-//===- ARMInstrVFP.td - VFP support for ARM ----------------*- tablegen -*-===//
+//===-- ARMInstrVFP.td - VFP support for ARM ---------------*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
let ParserMatchClass = FPImmOperand;
}
+def alignedload32 : PatFrag<(ops node:$ptr), (load node:$ptr), [{
+ return cast<LoadSDNode>(N)->getAlignment() >= 4;
+}]>;
+
+def alignedstore32 : PatFrag<(ops node:$val, node:$ptr),
+ (store node:$val, node:$ptr), [{
+ return cast<StoreSDNode>(N)->getAlignment() >= 4;
+}]>;
+
// The VCVT to/from fixed-point instructions encode the 'fbits' operand
// (the number of fixed bits) differently than it appears in the assembly
// source. It's encoded as "Size - fbits" where Size is the size of the
def VLDRD : ADI5<0b1101, 0b01, (outs DPR:$Dd), (ins addrmode5:$addr),
IIC_fpLoad64, "vldr", "\t$Dd, $addr",
- [(set DPR:$Dd, (f64 (load addrmode5:$addr)))]>;
+ [(set DPR:$Dd, (f64 (alignedload32 addrmode5:$addr)))]>;
def VLDRS : ASI5<0b1101, 0b01, (outs SPR:$Sd), (ins addrmode5:$addr),
IIC_fpLoad32, "vldr", "\t$Sd, $addr",
def VSTRD : ADI5<0b1101, 0b00, (outs), (ins DPR:$Dd, addrmode5:$addr),
IIC_fpStore64, "vstr", "\t$Dd, $addr",
- [(store (f64 DPR:$Dd), addrmode5:$addr)]>;
+ [(alignedstore32 (f64 DPR:$Dd), addrmode5:$addr)]>;
def VSTRS : ASI5<0b1101, 0b00, (outs), (ins SPR:$Sd, addrmode5:$addr),
IIC_fpStore32, "vstr", "\t$Sd, $addr",
Requires<[HasVFP2]>;
def : InstAlias<"vpop${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:$r)>;
// FLDMX, FSTMX - mixing S/D registers for pre-armv6 cores
// FP Binary Operations.
//
+let TwoOperandAliasConstraint = "$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, $Sm",
let D = VFPNeonA8Domain;
}
+let TwoOperandAliasConstraint = "$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, $Sm",
let D = VFPNeonA8Domain;
}
+let TwoOperandAliasConstraint = "$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, $Sm",
(VNMULS SPR:$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, $Dm",
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
-} // Defs = [FPSCR]
+} // Defs = [FPSCR_NZCV]
//===----------------------------------------------------------------------===//
// FP Unary Operations.
let D = VFPNeonA8Domain;
}
-let Defs = [FPSCR] in {
+let Defs = [FPSCR_NZCV] in {
def VCMPEZD : ADuI<0b11101, 0b11, 0b0101, 0b11, 0,
(outs), (ins DPR:$Dd),
IIC_fpCMP64, "vcmpe", ".f64\t$Dd, #0",
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
}
-} // Defs = [FPSCR]
+} // Defs = [FPSCR_NZCV]
def VCVTDS : ASuI<0b11101, 0b11, 0b0111, 0b11, 0,
(outs DPR:$Dd), (ins SPR:$Sm),
// Between half-precision and single-precision. For disassembly only.
// FIXME: Verify encoding after integrated assembler is working.
-def VCVTBSH: ASuI<0b11101, 0b11, 0b0010, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm),
+def VCVTBHS: ASuI<0b11101, 0b11, 0b0010, 0b01, 0, (outs SPR:$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:$a), GPR))>;
-
-def VCVTBHS: ASuI<0b11101, 0b11, 0b0011, 0b01, 0, (outs SPR:$Sd), (ins SPR:$Sm),
+def VCVTBSH: ASuI<0b11101, 0b11, 0b0011, 0b01, 0, (outs SPR:$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:$a), GPR))>;
-def VCVTTSH: ASuI<0b11101, 0b11, 0b0010, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
+def : Pat<(f16_to_f32 GPR:$a),
+ (VCVTBHS (COPY_TO_REGCLASS GPR:$a, SPR))>;
+
+def VCVTTHS: ASuI<0b11101, 0b11, 0b0010, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
/* FIXME */ IIC_fpCVTSH, "vcvtt", ".f32.f16\t$Sd, $Sm",
[/* For disassembly only; pattern left blank */]>;
-def VCVTTHS: ASuI<0b11101, 0b11, 0b0011, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
+def VCVTTSH: ASuI<0b11101, 0b11, 0b0011, 0b11, 0, (outs SPR:$Sd), (ins SPR:$Sm),
/* FIXME */ IIC_fpCVTHS, "vcvtt", ".f16.f32\t$Sd, $Sm",
[/* For disassembly only; pattern left blank */]>;
let D = VFPNeonDomain;
}
+// Bitcast i32 -> f32. NEON prefers to use VMOVDRR.
