OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

[AArch64][SVE] Add lowering for llvm fceil 

Add the functionality to lower fceil for passthru variant

Reviewed By: paulwalker-arm

Differential Revision: https://reviews.llvm.org/D84548
This commit is contained in:
Muhammad Asif Manzoor 2020-08-26 15:36:26 -04:00 committed by Danilo C. Grael
parent d1e6103a79
commit fd536eeed9
5 changed files with 86 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -138,6 +138,7 @@ static bool isMergePassthruOpcode(unsigned Opc) {
case AArch64ISD::FNEG_MERGE_PASSTHRU:
case AArch64ISD::SIGN_EXTEND_INREG_MERGE_PASSTHRU:
case AArch64ISD::ZERO_EXTEND_INREG_MERGE_PASSTHRU:
case AArch64ISD::FCEIL_MERGE_PASSTHRU:
return true;
}
}
@ -972,6 +973,7 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FMUL, VT, Custom);
setOperationAction(ISD::FNEG, VT, Custom);
setOperationAction(ISD::FSUB, VT, Custom);
setOperationAction(ISD::FCEIL, VT, Custom);
}
}
@ -1476,6 +1478,7 @@ const char *AArch64TargetLowering::getTargetNodeName(unsigned Opcode) const {
MAKE_CASE(AArch64ISD::FNEG_MERGE_PASSTHRU)
MAKE_CASE(AArch64ISD::SIGN_EXTEND_INREG_MERGE_PASSTHRU)
MAKE_CASE(AArch64ISD::ZERO_EXTEND_INREG_MERGE_PASSTHRU)
MAKE_CASE(AArch64ISD::FCEIL_MERGE_PASSTHRU)
MAKE_CASE(AArch64ISD::SETCC_MERGE_ZERO)
MAKE_CASE(AArch64ISD::ADC)
MAKE_CASE(AArch64ISD::SBC)
@ -3337,6 +3340,9 @@ SDValue AArch64TargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
case Intrinsic::aarch64_sve_fneg:
return DAG.getNode(AArch64ISD::FNEG_MERGE_PASSTHRU, dl, Op.getValueType(),
Op.getOperand(2), Op.getOperand(3), Op.getOperand(1));
case Intrinsic::aarch64_sve_frintp:
return DAG.getNode(AArch64ISD::FCEIL_MERGE_PASSTHRU, dl, Op.getValueType(),
Op.getOperand(2), Op.getOperand(3), Op.getOperand(1));
case Intrinsic::aarch64_sve_convert_to_svbool: {
EVT OutVT = Op.getValueType();
EVT InVT = Op.getOperand(1).getValueType();
@ -3633,6 +3639,8 @@ SDValue AArch64TargetLowering::LowerOperation(SDValue Op,
return LowerToPredicatedOp(Op, DAG, AArch64ISD::FDIV_PRED);
case ISD::FNEG:
return LowerToPredicatedOp(Op, DAG, AArch64ISD::FNEG_MERGE_PASSTHRU);
case ISD::FCEIL:
return LowerToPredicatedOp(Op, DAG, AArch64ISD::FCEIL_MERGE_PASSTHRU);
case ISD::FP_ROUND:
case ISD::STRICT_FP_ROUND:
return LowerFP_ROUND(Op, DAG);

1
llvm/lib/Target/AArch64/AArch64ISelLowering.h
View File

@ -95,6 +95,7 @@ enum NodeType : unsigned {
// Predicated instructions with the result of inactive lanes provided by the
// last operand.
FCEIL_MERGE_PASSTHRU,
FNEG_MERGE_PASSTHRU,
SIGN_EXTEND_INREG_MERGE_PASSTHRU,
ZERO_EXTEND_INREG_MERGE_PASSTHRU,

