blob: 9d1bfa414dff71cc80429920adc037e51fe0c1d4 [file] [log] [blame]
//===-- ARMInstrVFP.td - VFP support for ARM ---------------*- tablegen -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file describes the ARM VFP instruction set.
//
//===----------------------------------------------------------------------===//
def SDT_CMPFP0 : SDTypeProfile<0, 1, [SDTCisFP<0>]>;
def SDT_VMOVDRR : SDTypeProfile<1, 2, [SDTCisVT<0, f64>, SDTCisVT<1, i32>,
SDTCisSameAs<1, 2>]>;
def SDT_VMOVRRD : SDTypeProfile<2, 1, [SDTCisVT<0, i32>, SDTCisSameAs<0, 1>,
SDTCisVT<2, f64>]>;
def SDT_VMOVSR : SDTypeProfile<1, 1, [SDTCisVT<0, f32>, SDTCisVT<1, i32>]>;
def arm_fmstat : SDNode<"ARMISD::FMSTAT", SDTNone, [SDNPInGlue, SDNPOutGlue]>;
def arm_cmpfp : SDNode<"ARMISD::CMPFP", SDT_ARMCmp, [SDNPOutGlue]>;
def arm_cmpfp0 : SDNode<"ARMISD::CMPFPw0", SDT_CMPFP0, [SDNPOutGlue]>;
def arm_cmpfpe : SDNode<"ARMISD::CMPFPE", SDT_ARMCmp, [SDNPOutGlue]>;
def arm_cmpfpe0: SDNode<"ARMISD::CMPFPEw0",SDT_CMPFP0, [SDNPOutGlue]>;
def arm_fmdrr : SDNode<"ARMISD::VMOVDRR", SDT_VMOVDRR>;
def arm_fmrrd : SDNode<"ARMISD::VMOVRRD", SDT_VMOVRRD>;
def arm_vmovsr : SDNode<"ARMISD::VMOVSR", SDT_VMOVSR>;
def SDT_VMOVhr : SDTypeProfile<1, 1, [SDTCisFP<0>, SDTCisVT<1, i32>] >;
def SDT_VMOVrh : SDTypeProfile<1, 1, [SDTCisVT<0, i32>, SDTCisFP<1>] >;
def arm_vmovhr : SDNode<"ARMISD::VMOVhr", SDT_VMOVhr>;
def arm_vmovrh : SDNode<"ARMISD::VMOVrh", SDT_VMOVrh>;
//===----------------------------------------------------------------------===//
// Operand Definitions.
//
// 8-bit floating-point immediate encodings.
def FPImmOperand : AsmOperandClass {
let Name = "FPImm";
let ParserMethod = "parseFPImm";
}
def vfp_f16imm : Operand<f16>,
PatLeaf<(f16 fpimm), [{
return ARM_AM::getFP16Imm(N->getValueAPF()) != -1;
}], SDNodeXForm<fpimm, [{
APFloat InVal = N->getValueAPF();
uint32_t enc = ARM_AM::getFP16Imm(InVal);
return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i32);
}]>> {
let PrintMethod = "printFPImmOperand";
let ParserMatchClass = FPImmOperand;
}
def vfp_f32f16imm_xform : SDNodeXForm<fpimm, [{
APFloat InVal = N->getValueAPF();
uint32_t enc = ARM_AM::getFP32FP16Imm(InVal);
return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i32);
}]>;
def vfp_f32f16imm : PatLeaf<(f32 fpimm), [{
return ARM_AM::getFP32FP16Imm(N->getValueAPF()) != -1;
}], vfp_f32f16imm_xform>;
def vfp_f32imm_xform : SDNodeXForm<fpimm, [{
APFloat InVal = N->getValueAPF();
uint32_t enc = ARM_AM::getFP32Imm(InVal);
return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i32);
}]>;
def gi_vfp_f32imm : GICustomOperandRenderer<"renderVFPF32Imm">,
GISDNodeXFormEquiv<vfp_f32imm_xform>;
def vfp_f32imm : Operand<f32>,
PatLeaf<(f32 fpimm), [{
return ARM_AM::getFP32Imm(N->getValueAPF()) != -1;
}], vfp_f32imm_xform> {
let PrintMethod = "printFPImmOperand";
let ParserMatchClass = FPImmOperand;
let GISelPredicateCode = [{
const auto &MO = MI.getOperand(1);
if (!MO.isFPImm())
return false;
return ARM_AM::getFP32Imm(MO.getFPImm()->getValueAPF()) != -1;
}];
}
def vfp_f64imm_xform : SDNodeXForm<fpimm, [{
APFloat InVal = N->getValueAPF();
uint32_t enc = ARM_AM::getFP64Imm(InVal);
return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i32);
}]>;
def gi_vfp_f64imm : GICustomOperandRenderer<"renderVFPF64Imm">,
GISDNodeXFormEquiv<vfp_f64imm_xform>;
def vfp_f64imm : Operand<f64>,
PatLeaf<(f64 fpimm), [{
return ARM_AM::getFP64Imm(N->getValueAPF()) != -1;
}], vfp_f64imm_xform> {
let PrintMethod = "printFPImmOperand";
let ParserMatchClass = FPImmOperand;
let GISelPredicateCode = [{
const auto &MO = MI.getOperand(1);
if (!MO.isFPImm())
return false;
return ARM_AM::getFP64Imm(MO.getFPImm()->getValueAPF()) != -1;
}];
}
def alignedload16 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
return cast<LoadSDNode>(N)->getAlignment() >= 2;
}]>;
def alignedload32 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
return cast<LoadSDNode>(N)->getAlignment() >= 4;
}]>;
def alignedstore16 : PatFrag<(ops node:$val, node:$ptr),
(store node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->getAlignment() >= 2;
}]>;
def alignedstore32 : PatFrag<(ops node:$val, node:$ptr),
(store node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->getAlignment() >= 4;
}]>;
// The VCVT to/from fixed-point instructions encode the 'fbits' operand
// (the number of fixed bits) differently than it appears in the assembly
// source. It's encoded as "Size - fbits" where Size is the size of the
// fixed-point representation (32 or 16) and fbits is the value appearing
// in the assembly source, an integer in [0,16] or (0,32], depending on size.
def fbits32_asm_operand : AsmOperandClass { let Name = "FBits32"; }
def fbits32 : Operand<i32> {
let PrintMethod = "printFBits32";
let ParserMatchClass = fbits32_asm_operand;
}
def fbits16_asm_operand : AsmOperandClass { let Name = "FBits16"; }
def fbits16 : Operand<i32> {
let PrintMethod = "printFBits16";
let ParserMatchClass = fbits16_asm_operand;
}
//===----------------------------------------------------------------------===//
// Load / store Instructions.
//
let canFoldAsLoad = 1, isReMaterializable = 1 in {
def VLDRD : ADI5<0b1101, 0b01, (outs DPR:$Dd), (ins addrmode5:$addr),
IIC_fpLoad64, "vldr", "\t$Dd, $addr",
[(set DPR:$Dd, (f64 (alignedload32 addrmode5:$addr)))]>,
Requires<[HasFPRegs]>;
def VLDRS : ASI5<0b1101, 0b01, (outs SPR:$Sd), (ins addrmode5:$addr),
IIC_fpLoad32, "vldr", "\t$Sd, $addr",
[(set SPR:$Sd, (alignedload32 addrmode5:$addr))]>,
Requires<[HasFPRegs]> {
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
}
let isUnpredicable = 1 in
def VLDRH : AHI5<0b1101, 0b01, (outs HPR:$Sd), (ins addrmode5fp16:$addr),
IIC_fpLoad16, "vldr", ".16\t$Sd, $addr",
[(set HPR:$Sd, (f16 (alignedload16 addrmode5fp16:$addr)))]>,
Requires<[HasFPRegs16]>;
} // End of 'let canFoldAsLoad = 1, isReMaterializable = 1 in'
def : Pat<(bf16 (alignedload16 addrmode5fp16:$addr)),
(VLDRH addrmode5fp16:$addr)> {
let Predicates = [HasFPRegs16];
}
def : Pat<(bf16 (alignedload16 addrmode3:$addr)),
(COPY_TO_REGCLASS (LDRH addrmode3:$addr), HPR)> {
let Predicates = [HasNoFPRegs16, IsARM];
}
def : Pat<(bf16 (alignedload16 t2addrmode_imm12:$addr)),
(COPY_TO_REGCLASS (t2LDRHi12 t2addrmode_imm12:$addr), HPR)> {
let Predicates = [HasNoFPRegs16, IsThumb];
}
def VSTRD : ADI5<0b1101, 0b00, (outs), (ins DPR:$Dd, addrmode5:$addr),
IIC_fpStore64, "vstr", "\t$Dd, $addr",
[(alignedstore32 (f64 DPR:$Dd), addrmode5:$addr)]>,
Requires<[HasFPRegs]>;
def VSTRS : ASI5<0b1101, 0b00, (outs), (ins SPR:$Sd, addrmode5:$addr),
IIC_fpStore32, "vstr", "\t$Sd, $addr",
[(alignedstore32 SPR:$Sd, addrmode5:$addr)]>,
Requires<[HasFPRegs]> {
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
}
let isUnpredicable = 1 in
def VSTRH : AHI5<0b1101, 0b00, (outs), (ins HPR:$Sd, addrmode5fp16:$addr),
IIC_fpStore16, "vstr", ".16\t$Sd, $addr",
[(alignedstore16 (f16 HPR:$Sd), addrmode5fp16:$addr)]>,
Requires<[HasFPRegs16]>;
def : Pat<(alignedstore16 (bf16 HPR:$Sd), addrmode5fp16:$addr),
(VSTRH (bf16 HPR:$Sd), addrmode5fp16:$addr)> {
let Predicates = [HasFPRegs16];
}
def : Pat<(alignedstore16 (bf16 HPR:$Sd), addrmode3:$addr),
(STRH (COPY_TO_REGCLASS $Sd, GPR), addrmode3:$addr)> {
let Predicates = [HasNoFPRegs16, IsARM];
}
def : Pat<(alignedstore16 (bf16 HPR:$Sd), t2addrmode_imm12:$addr),
(t2STRHi12 (COPY_TO_REGCLASS $Sd, GPR), t2addrmode_imm12:$addr)> {
let Predicates = [HasNoFPRegs16, IsThumb];
}
//===----------------------------------------------------------------------===//
// Load / store multiple Instructions.
