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>;
def VLDRS : ASI5<0b1101, 0b01, (outs SPR:$Sd), (ins addrmode5:$addr),
IIC_fpLoad32, "vldr", ".32\t$Sd, $addr",
- [(set SPR:$Sd, (load addrmode5:$addr))]>;
+ [(set SPR:$Sd, (load addrmode5:$addr))]> {
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
+}
} // End of 'let canFoldAsLoad = 1, isReMaterializable = 1 in'
def VSTRS : ASI5<0b1101, 0b00, (outs), (ins SPR:$Sd, addrmode5:$addr),
IIC_fpStore32, "vstr", ".32\t$Sd, $addr",
- [(store SPR:$Sd, addrmode5:$addr)]>;
+ [(store SPR:$Sd, addrmode5:$addr)]> {
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
+}
//===----------------------------------------------------------------------===//
// Load / store multiple Instructions.
//
-multiclass vfp_ldst_d_mult<string asm, bit L_bit,
- InstrItinClass itin, InstrItinClass itin_upd> {
- def ia :
- AXDI4<(outs), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
+multiclass vfp_ldst_mult<string asm, bit L_bit,
+ InstrItinClass itin, InstrItinClass itin_upd> {
+ // Double Precision
+ def DIA :
+ AXDI4<(outs), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs, variable_ops),
IndexModeNone, itin,
- !strconcat(asm, "${p}\t$Rn, $regs"), "", []> {
+ !strconcat(asm, "ia${p}\t$Rn, $regs"), "", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 0; // No writeback
let Inst{20} = L_bit;
}
- def ia_UPD :
- AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
+ def DIA_UPD :
+ AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs,
+ variable_ops),
IndexModeUpd, itin_upd,
- !strconcat(asm, "${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
+ !strconcat(asm, "ia${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
}
- def db :
- AXDI4<(outs), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
- IndexModeNone, itin,
- !strconcat(asm, "db${p}\t$Rn, $regs"), "", []> {
- let Inst{24-23} = 0b10; // Decrement Before
- let Inst{21} = 0; // No writeback
- let Inst{20} = L_bit;
- }
- def db_UPD :
- AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
+ def DDB_UPD :
+ AXDI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, dpr_reglist:$regs,
+ variable_ops),
IndexModeUpd, itin_upd,
!strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b10; // Decrement Before
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
}
-}
-multiclass vfp_ldst_s_mult<string asm, bit L_bit,
- InstrItinClass itin, InstrItinClass itin_upd> {
- def ia :
- AXSI4<(outs), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
+ // Single Precision
+ def SIA :
+ AXSI4<(outs), (ins GPR:$Rn, pred:$p, spr_reglist:$regs, variable_ops),
IndexModeNone, itin,
- !strconcat(asm, "${p}\t$Rn, $regs"), "", []> {
+ !strconcat(asm, "ia${p}\t$Rn, $regs"), "", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 0; // No writeback
let Inst{20} = L_bit;
+
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines.
+ let D = VFPNeonDomain;
}
- def ia_UPD :
- AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
+ def SIA_UPD :
+ AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs,
+ variable_ops),
IndexModeUpd, itin_upd,
- !strconcat(asm, "${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
+ !strconcat(asm, "ia${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b01; // Increment After
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
+
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines.
+ let D = VFPNeonDomain;
}
- def db :
- AXSI4<(outs), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
- IndexModeNone, itin,
- !strconcat(asm, "db${p}\t$Rn, $regs"), "", []> {
- let Inst{24-23} = 0b10; // Decrement Before
- let Inst{21} = 0; // No writeback
- let Inst{20} = L_bit;
- }
- def db_UPD :
- AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, reglist:$regs, variable_ops),
+ def SDB_UPD :
+ AXSI4<(outs GPR:$wb), (ins GPR:$Rn, pred:$p, spr_reglist:$regs,
+ variable_ops),
IndexModeUpd, itin_upd,
!strconcat(asm, "db${p}\t$Rn!, $regs"), "$Rn = $wb", []> {
let Inst{24-23} = 0b10; // Decrement Before
let Inst{21} = 1; // Writeback
let Inst{20} = L_bit;
- }
-}
-let mayLoad = 1, neverHasSideEffects = 1, hasExtraDefRegAllocReq = 1,
- isCodeGenOnly = 1 in {
-def VLDMD : AXDI4<(outs), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$dsts, variable_ops),
- IndexModeNone, IIC_fpLoad_m,
- "vldm${amode}${p}\t$Rn, $dsts", "", []> {
- let Inst{21} = 0; // wback = (W == '1')
- let Inst{20} = 1; // Load
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines.
