Skip to content

Commit

Permalink
[AArch64][SVE] Remove false register dependency for unary FP convert …
Browse files Browse the repository at this point in the history 
…operations

Generate movprfx for floating point convert zeroing pseudo operations

Differential Revision: https://reviews.llvm.org/D118617

(cherry picked from commit 6b73a4c)
  • Loading branch information
@MDevereau @llvmbot
MDevereau authored and llvmbot committed Feb 7, 2022
1 parent 0f27bf2 commit 2bae96d
Show file tree
Hide file tree
Showing 5 changed files with 470 additions and 45 deletions.
53 changes: 27 additions & 26 deletions llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1679,60 +1679,61 @@ let Predicates = [HasSVEorStreamingSVE] in {
defm FCVTZS_ZPmZ_DtoD : sve_fp_2op_p_zd< 0b1111110, "fcvtzs", ZPR64, ZPR64, null_frag, AArch64fcvtzs_mt, nxv2i64, nxv2i1, nxv2f64, ElementSizeD>;
defm FCVTZU_ZPmZ_DtoD : sve_fp_2op_p_zd< 0b1111111, "fcvtzu", ZPR64, ZPR64, null_frag, AArch64fcvtzu_mt, nxv2i64, nxv2i1, nxv2f64, ElementSizeD>;

def : Pat<(nxv2f32 (AArch64fcvte_mt (nxv2i1 PPR:$Pg), (nxv2f16 ZPR:$Zs), (nxv2f32 ZPR:$Zd))),
(FCVT_ZPmZ_HtoS ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
//These patterns exist to improve the code quality of conversions on unpacked types.
def : Pat<(nxv2f32 (AArch64fcvte_mt (nxv2i1 (SVEAllActive):$Pg), (nxv2f16 ZPR:$Zs), (nxv2f32 ZPR:$Zd))),
(FCVT_ZPmZ_HtoS_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

// FP_ROUND has an additional 'precise' flag which indicates the type of rounding.
// This is ignored by the pattern below where it is matched by (i64 timm0_1)
def : Pat<(nxv2f16 (AArch64fcvtr_mt (nxv2i1 PPR:$Pg), (nxv2f32 ZPR:$Zs), (i64 timm0_1), (nxv2f16 ZPR:$Zd))),
(FCVT_ZPmZ_StoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
def : Pat<(nxv2f16 (AArch64fcvtr_mt (nxv2i1 (SVEAllActive):$Pg), (nxv2f32 ZPR:$Zs), (i64 timm0_1), (nxv2f16 ZPR:$Zd))),
(FCVT_ZPmZ_StoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

// Floating-point -> signed integer
def : Pat<(nxv2f16 (AArch64scvtf_mt (nxv2i1 PPR:$Pg),
// Signed integer -> Floating-point
def : Pat<(nxv2f16 (AArch64scvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(sext_inreg (nxv2i64 ZPR:$Zs), nxv2i16), (nxv2f16 ZPR:$Zd))),
(SCVTF_ZPmZ_HtoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(SCVTF_ZPmZ_HtoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv4f16 (AArch64scvtf_mt (nxv4i1 PPR:$Pg),
def : Pat<(nxv4f16 (AArch64scvtf_mt (nxv4i1 (SVEAllActive):$Pg),
(sext_inreg (nxv4i32 ZPR:$Zs), nxv4i16), (nxv4f16 ZPR:$Zd))),
(SCVTF_ZPmZ_HtoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(SCVTF_ZPmZ_HtoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv2f16 (AArch64scvtf_mt (nxv2i1 PPR:$Pg),
def : Pat<(nxv2f16 (AArch64scvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(sext_inreg (nxv2i64 ZPR:$Zs), nxv2i32), (nxv2f16 ZPR:$Zd))),
(SCVTF_ZPmZ_StoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(SCVTF_ZPmZ_StoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv2f32 (AArch64scvtf_mt (nxv2i1 PPR:$Pg),
def : Pat<(nxv2f32 (AArch64scvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(sext_inreg (nxv2i64 ZPR:$Zs), nxv2i32), (nxv2f32 ZPR:$Zd))),
(SCVTF_ZPmZ_StoS ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(SCVTF_ZPmZ_StoS_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv2f64 (AArch64scvtf_mt (nxv2i1 PPR:$Pg),
def : Pat<(nxv2f64 (AArch64scvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(sext_inreg (nxv2i64 ZPR:$Zs), nxv2i32), (nxv2f64 ZPR:$Zd))),
(SCVTF_ZPmZ_StoD ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(SCVTF_ZPmZ_StoD_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