//
multiclass vfp_ldst_mult<string asm, bit L_bit,
InstrItinClass itin, InstrItinClass itin_upd> {
let Predicates = [HasFPRegs] in {
// Double Precision
def DIA :
AXDI4<(outs), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
IndexModeNone, itin,
!strconcat(asm, "ia${p}\t$Rn, $regs"), "", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 0; // No writeback
let Inst{20} = L_bit;
}
def DIA_UPD :
AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs,
variable_ops),
IndexModeUpd, itin_upd,
!strconcat(asm, "ia${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
}
def DDB_UPD :
AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs,
variable_ops),
IndexModeUpd, itin_upd,
!strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b10; // Decrement Before
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
}
// Single Precision
def SIA :
AXSI4<(outs), (ins GPR:$Rn, pred:$p, spr_reglist:$regs, variable_ops),
IndexModeNone, itin,
!strconcat(asm, "ia${p}\t$Rn, $regs"), "", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 0; // No writeback
let Inst{20} = L_bit;
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines.
let D = VFPNeonDomain;
}
def SIA_UPD :
AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs,
variable_ops),
IndexModeUpd, itin_upd,
!strconcat(asm, "ia${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines.
let D = VFPNeonDomain;
}
def SDB_UPD :
AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs,
variable_ops),
IndexModeUpd, itin_upd,
!strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b10; // Decrement Before
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines.
let D = VFPNeonDomain;
}
}
}
let hasSideEffects = 0 in {
let mayLoad = 1, hasExtraDefRegAllocReq = 1 in
defm VLDM : vfp_ldst_mult<"vldm", 1, IIC_fpLoad_m, IIC_fpLoad_mu>;
let mayStore = 1, hasExtraSrcRegAllocReq = 1 in
defm VSTM : vfp_ldst_mult<"vstm", 0, IIC_fpStore_m, IIC_fpStore_mu>;
} // hasSideEffects
def : MnemonicAlias<"vldm", "vldmia">;
def : MnemonicAlias<"vstm", "vstmia">;
//===----------------------------------------------------------------------===//
// Lazy load / store multiple Instructions
//
def VLLDM : AXSI4<(outs), (ins GPRnopc:$Rn, pred:$p), IndexModeNone,
NoItinerary, "vlldm${p}\t$Rn", "", []>,
Requires<[HasV8MMainline, Has8MSecExt]> {
let Inst{24-23} = 0b00;
let Inst{22} = 0;
let Inst{21} = 1;
let Inst{20} = 1;
let Inst{15-12} = 0;
let Inst{7-0} = 0;
let mayLoad = 1;
let Defs = [Q0, Q1, Q2, Q3, Q4, Q5, Q6, Q7, VPR, FPSCR, FPSCR_NZCV];
}
def VLSTM : AXSI4<(outs), (ins GPRnopc:$Rn, pred:$p), IndexModeNone,
NoItinerary, "vlstm${p}\t$Rn", "", []>,
Requires<[HasV8MMainline, Has8MSecExt]> {
let Inst{24-23} = 0b00;
let Inst{22} = 0;
let Inst{21} = 1;
let Inst{20} = 0;
let Inst{15-12} = 0;
let Inst{7-0} = 0;
let mayStore = 1;
}
def : InstAlias<"vpush${p} $r", (VSTMDDB_UPD SP, pred:$p, dpr_reglist:$r), 0>,
Requires<[HasFPRegs]>;
def : InstAlias<"vpush${p} $r", (VSTMSDB_UPD SP, pred:$p, spr_reglist:$r), 0>,
Requires<[HasFPRegs]>;
def : InstAlias<"vpop${p} $r", (VLDMDIA_UPD SP, pred:$p, dpr_reglist:$r), 0>,
Requires<[HasFPRegs]>;
def : InstAlias<"vpop${p} $r", (VLDMSIA_UPD SP, pred:$p, spr_reglist:$r), 0>,
Requires<[HasFPRegs]>;
defm : VFPDTAnyInstAlias<"vpush${p}", "$r",
(VSTMSDB_UPD SP, pred:$p, spr_reglist:$r)>;
defm : VFPDTAnyInstAlias<"vpush${p}", "$r",
(VSTMDDB_UPD SP, pred:$p, dpr_reglist:$r)>;
defm : VFPDTAnyInstAlias<"vpop${p}", "$r",
(VLDMSIA_UPD SP, pred:$p, spr_reglist:$r)>;
defm : VFPDTAnyInstAlias<"vpop${p}", "$r",
(VLDMDIA_UPD SP, pred:$p, dpr_reglist:$r)>;
// FLDMX, FSTMX - Load and store multiple unknown precision registers for
// pre-armv6 cores.
// These instruction are deprecated so we don't want them to get selected.
// However, there is no UAL syntax for them, so we keep them around for
// (dis)assembly only.
multiclass vfp_ldstx_mult<string asm, bit L_bit> {
let Predicates = [HasFPRegs], hasNoSchedulingInfo = 1 in {
// Unknown precision
def XIA :
AXXI4<(outs), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
IndexModeNone, !strconcat(asm, "iax${p}\t$Rn, $regs"), "", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 0; // No writeback
let Inst{20} = L_bit;
}
def XIA_UPD :
AXXI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
IndexModeUpd, !strconcat(asm, "iax${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
}
def XDB_UPD :
AXXI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
IndexModeUpd, !strconcat(asm, "dbx${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b10; // Decrement Before
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
}
}
}
defm FLDM : vfp_ldstx_mult<"fldm", 1>;
defm FSTM : vfp_ldstx_mult<"fstm", 0>;
def : VFP2MnemonicAlias<"fldmeax", "fldmdbx">;
def : VFP2MnemonicAlias<"fldmfdx", "fldmiax">;
def : VFP2MnemonicAlias<"fstmeax", "fstmiax">;
def : VFP2MnemonicAlias<"fstmfdx", "fstmdbx">;
//===----------------------------------------------------------------------===//
// FP Binary Operations.
//
let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VADDD : ADbI<0b11100, 0b11, 0, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
IIC_fpALU64, "vadd", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fadd DPR:$Dn, (f64 DPR:$Dm)))]>,
Sched<[WriteFPALU64]>;
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VADDS : ASbIn<0b11100, 0b11, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
IIC_fpALU32, "vadd", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fadd SPR:$Sn, SPR:$Sm))]>,
Sched<[WriteFPALU32]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VADDH : AHbI<0b11100, 0b11, 0, 0,
(outs HPR:$Sd), (ins HPR:$Sn, HPR:$Sm),
IIC_fpALU16, "vadd", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fadd (f16 HPR:$Sn), (f16 HPR:$Sm)))]>,
Sched<[WriteFPALU32]>;
let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VSUBD : ADbI<0b11100, 0b11, 1, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
IIC_fpALU64, "vsub", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fsub DPR:$Dn, (f64 DPR:$Dm)))]>,
Sched<[WriteFPALU64]>;
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VSUBS : ASbIn<0b11100, 0b11, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
IIC_fpALU32, "vsub", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fsub SPR:$Sn, SPR:$Sm))]>,
Sched<[WriteFPALU32]>{
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VSUBH : AHbI<0b11100, 0b11, 1, 0,
(outs HPR:$Sd), (ins HPR:$Sn, HPR:$Sm),
IIC_fpALU16, "vsub", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fsub (f16 HPR:$Sn), (f16 HPR:$Sm)))]>,
Sched<[WriteFPALU32]>;
let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VDIVD : ADbI<0b11101, 0b00, 0, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
IIC_fpDIV64, "vdiv", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fdiv DPR:$Dn, (f64 DPR:$Dm)))]>,
Sched<[WriteFPDIV64]>;
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VDIVS : ASbI<0b11101, 0b00, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
IIC_fpDIV32, "vdiv", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fdiv SPR:$Sn, SPR:$Sm))]>,
Sched<[WriteFPDIV32]>;
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VDIVH : AHbI<0b11101, 0b00, 0, 0,
(outs HPR:$Sd), (ins HPR:$Sn, HPR:$Sm),
IIC_fpDIV16, "vdiv", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fdiv (f16 HPR:$Sn), (f16 HPR:$Sm)))]>,
Sched<[WriteFPDIV32]>;
let TwoOperandAliasConstraint = "$Dn = $Dd" in
def VMULD : ADbI<0b11100, 0b10, 0, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
IIC_fpMUL64, "vmul", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fmul DPR:$Dn, (f64 DPR:$Dm)))]>,
Sched<[WriteFPMUL64, ReadFPMUL, ReadFPMUL]>;
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VMULS : ASbIn<0b11100, 0b10, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
IIC_fpMUL32, "vmul", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fmul SPR:$Sn, SPR:$Sm))]>,
Sched<[WriteFPMUL32, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
let TwoOperandAliasConstraint = "$Sn = $Sd" in
def VMULH : AHbI<0b11100, 0b10, 0, 0,
(outs HPR:$Sd), (ins HPR:$Sn, HPR:$Sm),
IIC_fpMUL16, "vmul", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fmul (f16 HPR:$Sn), (f16 HPR:$Sm)))]>,
Sched<[WriteFPMUL32, ReadFPMUL, ReadFPMUL]>;
def VNMULD : ADbI<0b11100, 0b10, 1, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
IIC_fpMUL64, "vnmul", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fneg (fmul DPR:$Dn, (f64 DPR:$Dm))))]>,
Sched<[WriteFPMUL64, ReadFPMUL, ReadFPMUL]>;
def VNMULS : ASbI<0b11100, 0b10, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
IIC_fpMUL32, "vnmul", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fneg (fmul SPR:$Sn, SPR:$Sm)))]>,
Sched<[WriteFPMUL32, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VNMULH : AHbI<0b11100, 0b10, 1, 0,
(outs HPR:$Sd), (ins HPR:$Sn, HPR:$Sm),
IIC_fpMUL16, "vnmul", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fneg (fmul (f16 HPR:$Sn), (f16 HPR:$Sm))))]>,
Sched<[WriteFPMUL32, ReadFPMUL, ReadFPMUL]>;
multiclass vsel_inst<string op, bits<2> opc, int CC> {
let DecoderNamespace = "VFPV8", PostEncoderMethod = "",
Uses = [CPSR], AddedComplexity = 4, isUnpredicable = 1 in {
def H : AHbInp<0b11100, opc, 0,
(outs HPR:$Sd), (ins HPR:$Sn, HPR:$Sm),
NoItinerary, !strconcat("vsel", op, ".f16\t$Sd, $Sn, $Sm"),
[(set (f16 HPR:$Sd), (ARMcmov (f16 HPR:$Sm), (f16 HPR:$Sn), CC))]>,
Requires<[HasFullFP16]>;
def S : ASbInp<0b11100, opc, 0,
(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
NoItinerary, !strconcat("vsel", op, ".f32\t$Sd, $Sn, $Sm"),
[(set SPR:$Sd, (ARMcmov SPR:$Sm, SPR:$Sn, CC))]>,
Requires<[HasFPARMv8]>;
def D : ADbInp<0b11100, opc, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
NoItinerary, !strconcat("vsel", op, ".f64\t$Dd, $Dn, $Dm"),
[(set DPR:$Dd, (ARMcmov (f64 DPR:$Dm), (f64 DPR:$Dn), CC))]>,
Requires<[HasFPARMv8, HasDPVFP]>;
}
}
// The CC constants here match ARMCC::CondCodes.