def VMOVSR : AVConv4I<0b11100000, 0b1010,
(outs SPR:$Sn), (ins GPR:$Rt),
IIC_fpMOVIS, "vmov", "\t$Sn, $Rt",
- [(set SPR:$Sn, (bitconvert GPR:$Rt))]> {
+ [(set SPR:$Sn, (bitconvert GPR:$Rt))]>,
+ Requires<[HasVFP2, UseVMOVSR]> {
// Instruction operands.
bits<5> Sn;
bits<4> Rt;
bits<4> Rt2;
// Encode instruction operands.
- let Inst{3-0} = src1{3-0};
- let Inst{5} = src1{4};
+ let Inst{3-0} = src1{4-1};
+ let Inst{5} = src1{0};
let Inst{15-12} = Rt;
let Inst{19-16} = Rt2;
bits<4> src2;
// Encode instruction operands.
- let Inst{3-0} = dst1{3-0};
- let Inst{5} = dst1{4};
+ let Inst{3-0} = dst1{4-1};
+ let Inst{5} = dst1{0};
let Inst{15-12} = src1;
let Inst{19-16} = src2;
// FP to Fixed-Point:
-def VTOSHS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 0,
+// Single Precision register
+class AVConv1XInsS_Encode<bits<5> op1, bits<2> op2, bits<4> op3, bits<4> op4,
+ bit op5, dag oops, dag iops, InstrItinClass itin,
+ string opc, string asm, list<dag> pattern>
+ : AVConv1XI<op1, op2, op3, op4, op5, oops, iops, itin, opc, asm, pattern> {
+ bits<5> dst;
+ // if dp_operation then UInt(D:Vd) else UInt(Vd:D);
+ let Inst{22} = dst{0};
+ let Inst{15-12} = dst{4-1};
+}
+
+// Double Precision register
+class AVConv1XInsD_Encode<bits<5> op1, bits<2> op2, bits<4> op3, bits<4> op4,
+ bit op5, dag oops, dag iops, InstrItinClass itin,
+ string opc, string asm, list<dag> pattern>
+ : AVConv1XI<op1, op2, op3, op4, op5, oops, iops, itin, opc, asm, pattern> {
+ bits<5> dst;
+ // if dp_operation then UInt(D:Vd) else UInt(Vd:D);
+ let Inst{22} = dst{4};
+ let Inst{15-12} = dst{3-0};
+}
+
+def VTOSHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTSI, "vcvt", ".s16.f32\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VTOUHS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 0,
+def VTOUHS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTSI, "vcvt", ".u16.f32\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VTOSLS : AVConv1XI<0b11101, 0b11, 0b1110, 0b1010, 1,
+def VTOSLS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1110, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTSI, "vcvt", ".s32.f32\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VTOULS : AVConv1XI<0b11101, 0b11, 0b1111, 0b1010, 1,
+def VTOULS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1111, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTSI, "vcvt", ".u32.f32\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VTOSHD : AVConv1XI<0b11101, 0b11, 0b1110, 0b1011, 0,
+def VTOSHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTDI, "vcvt", ".s16.f64\t$dst, $a, $fbits", []>;
-def VTOUHD : AVConv1XI<0b11101, 0b11, 0b1111, 0b1011, 0,
+def VTOUHD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTDI, "vcvt", ".u16.f64\t$dst, $a, $fbits", []>;
-def VTOSLD : AVConv1XI<0b11101, 0b11, 0b1110, 0b1011, 1,
+def VTOSLD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1110, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTDI, "vcvt", ".s32.f64\t$dst, $a, $fbits", []>;
-def VTOULD : AVConv1XI<0b11101, 0b11, 0b1111, 0b1011, 1,
+def VTOULD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1111, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTDI, "vcvt", ".u32.f64\t$dst, $a, $fbits", []>;
// Fixed-Point to FP:
-def VSHTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 0,
+def VSHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.s16\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VUHTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 0,
+def VUHTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 0,
(outs SPR:$dst), (ins SPR:$a, fbits16:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.u16\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VSLTOS : AVConv1XI<0b11101, 0b11, 0b1010, 0b1010, 1,
+def VSLTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1010, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.s32\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VULTOS : AVConv1XI<0b11101, 0b11, 0b1011, 0b1010, 1,
+def VULTOS : AVConv1XInsS_Encode<0b11101, 0b11, 0b1011, 0b1010, 1,
(outs SPR:$dst), (ins SPR:$a, fbits32:$fbits),
