$Vd),
|
|
(ins QPR:$Vn, QPR:$Vm), N3RegFrm, IIC_VBINiQ,
|
|
"vbic", "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (v4i32 (and QPR:$Vn,
|
|
(vnotq QPR:$Vm))))]>;
|
|
}
|
|
|
|
def VBICiv4i16 : N1ModImm<1, 0b000, {1,0,?,1}, 0, 0, 1, 1,
|
|
(outs DPR:$Vd), (ins nImmSplatI16:$SIMM, DPR:$src),
|
|
IIC_VMOVImm,
|
|
"vbic", "i16", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set DPR:$Vd,
|
|
(v4i16 (NEONvbicImm DPR:$src, timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VBICiv2i32 : N1ModImm<1, 0b000, {0,?,?,1}, 0, 0, 1, 1,
|
|
(outs DPR:$Vd), (ins nImmSplatI32:$SIMM, DPR:$src),
|
|
IIC_VMOVImm,
|
|
"vbic", "i32", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set DPR:$Vd,
|
|
(v2i32 (NEONvbicImm DPR:$src, timm:$SIMM)))]> {
|
|
let Inst{10-9} = SIMM{10-9};
|
|
}
|
|
|
|
def VBICiv8i16 : N1ModImm<1, 0b000, {1,0,?,1}, 0, 1, 1, 1,
|
|
(outs QPR:$Vd), (ins nImmSplatI16:$SIMM, QPR:$src),
|
|
IIC_VMOVImm,
|
|
"vbic", "i16", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set QPR:$Vd,
|
|
(v8i16 (NEONvbicImm QPR:$src, timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VBICiv4i32 : N1ModImm<1, 0b000, {0,?,?,1}, 0, 1, 1, 1,
|
|
(outs QPR:$Vd), (ins nImmSplatI32:$SIMM, QPR:$src),
|
|
IIC_VMOVImm,
|
|
"vbic", "i32", "$Vd, $SIMM", "$src = $Vd",
|
|
[(set QPR:$Vd,
|
|
(v4i32 (NEONvbicImm QPR:$src, timm:$SIMM)))]> {
|
|
let Inst{10-9} = SIMM{10-9};
|
|
}
|
|
|
|
// VORN : Vector Bitwise OR NOT
|
|
def VORNd : N3VX<0, 0, 0b11, 0b0001, 0, 1, (outs DPR:$Vd),
|
|
(ins DPR:$Vn, DPR:$Vm), N3RegFrm, IIC_VBINiD,
|
|
"vorn", "$Vd, $Vn, $Vm", "",
|
|
[(set DPR:$Vd, (v2i32 (or DPR:$Vn,
|
|
(vnotd DPR:$Vm))))]>;
|
|
def VORNq : N3VX<0, 0, 0b11, 0b0001, 1, 1, (outs QPR:$Vd),
|
|
(ins QPR:$Vn, QPR:$Vm), N3RegFrm, IIC_VBINiQ,
|
|
"vorn", "$Vd, $Vn, $Vm", "",
|
|
[(set QPR:$Vd, (v4i32 (or QPR:$Vn,
|
|
(vnotq QPR:$Vm))))]>;
|
|
|
|
// VMVN : Vector Bitwise NOT (Immediate)
|
|
|
|
let isReMaterializable = 1 in {
|
|
|
|
def VMVNv4i16 : N1ModImm<1, 0b000, {1,0,?,0}, 0, 0, 1, 1, (outs DPR:$Vd),
|
|
(ins nImmSplatI16:$SIMM), IIC_VMOVImm,
|
|
"vmvn", "i16", "$Vd, $SIMM", "",
|
|
[(set DPR:$Vd, (v4i16 (NEONvmvnImm timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VMVNv8i16 : N1ModImm<1, 0b000, {1,0,?,0}, 0, 1, 1, 1, (outs QPR:$Vd),
|
|
(ins nImmSplatI16:$SIMM), IIC_VMOVImm,
|
|
"vmvn", "i16", "$Vd, $SIMM", "",
|
|
[(set QPR:$Vd, (v8i16 (NEONvmvnImm timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VMVNv2i32 : N1ModImm<1, 0b000, {?,?,?,?}, 0, 0, 1, 1, (outs DPR:$Vd),
|
|
(ins nImmVMOVI32:$SIMM), IIC_VMOVImm,
|
|
"vmvn", "i32", "$Vd, $SIMM", "",
|
|
[(set DPR:$Vd, (v2i32 (NEONvmvnImm timm:$SIMM)))]> {
|
|
let Inst{11-8} = SIMM{11-8};
|
|
}
|
|
|
|
def VMVNv4i32 : N1ModImm<1, 0b000, {?,?,?,?}, 0, 1, 1, 1, (outs QPR:$Vd),
|
|
(ins nImmVMOVI32:$SIMM), IIC_VMOVImm,
|
|
"vmvn", "i32", "$Vd, $SIMM", "",
|
|
[(set QPR:$Vd, (v4i32 (NEONvmvnImm timm:$SIMM)))]> {
|
|
let Inst{11-8} = SIMM{11-8};
|
|
}
|
|
}
|
|
|
|
// VMVN : Vector Bitwise NOT
|
|
def VMVNd : N2VX<0b11, 0b11, 0b00, 0b00, 0b01011, 0, 0,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), IIC_VSUBiD,
|
|
"vmvn", "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (v2i32 (vnotd DPR:$Vm)))]>;
|
|
def VMVNq : N2VX<0b11, 0b11, 0b00, 0b00, 0b01011, 1, 0,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), IIC_VSUBiD,
|
|
"vmvn", "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (v4i32 (vnotq QPR:$Vm)))]>;
|
|
def : Pat<(v2i32 (vnotd DPR:$src)), (VMVNd DPR:$src)>;
|
|
def : Pat<(v4i32 (vnotq QPR:$src)), (VMVNq QPR:$src)>;
|
|
|
|
// VBSL : Vector Bitwise Select
|
|
def VBSLd : N3VX<1, 0, 0b01, 0b0001, 0, 1, (outs DPR:$Vd),
|
|
(ins DPR:$src1, DPR:$Vn, DPR:$Vm),
|
|
N3RegFrm, IIC_VCNTiD,
|
|
"vbsl", "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set DPR:$Vd,
|
|
(v2i32 (NEONvbsl DPR:$src1, DPR:$Vn, DPR:$Vm)))]>;
|
|
def : Pat<(v8i8 (int_arm_neon_vbsl (v8i8 DPR:$src1),
|
|
(v8i8 DPR:$Vn), (v8i8 DPR:$Vm))),
|
|
(VBSLd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v4i16 (int_arm_neon_vbsl (v4i16 DPR:$src1),
|
|
(v4i16 DPR:$Vn), (v4i16 DPR:$Vm))),
|
|
(VBSLd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v2i32 (int_arm_neon_vbsl (v2i32 DPR:$src1),
|
|
(v2i32 DPR:$Vn), (v2i32 DPR:$Vm))),
|
|
(VBSLd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v2f32 (int_arm_neon_vbsl (v2f32 DPR:$src1),
|
|
(v2f32 DPR:$Vn), (v2f32 DPR:$Vm))),
|
|
(VBSLd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v1i64 (int_arm_neon_vbsl (v1i64 DPR:$src1),
|
|
(v1i64 DPR:$Vn), (v1i64 DPR:$Vm))),
|
|
(VBSLd DPR:$src1, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
|
|
def : Pat<(v2i32 (or (and DPR:$Vn, DPR:$Vd),
|
|
(and DPR:$Vm, (vnotd DPR:$Vd)))),
|
|
(VBSLd DPR:$Vd, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
|
|
def : Pat<(v1i64 (or (and DPR:$Vn, DPR:$Vd),
|
|
(and DPR:$Vm, (vnotd DPR:$Vd)))),
|
|
(VBSLd DPR:$Vd, DPR:$Vn, DPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
|
|
def VBSLq : N3VX<1, 0, 0b01, 0b0001, 1, 1, (outs QPR:$Vd),
|
|
(ins QPR:$src1, QPR:$Vn, QPR:$Vm),
|
|
N3RegFrm, IIC_VCNTiQ,
|
|
"vbsl", "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[(set QPR:$Vd,
|
|
(v4i32 (NEONvbsl QPR:$src1, QPR:$Vn, QPR:$Vm)))]>;
|
|
|
|
def : Pat<(v16i8 (int_arm_neon_vbsl (v16i8 QPR:$src1),
|
|
(v16i8 QPR:$Vn), (v16i8 QPR:$Vm))),
|
|
(VBSLq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v8i16 (int_arm_neon_vbsl (v8i16 QPR:$src1),
|
|
(v8i16 QPR:$Vn), (v8i16 QPR:$Vm))),
|
|
(VBSLq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v4i32 (int_arm_neon_vbsl (v4i32 QPR:$src1),
|
|
(v4i32 QPR:$Vn), (v4i32 QPR:$Vm))),
|
|
(VBSLq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v4f32 (int_arm_neon_vbsl (v4f32 QPR:$src1),
|
|
(v4f32 QPR:$Vn), (v4f32 QPR:$Vm))),
|
|
(VBSLq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v2i64 (int_arm_neon_vbsl (v2i64 QPR:$src1),
|
|
(v2i64 QPR:$Vn), (v2i64 QPR:$Vm))),
|
|
(VBSLq QPR:$src1, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
|
|
def : Pat<(v4i32 (or (and QPR:$Vn, QPR:$Vd),
|
|
(and QPR:$Vm, (vnotq QPR:$Vd)))),
|
|
(VBSLq QPR:$Vd, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
def : Pat<(v2i64 (or (and QPR:$Vn, QPR:$Vd),
|
|
(and QPR:$Vm, (vnotq QPR:$Vd)))),
|
|
(VBSLq QPR:$Vd, QPR:$Vn, QPR:$Vm)>,
|
|
Requires<[HasNEON]>;
|
|
|
|
// VBIF : Vector Bitwise Insert if False
|
|
// like VBSL but with: "vbif $dst, $src3, $src1", "$src2 = $dst",
|
|
// FIXME: This instruction's encoding MAY NOT BE correct.
|
|
def VBIFd : N3VX<1, 0, 0b11, 0b0001, 0, 1,
|
|
(outs DPR:$Vd), (ins DPR:$src1, DPR:$Vn, DPR:$Vm),
|
|
N3RegFrm, IIC_VBINiD,
|
|
"vbif", "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[]>;
|
|
def VBIFq : N3VX<1, 0, 0b11, 0b0001, 1, 1,
|
|
(outs QPR:$Vd), (ins QPR:$src1, QPR:$Vn, QPR:$Vm),
|
|
N3RegFrm, IIC_VBINiQ,
|
|
"vbif", "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[]>;
|
|
|
|
// VBIT : Vector Bitwise Insert if True
|
|
// like VBSL but with: "vbit $dst, $src2, $src1", "$src3 = $dst",
|
|
// FIXME: This instruction's encoding MAY NOT BE correct.
|
|
def VBITd : N3VX<1, 0, 0b10, 0b0001, 0, 1,
|
|
(outs DPR:$Vd), (ins DPR:$src1, DPR:$Vn, DPR:$Vm),
|
|
N3RegFrm, IIC_VBINiD,
|
|
"vbit", "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[]>;
|
|
def VBITq : N3VX<1, 0, 0b10, 0b0001, 1, 1,
|
|
(outs QPR:$Vd), (ins QPR:$src1, QPR:$Vn, QPR:$Vm),
|
|
N3RegFrm, IIC_VBINiQ,
|
|
"vbit", "$Vd, $Vn, $Vm", "$src1 = $Vd",
|
|
[]>;
|
|
|
|
// VBIT/VBIF are not yet implemented. The TwoAddress pass will not go looking
|
|
// for equivalent operations with different register constraints; it just
|
|
// inserts copies.
|
|
|
|
// Vector Absolute Differences.
|
|
|
|
// VABD : Vector Absolute Difference
|
|
defm VABDs : N3VInt_QHS<0, 0, 0b0111, 0, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vabd", "s", int_arm_neon_vabds, 1>;
|
|
defm VABDu : N3VInt_QHS<1, 0, 0b0111, 0, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vabd", "u", int_arm_neon_vabdu, 1>;
|
|
def VABDfd : N3VDInt<1, 0, 0b10, 0b1101, 0, N3RegFrm, IIC_VBIND,
|
|
"vabd", "f32", v2f32, v2f32, int_arm_neon_vabds, 1>;
|
|
def VABDfq : N3VQInt<1, 0, 0b10, 0b1101, 0, N3RegFrm, IIC_VBINQ,
|
|
"vabd", "f32", v4f32, v4f32, int_arm_neon_vabds, 1>;
|
|
def VABDhd : N3VDInt<1, 0, 0b11, 0b1101, 0, N3RegFrm, IIC_VBIND,
|
|
"vabd", "f16", v4f16, v4f16, int_arm_neon_vabds, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VABDhq : N3VQInt<1, 0, 0b11, 0b1101, 0, N3RegFrm, IIC_VBINQ,
|
|
"vabd", "f16", v8f16, v8f16, int_arm_neon_vabds, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VABDL : Vector Absolute Difference Long (Q = | D - D |)
|
|
defm VABDLs : N3VLIntExt_QHS<0,1,0b0111,0, IIC_VSUBi4Q,
|
|
"vabdl", "s", int_arm_neon_vabds, zext, 1>;
|
|
defm VABDLu : N3VLIntExt_QHS<1,1,0b0111,0, IIC_VSUBi4Q,
|
|
"vabdl", "u", int_arm_neon_vabdu, zext, 1>;
|
|
|
|
def : Pat<(v8i16 (abs (sub (zext (v8i8 DPR:$opA)), (zext (v8i8 DPR:$opB))))),
|
|
(VABDLuv8i16 DPR:$opA, DPR:$opB)>;
|
|
def : Pat<(v4i32 (abs (sub (zext (v4i16 DPR:$opA)), (zext (v4i16 DPR:$opB))))),
|
|
(VABDLuv4i32 DPR:$opA, DPR:$opB)>;
|
|
|
|
// ISD::ABS is not legal for v2i64, so VABDL needs to be matched from the
|
|
// shift/xor pattern for ABS.
|
|
|
|
def abd_shr :
|
|
PatFrag<(ops node:$in1, node:$in2, node:$shift),
|
|
(NEONvshrs (sub (zext node:$in1),
|
|
(zext node:$in2)), (i32 $shift))>;
|
|
|
|
def : Pat<(xor (v4i32 (bitconvert (v2i64 (abd_shr (v2i32 DPR:$opA), (v2i32 DPR:$opB), 63)))),
|
|
(v4i32 (bitconvert (v2i64 (add (sub (zext (v2i32 DPR:$opA)),
|
|
(zext (v2i32 DPR:$opB))),
|
|
(abd_shr (v2i32 DPR:$opA), (v2i32 DPR:$opB), 63)))))),
|
|
(VABDLuv2i64 DPR:$opA, DPR:$opB)>;
|
|
|
|
// VABA : Vector Absolute Difference and Accumulate
|
|
defm VABAs : N3VIntOp_QHS<0,0,0b0111,1, IIC_VABAD, IIC_VABAQ,
|
|
"vaba", "s", int_arm_neon_vabds, add>;
|
|
defm VABAu : N3VIntOp_QHS<1,0,0b0111,1, IIC_VABAD, IIC_VABAQ,
|
|
"vaba", "u", int_arm_neon_vabdu, add>;
|
|
|
|
// VABAL : Vector Absolute Difference and Accumulate Long (Q += | D - D |)
|
|
defm VABALs : N3VLIntExtOp_QHS<0,1,0b0101,0, IIC_VABAD,
|
|
"vabal", "s", int_arm_neon_vabds, zext, add>;
|
|
defm VABALu : N3VLIntExtOp_QHS<1,1,0b0101,0, IIC_VABAD,
|
|
"vabal", "u", int_arm_neon_vabdu, zext, add>;
|
|
|
|
// Vector Maximum and Minimum.
|
|
|
|
// VMAX : Vector Maximum
|
|
defm VMAXs : N3VInt_QHS<0, 0, 0b0110, 0, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vmax", "s", smax, 1>;
|
|
defm VMAXu : N3VInt_QHS<1, 0, 0b0110, 0, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vmax", "u", umax, 1>;
|
|
def VMAXfd : N3VDInt<0, 0, 0b00, 0b1111, 0, N3RegFrm, IIC_VBIND,
|
|
"vmax", "f32",
|
|
v2f32, v2f32, fmaxnan, 1>;
|
|
def VMAXfq : N3VQInt<0, 0, 0b00, 0b1111, 0, N3RegFrm, IIC_VBINQ,
|
|
"vmax", "f32",
|
|
v4f32, v4f32, fmaxnan, 1>;
|
|
def VMAXhd : N3VDInt<0, 0, 0b01, 0b1111, 0, N3RegFrm, IIC_VBIND,
|
|
"vmax", "f16",
|
|
v4f16, v4f16, fmaxnan, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VMAXhq : N3VQInt<0, 0, 0b01, 0b1111, 0, N3RegFrm, IIC_VBINQ,
|
|
"vmax", "f16",
|
|
v8f16, v8f16, fmaxnan, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VMAXNM
|
|
let PostEncoderMethod = "NEONThumb2V8PostEncoder", DecoderNamespace = "v8NEON" in {
|
|
def VMAXNMNDf : N3VDIntnp<0b00110, 0b00, 0b1111, 0, 1,
|
|
N3RegFrm, NoItinerary, "vmaxnm", "f32",
|
|
v2f32, v2f32, fmaxnum, 1>,
|
|
Requires<[HasV8, HasNEON]>;
|
|
def VMAXNMNQf : N3VQIntnp<0b00110, 0b00, 0b1111, 1, 1,
|
|
N3RegFrm, NoItinerary, "vmaxnm", "f32",
|
|
v4f32, v4f32, fmaxnum, 1>,
|
|
Requires<[HasV8, HasNEON]>;
|
|
def VMAXNMNDh : N3VDIntnp<0b00110, 0b01, 0b1111, 0, 1,
|
|
N3RegFrm, NoItinerary, "vmaxnm", "f16",
|
|
v4f16, v4f16, fmaxnum, 1>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
def VMAXNMNQh : N3VQIntnp<0b00110, 0b01, 0b1111, 1, 1,
|
|
N3RegFrm, NoItinerary, "vmaxnm", "f16",
|
|
v8f16, v8f16, fmaxnum, 1>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
}
|
|
|
|
// VMIN : Vector Minimum
|
|
defm VMINs : N3VInt_QHS<0, 0, 0b0110, 1, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vmin", "s", smin, 1>;
|
|
defm VMINu : N3VInt_QHS<1, 0, 0b0110, 1, N3RegFrm,
|
|
IIC_VSUBi4D, IIC_VSUBi4D, IIC_VSUBi4Q, IIC_VSUBi4Q,
|
|
"vmin", "u", umin, 1>;
|
|
def VMINfd : N3VDInt<0, 0, 0b10, 0b1111, 0, N3RegFrm, IIC_VBIND,
|
|
"vmin", "f32",
|
|
v2f32, v2f32, fminnan, 1>;
|
|
def VMINfq : N3VQInt<0, 0, 0b10, 0b1111, 0, N3RegFrm, IIC_VBINQ,
|
|
"vmin", "f32",
|
|
v4f32, v4f32, fminnan, 1>;
|
|
def VMINhd : N3VDInt<0, 0, 0b11, 0b1111, 0, N3RegFrm, IIC_VBIND,
|
|
"vmin", "f16",
|
|
v4f16, v4f16, fminnan, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VMINhq : N3VQInt<0, 0, 0b11, 0b1111, 0, N3RegFrm, IIC_VBINQ,
|
|
"vmin", "f16",
|
|
v8f16, v8f16, fminnan, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VMINNM
|
|
let PostEncoderMethod = "NEONThumb2V8PostEncoder", DecoderNamespace = "v8NEON" in {
|
|
def VMINNMNDf : N3VDIntnp<0b00110, 0b10, 0b1111, 0, 1,
|
|
N3RegFrm, NoItinerary, "vminnm", "f32",
|
|
v2f32, v2f32, fminnum, 1>,
|
|
Requires<[HasV8, HasNEON]>;
|
|
def VMINNMNQf : N3VQIntnp<0b00110, 0b10, 0b1111, 1, 1,
|
|
N3RegFrm, NoItinerary, "vminnm", "f32",
|
|
v4f32, v4f32, fminnum, 1>,
|
|
Requires<[HasV8, HasNEON]>;
|
|
def VMINNMNDh : N3VDIntnp<0b00110, 0b11, 0b1111, 0, 1,
|
|
N3RegFrm, NoItinerary, "vminnm", "f16",
|
|
v4f16, v4f16, fminnum, 1>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
def VMINNMNQh : N3VQIntnp<0b00110, 0b11, 0b1111, 1, 1,
|
|
N3RegFrm, NoItinerary, "vminnm", "f16",
|
|
v8f16, v8f16, fminnum, 1>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
}
|
|
|
|
// Vector Pairwise Operations.