defm VSELGT : vsel_inst<"gt", 0b11, 12>;
defm VSELGE : vsel_inst<"ge", 0b10, 10>;
defm VSELEQ : vsel_inst<"eq", 0b00, 0>;
defm VSELVS : vsel_inst<"vs", 0b01, 6>;
multiclass vmaxmin_inst<string op, bit opc, SDNode SD> {
let DecoderNamespace = "VFPV8", PostEncoderMethod = "",
isUnpredicable = 1 in {
def H : AHbInp<0b11101, 0b00, opc,
(outs HPR:$Sd), (ins HPR:$Sn, HPR:$Sm),
NoItinerary, !strconcat(op, ".f16\t$Sd, $Sn, $Sm"),
[(set (f16 HPR:$Sd), (SD (f16 HPR:$Sn), (f16 HPR:$Sm)))]>,
Requires<[HasFullFP16]>;
def S : ASbInp<0b11101, 0b00, opc,
(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm),
NoItinerary, !strconcat(op, ".f32\t$Sd, $Sn, $Sm"),
[(set SPR:$Sd, (SD SPR:$Sn, SPR:$Sm))]>,
Requires<[HasFPARMv8]>;
def D : ADbInp<0b11101, 0b00, opc,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
NoItinerary, !strconcat(op, ".f64\t$Dd, $Dn, $Dm"),
[(set DPR:$Dd, (f64 (SD (f64 DPR:$Dn), (f64 DPR:$Dm))))]>,
Requires<[HasFPARMv8, HasDPVFP]>;
}
}
defm VFP_VMAXNM : vmaxmin_inst<"vmaxnm", 0, fmaxnum>;
defm VFP_VMINNM : vmaxmin_inst<"vminnm", 1, fminnum>;
// Match reassociated forms only if not sign dependent rounding.
def : Pat<(fmul (fneg DPR:$a), (f64 DPR:$b)),
(VNMULD DPR:$a, DPR:$b)>,
Requires<[NoHonorSignDependentRounding,HasDPVFP]>;
def : Pat<(fmul (fneg SPR:$a), SPR:$b),
(VNMULS SPR:$a, SPR:$b)>, Requires<[NoHonorSignDependentRounding]>;
// These are encoded as unary instructions.
let Defs = [FPSCR_NZCV] in {
def VCMPED : ADuI<0b11101, 0b11, 0b0100, 0b11, 0,
(outs), (ins DPR:$Dd, DPR:$Dm),
IIC_fpCMP64, "vcmpe", ".f64\t$Dd, $Dm",
[(arm_cmpfpe DPR:$Dd, (f64 DPR:$Dm))]>;
def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0,
(outs), (ins SPR:$Sd, SPR:$Sm),
IIC_fpCMP32, "vcmpe", ".f32\t$Sd, $Sm",
[(arm_cmpfpe SPR:$Sd, SPR:$Sm)]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VCMPEH : AHuI<0b11101, 0b11, 0b0100, 0b11, 0,
(outs), (ins HPR:$Sd, HPR:$Sm),
IIC_fpCMP16, "vcmpe", ".f16\t$Sd, $Sm",
[(arm_cmpfpe (f16 HPR:$Sd), (f16 HPR:$Sm))]>;
def VCMPD : ADuI<0b11101, 0b11, 0b0100, 0b01, 0,
(outs), (ins DPR:$Dd, DPR:$Dm),
IIC_fpCMP64, "vcmp", ".f64\t$Dd, $Dm",
[(arm_cmpfp DPR:$Dd, (f64 DPR:$Dm))]>;
def VCMPS : ASuI<0b11101, 0b11, 0b0100, 0b01, 0,
(outs), (ins SPR:$Sd, SPR:$Sm),
IIC_fpCMP32, "vcmp", ".f32\t$Sd, $Sm",
[(arm_cmpfp SPR:$Sd, SPR:$Sm)]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VCMPH : AHuI<0b11101, 0b11, 0b0100, 0b01, 0,
(outs), (ins HPR:$Sd, HPR:$Sm),
IIC_fpCMP16, "vcmp", ".f16\t$Sd, $Sm",
[(arm_cmpfp (f16 HPR:$Sd), (f16 HPR:$Sm))]>;
} // Defs = [FPSCR_NZCV]
//===----------------------------------------------------------------------===//
// FP Unary Operations.
//
def VABSD : ADuI<0b11101, 0b11, 0b0000, 0b11, 0,
(outs DPR:$Dd), (ins DPR:$Dm),
IIC_fpUNA64, "vabs", ".f64\t$Dd, $Dm",
[(set DPR:$Dd, (fabs (f64 DPR:$Dm)))]>;
def VABSS : ASuIn<0b11101, 0b11, 0b0000, 0b11, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpUNA32, "vabs", ".f32\t$Sd, $Sm",
[(set SPR:$Sd, (fabs SPR:$Sm))]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VABSH : AHuI<0b11101, 0b11, 0b0000, 0b11, 0,
(outs HPR:$Sd), (ins HPR:$Sm),
IIC_fpUNA16, "vabs", ".f16\t$Sd, $Sm",
[(set (f16 HPR:$Sd), (fabs (f16 HPR:$Sm)))]>;
let Defs = [FPSCR_NZCV] in {
def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0,
(outs), (ins DPR:$Dd),
IIC_fpCMP64, "vcmpe", ".f64\t$Dd, #0",
[(arm_cmpfpe0 (f64 DPR:$Dd))]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
}
def VCMPEZS : ASuI<0b11101, 0b11, 0b0101, 0b11, 0,
(outs), (ins SPR:$Sd),
IIC_fpCMP32, "vcmpe", ".f32\t$Sd, #0",
[(arm_cmpfpe0 SPR:$Sd)]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VCMPEZH : AHuI<0b11101, 0b11, 0b0101, 0b11, 0,
(outs), (ins HPR:$Sd),
IIC_fpCMP16, "vcmpe", ".f16\t$Sd, #0",
[(arm_cmpfpe0 (f16 HPR:$Sd))]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
}
def VCMPZD : ADuI<0b11101, 0b11, 0b0101, 0b01, 0,
(outs), (ins DPR:$Dd),
IIC_fpCMP64, "vcmp", ".f64\t$Dd, #0",
[(arm_cmpfp0 (f64 DPR:$Dd))]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
}
def VCMPZS : ASuI<0b11101, 0b11, 0b0101, 0b01, 0,
(outs), (ins SPR:$Sd),
IIC_fpCMP32, "vcmp", ".f32\t$Sd, #0",
[(arm_cmpfp0 SPR:$Sd)]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VCMPZH : AHuI<0b11101, 0b11, 0b0101, 0b01, 0,
(outs), (ins HPR:$Sd),
IIC_fpCMP16, "vcmp", ".f16\t$Sd, #0",
[(arm_cmpfp0 (f16 HPR:$Sd))]> {
let Inst{3-0} = 0b0000;
let Inst{5} = 0;
}
} // Defs = [FPSCR_NZCV]
def VCVTDS : ASuI<0b11101, 0b11, 0b0111, 0b11, 0,
(outs DPR:$Dd), (ins SPR:$Sm),
IIC_fpCVTDS, "vcvt", ".f64.f32\t$Dd, $Sm",
[(set DPR:$Dd, (fpextend SPR:$Sm))]>,
Sched<[WriteFPCVT]> {
// Instruction operands.
bits<5> Dd;
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let Inst{15-12} = Dd{3-0};
let Inst{22} = Dd{4};
let Predicates = [HasVFP2, HasDPVFP];
let hasSideEffects = 0;
}
// Special case encoding: bits 11-8 is 0b1011.
def VCVTSD : VFPAI<(outs SPR:$Sd), (ins DPR:$Dm), VFPUnaryFrm,
IIC_fpCVTSD, "vcvt", ".f32.f64\t$Sd, $Dm",
[(set SPR:$Sd, (fpround DPR:$Dm))]>,
Sched<[WriteFPCVT]> {
// Instruction operands.
bits<5> Sd;
bits<5> Dm;
// Encode instruction operands.
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let Inst{27-23} = 0b11101;
let Inst{21-16} = 0b110111;
let Inst{11-8} = 0b1011;
let Inst{7-6} = 0b11;
let Inst{4} = 0;
let Predicates = [HasVFP2, HasDPVFP];
let hasSideEffects = 0;
}
// Between half, single and double-precision.
let hasSideEffects = 0 in
def VCVTBHS: ASuI<0b11101, 0b11, 0b0010, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm),
/* FIXME */ IIC_fpCVTSH, "vcvtb", ".f32.f16\t$Sd, $Sm",
[/* Intentionally left blank, see patterns below */]>,
Requires<[HasFP16]>,
Sched<[WriteFPCVT]>;
def : FP16Pat<(f32 (fpextend (f16 HPR:$Sm))),
(VCVTBHS (COPY_TO_REGCLASS (f16 HPR:$Sm), SPR))>;
def : FP16Pat<(f16_to_fp GPR:$a),
(VCVTBHS (COPY_TO_REGCLASS GPR:$a, SPR))>;
let hasSideEffects = 0 in
def VCVTBSH: ASuI<0b11101, 0b11, 0b0011, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm),
/* FIXME */ IIC_fpCVTHS, "vcvtb", ".f16.f32\t$Sd, $Sm",
[/* Intentionally left blank, see patterns below */]>,
Requires<[HasFP16]>,
Sched<[WriteFPCVT]>;
def : FP16Pat<(f16 (fpround SPR:$Sm)),
(COPY_TO_REGCLASS (VCVTBSH SPR:$Sm), HPR)>;
def : FP16Pat<(fp_to_f16 SPR:$a),
(i32 (COPY_TO_REGCLASS (VCVTBSH SPR:$a), GPR))>;
def : FP16Pat<(insertelt (v8f16 MQPR:$src1), (f16 (fpround (f32 SPR:$src2))), imm_even:$lane),
(v8f16 (INSERT_SUBREG (v8f16 MQPR:$src1), (VCVTBSH SPR:$src2),
(SSubReg_f16_reg imm:$lane)))>;
def : FP16Pat<(insertelt (v4f16 DPR:$src1), (f16 (fpround (f32 SPR:$src2))), imm_even:$lane),
(v4f16 (INSERT_SUBREG (v4f16 DPR:$src1), (VCVTBSH SPR:$src2),
(SSubReg_f16_reg imm:$lane)))>;
let hasSideEffects = 0 in
def VCVTTHS: ASuI<0b11101, 0b11, 0b0010, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
/* FIXME */ IIC_fpCVTSH, "vcvtt", ".f32.f16\t$Sd, $Sm",
[/* Intentionally left blank, see patterns below */]>,
Requires<[HasFP16]>,
Sched<[WriteFPCVT]>;
def : FP16Pat<(f32 (fpextend (extractelt (v8f16 MQPR:$src), imm_odd:$lane))),
(VCVTTHS (EXTRACT_SUBREG MQPR:$src, (SSubReg_f16_reg imm_odd:$lane)))>;
def : FP16Pat<(f32 (fpextend (extractelt (v4f16 DPR:$src), imm_odd:$lane))),
(VCVTTHS (EXTRACT_SUBREG
(v2f32 (COPY_TO_REGCLASS (v4f16 DPR:$src), DPR_VFP2)),
(SSubReg_f16_reg imm_odd:$lane)))>;
let hasSideEffects = 0 in
def VCVTTSH: ASuI<0b11101, 0b11, 0b0011, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
/* FIXME */ IIC_fpCVTHS, "vcvtt", ".f16.f32\t$Sd, $Sm",
[/* Intentionally left blank, see patterns below */]>,
Requires<[HasFP16]>,
Sched<[WriteFPCVT]>;
def : FP16Pat<(insertelt (v8f16 MQPR:$src1), (f16 (fpround (f32 SPR:$src2))), imm_odd:$lane),
(v8f16 (INSERT_SUBREG (v8f16 MQPR:$src1), (VCVTTSH SPR:$src2),
(SSubReg_f16_reg imm:$lane)))>;
def : FP16Pat<(insertelt (v4f16 DPR:$src1), (f16 (fpround (f32 SPR:$src2))), imm_odd:$lane),
(v4f16 (INSERT_SUBREG (v4f16 DPR:$src1), (VCVTTSH SPR:$src2),
(SSubReg_f16_reg imm:$lane)))>;
def VCVTBHD : ADuI<0b11101, 0b11, 0b0010, 0b01, 0,
(outs DPR:$Dd), (ins SPR:$Sm),
NoItinerary, "vcvtb", ".f64.f16\t$Dd, $Sm",
[/* Intentionally left blank, see patterns below */]>,
Requires<[HasFPARMv8, HasDPVFP]>,
Sched<[WriteFPCVT]> {
// Instruction operands.
