forked from OSchip/llvm-project
970 lines
36 KiB
TableGen
970 lines
36 KiB
TableGen
//=- HexagonInstrInfoV5.td - Target Desc. for Hexagon Target -*- tablegen -*-=//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file describes the Hexagon V5 instructions in TableGen format.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// XTYPE/MPY
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let isCodeGenOnly = 0 in
|
|
def S2_asr_i_p_rnd : S_2OpInstImm<"asr", 0b110, 0b111, u6Imm,
|
|
[(set I64:$dst,
|
|
(sra (i64 (add (i64 (sra I64:$src1, u6ImmPred:$src2)), 1)),
|
|
(i32 1)))], 1>,
|
|
Requires<[HasV5T]> {
|
|
bits<6> src2;
|
|
let Inst{13-8} = src2;
|
|
}
|
|
|
|
let isCodeGenOnly = 0 in
|
|
def C4_fastcorner9 : T_LOGICAL_2OP<"fastcorner9", 0b000, 0, 0>,
|
|
Requires<[HasV5T]> {
|
|
let Inst{13,7,4} = 0b111;
|
|
}
|
|
|
|
let isCodeGenOnly = 0 in
|
|
def C4_fastcorner9_not : T_LOGICAL_2OP<"!fastcorner9", 0b000, 0, 0>,
|
|
Requires<[HasV5T]> {
|
|
let Inst{20,13,7,4} = 0b1111;
|
|
}
|
|
|
|
def SDTHexagonFCONST32 : SDTypeProfile<1, 1, [
|
|
SDTCisVT<0, f32>,
|
|
SDTCisPtrTy<1>]>;
|
|
def HexagonFCONST32 : SDNode<"HexagonISD::FCONST32", SDTHexagonFCONST32>;
|
|
|
|
let isReMaterializable = 1, isMoveImm = 1 in
|
|
def FCONST32_nsdata : LDInst<(outs IntRegs:$dst), (ins globaladdress:$global),
|
|
"$dst = CONST32(#$global)",
|
|
[(set (f32 IntRegs:$dst),
|
|
(HexagonFCONST32 tglobaladdr:$global))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let isReMaterializable = 1, isMoveImm = 1 in
|
|
def CONST64_Float_Real : LDInst<(outs DoubleRegs:$dst), (ins f64imm:$src1),
|
|
"$dst = CONST64(#$src1)",
|
|
[(set DoubleRegs:$dst, fpimm:$src1)]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let isReMaterializable = 1, isMoveImm = 1 in
|
|
def CONST32_Float_Real : LDInst<(outs IntRegs:$dst), (ins f32imm:$src1),
|
|
"$dst = CONST32(#$src1)",
|
|
[(set IntRegs:$dst, fpimm:$src1)]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// Transfer immediate float.
|
|
// Only works with single precision fp value.
|
|
// For double precision, use CONST64_float_real, as 64bit transfer
|
|
// can only hold 40-bit values - 32 from const ext + 8 bit immediate.
|
|
// Make sure that complexity is more than the CONST32 pattern in
|
|
// HexagonInstrInfo.td patterns.