|
|
|
|
// VPADD : Vector Pairwise Add
|
|
def VPADDi8 : N3VDInt<0, 0, 0b00, 0b1011, 1, N3RegFrm, IIC_VSHLiD,
|
|
"vpadd", "i8",
|
|
v8i8, v8i8, int_arm_neon_vpadd, 0>;
|
|
def VPADDi16 : N3VDInt<0, 0, 0b01, 0b1011, 1, N3RegFrm, IIC_VSHLiD,
|
|
"vpadd", "i16",
|
|
v4i16, v4i16, int_arm_neon_vpadd, 0>;
|
|
def VPADDi32 : N3VDInt<0, 0, 0b10, 0b1011, 1, N3RegFrm, IIC_VSHLiD,
|
|
"vpadd", "i32",
|
|
v2i32, v2i32, int_arm_neon_vpadd, 0>;
|
|
def VPADDf : N3VDInt<1, 0, 0b00, 0b1101, 0, N3RegFrm,
|
|
IIC_VPBIND, "vpadd", "f32",
|
|
v2f32, v2f32, int_arm_neon_vpadd, 0>;
|
|
def VPADDh : N3VDInt<1, 0, 0b01, 0b1101, 0, N3RegFrm,
|
|
IIC_VPBIND, "vpadd", "f16",
|
|
v4f16, v4f16, int_arm_neon_vpadd, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VPADDL : Vector Pairwise Add Long
|
|
defm VPADDLs : N2VPLInt_QHS<0b11, 0b11, 0b00, 0b00100, 0, "vpaddl", "s",
|
|
int_arm_neon_vpaddls>;
|
|
defm VPADDLu : N2VPLInt_QHS<0b11, 0b11, 0b00, 0b00101, 0, "vpaddl", "u",
|
|
int_arm_neon_vpaddlu>;
|
|
|
|
// VPADAL : Vector Pairwise Add and Accumulate Long
|
|
defm VPADALs : N2VPLInt2_QHS<0b11, 0b11, 0b00, 0b01100, 0, "vpadal", "s",
|
|
int_arm_neon_vpadals>;
|
|
defm VPADALu : N2VPLInt2_QHS<0b11, 0b11, 0b00, 0b01101, 0, "vpadal", "u",
|
|
int_arm_neon_vpadalu>;
|
|
|
|
// VPMAX : Vector Pairwise Maximum
|
|
def VPMAXs8 : N3VDInt<0, 0, 0b00, 0b1010, 0, N3RegFrm, IIC_VSUBi4D, "vpmax",
|
|
"s8", v8i8, v8i8, int_arm_neon_vpmaxs, 0>;
|
|
def VPMAXs16 : N3VDInt<0, 0, 0b01, 0b1010, 0, N3RegFrm, IIC_VSUBi4D, "vpmax",
|
|
"s16", v4i16, v4i16, int_arm_neon_vpmaxs, 0>;
|
|
def VPMAXs32 : N3VDInt<0, 0, 0b10, 0b1010, 0, N3RegFrm, IIC_VSUBi4D, "vpmax",
|
|
"s32", v2i32, v2i32, int_arm_neon_vpmaxs, 0>;
|
|
def VPMAXu8 : N3VDInt<1, 0, 0b00, 0b1010, 0, N3RegFrm, IIC_VSUBi4D, "vpmax",
|
|
"u8", v8i8, v8i8, int_arm_neon_vpmaxu, 0>;
|
|
def VPMAXu16 : N3VDInt<1, 0, 0b01, 0b1010, 0, N3RegFrm, IIC_VSUBi4D, "vpmax",
|
|
"u16", v4i16, v4i16, int_arm_neon_vpmaxu, 0>;
|
|
def VPMAXu32 : N3VDInt<1, 0, 0b10, 0b1010, 0, N3RegFrm, IIC_VSUBi4D, "vpmax",
|
|
"u32", v2i32, v2i32, int_arm_neon_vpmaxu, 0>;
|
|
def VPMAXf : N3VDInt<1, 0, 0b00, 0b1111, 0, N3RegFrm, IIC_VPBIND, "vpmax",
|
|
"f32", v2f32, v2f32, int_arm_neon_vpmaxs, 0>;
|
|
def VPMAXh : N3VDInt<1, 0, 0b01, 0b1111, 0, N3RegFrm, IIC_VPBIND, "vpmax",
|
|
"f16", v4f16, v4f16, int_arm_neon_vpmaxs, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VPMIN : Vector Pairwise Minimum
|
|
def VPMINs8 : N3VDInt<0, 0, 0b00, 0b1010, 1, N3RegFrm, IIC_VSUBi4D, "vpmin",
|
|
"s8", v8i8, v8i8, int_arm_neon_vpmins, 0>;
|
|
def VPMINs16 : N3VDInt<0, 0, 0b01, 0b1010, 1, N3RegFrm, IIC_VSUBi4D, "vpmin",
|
|
"s16", v4i16, v4i16, int_arm_neon_vpmins, 0>;
|
|
def VPMINs32 : N3VDInt<0, 0, 0b10, 0b1010, 1, N3RegFrm, IIC_VSUBi4D, "vpmin",
|
|
"s32", v2i32, v2i32, int_arm_neon_vpmins, 0>;
|
|
def VPMINu8 : N3VDInt<1, 0, 0b00, 0b1010, 1, N3RegFrm, IIC_VSUBi4D, "vpmin",
|
|
"u8", v8i8, v8i8, int_arm_neon_vpminu, 0>;
|
|
def VPMINu16 : N3VDInt<1, 0, 0b01, 0b1010, 1, N3RegFrm, IIC_VSUBi4D, "vpmin",
|
|
"u16", v4i16, v4i16, int_arm_neon_vpminu, 0>;
|
|
def VPMINu32 : N3VDInt<1, 0, 0b10, 0b1010, 1, N3RegFrm, IIC_VSUBi4D, "vpmin",
|
|
"u32", v2i32, v2i32, int_arm_neon_vpminu, 0>;
|
|
def VPMINf : N3VDInt<1, 0, 0b10, 0b1111, 0, N3RegFrm, IIC_VPBIND, "vpmin",
|
|
"f32", v2f32, v2f32, int_arm_neon_vpmins, 0>;
|
|
def VPMINh : N3VDInt<1, 0, 0b11, 0b1111, 0, N3RegFrm, IIC_VPBIND, "vpmin",
|
|
"f16", v4f16, v4f16, int_arm_neon_vpmins, 0>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// Vector Reciprocal and Reciprocal Square Root Estimate and Step.
|
|
|
|
// VRECPE : Vector Reciprocal Estimate
|
|
def VRECPEd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01000, 0,
|
|
IIC_VUNAD, "vrecpe", "u32",
|
|
v2i32, v2i32, int_arm_neon_vrecpe>;
|
|
def VRECPEq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01000, 0,
|
|
IIC_VUNAQ, "vrecpe", "u32",
|
|
v4i32, v4i32, int_arm_neon_vrecpe>;
|
|
def VRECPEfd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01010, 0,
|
|
IIC_VUNAD, "vrecpe", "f32",
|
|
v2f32, v2f32, int_arm_neon_vrecpe>;
|
|
def VRECPEfq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01010, 0,
|
|
IIC_VUNAQ, "vrecpe", "f32",
|
|
v4f32, v4f32, int_arm_neon_vrecpe>;
|
|
def VRECPEhd : N2VDInt<0b11, 0b11, 0b01, 0b11, 0b01010, 0,
|
|
IIC_VUNAD, "vrecpe", "f16",
|
|
v4f16, v4f16, int_arm_neon_vrecpe>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VRECPEhq : N2VQInt<0b11, 0b11, 0b01, 0b11, 0b01010, 0,
|
|
IIC_VUNAQ, "vrecpe", "f16",
|
|
v8f16, v8f16, int_arm_neon_vrecpe>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VRECPS : Vector Reciprocal Step
|
|
def VRECPSfd : N3VDInt<0, 0, 0b00, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSD, "vrecps", "f32",
|
|
v2f32, v2f32, int_arm_neon_vrecps, 1>;
|
|
def VRECPSfq : N3VQInt<0, 0, 0b00, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSQ, "vrecps", "f32",
|
|
v4f32, v4f32, int_arm_neon_vrecps, 1>;
|
|
def VRECPShd : N3VDInt<0, 0, 0b01, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSD, "vrecps", "f16",
|
|
v4f16, v4f16, int_arm_neon_vrecps, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VRECPShq : N3VQInt<0, 0, 0b01, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSQ, "vrecps", "f16",
|
|
v8f16, v8f16, int_arm_neon_vrecps, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VRSQRTE : Vector Reciprocal Square Root Estimate
|
|
def VRSQRTEd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01001, 0,
|
|
IIC_VUNAD, "vrsqrte", "u32",
|
|
v2i32, v2i32, int_arm_neon_vrsqrte>;
|
|
def VRSQRTEq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01001, 0,
|
|
IIC_VUNAQ, "vrsqrte", "u32",
|
|
v4i32, v4i32, int_arm_neon_vrsqrte>;
|
|
def VRSQRTEfd : N2VDInt<0b11, 0b11, 0b10, 0b11, 0b01011, 0,
|
|
IIC_VUNAD, "vrsqrte", "f32",
|
|
v2f32, v2f32, int_arm_neon_vrsqrte>;
|
|
def VRSQRTEfq : N2VQInt<0b11, 0b11, 0b10, 0b11, 0b01011, 0,
|
|
IIC_VUNAQ, "vrsqrte", "f32",
|
|
v4f32, v4f32, int_arm_neon_vrsqrte>;
|
|
def VRSQRTEhd : N2VDInt<0b11, 0b11, 0b01, 0b11, 0b01011, 0,
|
|
IIC_VUNAD, "vrsqrte", "f16",
|
|
v4f16, v4f16, int_arm_neon_vrsqrte>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VRSQRTEhq : N2VQInt<0b11, 0b11, 0b01, 0b11, 0b01011, 0,
|
|
IIC_VUNAQ, "vrsqrte", "f16",
|
|
v8f16, v8f16, int_arm_neon_vrsqrte>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VRSQRTS : Vector Reciprocal Square Root Step
|
|
def VRSQRTSfd : N3VDInt<0, 0, 0b10, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSD, "vrsqrts", "f32",
|
|
v2f32, v2f32, int_arm_neon_vrsqrts, 1>;
|
|
def VRSQRTSfq : N3VQInt<0, 0, 0b10, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSQ, "vrsqrts", "f32",
|
|
v4f32, v4f32, int_arm_neon_vrsqrts, 1>;
|
|
def VRSQRTShd : N3VDInt<0, 0, 0b11, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSD, "vrsqrts", "f16",
|
|
v4f16, v4f16, int_arm_neon_vrsqrts, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VRSQRTShq : N3VQInt<0, 0, 0b11, 0b1111, 1, N3RegFrm,
|
|
IIC_VRECSQ, "vrsqrts", "f16",
|
|
v8f16, v8f16, int_arm_neon_vrsqrts, 1>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// Vector Shifts.
|
|
|
|
// VSHL : Vector Shift
|
|
defm VSHLs : N3VInt_QHSDSh<0, 0, 0b0100, 0, N3RegVShFrm,
|
|
IIC_VSHLiD, IIC_VSHLiD, IIC_VSHLiQ, IIC_VSHLiQ,
|
|
"vshl", "s", int_arm_neon_vshifts>;
|
|
defm VSHLu : N3VInt_QHSDSh<1, 0, 0b0100, 0, N3RegVShFrm,
|
|
IIC_VSHLiD, IIC_VSHLiD, IIC_VSHLiQ, IIC_VSHLiQ,
|
|
"vshl", "u", int_arm_neon_vshiftu>;
|
|
|
|
// VSHL : Vector Shift Left (Immediate)
|
|
defm VSHLi : N2VShL_QHSD<0, 1, 0b0101, 1, IIC_VSHLiD, "vshl", "i", NEONvshl>;
|
|
|
|
// VSHR : Vector Shift Right (Immediate)
|
|
defm VSHRs : N2VShR_QHSD<0, 1, 0b0000, 1, IIC_VSHLiD, "vshr", "s", "VSHRs",
|
|
NEONvshrs>;
|
|
defm VSHRu : N2VShR_QHSD<1, 1, 0b0000, 1, IIC_VSHLiD, "vshr", "u", "VSHRu",
|
|
NEONvshru>;
|
|
|
|
// VSHLL : Vector Shift Left Long
|
|
defm VSHLLs : N2VLSh_QHS<0, 1, 0b1010, 0, 0, 1, "vshll", "s",
|
|
PatFrag<(ops node:$LHS, node:$RHS), (NEONvshl (sext node:$LHS), node:$RHS)>>;
|
|
defm VSHLLu : N2VLSh_QHS<1, 1, 0b1010, 0, 0, 1, "vshll", "u",
|
|
PatFrag<(ops node:$LHS, node:$RHS), (NEONvshl (zext node:$LHS), node:$RHS)>>;
|
|
|
|
// VSHLL : Vector Shift Left Long (with maximum shift count)
|
|
class N2VLShMax<bit op24, bit op23, bits<6> op21_16, bits<4> op11_8, bit op7,
|
|
bit op6, bit op4, string OpcodeStr, string Dt, ValueType ResTy,
|
|
ValueType OpTy, Operand ImmTy>
|
|
: N2VLSh<op24, op23, op11_8, op7, op6, op4, OpcodeStr, Dt,
|
|
ResTy, OpTy, ImmTy, null_frag> {
|
|
let Inst{21-16} = op21_16;
|
|
let DecoderMethod = "DecodeVSHLMaxInstruction";
|
|
}
|
|
def VSHLLi8 : N2VLShMax<1, 1, 0b110010, 0b0011, 0, 0, 0, "vshll", "i8",
|
|
v8i16, v8i8, imm8>;
|
|
def VSHLLi16 : N2VLShMax<1, 1, 0b110110, 0b0011, 0, 0, 0, "vshll", "i16",
|
|
v4i32, v4i16, imm16>;
|
|
def VSHLLi32 : N2VLShMax<1, 1, 0b111010, 0b0011, 0, 0, 0, "vshll", "i32",
|
|
v2i64, v2i32, imm32>;
|
|
|
|
def : Pat<(v8i16 (NEONvshl (zext (v8i8 DPR:$Rn)), (i32 8))),
|
|
(VSHLLi8 DPR:$Rn, 8)>;
|
|
def : Pat<(v4i32 (NEONvshl (zext (v4i16 DPR:$Rn)), (i32 16))),
|
|
(VSHLLi16 DPR:$Rn, 16)>;
|
|
def : Pat<(v2i64 (NEONvshl (zext (v2i32 DPR:$Rn)), (i32 32))),
|
|
(VSHLLi32 DPR:$Rn, 32)>;
|
|
def : Pat<(v8i16 (NEONvshl (sext (v8i8 DPR:$Rn)), (i32 8))),
|
|
(VSHLLi8 DPR:$Rn, 8)>;
|
|
def : Pat<(v4i32 (NEONvshl (sext (v4i16 DPR:$Rn)), (i32 16))),
|
|
(VSHLLi16 DPR:$Rn, 16)>;
|
|
def : Pat<(v2i64 (NEONvshl (sext (v2i32 DPR:$Rn)), (i32 32))),
|
|
(VSHLLi32 DPR:$Rn, 32)>;
|
|
def : Pat<(v8i16 (NEONvshl (anyext (v8i8 DPR:$Rn)), (i32 8))),
|
|
(VSHLLi8 DPR:$Rn, 8)>;
|
|
def : Pat<(v4i32 (NEONvshl (anyext (v4i16 DPR:$Rn)), (i32 16))),
|
|
(VSHLLi16 DPR:$Rn, 16)>;
|
|
def : Pat<(v2i64 (NEONvshl (anyext (v2i32 DPR:$Rn)), (i32 32))),
|
|
(VSHLLi32 DPR:$Rn, 32)>;
|
|
|
|
// VSHRN : Vector Shift Right and Narrow
|
|
defm VSHRN : N2VNSh_HSD<0,1,0b1000,0,0,1, IIC_VSHLiD, "vshrn", "i",
|
|
PatFrag<(ops node:$Rn, node:$amt),
|
|
(trunc (NEONvshrs node:$Rn, node:$amt))>>;
|
|
|
|
def : Pat<(v8i8 (trunc (NEONvshru (v8i16 QPR:$Vn), shr_imm8:$amt))),
|
|
(VSHRNv8i8 QPR:$Vn, shr_imm8:$amt)>;
|
|
def : Pat<(v4i16 (trunc (NEONvshru (v4i32 QPR:$Vn), shr_imm16:$amt))),
|
|
(VSHRNv4i16 QPR:$Vn, shr_imm16:$amt)>;
|
|
def : Pat<(v2i32 (trunc (NEONvshru (v2i64 QPR:$Vn), shr_imm32:$amt))),
|
|
(VSHRNv2i32 QPR:$Vn, shr_imm32:$amt)>;
|
|
|
|
// VRSHL : Vector Rounding Shift
|
|
defm VRSHLs : N3VInt_QHSDSh<0, 0, 0b0101, 0, N3RegVShFrm,
|
|
IIC_VSHLi4D, IIC_VSHLi4D, IIC_VSHLi4Q, IIC_VSHLi4Q,
|
|
"vrshl", "s", int_arm_neon_vrshifts>;
|
|
defm VRSHLu : N3VInt_QHSDSh<1, 0, 0b0101, 0, N3RegVShFrm,
|
|
IIC_VSHLi4D, IIC_VSHLi4D, IIC_VSHLi4Q, IIC_VSHLi4Q,
|
|
"vrshl", "u", int_arm_neon_vrshiftu>;
|
|
// VRSHR : Vector Rounding Shift Right
|
|
defm VRSHRs : N2VShR_QHSD<0,1,0b0010,1, IIC_VSHLi4D, "vrshr", "s", "VRSHRs",
|
|
NEONvrshrs>;
|
|
defm VRSHRu : N2VShR_QHSD<1,1,0b0010,1, IIC_VSHLi4D, "vrshr", "u", "VRSHRu",
|
|
NEONvrshru>;
|
|
|
|
// VRSHRN : Vector Rounding Shift Right and Narrow
|
|
defm VRSHRN : N2VNSh_HSD<0, 1, 0b1000, 0, 1, 1, IIC_VSHLi4D, "vrshrn", "i",
|
|
NEONvrshrn>;
|
|
|
|
// VQSHL : Vector Saturating Shift
|
|
defm VQSHLs : N3VInt_QHSDSh<0, 0, 0b0100, 1, N3RegVShFrm,
|
|
IIC_VSHLi4D, IIC_VSHLi4D, IIC_VSHLi4Q, IIC_VSHLi4Q,
|
|
"vqshl", "s", int_arm_neon_vqshifts>;
|
|
defm VQSHLu : N3VInt_QHSDSh<1, 0, 0b0100, 1, N3RegVShFrm,
|
|
IIC_VSHLi4D, IIC_VSHLi4D, IIC_VSHLi4Q, IIC_VSHLi4Q,
|
|
"vqshl", "u", int_arm_neon_vqshiftu>;
|
|
// VQSHL : Vector Saturating Shift Left (Immediate)
|
|
defm VQSHLsi : N2VShL_QHSD<0,1,0b0111,1, IIC_VSHLi4D, "vqshl", "s",NEONvqshls>;
|
|
defm VQSHLui : N2VShL_QHSD<1,1,0b0111,1, IIC_VSHLi4D, "vqshl", "u",NEONvqshlu>;
|
|
|
|
// VQSHLU : Vector Saturating Shift Left (Immediate, Unsigned)
|
|
defm VQSHLsu : N2VShL_QHSD<1,1,0b0110,1, IIC_VSHLi4D,"vqshlu","s",NEONvqshlsu>;
|
|
|
|
// VQSHRN : Vector Saturating Shift Right and Narrow
|
|
defm VQSHRNs : N2VNSh_HSD<0, 1, 0b1001, 0, 0, 1, IIC_VSHLi4D, "vqshrn", "s",
|
|
NEONvqshrns>;
|
|
defm VQSHRNu : N2VNSh_HSD<1, 1, 0b1001, 0, 0, 1, IIC_VSHLi4D, "vqshrn", "u",
|
|
NEONvqshrnu>;
|
|
|
|
// VQSHRUN : Vector Saturating Shift Right and Narrow (Unsigned)
|
|
defm VQSHRUN : N2VNSh_HSD<1, 1, 0b1000, 0, 0, 1, IIC_VSHLi4D, "vqshrun", "s",
|
|
NEONvqshrnsu>;
|
|
|
|
// VQRSHL : Vector Saturating Rounding Shift
|
|
defm VQRSHLs : N3VInt_QHSDSh<0, 0, 0b0101, 1, N3RegVShFrm,
|
|
IIC_VSHLi4D, IIC_VSHLi4D, IIC_VSHLi4Q, IIC_VSHLi4Q,
|
|
"vqrshl", "s", int_arm_neon_vqrshifts>;
|
|
defm VQRSHLu : N3VInt_QHSDSh<1, 0, 0b0101, 1, N3RegVShFrm,
|
|
IIC_VSHLi4D, IIC_VSHLi4D, IIC_VSHLi4Q, IIC_VSHLi4Q,
|
|
"vqrshl", "u", int_arm_neon_vqrshiftu>;
|
|
|
|
// VQRSHRN : Vector Saturating Rounding Shift Right and Narrow
|
|
defm VQRSHRNs : N2VNSh_HSD<0, 1, 0b1001, 0, 1, 1, IIC_VSHLi4D, "vqrshrn", "s",
|
|
NEONvqrshrns>;
|
|
defm VQRSHRNu : N2VNSh_HSD<1, 1, 0b1001, 0, 1, 1, IIC_VSHLi4D, "vqrshrn", "u",
|
|
NEONvqrshrnu>;
|
|
|
|
// VQRSHRUN : Vector Saturating Rounding Shift Right and Narrow (Unsigned)
|
|
defm VQRSHRUN : N2VNSh_HSD<1, 1, 0b1000, 0, 1, 1, IIC_VSHLi4D, "vqrshrun", "s",
|
|
NEONvqrshrnsu>;
|
|
|
|
// VSRA : Vector Shift Right and Accumulate
|
|
defm VSRAs : N2VShAdd_QHSD<0, 1, 0b0001, 1, "vsra", "s", NEONvshrs>;
|
|
defm VSRAu : N2VShAdd_QHSD<1, 1, 0b0001, 1, "vsra", "u", NEONvshru>;
|
|
// VRSRA : Vector Rounding Shift Right and Accumulate
|
|
defm VRSRAs : N2VShAdd_QHSD<0, 1, 0b0011, 1, "vrsra", "s", NEONvrshrs>;
|
|
defm VRSRAu : N2VShAdd_QHSD<1, 1, 0b0011, 1, "vrsra", "u", NEONvrshru>;
|
|
|
|
// VSLI : Vector Shift Left and Insert
|
|
defm VSLI : N2VShInsL_QHSD<1, 1, 0b0101, 1, "vsli">;
|
|
|
|
// VSRI : Vector Shift Right and Insert
|
|
defm VSRI : N2VShInsR_QHSD<1, 1, 0b0100, 1, "vsri">;
|
|
|
|
// Vector Absolute and Saturating Absolute.
|
|
|
|
// VABS : Vector Absolute Value
|
|
defm VABS : N2VInt_QHS<0b11, 0b11, 0b01, 0b00110, 0,
|
|
IIC_VUNAiD, IIC_VUNAiQ, "vabs", "s", abs>;
|
|
def VABSfd : N2VD<0b11, 0b11, 0b10, 0b01, 0b01110, 0,
|
|
"vabs", "f32",
|
|
v2f32, v2f32, fabs>;
|
|
def VABSfq : N2VQ<0b11, 0b11, 0b10, 0b01, 0b01110, 0,
|
|
"vabs", "f32",
|
|
v4f32, v4f32, fabs>;
|
|
def VABShd : N2VD<0b11, 0b11, 0b01, 0b01, 0b01110, 0,
|
|
"vabs", "f16",
|
|
v4f16, v4f16, fabs>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VABShq : N2VQ<0b11, 0b11, 0b01, 0b01, 0b01110, 0,
|
|
"vabs", "f16",
|
|
v8f16, v8f16, fabs>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VQABS : Vector Saturating Absolute Value
|
|
defm VQABS : N2VInt_QHS<0b11, 0b11, 0b00, 0b01110, 0,
|
|
IIC_VQUNAiD, IIC_VQUNAiQ, "vqabs", "s",
|
|
int_arm_neon_vqabs>;
|
|
|
|
// Vector Negate.