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let hasSideEffects = 0;
}
def : FullFP16Pat<(f64 (fpextend (f16 HPR:$Sm))),
(VCVTBHD (COPY_TO_REGCLASS (f16 HPR:$Sm), SPR))>,
Requires<[HasFPARMv8, HasDPVFP]>;
def : FP16Pat<(f64 (f16_to_fp GPR:$a)),
(VCVTBHD (COPY_TO_REGCLASS GPR:$a, SPR))>,
Requires<[HasFPARMv8, HasDPVFP]>;
def VCVTBDH : ADuI<0b11101, 0b11, 0b0011, 0b01, 0,
(outs SPR:$Sd), (ins DPR:$Dm),
NoItinerary, "vcvtb", ".f16.f64\t$Sd, $Dm",
[/* Intentionally left blank, see patterns below */]>,
Requires<[HasFPARMv8, HasDPVFP]> {
// Instruction operands.
bits<5> Sd;
bits<5> Dm;
// Encode instruction operands.
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let hasSideEffects = 0;
}
def : FullFP16Pat<(f16 (fpround DPR:$Dm)),
(COPY_TO_REGCLASS (VCVTBDH DPR:$Dm), HPR)>,
Requires<[HasFPARMv8, HasDPVFP]>;
def : FP16Pat<(fp_to_f16 (f64 DPR:$a)),
(i32 (COPY_TO_REGCLASS (VCVTBDH DPR:$a), GPR))>,
Requires<[HasFPARMv8, HasDPVFP]>;
def VCVTTHD : ADuI<0b11101, 0b11, 0b0010, 0b11, 0,
(outs DPR:$Dd), (ins SPR:$Sm),
NoItinerary, "vcvtt", ".f64.f16\t$Dd, $Sm",
[]>, Requires<[HasFPARMv8, HasDPVFP]> {
// Instruction operands.
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let hasSideEffects = 0;
}
def VCVTTDH : ADuI<0b11101, 0b11, 0b0011, 0b11, 0,
(outs SPR:$Sd), (ins DPR:$Dm),
NoItinerary, "vcvtt", ".f16.f64\t$Sd, $Dm",
[]>, Requires<[HasFPARMv8, HasDPVFP]> {
// Instruction operands.
bits<5> Sd;
bits<5> Dm;
// Encode instruction operands.
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let hasSideEffects = 0;
}
multiclass vcvt_inst<string opc, bits<2> rm,
SDPatternOperator node = null_frag> {
let PostEncoderMethod = "", DecoderNamespace = "VFPV8", hasSideEffects = 0 in {
def SH : AHuInp<0b11101, 0b11, 0b1100, 0b11, 0,
(outs SPR:$Sd), (ins HPR:$Sm),
NoItinerary, !strconcat("vcvt", opc, ".s32.f16\t$Sd, $Sm"),
[]>,
Requires<[HasFullFP16]> {
let Inst{17-16} = rm;
}
def UH : AHuInp<0b11101, 0b11, 0b1100, 0b01, 0,
(outs SPR:$Sd), (ins HPR:$Sm),
NoItinerary, !strconcat("vcvt", opc, ".u32.f16\t$Sd, $Sm"),
[]>,
Requires<[HasFullFP16]> {
let Inst{17-16} = rm;
}
def SS : ASuInp<0b11101, 0b11, 0b1100, 0b11, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
NoItinerary, !strconcat("vcvt", opc, ".s32.f32\t$Sd, $Sm"),
[]>,
Requires<[HasFPARMv8]> {
let Inst{17-16} = rm;
}
def US : ASuInp<0b11101, 0b11, 0b1100, 0b01, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
NoItinerary, !strconcat("vcvt", opc, ".u32.f32\t$Sd, $Sm"),
[]>,
Requires<[HasFPARMv8]> {
let Inst{17-16} = rm;
}
def SD : ASuInp<0b11101, 0b11, 0b1100, 0b11, 0,
(outs SPR:$Sd), (ins DPR:$Dm),
NoItinerary, !strconcat("vcvt", opc, ".s32.f64\t$Sd, $Dm"),
[]>,
Requires<[HasFPARMv8, HasDPVFP]> {
bits<5> Dm;
let Inst{17-16} = rm;
// Encode instruction operands.
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let Inst{8} = 1;
}
def UD : ASuInp<0b11101, 0b11, 0b1100, 0b01, 0,
(outs SPR:$Sd), (ins DPR:$Dm),
NoItinerary, !strconcat("vcvt", opc, ".u32.f64\t$Sd, $Dm"),
[]>,
Requires<[HasFPARMv8, HasDPVFP]> {
bits<5> Dm;
let Inst{17-16} = rm;
// Encode instruction operands
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let Inst{8} = 1;
}
}
let Predicates = [HasFPARMv8] in {
let Predicates = [HasFullFP16] in {
def : Pat<(i32 (fp_to_sint (node (f16 HPR:$a)))),
(COPY_TO_REGCLASS
(!cast<Instruction>(NAME#"SH") (f16 HPR:$a)),
GPR)>;
def : Pat<(i32 (fp_to_uint (node (f16 HPR:$a)))),
(COPY_TO_REGCLASS
(!cast<Instruction>(NAME#"UH") (f16 HPR:$a)),
GPR)>;
}
def : Pat<(i32 (fp_to_sint (node SPR:$a))),
(COPY_TO_REGCLASS
(!cast<Instruction>(NAME#"SS") SPR:$a),
GPR)>;
def : Pat<(i32 (fp_to_uint (node SPR:$a))),
(COPY_TO_REGCLASS
(!cast<Instruction>(NAME#"US") SPR:$a),
GPR)>;
}
let Predicates = [HasFPARMv8, HasDPVFP] in {
def : Pat<(i32 (fp_to_sint (node (f64 DPR:$a)))),
(COPY_TO_REGCLASS
(!cast<Instruction>(NAME#"SD") DPR:$a),
GPR)>;
def : Pat<(i32 (fp_to_uint (node (f64 DPR:$a)))),
(COPY_TO_REGCLASS
(!cast<Instruction>(NAME#"UD") DPR:$a),
GPR)>;
}
}
defm VCVTA : vcvt_inst<"a", 0b00, fround>;
defm VCVTN : vcvt_inst<"n", 0b01>;
defm VCVTP : vcvt_inst<"p", 0b10, fceil>;
defm VCVTM : vcvt_inst<"m", 0b11, ffloor>;
def VNEGD : ADuI<0b11101, 0b11, 0b0001, 0b01, 0,
(outs DPR:$Dd), (ins DPR:$Dm),
IIC_fpUNA64, "vneg", ".f64\t$Dd, $Dm",
[(set DPR:$Dd, (fneg (f64 DPR:$Dm)))]>;
def VNEGS : ASuIn<0b11101, 0b11, 0b0001, 0b01, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpUNA32, "vneg", ".f32\t$Sd, $Sm",
[(set SPR:$Sd, (fneg SPR:$Sm))]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VNEGH : AHuI<0b11101, 0b11, 0b0001, 0b01, 0,
(outs HPR:$Sd), (ins HPR:$Sm),
IIC_fpUNA16, "vneg", ".f16\t$Sd, $Sm",
[(set (f16 HPR:$Sd), (fneg (f16 HPR:$Sm)))]>;
multiclass vrint_inst_zrx<string opc, bit op, bit op2, SDPatternOperator node> {
def H : AHuI<0b11101, 0b11, 0b0110, 0b11, 0,
(outs HPR:$Sd), (ins HPR:$Sm),
NoItinerary, !strconcat("vrint", opc), ".f16\t$Sd, $Sm",
[(set (f16 HPR:$Sd), (node (f16 HPR:$Sm)))]>,
Requires<[HasFullFP16]> {
let Inst{7} = op2;
let Inst{16} = op;
}
def S : ASuI<0b11101, 0b11, 0b0110, 0b11, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
NoItinerary, !strconcat("vrint", opc), ".f32\t$Sd, $Sm",
[(set (f32 SPR:$Sd), (node (f32 SPR:$Sm)))]>,
Requires<[HasFPARMv8]> {
let Inst{7} = op2;
let Inst{16} = op;
}
def D : ADuI<0b11101, 0b11, 0b0110, 0b11, 0,
(outs DPR:$Dd), (ins DPR:$Dm),
NoItinerary, !strconcat("vrint", opc), ".f64\t$Dd, $Dm",
[(set (f64 DPR:$Dd), (node (f64 DPR:$Dm)))]>,
Requires<[HasFPARMv8, HasDPVFP]> {
let Inst{7} = op2;
let Inst{16} = op;
}
def : InstAlias<!strconcat("vrint", opc, "$p.f16.f16\t$Sd, $Sm"),
(!cast<Instruction>(NAME#"H") SPR:$Sd, SPR:$Sm, pred:$p), 0>,
Requires<[HasFullFP16]>;
def : InstAlias<!strconcat("vrint", opc, "$p.f32.f32\t$Sd, $Sm"),
(!cast<Instruction>(NAME#"S") SPR:$Sd, SPR:$Sm, pred:$p), 0>,
Requires<[HasFPARMv8]>;
