X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FARM%2FARMInstrVFP.td;h=a5494819d1660993ded0473bdc8677012e6e52bb;hb=dd2836776f435d4b6de8d780228d02da15c37e7f;hp=a9c99a191cb9fa6dc0ddd3716469d41d1567f0a0;hpb=73fe34a3ee866867d5028f4a9afa2c3b8efebcba;p=oota-llvm.git diff --git a/lib/Target/ARM/ARMInstrVFP.td b/lib/Target/ARM/ARMInstrVFP.td index a9c99a191cb..a5494819d16 100644 --- a/lib/Target/ARM/ARMInstrVFP.td +++ b/lib/Target/ARM/ARMInstrVFP.td @@ -1,4 +1,4 @@ -//===- ARMInstrVFP.td - VFP support for ARM ----------------*- tablegen -*-===// +//===-- ARMInstrVFP.td - VFP support for ARM ---------------*- tablegen -*-===// // // The LLVM Compiler Infrastructure // @@ -21,9 +21,9 @@ def arm_ftoui : SDNode<"ARMISD::FTOUI", SDT_FTOI>; def arm_ftosi : SDNode<"ARMISD::FTOSI", SDT_FTOI>; def arm_sitof : SDNode<"ARMISD::SITOF", SDT_ITOF>; def arm_uitof : SDNode<"ARMISD::UITOF", SDT_ITOF>; -def arm_fmstat : SDNode<"ARMISD::FMSTAT", SDTNone, [SDNPInFlag, SDNPOutFlag]>; -def arm_cmpfp : SDNode<"ARMISD::CMPFP", SDT_ARMCmp, [SDNPOutFlag]>; -def arm_cmpfp0 : SDNode<"ARMISD::CMPFPw0", SDT_CMPFP0, [SDNPOutFlag]>; +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_fmdrr : SDNode<"ARMISD::VMOVDRR", SDT_VMOVDRR>; @@ -31,20 +31,61 @@ def arm_fmdrr : SDNode<"ARMISD::VMOVDRR", SDT_VMOVDRR>; // Operand Definitions. // +// 8-bit floating-point immediate encodings. +def FPImmOperand : AsmOperandClass { + let Name = "FPImm"; + let ParserMethod = "parseFPImm"; +} + def vfp_f32imm : Operand, PatLeaf<(f32 fpimm), [{ - return ARM::getVFPf32Imm(N->getValueAPF()) != -1; - }]> { - let PrintMethod = "printVFPf32ImmOperand"; + return ARM_AM::getFP32Imm(N->getValueAPF()) != -1; + }], SDNodeXFormgetValueAPF(); + uint32_t enc = ARM_AM::getFP32Imm(InVal); + return CurDAG->getTargetConstant(enc, MVT::i32); + }]>> { + let PrintMethod = "printFPImmOperand"; + let ParserMatchClass = FPImmOperand; } def vfp_f64imm : Operand, PatLeaf<(f64 fpimm), [{ - return ARM::getVFPf64Imm(N->getValueAPF()) != -1; - }]> { - let PrintMethod = "printVFPf64ImmOperand"; + return ARM_AM::getFP64Imm(N->getValueAPF()) != -1; + }], SDNodeXFormgetValueAPF(); + uint32_t enc = ARM_AM::getFP64Imm(InVal); + return CurDAG->getTargetConstant(enc, MVT::i32); + }]>> { + let PrintMethod = "printFPImmOperand"; + let ParserMatchClass = FPImmOperand; +} + +def alignedload32 : PatFrag<(ops node:$ptr), (load node:$ptr), [{ + return cast(N)->getAlignment() >= 4; +}]>; + +def alignedstore32 : PatFrag<(ops node:$val, node:$ptr), + (store node:$val, node:$ptr), [{ + return cast(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 { + let PrintMethod = "printFBits32"; + let ParserMatchClass = fbits32_asm_operand; } +def fbits16_asm_operand : AsmOperandClass { let Name = "FBits16"; } +def fbits16 : Operand { + let PrintMethod = "printFBits16"; + let ParserMatchClass = fbits16_asm_operand; +} //===----------------------------------------------------------------------===// // Load / store Instructions. @@ -53,22 +94,30 @@ def vfp_f64imm : Operand, let canFoldAsLoad = 1, isReMaterializable = 1 in { def VLDRD : ADI5<0b1101, 0b01, (outs DPR:$Dd), (ins addrmode5:$addr), - IIC_fpLoad64, "vldr", ".64\t$Dd, $addr", - [(set DPR:$Dd, (f64 (load addrmode5:$addr)))]>; + IIC_fpLoad64, "vldr", "\t$Dd, $addr", + [(set DPR:$Dd, (f64 (alignedload32 addrmode5:$addr)))]>; def VLDRS : ASI5<0b1101, 0b01, (outs SPR:$Sd), (ins addrmode5:$addr), - IIC_fpLoad32, "vldr", ".32\t$Sd, $addr", - [(set SPR:$Sd, (load addrmode5:$addr))]>; + IIC_fpLoad32, "vldr", "\t$Sd, $addr", + [(set SPR:$Sd, (load addrmode5:$addr))]> { + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; +} } // End of 'let canFoldAsLoad = 1, isReMaterializable = 1 in' def VSTRD : ADI5<0b1101, 0b00, (outs), (ins DPR:$Dd, addrmode5:$addr), - IIC_fpStore64, "vstr", ".64\t$Dd, $addr", - [(store (f64 DPR:$Dd), addrmode5:$addr)]>; + IIC_fpStore64, "vstr", "\t$Dd, $addr", + [(alignedstore32 (f64 DPR:$Dd), addrmode5:$addr)]>; def VSTRS : ASI5<0b1101, 0b00, (outs), (ins SPR:$Sd, addrmode5:$addr), - IIC_fpStore32, "vstr", ".32\t$Sd, $addr", - [(store SPR:$Sd, addrmode5:$addr)]>; + IIC_fpStore32, "vstr", "\t$Sd, $addr", + [(store SPR:$Sd, addrmode5:$addr)]> { + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; +} //===----------------------------------------------------------------------===// // Load / store multiple Instructions. @@ -78,7 +127,7 @@ multiclass vfp_ldst_mult { // Double Precision def DIA : - AXDI4<(outs), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops), + AXDI4<(outs), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops), IndexModeNone, itin, !strconcat(asm, "ia${p}\t$Rn, $regs"), "", []> { let Inst{24-23} = 0b01; // Increment After @@ -86,23 +135,17 @@ multiclass vfp_ldst_mult { let Inst{24-23} = 0b01; // Increment After let Inst{21} = 1; // Writeback let Inst{20} = L_bit; } - def DDB : - AXDI4<(outs), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops), - IndexModeNone, itin, - !strconcat(asm, "db${p}\t$Rn, $regs"), "", []> { - let Inst{24-23} = 0b10; // Decrement Before - let Inst{21} = 0; // No writeback - let Inst{20} = L_bit; - } def DDB_UPD : - AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops), + AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, + variable_ops), IndexModeUpd, itin_upd, !strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> { let Inst{24-23} = 0b10; // Decrement Before @@ -112,36 +155,42 @@ multiclass vfp_ldst_mult { let Inst{24-23} = 0b01; // Increment After let Inst{21} = 0; // No writeback let Inst{20} = L_bit; + + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines. + let D = VFPNeonDomain; } def SIA_UPD : - AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops), + AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs, + variable_ops), IndexModeUpd, itin_upd, !strconcat(asm, "ia${p}\t$Rn!, $regs"), "$Rn = $wb", []> { let Inst{24-23} = 0b01; // Increment After let Inst{21} = 1; // Writeback let Inst{20} = L_bit; - } - def SDB : - AXSI4<(outs), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops), - IndexModeNone, itin, - !strconcat(asm, "db${p}\t$Rn, $regs"), "", []> { - let Inst{24-23} = 0b10; // Decrement Before - let Inst{21} = 0; // No writeback - let Inst{20} = L_bit; + + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines. + let D = VFPNeonDomain; } def SDB_UPD : - AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops), + AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs, + variable_ops), IndexModeUpd, itin_upd, !strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> { let Inst{24-23} = 