|
|
|
|
def vnegd : PatFrag<(ops node:$in),
|
|
(sub (bitconvert (v2i32 NEONimmAllZerosV)), node:$in)>;
|
|
def vnegq : PatFrag<(ops node:$in),
|
|
(sub (bitconvert (v4i32 NEONimmAllZerosV)), node:$in)>;
|
|
|
|
class VNEGD<bits<2> size, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, size, 0b01, 0b00111, 0, 0, (outs DPR:$Vd), (ins DPR:$Vm),
|
|
IIC_VSHLiD, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (Ty (vnegd DPR:$Vm)))]>;
|
|
class VNEGQ<bits<2> size, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, size, 0b01, 0b00111, 1, 0, (outs QPR:$Vd), (ins QPR:$Vm),
|
|
IIC_VSHLiQ, OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (Ty (vnegq QPR:$Vm)))]>;
|
|
|
|
// VNEG : Vector Negate (integer)
|
|
def VNEGs8d : VNEGD<0b00, "vneg", "s8", v8i8>;
|
|
def VNEGs16d : VNEGD<0b01, "vneg", "s16", v4i16>;
|
|
def VNEGs32d : VNEGD<0b10, "vneg", "s32", v2i32>;
|
|
def VNEGs8q : VNEGQ<0b00, "vneg", "s8", v16i8>;
|
|
def VNEGs16q : VNEGQ<0b01, "vneg", "s16", v8i16>;
|
|
def VNEGs32q : VNEGQ<0b10, "vneg", "s32", v4i32>;
|
|
|
|
// VNEG : Vector Negate (floating-point)
|
|
def VNEGfd : N2V<0b11, 0b11, 0b10, 0b01, 0b01111, 0, 0,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), IIC_VUNAD,
|
|
"vneg", "f32", "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (v2f32 (fneg DPR:$Vm)))]>;
|
|
def VNEGf32q : N2V<0b11, 0b11, 0b10, 0b01, 0b01111, 1, 0,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), IIC_VUNAQ,
|
|
"vneg", "f32", "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (v4f32 (fneg QPR:$Vm)))]>;
|
|
def VNEGhd : N2V<0b11, 0b11, 0b01, 0b01, 0b01111, 0, 0,
|
|
(outs DPR:$Vd), (ins DPR:$Vm), IIC_VUNAD,
|
|
"vneg", "f16", "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (v4f16 (fneg DPR:$Vm)))]>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VNEGhq : N2V<0b11, 0b11, 0b01, 0b01, 0b01111, 1, 0,
|
|
(outs QPR:$Vd), (ins QPR:$Vm), IIC_VUNAQ,
|
|
"vneg", "f16", "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (v8f16 (fneg QPR:$Vm)))]>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
def : Pat<(v8i8 (vnegd DPR:$src)), (VNEGs8d DPR:$src)>;
|
|
def : Pat<(v4i16 (vnegd DPR:$src)), (VNEGs16d DPR:$src)>;
|
|
def : Pat<(v2i32 (vnegd DPR:$src)), (VNEGs32d DPR:$src)>;
|
|
def : Pat<(v16i8 (vnegq QPR:$src)), (VNEGs8q QPR:$src)>;
|
|
def : Pat<(v8i16 (vnegq QPR:$src)), (VNEGs16q QPR:$src)>;
|
|
def : Pat<(v4i32 (vnegq QPR:$src)), (VNEGs32q QPR:$src)>;
|
|
|
|
// VQNEG : Vector Saturating Negate
|
|
defm VQNEG : N2VInt_QHS<0b11, 0b11, 0b00, 0b01111, 0,
|
|
IIC_VQUNAiD, IIC_VQUNAiQ, "vqneg", "s",
|
|
int_arm_neon_vqneg>;
|
|
|
|
// Vector Bit Counting Operations.
|
|
|
|
// VCLS : Vector Count Leading Sign Bits
|
|
defm VCLS : N2VInt_QHS<0b11, 0b11, 0b00, 0b01000, 0,
|
|
IIC_VCNTiD, IIC_VCNTiQ, "vcls", "s",
|
|
int_arm_neon_vcls>;
|
|
// VCLZ : Vector Count Leading Zeros
|
|
defm VCLZ : N2VInt_QHS<0b11, 0b11, 0b00, 0b01001, 0,
|
|
IIC_VCNTiD, IIC_VCNTiQ, "vclz", "i",
|
|
ctlz>;
|
|
// VCNT : Vector Count One Bits
|
|
def VCNTd : N2VDInt<0b11, 0b11, 0b00, 0b00, 0b01010, 0,
|
|
IIC_VCNTiD, "vcnt", "8",
|
|
v8i8, v8i8, ctpop>;
|
|
def VCNTq : N2VQInt<0b11, 0b11, 0b00, 0b00, 0b01010, 0,
|
|
IIC_VCNTiQ, "vcnt", "8",
|
|
v16i8, v16i8, ctpop>;
|
|
|
|
// Vector Swap
|
|
def VSWPd : N2VX<0b11, 0b11, 0b00, 0b10, 0b00000, 0, 0,
|
|
(outs DPR:$Vd, DPR:$Vm), (ins DPR:$in1, DPR:$in2),
|
|
NoItinerary, "vswp", "$Vd, $Vm", "$in1 = $Vd, $in2 = $Vm",
|
|
[]>;
|
|
def VSWPq : N2VX<0b11, 0b11, 0b00, 0b10, 0b00000, 1, 0,
|
|
(outs QPR:$Vd, QPR:$Vm), (ins QPR:$in1, QPR:$in2),
|
|
NoItinerary, "vswp", "$Vd, $Vm", "$in1 = $Vd, $in2 = $Vm",
|
|
[]>;
|
|
|
|
// Vector Move Operations.
|
|
|
|
// VMOV : Vector Move (Register)
|
|
def : NEONInstAlias<"vmov${p} $Vd, $Vm",
|
|
(VORRd DPR:$Vd, DPR:$Vm, DPR:$Vm, pred:$p)>;
|
|
def : NEONInstAlias<"vmov${p} $Vd, $Vm",
|
|
(VORRq QPR:$Vd, QPR:$Vm, QPR:$Vm, pred:$p)>;
|
|
|
|
// VMOV : Vector Move (Immediate)
|
|
|
|
// Although VMOVs are not strictly speaking cheap, they are as expensive
|
|
// as their copies counterpart (VORR), so we should prefer rematerialization
|
|
// over splitting when it applies.
|
|
let isReMaterializable = 1, isAsCheapAsAMove=1 in {
|
|
def VMOVv8i8 : N1ModImm<1, 0b000, 0b1110, 0, 0, 0, 1, (outs DPR:$Vd),
|
|
(ins nImmSplatI8:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i8", "$Vd, $SIMM", "",
|
|
[(set DPR:$Vd, (v8i8 (NEONvmovImm timm:$SIMM)))]>;
|
|
def VMOVv16i8 : N1ModImm<1, 0b000, 0b1110, 0, 1, 0, 1, (outs QPR:$Vd),
|
|
(ins nImmSplatI8:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i8", "$Vd, $SIMM", "",
|
|
[(set QPR:$Vd, (v16i8 (NEONvmovImm timm:$SIMM)))]>;
|
|
|
|
def VMOVv4i16 : N1ModImm<1, 0b000, {1,0,?,0}, 0, 0, 0, 1, (outs DPR:$Vd),
|
|
(ins nImmSplatI16:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i16", "$Vd, $SIMM", "",
|
|
[(set DPR:$Vd, (v4i16 (NEONvmovImm timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VMOVv8i16 : N1ModImm<1, 0b000, {1,0,?,0}, 0, 1, 0, 1, (outs QPR:$Vd),
|
|
(ins nImmSplatI16:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i16", "$Vd, $SIMM", "",
|
|
[(set QPR:$Vd, (v8i16 (NEONvmovImm timm:$SIMM)))]> {
|
|
let Inst{9} = SIMM{9};
|
|
}
|
|
|
|
def VMOVv2i32 : N1ModImm<1, 0b000, {?,?,?,?}, 0, 0, 0, 1, (outs DPR:$Vd),
|
|
(ins nImmVMOVI32:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i32", "$Vd, $SIMM", "",
|
|
[(set DPR:$Vd, (v2i32 (NEONvmovImm timm:$SIMM)))]> {
|
|
let Inst{11-8} = SIMM{11-8};
|
|
}
|
|
|
|
def VMOVv4i32 : N1ModImm<1, 0b000, {?,?,?,?}, 0, 1, 0, 1, (outs QPR:$Vd),
|
|
(ins nImmVMOVI32:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i32", "$Vd, $SIMM", "",
|
|
[(set QPR:$Vd, (v4i32 (NEONvmovImm timm:$SIMM)))]> {
|
|
let Inst{11-8} = SIMM{11-8};
|
|
}
|
|
|
|
def VMOVv1i64 : N1ModImm<1, 0b000, 0b1110, 0, 0, 1, 1, (outs DPR:$Vd),
|
|
(ins nImmSplatI64:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i64", "$Vd, $SIMM", "",
|
|
[(set DPR:$Vd, (v1i64 (NEONvmovImm timm:$SIMM)))]>;
|
|
def VMOVv2i64 : N1ModImm<1, 0b000, 0b1110, 0, 1, 1, 1, (outs QPR:$Vd),
|
|
(ins nImmSplatI64:$SIMM), IIC_VMOVImm,
|
|
"vmov", "i64", "$Vd, $SIMM", "",
|
|
[(set QPR:$Vd, (v2i64 (NEONvmovImm timm:$SIMM)))]>;
|
|
|
|
def VMOVv2f32 : N1ModImm<1, 0b000, 0b1111, 0, 0, 0, 1, (outs DPR:$Vd),
|
|
(ins nImmVMOVF32:$SIMM), IIC_VMOVImm,
|
|
"vmov", "f32", "$Vd, $SIMM", "",
|
|
[(set DPR:$Vd, (v2f32 (NEONvmovFPImm timm:$SIMM)))]>;
|
|
def VMOVv4f32 : N1ModImm<1, 0b000, 0b1111, 0, 1, 0, 1, (outs QPR:$Vd),
|
|
(ins nImmVMOVF32:$SIMM), IIC_VMOVImm,
|
|
"vmov", "f32", "$Vd, $SIMM", "",
|
|
[(set QPR:$Vd, (v4f32 (NEONvmovFPImm timm:$SIMM)))]>;
|
|
} // isReMaterializable, isAsCheapAsAMove
|
|
|
|
// Add support for bytes replication feature, so it could be GAS compatible.
|
|
multiclass NEONImmReplicateI8InstAlias<ValueType To> {
|
|
// E.g. instructions below:
|
|
// "vmov.i32 d0, #0xffffffff"
|
|
// "vmov.i32 d0, #0xabababab"
|
|
// "vmov.i16 d0, #0xabab"
|
|
// are incorrect, but we could deal with such cases.
|
|
// For last two instructions, for example, it should emit:
|
|
// "vmov.i8 d0, #0xab"
|
|
def : NEONInstAlias<"vmov${p}.i" # To.Size # " $Vd, $Vm",
|
|
(VMOVv8i8 DPR:$Vd, nImmVMOVIReplicate<i8, To>:$Vm, pred:$p)>;
|
|
def : NEONInstAlias<"vmov${p}.i" # To.Size # " $Vd, $Vm",
|
|
(VMOVv16i8 QPR:$Vd, nImmVMOVIReplicate<i8, To>:$Vm, pred:$p)>;
|
|
// Also add same support for VMVN instructions. So instruction:
|
|
// "vmvn.i32 d0, #0xabababab"
|
|
// actually means:
|
|
// "vmov.i8 d0, #0x54"
|
|
def : NEONInstAlias<"vmvn${p}.i" # To.Size # " $Vd, $Vm",
|
|
(VMOVv8i8 DPR:$Vd, nImmVINVIReplicate<i8, To>:$Vm, pred:$p)>;
|
|
def : NEONInstAlias<"vmvn${p}.i" # To.Size # " $Vd, $Vm",
|
|
(VMOVv16i8 QPR:$Vd, nImmVINVIReplicate<i8, To>:$Vm, pred:$p)>;
|
|
}
|
|
|
|
defm : NEONImmReplicateI8InstAlias<i16>;
|
|
defm : NEONImmReplicateI8InstAlias<i32>;
|
|
defm : NEONImmReplicateI8InstAlias<i64>;
|
|
|
|
// Similar to above for types other than i8, e.g.:
|
|
// "vmov.i32 d0, #0xab00ab00" -> "vmov.i16 d0, #0xab00"
|
|
// "vmvn.i64 q0, #0xab000000ab000000" -> "vmvn.i32 q0, #0xab000000"
|
|
// In this case we do not canonicalize VMVN to VMOV
|
|
multiclass NEONImmReplicateInstAlias<ValueType From, NeonI V8, NeonI V16,
|
|
NeonI NV8, NeonI NV16, ValueType To> {
|
|
def : NEONInstAlias<"vmov${p}.i" # To.Size # " $Vd, $Vm",
|
|
(V8 DPR:$Vd, nImmVMOVIReplicate<From, To>:$Vm, pred:$p)>;
|
|
def : NEONInstAlias<"vmov${p}.i" # To.Size # " $Vd, $Vm",
|
|
(V16 QPR:$Vd, nImmVMOVIReplicate<From, To>:$Vm, pred:$p)>;
|
|
def : NEONInstAlias<"vmvn${p}.i" # To.Size # " $Vd, $Vm",
|
|
(NV8 DPR:$Vd, nImmVMOVIReplicate<From, To>:$Vm, pred:$p)>;
|
|
def : NEONInstAlias<"vmvn${p}.i" # To.Size # " $Vd, $Vm",
|
|
(NV16 QPR:$Vd, nImmVMOVIReplicate<From, To>:$Vm, pred:$p)>;
|
|
}
|
|
|
|
defm : NEONImmReplicateInstAlias<i16, VMOVv4i16, VMOVv8i16,
|
|
VMVNv4i16, VMVNv8i16, i32>;
|
|
defm : NEONImmReplicateInstAlias<i16, VMOVv4i16, VMOVv8i16,
|
|
VMVNv4i16, VMVNv8i16, i64>;
|
|
defm : NEONImmReplicateInstAlias<i32, VMOVv2i32, VMOVv4i32,
|
|
VMVNv2i32, VMVNv4i32, i64>;
|
|
// TODO: add "VMOV <-> VMVN" conversion for cases like
|
|
// "vmov.i32 d0, #0xffaaffaa" -> "vmvn.i16 d0, #0x55"
|
|
// "vmvn.i32 d0, #0xaaffaaff" -> "vmov.i16 d0, #0xff00"
|
|
|
|
// On some CPUs the two instructions "vmov.i32 dD, #0" and "vmov.i32 qD, #0"
|
|
// require zero cycles to execute so they should be used wherever possible for
|
|
// setting a register to zero.
|
|
|
|
// Even without these pseudo-insts we would probably end up with the correct
|
|
// instruction, but we could not mark the general ones with "isAsCheapAsAMove"
|
|
// since they are sometimes rather expensive (in general).
|
|
|
|
let AddedComplexity = 50, isAsCheapAsAMove = 1, isReMaterializable = 1 in {
|
|
def VMOVD0 : ARMPseudoExpand<(outs DPR:$Vd), (ins), 4, IIC_VMOVImm,
|
|
[(set DPR:$Vd, (v2i32 NEONimmAllZerosV))],
|
|
(VMOVv2i32 DPR:$Vd, 0, (ops 14, zero_reg))>,
|
|
Requires<[HasZCZ]>;
|
|
def VMOVQ0 : ARMPseudoExpand<(outs QPR:$Vd), (ins), 4, IIC_VMOVImm,
|
|
[(set QPR:$Vd, (v4i32 NEONimmAllZerosV))],
|
|
(VMOVv4i32 QPR:$Vd, 0, (ops 14, zero_reg))>,
|
|
Requires<[HasZCZ]>;
|
|
}
|
|
|
|
// VMOV : Vector Get Lane (move scalar to ARM core register)
|
|
|
|
def VGETLNs8 : NVGetLane<{1,1,1,0,0,1,?,1}, 0b1011, {?,?},
|
|
(outs GPR:$R), (ins DPR:$V, VectorIndex8:$lane),
|
|
IIC_VMOVSI, "vmov", "s8", "$R, $V$lane",
|
|
[(set GPR:$R, (NEONvgetlanes (v8i8 DPR:$V),
|
|
imm:$lane))]> {
|
|
let Inst{21} = lane{2};
|
|
let Inst{6-5} = lane{1-0};
|
|
}
|
|
def VGETLNs16 : NVGetLane<{1,1,1,0,0,0,?,1}, 0b1011, {?,1},
|
|
(outs GPR:$R), (ins DPR:$V, VectorIndex16:$lane),
|
|
IIC_VMOVSI, "vmov", "s16", "$R, $V$lane",
|
|
[(set GPR:$R, (NEONvgetlanes (v4i16 DPR:$V),
|
|
imm:$lane))]> {
|
|
let Inst{21} = lane{1};
|
|
let Inst{6} = lane{0};
|
|
}
|
|
def VGETLNu8 : NVGetLane<{1,1,1,0,1,1,?,1}, 0b1011, {?,?},
|
|
(outs GPR:$R), (ins DPR:$V, VectorIndex8:$lane),
|
|
IIC_VMOVSI, "vmov", "u8", "$R, $V$lane",
|
|
[(set GPR:$R, (NEONvgetlaneu (v8i8 DPR:$V),
|
|
imm:$lane))]> {
|
|
let Inst{21} = lane{2};
|
|
let Inst{6-5} = lane{1-0};
|
|
}
|
|
def VGETLNu16 : NVGetLane<{1,1,1,0,1,0,?,1}, 0b1011, {?,1},
|
|
(outs GPR:$R), (ins DPR:$V, VectorIndex16:$lane),
|
|
IIC_VMOVSI, "vmov", "u16", "$R, $V$lane",
|
|
[(set GPR:$R, (NEONvgetlaneu (v4i16 DPR:$V),
|
|
imm:$lane))]> {
|
|
let Inst{21} = lane{1};
|
|
let Inst{6} = lane{0};
|
|
}
|
|
def VGETLNi32 : NVGetLane<{1,1,1,0,0,0,?,1}, 0b1011, 0b00,
|
|
(outs GPR:$R), (ins DPR:$V, VectorIndex32:$lane),
|
|
IIC_VMOVSI, "vmov", "32", "$R, $V$lane",
|
|
[(set GPR:$R, (extractelt (v2i32 DPR:$V),
|
|
imm:$lane))]>,
|
|
Requires<[HasVFP2, HasFastVGETLNi32]> {
|
|
let Inst{21} = lane{0};
|
|
}
|
|
// def VGETLNf32: see FMRDH and FMRDL in ARMInstrVFP.td
|
|
def : Pat<(NEONvgetlanes (v16i8 QPR:$src), imm:$lane),
|
|
(VGETLNs8 (v8i8 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i8_reg imm:$lane))),
|
|
(SubReg_i8_lane imm:$lane))>;
|
|
def : Pat<(NEONvgetlanes (v8i16 QPR:$src), imm:$lane),
|
|
(VGETLNs16 (v4i16 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane))>;
|
|
def : Pat<(NEONvgetlaneu (v16i8 QPR:$src), imm:$lane),
|
|
(VGETLNu8 (v8i8 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i8_reg imm:$lane))),
|
|
(SubReg_i8_lane imm:$lane))>;
|
|
def : Pat<(NEONvgetlaneu (v8i16 QPR:$src), imm:$lane),
|
|
(VGETLNu16 (v4i16 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane))>;
|
|
def : Pat<(extractelt (v4i32 QPR:$src), imm:$lane),
|
|
(VGETLNi32 (v2i32 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane))>,
|
|
Requires<[HasNEON, HasFastVGETLNi32]>;
|
|
def : Pat<(extractelt (v2i32 DPR:$src), imm:$lane),
|
|
(COPY_TO_REGCLASS
|
|
(i32 (EXTRACT_SUBREG DPR:$src, (SSubReg_f32_reg imm:$lane))), GPR)>,
|
|
Requires<[HasNEON, HasSlowVGETLNi32]>;
|
|
def : Pat<(extractelt (v4i32 QPR:$src), imm:$lane),
|
|
(COPY_TO_REGCLASS
|
|
(i32 (EXTRACT_SUBREG QPR:$src, (SSubReg_f32_reg imm:$lane))), GPR)>,
|
|
Requires<[HasNEON, HasSlowVGETLNi32]>;
|
|
def : Pat<(extractelt (v2f32 DPR:$src1), imm:$src2),
|
|
(EXTRACT_SUBREG (v2f32 (COPY_TO_REGCLASS (v2f32 DPR:$src1),DPR_VFP2)),
|
|
(SSubReg_f32_reg imm:$src2))>;
|
|
def : Pat<(extractelt (v4f32 QPR:$src1), imm:$src2),
|
|
(EXTRACT_SUBREG (v4f32 (COPY_TO_REGCLASS (v4f32 QPR:$src1),QPR_VFP2)),
|
|
(SSubReg_f32_reg imm:$src2))>;
|
|
//def : Pat<(extractelt (v2i64 QPR:$src1), imm:$src2),
|
|
// (EXTRACT_SUBREG QPR:$src1, (DSubReg_f64_reg imm:$src2))>;
|
|
def : Pat<(extractelt (v2f64 QPR:$src1), imm:$src2),
|
|
(EXTRACT_SUBREG QPR:$src1, (DSubReg_f64_reg imm:$src2))>;
|
|
|
|
|
|
// VMOV : Vector Set Lane (move ARM core register to scalar)
|
|
|
|
let Constraints = "$src1 = $V" in {
|
|