3
llvm/lib/Target/AArch64/AArch64SVEInstrInfo.td
View File

@ -202,6 +202,7 @@ def SDT_AArch64IntExtend : SDTypeProfile<1, 4, [
def AArch64fneg_mt : SDNode<"AArch64ISD::FNEG_MERGE_PASSTHRU", SDT_AArch64Arith>;
def AArch64sxt_mt : SDNode<"AArch64ISD::SIGN_EXTEND_INREG_MERGE_PASSTHRU", SDT_AArch64IntExtend>;
def AArch64uxt_mt : SDNode<"AArch64ISD::ZERO_EXTEND_INREG_MERGE_PASSTHRU", SDT_AArch64IntExtend>;
def AArch64frintp_mt : SDNode<"AArch64ISD::FCEIL_MERGE_PASSTHRU", SDT_AArch64Arith>;
def SDT_AArch64ReduceWithInit : SDTypeProfile<1, 3, [SDTCisVec<1>, SDTCisVec<3>]>;
def AArch64clasta_n : SDNode<"AArch64ISD::CLASTA_N", SDT_AArch64ReduceWithInit>;
@ -1416,7 +1417,7 @@ multiclass sve_prefetch<SDPatternOperator prefetch, ValueType PredTy, Instructio
defm FCVTZU_ZPmZ_DtoD : sve_fp_2op_p_zd<0b1111111, "fcvtzu", ZPR64, ZPR64, int_aarch64_sve_fcvtzu, nxv2i64, nxv2i1, nxv2f64, ElementSizeD>;
defm FRINTN_ZPmZ : sve_fp_2op_p_zd_HSD<0b00000, "frintn", int_aarch64_sve_frintn>;
defm FRINTP_ZPmZ : sve_fp_2op_p_zd_HSD<0b00001, "frintp", int_aarch64_sve_frintp>;
defm FRINTP_ZPmZ : sve_fp_2op_p_zd_HSD<0b00001, "frintp", int_aarch64_sve_frintp, AArch64frintp_mt>;
defm FRINTM_ZPmZ : sve_fp_2op_p_zd_HSD<0b00010, "frintm", int_aarch64_sve_frintm>;
defm FRINTZ_ZPmZ : sve_fp_2op_p_zd_HSD<0b00011, "frintz", int_aarch64_sve_frintz>;
defm FRINTA_ZPmZ : sve_fp_2op_p_zd_HSD<0b00100, "frinta", int_aarch64_sve_frinta>;

16
llvm/lib/Target/AArch64/SVEInstrFormats.td
View File

@ -2286,14 +2286,22 @@ multiclass sve_fp_2op_p_zd<bits<7> opc, string asm,
def : SVE_3_Op_Pat<vt1, op, vt1, vt2, vt3, !cast<Instruction>(NAME)>;
}
multiclass sve_fp_2op_p_zd_HSD<bits<5> opc, string asm, SDPatternOperator op> {
multiclass sve_fp_2op_p_zd_HSD<bits<5> opc, string asm, SDPatternOperator op_merge,
SDPatternOperator op_pt = null_frag> {
def _H : sve_fp_2op_p_zd<{ 0b01, opc }, asm, ZPR16, ZPR16, ElementSizeH>;
def _S : sve_fp_2op_p_zd<{ 0b10, opc }, asm, ZPR32, ZPR32, ElementSizeS>;
def _D : sve_fp_2op_p_zd<{ 0b11, opc }, asm, ZPR64, ZPR64, ElementSizeD>;
def : SVE_3_Op_Pat<nxv8f16, op, nxv8f16, nxv8i1, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv4f32, op, nxv4f32, nxv4i1, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2f64, op, nxv2f64, nxv2i1, nxv2f64, !cast<Instruction>(NAME # _D)>;
def : SVE_3_Op_Pat<nxv8f16, op_merge, nxv8f16, nxv8i1, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv4f32, op_merge, nxv4f32, nxv4i1, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2f64, op_merge, nxv2f64, nxv2i1, nxv2f64, !cast<Instruction>(NAME # _D)>;
def : SVE_1_Op_Passthru_Pat<nxv8f16, op_pt, nxv8i1, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_1_Op_Passthru_Pat<nxv4f16, op_pt, nxv4i1, nxv4f16, !cast<Instruction>(NAME # _H)>;
def : SVE_1_Op_Passthru_Pat<nxv2f16, op_pt, nxv2i1, nxv2f16, !cast<Instruction>(NAME # _H)>;
def : SVE_1_Op_Passthru_Pat<nxv4f32, op_pt, nxv4i1, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_1_Op_Passthru_Pat<nxv2f32, op_pt, nxv2i1, nxv2f32, !cast<Instruction>(NAME # _S)>;
def : SVE_1_Op_Passthru_Pat<nxv2f64, op_pt, nxv2i1, nxv2f64, !cast<Instruction>(NAME # _D)>;
}
multiclass sve2_fp_flogb<string asm, SDPatternOperator op> {