0b10; // Decrement Before let Inst{21} = 1; // Writeback let Inst{20} = L_bit; + + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines. + let D = VFPNeonDomain; } } @@ -151,55 +200,151 @@ let mayLoad = 1, hasExtraDefRegAllocReq = 1 in defm VLDM : vfp_ldst_mult<"vldm", 1, IIC_fpLoad_m, IIC_fpLoad_mu>; let mayStore = 1, hasExtraSrcRegAllocReq = 1 in -defm VSTM : vfp_ldst_mult<"vstm", 0, IIC_fpLoad_m, IIC_fpLoad_mu>; +defm VSTM : vfp_ldst_mult<"vstm", 0, IIC_fpStore_m, IIC_fpStore_mu>; } // neverHasSideEffects -// FLDMX, FSTMX - mixing S/D registers for pre-armv6 cores +def : MnemonicAlias<"vldm", "vldmia">; +def : MnemonicAlias<"vstm", "vstmia">; + +// FLDM/FSTM - Load / Store multiple single / double precision registers for +// pre-ARMv6 cores. +// These instructions are deprecated! +def : VFP2MnemonicAlias<"fldmias", "vldmia">; +def : VFP2MnemonicAlias<"fldmdbs", "vldmdb">; +def : VFP2MnemonicAlias<"fldmeas", "vldmdb">; +def : VFP2MnemonicAlias<"fldmfds", "vldmia">; +def : VFP2MnemonicAlias<"fldmiad", "vldmia">; +def : VFP2MnemonicAlias<"fldmdbd", "vldmdb">; +def : VFP2MnemonicAlias<"fldmead", "vldmdb">; +def : VFP2MnemonicAlias<"fldmfdd", "vldmia">; + +def : VFP2MnemonicAlias<"fstmias", "vstmia">; +def : VFP2MnemonicAlias<"fstmdbs", "vstmdb">; +def : VFP2MnemonicAlias<"fstmeas", "vstmia">; +def : VFP2MnemonicAlias<"fstmfds", "vstmdb">; +def : VFP2MnemonicAlias<"fstmiad", "vstmia">; +def : VFP2MnemonicAlias<"fstmdbd", "vstmdb">; +def : VFP2MnemonicAlias<"fstmead", "vstmia">; +def : VFP2MnemonicAlias<"fstmfdd", "vstmdb">; + +def : InstAlias<"vpush${p} $r", (VSTMDDB_UPD SP, pred:$p, dpr_reglist:$r)>, + Requires<[HasVFP2]>; +def : InstAlias<"vpush${p} $r", (VSTMSDB_UPD SP, pred:$p, spr_reglist:$r)>, + Requires<[HasVFP2]>; +def : InstAlias<"vpop${p} $r", (VLDMDIA_UPD SP, pred:$p, dpr_reglist:$r)>, + Requires<[HasVFP2]>; +def : InstAlias<"vpop${p} $r", (VLDMSIA_UPD SP, pred:$p, spr_reglist:$r)>, + Requires<[HasVFP2]>; +defm : VFPDTAnyInstAlias<"vpush${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:$r)>; + +// FLDMX, FSTMX - Load and store multiple unknown precision registers for +// pre-armv6 cores. +// These instruction are deprecated so we don't want them to get selected. +multiclass vfp_ldstx_mult { + // Unknown precision + def XIA : + AXXI4<(outs), (ins GPR:$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)))]>; +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))]>; + [(set SPR:$Sd, (fadd SPR:$Sn, SPR:$Sm))]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} +let TwoOperandAliasConstraint = "$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)))]>; +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))]>; + [(set SPR:$Sd, (fsub SPR:$Sn, SPR:$Sm))]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} +let TwoOperandAliasConstraint = "$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)))]>; +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))]>; +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)))]>; +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))]>; + [(set SPR:$Sd, (fmul SPR:$Sn, SPR:$Sm))]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} def VNMULD : ADbI<0b11100, 0b10, 1, 0, (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm), @@ -209,16 +354,63 @@ def VNMULD : ADbI<0b11100, 0b10, 1, 0, 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)))]>; + [(set SPR:$Sd, (fneg (fmul SPR:$Sn, SPR:$Sm)))]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} + +multiclass vsel_inst opc, int CC> { + let DecoderNamespace = "VFPV8", PostEncoderMethod = "", + Uses = [CPSR], AddedComplexity = 4 in { + def S : ASbInp<0b11100, opc, 0, + (outs SPR:$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 { + let DecoderNamespace = "VFPV8", PostEncoderMethod = "" in { + 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 VMAXNM : vmaxmin_inst<"vmaxnm", 0, ARMvmaxnm>; +defm VMINNM : vmaxmin_inst<"vminnm", 1, ARMvminnm>; // 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]>; + (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] in { +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, $Dm", @@ -227,7 +419,11 @@ def VCMPED : ADuI<0b11101, 0b11, 0b0100, 0b11, 0, def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0, (outs), (ins SPR:$Sd, SPR:$Sm), IIC_fpCMP32, "vcmpe", ".f32\t$Sd, $Sm", - [(arm_cmpfp SPR:$Sd, SPR:$Sm)]>; + [(arm_cmpfp SPR:$Sd, SPR:$Sm)]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} // FIXME: Verify encoding after integrated assembler is working. def VCMPD : ADuI<0b11101, 0b11, 0b0100, 0b01, 0, @@ -238,8 +434,12 @@ def VCMPD : ADuI<0b11101, 0b11, 0b0100, 0b01, 0, def VCMPS : ASuI<0b11101, 0b11, 0b0100, 0b01, 0, (outs), (ins SPR:$Sd, SPR:$Sm), IIC_fpCMP32, "vcmp", ".f32\t$Sd, $Sm", - [/* For disassembly only; pattern left blank */]>; + [/* For disassembly only; pattern left blank */]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; } +} // Defs = [FPSCR_NZCV] //===----------------------------------------------------------------------===// // FP Unary Operations. @@ -253,9 +453,13 @@ def VABSD : ADuI<0b11101, 0b11, 0b0000, 0b11, 0, def VABSS : ASuIn<0b11101, 0b11, 0b0000, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm), IIC_fpUNA32, "vabs", ".f32\t$Sd, $Sm", - [(set SPR:$Sd, (fabs SPR:$Sm))]>; + [(set SPR:$Sd, (fabs SPR:$Sm))]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -let Defs = [FPSCR] in { +let Defs = [FPSCR_NZCV] in { def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0, (outs), (ins DPR:$Dd), IIC_fpCMP64, "vcmpe", ".f64\t$Dd, #0", @@ -270,6 +474,10 @@ def VCMPEZS : ASuI<0b11101, 0b11, 0b0101, 0b11, 0, [(arm_cmpfp0 SPR:$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; } // FIXME: Verify encoding after integrated assembler is working. @@ -287,8 +495,12 @@ def VCMPZS : ASuI<0b11101, 0b11, 0b0101, 0b01, 0, [/* For disassembly only; pattern left blank */]> { 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; } -} +} // Defs = [FPSCR_NZCV] def VCVTDS : ASuI<0b11101, 0b11, 0b0111, 0b11, 0, (outs DPR:$Dd), (ins SPR:$Sm), @@ -324,33 +536,140 @@ def VCVTSD : VFPAI<(outs SPR:$Sd), (ins DPR:$Dm), VFPUnaryFrm, let Inst{11-8} = 0b1011; let Inst{7-6} = 0b11; let Inst{4} = 0; + + let Predicates = [HasVFP2, HasDPVFP]; } -// Between half-precision and single-precision. For disassembly only. +// Between half, single and double-precision. For disassembly only. // FIXME: Verify encoding after integrated assembler is working. -def VCVTBSH: ASuI<0b11101, 0b11, 0b0010, 0b01, 0, (outs SPR:$dst), (ins SPR:$a), - /* FIXME */ IIC_fpCVTSH, "vcvtb", ".f32.f16\t$dst, $a", +def