def : InstAlias<!strconcat("vrint", opc, "$p.f64.f64\t$Dd, $Dm"),
(!cast<Instruction>(NAME#"D") DPR:$Dd, DPR:$Dm, pred:$p), 0>,
Requires<[HasFPARMv8,HasDPVFP]>;
}
defm VRINTZ : vrint_inst_zrx<"z", 0, 1, ftrunc>;
defm VRINTR : vrint_inst_zrx<"r", 0, 0, fnearbyint>;
defm VRINTX : vrint_inst_zrx<"x", 1, 0, frint>;
multiclass vrint_inst_anpm<string opc, bits<2> rm,
SDPatternOperator node = null_frag> {
let PostEncoderMethod = "", DecoderNamespace = "VFPV8",
isUnpredicable = 1 in {
def H : AHuInp<0b11101, 0b11, 0b1000, 0b01, 0,
(outs HPR:$Sd), (ins HPR:$Sm),
NoItinerary, !strconcat("vrint", opc, ".f16\t$Sd, $Sm"),
[(set (f16 HPR:$Sd), (node (f16 HPR:$Sm)))]>,
Requires<[HasFullFP16]> {
let Inst{17-16} = rm;
}
def S : ASuInp<0b11101, 0b11, 0b1000, 0b01, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
NoItinerary, !strconcat("vrint", opc, ".f32\t$Sd, $Sm"),
[(set (f32 SPR:$Sd), (node (f32 SPR:$Sm)))]>,
Requires<[HasFPARMv8]> {
let Inst{17-16} = rm;
}
def D : ADuInp<0b11101, 0b11, 0b1000, 0b01, 0,
(outs DPR:$Dd), (ins DPR:$Dm),
NoItinerary, !strconcat("vrint", opc, ".f64\t$Dd, $Dm"),
[(set (f64 DPR:$Dd), (node (f64 DPR:$Dm)))]>,
Requires<[HasFPARMv8, HasDPVFP]> {
let Inst{17-16} = rm;
}
}
def : InstAlias<!strconcat("vrint", opc, ".f32.f32\t$Sd, $Sm"),
(!cast<Instruction>(NAME#"S") SPR:$Sd, SPR:$Sm), 0>,
Requires<[HasFPARMv8]>;
def : InstAlias<!strconcat("vrint", opc, ".f64.f64\t$Dd, $Dm"),
(!cast<Instruction>(NAME#"D") DPR:$Dd, DPR:$Dm), 0>,
Requires<[HasFPARMv8,HasDPVFP]>;
}
defm VRINTA : vrint_inst_anpm<"a", 0b00, fround>;
defm VRINTN : vrint_inst_anpm<"n", 0b01, int_arm_neon_vrintn>;
defm VRINTP : vrint_inst_anpm<"p", 0b10, fceil>;
defm VRINTM : vrint_inst_anpm<"m", 0b11, ffloor>;
def VSQRTD : ADuI<0b11101, 0b11, 0b0001, 0b11, 0,
(outs DPR:$Dd), (ins DPR:$Dm),
IIC_fpSQRT64, "vsqrt", ".f64\t$Dd, $Dm",
[(set DPR:$Dd, (fsqrt (f64 DPR:$Dm)))]>,
Sched<[WriteFPSQRT64]>;
def VSQRTS : ASuI<0b11101, 0b11, 0b0001, 0b11, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpSQRT32, "vsqrt", ".f32\t$Sd, $Sm",
[(set SPR:$Sd, (fsqrt SPR:$Sm))]>,
Sched<[WriteFPSQRT32]>;
def VSQRTH : AHuI<0b11101, 0b11, 0b0001, 0b11, 0,
(outs HPR:$Sd), (ins HPR:$Sm),
IIC_fpSQRT16, "vsqrt", ".f16\t$Sd, $Sm",
[(set (f16 HPR:$Sd), (fsqrt (f16 HPR:$Sm)))]>;
let hasSideEffects = 0 in {
let isMoveReg = 1 in {
def VMOVD : ADuI<0b11101, 0b11, 0b0000, 0b01, 0,
(outs DPR:$Dd), (ins DPR:$Dm),
IIC_fpUNA64, "vmov", ".f64\t$Dd, $Dm", []>,
Requires<[HasFPRegs64]>;
def VMOVS : ASuI<0b11101, 0b11, 0b0000, 0b01, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpUNA32, "vmov", ".f32\t$Sd, $Sm", []>,
Requires<[HasFPRegs]>;
} // isMoveReg
let PostEncoderMethod = "", DecoderNamespace = "VFPV8", isUnpredicable = 1 in {
def VMOVH : ASuInp<0b11101, 0b11, 0b0000, 0b01, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpUNA16, "vmovx.f16\t$Sd, $Sm", []>,
Requires<[HasFullFP16]>;
def VINSH : ASuInp<0b11101, 0b11, 0b0000, 0b11, 0,
(outs SPR:$Sd), (ins SPR:$Sda, SPR:$Sm),
IIC_fpUNA16, "vins.f16\t$Sd, $Sm", []>,
Requires<[HasFullFP16]> {
let Constraints = "$Sd = $Sda";
}
} // PostEncoderMethod
} // hasSideEffects
//===----------------------------------------------------------------------===//
// FP <-> GPR Copies. Int <-> FP Conversions.
//
let isMoveReg = 1 in {
def VMOVRS : AVConv2I<0b11100001, 0b1010,
(outs GPR:$Rt), (ins SPR:$Sn),
IIC_fpMOVSI, "vmov", "\t$Rt, $Sn",
[(set GPR:$Rt, (bitconvert SPR:$Sn))]>,
Requires<[HasFPRegs]>,
Sched<[WriteFPMOV]> {
// Instruction operands.
bits<4> Rt;
bits<5> Sn;
// Encode instruction operands.
let Inst{19-16} = Sn{4-1};
let Inst{7} = Sn{0};
let Inst{15-12} = Rt;
let Inst{6-5} = 0b00;
let Inst{3-0} = 0b0000;
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
}
// Bitcast i32 -> f32. NEON prefers to use VMOVDRR.
def VMOVSR : AVConv4I<0b11100000, 0b1010,
(outs SPR:$Sn), (ins GPR:$Rt),
IIC_fpMOVIS, "vmov", "\t$Sn, $Rt",
[(set SPR:$Sn, (bitconvert GPR:$Rt))]>,
Requires<[HasFPRegs, UseVMOVSR]>,
Sched<[WriteFPMOV]> {
// Instruction operands.
bits<5> Sn;
bits<4> Rt;
// Encode instruction operands.
let Inst{19-16} = Sn{4-1};
let Inst{7} = Sn{0};
let Inst{15-12} = Rt;
let Inst{6-5} = 0b00;
let Inst{3-0} = 0b0000;
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
}
} // isMoveReg
def : Pat<(arm_vmovsr GPR:$Rt), (VMOVSR GPR:$Rt)>, Requires<[HasVFP2, UseVMOVSR]>;
let hasSideEffects = 0 in {
def VMOVRRD : AVConv3I<0b11000101, 0b1011,
(outs GPR:$Rt, GPR:$Rt2), (ins DPR:$Dm),
IIC_fpMOVDI, "vmov", "\t$Rt, $Rt2, $Dm",
[(set GPR:$Rt, GPR:$Rt2, (arm_fmrrd DPR:$Dm))]>,
Requires<[HasFPRegs]>,
Sched<[WriteFPMOV]> {
// Instruction operands.
bits<5> Dm;
bits<4> Rt;
bits<4> Rt2;
// Encode instruction operands.
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let Inst{15-12} = Rt;
let Inst{19-16} = Rt2;
let Inst{7-6} = 0b00;
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
// This instruction is equivalent to
// $Rt = EXTRACT_SUBREG $Dm, ssub_0
// $Rt2 = EXTRACT_SUBREG $Dm, ssub_1
let isExtractSubreg = 1;
}
def VMOVRRS : AVConv3I<0b11000101, 0b1010,
(outs GPR:$Rt, GPR:$Rt2), (ins SPR:$src1, SPR:$src2),
IIC_fpMOVDI, "vmov", "\t$Rt, $Rt2, $src1, $src2",
[/* For disassembly only; pattern left blank */]>,
Requires<[HasFPRegs]>,
Sched<[WriteFPMOV]> {
bits<5> src1;
bits<4> Rt;
bits<4> Rt2;
// Encode instruction operands.
let Inst{3-0} = src1{4-1};
let Inst{5} = src1{0};
let Inst{15-12} = Rt;
let Inst{19-16} = Rt2;
let Inst{7-6} = 0b00;
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
let DecoderMethod = "DecodeVMOVRRS";
}
} // hasSideEffects
// FMDHR: GPR -> SPR
// FMDLR: GPR -> SPR
def VMOVDRR : AVConv5I<0b11000100, 0b1011,
(outs DPR:$Dm), (ins GPR:$Rt, GPR:$Rt2),
IIC_fpMOVID, "vmov", "\t$Dm, $Rt, $Rt2",
[(set DPR:$Dm, (arm_fmdrr GPR:$Rt, GPR:$Rt2))]>,
Requires<[HasFPRegs]>,
Sched<[WriteFPMOV]> {
// Instruction operands.
bits<5> Dm;
bits<4> Rt;
bits<4> Rt2;
// Encode instruction operands.