def VSETLNi8 : NVSetLane<{1,1,1,0,0,1,?,0}, 0b1011, {?,?}, (outs DPR:$V),
|
|
(ins DPR:$src1, GPR:$R, VectorIndex8:$lane),
|
|
IIC_VMOVISL, "vmov", "8", "$V$lane, $R",
|
|
[(set DPR:$V, (vector_insert (v8i8 DPR:$src1),
|
|
GPR:$R, imm:$lane))]> {
|
|
let Inst{21} = lane{2};
|
|
let Inst{6-5} = lane{1-0};
|
|
}
|
|
def VSETLNi16 : NVSetLane<{1,1,1,0,0,0,?,0}, 0b1011, {?,1}, (outs DPR:$V),
|
|
(ins DPR:$src1, GPR:$R, VectorIndex16:$lane),
|
|
IIC_VMOVISL, "vmov", "16", "$V$lane, $R",
|
|
[(set DPR:$V, (vector_insert (v4i16 DPR:$src1),
|
|
GPR:$R, imm:$lane))]> {
|
|
let Inst{21} = lane{1};
|
|
let Inst{6} = lane{0};
|
|
}
|
|
def VSETLNi32 : NVSetLane<{1,1,1,0,0,0,?,0}, 0b1011, 0b00, (outs DPR:$V),
|
|
(ins DPR:$src1, GPR:$R, VectorIndex32:$lane),
|
|
IIC_VMOVISL, "vmov", "32", "$V$lane, $R",
|
|
[(set DPR:$V, (insertelt (v2i32 DPR:$src1),
|
|
GPR:$R, imm:$lane))]>,
|
|
Requires<[HasVFP2]> {
|
|
let Inst{21} = lane{0};
|
|
// This instruction is equivalent as
|
|
// $V = INSERT_SUBREG $src1, $R, translateImmToSubIdx($imm)
|
|
let isInsertSubreg = 1;
|
|
}
|
|
}
|
|
def : Pat<(vector_insert (v16i8 QPR:$src1), GPR:$src2, imm:$lane),
|
|
(v16i8 (INSERT_SUBREG QPR:$src1,
|
|
(v8i8 (VSETLNi8 (v8i8 (EXTRACT_SUBREG QPR:$src1,
|
|
(DSubReg_i8_reg imm:$lane))),
|
|
GPR:$src2, (SubReg_i8_lane imm:$lane))),
|
|
(DSubReg_i8_reg imm:$lane)))>;
|
|
def : Pat<(vector_insert (v8i16 QPR:$src1), GPR:$src2, imm:$lane),
|
|
(v8i16 (INSERT_SUBREG QPR:$src1,
|
|
(v4i16 (VSETLNi16 (v4i16 (EXTRACT_SUBREG QPR:$src1,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
GPR:$src2, (SubReg_i16_lane imm:$lane))),
|
|
(DSubReg_i16_reg imm:$lane)))>;
|
|
def : Pat<(insertelt (v4i32 QPR:$src1), GPR:$src2, imm:$lane),
|
|
(v4i32 (INSERT_SUBREG QPR:$src1,
|
|
(v2i32 (VSETLNi32 (v2i32 (EXTRACT_SUBREG QPR:$src1,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
GPR:$src2, (SubReg_i32_lane imm:$lane))),
|
|
(DSubReg_i32_reg imm:$lane)))>;
|
|
|
|
def : Pat<(v2f32 (insertelt DPR:$src1, SPR:$src2, imm:$src3)),
|
|
(INSERT_SUBREG (v2f32 (COPY_TO_REGCLASS DPR:$src1, DPR_VFP2)),
|
|
SPR:$src2, (SSubReg_f32_reg imm:$src3))>;
|
|
def : Pat<(v4f32 (insertelt QPR:$src1, SPR:$src2, imm:$src3)),
|
|
(INSERT_SUBREG (v4f32 (COPY_TO_REGCLASS QPR:$src1, QPR_VFP2)),
|
|
SPR:$src2, (SSubReg_f32_reg imm:$src3))>;
|
|
|
|
//def : Pat<(v2i64 (insertelt QPR:$src1, DPR:$src2, imm:$src3)),
|
|
// (INSERT_SUBREG QPR:$src1, DPR:$src2, (DSubReg_f64_reg imm:$src3))>;
|
|
def : Pat<(v2f64 (insertelt QPR:$src1, DPR:$src2, imm:$src3)),
|
|
(INSERT_SUBREG QPR:$src1, DPR:$src2, (DSubReg_f64_reg imm:$src3))>;
|
|
|
|
def : Pat<(v2f32 (scalar_to_vector SPR:$src)),
|
|
(INSERT_SUBREG (v2f32 (IMPLICIT_DEF)), SPR:$src, ssub_0)>;
|
|
def : Pat<(v2f64 (scalar_to_vector (f64 DPR:$src))),
|
|
(INSERT_SUBREG (v2f64 (IMPLICIT_DEF)), DPR:$src, dsub_0)>;
|
|
def : Pat<(v4f32 (scalar_to_vector SPR:$src)),
|
|
(INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), SPR:$src, ssub_0)>;
|
|
|
|
def : Pat<(v8i8 (scalar_to_vector GPR:$src)),
|
|
(VSETLNi8 (v8i8 (IMPLICIT_DEF)), GPR:$src, (i32 0))>;
|
|
def : Pat<(v4i16 (scalar_to_vector GPR:$src)),
|
|
(VSETLNi16 (v4i16 (IMPLICIT_DEF)), GPR:$src, (i32 0))>;
|
|
def : Pat<(v2i32 (scalar_to_vector GPR:$src)),
|
|
(VSETLNi32 (v2i32 (IMPLICIT_DEF)), GPR:$src, (i32 0))>;
|
|
|
|
def : Pat<(v16i8 (scalar_to_vector GPR:$src)),
|
|
(INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
|
|
(VSETLNi8 (v8i8 (IMPLICIT_DEF)), GPR:$src, (i32 0)),
|
|
dsub_0)>;
|
|
def : Pat<(v8i16 (scalar_to_vector GPR:$src)),
|
|
(INSERT_SUBREG (v8i16 (IMPLICIT_DEF)),
|
|
(VSETLNi16 (v4i16 (IMPLICIT_DEF)), GPR:$src, (i32 0)),
|
|
dsub_0)>;
|
|
def : Pat<(v4i32 (scalar_to_vector GPR:$src)),
|
|
(INSERT_SUBREG (v4i32 (IMPLICIT_DEF)),
|
|
(VSETLNi32 (v2i32 (IMPLICIT_DEF)), GPR:$src, (i32 0)),
|
|
dsub_0)>;
|
|
|
|
// VDUP : Vector Duplicate (from ARM core register to all elements)
|
|
|
|
class VDUPD<bits<8> opcod1, bits<2> opcod3, string Dt, ValueType Ty>
|
|
: NVDup<opcod1, 0b1011, opcod3, (outs DPR:$V), (ins GPR:$R),
|
|
IIC_VMOVIS, "vdup", Dt, "$V, $R",
|
|
[(set DPR:$V, (Ty (NEONvdup (i32 GPR:$R))))]>;
|
|
class VDUPQ<bits<8> opcod1, bits<2> opcod3, string Dt, ValueType Ty>
|
|
: NVDup<opcod1, 0b1011, opcod3, (outs QPR:$V), (ins GPR:$R),
|
|
IIC_VMOVIS, "vdup", Dt, "$V, $R",
|
|
[(set QPR:$V, (Ty (NEONvdup (i32 GPR:$R))))]>;
|
|
|
|
def VDUP8d : VDUPD<0b11101100, 0b00, "8", v8i8>;
|
|
def VDUP16d : VDUPD<0b11101000, 0b01, "16", v4i16>;
|
|
def VDUP32d : VDUPD<0b11101000, 0b00, "32", v2i32>,
|
|
Requires<[HasNEON, HasFastVDUP32]>;
|
|
def VDUP8q : VDUPQ<0b11101110, 0b00, "8", v16i8>;
|
|
def VDUP16q : VDUPQ<0b11101010, 0b01, "16", v8i16>;
|
|
def VDUP32q : VDUPQ<0b11101010, 0b00, "32", v4i32>;
|
|
|
|
// NEONvdup patterns for uarchs with fast VDUP.32.
|
|
def : Pat<(v2f32 (NEONvdup (f32 (bitconvert GPR:$R)))), (VDUP32d GPR:$R)>,
|
|
Requires<[HasNEON,HasFastVDUP32]>;
|
|
def : Pat<(v4f32 (NEONvdup (f32 (bitconvert GPR:$R)))), (VDUP32q GPR:$R)>;
|
|
|
|
// NEONvdup patterns for uarchs with slow VDUP.32 - use VMOVDRR instead.
|
|
def : Pat<(v2i32 (NEONvdup (i32 GPR:$R))), (VMOVDRR GPR:$R, GPR:$R)>,
|
|
Requires<[HasNEON,HasSlowVDUP32]>;
|
|
def : Pat<(v2f32 (NEONvdup (f32 (bitconvert GPR:$R)))), (VMOVDRR GPR:$R, GPR:$R)>,
|
|
Requires<[HasNEON,HasSlowVDUP32]>;
|
|
|
|
// VDUP : Vector Duplicate Lane (from scalar to all elements)
|
|
|
|
class VDUPLND<bits<4> op19_16, string OpcodeStr, string Dt,
|
|
ValueType Ty, Operand IdxTy>
|
|
: NVDupLane<op19_16, 0, (outs DPR:$Vd), (ins DPR:$Vm, IdxTy:$lane),
|
|
IIC_VMOVD, OpcodeStr, Dt, "$Vd, $Vm$lane",
|
|
[(set DPR:$Vd, (Ty (NEONvduplane (Ty DPR:$Vm), imm:$lane)))]>;
|
|
|
|
class VDUPLNQ<bits<4> op19_16, string OpcodeStr, string Dt,
|
|
ValueType ResTy, ValueType OpTy, Operand IdxTy>
|
|
: NVDupLane<op19_16, 1, (outs QPR:$Vd), (ins DPR:$Vm, IdxTy:$lane),
|
|
IIC_VMOVQ, OpcodeStr, Dt, "$Vd, $Vm$lane",
|
|
[(set QPR:$Vd, (ResTy (NEONvduplane (OpTy DPR:$Vm),
|
|
VectorIndex32:$lane)))]>;
|
|
|
|
// Inst{19-16} is partially specified depending on the element size.
|
|
|
|
def VDUPLN8d : VDUPLND<{?,?,?,1}, "vdup", "8", v8i8, VectorIndex8> {
|
|
bits<3> lane;
|
|
let Inst{19-17} = lane{2-0};
|
|
}
|
|
def VDUPLN16d : VDUPLND<{?,?,1,0}, "vdup", "16", v4i16, VectorIndex16> {
|
|
bits<2> lane;
|
|
let Inst{19-18} = lane{1-0};
|
|
}
|
|
def VDUPLN32d : VDUPLND<{?,1,0,0}, "vdup", "32", v2i32, VectorIndex32> {
|
|
bits<1> lane;
|
|
let Inst{19} = lane{0};
|
|
}
|
|
def VDUPLN8q : VDUPLNQ<{?,?,?,1}, "vdup", "8", v16i8, v8i8, VectorIndex8> {
|
|
bits<3> lane;
|
|
let Inst{19-17} = lane{2-0};
|
|
}
|
|
def VDUPLN16q : VDUPLNQ<{?,?,1,0}, "vdup", "16", v8i16, v4i16, VectorIndex16> {
|
|
bits<2> lane;
|
|
let Inst{19-18} = lane{1-0};
|
|
}
|
|
def VDUPLN32q : VDUPLNQ<{?,1,0,0}, "vdup", "32", v4i32, v2i32, VectorIndex32> {
|
|
bits<1> lane;
|
|
let Inst{19} = lane{0};
|
|
}
|
|
|
|
def : Pat<(v4f16 (NEONvduplane (v4f16 DPR:$Vm), imm:$lane)),
|
|
(VDUPLN32d DPR:$Vm, imm:$lane)>;
|
|
|
|
def : Pat<(v2f32 (NEONvduplane (v2f32 DPR:$Vm), imm:$lane)),
|
|
(VDUPLN32d DPR:$Vm, imm:$lane)>;
|
|
|
|
def : Pat<(v4f32 (NEONvduplane (v2f32 DPR:$Vm), imm:$lane)),
|
|
(VDUPLN32q DPR:$Vm, imm:$lane)>;
|
|
|
|
def : Pat<(v16i8 (NEONvduplane (v16i8 QPR:$src), imm:$lane)),
|
|
(v16i8 (VDUPLN8q (v8i8 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i8_reg imm:$lane))),
|
|
(SubReg_i8_lane imm:$lane)))>;
|
|
def : Pat<(v8i16 (NEONvduplane (v8i16 QPR:$src), imm:$lane)),
|
|
(v8i16 (VDUPLN16q (v4i16 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
def : Pat<(v8f16 (NEONvduplane (v8f16 QPR:$src), imm:$lane)),
|
|
(v8f16 (VDUPLN16q (v4f16 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i16_reg imm:$lane))),
|
|
(SubReg_i16_lane imm:$lane)))>;
|
|
def : Pat<(v4i32 (NEONvduplane (v4i32 QPR:$src), imm:$lane)),
|
|
(v4i32 (VDUPLN32q (v2i32 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
def : Pat<(v4f32 (NEONvduplane (v4f32 QPR:$src), imm:$lane)),
|
|
(v4f32 (VDUPLN32q (v2f32 (EXTRACT_SUBREG QPR:$src,
|
|
(DSubReg_i32_reg imm:$lane))),
|
|
(SubReg_i32_lane imm:$lane)))>;
|
|
|
|
def : Pat<(v4f16 (NEONvdup HPR:$src)),
|
|
(v4f16 (VDUPLN16d (INSERT_SUBREG (v4f16 (IMPLICIT_DEF)),
|
|
HPR:$src, ssub_0), (i32 0)))>;
|
|
def : Pat<(v2f32 (NEONvdup (f32 SPR:$src))),
|
|
(v2f32 (VDUPLN32d (INSERT_SUBREG (v2f32 (IMPLICIT_DEF)),
|
|
SPR:$src, ssub_0), (i32 0)))>;
|
|
def : Pat<(v4f32 (NEONvdup (f32 SPR:$src))),
|
|
(v4f32 (VDUPLN32q (INSERT_SUBREG (v2f32 (IMPLICIT_DEF)),
|
|
SPR:$src, ssub_0), (i32 0)))>;
|
|
def : Pat<(v8f16 (NEONvdup HPR:$src)),
|
|
(v8f16 (VDUPLN16q (INSERT_SUBREG (v4f16 (IMPLICIT_DEF)),
|
|
HPR:$src, ssub_0), (i32 0)))>;
|
|
|
|
// VMOVN : Vector Narrowing Move
|
|
defm VMOVN : N2VN_HSD<0b11,0b11,0b10,0b00100,0,0, IIC_VMOVN,
|
|
"vmovn", "i", trunc>;
|
|
// VQMOVN : Vector Saturating Narrowing Move
|
|
defm VQMOVNs : N2VNInt_HSD<0b11,0b11,0b10,0b00101,0,0, IIC_VQUNAiD,
|
|
"vqmovn", "s", int_arm_neon_vqmovns>;
|
|
defm VQMOVNu : N2VNInt_HSD<0b11,0b11,0b10,0b00101,1,0, IIC_VQUNAiD,
|
|
"vqmovn", "u", int_arm_neon_vqmovnu>;
|
|
defm VQMOVNsu : N2VNInt_HSD<0b11,0b11,0b10,0b00100,1,0, IIC_VQUNAiD,
|
|
"vqmovun", "s", int_arm_neon_vqmovnsu>;
|
|
// VMOVL : Vector Lengthening Move
|
|
defm VMOVLs : N2VL_QHS<0b01,0b10100,0,1, "vmovl", "s", sext>;
|
|
defm VMOVLu : N2VL_QHS<0b11,0b10100,0,1, "vmovl", "u", zext>;
|
|
def : Pat<(v8i16 (anyext (v8i8 DPR:$Vm))), (VMOVLuv8i16 DPR:$Vm)>;
|
|
def : Pat<(v4i32 (anyext (v4i16 DPR:$Vm))), (VMOVLuv4i32 DPR:$Vm)>;
|
|
def : Pat<(v2i64 (anyext (v2i32 DPR:$Vm))), (VMOVLuv2i64 DPR:$Vm)>;
|
|
|
|
// Vector Conversions.
|
|
|
|
// VCVT : Vector Convert Between Floating-Point and Integers
|
|
def VCVTf2sd : N2VD<0b11, 0b11, 0b10, 0b11, 0b01110, 0, "vcvt", "s32.f32",
|
|
v2i32, v2f32, fp_to_sint>;
|
|
def VCVTf2ud : N2VD<0b11, 0b11, 0b10, 0b11, 0b01111, 0, "vcvt", "u32.f32",
|
|
v2i32, v2f32, fp_to_uint>;
|
|
def VCVTs2fd : N2VD<0b11, 0b11, 0b10, 0b11, 0b01100, 0, "vcvt", "f32.s32",
|
|
v2f32, v2i32, sint_to_fp>;
|
|
def VCVTu2fd : N2VD<0b11, 0b11, 0b10, 0b11, 0b01101, 0, "vcvt", "f32.u32",
|
|
v2f32, v2i32, uint_to_fp>;
|
|
|
|
def VCVTf2sq : N2VQ<0b11, 0b11, 0b10, 0b11, 0b01110, 0, "vcvt", "s32.f32",
|
|
v4i32, v4f32, fp_to_sint>;
|
|
def VCVTf2uq : N2VQ<0b11, 0b11, 0b10, 0b11, 0b01111, 0, "vcvt", "u32.f32",
|
|
v4i32, v4f32, fp_to_uint>;
|
|
def VCVTs2fq : N2VQ<0b11, 0b11, 0b10, 0b11, 0b01100, 0, "vcvt", "f32.s32",
|
|
v4f32, v4i32, sint_to_fp>;
|
|
def VCVTu2fq : N2VQ<0b11, 0b11, 0b10, 0b11, 0b01101, 0, "vcvt", "f32.u32",
|
|
v4f32, v4i32, uint_to_fp>;
|
|
|
|
def VCVTh2sd : N2VD<0b11, 0b11, 0b01, 0b11, 0b01110, 0, "vcvt", "s16.f16",
|
|
v4i16, v4f16, fp_to_sint>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCVTh2ud : N2VD<0b11, 0b11, 0b01, 0b11, 0b01111, 0, "vcvt", "u16.f16",
|
|
v4i16, v4f16, fp_to_uint>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCVTs2hd : N2VD<0b11, 0b11, 0b01, 0b11, 0b01100, 0, "vcvt", "f16.s16",
|
|
v4f16, v4i16, sint_to_fp>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCVTu2hd : N2VD<0b11, 0b11, 0b01, 0b11, 0b01101, 0, "vcvt", "f16.u16",
|
|
v4f16, v4i16, uint_to_fp>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
def VCVTh2sq : N2VQ<0b11, 0b11, 0b01, 0b11, 0b01110, 0, "vcvt", "s16.f16",
|
|
v8i16, v8f16, fp_to_sint>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCVTh2uq : N2VQ<0b11, 0b11, 0b01, 0b11, 0b01111, 0, "vcvt", "u16.f16",
|
|
v8i16, v8f16, fp_to_uint>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCVTs2hq : N2VQ<0b11, 0b11, 0b01, 0b11, 0b01100, 0, "vcvt", "f16.s16",
|
|
v8f16, v8i16, sint_to_fp>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
def VCVTu2hq : N2VQ<0b11, 0b11, 0b01, 0b11, 0b01101, 0, "vcvt", "f16.u16",
|
|
v8f16, v8i16, uint_to_fp>,
|
|
Requires<[HasNEON, HasFullFP16]>;
|
|
|
|
// VCVT{A, N, P, M}
|
|
multiclass VCVT_FPI<string op, bits<3> op10_8, SDPatternOperator IntS,
|
|
SDPatternOperator IntU> {
|
|
let PostEncoderMethod = "NEONThumb2V8PostEncoder", DecoderNamespace = "v8NEON" in {
|
|
def SDf : N2VDIntnp<0b10, 0b11, op10_8, 0, NoItinerary, !strconcat("vcvt", op),
|
|
"s32.f32", v2i32, v2f32, IntS>, Requires<[HasV8, HasNEON]>;
|
|
def SQf : N2VQIntnp<0b10, 0b11, op10_8, 0, NoItinerary, !strconcat("vcvt", op),
|
|
"s32.f32", v4i32, v4f32, IntS>, Requires<[HasV8, HasNEON]>;
|
|
def UDf : N2VDIntnp<0b10, 0b11, op10_8, 1, NoItinerary, !strconcat("vcvt", op),
|
|
"u32.f32", v2i32, v2f32, IntU>, Requires<[HasV8, HasNEON]>;
|
|
def UQf : N2VQIntnp<0b10, 0b11, op10_8, 1, NoItinerary, !strconcat("vcvt", op),
|
|
"u32.f32", v4i32, v4f32, IntU>, Requires<[HasV8, HasNEON]>;
|
|
def SDh : N2VDIntnp<0b01, 0b11, op10_8, 0, NoItinerary, !strconcat("vcvt", op),
|
|
"s16.f16", v4i16, v4f16, IntS>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
def SQh : N2VQIntnp<0b01, 0b11, op10_8, 0, NoItinerary, !strconcat("vcvt", op),
|
|
"s16.f16", v8i16, v8f16, IntS>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
def UDh : N2VDIntnp<0b01, 0b11, op10_8, 1, NoItinerary, !strconcat("vcvt", op),
|
|
"u16.f16", v4i16, v4f16, IntU>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
def UQh : N2VQIntnp<0b01, 0b11, op10_8, 1, NoItinerary, !strconcat("vcvt", op),
|
|
"u16.f16", v8i16, v8f16, IntU>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]>;
|
|
}
|
|
}
|
|
|
|
defm VCVTAN : VCVT_FPI<"a", 0b000, int_arm_neon_vcvtas, int_arm_neon_vcvtau>;
|
|
defm VCVTNN : VCVT_FPI<"n", 0b001, int_arm_neon_vcvtns, int_arm_neon_vcvtnu>;
|
|
defm VCVTPN : VCVT_FPI<"p", 0b010, int_arm_neon_vcvtps, int_arm_neon_vcvtpu>;
|
|
defm VCVTMN : VCVT_FPI<"m", 0b011, int_arm_neon_vcvtms, int_arm_neon_vcvtmu>;
|
|
|
|
// VCVT : Vector Convert Between Floating-Point and Fixed-Point.