VCVTBHS: ASuI<0b11101, 0b11, 0b0010, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm), + /* FIXME */ IIC_fpCVTSH, "vcvtb", ".f32.f16\t$Sd, $Sm", [/* For disassembly only; pattern left blank */]>; -def : ARMPat<(f32_to_f16 SPR:$a), - (i32 (COPY_TO_REGCLASS (VCVTBSH SPR:$a), GPR))>; - -def VCVTBHS: ASuI<0b11101, 0b11, 0b0011, 0b01, 0, (outs SPR:$dst), (ins SPR:$a), - /* FIXME */ IIC_fpCVTHS, "vcvtb", ".f16.f32\t$dst, $a", +def VCVTBSH: ASuI<0b11101, 0b11, 0b0011, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm), + /* FIXME */ IIC_fpCVTHS, "vcvtb", ".f16.f32\t$Sd, $Sm", [/* For disassembly only; pattern left blank */]>; -def : ARMPat<(f16_to_f32 GPR:$a), - (VCVTBHS (COPY_TO_REGCLASS GPR:$a, SPR))>; +def : Pat<(f32_to_f16 SPR:$a), + (i32 (COPY_TO_REGCLASS (VCVTBSH SPR:$a), GPR))>; + +def : Pat<(f16_to_f32 GPR:$a), + (VCVTBHS (COPY_TO_REGCLASS GPR:$a, SPR))>; -def VCVTTSH: ASuI<0b11101, 0b11, 0b0010, 0b11, 0, (outs SPR:$dst), (ins SPR:$a), - /* FIXME */ IIC_fpCVTSH, "vcvtt", ".f32.f16\t$dst, $a", +def VCVTTHS: ASuI<0b11101, 0b11, 0b0010, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm), + /* FIXME */ IIC_fpCVTSH, "vcvtt", ".f32.f16\t$Sd, $Sm", [/* For disassembly only; pattern left blank */]>; -def VCVTTHS: ASuI<0b11101, 0b11, 0b0011, 0b11, 0, (outs SPR:$dst), (ins SPR:$a), - /* FIXME */ IIC_fpCVTHS, "vcvtt", ".f16.f32\t$dst, $a", +def VCVTTSH: ASuI<0b11101, 0b11, 0b0011, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm), + /* FIXME */ IIC_fpCVTHS, "vcvtt", ".f16.f32\t$Sd, $Sm", [/* For disassembly only; pattern left blank */]>; +def VCVTBHD : ADuI<0b11101, 0b11, 0b0010, 0b01, 0, + (outs DPR:$Dd), (ins SPR:$Sm), + NoItinerary, "vcvtb", ".f64.f16\t$Dd, $Sm", + []>, Requires<[HasFPARMv8, HasDPVFP]> { + // Instruction operands. + bits<5> Sm; + + // Encode instruction operands. + let Inst{3-0} = Sm{4-1}; + let Inst{5} = Sm{0}; +} + +def VCVTBDH : ADuI<0b11101, 0b11, 0b0011, 0b01, 0, + (outs SPR:$Sd), (ins DPR:$Dm), + NoItinerary, "vcvtb", ".f16.f64\t$Sd, $Dm", + []>, Requires<[HasFPARMv8, HasDPVFP]> { + // Instruction operands. + bits<5> Sd; + bits<5> Dm; + + // Encode instruction operands. + let Inst{3-0} = Dm{3-0}; + let Inst{5} = Dm{4}; + let Inst{15-12} = Sd{4-1}; + let Inst{22} = Sd{0}; +} + +def VCVTTHD : ADuI<0b11101, 0b11, 0b0010, 0b11, 0, + (outs DPR:$Dd), (ins SPR:$Sm), + NoItinerary, "vcvtt", ".f64.f16\t$Dd, $Sm", + []>, Requires<[HasFPARMv8, HasDPVFP]> { + // Instruction operands. + bits<5> Sm; + + // Encode instruction operands. + let Inst{3-0} = Sm{4-1}; + let Inst{5} = Sm{0}; +} + +def VCVTTDH : ADuI<0b11101, 0b11, 0b0011, 0b11, 0, + (outs SPR:$Sd), (ins DPR:$Dm), + NoItinerary, "vcvtt", ".f16.f64\t$Sd, $Dm", + []>, Requires<[HasFPARMv8, HasDPVFP]> { + // Instruction operands. + bits<5> Sd; + bits<5> Dm; + + // Encode instruction operands. + let Inst{15-12} = Sd{4-1}; + let Inst{22} = Sd{0}; + let Inst{3-0} = Dm{3-0}; + let Inst{5} = Dm{4}; +} + +multiclass vcvt_inst rm> { + let PostEncoderMethod = "", DecoderNamespace = "VFPV8" in { + def SS : ASuInp<0b11101, 0b11, 0b1100, 0b11, 0, + (outs SPR:$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, $Dm"), + []>, Requires<[HasFPARMv8, HasDPVFP]> { + bits<5> Dm; + + let Inst{17-16} = rm; + + // Encode instruction operands + let Inst{3-0} = Dm{3-0}; + let Inst{5} = Dm{4}; + let Inst{8} = 1; + } + } +} + +defm VCVTA : vcvt_inst<"a", 0b00>; +defm VCVTN : vcvt_inst<"n", 0b01>; +defm VCVTP : vcvt_inst<"p", 0b10>; +defm VCVTM : vcvt_inst<"m", 0b11>; + def VNEGD : ADuI<0b11101, 0b11, 0b0001, 0b01, 0, (outs DPR:$Dd), (ins DPR:$Dm), IIC_fpUNA64, "vneg", ".f64\t$Dd, $Dm", @@ -359,7 +678,68 @@ def VNEGD : ADuI<0b11101, 0b11, 0b0001, 0b01, 0, def VNEGS : ASuIn<0b11101, 0b11, 0b0001, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm), IIC_fpUNA32, "vneg", ".f32\t$Sd, $Sm", - [(set SPR:$Sd, (fneg SPR:$Sm))]>; + [(set SPR:$Sd, (fneg SPR:$Sm))]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} + +multiclass vrint_inst_zrx { + def S : ASuI<0b11101, 0b11, 0b0110, 0b11, 0, + (outs SPR:$Sd), (ins SPR:$Sm), + NoItinerary, !strconcat("vrint", opc), ".f32\t$Sd, $Sm", + []>, Requires<[HasFPARMv8]> { + let Inst{7} = op2; + let Inst{16} = op; + } + def D : ADuI<0b11101, 0b11, 0b0110, 0b11, 0, + (outs DPR:$Dd), (ins DPR:$Dm), + NoItinerary, !strconcat("vrint", opc), ".f64\t$Dd, $Dm", + []>, Requires<[HasFPARMv8, HasDPVFP]> { + let Inst{7} = op2; + let Inst{16} = op; + } + + def : InstAlias(NAME#"S") SPR:$Sd, SPR:$Sm, pred:$p)>, + Requires<[HasFPARMv8]>; + def : InstAlias(NAME#"D") DPR:$Dd, DPR:$Dm, pred:$p)>, + Requires<[HasFPARMv8,HasDPVFP]>; +} + +defm VRINTZ : vrint_inst_zrx<"z", 0, 1>; +defm VRINTR : vrint_inst_zrx<"r", 0, 0>; +defm VRINTX : vrint_inst_zrx<"x", 1, 0>; + +multiclass vrint_inst_anpm rm> { + let PostEncoderMethod = "", DecoderNamespace = "VFPV8" in { + def S : ASuInp<0b11101, 0b11, 0b1000, 0b01, 0, + (outs SPR:$Sd), (ins SPR:$Sm), + NoItinerary, !strconcat("vrint", opc, ".f32\t$Sd, $Sm"), + []>, Requires<[HasFPARMv8]> { + let Inst{17-16} = rm; + } + def D : ADuInp<0b11101, 0b11, 0b1000, 0b01, 0, + (outs DPR:$Dd), (ins DPR:$Dm), + NoItinerary, !strconcat("vrint", opc, ".f64\t$Dd, $Dm"), + []>, Requires<[HasFPARMv8, HasDPVFP]> { + let Inst{17-16} = rm; + } + } + + def : InstAlias(NAME#"S") SPR:$Sd, SPR:$Sm)>, + Requires<[HasFPARMv8]>; + def : InstAlias(NAME#"D") DPR:$Dd, DPR:$Dm)>, + Requires<[HasFPARMv8,HasDPVFP]>; +} + +defm VRINTA : vrint_inst_anpm<"a", 0b00>; +defm VRINTN : vrint_inst_anpm<"n", 0b01>; +defm VRINTP : vrint_inst_anpm<"p", 0b10>; +defm VRINTM : vrint_inst_anpm<"m", 0b11>; def VSQRTD : ADuI<0b11101, 0b11, 0b0001, 0b11, 0, (outs DPR:$Dd), (ins DPR:$Dm), @@ -400,12 +780,18 @@ def VMOVRS : AVConv2I<0b11100001, 0b1010, let Inst{6-5} = 0b00; let Inst{3-0} = 0b0000; + + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; } +// Bitcast i32 -> f32. NEON prefers to use VMOVDRR. def VMOVSR : AVConv4I<0b11100000, 0b1010, (outs SPR:$Sn), (ins GPR:$Rt), IIC_fpMOVIS, "vmov", "\t$Sn, $Rt", - [(set SPR:$Sn, (bitconvert GPR:$Rt))]> { + [(set SPR:$Sn, (bitconvert GPR:$Rt))]>, + Requires<[HasVFP2, UseVMOVSR]> { // Instruction operands. bits<5> Sn; bits<4> Rt; @@ -417,6 +803,10 @@ def VMOVSR : AVConv4I<0b11100000, 0b1010, let Inst{6-5} = 0b00; let Inst{3-0} = 0b0000; + + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; } let neverHasSideEffects = 1 in { @@ -436,13 +826,32 @@ def VMOVRRD : AVConv3I<0b11000101, 0b1011, let Inst{19-16} = Rt2; let Inst{7-6} = 0b00; + + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; } def VMOVRRS : AVConv3I<0b11000101, 0b1010, - (outs