|
|
let isExtended = 1, opExtendable = 1, isMoveImm = 1, isReMaterializable = 1,
|
|
isPredicable = 1, AddedComplexity = 30, validSubTargets = HasV5SubT,
|
|
isCodeGenOnly = 1 in
|
|
def TFRI_f : ALU32_ri<(outs IntRegs:$dst), (ins f32Ext:$src1),
|
|
"$dst = #$src1",
|
|
[(set IntRegs:$dst, fpimm:$src1)]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let isExtended = 1, opExtendable = 2, isPredicated = 1,
|
|
hasSideEffects = 0, validSubTargets = HasV5SubT in
|
|
def TFRI_cPt_f : ALU32_ri<(outs IntRegs:$dst),
|
|
(ins PredRegs:$src1, f32Ext:$src2),
|
|
"if ($src1) $dst = #$src2",
|
|
[]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let isExtended = 1, opExtendable = 2, isPredicated = 1, isPredicatedFalse = 1,
|
|
hasSideEffects = 0, validSubTargets = HasV5SubT in
|
|
def TFRI_cNotPt_f : ALU32_ri<(outs IntRegs:$dst),
|
|
(ins PredRegs:$src1, f32Ext:$src2),
|
|
"if (!$src1) $dst =#$src2",
|
|
[]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def SDTHexagonI32I64: SDTypeProfile<1, 1, [SDTCisVT<0, i32>,
|
|
SDTCisVT<1, i64>]>;
|
|
|
|
def HexagonPOPCOUNT: SDNode<"HexagonISD::POPCOUNT", SDTHexagonI32I64>;
|
|
|
|
let hasNewValue = 1, validSubTargets = HasV5SubT, isCodeGenOnly = 0 in
|
|
def S5_popcountp : ALU64_rr<(outs IntRegs:$Rd), (ins DoubleRegs:$Rss),
|
|
"$Rd = popcount($Rss)",
|
|
[(set I32:$Rd, (HexagonPOPCOUNT I64:$Rss))], "", S_2op_tc_2_SLOT23>,
|
|
Requires<[HasV5T]> {
|
|
bits<5> Rd;
|
|
bits<5> Rss;
|
|
|
|
let IClass = 0b1000;
|
|
|
|
let Inst{27-21} = 0b1000011;
|
|
let Inst{7-5} = 0b011;
|
|
let Inst{4-0} = Rd;
|
|
let Inst{20-16} = Rss;
|
|
}
|
|
|
|
defm: Loadx_pat<load, f32, s11_2ExtPred, L2_loadri_io>;
|
|
defm: Loadx_pat<load, f64, s11_3ExtPred, L2_loadrd_io>;
|
|
|
|
defm: Storex_pat<store, F32, s11_2ExtPred, S2_storeri_io>;
|
|
defm: Storex_pat<store, F64, s11_3ExtPred, S2_storerd_io>;
|
|
|
|
let isFP = 1, hasNewValue = 1, opNewValue = 0 in
|
|
class T_MInstFloat <string mnemonic, bits<3> MajOp, bits<3> MinOp>
|
|
: MInst<(outs IntRegs:$Rd),
|
|
(ins IntRegs:$Rs, IntRegs:$Rt),
|
|
"$Rd = "#mnemonic#"($Rs, $Rt)", [],
|
|
"" , M_tc_3or4x_SLOT23 > ,
|
|
Requires<[HasV5T]> {
|
|
bits<5> Rd;
|
|
bits<5> Rs;
|
|
bits<5> Rt;
|
|
|
|
let IClass = 0b1110;
|
|
|
|
let Inst{27-24} = 0b1011;
|
|
let Inst{23-21} = MajOp;
|
|
let Inst{20-16} = Rs;
|
|
let Inst{13} = 0b0;
|
|
let Inst{12-8} = Rt;
|
|
let Inst{7-5} = MinOp;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let isCommutable = 1, isCodeGenOnly = 0 in {
|
|
def F2_sfadd : T_MInstFloat < "sfadd", 0b000, 0b000>;
|
|
def F2_sfmpy : T_MInstFloat < "sfmpy", 0b010, 0b000>;
|
|
}
|
|
|
|
let isCodeGenOnly = 0 in
|
|
def F2_sfsub : T_MInstFloat < "sfsub", 0b000, 0b001>;
|
|
|
|
let Itinerary = M_tc_3x_SLOT23, isCodeGenOnly = 0 in {
|
|
def F2_sfmax : T_MInstFloat < "sfmax", 0b100, 0b000>;
|
|
def F2_sfmin : T_MInstFloat < "sfmin", 0b100, 0b001>;
|
|
}
|
|
|
|
let isCodeGenOnly = 0 in {
|
|
def F2_sffixupn : T_MInstFloat < "sffixupn", 0b110, 0b000>;
|
|
def F2_sffixupd : T_MInstFloat < "sffixupd", 0b110, 0b001>;
|
|
}
|
|
|
|
// F2_sfrecipa: Reciprocal approximation for division.