// Floating-point -> unsigned integer
def : Pat<(nxv2f16 (AArch64ucvtf_mt (nxv2i1 PPR:$Pg),
// Unsigned integer -> Floating-point
def : Pat<(nxv2f16 (AArch64ucvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(and (nxv2i64 ZPR:$Zs),
(nxv2i64 (AArch64dup (i64 0xFFFF)))), (nxv2f16 ZPR:$Zd))),
(UCVTF_ZPmZ_HtoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(UCVTF_ZPmZ_HtoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv2f16 (AArch64ucvtf_mt (nxv2i1 PPR:$Pg),
def : Pat<(nxv2f16 (AArch64ucvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(and (nxv2i64 ZPR:$Zs),
(nxv2i64 (AArch64dup (i64 0xFFFFFFFF)))), (nxv2f16 ZPR:$Zd))),
(UCVTF_ZPmZ_StoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(UCVTF_ZPmZ_StoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv4f16 (AArch64ucvtf_mt (nxv4i1 PPR:$Pg),
def : Pat<(nxv4f16 (AArch64ucvtf_mt (nxv4i1 (SVEAllActive):$Pg),
(and (nxv4i32 ZPR:$Zs),
(nxv4i32 (AArch64dup (i32 0xFFFF)))), (nxv4f16 ZPR:$Zd))),
(UCVTF_ZPmZ_HtoH ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(UCVTF_ZPmZ_HtoH_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv2f32 (AArch64ucvtf_mt (nxv2i1 PPR:$Pg),
def : Pat<(nxv2f32 (AArch64ucvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(and (nxv2i64 ZPR:$Zs),
(nxv2i64 (AArch64dup (i64 0xFFFFFFFF)))), (nxv2f32 ZPR:$Zd))),
(UCVTF_ZPmZ_StoS ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(UCVTF_ZPmZ_StoS_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

def : Pat<(nxv2f64 (AArch64ucvtf_mt (nxv2i1 PPR:$Pg),
def : Pat<(nxv2f64 (AArch64ucvtf_mt (nxv2i1 (SVEAllActive):$Pg),
(and (nxv2i64 ZPR:$Zs),
(nxv2i64 (AArch64dup (i64 0xFFFFFFFF)))), (nxv2f64 ZPR:$Zd))),
(UCVTF_ZPmZ_StoD ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;
(UCVTF_ZPmZ_StoD_UNDEF ZPR:$Zd, PPR:$Pg, ZPR:$Zs)>;

defm FRINTN_ZPmZ : sve_fp_2op_p_zd_HSD<0b00000, "frintn", AArch64frintn_mt>;
defm FRINTP_ZPmZ : sve_fp_2op_p_zd_HSD<0b00001, "frintp", AArch64frintp_mt>;
Expand Down
25 changes: 20 additions & 5 deletions llvm/lib/Target/AArch64/SVEInstrFormats.td
View file
Original file line number Diff line number Diff line change
Expand Up @@ -370,6 +370,14 @@ class SVE_1_Op_Passthru_Round_Pat<ValueType vtd, SDPatternOperator op, ValueType
: Pat<(vtd (op pg:$Op1, vts:$Op2, (i64 timm0_1), vtd:$Op3)),
(inst $Op3, $Op1, $Op2)>;