|
|
let DecoderMethod = "DecodeVCVTD" in {
|
|
def VCVTf2xsd : N2VCvtD<0, 1, 0b1111, 0, 1, "vcvt", "s32.f32",
|
|
v2i32, v2f32, int_arm_neon_vcvtfp2fxs>;
|
|
def VCVTf2xud : N2VCvtD<1, 1, 0b1111, 0, 1, "vcvt", "u32.f32",
|
|
v2i32, v2f32, int_arm_neon_vcvtfp2fxu>;
|
|
def VCVTxs2fd : N2VCvtD<0, 1, 0b1110, 0, 1, "vcvt", "f32.s32",
|
|
v2f32, v2i32, int_arm_neon_vcvtfxs2fp>;
|
|
def VCVTxu2fd : N2VCvtD<1, 1, 0b1110, 0, 1, "vcvt", "f32.u32",
|
|
v2f32, v2i32, int_arm_neon_vcvtfxu2fp>;
|
|
let Predicates = [HasNEON, HasFullFP16] in {
|
|
def VCVTh2xsd : N2VCvtD<0, 1, 0b1101, 0, 1, "vcvt", "s16.f16",
|
|
v4i16, v4f16, int_arm_neon_vcvtfp2fxs>;
|
|
def VCVTh2xud : N2VCvtD<1, 1, 0b1101, 0, 1, "vcvt", "u16.f16",
|
|
v4i16, v4f16, int_arm_neon_vcvtfp2fxu>;
|
|
def VCVTxs2hd : N2VCvtD<0, 1, 0b1100, 0, 1, "vcvt", "f16.s16",
|
|
v4f16, v4i16, int_arm_neon_vcvtfxs2fp>;
|
|
def VCVTxu2hd : N2VCvtD<1, 1, 0b1100, 0, 1, "vcvt", "f16.u16",
|
|
v4f16, v4i16, int_arm_neon_vcvtfxu2fp>;
|
|
} // Predicates = [HasNEON, HasFullFP16]
|
|
}
|
|
|
|
let DecoderMethod = "DecodeVCVTQ" in {
|
|
def VCVTf2xsq : N2VCvtQ<0, 1, 0b1111, 0, 1, "vcvt", "s32.f32",
|
|
v4i32, v4f32, int_arm_neon_vcvtfp2fxs>;
|
|
def VCVTf2xuq : N2VCvtQ<1, 1, 0b1111, 0, 1, "vcvt", "u32.f32",
|
|
v4i32, v4f32, int_arm_neon_vcvtfp2fxu>;
|
|
def VCVTxs2fq : N2VCvtQ<0, 1, 0b1110, 0, 1, "vcvt", "f32.s32",
|
|
v4f32, v4i32, int_arm_neon_vcvtfxs2fp>;
|
|
def VCVTxu2fq : N2VCvtQ<1, 1, 0b1110, 0, 1, "vcvt", "f32.u32",
|
|
v4f32, v4i32, int_arm_neon_vcvtfxu2fp>;
|
|
let Predicates = [HasNEON, HasFullFP16] in {
|
|
def VCVTh2xsq : N2VCvtQ<0, 1, 0b1101, 0, 1, "vcvt", "s16.f16",
|
|
v8i16, v8f16, int_arm_neon_vcvtfp2fxs>;
|
|
def VCVTh2xuq : N2VCvtQ<1, 1, 0b1101, 0, 1, "vcvt", "u16.f16",
|
|
v8i16, v8f16, int_arm_neon_vcvtfp2fxu>;
|
|
def VCVTxs2hq : N2VCvtQ<0, 1, 0b1100, 0, 1, "vcvt", "f16.s16",
|
|
v8f16, v8i16, int_arm_neon_vcvtfxs2fp>;
|
|
def VCVTxu2hq : N2VCvtQ<1, 1, 0b1100, 0, 1, "vcvt", "f16.u16",
|
|
v8f16, v8i16, int_arm_neon_vcvtfxu2fp>;
|
|
} // Predicates = [HasNEON, HasFullFP16]
|
|
}
|
|
|
|
def : NEONInstAlias<"vcvt${p}.s32.f32 $Dd, $Dm, #0",
|
|
(VCVTf2sd DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.u32.f32 $Dd, $Dm, #0",
|
|
(VCVTf2ud DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f32.s32 $Dd, $Dm, #0",
|
|
(VCVTs2fd DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f32.u32 $Dd, $Dm, #0",
|
|
(VCVTu2fd DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
|
|
def : NEONInstAlias<"vcvt${p}.s32.f32 $Qd, $Qm, #0",
|
|
(VCVTf2sq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.u32.f32 $Qd, $Qm, #0",
|
|
(VCVTf2uq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f32.s32 $Qd, $Qm, #0",
|
|
(VCVTs2fq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f32.u32 $Qd, $Qm, #0",
|
|
(VCVTu2fq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
|
|
def : NEONInstAlias<"vcvt${p}.s16.f16 $Dd, $Dm, #0",
|
|
(VCVTh2sd DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.u16.f16 $Dd, $Dm, #0",
|
|
(VCVTh2ud DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f16.s16 $Dd, $Dm, #0",
|
|
(VCVTs2hd DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f16.u16 $Dd, $Dm, #0",
|
|
(VCVTu2hd DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
|
|
def : NEONInstAlias<"vcvt${p}.s16.f16 $Qd, $Qm, #0",
|
|
(VCVTh2sq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.u16.f16 $Qd, $Qm, #0",
|
|
(VCVTh2uq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f16.s16 $Qd, $Qm, #0",
|
|
(VCVTs2hq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
def : NEONInstAlias<"vcvt${p}.f16.u16 $Qd, $Qm, #0",
|
|
(VCVTu2hq QPR:$Qd, QPR:$Qm, pred:$p)>;
|
|
|
|
|
|
// VCVT : Vector Convert Between Half-Precision and Single-Precision.
|
|
def VCVTf2h : N2VNInt<0b11, 0b11, 0b01, 0b10, 0b01100, 0, 0,
|
|
IIC_VUNAQ, "vcvt", "f16.f32",
|
|
v4i16, v4f32, int_arm_neon_vcvtfp2hf>,
|
|
Requires<[HasNEON, HasFP16]>;
|
|
def VCVTh2f : N2VLInt<0b11, 0b11, 0b01, 0b10, 0b01110, 0, 0,
|
|
IIC_VUNAQ, "vcvt", "f32.f16",
|
|
v4f32, v4i16, int_arm_neon_vcvthf2fp>,
|
|
Requires<[HasNEON, HasFP16]>;
|
|
|
|
// Vector Reverse.
|
|
|
|
// VREV64 : Vector Reverse elements within 64-bit doublewords
|
|
|
|
class VREV64D<bits<2> op19_18, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, op19_18, 0b00, 0b00000, 0, 0, (outs DPR:$Vd),
|
|
(ins DPR:$Vm), IIC_VMOVD,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (Ty (NEONvrev64 (Ty DPR:$Vm))))]>;
|
|
class VREV64Q<bits<2> op19_18, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, op19_18, 0b00, 0b00000, 1, 0, (outs QPR:$Vd),
|
|
(ins QPR:$Vm), IIC_VMOVQ,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (Ty (NEONvrev64 (Ty QPR:$Vm))))]>;
|
|
|
|
def VREV64d8 : VREV64D<0b00, "vrev64", "8", v8i8>;
|
|
def VREV64d16 : VREV64D<0b01, "vrev64", "16", v4i16>;
|
|
def VREV64d32 : VREV64D<0b10, "vrev64", "32", v2i32>;
|
|
def : Pat<(v2f32 (NEONvrev64 (v2f32 DPR:$Vm))), (VREV64d32 DPR:$Vm)>;
|
|
|
|
def VREV64q8 : VREV64Q<0b00, "vrev64", "8", v16i8>;
|
|
def VREV64q16 : VREV64Q<0b01, "vrev64", "16", v8i16>;
|
|
def VREV64q32 : VREV64Q<0b10, "vrev64", "32", v4i32>;
|
|
def : Pat<(v4f32 (NEONvrev64 (v4f32 QPR:$Vm))), (VREV64q32 QPR:$Vm)>;
|
|
def : Pat<(v8f16 (NEONvrev64 (v8f16 QPR:$Vm))), (VREV64q16 QPR:$Vm)>;
|
|
def : Pat<(v4f16 (NEONvrev64 (v4f16 DPR:$Vm))), (VREV64d16 DPR:$Vm)>;
|
|
|
|
// VREV32 : Vector Reverse elements within 32-bit words
|
|
|
|
class VREV32D<bits<2> op19_18, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, op19_18, 0b00, 0b00001, 0, 0, (outs DPR:$Vd),
|
|
(ins DPR:$Vm), IIC_VMOVD,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (Ty (NEONvrev32 (Ty DPR:$Vm))))]>;
|
|
class VREV32Q<bits<2> op19_18, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, op19_18, 0b00, 0b00001, 1, 0, (outs QPR:$Vd),
|
|
(ins QPR:$Vm), IIC_VMOVQ,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (Ty (NEONvrev32 (Ty QPR:$Vm))))]>;
|
|
|
|
def VREV32d8 : VREV32D<0b00, "vrev32", "8", v8i8>;
|
|
def VREV32d16 : VREV32D<0b01, "vrev32", "16", v4i16>;
|
|
|
|
def VREV32q8 : VREV32Q<0b00, "vrev32", "8", v16i8>;
|
|
def VREV32q16 : VREV32Q<0b01, "vrev32", "16", v8i16>;
|
|
|
|
// VREV16 : Vector Reverse elements within 16-bit halfwords
|
|
|
|
class VREV16D<bits<2> op19_18, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, op19_18, 0b00, 0b00010, 0, 0, (outs DPR:$Vd),
|
|
(ins DPR:$Vm), IIC_VMOVD,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set DPR:$Vd, (Ty (NEONvrev16 (Ty DPR:$Vm))))]>;
|
|
class VREV16Q<bits<2> op19_18, string OpcodeStr, string Dt, ValueType Ty>
|
|
: N2V<0b11, 0b11, op19_18, 0b00, 0b00010, 1, 0, (outs QPR:$Vd),
|
|
(ins QPR:$Vm), IIC_VMOVQ,
|
|
OpcodeStr, Dt, "$Vd, $Vm", "",
|
|
[(set QPR:$Vd, (Ty (NEONvrev16 (Ty QPR:$Vm))))]>;
|
|
|
|
def VREV16d8 : VREV16D<0b00, "vrev16", "8", v8i8>;
|
|
def VREV16q8 : VREV16Q<0b00, "vrev16", "8", v16i8>;
|
|
|
|
// Other Vector Shuffles.
|
|
|
|
// Aligned extractions: really just dropping registers
|
|
|
|
class AlignedVEXTq<ValueType DestTy, ValueType SrcTy, SDNodeXForm LaneCVT>
|
|
: Pat<(DestTy (vector_extract_subvec (SrcTy QPR:$src), (i32 imm:$start))),
|
|
(EXTRACT_SUBREG (SrcTy QPR:$src), (LaneCVT imm:$start))>;
|
|
|
|
def : AlignedVEXTq<v8i8, v16i8, DSubReg_i8_reg>;
|
|
|
|
def : AlignedVEXTq<v4i16, v8i16, DSubReg_i16_reg>;
|
|
|
|
def : AlignedVEXTq<v2i32, v4i32, DSubReg_i32_reg>;
|
|
|
|
def : AlignedVEXTq<v1i64, v2i64, DSubReg_f64_reg>;
|
|
|
|
def : AlignedVEXTq<v2f32, v4f32, DSubReg_i32_reg>;
|
|
|
|
|
|
// VEXT : Vector Extract
|
|
|
|
|
|
// All of these have a two-operand InstAlias.
|
|
let TwoOperandAliasConstraint = "$Vn = $Vd" in {
|
|
class VEXTd<string OpcodeStr, string Dt, ValueType Ty, Operand immTy>
|
|
: N3V<0,1,0b11,{?,?,?,?},0,0, (outs DPR:$Vd),
|
|
(ins DPR:$Vn, DPR:$Vm, immTy:$index), NVExtFrm,
|
|
IIC_VEXTD, OpcodeStr, Dt, "$Vd, $Vn, $Vm, $index", "",
|
|
[(set DPR:$Vd, (Ty (NEONvext (Ty DPR:$Vn),
|
|
(Ty DPR:$Vm), imm:$index)))]> {
|
|
bits<3> index;
|
|
let Inst{11} = 0b0;
|
|
let Inst{10-8} = index{2-0};
|
|
}
|
|
|
|
class VEXTq<string OpcodeStr, string Dt, ValueType Ty, Operand immTy>
|
|
: N3V<0,1,0b11,{?,?,?,?},1,0, (outs QPR:$Vd),
|
|
(ins QPR:$Vn, QPR:$Vm, imm0_15:$index), NVExtFrm,
|
|
IIC_VEXTQ, OpcodeStr, Dt, "$Vd, $Vn, $Vm, $index", "",
|
|
[(set QPR:$Vd, (Ty (NEONvext (Ty QPR:$Vn),
|
|
(Ty QPR:$Vm), imm:$index)))]> {
|
|
bits<4> index;
|
|
let Inst{11-8} = index{3-0};
|
|
}
|
|
}
|
|
|
|
def VEXTd8 : VEXTd<"vext", "8", v8i8, imm0_7> {
|
|
let Inst{10-8} = index{2-0};
|
|
}
|
|
def VEXTd16 : VEXTd<"vext", "16", v4i16, imm0_3> {
|
|
let Inst{10-9} = index{1-0};
|
|
let Inst{8} = 0b0;
|
|
}
|
|
def : Pat<(v4f16 (NEONvext (v4f16 DPR:$Vn), (v4f16 DPR:$Vm), (i32 imm:$index))),
|
|
(VEXTd16 DPR:$Vn, DPR:$Vm, imm:$index)>;
|
|
|
|
def VEXTd32 : VEXTd<"vext", "32", v2i32, imm0_1> {
|
|
let Inst{10} = index{0};
|
|
let Inst{9-8} = 0b00;
|
|
}
|
|
def : Pat<(v2f32 (NEONvext (v2f32 DPR:$Vn), (v2f32 DPR:$Vm), (i32 imm:$index))),
|
|
(VEXTd32 DPR:$Vn, DPR:$Vm, imm:$index)>;
|
|
|
|
def VEXTq8 : VEXTq<"vext", "8", v16i8, imm0_15> {
|
|
let Inst{11-8} = index{3-0};
|
|
}
|
|
def VEXTq16 : VEXTq<"vext", "16", v8i16, imm0_7> {
|
|
let Inst{11-9} = index{2-0};
|
|
let Inst{8} = 0b0;
|
|
}
|
|
def : Pat<(v8f16 (NEONvext (v8f16 QPR:$Vn), (v8f16 QPR:$Vm), (i32 imm:$index))),
|
|
(VEXTq16 QPR:$Vn, QPR:$Vm, imm:$index)>;
|
|
|
|
def VEXTq32 : VEXTq<"vext", "32", v4i32, imm0_3> {
|
|
let Inst{11-10} = index{1-0};
|
|
let Inst{9-8} = 0b00;
|
|
}
|
|
def VEXTq64 : VEXTq<"vext", "64", v2i64, imm0_1> {
|
|
let Inst{11} = index{0};
|
|
let Inst{10-8} = 0b000;
|
|
}
|
|
def : Pat<(v4f32 (NEONvext (v4f32 QPR:$Vn), (v4f32 QPR:$Vm), (i32 imm:$index))),
|
|
(VEXTq32 QPR:$Vn, QPR:$Vm, imm:$index)>;
|
|
|
|
// VTRN : Vector Transpose
|
|
|
|
def VTRNd8 : N2VDShuffle<0b00, 0b00001, "vtrn", "8">;
|
|
def VTRNd16 : N2VDShuffle<0b01, 0b00001, "vtrn", "16">;
|
|
def VTRNd32 : N2VDShuffle<0b10, 0b00001, "vtrn", "32">;
|
|
|
|
def VTRNq8 : N2VQShuffle<0b00, 0b00001, IIC_VPERMQ, "vtrn", "8">;
|
|
def VTRNq16 : N2VQShuffle<0b01, 0b00001, IIC_VPERMQ, "vtrn", "16">;
|
|
def VTRNq32 : N2VQShuffle<0b10, 0b00001, IIC_VPERMQ, "vtrn", "32">;
|
|
|
|
// VUZP : Vector Unzip (Deinterleave)
|
|
|
|
def VUZPd8 : N2VDShuffle<0b00, 0b00010, "vuzp", "8">;
|
|
def VUZPd16 : N2VDShuffle<0b01, 0b00010, "vuzp", "16">;
|
|
// vuzp.32 Dd, Dm is a pseudo-instruction expanded to vtrn.32 Dd, Dm.
|
|
def : NEONInstAlias<"vuzp${p}.32 $Dd, $Dm",
|
|
(VTRNd32 DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
|
|
def VUZPq8 : N2VQShuffle<0b00, 0b00010, IIC_VPERMQ3, "vuzp", "8">;
|
|
def VUZPq16 : N2VQShuffle<0b01, 0b00010, IIC_VPERMQ3, "vuzp", "16">;
|
|
def VUZPq32 : N2VQShuffle<0b10, 0b00010, IIC_VPERMQ3, "vuzp", "32">;
|
|
|
|
// VZIP : Vector Zip (Interleave)
|
|
|
|
def VZIPd8 : N2VDShuffle<0b00, 0b00011, "vzip", "8">;
|
|
def VZIPd16 : N2VDShuffle<0b01, 0b00011, "vzip", "16">;
|
|
// vzip.32 Dd, Dm is a pseudo-instruction expanded to vtrn.32 Dd, Dm.
|
|
def : NEONInstAlias<"vzip${p}.32 $Dd, $Dm",
|
|
(VTRNd32 DPR:$Dd, DPR:$Dm, pred:$p)>;
|
|
|
|
def VZIPq8 : N2VQShuffle<0b00, 0b00011, IIC_VPERMQ3, "vzip", "8">;
|
|
def VZIPq16 : N2VQShuffle<0b01, 0b00011, IIC_VPERMQ3, "vzip", "16">;
|
|
def VZIPq32 : N2VQShuffle<0b10, 0b00011, IIC_VPERMQ3, "vzip", "32">;
|
|
|
|
// Vector Table Lookup and Table Extension.