63
llvm/test/CodeGen/AArch64/sve-fp.ll
View File

@ -480,6 +480,62 @@ define void @float_copy(<vscale x 4 x float>* %P1, <vscale x 4 x float>* %P2) {
ret void
}
; FCEIL
define <vscale x 8 x half> @frintp_nxv8f16(<vscale x 8 x half> %a) {
; CHECK-LABEL: frintp_nxv8f16:
; CHECK: ptrue p0.h
; CHECK-NEXT: frintp z0.h, p0/m, z0.h
; CHECK-NEXT: ret
%res = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> %a)
ret <vscale x 8 x half> %res
}
define <vscale x 4 x half> @frintp_nxv4f16(<vscale x 4 x half> %a) {
; CHECK-LABEL: frintp_nxv4f16:
; CHECK: ptrue p0.s
; CHECK-NEXT: frintp z0.h, p0/m, z0.h
; CHECK-NEXT: ret
%res = call <vscale x 4 x half> @llvm.ceil.nxv4f16(<vscale x 4 x half> %a)
ret <vscale x 4 x half> %res
}
define <vscale x 2 x half> @frintp_nxv2f16(<vscale x 2 x half> %a) {
; CHECK-LABEL: frintp_nxv2f16:
; CHECK: ptrue p0.d
; CHECK-NEXT: frintp z0.h, p0/m, z0.h
; CHECK-NEXT: ret
%res = call <vscale x 2 x half> @llvm.ceil.nxv2f16(<vscale x 2 x half> %a)
ret <vscale x 2 x half> %res
}
define <vscale x 4 x float> @frintp_nxv4f32(<vscale x 4 x float> %a) {
; CHECK-LABEL: frintp_nxv4f32:
; CHECK: ptrue p0.s
; CHECK-NEXT: frintp z0.s, p0/m, z0.s
; CHECK-NEXT: ret
%res = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> %a)
ret <vscale x 4 x float> %res
}
define <vscale x 2 x float> @frintp_nxv2f32(<vscale x 2 x float> %a) {
; CHECK-LABEL: frintp_nxv2f32:
; CHECK: ptrue p0.d
; CHECK-NEXT: frintp z0.s, p0/m, z0.s
; CHECK-NEXT: ret
%res = call <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float> %a)
ret <vscale x 2 x float> %res
}
define <vscale x 2 x double> @frintp_nxv2f64(<vscale x 2 x double> %a) {
; CHECK-LABEL: frintp_nxv2f64:
; CHECK: ptrue p0.d
; CHECK-NEXT: frintp z0.d, p0/m, z0.d
; CHECK-NEXT: ret
%res = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> %a)
ret <vscale x 2 x double> %res
}
declare <vscale x 8 x half> @llvm.aarch64.sve.frecps.x.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.frecps.x.nxv4f32(<vscale x 4 x float> , <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.frecps.x.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
@ -495,5 +551,12 @@ declare <vscale x 8 x half> @llvm.fma.nxv8f16(<vscale x 8 x half>, <vscale x 8 x
declare <vscale x 4 x half> @llvm.fma.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 2 x half> @llvm.fma.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>, <vscale x 2 x half>)
declare <vscale x 8 x half> @llvm.ceil.nxv8f16( <vscale x 8 x half>)
declare <vscale x 4 x half> @llvm.ceil.nxv4f16( <vscale x 4 x half>)
declare <vscale x 2 x half> @llvm.ceil.nxv2f16( <vscale x 2 x half>)
declare <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float>)
declare <vscale x 2 x float> @llvm.ceil.nxv2f32(<vscale x 2 x float>)
declare <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double>)
; Function Attrs: nounwind readnone
declare double @llvm.aarch64.sve.faddv.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>) #2