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let Inst{15-12} = Rt;
let Inst{19-16} = Rt2;
let Inst{7-6} = 0b00;
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
// This instruction is equivalent to
// $Dm = REG_SEQUENCE $Rt, ssub_0, $Rt2, ssub_1
let isRegSequence = 1;
}
// Hoist an fabs or a fneg of a value coming from integer registers
// and do the fabs/fneg on the integer value. This is never a lose
// and could enable the conversion to float to be removed completely.
def : Pat<(fabs (arm_fmdrr GPR:$Rl, GPR:$Rh)),
(VMOVDRR GPR:$Rl, (BFC GPR:$Rh, (i32 0x7FFFFFFF)))>,
Requires<[IsARM, HasV6T2]>;
def : Pat<(fabs (arm_fmdrr GPR:$Rl, GPR:$Rh)),
(VMOVDRR GPR:$Rl, (t2BFC GPR:$Rh, (i32 0x7FFFFFFF)))>,
Requires<[IsThumb2, HasV6T2]>;
def : Pat<(fneg (arm_fmdrr GPR:$Rl, GPR:$Rh)),
(VMOVDRR GPR:$Rl, (EORri GPR:$Rh, (i32 0x80000000)))>,
Requires<[IsARM]>;
def : Pat<(fneg (arm_fmdrr GPR:$Rl, GPR:$Rh)),
(VMOVDRR GPR:$Rl, (t2EORri GPR:$Rh, (i32 0x80000000)))>,
Requires<[IsThumb2]>;
let hasSideEffects = 0 in
def VMOVSRR : AVConv5I<0b11000100, 0b1010,
(outs SPR:$dst1, SPR:$dst2), (ins GPR:$src1, GPR:$src2),
IIC_fpMOVID, "vmov", "\t$dst1, $dst2, $src1, $src2",
[/* For disassembly only; pattern left blank */]>,
Requires<[HasFPRegs]>,
Sched<[WriteFPMOV]> {
// Instruction operands.
bits<5> dst1;
bits<4> src1;
bits<4> src2;
// Encode instruction operands.
let Inst{3-0} = dst1{4-1};
let Inst{5} = dst1{0};
let Inst{15-12} = src1;
let Inst{19-16} = src2;
let Inst{7-6} = 0b00;
// Some single precision VFP instructions may be executed on both NEON and VFP
// pipelines.
let D = VFPNeonDomain;
let DecoderMethod = "DecodeVMOVSRR";
}
// Move H->R, clearing top 16 bits
def VMOVRH : AVConv2I<0b11100001, 0b1001,
(outs rGPR:$Rt), (ins HPR:$Sn),
IIC_fpMOVSI, "vmov", ".f16\t$Rt, $Sn",
[]>,
Requires<[HasFPRegs16]>,
Sched<[WriteFPMOV]> {
// Instruction operands.
bits<4> Rt;
bits<5> Sn;
// Encode instruction operands.
let Inst{19-16} = Sn{4-1};
let Inst{7} = Sn{0};
let Inst{15-12} = Rt;
let Inst{6-5} = 0b00;
let Inst{3-0} = 0b0000;
let isUnpredicable = 1;
}
// Move R->H, clearing top 16 bits
def VMOVHR : AVConv4I<0b11100000, 0b1001,
(outs HPR:$Sn), (ins rGPR:$Rt),
IIC_fpMOVIS, "vmov", ".f16\t$Sn, $Rt",
[]>,
Requires<[HasFPRegs16]>,
Sched<[WriteFPMOV]> {
// Instruction operands.
bits<5> Sn;
bits<4> Rt;
// Encode instruction operands.
let Inst{19-16} = Sn{4-1};
let Inst{7} = Sn{0};
let Inst{15-12} = Rt;
let Inst{6-5} = 0b00;
let Inst{3-0} = 0b0000;
let isUnpredicable = 1;
}
def : FPRegs16Pat<(arm_vmovrh (f16 HPR:$Sn)), (VMOVRH (f16 HPR:$Sn))>;
def : FPRegs16Pat<(arm_vmovrh (bf16 HPR:$Sn)), (VMOVRH (bf16 HPR:$Sn))>;
def : FPRegs16Pat<(f16 (arm_vmovhr rGPR:$Rt)), (VMOVHR rGPR:$Rt)>;
def : FPRegs16Pat<(bf16 (arm_vmovhr rGPR:$Rt)), (VMOVHR rGPR:$Rt)>;
// FMRDH: SPR -> GPR
// FMRDL: SPR -> GPR
// FMRRS: SPR -> GPR
// FMRX: SPR system reg -> GPR
// FMSRR: GPR -> SPR
// FMXR: GPR -> VFP system reg
// Int -> FP:
class AVConv1IDs_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
bits<4> opcod4, dag oops, dag iops,
InstrItinClass itin, string opc, string asm,
list<dag> pattern>
: AVConv1I<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
pattern> {
// Instruction operands.
bits<5> Dd;
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let Inst{15-12} = Dd{3-0};
let Inst{22} = Dd{4};
let Predicates = [HasVFP2, HasDPVFP];
let hasSideEffects = 0;
}
class AVConv1InSs_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
bits<4> opcod4, dag oops, dag iops,InstrItinClass itin,
string opc, string asm, list<dag> pattern>
: AVConv1In<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
pattern> {
// Instruction operands.
bits<5> Sd;
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let hasSideEffects = 0;
}
class AVConv1IHs_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
bits<4> opcod4, dag oops, dag iops,
InstrItinClass itin, string opc, string asm,
list<dag> pattern>
: AVConv1I<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
pattern> {
// Instruction operands.
bits<5> Sd;
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let Predicates = [HasFullFP16];
let hasSideEffects = 0;
}
def VSITOD : AVConv1IDs_Encode<0b11101, 0b11, 0b1000, 0b1011,
(outs DPR:$Dd), (ins SPR:$Sm),
IIC_fpCVTID, "vcvt", ".f64.s32\t$Dd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // s32
}
let Predicates=[HasVFP2, HasDPVFP] in {
def : VFPPat<(f64 (sint_to_fp GPR:$a)),
(VSITOD (COPY_TO_REGCLASS GPR:$a, SPR))>;
def : VFPPat<(f64 (sint_to_fp (i32 (alignedload32 addrmode5:$a)))),
(VSITOD (VLDRS addrmode5:$a))>;
}
def VSITOS : AVConv1InSs_Encode<0b11101, 0b11, 0b1000, 0b1010,
(outs SPR:$Sd),(ins SPR:$Sm),
IIC_fpCVTIS, "vcvt", ".f32.s32\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // s32
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def : VFPNoNEONPat<(f32 (sint_to_fp GPR:$a)),
(VSITOS (COPY_TO_REGCLASS GPR:$a, SPR))>;
def : VFPNoNEONPat<(f32 (sint_to_fp (i32 (alignedload32 addrmode5:$a)))),
(VSITOS (VLDRS addrmode5:$a))>;
def VSITOH : AVConv1IHs_Encode<0b11101, 0b11, 0b1000, 0b1001,
(outs HPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTIH, "vcvt", ".f16.s32\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // s32
let isUnpredicable = 1;
}
def : VFPNoNEONPat<(f16 (sint_to_fp GPR:$a)),
(VSITOH (COPY_TO_REGCLASS GPR:$a, SPR))>;
def VUITOD : AVConv1IDs_Encode<0b11101, 0b11, 0b1000, 0b1011,
(outs DPR:$Dd), (ins SPR:$Sm),
IIC_fpCVTID, "vcvt", ".f64.u32\t$Dd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // u32
}
let Predicates=[HasVFP2, HasDPVFP] in {
def : VFPPat<(f64 (uint_to_fp GPR:$a)),
(VUITOD (COPY_TO_REGCLASS GPR:$a, SPR))>;
def : VFPPat<(f64 (uint_to_fp (i32 (alignedload32 addrmode5:$a)))),
(VUITOD (VLDRS addrmode5:$a))>;
}
def VUITOS : AVConv1InSs_Encode<0b11101, 0b11, 0b1000, 0b1010,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTIS, "vcvt", ".f32.u32\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // u32
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def : VFPNoNEONPat<(f32 (uint_to_fp GPR:$a)),
(VUITOS (COPY_TO_REGCLASS GPR:$a, SPR))>;
def : VFPNoNEONPat<(f32 (uint_to_fp (i32 (alignedload32 addrmode5:$a)))),
(VUITOS (VLDRS addrmode5:$a))>;
def VUITOH : AVConv1IHs_Encode<0b11101, 0b11, 0b1000, 0b1001,
(outs HPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTIH, "vcvt", ".f16.u32\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // u32
let isUnpredicable = 1;
}
def : VFPNoNEONPat<(f16 (uint_to_fp GPR:$a)),
(VUITOH (COPY_TO_REGCLASS GPR:$a, SPR))>;
// FP -> Int:
class AVConv1IsD_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
bits<4> opcod4, dag oops, dag iops,
InstrItinClass itin, string opc, string asm,
list<dag> pattern>
: AVConv1I<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
pattern> {
// Instruction operands.
bits<5> Sd;
bits<5> Dm;
// Encode instruction operands.
let Inst{3-0} = Dm{3-0};
let Inst{5} = Dm{4};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let Predicates = [HasVFP2, HasDPVFP];
let hasSideEffects = 0;
}
class AVConv1InsS_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
bits<4> opcod4, dag oops, dag iops,
InstrItinClass itin, string opc, string asm,
list<dag> pattern>
: AVConv1In<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
pattern> {
// Instruction operands.
bits<5> Sd;
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let hasSideEffects = 0;
}
class AVConv1IsH_Encode<bits<5> opcod1, bits<2> opcod2, bits<4> opcod3,
bits<4> opcod4, dag oops, dag iops,
InstrItinClass itin, string opc, string asm,
list<dag> pattern>
: AVConv1I<opcod1, opcod2, opcod3, opcod4, oops, iops, itin, opc, asm,
pattern> {
// Instruction operands.
bits<5> Sd;
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let Predicates = [HasFullFP16];
let hasSideEffects = 0;
}
// Always set Z bit in the instruction, i.e. "round towards zero" variants.