|
|
|
|
// VTBL : Vector Table Lookup
|
|
let DecoderMethod = "DecodeTBLInstruction" in {
|
|
def VTBL1
|
|
: N3V<1,1,0b11,0b1000,0,0, (outs DPR:$Vd),
|
|
(ins VecListOneD:$Vn, DPR:$Vm), NVTBLFrm, IIC_VTB1,
|
|
"vtbl", "8", "$Vd, $Vn, $Vm", "",
|
|
[(set DPR:$Vd, (v8i8 (NEONvtbl1 VecListOneD:$Vn, DPR:$Vm)))]>;
|
|
|
|
let hasExtraSrcRegAllocReq = 1 in {
|
|
def VTBL2
|
|
: N3V<1,1,0b11,0b1001,0,0, (outs DPR:$Vd),
|
|
(ins VecListDPair:$Vn, DPR:$Vm), NVTBLFrm, IIC_VTB2,
|
|
"vtbl", "8", "$Vd, $Vn, $Vm", "", []>;
|
|
def VTBL3
|
|
: N3V<1,1,0b11,0b1010,0,0, (outs DPR:$Vd),
|
|
(ins VecListThreeD:$Vn, DPR:$Vm), NVTBLFrm, IIC_VTB3,
|
|
"vtbl", "8", "$Vd, $Vn, $Vm", "", []>;
|
|
def VTBL4
|
|
: N3V<1,1,0b11,0b1011,0,0, (outs DPR:$Vd),
|
|
(ins VecListFourD:$Vn, DPR:$Vm),
|
|
NVTBLFrm, IIC_VTB4,
|
|
"vtbl", "8", "$Vd, $Vn, $Vm", "", []>;
|
|
} // hasExtraSrcRegAllocReq = 1
|
|
|
|
def VTBL3Pseudo
|
|
: PseudoNeonI<(outs DPR:$dst), (ins QQPR:$tbl, DPR:$src), IIC_VTB3, "", []>;
|
|
def VTBL4Pseudo
|
|
: PseudoNeonI<(outs DPR:$dst), (ins QQPR:$tbl, DPR:$src), IIC_VTB4, "", []>;
|
|
|
|
// VTBX : Vector Table Extension
|
|
def VTBX1
|
|
: N3V<1,1,0b11,0b1000,1,0, (outs DPR:$Vd),
|
|
(ins DPR:$orig, VecListOneD:$Vn, DPR:$Vm), NVTBLFrm, IIC_VTBX1,
|
|
"vtbx", "8", "$Vd, $Vn, $Vm", "$orig = $Vd",
|
|
[(set DPR:$Vd, (v8i8 (int_arm_neon_vtbx1
|
|
DPR:$orig, VecListOneD:$Vn, DPR:$Vm)))]>;
|
|
let hasExtraSrcRegAllocReq = 1 in {
|
|
def VTBX2
|
|
: N3V<1,1,0b11,0b1001,1,0, (outs DPR:$Vd),
|
|
(ins DPR:$orig, VecListDPair:$Vn, DPR:$Vm), NVTBLFrm, IIC_VTBX2,
|
|
"vtbx", "8", "$Vd, $Vn, $Vm", "$orig = $Vd", []>;
|
|
def VTBX3
|
|
: N3V<1,1,0b11,0b1010,1,0, (outs DPR:$Vd),
|
|
(ins DPR:$orig, VecListThreeD:$Vn, DPR:$Vm),
|
|
NVTBLFrm, IIC_VTBX3,
|
|
"vtbx", "8", "$Vd, $Vn, $Vm",
|
|
"$orig = $Vd", []>;
|
|
def VTBX4
|
|
: N3V<1,1,0b11,0b1011,1,0, (outs DPR:$Vd),
|
|
(ins DPR:$orig, VecListFourD:$Vn, DPR:$Vm), NVTBLFrm, IIC_VTBX4,
|
|
"vtbx", "8", "$Vd, $Vn, $Vm",
|
|
"$orig = $Vd", []>;
|
|
} // hasExtraSrcRegAllocReq = 1
|
|
|
|
def VTBX3Pseudo
|
|
: PseudoNeonI<(outs DPR:$dst), (ins DPR:$orig, QQPR:$tbl, DPR:$src),
|
|
IIC_VTBX3, "$orig = $dst", []>;
|
|
def VTBX4Pseudo
|
|
: PseudoNeonI<(outs DPR:$dst), (ins DPR:$orig, QQPR:$tbl, DPR:$src),
|
|
IIC_VTBX4, "$orig = $dst", []>;
|
|
} // DecoderMethod = "DecodeTBLInstruction"
|
|
|
|
def : Pat<(v8i8 (NEONvtbl2 v8i8:$Vn0, v8i8:$Vn1, v8i8:$Vm)),
|
|
(v8i8 (VTBL2 (REG_SEQUENCE DPair, v8i8:$Vn0, dsub_0,
|
|
v8i8:$Vn1, dsub_1),
|
|
v8i8:$Vm))>;
|
|
def : Pat<(v8i8 (int_arm_neon_vtbx2 v8i8:$orig, v8i8:$Vn0, v8i8:$Vn1,
|
|
v8i8:$Vm)),
|
|
(v8i8 (VTBX2 v8i8:$orig,
|
|
(REG_SEQUENCE DPair, v8i8:$Vn0, dsub_0,
|
|
v8i8:$Vn1, dsub_1),
|
|
v8i8:$Vm))>;
|
|
|
|
def : Pat<(v8i8 (int_arm_neon_vtbl3 v8i8:$Vn0, v8i8:$Vn1,
|
|
v8i8:$Vn2, v8i8:$Vm)),
|
|
(v8i8 (VTBL3Pseudo (REG_SEQUENCE QQPR, v8i8:$Vn0, dsub_0,
|
|
v8i8:$Vn1, dsub_1,
|
|
v8i8:$Vn2, dsub_2,
|
|
(v8i8 (IMPLICIT_DEF)), dsub_3),
|
|
v8i8:$Vm))>;
|
|
def : Pat<(v8i8 (int_arm_neon_vtbx3 v8i8:$orig, v8i8:$Vn0, v8i8:$Vn1,
|
|
v8i8:$Vn2, v8i8:$Vm)),
|
|
(v8i8 (VTBX3Pseudo v8i8:$orig,
|
|
(REG_SEQUENCE QQPR, v8i8:$Vn0, dsub_0,
|
|
v8i8:$Vn1, dsub_1,
|
|
v8i8:$Vn2, dsub_2,
|
|
(v8i8 (IMPLICIT_DEF)), dsub_3),
|
|
v8i8:$Vm))>;
|
|
|
|
def : Pat<(v8i8 (int_arm_neon_vtbl4 v8i8:$Vn0, v8i8:$Vn1,
|
|
v8i8:$Vn2, v8i8:$Vn3, v8i8:$Vm)),
|
|
(v8i8 (VTBL4Pseudo (REG_SEQUENCE QQPR, v8i8:$Vn0, dsub_0,
|
|
v8i8:$Vn1, dsub_1,
|
|
v8i8:$Vn2, dsub_2,
|
|
v8i8:$Vn3, dsub_3),
|
|
v8i8:$Vm))>;
|
|
def : Pat<(v8i8 (int_arm_neon_vtbx4 v8i8:$orig, v8i8:$Vn0, v8i8:$Vn1,
|
|
v8i8:$Vn2, v8i8:$Vn3, v8i8:$Vm)),
|
|
(v8i8 (VTBX4Pseudo v8i8:$orig,
|
|
(REG_SEQUENCE QQPR, v8i8:$Vn0, dsub_0,
|
|
v8i8:$Vn1, dsub_1,
|
|
v8i8:$Vn2, dsub_2,
|
|
v8i8:$Vn3, dsub_3),
|
|
v8i8:$Vm))>;
|
|
|
|
// VRINT : Vector Rounding
|
|
multiclass VRINT_FPI<string op, bits<3> op9_7, SDPatternOperator Int> {
|
|
let PostEncoderMethod = "NEONThumb2V8PostEncoder", DecoderNamespace = "v8NEON" in {
|
|
def Df : N2VDIntnp<0b10, 0b10, 0b100, 0, NoItinerary,
|
|
!strconcat("vrint", op), "f32",
|
|
v2f32, v2f32, Int>, Requires<[HasV8, HasNEON]> {
|
|
let Inst{9-7} = op9_7;
|
|
}
|
|
def Qf : N2VQIntnp<0b10, 0b10, 0b100, 0, NoItinerary,
|
|
!strconcat("vrint", op), "f32",
|
|
v4f32, v4f32, Int>, Requires<[HasV8, HasNEON]> {
|
|
let Inst{9-7} = op9_7;
|
|
}
|
|
def Dh : N2VDIntnp<0b01, 0b10, 0b100, 0, NoItinerary,
|
|
!strconcat("vrint", op), "f16",
|
|
v4f16, v4f16, Int>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]> {
|
|
let Inst{9-7} = op9_7;
|
|
}
|
|
def Qh : N2VQIntnp<0b01, 0b10, 0b100, 0, NoItinerary,
|
|
!strconcat("vrint", op), "f16",
|
|
v8f16, v8f16, Int>,
|
|
Requires<[HasV8, HasNEON, HasFullFP16]> {
|
|
let Inst{9-7} = op9_7;
|
|
}
|
|
}
|
|
|
|
def : NEONInstAlias<!strconcat("vrint", op, ".f32.f32\t$Dd, $Dm"),
|
|
(!cast<Instruction>(NAME#"Df") DPR:$Dd, DPR:$Dm)>;
|
|
def : NEONInstAlias<!strconcat("vrint", op, ".f32.f32\t$Qd, $Qm"),
|
|
(!cast<Instruction>(NAME#"Qf") QPR:$Qd, QPR:$Qm)>;
|
|
let Predicates = [HasNEON, HasFullFP16] in {
|
|
def : NEONInstAlias<!strconcat("vrint", op, ".f16.f16\t$Dd, $Dm"),
|
|
(!cast<Instruction>(NAME#"Dh") DPR:$Dd, DPR:$Dm)>;
|
|
def : NEONInstAlias<!strconcat("vrint", op, ".f16.f16\t$Qd, $Qm"),
|
|
(!cast<Instruction>(NAME#"Qh") QPR:$Qd, QPR:$Qm)>;
|
|
}
|
|
}
|
|
|
|
defm VRINTNN : VRINT_FPI<"n", 0b000, int_arm_neon_vrintn>;
|
|
defm VRINTXN : VRINT_FPI<"x", 0b001, int_arm_neon_vrintx>;
|
|
defm VRINTAN : VRINT_FPI<"a", 0b010, int_arm_neon_vrinta>;
|
|
defm VRINTZN : VRINT_FPI<"z", 0b011, int_arm_neon_vrintz>;
|
|
defm VRINTMN : VRINT_FPI<"m", 0b101, int_arm_neon_vrintm>;
|
|
defm VRINTPN : VRINT_FPI<"p", 0b111, int_arm_neon_vrintp>;
|
|
|
|
// Cryptography instructions
|
|
let PostEncoderMethod = "NEONThumb2DataIPostEncoder",
|
|
DecoderNamespace = "v8Crypto", hasSideEffects = 0 in {
|
|
class AES<string op, bit op7, bit op6, SDPatternOperator Int>
|
|
: N2VQIntXnp<0b00, 0b00, 0b011, op6, op7, NoItinerary,
|
|
!strconcat("aes", op), "8", v16i8, v16i8, Int>,
|
|
Requires<[HasV8, HasCrypto]>;
|
|
class AES2Op<string op, bit op7, bit op6, SDPatternOperator Int>
|
|
: N2VQIntX2np<0b00, 0b00, 0b011, op6, op7, NoItinerary,
|
|
!strconcat("aes", op), "8", v16i8, v16i8, Int>,
|
|
Requires<[HasV8, HasCrypto]>;
|
|
class N2SHA<string op, bits<2> op17_16, bits<3> op10_8, bit op7, bit op6,
|
|
SDPatternOperator Int>
|
|
: N2VQIntXnp<0b10, op17_16, op10_8, op6, op7, NoItinerary,
|
|
!strconcat("sha", op), "32", v4i32, v4i32, Int>,
|
|
Requires<[HasV8, HasCrypto]>;
|
|
class N2SHA2Op<string op, bits<2> op17_16, bits<3> op10_8, bit op7, bit op6,
|
|
SDPatternOperator Int>
|
|
: N2VQIntX2np<0b10, op17_16, op10_8, op6, op7, NoItinerary,
|
|
!strconcat("sha", op), "32", v4i32, v4i32, Int>,
|
|
Requires<[HasV8, HasCrypto]>;
|
|
class N3SHA3Op<string op, bits<5> op27_23, bits<2> op21_20, SDPatternOperator Int>
|
|
: N3VQInt3np<op27_23, op21_20, 0b1100, 1, 0, N3RegFrm, NoItinerary,
|
|
!strconcat("sha", op), "32", v4i32, v4i32, Int, 0>,
|
|
Requires<[HasV8, HasCrypto]>;
|
|
}
|
|
|
|
def AESD : AES2Op<"d", 0, 1, int_arm_neon_aesd>;
|
|
def AESE : AES2Op<"e", 0, 0, int_arm_neon_aese>;
|
|
def AESIMC : AES<"imc", 1, 1, int_arm_neon_aesimc>;
|
|
def AESMC : AES<"mc", 1, 0, int_arm_neon_aesmc>;
|
|
|
|
def SHA1H : N2SHA<"1h", 0b01, 0b010, 1, 1, null_frag>;
|
|
def SHA1SU1 : N2SHA2Op<"1su1", 0b10, 0b011, 1, 0, int_arm_neon_sha1su1>;
|
|
def SHA256SU0 : N2SHA2Op<"256su0", 0b10, 0b011, 1, 1, int_arm_neon_sha256su0>;
|
|
def SHA1C : N3SHA3Op<"1c", 0b00100, 0b00, null_frag>;
|
|
def SHA1M : N3SHA3Op<"1m", 0b00100, 0b10, null_frag>;
|
|
def SHA1P : N3SHA3Op<"1p", 0b00100, 0b01, null_frag>;
|
|
def SHA1SU0 : N3SHA3Op<"1su0", 0b00100, 0b11, int_arm_neon_sha1su0>;
|
|
def SHA256H : N3SHA3Op<"256h", 0b00110, 0b00, int_arm_neon_sha256h>;
|
|
def SHA256H2 : N3SHA3Op<"256h2", 0b00110, 0b01, int_arm_neon_sha256h2>;
|
|
def SHA256SU1 : N3SHA3Op<"256su1", 0b00110, 0b10, int_arm_neon_sha256su1>;
|
|
|
|
def : Pat<(i32 (int_arm_neon_sha1h i32:$Rn)),
|
|
(COPY_TO_REGCLASS (f32 (EXTRACT_SUBREG
|
|
(SHA1H (SUBREG_TO_REG (i64 0),
|
|
(f32 (COPY_TO_REGCLASS i32:$Rn, SPR)),
|
|
ssub_0)),
|
|
ssub_0)), GPR)>;
|
|
|
|
def : Pat<(v4i32 (int_arm_neon_sha1c v4i32:$hash_abcd, i32:$hash_e, v4i32:$wk)),
|
|
(SHA1C v4i32:$hash_abcd,
|
|
(SUBREG_TO_REG (i64 0),
|
|
(f32 (COPY_TO_REGCLASS i32:$hash_e, SPR)),
|
|
ssub_0),
|
|
v4i32:$wk)>;
|
|
|
|
def : Pat<(v4i32 (int_arm_neon_sha1m v4i32:$hash_abcd, i32:$hash_e, v4i32:$wk)),
|
|
(SHA1M v4i32:$hash_abcd,
|
|
(SUBREG_TO_REG (i64 0),
|
|
(f32 (COPY_TO_REGCLASS i32:$hash_e, SPR)),
|
|
ssub_0),
|
|
v4i32:$wk)>;
|
|
|
|
def : Pat<(v4i32 (int_arm_neon_sha1p v4i32:$hash_abcd, i32:$hash_e, v4i32:$wk)),
|
|
(SHA1P v4i32:$hash_abcd,
|
|
(SUBREG_TO_REG (i64 0),
|
|
(f32 (COPY_TO_REGCLASS i32:$hash_e, SPR)),
|
|
ssub_0),
|
|
v4i32:$wk)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// NEON instructions for single-precision FP math
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class N2VSPat<SDNode OpNode, NeonI Inst>
|
|
: NEONFPPat<(f32 (OpNode SPR:$a)),
|
|
(EXTRACT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (Inst
|
|
(INSERT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (v2f32 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
SPR:$a, ssub_0)), DPR_VFP2)), ssub_0)>;
|
|
|
|
class N3VSPat<SDNode OpNode, NeonI Inst>
|
|
: NEONFPPat<(f32 (OpNode SPR:$a, SPR:$b)),
|
|
(EXTRACT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (Inst
|
|
(INSERT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (v2f32 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
SPR:$a, ssub_0),
|
|
(INSERT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (v2f32 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
SPR:$b, ssub_0)), DPR_VFP2)), ssub_0)>;
|
|
|
|
class N3VSPatFP16<SDNode OpNode, NeonI Inst>
|
|
: NEONFPPat<(f16 (OpNode HPR:$a, HPR:$b)),
|
|
(EXTRACT_SUBREG
|
|
(v4f16 (COPY_TO_REGCLASS (Inst
|
|
(INSERT_SUBREG
|
|
(v4f16 (COPY_TO_REGCLASS (v4f16 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
HPR:$a, ssub_0),
|
|
(INSERT_SUBREG
|
|
(v4f16 (COPY_TO_REGCLASS (v4f16 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
HPR:$b, ssub_0)), DPR_VFP2)), ssub_0)>;
|
|
|
|
class N3VSMulOpPat<SDNode MulNode, SDNode OpNode, NeonI Inst>
|
|
: NEONFPPat<(f32 (OpNode SPR:$acc, (f32 (MulNode SPR:$a, SPR:$b)))),
|
|
(EXTRACT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (Inst
|
|
(INSERT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (v2f32 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
SPR:$acc, ssub_0),
|
|
(INSERT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (v2f32 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
SPR:$a, ssub_0),
|
|
(INSERT_SUBREG
|
|
(v2f32 (COPY_TO_REGCLASS (v2f32 (IMPLICIT_DEF)), DPR_VFP2)),
|
|
SPR:$b, ssub_0)), DPR_VFP2)), ssub_0)>;
|
|
|
|
class NVCVTIFPat<SDNode OpNode, NeonI Inst>
|
|
: NEONFPPat<(f32 (OpNode GPR:$a)),
|
|
(f32 (EXTRACT_SUBREG
|
|
(v2f32 (Inst
|
|
(INSERT_SUBREG
|
|
(v2f32 (IMPLICIT_DEF)),
|
|
(i32 (COPY_TO_REGCLASS GPR:$a, SPR)), ssub_0))),
|
|
ssub_0))>;
|
|
class NVCVTFIPat<SDNode OpNode, NeonI Inst>
|
|
: NEONFPPat<(i32 (OpNode SPR:$a)),
|
|
(i32 (EXTRACT_SUBREG
|
|
(v2f32 (Inst (INSERT_SUBREG (v2f32 (IMPLICIT_DEF)),
|
|
SPR:$a, ssub_0))),
|
|
ssub_0))>;
|
|
|
|
def : N3VSPat<fadd, VADDfd>;
|
|
def : N3VSPat<fsub, VSUBfd>;
|
|
def : N3VSPat<fmul, VMULfd>;
|
|
def : N3VSMulOpPat<fmul, fadd, VMLAfd>,
|
|
Requires<[HasNEON, UseNEONForFP, UseFPVMLx, DontUseFusedMAC]>;
|
|
def : N3VSMulOpPat<fmul, fsub, VMLSfd>,
|
|
Requires<[HasNEON, UseNEONForFP, UseFPVMLx, DontUseFusedMAC]>;
|
|
def : N3VSMulOpPat<fmul, fadd, VFMAfd>,
|
|
Requires<[HasVFP4, UseNEONForFP, UseFusedMAC]>;
|
|
def : N3VSMulOpPat<fmul, fsub, VFMSfd>,
|
|
Requires<[HasVFP4, UseNEONForFP, UseFusedMAC]>;
|
|
def : N2VSPat<fabs, VABSfd>;
|
|
def : N2VSPat<fneg, VNEGfd>;
|
|
def : N3VSPatFP16<fmaxnan, VMAXhd>, Requires<[HasFullFP16]>;
|
|
def : N3VSPatFP16<fminnan, VMINhd>, Requires<[HasFullFP16]>;
|
|
def : N3VSPat<fmaxnan, VMAXfd>, Requires<[HasNEON]>;
|
|
def : N3VSPat<fminnan, VMINfd>, Requires<[HasNEON]>;
|
|
def : NVCVTFIPat<fp_to_sint, VCVTf2sd>;
|
|
def : NVCVTFIPat<fp_to_uint, VCVTf2ud>;
|
|
def : NVCVTIFPat<sint_to_fp, VCVTs2fd>;
|
|
def : NVCVTIFPat<uint_to_fp, VCVTu2fd>;
|
|
|
|
// NEON doesn't have any f64 conversions, so provide patterns to make
|
|
// sure the VFP conversions match when extracting from a vector.
|
|
def : VFPPat<(f64 (sint_to_fp (extractelt (v2i32 DPR:$src), imm:$lane))),
|
|
(VSITOD (EXTRACT_SUBREG DPR:$src, (SSubReg_f32_reg imm:$lane)))>;
|
|
def : VFPPat<(f64 (sint_to_fp (extractelt (v4i32 QPR:$src), imm:$lane))),
|
|
(VSITOD (EXTRACT_SUBREG QPR:$src, (SSubReg_f32_reg imm:$lane)))>;
|
|
def : VFPPat<(f64 (uint_to_fp (extractelt (v2i32 DPR:$src), imm:$lane))),
|
|
(VUITOD (EXTRACT_SUBREG DPR:$src, (SSubReg_f32_reg imm:$lane)))>;
|
|
def : VFPPat<(f64 (uint_to_fp (extractelt (v4i32 QPR:$src), imm:$lane))),
|
|
(VUITOD (EXTRACT_SUBREG QPR:$src, (SSubReg_f32_reg imm:$lane)))>;
|
|
|
|
|
|
// Prefer VMOVDRR for i32 -> f32 bitcasts, it can write all DPR registers.