GPR:$wb, GPR:$dst2), (ins SPR:$src1, SPR:$src2), - IIC_fpMOVDI, "vmov", "\t$wb, $dst2, $src1, $src2", + (outs GPR:$Rt, GPR:$Rt2), (ins SPR:$src1, SPR:$src2), + IIC_fpMOVDI, "vmov", "\t$Rt, $Rt2, $src1, $src2", [/* For disassembly only; pattern left blank */]> { + bits<5> src1; + bits<4> Rt; + bits<4> Rt2; + + // Encode instruction operands. + let Inst{3-0} = src1{4-1}; + let Inst{5} = src1{0}; + let Inst{15-12} = Rt; + let Inst{19-16} = Rt2; + let Inst{7-6} = 0b00; + + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; + let DecoderMethod = "DecodeVMOVRRS"; } } // neverHasSideEffects @@ -465,6 +874,10 @@ def VMOVDRR : AVConv5I<0b11000100, 0b1011, let Inst{19-16} = Rt2; let Inst{7-6} = 0b00; + + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; } let neverHasSideEffects = 1 in @@ -472,7 +885,24 @@ def VMOVSRR : AVConv5I<0b11000100, 0b1010, (outs SPR:$dst1, SPR:$dst2), (ins GPR:$src1, GPR:$src2), IIC_fpMOVID, "vmov", "\t$dst1, $dst2, $src1, $src2", [/* For disassembly only; pattern left blank */]> { + // Instruction operands. + bits<5> dst1; + bits<4> src1; + bits<4> src2; + + // Encode instruction operands. + let Inst{3-0} = dst1{4-1}; + let Inst{5} = dst1{0}; + let Inst{15-12} = src1; + let Inst{19-16} = src2; + let Inst{7-6} = 0b00; + + // Some single precision VFP instructions may be executed on both NEON and VFP + // pipelines. + let D = VFPNeonDomain; + + let DecoderMethod = "DecodeVMOVSRR"; } // FMRDH: SPR -> GPR @@ -500,6 +930,8 @@ class AVConv1IDs_Encode opcod1, bits<2> opcod2, bits<4> opcod3, let Inst{5} = Sm{0}; let Inst{15-12} = Dd{3-0}; let Inst{22} = Dd{4}; + + let Predicates = [HasVFP2, HasDPVFP]; } class AVConv1InSs_Encode opcod1, bits<2> opcod2, bits<4> opcod3, @@ -530,6 +962,10 @@ def VSITOS : AVConv1InSs_Encode<0b11101, 0b11, 0b1000, 0b1010, IIC_fpCVTIS, "vcvt", ".f32.s32\t$Sd, $Sm", [(set SPR:$Sd, (arm_sitof SPR:$Sm))]> { let Inst{7} = 1; // s32 + + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; } def VUITOD : AVConv1IDs_Encode<0b11101, 0b11, 0b1000, 0b1011, @@ -544,6 +980,10 @@ def VUITOS : AVConv1InSs_Encode<0b11101, 0b11, 0b1000, 0b1010, IIC_fpCVTIS, "vcvt", ".f32.u32\t$Sd, $Sm", [(set SPR:$Sd, (arm_uitof SPR:$Sm))]> { let Inst{7} = 0; // u32 + + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; } // FP -> Int: @@ -563,6 +1003,8 @@ class AVConv1IsD_Encode opcod1, bits<2> opcod2, bits<4> opcod3, let Inst{5} = Dm{4}; let Inst{15-12} = Sd{4-1}; let Inst{22} = Sd{0}; + + let Predicates = [HasVFP2, HasDPVFP]; } class AVConv1InsS_Encode opcod1, bits<2> opcod2, bits<4> opcod3, @@ -595,6 +1037,10 @@ def VTOSIZS : AVConv1InsS_Encode<0b11101, 0b11, 0b1101, 0b1010, IIC_fpCVTSI, "vcvt", ".s32.f32\t$Sd, $Sm", [(set SPR:$Sd, (arm_ftosi SPR:$Sm))]> { let Inst{7} = 1; // Z bit + + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; } def VTOUIZD : AVConv1IsD_Encode<0b11101, 0b11, 0b1100, 0b1011, @@ -609,10 +1055,13 @@ def VTOUIZS : AVConv1InsS_Encode<0b11101, 0b11, 0b1100, 0b1010, IIC_fpCVTSI, "vcvt", ".u32.f32\t$Sd, $Sm", [(set SPR:$Sd, (arm_ftoui SPR:$Sm))]> { let Inst{7} = 1; // Z bit + + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; } // And the Z bit '0' variants, i.e. use the rounding mode specified by FPSCR. -// For disassembly only. let Uses = [FPSCR] in { // FIXME: Verify encoding after integrated assembler is working. def VTOSIRD : AVConv1IsD_Encode<0b11101, 0b11, 0b1101, 0b1011, @@ -651,255 +1100,450 @@ def VTOUIRS : AVConv1InsS_Encode<0b11101, 0b11, 0b1100, 0b1010, // S32 (U=0, sx=1) -> SL // U32 (U=1, sx=1) -> UL -// FIXME: Marking these as codegen only seems wrong. They are real -// instructions(?) -let Constraints = "$a = $dst", isCodeGenOnly = 1 in { +let Constraints = "$a = $dst" in { // FP to Fixed-Point: -def VTOSHS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 0, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTSI, "vcvt", ".s16.f32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +// Single Precision register +class AVConv1XInsS_Encode op1, bits<2> op2, bits<4> op3, bits<4> op4, + bit op5, dag oops, dag iops, InstrItinClass itin, + string opc, string asm, list pattern> + : AVConv1XI, + Sched<[WriteCvtFP]> { + bits<5> dst; + // if dp_operation then UInt(D:Vd) else UInt(Vd:D); + let Inst{22} = dst{0}; + let Inst{15-12} = dst{4-1}; +} -def VTOUHS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 0, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTSI, "vcvt", ".u16.f32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +// Double Precision register +class AVConv1XInsD_Encode op1, bits<2> op2, bits<4> op3, bits<4> op4, + bit op5, dag oops, dag iops, InstrItinClass itin, + string opc, string asm, list pattern> + : AVConv1XI, + Sched<[WriteCvtFP]> { + bits<5> dst; + // if dp_operation then UInt(D:Vd) else UInt(Vd:D); + let Inst{22} = dst{4}; + let Inst{15-12} = dst{3-0}; + + let Predicates = [HasVFP2, HasDPVFP]; +} -def VTOSLS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 1, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTSI, "vcvt", ".s32.f32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VTOSHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 0, + (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits), + IIC_fpCVTSI, "vcvt", ".s16.f32\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VTOULS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 1, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTSI, "vcvt", ".u32.f32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VTOUHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 0, + (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits), + IIC_fpCVTSI, "vcvt", ".u16.f32\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VTOSHD : AVConv1XI<0b11101, 0b11, 0b1110, 0b1011, 0, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTDI, "vcvt", ".s16.f64\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VTOSLS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 1, + (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits), + IIC_fpCVTSI, "vcvt", ".s32.f32\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VTOUHD : AVConv1XI<0b11101, 0b11, 0b1111, 0b1011, 0, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTDI, "vcvt", ".u16.f64\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VTOULS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 1, + (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits), + IIC_fpCVTSI, "vcvt", ".u32.f32\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VTOSLD : AVConv1XI<0b11101, 0b11, 0b1110, 0b1011, 1, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTDI, "vcvt", ".s32.f64\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VTOSHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 0, + (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits), + IIC_fpCVTDI, "vcvt", ".s16.f64\t$dst, $a, $fbits", []>; -def VTOULD : AVConv1XI<0b11101, 0b11, 0b1111, 0b1011, 1, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTDI, "vcvt", ".u32.f64\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VTOUHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 0, + (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits), + IIC_fpCVTDI, "vcvt", ".u16.f64\t$dst, $a, $fbits", []>; + +def VTOSLD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 1, + (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits), + IIC_fpCVTDI, "vcvt", ".s32.f64\t$dst, $a, $fbits", []>; + +def VTOULD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 1, + (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits), + IIC_fpCVTDI, "vcvt", ".u32.f64\t$dst, $a, $fbits", []>; // Fixed-Point to FP: -def VSHTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 0, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTIS, "vcvt", ".f32.s16\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VSHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 0, + (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits), + IIC_fpCVTIS, "vcvt", ".f32.s16\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VUHTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 0, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTIS, "vcvt", ".f32.u16\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VUHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 0, + (outs SPR:$dst), (ins SPR:$a, fbits16:$fbits), + IIC_fpCVTIS, "vcvt", ".f32.u16\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VSLTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 1, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTIS, "vcvt", ".f32.s32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VSLTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 1, + (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits), + IIC_fpCVTIS, "vcvt", ".f32.s32\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VULTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 1, - (outs SPR:$dst), (ins SPR:$a, i32imm:$fbits), - IIC_fpCVTIS, "vcvt", ".f32.u32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VULTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 1, + (outs SPR:$dst), (ins SPR:$a, fbits32:$fbits), + IIC_fpCVTIS, "vcvt", ".f32.u32\t$dst, $a, $fbits", []> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def VSHTOD : AVConv1XI<0b11101, 0b11, 0b1010, 0b1011, 0, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTID, "vcvt", ".f64.s16\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VSHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 0, + (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits), + IIC_fpCVTID, "vcvt", ".f64.s16\t$dst, $a, $fbits", []>; -def VUHTOD : AVConv1XI<0b11101, 0b11, 0b1011, 0b1011, 0, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTID, "vcvt", ".f64.u16\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VUHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 0, + (outs DPR:$dst), (ins DPR:$a, fbits16:$fbits), + IIC_fpCVTID, "vcvt", ".f64.u16\t$dst, $a, $fbits", []>; -def VSLTOD : AVConv1XI<0b11101, 0b11, 0b1010, 0b1011, 1, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTID, "vcvt", ".f64.s32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VSLTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 1, + (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits), + IIC_fpCVTID, "vcvt", ".f64.s32\t$dst, $a, $fbits", []>; -def VULTOD : AVConv1XI<0b11101, 0b11, 0b1011, 0b1011, 1, - (outs DPR:$dst), (ins DPR:$a, i32imm:$fbits), - IIC_fpCVTID, "vcvt", ".f64.u32\t$dst, $a, $fbits", - [/* For disassembly only; pattern left blank */]>; +def VULTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 1, + (outs DPR:$dst), (ins DPR:$a, fbits32:$fbits), + IIC_fpCVTID, "vcvt", ".f64.u32\t$dst, $a, $fbits", []>; -} // End of 'let Constraints = "$a = $dst", isCodeGenOnly = 1 in' +} // End of 'let Constraints = "$a = $dst" in' //===----------------------------------------------------------------------===// -// FP FMA Operations. +// FP Multiply-Accumulate Operations. // def VMLAD : ADbI<0b11100, 0b00, 0, 0, (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm), IIC_fpMAC64, "vmla", ".f64\t$Dd, $Dn, $Dm", - [(set DPR:$Dd, (fadd (fmul DPR:$Dn, DPR:$Dm), - (f64 DPR:$Ddin)))]>, + [(set DPR:$Dd, (fadd_mlx (fmul_su DPR:$Dn, DPR:$Dm), + (f64 DPR:$Ddin)))]>, RegConstraint<"$Ddin = $Dd">, - Requires<[HasVFP2,UseVMLx]>; + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; def VMLAS : ASbIn<0b11100, 0b00, 0, 0, (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm), IIC_fpMAC32, "vmla", ".f32\t$Sd, $Sn, $Sm", - [(set SPR:$Sd, (fadd (fmul SPR:$Sn, SPR:$Sm), - SPR:$Sdin))]>, + [(set SPR:$Sd, (fadd_mlx (fmul_su SPR:$Sn, SPR:$Sm), + SPR:$Sdin))]>, RegConstraint<"$Sdin = $Sd">, - Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def : Pat<(fadd DPR:$dstin, (fmul DPR:$a, (f64 DPR:$b))), +def : Pat<(fadd_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))), (VMLAD DPR:$dstin, DPR:$a, DPR:$b)>, - Requires<[HasVFP2,UseVMLx]>; -def : Pat<(fadd SPR:$dstin, (fmul SPR:$a, SPR:$b)), + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; +def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)), (VMLAS SPR:$dstin, SPR:$a, SPR:$b)>, - Requires<[HasVFP2,DontUseNEONForFP, UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP, UseFPVMLx,DontUseFusedMAC]>; def VMLSD : ADbI<0b11100, 0b00, 1, 0, (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm), IIC_fpMAC64, "vmls", ".f64\t$Dd, $Dn, $Dm", - [(set DPR:$Dd, (fadd (fneg (fmul DPR:$Dn,DPR:$Dm)), - (f64 DPR:$Ddin)))]>, + [(set DPR:$Dd, (fadd_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)), + (f64 DPR:$Ddin)))]>, RegConstraint<"$Ddin = $Dd">, - Requires<[HasVFP2,UseVMLx]>; + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; def VMLSS : ASbIn<0b11100, 0b00, 1, 0, (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm), IIC_fpMAC32, "vmls", ".f32\t$Sd, $Sn, $Sm", - [(set SPR:$Sd, (fadd (fneg (fmul SPR:$Sn, SPR:$Sm)), - SPR:$Sdin))]>, + [(set SPR:$Sd, (fadd_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)), + SPR:$Sdin))]>, RegConstraint<"$Sdin = $Sd">, - Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def : Pat<(fsub DPR:$dstin, (fmul DPR:$a, (f64 DPR:$b))), +def : Pat<(fsub_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))), (VMLSD