def VTOSIZD : AVConv1IsD_Encode<0b11101, 0b11, 0b1101, 0b1011,
(outs SPR:$Sd), (ins DPR:$Dm),
IIC_fpCVTDI, "vcvt", ".s32.f64\t$Sd, $Dm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // Z bit
}
let Predicates=[HasVFP2, HasDPVFP] in {
def : VFPPat<(i32 (fp_to_sint (f64 DPR:$a))),
(COPY_TO_REGCLASS (VTOSIZD DPR:$a), GPR)>;
def : VFPPat<(i32 (fp_to_sint_sat (f64 DPR:$a), i32)),
(COPY_TO_REGCLASS (VTOSIZD DPR:$a), GPR)>;
def : VFPPat<(alignedstore32 (i32 (fp_to_sint (f64 DPR:$a))), addrmode5:$ptr),
(VSTRS (VTOSIZD DPR:$a), addrmode5:$ptr)>;
def : VFPPat<(alignedstore32 (i32 (fp_to_sint_sat (f64 DPR:$a), i32)), addrmode5:$ptr),
(VSTRS (VTOSIZD DPR:$a), addrmode5:$ptr)>;
}
def VTOSIZS : AVConv1InsS_Encode<0b11101, 0b11, 0b1101, 0b1010,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTSI, "vcvt", ".s32.f32\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // Z bit
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def : VFPNoNEONPat<(i32 (fp_to_sint SPR:$a)),
(COPY_TO_REGCLASS (VTOSIZS SPR:$a), GPR)>;
def : VFPPat<(i32 (fp_to_sint_sat SPR:$a, i32)),
(COPY_TO_REGCLASS (VTOSIZS SPR:$a), GPR)>;
def : VFPNoNEONPat<(alignedstore32 (i32 (fp_to_sint (f32 SPR:$a))),
addrmode5:$ptr),
(VSTRS (VTOSIZS SPR:$a), addrmode5:$ptr)>;
def : VFPPat<(alignedstore32 (i32 (fp_to_sint_sat (f32 SPR:$a), i32)),
addrmode5:$ptr),
(VSTRS (VTOSIZS SPR:$a), addrmode5:$ptr)>;
def VTOSIZH : AVConv1IsH_Encode<0b11101, 0b11, 0b1101, 0b1001,
(outs SPR:$Sd), (ins HPR:$Sm),
IIC_fpCVTHI, "vcvt", ".s32.f16\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // Z bit
let isUnpredicable = 1;
}
def : VFPNoNEONPat<(i32 (fp_to_sint (f16 HPR:$a))),
(COPY_TO_REGCLASS (VTOSIZH (f16 HPR:$a)), GPR)>;
def : VFPPat<(i32 (fp_to_sint_sat (f16 HPR:$a), i32)),
(COPY_TO_REGCLASS (VTOSIZH (f16 HPR:$a)), GPR)>;
def VTOUIZD : AVConv1IsD_Encode<0b11101, 0b11, 0b1100, 0b1011,
(outs SPR:$Sd), (ins DPR:$Dm),
IIC_fpCVTDI, "vcvt", ".u32.f64\t$Sd, $Dm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // Z bit
}
let Predicates=[HasVFP2, HasDPVFP] in {
def : VFPPat<(i32 (fp_to_uint (f64 DPR:$a))),
(COPY_TO_REGCLASS (VTOUIZD DPR:$a), GPR)>;
def : VFPPat<(i32 (fp_to_uint_sat (f64 DPR:$a), i32)),
(COPY_TO_REGCLASS (VTOUIZD DPR:$a), GPR)>;
def : VFPPat<(alignedstore32 (i32 (fp_to_uint (f64 DPR:$a))), addrmode5:$ptr),
(VSTRS (VTOUIZD DPR:$a), addrmode5:$ptr)>;
def : VFPPat<(alignedstore32 (i32 (fp_to_uint_sat (f64 DPR:$a), i32)), addrmode5:$ptr),
(VSTRS (VTOUIZD DPR:$a), addrmode5:$ptr)>;
}
def VTOUIZS : AVConv1InsS_Encode<0b11101, 0b11, 0b1100, 0b1010,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTSI, "vcvt", ".u32.f32\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // Z bit
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def : VFPNoNEONPat<(i32 (fp_to_uint SPR:$a)),
(COPY_TO_REGCLASS (VTOUIZS SPR:$a), GPR)>;
def : VFPPat<(i32 (fp_to_uint_sat SPR:$a, i32)),
(COPY_TO_REGCLASS (VTOUIZS SPR:$a), GPR)>;
def : VFPNoNEONPat<(alignedstore32 (i32 (fp_to_uint (f32 SPR:$a))),
addrmode5:$ptr),
(VSTRS (VTOUIZS SPR:$a), addrmode5:$ptr)>;
def : VFPPat<(alignedstore32 (i32 (fp_to_uint_sat (f32 SPR:$a), i32)),
addrmode5:$ptr),
(VSTRS (VTOUIZS SPR:$a), addrmode5:$ptr)>;
def VTOUIZH : AVConv1IsH_Encode<0b11101, 0b11, 0b1100, 0b1001,
(outs SPR:$Sd), (ins HPR:$Sm),
IIC_fpCVTHI, "vcvt", ".u32.f16\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 1; // Z bit
let isUnpredicable = 1;
}
def : VFPNoNEONPat<(i32 (fp_to_uint (f16 HPR:$a))),
(COPY_TO_REGCLASS (VTOUIZH (f16 HPR:$a)), GPR)>;
def : VFPPat<(i32 (fp_to_uint_sat (f16 HPR:$a), i32)),
(COPY_TO_REGCLASS (VTOUIZH (f16 HPR:$a)), GPR)>;
// And the Z bit '0' variants, i.e. use the rounding mode specified by FPSCR.
let Uses = [FPSCR] in {
def VTOSIRD : AVConv1IsD_Encode<0b11101, 0b11, 0b1101, 0b1011,
(outs SPR:$Sd), (ins DPR:$Dm),
IIC_fpCVTDI, "vcvtr", ".s32.f64\t$Sd, $Dm",
[(set SPR:$Sd, (int_arm_vcvtr (f64 DPR:$Dm)))]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // Z bit
}
def VTOSIRS : AVConv1InsS_Encode<0b11101, 0b11, 0b1101, 0b1010,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTSI, "vcvtr", ".s32.f32\t$Sd, $Sm",
[(set SPR:$Sd, (int_arm_vcvtr SPR:$Sm))]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // Z bit
}
def VTOSIRH : AVConv1IsH_Encode<0b11101, 0b11, 0b1101, 0b1001,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTHI, "vcvtr", ".s32.f16\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // Z bit
let isUnpredicable = 1;
}
def VTOUIRD : AVConv1IsD_Encode<0b11101, 0b11, 0b1100, 0b1011,
(outs SPR:$Sd), (ins DPR:$Dm),
IIC_fpCVTDI, "vcvtr", ".u32.f64\t$Sd, $Dm",
[(set SPR:$Sd, (int_arm_vcvtru(f64 DPR:$Dm)))]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // Z bit
}
def VTOUIRS : AVConv1InsS_Encode<0b11101, 0b11, 0b1100, 0b1010,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTSI, "vcvtr", ".u32.f32\t$Sd, $Sm",
[(set SPR:$Sd, (int_arm_vcvtru SPR:$Sm))]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // Z bit
}
def VTOUIRH : AVConv1IsH_Encode<0b11101, 0b11, 0b1100, 0b1001,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpCVTHI, "vcvtr", ".u32.f16\t$Sd, $Sm",
[]>,
Sched<[WriteFPCVT]> {
let Inst{7} = 0; // Z bit
let isUnpredicable = 1;
}
}
// v8.3-a Javascript Convert to Signed fixed-point
def VJCVT : AVConv1IsD_Encode<0b11101, 0b11, 0b1001, 0b1011,
(outs SPR:$Sd), (ins DPR:$Dm),
IIC_fpCVTDI, "vjcvt", ".s32.f64\t$Sd, $Dm",
[]>,
Requires<[HasFPARMv8, HasV8_3a]> {
let Inst{7} = 1; // Z bit
}
// Convert between floating-point and fixed-point
// Data type for fixed-point naming convention:
// S16 (U=0, sx=0) -> SH
// U16 (U=1, sx=0) -> UH
// S32 (U=0, sx=1) -> SL
// U32 (U=1, sx=1) -> UL
let Constraints = "$a = $dst" in {
// FP to Fixed-Point:
// Single Precision register
class AVConv1XInsS_Encode<bits<5> op1, bits<2> op2, bits<4> op3, bits<4> op4,
bit op5, dag oops, dag iops, InstrItinClass itin,
string opc, string asm, list<dag> pattern>
: AVConv1XI<op1, op2, op3, op4, op5, oops, iops, itin, opc, asm, pattern> {
bits<5> dst;
// if dp_operation then UInt(D:Vd) else UInt(Vd:D);
let Inst{22} = dst{0};
let Inst{15-12} = dst{4-1};
let hasSideEffects = 0;
}
// Double Precision register
class AVConv1XInsD_Encode<bits<5> op1, bits<2> op2, bits<4> op3, bits<4> op4,
bit op5, dag oops, dag iops, InstrItinClass itin,
string opc, string asm, list<dag> pattern>
: AVConv1XI<op1, op2, op3, op4, op5, oops, iops, itin, opc, asm, pattern> {
bits<5> dst;
// if dp_operation then UInt(D:Vd) else UInt(Vd:D);
let Inst{22} = dst{4};
let Inst{15-12} = dst{3-0};
let hasSideEffects = 0;
let Predicates = [HasVFP2, HasDPVFP];
}
let isUnpredicable = 1 in {
def VTOSHH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1001, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTHI, "vcvt", ".s16.f16\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
def VTOUHH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1001, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTHI, "vcvt", ".u16.f16\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
def VTOSLH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1001, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTHI, "vcvt", ".s32.f16\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
def VTOULH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1001, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTHI, "vcvt", ".u32.f16\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
} // End of 'let isUnpredicable = 1 in'
def VTOSHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTSI, "vcvt", ".s16.f32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VTOUHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTSI, "vcvt", ".u16.f32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VTOSLS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTSI, "vcvt", ".s32.f32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VTOULS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTSI, "vcvt", ".u32.f32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VTOSHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTDI, "vcvt", ".s16.f64\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
def VTOUHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTDI, "vcvt", ".u16.f64\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
def VTOSLD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTDI, "vcvt", ".s32.f64\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
def VTOULD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTDI, "vcvt", ".u32.f64\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
// Fixed-Point to FP:
let isUnpredicable = 1 in {
def VSHTOH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1001, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTIH, "vcvt", ".f16.s16\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
def VUHTOH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1001, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTIH, "vcvt", ".f16.u16\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
def VSLTOH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1001, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTIH, "vcvt", ".f16.s32\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
def VULTOH : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1001, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTIH, "vcvt", ".f16.u32\t$dst, $a, $fbits", []>,
Requires<[HasFullFP16]>,
Sched<[WriteFPCVT]>;
} // End of 'let isUnpredicable = 1 in'
def VSHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.s16\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VUHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.u16\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VSLTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.s32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VULTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.u32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VSHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTID, "vcvt", ".f64.s16\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
def VUHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTID, "vcvt", ".f64.u16\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
def VSLTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTID, "vcvt", ".f64.s32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
def VULTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTID, "vcvt", ".f64.u32\t$dst, $a, $fbits", []>,
Sched<[WriteFPCVT]>;
} // End of 'let Constraints = "$a = $dst" in'
// BFloat16 - Single precision, unary, predicated
class BF16_VCVT<string opc, bits<2> op7_6>
: VFPAI<(outs SPR:$Sd), (ins SPR:$dst, SPR:$Sm),
VFPUnaryFrm, NoItinerary,
opc, ".bf16.f32\t$Sd, $Sm", []>,
RegConstraint<"$dst = $Sd">,
Requires<[HasBF16]>,
Sched<[]> {
bits<5> Sd;
bits<5> Sm;
// Encode instruction operands.
let Inst{3-0} = Sm{4-1};
let Inst{5} = Sm{0};
let Inst{15-12} = Sd{4-1};
let Inst{22} = Sd{0};
let Inst{27-23} = 0b11101; // opcode1
let Inst{21-20} = 0b11; // opcode2
let Inst{19-16} = 0b0011; // opcode3
let Inst{11-8} = 0b1001;
let Inst{7-6} = op7_6;
let Inst{4} = 0;
let DecoderNamespace = "VFPV8";
let hasSideEffects = 0;
}
def BF16_VCVTB : BF16_VCVT<"vcvtb", 0b01>;
def BF16_VCVTT : BF16_VCVT<"vcvtt", 0b11>;
//===----------------------------------------------------------------------===//
// FP Multiply-Accumulate Operations.