+ let D = VFPNeonDomain;
+ }
}
-def VLDMS : AXSI4<(outs), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$dsts, variable_ops),
- IndexModeNone, IIC_fpLoad_m,
- "vldm${amode}${p}\t$Rn, $dsts", "", []> {
- let Inst{21} = 0; // wback = (W == '1')
- let Inst{20} = 1; // Load
-}
+let neverHasSideEffects = 1 in {
-def VLDMD_UPD : AXDI4<(outs GPR:$wb), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$dsts, variable_ops),
- IndexModeUpd, IIC_fpLoad_mu,
- "vldm${amode}${p}\t$Rn!, $dsts",
- "$Rn = $wb", []> {
- let Inst{21} = 1; // wback = (W == '1')
- let Inst{20} = 1; // Load
-}
+let mayLoad = 1, hasExtraDefRegAllocReq = 1 in
+defm VLDM : vfp_ldst_mult<"vldm", 1, IIC_fpLoad_m, IIC_fpLoad_mu>;
-def VLDMS_UPD : AXSI4<(outs GPR:$wb), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$dsts, variable_ops),
- IndexModeUpd, IIC_fpLoad_mu,
- "vldm${amode}${p}\t$Rn!, $dsts",
- "$Rn = $wb", []> {
- let Inst{21} = 1; // wback = (W == '1')
- let Inst{20} = 1; // Load
-}
-} // mayLoad, neverHasSideEffects, hasExtraDefRegAllocReq
-
-let mayStore = 1, neverHasSideEffects = 1, hasExtraSrcRegAllocReq = 1,
- isCodeGenOnly = 1 in {
-def VSTMD : AXDI4<(outs), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$srcs, variable_ops),
- IndexModeNone, IIC_fpStore_m,
- "vstm${amode}${p}\t$Rn, $srcs", "", []> {
- let Inst{21} = 0; // wback = (W == '1')
- let Inst{20} = 0; // Store
-}
+let mayStore = 1, hasExtraSrcRegAllocReq = 1 in
+defm VSTM : vfp_ldst_mult<"vstm", 0, IIC_fpLoad_m, IIC_fpLoad_mu>;
-def VSTMS : AXSI4<(outs), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$srcs, variable_ops), IndexModeNone,
- IIC_fpStore_m,
- "vstm${amode}${p}\t$Rn, $srcs", "", []> {
- let Inst{21} = 0; // wback = (W == '1')
- let Inst{20} = 0; // Store
-}
+} // neverHasSideEffects
-def VSTMD_UPD : AXDI4<(outs GPR:$wb), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$srcs, variable_ops),
- IndexModeUpd, IIC_fpStore_mu,
- "vstm${amode}${p}\t$Rn!, $srcs",
- "$Rn = $wb", []> {
- let Inst{21} = 1; // wback = (W == '1')
- let Inst{20} = 0; // Store
-}
+def : MnemonicAlias<"vldm", "vldmia">;
+def : MnemonicAlias<"vstm", "vstmia">;
-def VSTMS_UPD : AXSI4<(outs GPR:$wb), (ins GPR:$Rn, ldstm_mode:$amode, pred:$p,
- reglist:$srcs, variable_ops),
- IndexModeUpd, IIC_fpStore_mu,
- "vstm${amode}${p}\t$Rn!, $srcs",
- "$Rn = $wb", []> {
- let Inst{21} = 1; // wback = (W == '1')
- let Inst{20} = 0; // Store
-}
-} // mayStore, neverHasSideEffects, hasExtraSrcRegAllocReq
+def : InstAlias<"vpush${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:$r)>,
+ Requires<[HasVFP2]>;
// FLDMX, FSTMX - mixing S/D registers for pre-armv6 cores
def VADDS : ASbIn<0b11100, 0b11, 0, 0,
(outs SPR:$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:$Sm))]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VSUBD : ADbI<0b11100, 0b11, 1, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
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:$Sm))]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VDIVD : ADbI<0b11101, 0b00, 0, 0,
(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
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),
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:$Sm)))]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
// Match reassociated forms only if not sign dependent rounding.
def : Pat<(fmul (fneg DPR:$a), (f64 DPR:$b)),
def VCMPES : ASuI<0b11101, 0b11, 0b0100, 0b11, 0,
(outs), (ins SPR:$Sd, SPR:$Sm),
IIC_fpCMP32, "vcmpe", ".f32\t$Sd, $Sm",
- [(arm_cmpfp SPR:$Sd, SPR:$Sm)]>;
+ [(arm_cmpfp SPR:$Sd, SPR:$Sm)]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
// FIXME: Verify encoding after integrated assembler is working.
def VCMPD : ADuI<0b11101, 0b11, 0b0100, 0b01, 0,
def VCMPS : ASuI<0b11101, 0b11, 0b0100, 0b01, 0,
(outs), (ins SPR:$Sd, SPR:$Sm),
IIC_fpCMP32, "vcmp", ".f32\t$Sd, $Sm",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
}
+} // Defs = [FPSCR]
//===----------------------------------------------------------------------===//
// FP Unary Operations.