multiclass SVE_1_Op_PassthruUndef_Round_Pat<ValueType vtd, SDPatternOperator op, ValueType pg,
ValueType vts, Instruction inst>{
def : Pat<(vtd (op pg:$Op1, vts:$Op2, (i64 timm0_1), (vtd undef))),
(inst (IMPLICIT_DEF), $Op1, $Op2)>;
def : Pat<(vtd (op (pg (SVEAllActive:$Op1)), vts:$Op2, (i64 timm0_1), vtd:$Op3)),
(inst $Op3, $Op1, $Op2)>;
}

class SVE_1_Op_Imm_OptLsl_Reverse_Pat<ValueType vt, SDPatternOperator op, ZPRRegOp zprty,
ValueType it, ComplexPattern cpx, Instruction inst>
: Pat<(vt (op (vt (AArch64dup (it (cpx i32:$imm, i32:$shift)))), (vt zprty:$Op1))),
Expand Down Expand Up @@ -2589,8 +2597,8 @@ multiclass sve_fp_2op_p_zd<bits<7> opc, string asm,
SDPatternOperator int_op,
SDPatternOperator ir_op, ValueType vt1,
ValueType vt2, ValueType vt3, ElementSizeEnum Sz> {
def NAME : sve_fp_2op_p_zd<opc, asm, i_zprtype, o_zprtype, Sz>;

def NAME : sve_fp_2op_p_zd<opc, asm, i_zprtype, o_zprtype, Sz>,
SVEPseudo2Instr<NAME, 1>;
// convert vt1 to a packed type for the intrinsic patterns
defvar packedvt1 = !cond(!eq(!cast<string>(vt1), "nxv2f16"): nxv8f16,
!eq(!cast<string>(vt1), "nxv4f16"): nxv8f16,
Expand All @@ -2604,8 +2612,11 @@ multiclass sve_fp_2op_p_zd<bits<7> opc, string asm,
1 : vt3);

def : SVE_3_Op_Pat<packedvt1, int_op, packedvt1, vt2, packedvt3, !cast<Instruction>(NAME)>;

def : SVE_1_Op_Passthru_Pat<vt1, ir_op, vt2, vt3, !cast<Instruction>(NAME)>;

def _UNDEF : PredOneOpPassthruPseudo<NAME, !cast<ZPRRegOp>(i_zprtype)>;

defm : SVE_1_Op_PassthruUndef_Pat<vt1, ir_op, vt2, vt3, !cast<Instruction>(NAME # _UNDEF)>;
}

multiclass sve_fp_2op_p_zdr<bits<7> opc, string asm,
Expand All @@ -2614,7 +2625,8 @@ multiclass sve_fp_2op_p_zdr<bits<7> opc, string asm,
SDPatternOperator int_op,
SDPatternOperator ir_op, ValueType vt1,
ValueType vt2, ValueType vt3, ElementSizeEnum Sz> {
def NAME : sve_fp_2op_p_zd<opc, asm, i_zprtype, o_zprtype, Sz>;
def NAME : sve_fp_2op_p_zd<opc, asm, i_zprtype, o_zprtype, Sz>,
SVEPseudo2Instr<NAME, 1>;

// convert vt1 to a packed type for the intrinsic patterns
defvar packedvt1 = !cond(!eq(!cast<string>(vt1), "nxv2f16"): nxv8f16,
Expand All @@ -2623,8 +2635,11 @@ multiclass sve_fp_2op_p_zdr<bits<7> opc, string asm,
1 : vt1);

def : SVE_3_Op_Pat<packedvt1, int_op, packedvt1, vt2, vt3, !cast<Instruction>(NAME)>;

def : SVE_1_Op_Passthru_Round_Pat<vt1, ir_op, vt2, vt3, !cast<Instruction>(NAME)>;

def _UNDEF : PredOneOpPassthruPseudo<NAME, !cast<ZPRRegOp>(i_zprtype)>;

defm : SVE_1_Op_PassthruUndef_Round_Pat<vt1, ir_op, vt2, vt3, !cast<Instruction>(NAME # _UNDEF)>;
}

multiclass sve_fp_2op_p_zd_HSD<bits<5> opc, string asm, SDPatternOperator op> {
Expand Down
Loading

0 comments on commit 2bae96d

Please sign in to comment.