DPR:$dstin, DPR:$a, DPR:$b)>, - Requires<[HasVFP2,UseVMLx]>; -def : Pat<(fsub SPR:$dstin, (fmul SPR:$a, SPR:$b)), + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; +def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)), (VMLSS SPR:$dstin, SPR:$a, SPR:$b)>, - Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>; def VNMLAD : ADbI<0b11100, 0b01, 1, 0, (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm), IIC_fpMAC64, "vnmla", ".f64\t$Dd, $Dn, $Dm", - [(set DPR:$Dd,(fsub (fneg (fmul DPR:$Dn,DPR:$Dm)), - (f64 DPR:$Ddin)))]>, + [(set DPR:$Dd,(fsub_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)), + (f64 DPR:$Ddin)))]>, RegConstraint<"$Ddin = $Dd">, - Requires<[HasVFP2,UseVMLx]>; + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; def VNMLAS : ASbI<0b11100, 0b01, 1, 0, (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm), IIC_fpMAC32, "vnmla", ".f32\t$Sd, $Sn, $Sm", - [(set SPR:$Sd, (fsub (fneg (fmul SPR:$Sn, SPR:$Sm)), - SPR:$Sdin))]>, + [(set SPR:$Sd, (fsub_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)), + SPR:$Sdin))]>, RegConstraint<"$Sdin = $Sd">, - Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def : Pat<(fsub (fneg (fmul DPR:$a, (f64 DPR:$b))), DPR:$dstin), +def : Pat<(fsub_mlx (fneg (fmul_su DPR:$a, (f64 DPR:$b))), DPR:$dstin), (VNMLAD DPR:$dstin, DPR:$a, DPR:$b)>, - Requires<[HasVFP2,UseVMLx]>; -def : Pat<(fsub (fneg (fmul SPR:$a, SPR:$b)), SPR:$dstin), + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; +def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin), (VNMLAS SPR:$dstin, SPR:$a, SPR:$b)>, - Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>; def VNMLSD : ADbI<0b11100, 0b01, 0, 0, (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm), IIC_fpMAC64, "vnmls", ".f64\t$Dd, $Dn, $Dm", - [(set DPR:$Dd, (fsub (fmul DPR:$Dn, DPR:$Dm), - (f64 DPR:$Ddin)))]>, + [(set DPR:$Dd, (fsub_mlx (fmul_su DPR:$Dn, DPR:$Dm), + (f64 DPR:$Ddin)))]>, RegConstraint<"$Ddin = $Dd">, - Requires<[HasVFP2,UseVMLx]>; + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; def VNMLSS : ASbI<0b11100, 0b01, 0, 0, (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm), IIC_fpMAC32, "vnmls", ".f32\t$Sd, $Sn, $Sm", - [(set SPR:$Sd, (fsub (fmul SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>, + [(set SPR:$Sd, (fsub_mlx (fmul_su SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>, RegConstraint<"$Sdin = $Sd">, - Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines on A8. + let D = VFPNeonA8Domain; +} -def : Pat<(fsub (fmul DPR:$a, (f64 DPR:$b)), DPR:$dstin), +def : Pat<(fsub_mlx (fmul_su DPR:$a, (f64 DPR:$b)), DPR:$dstin), (VNMLSD DPR:$dstin, DPR:$a, DPR:$b)>, - Requires<[HasVFP2,UseVMLx]>; -def : Pat<(fsub (fmul SPR:$a, SPR:$b), SPR:$dstin), + Requires<[HasVFP2,HasDPVFP,UseFPVMLx,DontUseFusedMAC]>; +def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin), (VNMLSS SPR:$dstin, SPR:$a, SPR:$b)>, - Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>; + Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>; + +//===----------------------------------------------------------------------===// +// Fused FP Multiply-Accumulate Operations. +// +def VFMAD : ADbI<0b11101, 0b10, 0, 0, + (outs DPR:$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 = $Dd">, + Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>; + +def VFMAS : ASbIn<0b11101, 0b10, 0, 0, + (outs SPR:$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 = $Sd">, + Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines. +} + +def : Pat<(fadd_mlx DPR:$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:$b)>, + Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>; + +// Match @llvm.fma.* intrinsics +// (fma x, y, z) -> (vfms z, x, y) +def : Pat<(f64 (fma DPR:$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:$Sm)>, + Requires<[HasVFP4]>; + +def VFMSD : ADbI<0b11101, 0b10, 1, 0, + (outs DPR:$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 = $Dd">, + Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>; + +def VFMSS : ASbIn<0b11101, 0b10, 1, 0, + (outs SPR:$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 = $Sd">, + Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines. +} + +def : Pat<(fsub_mlx DPR:$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:$b)>, + Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>; + +// Match @llvm.fma.* intrinsics +// (fma (fneg x), y, z) -> (vfms z, x, y) +def : Pat<(f64 (fma (fneg DPR:$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:$Sm)>, + Requires<[HasVFP4]>; +// (fma x, (fneg y), z) -> (vfms z, x, y) +def : Pat<(f64 (fma DPR:$Dn, (fneg DPR:$Dm), DPR:$Ddin)), + (VFMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>, + Requires<[HasVFP4,HasDPVFP]>; +def : Pat<(f32 (fma SPR:$Sn, (fneg SPR:$Sm), SPR:$Sdin)), + (VFMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>, + Requires<[HasVFP4]>; + +def VFNMAD : ADbI<0b11101, 0b01, 1, 0, + (outs DPR:$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 = $Dd">, + Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>; + +def VFNMAS : ASbI<0b11101, 0b01, 1, 0, + (outs SPR:$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 = $Sd">, + Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines. +} + +def : Pat<(fsub_mlx (fneg (fmul_su DPR:$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))), + (VFNMAS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>, + Requires<[HasVFP4]>; +// (fma (fneg x), y, (fneg z)) -> (vfnma z, x, y) +def : Pat<(f64 (fma (fneg DPR:$Dn), DPR:$Dm, (fneg DPR:$Ddin))), + (VFNMAD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>, + Requires<[HasVFP4,HasDPVFP]>; +def : Pat<(f32 (fma (fneg SPR:$Sn), SPR:$Sm, (fneg SPR:$Sdin))), + (VFNMAS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>, + Requires<[HasVFP4]>; + +def VFNMSD : ADbI<0b11101, 0b01, 0, 0, + (outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm), + IIC_fpFMAC64, "vfnms", ".f64\t$Dd, $Dn, $Dm", + [(set DPR:$Dd, (fsub_mlx (fmul_su DPR:$Dn, DPR:$Dm), + (f64 DPR:$Ddin)))]>, + RegConstraint<"$Ddin = $Dd">, + Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>; + +def VFNMSS : ASbI<0b11101, 0b01, 0, 0, + (outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm), + IIC_fpFMAC32, "vfnms", ".f32\t$Sd, $Sn, $Sm", + [(set SPR:$Sd, (fsub_mlx (fmul_su SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>, + RegConstraint<"$Sdin = $Sd">, + Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]> { + // Some single precision VFP instructions may be executed on both NEON and + // VFP pipelines. +} +def : Pat<(fsub_mlx (fmul_su DPR:$a, (f64 DPR:$b)), DPR:$dstin), + (VFNMSD DPR:$dstin, DPR:$a, DPR:$b)>, + Requires<[HasVFP4,HasDPVFP,UseFusedMAC]>; +def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin), + (VFNMSS SPR:$dstin, SPR:$a, SPR:$b)>, + Requires<[HasVFP4,DontUseNEONForFP,UseFusedMAC]>; + +// Match @llvm.fma.