|
|
let isPredicateLate = 1, isFP = 1,
|
|
hasSideEffects = 0, hasNewValue = 1, isCodeGenOnly = 0 in
|
|
def F2_sfrecipa: MInst <
|
|
(outs IntRegs:$Rd, PredRegs:$Pe),
|
|
(ins IntRegs:$Rs, IntRegs:$Rt),
|
|
"$Rd, $Pe = sfrecipa($Rs, $Rt)">,
|
|
Requires<[HasV5T]> {
|
|
bits<5> Rd;
|
|
bits<2> Pe;
|
|
bits<5> Rs;
|
|
bits<5> Rt;
|
|
|
|
let IClass = 0b1110;
|
|
let Inst{27-21} = 0b1011111;
|
|
let Inst{20-16} = Rs;
|
|
let Inst{13} = 0b0;
|
|
let Inst{12-8} = Rt;
|
|
let Inst{7} = 0b1;
|
|
let Inst{6-5} = Pe;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
// F2_dfcmpeq: Floating point compare for equal.
|
|
let isCompare = 1, isFP = 1 in
|
|
class T_fcmp <string mnemonic, RegisterClass RC, bits<3> MinOp,
|
|
list<dag> pattern = [] >
|
|
: ALU64Inst <(outs PredRegs:$dst), (ins RC:$src1, RC:$src2),
|
|
"$dst = "#mnemonic#"($src1, $src2)", pattern,
|
|
"" , ALU64_tc_2early_SLOT23 > ,
|
|
Requires<[HasV5T]> {
|
|
bits<2> dst;
|
|
bits<5> src1;
|
|
bits<5> src2;
|
|
|
|
let IClass = 0b1101;
|
|
|
|
let Inst{27-21} = 0b0010111;
|
|
let Inst{20-16} = src1;
|
|
let Inst{12-8} = src2;
|
|
let Inst{7-5} = MinOp;
|
|
let Inst{1-0} = dst;
|
|
}
|
|
|
|
class T_fcmp64 <string mnemonic, PatFrag OpNode, bits<3> MinOp>
|
|
: T_fcmp <mnemonic, DoubleRegs, MinOp,
|
|
[(set I1:$dst, (OpNode F64:$src1, F64:$src2))]> {
|
|
let IClass = 0b1101;
|
|
let Inst{27-21} = 0b0010111;
|
|
}
|
|
|
|
class T_fcmp32 <string mnemonic, PatFrag OpNode, bits<3> MinOp>
|
|
: T_fcmp <mnemonic, IntRegs, MinOp,
|
|
[(set I1:$dst, (OpNode F32:$src1, F32:$src2))]> {
|
|
let IClass = 0b1100;
|
|
let Inst{27-21} = 0b0111111;
|
|
}
|
|
|
|
let isCodeGenOnly = 0 in {
|
|
def F2_dfcmpeq : T_fcmp64<"dfcmp.eq", setoeq, 0b000>;
|
|
def F2_dfcmpgt : T_fcmp64<"dfcmp.gt", setogt, 0b001>;
|
|
def F2_dfcmpge : T_fcmp64<"dfcmp.ge", setoge, 0b010>;
|
|
def F2_dfcmpuo : T_fcmp64<"dfcmp.uo", setuo, 0b011>;
|
|
|
|
def F2_sfcmpge : T_fcmp32<"sfcmp.ge", setoge, 0b000>;
|
|
def F2_sfcmpuo : T_fcmp32<"sfcmp.uo", setuo, 0b001>;
|
|
def F2_sfcmpeq : T_fcmp32<"sfcmp.eq", setoeq, 0b011>;
|
|
def F2_sfcmpgt : T_fcmp32<"sfcmp.gt", setogt, 0b100>;
|
|
}
|
|
|
|
// F2 convert template classes:
|
|
let isFP = 1 in
|
|
class F2_RDD_RSS_CONVERT<string mnemonic, bits<3> MinOp,
|
|
SDNode Op, PatLeaf RCOut, PatLeaf RCIn,
|
|
string chop ="">