IIC_fpCVTIS, "vcvt", ".f32.u32\t$dst, $a, $fbits", []> {
// Some single precision VFP instructions may be executed on both NEON and
let D = VFPNeonA8Domain;
}
-def VSHTOD : AVConv1XI<0b11101, 0b11, 0b1010, 0b1011, 0,
+def VSHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTID, "vcvt", ".f64.s16\t$dst, $a, $fbits", []>;
-def VUHTOD : AVConv1XI<0b11101, 0b11, 0b1011, 0b1011, 0,
+def VUHTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 0,
(outs DPR:$dst), (ins DPR:$a, fbits16:$fbits),
IIC_fpCVTID, "vcvt", ".f64.u16\t$dst, $a, $fbits", []>;
-def VSLTOD : AVConv1XI<0b11101, 0b11, 0b1010, 0b1011, 1,
+def VSLTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1010, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTID, "vcvt", ".f64.s32\t$dst, $a, $fbits", []>;
-def VULTOD : AVConv1XI<0b11101, 0b11, 0b1011, 0b1011, 1,
+def VULTOD : AVConv1XInsD_Encode<0b11101, 0b11, 0b1011, 0b1011, 1,
(outs DPR:$dst), (ins DPR:$a, fbits32:$fbits),
IIC_fpCVTID, "vcvt", ".f64.u32\t$dst, $a, $fbits", []>;
[(set DPR:$Dd, (fadd_mlx (fmul_su DPR:$Dn, DPR:$Dm),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def VMLAS : ASbIn<0b11100, 0b00, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
[(set SPR:$Sd, (fadd_mlx (fmul_su SPR:$Sn, SPR:$Sm),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
def : Pat<(fadd_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
(VMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fadd_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP, UseFPVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP, UseFPVMLx,DontUseFusedMAC]>;
def VMLSD : ADbI<0b11100, 0b00, 1, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
[(set DPR:$Dd, (fadd_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def VMLSS : ASbIn<0b11100, 0b00, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
[(set SPR:$Sd, (fadd_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
def : Pat<(fsub_mlx DPR:$dstin, (fmul_su DPR:$a, (f64 DPR:$b))),
(VMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fsub_mlx SPR:$dstin, (fmul_su SPR:$a, SPR:$b)),
(VMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>;
def VNMLAD : ADbI<0b11100, 0b01, 1, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
[(set DPR:$Dd,(fsub_mlx (fneg (fmul_su DPR:$Dn,DPR:$Dm)),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def VNMLAS : ASbI<0b11100, 0b01, 1, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
[(set SPR:$Sd, (fsub_mlx (fneg (fmul_su SPR:$Sn, SPR:$Sm)),
SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
def : Pat<(fsub_mlx (fneg (fmul_su DPR:$a, (f64 DPR:$b))), DPR:$dstin),
(VNMLAD DPR:$dstin, DPR:$a, DPR:$b)>,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fsub_mlx (fneg (fmul_su SPR:$a, SPR:$b)), SPR:$dstin),
(VNMLAS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>;
def VNMLSD : ADbI<0b11100, 0b01, 0, 0,
(outs DPR:$Dd), (ins DPR:$Ddin, DPR:$Dn, DPR:$Dm),
[(set DPR:$Dd, (fsub_mlx (fmul_su DPR:$Dn, DPR:$Dm),
(f64 DPR:$Ddin)))]>,
RegConstraint<"$Ddin = $Dd">,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def VNMLSS : ASbI<0b11100, 0b01, 0, 0,
(outs SPR:$Sd), (ins SPR:$Sdin, SPR:$Sn, SPR:$Sm),
IIC_fpMAC32, "vnmls", ".f32\t$Sd, $Sn, $Sm",
[(set SPR:$Sd, (fsub_mlx (fmul_su SPR:$Sn, SPR:$Sm), SPR:$Sdin))]>,
RegConstraint<"$Sdin = $Sd">,
- Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]> {
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]> {
// Some single precision VFP instructions may be executed on both NEON and
// VFP pipelines on A8.
let D = VFPNeonA8Domain;
def : Pat<(fsub_mlx (fmul_su DPR:$a, (f64 DPR:$b)), DPR:$dstin),
(VNMLSD DPR:$dstin, DPR:$a, DPR:$b)>,
- Requires<[HasVFP2,UseFPVMLx]>;
+ Requires<[HasVFP2,UseFPVMLx,DontUseFusedMAC]>;
def : Pat<(fsub_mlx (fmul_su SPR:$a, SPR:$b), SPR:$dstin),
(VNMLSS SPR:$dstin, SPR:$a, SPR:$b)>,
- Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx]>;
+ Requires<[HasVFP2,DontUseNEONForFP,UseFPVMLx,DontUseFusedMAC]>;
+
+//===----------------------------------------------------------------------===//
+// Fused FP Multiply-Accumulate Operations.