* intrinsics + +// (fma x, y, (fneg z)) -> (vfnms z, x, y)) +def : Pat<(f64 (fma DPR:$Dn, DPR:$Dm, (fneg DPR:$Ddin))), + (VFNMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>, + Requires<[HasVFP4,HasDPVFP]>; +def : Pat<(f32 (fma SPR:$Sn, SPR:$Sm, (fneg SPR:$Sdin))), + (VFNMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>, + Requires<[HasVFP4]>; +// (fneg (fma (fneg x), y, z)) -> (vfnms z, x, y) +def : Pat<(fneg (f64 (fma (fneg DPR:$Dn), DPR:$Dm, DPR:$Ddin))), + (VFNMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>, + Requires<[HasVFP4,HasDPVFP]>; +def : Pat<(fneg (f32 (fma (fneg SPR:$Sn), SPR:$Sm, SPR:$Sdin))), + (VFNMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>, + Requires<[HasVFP4]>; +// (fneg (fma x, (fneg y), z) -> (vfnms z, x, y) +def : Pat<(fneg (f64 (fma DPR:$Dn, (fneg DPR:$Dm), DPR:$Ddin))), + (VFNMSD DPR:$Ddin, DPR:$Dn, DPR:$Dm)>, + Requires<[HasVFP4,HasDPVFP]>; +def : Pat<(fneg (f32 (fma SPR:$Sn, (fneg SPR:$Sm), SPR:$Sdin))), + (VFNMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>, + Requires<[HasVFP4]>; //===----------------------------------------------------------------------===// // FP Conditional moves. // let neverHasSideEffects = 1 in { -def VMOVDcc : ADuI<0b11101, 0b11, 0b0000, 0b01, 0, - (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm), - IIC_fpUNA64, "vmov", ".f64\t$Dd, $Dm", - [/*(set DPR:$Dd, (ARMcmov DPR:$Dn, DPR:$Dm, imm:$cc))*/]>, - RegConstraint<"$Dn = $Dd">; - -def VMOVScc : ASuI<0b11101, 0b11, 0b0000, 0b01, 0, - (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm), - IIC_fpUNA32, "vmov", ".f32\t$Sd, $Sm", - [/*(set SPR:$Sd, (ARMcmov SPR:$Sn, SPR:$Sm, imm:$cc))*/]>, - RegConstraint<"$Sn = $Sd">; - -def VNEGDcc : ADuI<0b11101, 0b11, 0b0001, 0b01, 0, - (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm), - IIC_fpUNA64, "vneg", ".f64\t$Dd, $Dm", - [/*(set DPR:$Dd, (ARMcneg DPR:$Dn, DPR:$Dm, imm:$cc))*/]>, - RegConstraint<"$Dn = $Dd">; - -def VNEGScc : ASuI<0b11101, 0b11, 0b0001, 0b01, 0, - (outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm), - IIC_fpUNA32, "vneg", ".f32\t$Sd, $Sm", - [/*(set SPR:$Sd, (ARMcneg SPR:$Sn, SPR:$Sm, imm:$cc))*/]>, - RegConstraint<"$Sn = $Sd">; +def VMOVDcc : PseudoInst<(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm, cmovpred:$p), + IIC_fpUNA64, + [(set (f64 DPR:$Dd), + (ARMcmov DPR:$Dn, DPR:$Dm, cmovpred:$p))]>, + RegConstraint<"$Dn = $Dd">, Requires<[HasVFP2,HasDPVFP]>; + +def VMOVScc : PseudoInst<(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm, cmovpred:$p), + IIC_fpUNA32, + [(set (f32 SPR:$Sd), + (ARMcmov SPR:$Sn, SPR:$Sm, cmovpred:$p))]>, + RegConstraint<"$Sn = $Sd">, Requires<[HasVFP2]>; } // neverHasSideEffects //===----------------------------------------------------------------------===// -// Misc. +// Move from VFP System Register to ARM core register. // -// APSR is the application level alias of CPSR. This FPSCR N, Z, C, V flags -// to APSR. -let Defs = [CPSR], Uses = [FPSCR] in -def FMSTAT : VFPAI<(outs), (ins), VFPMiscFrm, IIC_fpSTAT, - "vmrs", "\tapsr_nzcv, fpscr", - [(arm_fmstat)]> { - let Inst{27-20} = 0b11101111; - let Inst{19-16} = 0b0001; - let Inst{15-12} = 0b1111; - let Inst{11-8} = 0b1010; - let Inst{7} = 0; - let Inst{6-5} = 0b00; - let Inst{4} = 1; - let Inst{3-0} = 0b0000; -} +class MovFromVFP opc19_16, dag oops, dag iops, string opc, string asm, + list pattern>: + VFPAI { -// FPSCR <-> GPR -let hasSideEffects = 1, Uses = [FPSCR] in -def VMRS : VFPAI<(outs GPR:$Rt), (ins), VFPMiscFrm, IIC_fpSTAT, - "vmrs", "\t$Rt, fpscr", - [(set GPR:$Rt, (int_arm_get_fpscr))]> { // Instruction operand. bits<4> Rt; - // Encode instruction operand. - let Inst{15-12} = Rt; - let Inst{27-20} = 0b11101111; - let Inst{19-16} = 0b0001; + let Inst{19-16} = opc19_16; + let Inst{15-12} = Rt; let Inst{11-8} = 0b1010; let Inst{7} = 0; let Inst{6-5} = 0b00; @@ -907,10 +1551,44 @@ def VMRS : VFPAI<(outs GPR:$Rt), (ins), VFPMiscFrm, IIC_fpSTAT, let Inst{3-0} = 0b0000; } -let Defs = [FPSCR] in -def VMSR : VFPAI<(outs), (ins GPR:$src), VFPMiscFrm, IIC_fpSTAT, - "vmsr", "\tfpscr, $src", - [(int_arm_set_fpscr GPR:$src)]> { +// APSR is the application level alias of CPSR. This FPSCR N, Z, C, V flags +// to APSR. +let Defs = [CPSR], Uses = [FPSCR_NZCV], Rt = 0b1111 /* apsr_nzcv */ in +def FMSTAT : MovFromVFP<0b0001 /* fpscr */, (outs), (ins), + "vmrs", "\tAPSR_nzcv, fpscr", [(arm_fmstat)]>; + +// Application level FPSCR -> GPR +let hasSideEffects = 1, Uses = [FPSCR] in +def VMRS : MovFromVFP<0b0001 /* fpscr */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, fpscr", + [(set GPR:$Rt, (int_arm_get_fpscr))]>; + +// System level FPEXC, FPSID -> GPR +let Uses = [FPSCR] in { + def VMRS_FPEXC : MovFromVFP<0b1000 /* fpexc */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, fpexc", []>; + def VMRS_FPSID : MovFromVFP<0b0000 /* fpsid */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, fpsid", []>; + def VMRS_MVFR0 : MovFromVFP<0b0111 /* mvfr0 */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, mvfr0", []>; + def VMRS_MVFR1 : MovFromVFP<0b0110 /* mvfr1 */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, mvfr1", []>; + def VMRS_MVFR2 : MovFromVFP<0b0101 /* mvfr2 */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, mvfr2", []>, Requires<[HasFPARMv8]>; + def VMRS_FPINST : MovFromVFP<0b1001 /* fpinst */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, fpinst", []>; + def VMRS_FPINST2 : MovFromVFP<0b1010 /* fpinst2 */, (outs GPR:$Rt), (ins), + "vmrs", "\t$Rt, fpinst2", []>; +} + +//===----------------------------------------------------------------------===// +// Move from ARM core register to VFP System Register. +// + +class MovToVFP opc19_16, dag oops, dag iops, string opc, string asm, + list pattern>: + VFPAI { + // Instruction operand. bits<4> src; @@ -918,57 +1596,169 @@ def VMSR : VFPAI<(outs), (ins GPR:$src), VFPMiscFrm, IIC_fpSTAT, let Inst{15-12} = src; let Inst{27-20} = 0b11101110; - let Inst{19-16} = 0b0001; + let Inst{19-16} = opc19_16; let Inst{11-8} = 0b1010; let Inst{7} = 0; let Inst{4} = 1; } +let Defs = [FPSCR] in { + // Application level GPR -> FPSCR + def VMSR : MovToVFP<0b0001 /* fpscr */, (outs), (ins GPR:$src), + "vmsr", "\tfpscr, $src", [(int_arm_set_fpscr GPR:$src)]>; + // System level GPR -> FPEXC + def VMSR_FPEXC : MovToVFP<0b1000 /* fpexc */, (outs), (ins GPR:$src), + "vmsr", "\tfpexc, $src", []>; + // System level GPR -> FPSID + def VMSR_FPSID : MovToVFP<0b0000 /* fpsid */, (outs), (ins GPR:$src), + "vmsr", "\tfpsid, $src", []>; + + def VMSR_FPINST : MovToVFP<0b1001 /* fpinst */, (outs), (ins GPR:$src), + "vmsr", "\tfpinst, $src", []>; + def VMSR_FPINST2 : MovToVFP<0b1010 /* fpinst2 */, (outs), (ins GPR:$src), + "vmsr", "\tfpinst2, $src", []>; +} + +//===----------------------------------------------------------------------===// +// Misc. +// + // Materialize FP immediates. VFP3 only. let isReMaterializable = 1 in { def FCONSTD : VFPAI<(outs DPR:$Dd), (ins vfp_f64imm:$imm), VFPMiscFrm, IIC_fpUNA64, "vmov", ".f64\t$Dd, $imm", - [(set DPR:$Dd, vfp_f64imm:$imm)]>, Requires<[HasVFP3]> { - // Instruction operands. - bits<5> Dd; - bits<32> imm; - - // Encode instruction operands. - let Inst{15-12} = Dd{3-0}; - let Inst{22} = Dd{4}; - let Inst{19} = imm{31}; - let Inst{18-16} = imm{22-20}; - let Inst{3-0} = imm{19-16}; + [(set DPR:$Dd, vfp_f64imm:$imm)]>, + Requires<[HasVFP3,HasDPVFP]> { + bits<5> Dd; + bits<8> imm; - // Encode remaining instruction bits. let Inst{27-23} = 0b11101; + let Inst{22} = Dd{4}; let Inst{21-20} = 0b11; + let Inst{19-16} = imm{7-4}; + let Inst{15-12} = Dd{3-0}; let Inst{11-9} = 0b101; let Inst{8} = 1; // Double precision. let Inst{7-4} = 0b0000; + let Inst{3-0} = imm{3-0}; } def FCONSTS : VFPAI<(outs SPR:$Sd), (ins vfp_f32imm:$imm), VFPMiscFrm, IIC_fpUNA32, "vmov", ".f32\t$Sd, $imm", [(set SPR:$Sd, vfp_f32imm:$imm)]>, Requires<[HasVFP3]> { - // Instruction operands. - bits<5> Sd; - bits<32> imm; - - // Encode instruction operands. - let Inst{15-12} = Sd{4-1}; - let Inst{22} = Sd{0}; - let Inst{19} = imm{31}; // The immediate is handled as a double. - let Inst{18-16} = imm{22-20}; - let Inst{3-0} = imm{19-16}; + bits<5> Sd; + bits<8> imm; - // Encode remaining instruction bits. let Inst{27-23} = 0b11101; + let Inst{22} = Sd{0}; let Inst{21-20} = 0b11; + let Inst{19-16} = imm{7-4}; + let Inst{15-12} = Sd{4-1}; let Inst{11-9} = 0b101; let Inst{8} = 0; // Single precision. let Inst{7-4} = 0b0000; + let Inst{3-0} = imm{3-0}; } } + +//===----------------------------------------------------------------------===// +// Assembler aliases. +// +// A few mnemonic aliases for pre-unifixed syntax. We don't guarantee to +// support them all, but supporting at least some of the basics is +// good to be friendly. +def : VFP2MnemonicAlias<"flds", "vldr">; +def : VFP2MnemonicAlias<"fldd", "vldr">; +def : VFP2MnemonicAlias<"fmrs", "vmov">; +def : VFP2MnemonicAlias<"fmsr", "vmov">; +def : VFP2MnemonicAlias<"fsqrts", "vsqrt">; +def : VFP2MnemonicAlias<"fsqrtd", "vsqrt">; +def : VFP2MnemonicAlias<"fadds", "vadd.f32">; +def : VFP2MnemonicAlias<"faddd", "vadd.f64">; +def : VFP2MnemonicAlias<"fmrdd", "vmov">; +def : VFP2MnemonicAlias<"fmrds", "vmov">; +def : VFP2MnemonicAlias<"fmrrd", "vmov">; +def : VFP2MnemonicAlias<"fmdrr", "vmov">; +def : VFP2MnemonicAlias<"fmuls", "vmul.f32">; +def : VFP2MnemonicAlias<"fmuld", "vmul.f64">; +def : VFP2MnemonicAlias<"fnegs", "vneg.f32">; +def : VFP2MnemonicAlias<"fnegd", "vneg.f64">; +def : VFP2MnemonicAlias<"ftosizd", "vcvt.s32.f64">; +def : VFP2MnemonicAlias<"ftosid", "vcvtr.s32.f64">; +def : VFP2MnemonicAlias<"ftosizs", "vcvt.s32.f32">; +def : VFP2MnemonicAlias<"ftosis", "vcvtr.s32.f32">; +def : VFP2MnemonicAlias<"ftouizd", "vcvt.u32.f64">; +def : VFP2MnemonicAlias<"ftouid", "vcvtr.u32.f64">; +def : VFP2MnemonicAlias<"ftouizs", "vcvt.u32.f32">; +def : VFP2MnemonicAlias<"ftouis", "vcvtr.u32.f32">; +def : VFP2MnemonicAlias<"fsitod", "vcvt.f64.s32">; +def : VFP2MnemonicAlias<"fsitos", "vcvt.f32.s32">; +def : VFP2MnemonicAlias<"fuitod", "vcvt.f64.u32">; +def : VFP2MnemonicAlias<"fuitos", "vcvt.f32.u32">; +def : VFP2MnemonicAlias<"fsts", "vstr">; +def : VFP2MnemonicAlias<"fstd", "vstr">; +def : VFP2MnemonicAlias<"fmacd", "vmla.f64">; +def : VFP2MnemonicAlias<"fmacs", "vmla.f32">; +def : VFP2MnemonicAlias<"fcpys", "vmov.f32">; +def : VFP2MnemonicAlias<"fcpyd", "vmov.f64">; +def : VFP2MnemonicAlias<"fcmps", "vcmp.f32">; +def : VFP2MnemonicAlias<"fcmpd", "vcmp.f64">; +def : VFP2MnemonicAlias<"fdivs", "vdiv.f32">; +def : VFP2MnemonicAlias<"fdivd", "vdiv.f64">; +def : VFP2MnemonicAlias<"fmrx", "vmrs">; +def : VFP2MnemonicAlias<"fmxr", "vmsr">; + +// Be friendly and accept the old form of zero-compare +def : VFP2DPInstAlias<"fcmpzd${p} $val", (VCMPZD DPR:$val, pred:$p)>; +def : VFP2InstAlias<"fcmpzs${p} $val", (VCMPZS SPR:$val, pred:$p)>; + + +def : VFP2InstAlias<"fmstat${p}", (FMSTAT pred:$p)>; +def : VFP2InstAlias<"fadds${p} $Sd, $Sn, $Sm", + (VADDS SPR:$Sd, SPR:$Sn, SPR:$Sm, pred:$p)>; +def : VFP2DPInstAlias<"faddd${p} $Dd, $Dn, $Dm", + (VADDD DPR:$Dd, DPR:$Dn, DPR:$Dm, pred:$p)>; +def : VFP2InstAlias<"fsubs${p} $Sd, $Sn, $Sm", + (VSUBS SPR:$Sd, SPR:$Sn, SPR:$Sm, pred:$p)>; +def : VFP2DPInstAlias<"fsubd${p} $Dd, $Dn, $Dm", + (VSUBD DPR:$Dd, DPR:$Dn, DPR:$Dm, pred:$p)>; + +// No need for the size suffix on VSQRT. It's implied by the register classes. +def : VFP2InstAlias<"vsqrt${p} $Sd, $Sm", (VSQRTS SPR:$Sd, SPR:$Sm, pred:$p)>; +def : VFP2DPInstAlias<"vsqrt${p} $Dd, $Dm", (VSQRTD DPR:$Dd, DPR:$Dm, pred:$p)>; + +// VLDR/VSTR accept an optional type suffix. +def : VFP2InstAlias<"vldr${p}.32 $Sd, $addr", + (VLDRS SPR:$Sd, addrmode5:$addr, pred:$p)>; +def : VFP2InstAlias<"vstr${p}.32 $Sd, $addr", + (VSTRS SPR:$Sd, addrmode5:$addr, pred:$p)>; +def : VFP2InstAlias<"vldr${p}.64 $Dd, $addr", + (VLDRD DPR:$Dd, addrmode5:$addr, pred:$p)>; +def : VFP2InstAlias<"vstr${p}.64 $Dd, $addr", + (VSTRD DPR:$Dd, addrmode5:$addr, pred:$p)>; + +// VMOV can accept optional 32-bit or less data type suffix suffix. +def : VFP2InstAlias<"vmov${p}.8 $Rt, $Sn", + (VMOVRS GPR:$Rt, SPR:$Sn, pred:$p)>; +def : VFP2InstAlias<"vmov${p}.16 $Rt, $Sn", + (VMOVRS GPR:$Rt, SPR:$Sn, pred:$p)>; +def : VFP2InstAlias<"vmov${p}.32 $Rt, $Sn", + (VMOVRS GPR:$Rt, SPR:$Sn, pred:$p)>; +def : VFP2InstAlias<"vmov${p}.8 $Sn, $Rt", + (VMOVSR SPR:$Sn, GPR:$Rt, pred:$p)>; +def : VFP2InstAlias<"vmov${p}.16 $Sn, $Rt", + (VMOVSR SPR:$Sn, GPR:$Rt, pred:$p)>; +def : VFP2InstAlias<"vmov${p}.32 $Sn, $Rt", + (VMOVSR SPR:$Sn, GPR:$Rt, pred:$p)>; + +def : VFP2InstAlias<"vmov${p}.f64 $Rt, $Rt2, $Dn", + (VMOVRRD GPR:$Rt, GPR:$Rt2, DPR:$Dn, pred:$p)>; +def : VFP2InstAlias<"vmov${p}.f64 $Dn, $Rt, $Rt2", + (VMOVDRR DPR:$Dn, GPR:$Rt, GPR:$Rt2, pred:$p)>; + +// VMOVS doesn't need the .f32 to disambiguate from the NEON encoding the way +// VMOVD does. +def : VFP2InstAlias<"vmov${p} $Sd, $Sm", + (VMOVS SPR:$Sd, SPR:$Sm, pred:$p)>;