|
|
: SInst <(outs DoubleRegs:$Rdd), (ins DoubleRegs:$Rss),
|
|
"$Rdd = "#mnemonic#"($Rss)"#chop,
|
|
[(set RCOut:$Rdd, (Op RCIn:$Rss))], "",
|
|
S_2op_tc_3or4x_SLOT23> {
|
|
bits<5> Rdd;
|
|
bits<5> Rss;
|
|
|
|
let IClass = 0b1000;
|
|
|
|
let Inst{27-21} = 0b0000111;
|
|
let Inst{20-16} = Rss;
|
|
let Inst{7-5} = MinOp;
|
|
let Inst{4-0} = Rdd;
|
|
}
|
|
|
|
let isFP = 1 in
|
|
class F2_RDD_RS_CONVERT<string mnemonic, bits<3> MinOp,
|
|
SDNode Op, PatLeaf RCOut, PatLeaf RCIn,
|
|
string chop ="">
|
|
: SInst <(outs DoubleRegs:$Rdd), (ins IntRegs:$Rs),
|
|
"$Rdd = "#mnemonic#"($Rs)"#chop,
|
|
[(set RCOut:$Rdd, (Op RCIn:$Rs))], "",
|
|
S_2op_tc_3or4x_SLOT23> {
|
|
bits<5> Rdd;
|
|
bits<5> Rs;
|
|
|
|
let IClass = 0b1000;
|
|
|
|
let Inst{27-21} = 0b0100100;
|
|
let Inst{20-16} = Rs;
|
|
let Inst{7-5} = MinOp;
|
|
let Inst{4-0} = Rdd;
|
|
}
|
|
|
|
let isFP = 1, hasNewValue = 1 in
|
|
class F2_RD_RSS_CONVERT<string mnemonic, bits<3> MinOp,
|
|
SDNode Op, PatLeaf RCOut, PatLeaf RCIn,
|
|
string chop ="">
|
|
: SInst <(outs IntRegs:$Rd), (ins DoubleRegs:$Rss),
|
|
"$Rd = "#mnemonic#"($Rss)"#chop,
|
|
[(set RCOut:$Rd, (Op RCIn:$Rss))], "",
|
|
S_2op_tc_3or4x_SLOT23> {
|
|
bits<5> Rd;
|
|
bits<5> Rss;
|
|
|
|
let IClass = 0b1000;
|
|
|
|
let Inst{27-24} = 0b1000;
|
|
let Inst{23-21} = MinOp;
|
|
let Inst{20-16} = Rss;
|
|
let Inst{7-5} = 0b001;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
let isFP = 1, hasNewValue = 1 in
|
|
class F2_RD_RS_CONVERT<string mnemonic, bits<3> MajOp, bits<3> MinOp,
|
|
SDNode Op, PatLeaf RCOut, PatLeaf RCIn,
|
|
string chop ="">
|
|
: SInst <(outs IntRegs:$Rd), (ins IntRegs:$Rs),
|
|
"$Rd = "#mnemonic#"($Rs)"#chop,
|
|
[(set RCOut:$Rd, (Op RCIn:$Rs))], "",
|
|
S_2op_tc_3or4x_SLOT23> {
|
|
bits<5> Rd;
|
|
bits<5> Rs;
|
|
|
|
let IClass = 0b1000;
|
|
|
|
let Inst{27-24} = 0b1011;
|
|
let Inst{23-21} = MajOp;
|
|
let Inst{20-16} = Rs;
|
|
let Inst{7-5} = MinOp;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
// Convert single precision to double precision and vice-versa.
|
|
let isCodeGenOnly = 0 in {
|
|
def F2_conv_sf2df : F2_RDD_RS_CONVERT <"convert_sf2df", 0b000,
|
|
fextend, F64, F32>;
|
|
|
|
def F2_conv_df2sf : F2_RD_RSS_CONVERT <"convert_df2sf", 0b000,
|
|
fround, F32, F64>;
|
|
|
|
// Convert Integer to Floating Point.