|
|
def : Pat<(f32 (bitconvert GPR:$a)),
|
|
(EXTRACT_SUBREG (VMOVDRR GPR:$a, GPR:$a), ssub_0)>,
|
|
Requires<[HasNEON, DontUseVMOVSR]>;
|
|
def : Pat<(arm_vmovsr GPR:$a),
|
|
(EXTRACT_SUBREG (VMOVDRR GPR:$a, GPR:$a), ssub_0)>,
|
|
Requires<[HasNEON, DontUseVMOVSR]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Non-Instruction Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// bit_convert
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v1i64 (bitconvert (v2i32 DPR:$src))), (v1i64 DPR:$src)>;
|
|
def : Pat<(v1i64 (bitconvert (v4i16 DPR:$src))), (v1i64 DPR:$src)>;
|
|
def : Pat<(v1i64 (bitconvert (v8i8 DPR:$src))), (v1i64 DPR:$src)>;
|
|
}
|
|
def : Pat<(v1i64 (bitconvert (f64 DPR:$src))), (v1i64 DPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v1i64 (bitconvert (v2f32 DPR:$src))), (v1i64 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (v1i64 DPR:$src))), (v2i32 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (v4i16 DPR:$src))), (v2i32 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (v8i8 DPR:$src))), (v2i32 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (f64 DPR:$src))), (v2i32 DPR:$src)>;
|
|
}
|
|
def : Pat<(v2i32 (bitconvert (v2f32 DPR:$src))), (v2i32 DPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v4i16 (bitconvert (v1i64 DPR:$src))), (v4i16 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (v2i32 DPR:$src))), (v4i16 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (v8i8 DPR:$src))), (v4i16 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (f64 DPR:$src))), (v4i16 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (v2f32 DPR:$src))), (v4i16 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v1i64 DPR:$src))), (v8i8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v2i32 DPR:$src))), (v8i8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v4i16 DPR:$src))), (v8i8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (f64 DPR:$src))), (v8i8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v2f32 DPR:$src))), (v8i8 DPR:$src)>;
|
|
}
|
|
def : Pat<(f64 (bitconvert (v1i64 DPR:$src))), (f64 DPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(f64 (bitconvert (v2i32 DPR:$src))), (f64 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v4i16 DPR:$src))), (f64 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v4f16 DPR:$src))), (f64 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v8i8 DPR:$src))), (f64 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v2f32 DPR:$src))), (f64 DPR:$src)>;
|
|
def : Pat<(v2f32 (bitconvert (f64 DPR:$src))), (v2f32 DPR:$src)>;
|
|
def : Pat<(v4f16 (bitconvert (f64 DPR:$src))), (v4f16 DPR:$src)>;
|
|
def : Pat<(v2f32 (bitconvert (v1i64 DPR:$src))), (v2f32 DPR:$src)>;
|
|
}
|
|
def : Pat<(v2f32 (bitconvert (v2i32 DPR:$src))), (v2f32 DPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v2f32 (bitconvert (v4i16 DPR:$src))), (v2f32 DPR:$src)>;
|
|
def : Pat<(v2f32 (bitconvert (v8i8 DPR:$src))), (v2f32 DPR:$src)>;
|
|
}
|
|
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v2i64 (bitconvert (v4i32 QPR:$src))), (v2i64 QPR:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v8i16 QPR:$src))), (v2i64 QPR:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v16i8 QPR:$src))), (v2i64 QPR:$src)>;
|
|
}
|
|
def : Pat<(v2i64 (bitconvert (v2f64 QPR:$src))), (v2i64 QPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v2i64 (bitconvert (v4f32 QPR:$src))), (v2i64 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v2i64 QPR:$src))), (v4i32 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v8i16 QPR:$src))), (v4i32 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v16i8 QPR:$src))), (v4i32 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v2f64 QPR:$src))), (v4i32 QPR:$src)>;
|
|
}
|
|
def : Pat<(v4i32 (bitconvert (v4f32 QPR:$src))), (v4i32 QPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v8i16 (bitconvert (v2i64 QPR:$src))), (v8i16 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4i32 QPR:$src))), (v8i16 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v16i8 QPR:$src))), (v8i16 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v2f64 QPR:$src))), (v8i16 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4f32 QPR:$src))), (v8i16 QPR:$src)>;
|
|
def : Pat<(v8f16 (bitconvert (v2f64 QPR:$src))), (v8f16 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v2i64 QPR:$src))), (v16i8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4i32 QPR:$src))), (v16i8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v8i16 QPR:$src))), (v16i8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v2f64 QPR:$src))), (v16i8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4f32 QPR:$src))), (v16i8 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v2i64 QPR:$src))), (v4f32 QPR:$src)>;
|
|
}
|
|
def : Pat<(v4f32 (bitconvert (v4i32 QPR:$src))), (v4f32 QPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v4f32 (bitconvert (v8i16 QPR:$src))), (v4f32 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v16i8 QPR:$src))), (v4f32 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v2f64 QPR:$src))), (v4f32 QPR:$src)>;
|
|
}
|
|
def : Pat<(v2f64 (bitconvert (v2i64 QPR:$src))), (v2f64 QPR:$src)>;
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v2f64 (bitconvert (v4i32 QPR:$src))), (v2f64 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v8i16 QPR:$src))), (v2f64 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v8f16 QPR:$src))), (v2f64 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v16i8 QPR:$src))), (v2f64 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v4f32 QPR:$src))), (v2f64 QPR:$src)>;
|
|
}
|
|
|
|
let Predicates = [IsBE] in {
|
|
// 64 bit conversions
|
|
def : Pat<(v1i64 (bitconvert (v2i32 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(v1i64 (bitconvert (v4i16 DPR:$src))), (VREV64d16 DPR:$src)>;
|
|
def : Pat<(v1i64 (bitconvert (v8i8 DPR:$src))), (VREV64d8 DPR:$src)>;
|
|
def : Pat<(v1i64 (bitconvert (v2f32 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (v1i64 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (v4i16 DPR:$src))), (VREV32d16 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (v8i8 DPR:$src))), (VREV32d8 DPR:$src)>;
|
|
def : Pat<(v2i32 (bitconvert (f64 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (v1i64 DPR:$src))), (VREV64d16 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (v2i32 DPR:$src))), (VREV32d16 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (v8i8 DPR:$src))), (VREV16d8 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (f64 DPR:$src))), (VREV64d16 DPR:$src)>;
|
|
def : Pat<(v4i16 (bitconvert (v2f32 DPR:$src))), (VREV32d16 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v1i64 DPR:$src))), (VREV64d8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v2i32 DPR:$src))), (VREV32d8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v4i16 DPR:$src))), (VREV16d8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (f64 DPR:$src))), (VREV64d8 DPR:$src)>;
|
|
def : Pat<(v8i8 (bitconvert (v2f32 DPR:$src))), (VREV32d8 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v2i32 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v4f16 DPR:$src))), (VREV64d16 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v4i16 DPR:$src))), (VREV64d16 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v8i8 DPR:$src))), (VREV64d8 DPR:$src)>;
|
|
def : Pat<(f64 (bitconvert (v2f32 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(v2f32 (bitconvert (f64 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(v2f32 (bitconvert (v1i64 DPR:$src))), (VREV64d32 DPR:$src)>;
|
|
def : Pat<(v2f32 (bitconvert (v4i16 DPR:$src))), (VREV32d16 DPR:$src)>;
|
|
def : Pat<(v2f32 (bitconvert (v8i8 DPR:$src))), (VREV32d8 DPR:$src)>;
|
|
|
|
// 128 bit conversions
|
|
def : Pat<(v2i64 (bitconvert (v4i32 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v8i16 QPR:$src))), (VREV64q16 QPR:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v16i8 QPR:$src))), (VREV64q8 QPR:$src)>;
|
|
def : Pat<(v2i64 (bitconvert (v4f32 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v2i64 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v8i16 QPR:$src))), (VREV32q16 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v16i8 QPR:$src))), (VREV32q8 QPR:$src)>;
|
|
def : Pat<(v4i32 (bitconvert (v2f64 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v2i64 QPR:$src))), (VREV64q16 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4i32 QPR:$src))), (VREV32q16 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v16i8 QPR:$src))), (VREV16q8 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v2f64 QPR:$src))), (VREV64q16 QPR:$src)>;
|
|
def : Pat<(v8f16 (bitconvert (v2f64 QPR:$src))), (VREV64q16 QPR:$src)>;
|
|
def : Pat<(v8i16 (bitconvert (v4f32 QPR:$src))), (VREV32q16 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v2i64 QPR:$src))), (VREV64q8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4i32 QPR:$src))), (VREV32q8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v8i16 QPR:$src))), (VREV16q8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v2f64 QPR:$src))), (VREV64q8 QPR:$src)>;
|
|
def : Pat<(v16i8 (bitconvert (v4f32 QPR:$src))), (VREV32q8 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v2i64 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v8i16 QPR:$src))), (VREV32q16 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v8f16 QPR:$src))), (VREV32q16 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v16i8 QPR:$src))), (VREV32q8 QPR:$src)>;
|
|
def : Pat<(v4f32 (bitconvert (v2f64 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v4i32 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v8i16 QPR:$src))), (VREV64q16 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v8f16 QPR:$src))), (VREV64q16 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v16i8 QPR:$src))), (VREV64q8 QPR:$src)>;
|
|
def : Pat<(v2f64 (bitconvert (v4f32 QPR:$src))), (VREV64q32 QPR:$src)>;
|
|
}
|
|
|
|
// Use VLD1/VST1 + VREV for non-word-aligned v2f64 load/store on Big Endian
|
|
def : Pat<(v2f64 (byte_alignedload addrmode6:$addr)),
|
|
(VREV64q8 (VLD1q8 addrmode6:$addr))>, Requires<[IsBE]>;
|
|
def : Pat<(byte_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
|
|
(VST1q8 addrmode6:$addr, (VREV64q8 QPR:$value))>, Requires<[IsBE]>;
|
|
def : Pat<(v2f64 (hword_alignedload addrmode6:$addr)),
|
|
(VREV64q16 (VLD1q16 addrmode6:$addr))>, Requires<[IsBE]>;
|
|
def : Pat<(hword_alignedstore (v2f64 QPR:$value), addrmode6:$addr),
|
|
(VST1q16 addrmode6:$addr, (VREV64q16 QPR:$value))>, Requires<[IsBE]>;
|
|
|
|
// Fold extracting an element out of a v2i32 into a vfp register.
|
|
def : Pat<(f32 (bitconvert (i32 (extractelt (v2i32 DPR:$src), imm:$lane)))),
|
|
(f32 (EXTRACT_SUBREG DPR:$src, (SSubReg_f32_reg imm:$lane)))>;
|
|
|
|
// Vector lengthening move with load, matching extending loads.
|
|
|
|
// extload, zextload and sextload for a standard lengthening load. Example:
|
|
// Lengthen_Single<"8", "i16", "8"> =
|
|
// Pat<(v8i16 (extloadvi8 addrmode6:$addr))
|
|
// (VMOVLuv8i16 (VLD1d8 addrmode6:$addr,
|
|
// (f64 (IMPLICIT_DEF)), (i32 0)))>;
|
|
multiclass Lengthen_Single<string DestLanes, string DestTy, string SrcTy> {
|
|
let AddedComplexity = 10 in {
|
|
def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("extloadvi" # SrcTy) addrmode6:$addr)),
|
|
(!cast<Instruction>("VMOVLuv" # DestLanes # DestTy)
|
|
(!cast<Instruction>("VLD1d" # SrcTy) addrmode6:$addr))>;
|
|
|
|
def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("zextloadvi" # SrcTy) addrmode6:$addr)),
|
|
(!cast<Instruction>("VMOVLuv" # DestLanes # DestTy)
|
|
(!cast<Instruction>("VLD1d" # SrcTy) addrmode6:$addr))>;
|
|
|
|
def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("sextloadvi" # SrcTy) addrmode6:$addr)),
|
|
(!cast<Instruction>("VMOVLsv" # DestLanes # DestTy)
|
|
(!cast<Instruction>("VLD1d" # SrcTy) addrmode6:$addr))>;
|
|
}
|
|
}
|
|
|
|
// extload, zextload and sextload for a lengthening load which only uses
|
|
// half the lanes available. Example:
|
|
// Lengthen_HalfSingle<"4", "i16", "8", "i16", "i8"> =
|
|
// Pat<(v4i16 (extloadvi8 addrmode6oneL32:$addr)),
|
|
// (EXTRACT_SUBREG (VMOVLuv8i16 (VLD1LNd32 addrmode6oneL32:$addr,
|
|
// (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
// dsub_0)>;
|
|
multiclass Lengthen_HalfSingle<string DestLanes, string DestTy, string SrcTy,
|
|
string InsnLanes, string InsnTy> {
|
|
def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("extloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # InsnLanes # InsnTy)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0)>;
|
|
def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("zextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # InsnLanes # InsnTy)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0)>;
|
|
def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("sextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # InsnLanes # InsnTy)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0)>;
|
|
}
|
|
|
|
// The following class definition is basically a copy of the
|
|
// Lengthen_HalfSingle definition above, however with an additional parameter
|
|
// "RevLanes" to select the correct VREV32dXX instruction. This is to convert
|
|
// data loaded by VLD1LN into proper vector format in big endian mode.
|
|
multiclass Lengthen_HalfSingle_Big_Endian<string DestLanes, string DestTy, string SrcTy,
|
|
string InsnLanes, string InsnTy, string RevLanes> {
|
|
def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("extloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # InsnLanes # InsnTy)
|
|
(!cast<Instruction>("VREV32d" # RevLanes)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0)>;
|
|
def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("zextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # InsnLanes # InsnTy)
|
|
(!cast<Instruction>("VREV32d" # RevLanes)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0)>;
|
|
def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("sextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # InsnLanes # InsnTy)
|
|
(!cast<Instruction>("VREV32d" # RevLanes)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0)>;
|
|
}
|
|
|
|
// extload, zextload and sextload for a lengthening load followed by another
|
|
// lengthening load, to quadruple the initial length.
|
|
//
|
|
// Lengthen_Double<"4", "i32", "i8", "8", "i16", "4", "i32"> =
|
|
// Pat<(v4i32 (extloadvi8 addrmode6oneL32:$addr))
|
|
// (EXTRACT_SUBREG (VMOVLuv4i32
|
|
// (EXTRACT_SUBREG (VMOVLuv8i16 (VLD1LNd32 addrmode6oneL32:$addr,
|
|
// (f64 (IMPLICIT_DEF)),
|
|
// (i32 0))),
|
|
// dsub_0)),
|
|
// dsub_0)>;
|
|
multiclass Lengthen_Double<string DestLanes, string DestTy, string SrcTy,
|
|
string Insn1Lanes, string Insn1Ty, string Insn2Lanes,
|
|
string Insn2Ty> {
|
|
def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("extloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0))>;
|
|
def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("zextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0))>;
|
|
def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("sextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(!cast<Instruction>("VMOVLsv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn1Lanes # Insn1Ty)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0))>;
|
|
}
|
|
|
|
// The following class definition is basically a copy of the
|
|
// Lengthen_Double definition above, however with an additional parameter
|
|
// "RevLanes" to select the correct VREV32dXX instruction. This is to convert
|
|
// data loaded by VLD1LN into proper vector format in big endian mode.
|
|
multiclass Lengthen_Double_Big_Endian<string DestLanes, string DestTy, string SrcTy,
|
|
string Insn1Lanes, string Insn1Ty, string Insn2Lanes,
|
|
string Insn2Ty, string RevLanes> {
|
|
def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("extloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(!cast<Instruction>("VREV32d" # RevLanes)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0))>;
|
|
def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("zextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(!cast<Instruction>("VREV32d" # RevLanes)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0))>;
|
|
def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("sextloadv" # SrcTy) addrmode6oneL32:$addr)),
|
|
(!cast<Instruction>("VMOVLsv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn1Lanes # Insn1Ty)
|
|
(!cast<Instruction>("VREV32d" # RevLanes)
|
|
(VLD1LNd32 addrmode6oneL32:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0))>;
|
|
}
|
|
|
|
// extload, zextload and sextload for a lengthening load followed by another
|
|
// lengthening load, to quadruple the initial length, but which ends up only
|
|
// requiring half the available lanes (a 64-bit outcome instead of a 128-bit).
|
|
//
|
|
// Lengthen_HalfDouble<"2", "i32", "i8", "8", "i16", "4", "i32"> =
|
|
// Pat<(v2i32 (extloadvi8 addrmode6:$addr))
|
|
// (EXTRACT_SUBREG (VMOVLuv4i32
|
|
// (EXTRACT_SUBREG (VMOVLuv8i16 (VLD1LNd16 addrmode6:$addr,
|
|
// (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
// dsub_0)),
|
|
// dsub_0)>;
|
|
multiclass Lengthen_HalfDouble<string DestLanes, string DestTy, string SrcTy,
|
|
string Insn1Lanes, string Insn1Ty, string Insn2Lanes,
|
|
string Insn2Ty> {
|
|
def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("extloadv" # SrcTy) addrmode6:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0)),
|
|
dsub_0)>;
|
|
def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("zextloadv" # SrcTy) addrmode6:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0)),
|
|
dsub_0)>;
|
|
def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("sextloadv" # SrcTy) addrmode6:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn1Lanes # Insn1Ty)
|
|
(VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0))),
|
|
dsub_0)),
|
|
dsub_0)>;
|
|
}
|
|
|
|
// The following class definition is basically a copy of the
|
|
// Lengthen_HalfDouble definition above, however with an additional VREV16d8
|
|
// instruction to convert data loaded by VLD1LN into proper vector format
|
|
// in big endian mode.
|
|
multiclass Lengthen_HalfDouble_Big_Endian<string DestLanes, string DestTy, string SrcTy,
|
|
string Insn1Lanes, string Insn1Ty, string Insn2Lanes,
|
|
string Insn2Ty> {
|
|
def _Any : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("extloadv" # SrcTy) addrmode6:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(!cast<Instruction>("VREV16d8")
|
|
(VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0)),
|
|
dsub_0)>;
|
|
def _Z : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("zextloadv" # SrcTy) addrmode6:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLuv" # Insn1Lanes # Insn1Ty)
|
|
(!cast<Instruction>("VREV16d8")
|
|
(VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0)),
|
|
dsub_0)>;
|
|
def _S : Pat<(!cast<ValueType>("v" # DestLanes # DestTy)
|
|
(!cast<PatFrag>("sextloadv" # SrcTy) addrmode6:$addr)),
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn2Lanes # Insn2Ty)
|
|
(EXTRACT_SUBREG (!cast<Instruction>("VMOVLsv" # Insn1Lanes # Insn1Ty)
|
|
(!cast<Instruction>("VREV16d8")
|
|
(VLD1LNd16 addrmode6:$addr, (f64 (IMPLICIT_DEF)), (i32 0)))),
|
|
dsub_0)),
|
|
dsub_0)>;
|
|
}
|
|
|
|
defm : Lengthen_Single<"8", "i16", "8">; // v8i8 -> v8i16
|
|
defm : Lengthen_Single<"4", "i32", "16">; // v4i16 -> v4i32
|
|
defm : Lengthen_Single<"2", "i64", "32">; // v2i32 -> v2i64
|
|
|
|
let Predicates = [IsLE] in {
|
|
defm : Lengthen_HalfSingle<"4", "i16", "i8", "8", "i16">; // v4i8 -> v4i16
|
|
defm : Lengthen_HalfSingle<"2", "i32", "i16", "4", "i32">; // v2i16 -> v2i32
|
|
|
|
// Double lengthening - v4i8 -> v4i16 -> v4i32
|
|
defm : Lengthen_Double<"4", "i32", "i8", "8", "i16", "4", "i32">;
|
|
// v2i8 -> v2i16 -> v2i32
|
|
defm : Lengthen_HalfDouble<"2", "i32", "i8", "8", "i16", "4", "i32">;
|
|
// v2i16 -> v2i32 -> v2i64
|
|
defm : Lengthen_Double<"2", "i64", "i16", "4", "i32", "2", "i64">;
|
|
}
|
|
|
|
let Predicates = [IsBE] in {
|
|
defm : Lengthen_HalfSingle_Big_Endian<"4", "i16", "i8", "8", "i16", "8">; // v4i8 -> v4i16
|
|
defm : Lengthen_HalfSingle_Big_Endian<"2", "i32", "i16", "4", "i32", "16">; // v2i16 -> v2i32
|
|
|
|
// Double lengthening - v4i8 -> v4i16 -> v4i32
|
|
defm : Lengthen_Double_Big_Endian<"4", "i32", "i8", "8", "i16", "4", "i32", "8">;
|
|
// v2i8 -> v2i16 -> v2i32
|
|
defm : Lengthen_HalfDouble_Big_Endian<"2", "i32", "i8", "8", "i16", "4", "i32">;
|
|
// v2i16 -> v2i32 -> v2i64
|
|
defm : Lengthen_Double_Big_Endian<"2", "i64", "i16", "4", "i32", "2", "i64", "16">;
|
|
}
|
|
|
|
// Triple lengthening - v2i8 -> v2i16 -> v2i32 -> v2i64
|
|
let Predicates = [IsLE] in {
|
|
def : Pat<(v2i64 (extloadvi8 addrmode6:$addr)),
|
|
(VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
|
|
(VLD1LNd16 addrmode6:$addr,
|
|
(f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
|
|
def : Pat<(v2i64 (zextloadvi8 addrmode6:$addr)),
|
|
(VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
|
|
(VLD1LNd16 addrmode6:$addr,
|
|
(f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
|
|
def : Pat<(v2i64 (sextloadvi8 addrmode6:$addr)),
|
|
(VMOVLsv2i64 (EXTRACT_SUBREG (VMOVLsv4i32 (EXTRACT_SUBREG (VMOVLsv8i16
|
|
(VLD1LNd16 addrmode6:$addr,
|
|
(f64 (IMPLICIT_DEF)), (i32 0))), dsub_0)), dsub_0))>;
|
|
}
|
|
// The following patterns are basically a copy of the patterns above,
|
|
// however with an additional VREV16d instruction to convert data
|
|
// loaded by VLD1LN into proper vector format in big endian mode.
|
|
let Predicates = [IsBE] in {
|
|
def : Pat<(v2i64 (extloadvi8 addrmode6:$addr)),
|
|
(VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
|
|
(!cast<Instruction>("VREV16d8")
|
|
(VLD1LNd16 addrmode6:$addr,
|
|
(f64 (IMPLICIT_DEF)), (i32 0)))), dsub_0)), dsub_0))>;
|
|
def : Pat<(v2i64 (zextloadvi8 addrmode6:$addr)),
|
|
(VMOVLuv2i64 (EXTRACT_SUBREG (VMOVLuv4i32 (EXTRACT_SUBREG (VMOVLuv8i16
|
|
(!cast<Instruction>("VREV16d8")
|
|
(VLD1LNd16 addrmode6:$addr,
|
|
(f64 (IMPLICIT_DEF)), (i32 0)))), dsub_0)), dsub_0))>;
|
|
def : Pat<(v2i64 (sextloadvi8 addrmode6:$addr)),
|
|
(VMOVLsv2i64 (EXTRACT_SUBREG (VMOVLsv4i32 (EXTRACT_SUBREG (VMOVLsv8i16
|
|
(!cast<Instruction>("VREV16d8")
|
|
(VLD1LNd16 addrmode6:$addr,
|
|
(f64 (IMPLICIT_DEF)), (i32 0)))), dsub_0)), dsub_0))>;
|
|
}
|
|
|
|
def : Pat<(v2i64 (concat_vectors DPR:$Dn, DPR:$Dm)),
|
|
(REG_SEQUENCE QPR, DPR:$Dn, dsub_0, DPR:$Dm, dsub_1)>;
|
|
def : Pat<(v4i32 (concat_vectors DPR:$Dn, DPR:$Dm)),
|
|
(REG_SEQUENCE QPR, DPR:$Dn, dsub_0, DPR:$Dm, dsub_1)>;
|
|
def : Pat<(v8i16 (concat_vectors DPR:$Dn, DPR:$Dm)),
|
|
(REG_SEQUENCE QPR, DPR:$Dn, dsub_0, DPR:$Dm, dsub_1)>;
|
|
def : Pat<(v16i8 (concat_vectors DPR:$Dn, DPR:$Dm)),
|
|
(REG_SEQUENCE QPR, DPR:$Dn, dsub_0, DPR:$Dm, dsub_1)>;
|
|
def : Pat<(v4f32 (concat_vectors DPR:$Dn, DPR:$Dm)),
|
|
(REG_SEQUENCE QPR, DPR:$Dn, dsub_0, DPR:$Dm, dsub_1)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Assembler aliases
|
|
//
|
|
|
|
def : VFP2InstAlias<"fmdhr${p} $Dd, $Rn",
|
|
(VSETLNi32 DPR:$Dd, GPR:$Rn, 1, pred:$p)>;
|
|
def : VFP2InstAlias<"fmdlr${p} $Dd, $Rn",
|
|
(VSETLNi32 DPR:$Dd, GPR:$Rn, 0, pred:$p)>;
|
|
|
|
// VAND/VBIC/VEOR/VORR accept but do not require a type suffix.