def VABSS : ASuIn<0b11101, 0b11, 0b0000, 0b11, 0,
(outs SPR:$Sd), (ins SPR:$Sm),
IIC_fpUNA32, "vabs", ".f32\t$Sd, $Sm",
- [(set SPR:$Sd, (fabs SPR:$Sm))]>;
+ [(set SPR:$Sd, (fabs SPR:$Sm))]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
let Defs = [FPSCR] in {
def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0,
[(arm_cmpfp0 SPR:$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.
[/* 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]
def VCVTDS : ASuI<0b11101, 0b11, 0b0111, 0b11, 0,
(outs DPR:$Dd), (ins SPR:$Sm),
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:$Sm))]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VSQRTD : ADuI<0b11101, 0b11, 0b0001, 0b11, 0,
(outs DPR:$Dd), (ins DPR:$Dm),
let Inst{6-5} = 0b00;
let Inst{3-0} = 0b0000;
+
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
}
def VMOVSR : AVConv4I<0b11100000, 0b1010,
let Inst{6-5} = 0b00;
let Inst{3-0} = 0b0000;
+
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
}
let neverHasSideEffects = 1 in {
let Inst{19-16} = Rt2;
let Inst{7-6} = 0b00;
+
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
}
def VMOVRRS : AVConv3I<0b11000101, 0b1010,
IIC_fpMOVDI, "vmov", "\t$wb, $dst2, $src1, $src2",
[/* For disassembly only; pattern left blank */]> {
let Inst{7-6} = 0b00;
+
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
}
} // neverHasSideEffects
let Inst{19-16} = Rt2;
let Inst{7-6} = 0b00;
+
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
}
let neverHasSideEffects = 1 in
IIC_fpMOVID, "vmov", "\t$dst1, $dst2, $src1, $src2",
[/* For disassembly only; pattern left blank */]> {
let Inst{7-6} = 0b00;
+
+ // Some single precision VFP instructions may be executed on both NEON and VFP
+ // pipelines.
+ let D = VFPNeonDomain;
}
// FMRDH: SPR -> GPR
IIC_fpCVTIS, "vcvt", ".f32.s32\t$Sd, $Sm",
[(set SPR:$Sd, (arm_sitof SPR:$Sm))]> {
let Inst{7} = 1; // s32
+
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
}
def VUITOD : AVConv1IDs_Encode<0b11101, 0b11, 0b1000, 0b1011,
IIC_fpCVTIS, "vcvt", ".f32.u32\t$Sd, $Sm",
[(set SPR:$Sd, (arm_uitof SPR:$Sm))]> {
let Inst{7} = 0; // u32
+
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
}
// FP -> Int:
IIC_fpCVTSI, "vcvt", ".s32.f32\t$Sd, $Sm",
[(set SPR:$Sd, (arm_ftosi SPR:$Sm))]> {
let Inst{7} = 1; // Z bit
+
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
}
def VTOUIZD : AVConv1IsD_Encode<0b11101, 0b11, 0b1100, 0b1011,
IIC_fpCVTSI, "vcvt", ".u32.f32\t$Sd, $Sm",
[(set SPR:$Sd, (arm_ftoui SPR:$Sm))]> {
let Inst{7} = 1; // Z bit
+
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
}
// And the Z bit '0' variants, i.e. use the rounding mode specified by FPSCR.
-// For disassembly only.
let Uses = [FPSCR] in {
// FIXME: Verify encoding after integrated assembler is working.