+//
+def VFMAD : ADbI<0b11101, 0b10, 0, 0,
+ (outs DPR:$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 = $Dd">,
+ Requires<[HasVFP4,UseFusedMAC]>;
+
+def VFMAS : ASbIn<0b11101, 0b10, 0, 0,
+ (outs SPR:$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:$b)>,
+ Requires<[HasVFP4,UseFusedMAC]>;
+def : Pat<(fadd_mlx SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(f32 (fma SPR:$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 = $Dd">,
+ Requires<[HasVFP4,UseFusedMAC]>;
+
+def VFMSS : ASbIn<0b11101, 0b10, 1, 0,
+ (outs SPR:$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:$b)>,
+ Requires<[HasVFP4,UseFusedMAC]>;
+def : Pat<(fsub_mlx SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(f32 (fma (fneg SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(f32 (fma SPR:$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 = $Dd">,
+ Requires<[HasVFP4,UseFusedMAC]>;
+
+def VFNMAS : ASbI<0b11101, 0b01, 1, 0,
+ (outs SPR:$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:$b)>,
+ Requires<[HasVFP4,UseFusedMAC]>;
+def : Pat<(fsub_mlx (fneg (fmul_su SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(fneg (fma (f32 SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(f32 (fma (fneg SPR:$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 = $Dd">,
+ Requires<[HasVFP4,UseFusedMAC]>;
+
+def VFNMSS : ASbI<0b11101, 0b01, 0, 0,
+ (outs SPR:$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:$b)>,
+ Requires<[HasVFP4,UseFusedMAC]>;
+def : Pat<(fsub_mlx (fmul_su SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(f32 (fma SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(fneg (f32 (fma (fneg SPR:$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:$Dm)>,
+ Requires<[HasVFP4]>;
+def : Pat<(fneg (f32 (fma SPR:$Sn, (fneg SPR:$Sm), SPR:$Sdin))),
+ (VFNMSS SPR:$Sdin, SPR:$Sn, SPR:$Sm)>,
+ Requires<[HasVFP4]>;
//===----------------------------------------------------------------------===//
// FP Conditional moves.
// APSR is the application level alias of CPSR. This FPSCR N, Z, C, V flags
// to APSR.
-let Defs = [CPSR], Uses = [FPSCR], Rt = 0b1111 /* apsr_nzcv */ in
+let Defs = [CPSR], Uses = [FPSCR_NZCV], Rt = 0b1111 /* apsr_nzcv */ in
def FMSTAT : MovFromVFP<0b0001 /* fpscr */, (outs), (ins),
- "vmrs", "\tapsr_nzcv, fpscr", [(arm_fmstat)]>;
+ "vmrs", "\tAPSR_nzcv, fpscr", [(arm_fmstat)]>;
// Application level FPSCR -> GPR
let hasSideEffects = 1, Uses = [FPSCR] in
"vmrs", "\t$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 : 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 : VFP2InstAlias<"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, $Sm",
def : VFP2InstAlias<"vstr${p}.64 $Dd, $addr",
(VSTRD DPR:$Dd, addrmode5:$addr, pred:$p)>;
-// VMUL has a two-operand form (implied destination operand)
-def : VFP2InstAlias<"vmul${p}.f64 $Dn, $Dm",
- (VMULD DPR:$Dn, DPR:$Dn, DPR:$Dm, pred:$p)>;
-def : VFP2InstAlias<"vmul${p}.f32 $Sn, $Sm",
- (VMULS SPR:$Sn, SPR:$Sn, SPR:$Sm, pred:$p)>;
-// VADD has a two-operand form (implied destination operand)
-def : VFP2InstAlias<"vadd${p}.f64 $Dn, $Dm",
- (VADDD DPR:$Dn, DPR:$Dn, DPR:$Dm, pred:$p)>;
-def : VFP2InstAlias<"vadd${p}.f32 $Sn, $Sm",
- (VADDS SPR:$Sn, SPR:$Sn, SPR:$Sm, pred:$p)>;
-// VSUB has a two-operand form (implied destination operand)
-def : VFP2InstAlias<"vsub${p}.f64 $Dn, $Dm",
- (VSUBD DPR:$Dn, DPR:$Dn, DPR:$Dm, pred:$p)>;
-def : VFP2InstAlias<"vsub${p}.f32 $Sn, $Sm",
- (VSUBS SPR:$Sn, SPR:$Sn, SPR:$Sm, 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)>;