//
def VMLAD : ADbI<0b11100, 0b00, 0, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
IIC_fpMAC64, "vmla", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fadd_mlx (fmul_su DPR:$Dn, DPR:$Dm),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>,
Sched<[WriteFPMAC64, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def VMLAS : ASbIn<0b11100, 0b00, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpMAC32, "vmla", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fadd_mlx (fmul_su SPR:$Sn, SPR:$Sm),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VMLAH : AHbI<0b11100, 0b00, 0, 0,
(outs HPR:$Sd), (ins HPR:$Sdin, HPR:$Sn, HPR:$Sm),
IIC_fpMAC16, "vmla", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fadd_mlx (fmul_su (f16 HPR:$Sn), (f16 HPR:$Sm)),
(f16 HPR:$Sdin)))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasFullFP16,UseFPVMLx]>;
def : Pat<(fadd_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
(VMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>;
def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP2,DontUseNEONForFP, UseFPVMLx]>;
def : Pat<(fadd_mlx HPR:$dstin, (fmul_su (f16 HPR:$a), HPR:$b)),
(VMLAH HPR:$dstin, (f16 HPR:$a), HPR:$b)>,
Requires<[HasFullFP16,DontUseNEONForFP, UseFPVMLx]>;
def VMLSD : ADbI<0b11100, 0b00, 1, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
IIC_fpMAC64, "vmls", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fadd_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>,
Sched<[WriteFPMAC64, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def VMLSS : ASbIn<0b11100, 0b00, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpMAC32, "vmls", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fadd_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VMLSH : AHbI<0b11100, 0b00, 1, 0,
(outs HPR:$Sd), (ins HPR:$Sdin, HPR:$Sn, HPR:$Sm),
IIC_fpMAC16, "vmls", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fadd_mlx (fneg (fmul_su (f16 HPR:$Sn), (f16 HPR:$Sm))),
(f16 HPR:$Sdin)))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasFullFP16,UseFPVMLx]>;
def : Pat<(fsub_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
(VMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>;
def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
def : Pat<(fsub_mlx HPR:$dstin, (fmul_su (f16 HPR:$a), HPR:$b)),
(VMLSH HPR:$dstin, (f16 HPR:$a), HPR:$b)>,
Requires<[HasFullFP16,DontUseNEONForFP,UseFPVMLx]>;
def VNMLAD : ADbI<0b11100, 0b01, 1, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
IIC_fpMAC64, "vnmla", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd,(fsub_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>,
Sched<[WriteFPMAC64, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def VNMLAS : ASbI<0b11100, 0b01, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpMAC32, "vnmla", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fsub_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VNMLAH : AHbI<0b11100, 0b01, 1, 0,
(outs HPR:$Sd), (ins HPR:$Sdin, HPR:$Sn, HPR:$Sm),
IIC_fpMAC16, "vnmla", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fsub_mlx (fneg (fmul_su (f16 HPR:$Sn), (f16 HPR:$Sm))),
(f16 HPR:$Sdin)))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasFullFP16,UseFPVMLx]>;
// (-(a * b) - dst) -> -(dst + (a * b))
def : Pat<(fsub_mlx (fneg (fmul_su DPR:$a, (f64 DPR:$b))), DPR:$dstin),
(VNMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>;
def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin),
(VNMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
def : Pat<(fsub_mlx (fneg (fmul_su (f16 HPR:$a), HPR:$b)), HPR:$dstin),
(VNMLAH HPR:$dstin, (f16 HPR:$a), HPR:$b)>,
Requires<[HasFullFP16,DontUseNEONForFP,UseFPVMLx]>;
// (-dst - (a * b)) -> -(dst + (a * b))
def : Pat<(fsub_mlx (fneg DPR:$dstin), (fmul_su DPR:$a, (f64 DPR:$b))),
(VNMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>;
def : Pat<(fsub_mlx (fneg SPR:$dstin), (fmul_su SPR:$a, SPR:$b)),
(VNMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
def : Pat<(fsub_mlx (fneg HPR:$dstin), (fmul_su (f16 HPR:$a), HPR:$b)),
(VNMLAH HPR:$dstin, (f16 HPR:$a), HPR:$b)>,
Requires<[HasFullFP16,DontUseNEONForFP,UseFPVMLx]>;
def VNMLSD : ADbI<0b11100, 0b01, 0, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
IIC_fpMAC64, "vnmls", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fsub_mlx (fmul_su DPR:$Dn, DPR:$Dm),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>,
Sched<[WriteFPMAC64, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def VNMLSS : ASbI<0b11100, 0b01, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpMAC32, "vnmls", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fsub_mlx (fmul_su SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
def VNMLSH : AHbI<0b11100, 0b01, 0, 0,
(outs HPR:$Sd), (ins HPR:$Sdin, HPR:$Sn, HPR:$Sm),
IIC_fpMAC16, "vnmls", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fsub_mlx (fmul_su (f16 HPR:$Sn), (f16 HPR:$Sm)), (f16 HPR:$Sdin)))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasFullFP16,UseFPVMLx]>;
def : Pat<(fsub_mlx (fmul_su DPR:$a, (f64 DPR:$b)), DPR:$dstin),
(VNMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP2,HasDPVFP,UseFPVMLx]>;
def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin),
(VNMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
def : Pat<(fsub_mlx (fmul_su (f16 HPR:$a), HPR:$b), HPR:$dstin),
(VNMLSH HPR:$dstin, (f16 HPR:$a), HPR:$b)>,
Requires<[HasFullFP16,DontUseNEONForFP,UseFPVMLx]>;
//===----------------------------------------------------------------------===//
// Fused FP Multiply-Accumulate Operations.
//
def VFMAD : ADbI<0b11101, 0b10, 0, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
IIC_fpFMAC64, "vfma", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fadd_mlx (fmul_su DPR:$Dn, DPR:$Dm),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>,
Sched<[WriteFPMAC64, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def VFMAS : ASbIn<0b11101, 0b10, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpFMAC32, "vfma", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fadd_mlx (fmul_su SPR:$Sn, SPR:$Sm),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines.
}
def VFMAH : AHbI<0b11101, 0b10, 0, 0,
(outs HPR:$Sd), (ins HPR:$Sdin, HPR:$Sn, HPR:$Sm),
IIC_fpFMAC16, "vfma", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fadd_mlx (fmul_su (f16 HPR:$Sn), (f16 HPR:$Sm)),
(f16 HPR:$Sdin)))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasFullFP16,UseFusedMAC]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def : Pat<(fadd_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
(VFMAD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>;
def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VFMAS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>;
def : Pat<(fadd_mlx HPR:$dstin, (fmul_su (f16 HPR:$a), HPR:$b)),
(VFMAH HPR:$dstin, (f16 HPR:$a), HPR:$b)>,
Requires<[HasFullFP16,DontUseNEONForFP,UseFusedMAC]>;
// Match @llvm.fma.* intrinsics
// (fma x, y, z) -> (vfms z, x, y)
def : Pat<(f64 (fma DPR:$Dn, DPR:$Dm, DPR:$Ddin)),
(VFMAD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
Requires<[HasVFP4,HasDPVFP]>;
def : Pat<(f32 (fma SPR:$Sn, SPR:$Sm, SPR:$Sdin)),
(VFMAS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
Requires<[HasVFP4]>;
def : Pat<(f16 (fma HPR:$Sn, HPR:$Sm, (f16 HPR:$Sdin))),
(VFMAH (f16 HPR:$Sdin), (f16 HPR:$Sn), (f16 HPR:$Sm))>,
Requires<[HasFullFP16]>;
def VFMSD : ADbI<0b11101, 0b10, 1, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
IIC_fpFMAC64, "vfms", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd, (fadd_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>,
Sched<[WriteFPMAC64, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def VFMSS : ASbIn<0b11101, 0b10, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpFMAC32, "vfms", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fadd_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines.
}
def VFMSH : AHbI<0b11101, 0b10, 1, 0,
(outs HPR:$Sd), (ins HPR:$Sdin, HPR:$Sn, HPR:$Sm),
IIC_fpFMAC16, "vfms", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fadd_mlx (fneg (fmul_su (f16 HPR:$Sn), (f16 HPR:$Sm))),
(f16 HPR:$Sdin)))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasFullFP16,UseFusedMAC]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def : Pat<(fsub_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
(VFMSD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>;
def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VFMSS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>;
def : Pat<(fsub_mlx HPR:$dstin, (fmul_su (f16 HPR:$a), HPR:$b)),
(VFMSH HPR:$dstin, (f16 HPR:$a), HPR:$b)>,
Requires<[HasFullFP16,DontUseNEONForFP,UseFusedMAC]>;
// Match @llvm.fma.* intrinsics
// (fma (fneg x), y, z) -> (vfms z, x, y)
def : Pat<(f64 (fma (fneg DPR:$Dn), DPR:$Dm, DPR:$Ddin)),
(VFMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
Requires<[HasVFP4,HasDPVFP]>;
def : Pat<(f32 (fma (fneg SPR:$Sn), SPR:$Sm, SPR:$Sdin)),
(VFMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
Requires<[HasVFP4]>;
def : Pat<(f16 (fma (fneg (f16 HPR:$Sn)), (f16 HPR:$Sm), (f16 HPR:$Sdin))),
(VFMSH (f16 HPR:$Sdin), (f16 HPR:$Sn), (f16 HPR:$Sm))>,
Requires<[HasFullFP16]>;
def VFNMAD : ADbI<0b11101, 0b01, 1, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
IIC_fpFMAC64, "vfnma", ".f64\t$Dd, $Dn, $Dm",
[(set DPR:$Dd,(fsub_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>,
Sched<[WriteFPMAC64, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def VFNMAS : ASbI<0b11101, 0b01, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpFMAC32, "vfnma", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fsub_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines.
}
def VFNMAH : AHbI<0b11101, 0b01, 1, 0,
(outs HPR:$Sd), (ins HPR:$Sdin, HPR:$Sn, HPR:$Sm),
IIC_fpFMAC16, "vfnma", ".f16\t$Sd, $Sn, $Sm",
[(set (f16 HPR:$Sd), (fsub_mlx (fneg (fmul_su (f16 HPR:$Sn), (f16 HPR:$Sm))),
(f16 HPR:$Sdin)))]>,
RegConstraint<"$Sdin = $Sd">,
Requires<[HasFullFP16,UseFusedMAC]>,
Sched<[WriteFPMAC32, ReadFPMAC, ReadFPMUL, ReadFPMUL]>;
def : Pat<(fsub_mlx (fneg (fmul_su DPR:$a, (f64 DPR:$b))), DPR:$dstin),
(VFNMAD DPR:$dstin, DPR:$a, DPR:$b)>,
Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>;
def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin),
(VFNMAS SPR:$dstin, SPR:$a, SPR:$b)>,
Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>;
// Match @llvm.fma.* intrinsics
// (fneg (fma x, y, z)) -> (vfnma z, x, y)
def : Pat<(fneg (fma (f64 DPR:$Dn), (f64 DPR:$Dm), (f64 DPR:$Ddin))),
(VFNMAD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>,
Requires<[HasVFP4,HasDPVFP]>;
def : Pat<(fneg (fma (f32 SPR:$Sn), (f32 SPR:$Sm), (f32 SPR:$Sdin))),