def VTOSIRD : AVConv1IsD_Encode<0b11101, 0b11, 0b1101, 0b1011,
def VTOSHS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTSI, "vcvt", ".s16.f32\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VTOUHS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTSI, "vcvt", ".u16.f32\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VTOSLS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTSI, "vcvt", ".s32.f32\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VTOULS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTSI, "vcvt", ".u32.f32\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VTOSHD : AVConv1XI<0b11101, 0b11, 0b1110, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
def VSHTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.s16\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VUHTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.u16\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VSLTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.s32\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VULTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, i32imm:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.u32\t$dst, $a, $fbits",
- [/* For disassembly only; pattern left blank */]>;
+ [/* For disassembly only; pattern left blank */]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
def VSHTOD : AVConv1XI<0b11101, 0b11, 0b1010, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, i32imm:$fbits),
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 = $Dd">,
- Requires<[HasVFP2,UseVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx]>;
def VMLAS : ASbIn<0b11100, 0b00, 0, 0,
(outs SPR:$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 = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
-def : Pat<(fadd DPR:$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:$b)),
+ Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP, UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP, UseFPVMLx]>;
def VMLSD : ADbI<0b11100, 0b00, 1, 0,
(outs DPR:$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 = $Dd">,
- Requires<[HasVFP2,UseVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx]>;
def VMLSS : ASbIn<0b11100, 0b00, 1, 0,
(outs SPR:$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 = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
-def : Pat<(fsub DPR:$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:$b)),
+ Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
def VNMLAD : ADbI<0b11100, 0b01, 1, 0,
(outs DPR:$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 = $Dd">,
- Requires<[HasVFP2,UseVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx]>;
def VNMLAS : ASbI<0b11100, 0b01, 1, 0,
(outs SPR:$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 = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
-def : Pat<(fsub (fneg (fmul DPR:$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:$dstin),
+ Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin),
(VNMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
def VNMLSD : ADbI<0b11100, 0b01, 0, 0,
(outs DPR:$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 = $Dd">,
- Requires<[HasVFP2,UseVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx]>;
def VNMLSS : ASbI<0b11100, 0b01, 0, 0,
(outs SPR:$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 = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ // Some single precision VFP instructions may be executed on both NEON and
+ // VFP pipelines on A8.
+ let D = VFPNeonA8Domain;
+}
-def : Pat<(fsub (fmul DPR:$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:$dstin),
+ Requires<[HasVFP2,UseFPVMLx]>;
+def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin),
(VNMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP,UseVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
//===----------------------------------------------------------------------===//
//
let neverHasSideEffects = 1 in {
-def VMOVDcc : ADuI<0b11101, 0b11, 0b0000, 0b01, 0,
- (outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm),
- IIC_fpUNA64, "vmov", ".f64\t$Dd, $Dm",
+def VMOVDcc : ARMPseudoInst<(outs DPR:$Dd), (ins DPR:$Dn, DPR:$Dm, pred:$p),
+ Size4Bytes, IIC_fpUNA64,
[/*(set DPR:$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, $Sm",
+def VMOVScc : ARMPseudoInst<(outs SPR:$Sd), (ins SPR:$Sn, SPR:$Sm, pred:$p),
+ Size4Bytes, IIC_fpUNA32,
[/*(set SPR:$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 = $Sd">;
} // neverHasSideEffects
//===----------------------------------------------------------------------===//
-// Misc.
+// Move from VFP System Register to ARM core register.
//
-// APSR is the application level alias of CPSR. This FPSCR N, Z, C, V flags
-// to APSR.
-let Defs = [CPSR], Uses = [FPSCR] in
-def FMSTAT : VFPAI<(outs), (ins), VFPMiscFrm, IIC_fpSTAT,
- "vmrs", "\tapsr_nzcv, fpscr",
- [(arm_fmstat)]> {
- let Inst{27-20} = 0b11101111;
- let Inst{19-16} = 0b0001;
- let Inst{15-12} = 0b1111;
- let Inst{11-8} = 0b1010;
- let Inst{7} = 0;
- let Inst{6-5} = 0b00;
- let Inst{4} = 1;
- let Inst{3-0} = 0b0000;
-}
+class MovFromVFP<bits<4> opc19_16, dag oops, dag iops, string opc, string asm,
+ list<dag> pattern>:
+ VFPAI<oops, iops, VFPMiscFrm, IIC_fpSTAT, opc, asm, pattern> {
-// FPSCR <-> GPR
-let hasSideEffects = 1, Uses = [FPSCR] in
-def VMRS : VFPAI<(outs GPR:$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;
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], 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$Rt, fpsid", []>;
+}
+
+//===----------------------------------------------------------------------===//
+// Move from ARM core register to VFP System Register.
+//
+
+class MovToVFP<bits<4> opc19_16, dag oops, dag iops, string opc, string asm,
+ list<dag> pattern>:
+ VFPAI<oops, iops, VFPMiscFrm, IIC_fpSTAT, opc, asm, pattern> {
+
// Instruction operand.
bits<4> src;
let Inst{15-12} = src;
let Inst{27-20} = 0b11101110;
- let Inst{19-16} = 0b0001;
+ let Inst{19-16} = opc19_16;
let Inst{11-8} = 0b1010;
let Inst{7} = 0;
let Inst{4} = 1;
}
+let Defs = [FPSCR] in {
+ // Application level GPR -> FPSCR
+ def VMSR : MovToVFP<0b0001 /* fpscr */, (outs), (ins GPR:$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, $src", []>;
+}
+
+//===----------------------------------------------------------------------===//
+// Misc.
+//
+
// Materialize FP immediates. VFP3 only.
let isReMaterializable = 1 in {
def FCONSTD : VFPAI<(outs DPR:$Dd), (ins vfp_f64imm:$imm),
projects / oota-llvm.git / blobdiff