|
|
defm : NEONDTAnyInstAlias<"vand${p}", "$Vd, $Vn, $Vm",
|
|
(VANDd DPR:$Vd, DPR:$Vn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vand${p}", "$Vd, $Vn, $Vm",
|
|
(VANDq QPR:$Vd, QPR:$Vn, QPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vbic${p}", "$Vd, $Vn, $Vm",
|
|
(VBICd DPR:$Vd, DPR:$Vn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vbic${p}", "$Vd, $Vn, $Vm",
|
|
(VBICq QPR:$Vd, QPR:$Vn, QPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"veor${p}", "$Vd, $Vn, $Vm",
|
|
(VEORd DPR:$Vd, DPR:$Vn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"veor${p}", "$Vd, $Vn, $Vm",
|
|
(VEORq QPR:$Vd, QPR:$Vn, QPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vorr${p}", "$Vd, $Vn, $Vm",
|
|
(VORRd DPR:$Vd, DPR:$Vn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vorr${p}", "$Vd, $Vn, $Vm",
|
|
(VORRq QPR:$Vd, QPR:$Vn, QPR:$Vm, pred:$p)>;
|
|
// ... two-operand aliases
|
|
defm : NEONDTAnyInstAlias<"vand${p}", "$Vdn, $Vm",
|
|
(VANDd DPR:$Vdn, DPR:$Vdn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vand${p}", "$Vdn, $Vm",
|
|
(VANDq QPR:$Vdn, QPR:$Vdn, QPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"veor${p}", "$Vdn, $Vm",
|
|
(VEORd DPR:$Vdn, DPR:$Vdn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"veor${p}", "$Vdn, $Vm",
|
|
(VEORq QPR:$Vdn, QPR:$Vdn, QPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vorr${p}", "$Vdn, $Vm",
|
|
(VORRd DPR:$Vdn, DPR:$Vdn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vorr${p}", "$Vdn, $Vm",
|
|
(VORRq QPR:$Vdn, QPR:$Vdn, QPR:$Vm, pred:$p)>;
|
|
// ... immediates
|
|
def : NEONInstAlias<"vand${p}.i16 $Vd, $imm",
|
|
(VBICiv4i16 DPR:$Vd, nImmSplatNotI16:$imm, pred:$p)>;
|
|
def : NEONInstAlias<"vand${p}.i32 $Vd, $imm",
|
|
(VBICiv2i32 DPR:$Vd, nImmSplatNotI32:$imm, pred:$p)>;
|
|
def : NEONInstAlias<"vand${p}.i16 $Vd, $imm",
|
|
(VBICiv8i16 QPR:$Vd, nImmSplatNotI16:$imm, pred:$p)>;
|
|
def : NEONInstAlias<"vand${p}.i32 $Vd, $imm",
|
|
(VBICiv4i32 QPR:$Vd, nImmSplatNotI32:$imm, pred:$p)>;
|
|
|
|
|
|
// VLD1 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VLD1LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vld1${p}", ".8", "$list, $addr",
|
|
(ins VecListOneDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD1LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vld1${p}", ".16", "$list, $addr",
|
|
(ins VecListOneDHWordIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VLD1LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vld1${p}", ".32", "$list, $addr",
|
|
(ins VecListOneDWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
|
|
def VLD1LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld1${p}", ".8", "$list, $addr!",
|
|
(ins VecListOneDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD1LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld1${p}", ".16", "$list, $addr!",
|
|
(ins VecListOneDHWordIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VLD1LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld1${p}", ".32", "$list, $addr!",
|
|
(ins VecListOneDWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VLD1LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld1${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListOneDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD1LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld1${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListOneDHWordIndexed:$list, addrmode6align16:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD1LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld1${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListOneDWordIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
|
|
// VST1 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VST1LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vst1${p}", ".8", "$list, $addr",
|
|
(ins VecListOneDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST1LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vst1${p}", ".16", "$list, $addr",
|
|
(ins VecListOneDHWordIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VST1LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vst1${p}", ".32", "$list, $addr",
|
|
(ins VecListOneDWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
|
|
def VST1LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst1${p}", ".8", "$list, $addr!",
|
|
(ins VecListOneDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST1LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst1${p}", ".16", "$list, $addr!",
|
|
(ins VecListOneDHWordIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VST1LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst1${p}", ".32", "$list, $addr!",
|
|
(ins VecListOneDWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VST1LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst1${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListOneDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST1LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst1${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListOneDHWordIndexed:$list, addrmode6align16:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST1LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst1${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListOneDWordIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
// VLD2 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VLD2LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vld2${p}", ".8", "$list, $addr",
|
|
(ins VecListTwoDByteIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vld2${p}", ".16", "$list, $addr",
|
|
(ins VecListTwoDHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vld2${p}", ".32", "$list, $addr",
|
|
(ins VecListTwoDWordIndexed:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD2LNqAsm_16 : NEONDataTypeAsmPseudoInst<"vld2${p}", ".16", "$list, $addr",
|
|
(ins VecListTwoQHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNqAsm_32 : NEONDataTypeAsmPseudoInst<"vld2${p}", ".32", "$list, $addr",
|
|
(ins VecListTwoQWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
|
|
def VLD2LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".8", "$list, $addr!",
|
|
(ins VecListTwoDByteIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".16", "$list, $addr!",
|
|
(ins VecListTwoDHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".32", "$list, $addr!",
|
|
(ins VecListTwoDWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".16", "$list, $addr!",
|
|
(ins VecListTwoQHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".32", "$list, $addr!",
|
|
(ins VecListTwoQWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VLD2LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListTwoDByteIndexed:$list, addrmode6align16:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD2LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListTwoDHWordIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD2LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListTwoDWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD2LNqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListTwoQHWordIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD2LNqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld2${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListTwoQWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
|
|
// VST2 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VST2LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vst2${p}", ".8", "$list, $addr",
|
|
(ins VecListTwoDByteIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VST2LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vst2${p}", ".16", "$list, $addr",
|
|
(ins VecListTwoDHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VST2LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vst2${p}", ".32", "$list, $addr",
|
|
(ins VecListTwoDWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VST2LNqAsm_16 : NEONDataTypeAsmPseudoInst<"vst2${p}", ".16", "$list, $addr",
|
|
(ins VecListTwoQHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VST2LNqAsm_32 : NEONDataTypeAsmPseudoInst<"vst2${p}", ".32", "$list, $addr",
|
|
(ins VecListTwoQWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
|
|
def VST2LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".8", "$list, $addr!",
|
|
(ins VecListTwoDByteIndexed:$list, addrmode6align16:$addr,
|
|
pred:$p)>;
|
|
def VST2LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".16", "$list, $addr!",
|
|
(ins VecListTwoDHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VST2LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".32", "$list, $addr!",
|
|
(ins VecListTwoDWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VST2LNqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".16", "$list, $addr!",
|
|
(ins VecListTwoQHWordIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VST2LNqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".32", "$list, $addr!",
|
|
(ins VecListTwoQWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VST2LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListTwoDByteIndexed:$list, addrmode6align16:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST2LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".16","$list, $addr, $Rm",
|
|
(ins VecListTwoDHWordIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST2LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListTwoDWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST2LNqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".16","$list, $addr, $Rm",
|
|
(ins VecListTwoQHWordIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST2LNqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst2${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListTwoQWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
// VLD3 all-lanes pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VLD3DUPdAsm_8 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPdAsm_16: NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPdAsm_32: NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPqAsm_8 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPqAsm_16: NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPqAsm_32: NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
|
|
def VLD3DUPdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPqWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3DUPdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3DUPdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3DUPdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeDAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3DUPqWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3DUPqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3DUPqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeQAllLanes:$list, addrmode6dupalignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
|
|
// VLD3 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VLD3LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeDHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeDWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNqAsm_16 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeQHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNqAsm_32 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeQWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
|
|
def VLD3LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeDHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeDWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeQHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeQWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VLD3LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeDHWordIndexed:$list,
|
|
addrmode6alignNone:$addr, rGPR:$Rm, pred:$p)>;
|
|
def VLD3LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeDWordIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3LNqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeQHWordIndexed:$list,
|
|
addrmode6alignNone:$addr, rGPR:$Rm, pred:$p)>;
|
|
def VLD3LNqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeQWordIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
// VLD3 multiple structure pseudo-instructions. These need special handling for
|
|
// the vector operands that the normal instructions don't yet model.
|
|
// FIXME: Remove these when the register classes and instructions are updated.
|
|
def VLD3dAsm_8 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3dAsm_16 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3dAsm_32 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3qAsm_8 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3qAsm_16 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3qAsm_32 : NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
|
|
def VLD3dWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3dWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3dWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3qWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3qWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3qWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VLD3dWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3dWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3dWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3qWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3qWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD3qWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
// VST3 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VST3LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeDHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeDWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNqAsm_16 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeQHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNqAsm_32 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeQWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
|
|
def VST3LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeDHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeDWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeQHWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeQWordIndexed:$list, addrmode6alignNone:$addr,
|
|
pred:$p)>;
|
|
def VST3LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeDByteIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST3LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeDHWordIndexed:$list,
|
|
addrmode6alignNone:$addr, rGPR:$Rm, pred:$p)>;
|
|
def VST3LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeDWordIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST3LNqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeQHWordIndexed:$list,
|
|
addrmode6alignNone:$addr, rGPR:$Rm, pred:$p)>;
|
|
def VST3LNqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeQWordIndexed:$list, addrmode6alignNone:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
|
|
// VST3 multiple structure pseudo-instructions. These need special handling for
|
|
// the vector operands that the normal instructions don't yet model.
|
|
// FIXME: Remove these when the register classes and instructions are updated.
|
|
def VST3dAsm_8 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3dAsm_16 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3dAsm_32 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3qAsm_8 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3qAsm_16 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3qAsm_32 : NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
|
|
def VST3dWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3dWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3dWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3qWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr!",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3qWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr!",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3qWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr!",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr, pred:$p)>;
|
|
def VST3dWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST3dWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST3dWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeD:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST3qWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST3qWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST3qWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst3${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListThreeQ:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
// VLD4 all-lanes pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VLD4DUPdAsm_8 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign32:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPdAsm_16: NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign64:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPdAsm_32: NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign64or128:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPqAsm_8 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign32:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPqAsm_16: NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign64:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPqAsm_32: NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign64or128:$addr,
|
|
pred:$p)>;
|
|
|
|
def VLD4DUPdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign32:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign64:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign64or128:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPqWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign32:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign64:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign64or128:$addr,
|
|
pred:$p)>;
|
|
def VLD4DUPdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4DUPdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourDAllLanes:$list, addrmode6dupalign64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4DUPdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourDAllLanes:$list,
|
|
addrmode6dupalign64or128:$addr, rGPR:$Rm, pred:$p)>;
|
|
def VLD4DUPqWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4DUPqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourQAllLanes:$list, addrmode6dupalign64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4DUPqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourQAllLanes:$list,
|
|
addrmode6dupalign64or128:$addr, rGPR:$Rm, pred:$p)>;
|
|
|
|
|
|
// VLD4 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VLD4LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourDByteIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourDHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourDWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNqAsm_16 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourQHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNqAsm_32 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourQWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
|
|
def VLD4LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourDByteIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourDHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourDWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourQHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourQWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
def VLD4LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourDByteIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourDHWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourDWordIndexed:$list,
|
|
addrmode6align64or128:$addr, rGPR:$Rm, pred:$p)>;
|
|
def VLD4LNqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourQHWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4LNqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourQWordIndexed:$list,
|
|
addrmode6align64or128:$addr, rGPR:$Rm, pred:$p)>;
|
|
|
|
|
|
|
|
// VLD4 multiple structure pseudo-instructions. These need special handling for
|
|
// the vector operands that the normal instructions don't yet model.
|
|
// FIXME: Remove these when the register classes and instructions are updated.
|
|
def VLD4dAsm_8 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4dAsm_16 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4dAsm_32 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4qAsm_8 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4qAsm_16 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4qAsm_32 : NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
|
|
def VLD4dWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4dWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4dWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4qWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4qWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4qWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VLD4dWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4dWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4dWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4qWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4qWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VLD4qWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vld4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
// VST4 single-lane pseudo-instructions. These need special handling for
|
|
// the lane index that an InstAlias can't handle, so we use these instead.
|
|
def VST4LNdAsm_8 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourDByteIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VST4LNdAsm_16 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourDHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VST4LNdAsm_32 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourDWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
def VST4LNqAsm_16 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourQHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VST4LNqAsm_32 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourQWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
|
|
def VST4LNdWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourDByteIndexed:$list, addrmode6align32:$addr,
|
|
pred:$p)>;
|
|
def VST4LNdWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourDHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VST4LNdWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourDWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
def VST4LNqWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourQHWordIndexed:$list, addrmode6align64:$addr,
|
|
pred:$p)>;
|
|
def VST4LNqWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourQWordIndexed:$list, addrmode6align64or128:$addr,
|
|
pred:$p)>;
|
|
def VST4LNdWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourDByteIndexed:$list, addrmode6align32:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4LNdWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourDHWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4LNdWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourDWordIndexed:$list,
|
|
addrmode6align64or128:$addr, rGPR:$Rm, pred:$p)>;
|
|
def VST4LNqWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourQHWordIndexed:$list, addrmode6align64:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4LNqWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourQWordIndexed:$list,
|
|
addrmode6align64or128:$addr, rGPR:$Rm, pred:$p)>;
|
|
|
|
|
|
// VST4 multiple structure pseudo-instructions. These need special handling for
|
|
// the vector operands that the normal instructions don't yet model.
|
|
// FIXME: Remove these when the register classes and instructions are updated.
|
|
def VST4dAsm_8 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4dAsm_16 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4dAsm_32 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4qAsm_8 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4qAsm_16 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4qAsm_32 : NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
|
|
def VST4dWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4dWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4dWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4qWB_fixed_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr!",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4qWB_fixed_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr!",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4qWB_fixed_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr!",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
pred:$p)>;
|
|
def VST4dWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4dWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4dWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourD:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4qWB_register_Asm_8 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".8", "$list, $addr, $Rm",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4qWB_register_Asm_16 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".16", "$list, $addr, $Rm",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
def VST4qWB_register_Asm_32 :
|
|
NEONDataTypeAsmPseudoInst<"vst4${p}", ".32", "$list, $addr, $Rm",
|
|
(ins VecListFourQ:$list, addrmode6align64or128or256:$addr,
|
|
rGPR:$Rm, pred:$p)>;
|
|
|
|
// VMOV/VMVN takes an optional datatype suffix
|
|
defm : NEONDTAnyInstAlias<"vmov${p}", "$Vd, $Vm",
|
|
(VORRd DPR:$Vd, DPR:$Vm, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vmov${p}", "$Vd, $Vm",
|
|
(VORRq QPR:$Vd, QPR:$Vm, QPR:$Vm, pred:$p)>;
|
|
|
|
defm : NEONDTAnyInstAlias<"vmvn${p}", "$Vd, $Vm",
|
|
(VMVNd DPR:$Vd, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vmvn${p}", "$Vd, $Vm",
|
|
(VMVNq QPR:$Vd, QPR:$Vm, pred:$p)>;
|
|
|
|
// VCLT (register) is an assembler alias for VCGT w/ the operands reversed.
|
|
// D-register versions.
|
|
def : NEONInstAlias<"vcle${p}.s8 $Dd, $Dn, $Dm",
|
|
(VCGEsv8i8 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.s16 $Dd, $Dn, $Dm",
|
|
(VCGEsv4i16 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.s32 $Dd, $Dn, $Dm",
|
|
(VCGEsv2i32 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.u8 $Dd, $Dn, $Dm",
|
|
(VCGEuv8i8 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.u16 $Dd, $Dn, $Dm",
|
|
(VCGEuv4i16 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.u32 $Dd, $Dn, $Dm",
|
|
(VCGEuv2i32 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.f32 $Dd, $Dn, $Dm",
|
|
(VCGEfd DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
let Predicates = [HasNEON, HasFullFP16] in
|
|
def : NEONInstAlias<"vcle${p}.f16 $Dd, $Dn, $Dm",
|
|
(VCGEhd DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
// Q-register versions.
|
|
def : NEONInstAlias<"vcle${p}.s8 $Qd, $Qn, $Qm",
|
|
(VCGEsv16i8 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.s16 $Qd, $Qn, $Qm",
|
|
(VCGEsv8i16 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.s32 $Qd, $Qn, $Qm",
|
|
(VCGEsv4i32 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.u8 $Qd, $Qn, $Qm",
|
|
(VCGEuv16i8 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.u16 $Qd, $Qn, $Qm",
|
|
(VCGEuv8i16 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.u32 $Qd, $Qn, $Qm",
|
|
(VCGEuv4i32 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vcle${p}.f32 $Qd, $Qn, $Qm",
|
|
(VCGEfq QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
let Predicates = [HasNEON, HasFullFP16] in
|
|
def : NEONInstAlias<"vcle${p}.f16 $Qd, $Qn, $Qm",
|
|
(VCGEhq QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
|
|
// VCLT (register) is an assembler alias for VCGT w/ the operands reversed.
|
|
// D-register versions.
|
|
def : NEONInstAlias<"vclt${p}.s8 $Dd, $Dn, $Dm",
|
|
(VCGTsv8i8 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.s16 $Dd, $Dn, $Dm",
|
|
(VCGTsv4i16 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.s32 $Dd, $Dn, $Dm",
|
|
(VCGTsv2i32 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.u8 $Dd, $Dn, $Dm",
|
|
(VCGTuv8i8 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.u16 $Dd, $Dn, $Dm",
|
|
(VCGTuv4i16 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.u32 $Dd, $Dn, $Dm",
|
|
(VCGTuv2i32 DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.f32 $Dd, $Dn, $Dm",
|
|
(VCGTfd DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
let Predicates = [HasNEON, HasFullFP16] in
|
|
def : NEONInstAlias<"vclt${p}.f16 $Dd, $Dn, $Dm",
|
|
(VCGThd DPR:$Dd, DPR:$Dm, DPR:$Dn, pred:$p)>;
|
|
// Q-register versions.
|
|
def : NEONInstAlias<"vclt${p}.s8 $Qd, $Qn, $Qm",
|
|
(VCGTsv16i8 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.s16 $Qd, $Qn, $Qm",
|
|
(VCGTsv8i16 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.s32 $Qd, $Qn, $Qm",
|
|
(VCGTsv4i32 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.u8 $Qd, $Qn, $Qm",
|
|
(VCGTuv16i8 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.u16 $Qd, $Qn, $Qm",
|
|
(VCGTuv8i16 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.u32 $Qd, $Qn, $Qm",
|
|
(VCGTuv4i32 QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
def : NEONInstAlias<"vclt${p}.f32 $Qd, $Qn, $Qm",
|
|
(VCGTfq QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
let Predicates = [HasNEON, HasFullFP16] in
|
|
def : NEONInstAlias<"vclt${p}.f16 $Qd, $Qn, $Qm",
|
|
(VCGThq QPR:$Qd, QPR:$Qm, QPR:$Qn, pred:$p)>;
|
|
|
|
// VSWP allows, but does not require, a type suffix.
|
|
defm : NEONDTAnyInstAlias<"vswp${p}", "$Vd, $Vm",
|
|
(VSWPd DPR:$Vd, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vswp${p}", "$Vd, $Vm",
|
|
(VSWPq QPR:$Vd, QPR:$Vm, pred:$p)>;
|
|
|
|
// VBIF, VBIT, and VBSL allow, but do not require, a type suffix.
|
|
defm : NEONDTAnyInstAlias<"vbif${p}", "$Vd, $Vn, $Vm",
|
|
(VBIFd DPR:$Vd, DPR:$Vn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vbit${p}", "$Vd, $Vn, $Vm",
|
|
(VBITd DPR:$Vd, DPR:$Vn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vbsl${p}", "$Vd, $Vn, $Vm",
|
|
(VBSLd DPR:$Vd, DPR:$Vn, DPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vbif${p}", "$Vd, $Vn, $Vm",
|
|
(VBIFq QPR:$Vd, QPR:$Vn, QPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vbit${p}", "$Vd, $Vn, $Vm",
|
|
(VBITq QPR:$Vd, QPR:$Vn, QPR:$Vm, pred:$p)>;
|
|
defm : NEONDTAnyInstAlias<"vbsl${p}", "$Vd, $Vn, $Vm",
|
|
(VBSLq QPR:$Vd, QPR:$Vn, QPR:$Vm, pred:$p)>;
|
|
|
|
// "vmov Rd, #-imm" can be handled via "vmvn".
|
|
def : NEONInstAlias<"vmov${p}.i32 $Vd, $imm",
|
|
(VMVNv2i32 DPR:$Vd, nImmVMOVI32Neg:$imm, pred:$p)>;
|
|
def : NEONInstAlias<"vmov${p}.i32 $Vd, $imm",
|
|
(VMVNv4i32 QPR:$Vd, nImmVMOVI32Neg:$imm, pred:$p)>;
|
|
def : NEONInstAlias<"vmvn${p}.i32 $Vd, $imm",
|
|
(VMOVv2i32 DPR:$Vd, nImmVMOVI32Neg:$imm, pred:$p)>;
|
|
def : NEONInstAlias<"vmvn${p}.i32 $Vd, $imm",
|
|
(VMOVv4i32 QPR:$Vd, nImmVMOVI32Neg:$imm, pred:$p)>;
|
|
|
|
// 'gas' compatibility aliases for quad-word instructions. Strictly speaking,
|
|
// these should restrict to just the Q register variants, but the register
|
|
// classes are enough to match correctly regardless, so we keep it simple
|
|
// and just use MnemonicAlias.
|
|
def : NEONMnemonicAlias<"vbicq", "vbic">;
|
|
def : NEONMnemonicAlias<"vandq", "vand">;
|
|
def : NEONMnemonicAlias<"veorq", "veor">;
|
|
def : NEONMnemonicAlias<"vorrq", "vorr">;
|
|
|
|
def : NEONMnemonicAlias<"vmovq", "vmov">;
|
|
def : NEONMnemonicAlias<"vmvnq", "vmvn">;
|
|
// Explicit versions for floating point so that the FPImm variants get
|
|
// handled early. The parser gets confused otherwise.
|
|
def : NEONMnemonicAlias<"vmovq.f32", "vmov.f32">;
|
|
def : NEONMnemonicAlias<"vmovq.f64", "vmov.f64">;
|
|
|
|
def : NEONMnemonicAlias<"vaddq", "vadd">;
|
|
def : NEONMnemonicAlias<"vsubq", "vsub">;
|
|
|
|
def : NEONMnemonicAlias<"vminq", "vmin">;
|
|
def : NEONMnemonicAlias<"vmaxq", "vmax">;
|
|
|
|
def : NEONMnemonicAlias<"vmulq", "vmul">;
|
|
|
|
def : NEONMnemonicAlias<"vabsq", "vabs">;
|
|
|
|
def : NEONMnemonicAlias<"vshlq", "vshl">;
|
|
def : NEONMnemonicAlias<"vshrq", "vshr">;
|
|
|
|
def : NEONMnemonicAlias<"vcvtq", "vcvt">;
|
|
|
|
def : NEONMnemonicAlias<"vcleq", "vcle">;
|
|
def : NEONMnemonicAlias<"vceqq", "vceq">;
|
|
|
|
def : NEONMnemonicAlias<"vzipq", "vzip">;
|
|
def : NEONMnemonicAlias<"vswpq", "vswp">;
|
|
|
|
def : NEONMnemonicAlias<"vrecpeq.f32", "vrecpe.f32">;
|
|
def : NEONMnemonicAlias<"vrecpeq.u32", "vrecpe.u32">;
|
|
|
|
|
|
// Alias for loading floating point immediates that aren't representable
|
|
// using the vmov.f32 encoding but the bitpattern is representable using
|
|
// the .i32 encoding.
|
|
def : NEONInstAlias<"vmov${p}.f32 $Vd, $imm",
|
|
(VMOVv4i32 QPR:$Vd, nImmVMOVI32:$imm, pred:$p)>;
|
|
def : NEONInstAlias<"vmov${p}.f32 $Vd, $imm",
|
|
(VMOVv2i32 DPR:$Vd, nImmVMOVI32:$imm, pred:$p)>;
|