|
|
def F2_conv_d2sf : F2_RD_RSS_CONVERT <"convert_d2sf", 0b010,
|
|
sint_to_fp, F32, I64>;
|
|
def F2_conv_ud2sf : F2_RD_RSS_CONVERT <"convert_ud2sf", 0b001,
|
|
uint_to_fp, F32, I64>;
|
|
def F2_conv_uw2sf : F2_RD_RS_CONVERT <"convert_uw2sf", 0b001, 0b000,
|
|
uint_to_fp, F32, I32>;
|
|
def F2_conv_w2sf : F2_RD_RS_CONVERT <"convert_w2sf", 0b010, 0b000,
|
|
sint_to_fp, F32, I32>;
|
|
def F2_conv_d2df : F2_RDD_RSS_CONVERT <"convert_d2df", 0b011,
|
|
sint_to_fp, F64, I64>;
|
|
def F2_conv_ud2df : F2_RDD_RSS_CONVERT <"convert_ud2df", 0b010,
|
|
uint_to_fp, F64, I64>;
|
|
def F2_conv_uw2df : F2_RDD_RS_CONVERT <"convert_uw2df", 0b001,
|
|
uint_to_fp, F64, I32>;
|
|
def F2_conv_w2df : F2_RDD_RS_CONVERT <"convert_w2df", 0b010,
|
|
sint_to_fp, F64, I32>;
|
|
|
|
// Convert Floating Point to Integer - default.
|
|
def F2_conv_df2uw_chop : F2_RD_RSS_CONVERT <"convert_df2uw", 0b101,
|
|
fp_to_uint, I32, F64, ":chop">;
|
|
def F2_conv_df2w_chop : F2_RD_RSS_CONVERT <"convert_df2w", 0b111,
|
|
fp_to_sint, I32, F64, ":chop">;
|
|
def F2_conv_sf2uw_chop : F2_RD_RS_CONVERT <"convert_sf2uw", 0b011, 0b001,
|
|
fp_to_uint, I32, F32, ":chop">;
|
|
def F2_conv_sf2w_chop : F2_RD_RS_CONVERT <"convert_sf2w", 0b100, 0b001,
|
|
fp_to_sint, I32, F32, ":chop">;
|
|
def F2_conv_df2d_chop : F2_RDD_RSS_CONVERT <"convert_df2d", 0b110,
|
|
fp_to_sint, I64, F64, ":chop">;
|
|
def F2_conv_df2ud_chop : F2_RDD_RSS_CONVERT <"convert_df2ud", 0b111,
|
|
fp_to_uint, I64, F64, ":chop">;
|
|
def F2_conv_sf2d_chop : F2_RDD_RS_CONVERT <"convert_sf2d", 0b110,
|
|
fp_to_sint, I64, F32, ":chop">;
|
|
def F2_conv_sf2ud_chop : F2_RDD_RS_CONVERT <"convert_sf2ud", 0b101,
|
|
fp_to_uint, I64, F32, ":chop">;
|
|
|
|
// Convert Floating Point to Integer: non-chopped.
|
|
let AddedComplexity = 20, Predicates = [HasV5T, IEEERndNearV5T] in {
|
|
def F2_conv_df2d : F2_RDD_RSS_CONVERT <"convert_df2d", 0b000,
|
|
fp_to_sint, I64, F64>;
|
|
def F2_conv_df2ud : F2_RDD_RSS_CONVERT <"convert_df2ud", 0b001,
|
|
fp_to_uint, I64, F64>;
|
|
def F2_conv_sf2ud : F2_RDD_RS_CONVERT <"convert_sf2ud", 0b011,
|
|
fp_to_uint, I64, F32>;
|
|
def F2_conv_sf2d : F2_RDD_RS_CONVERT <"convert_sf2d", 0b100,
|
|
fp_to_sint, I64, F32>;
|
|
def F2_conv_df2uw : F2_RD_RSS_CONVERT <"convert_df2uw", 0b011,
|
|
fp_to_uint, I32, F64>;
|
|
def F2_conv_df2w : F2_RD_RSS_CONVERT <"convert_df2w", 0b100,
|
|
fp_to_sint, I32, F64>;
|
|
def F2_conv_sf2uw : F2_RD_RS_CONVERT <"convert_sf2uw", 0b011, 0b000,
|
|
fp_to_uint, I32, F32>;
|
|
def F2_conv_sf2w : F2_RD_RS_CONVERT <"convert_sf2w", 0b100, 0b000,
|
|
fp_to_sint, I32, F32>;
|
|
}
|
|
}
|
|
|
|
// Fix up radicand.
|
|
let isFP = 1, hasNewValue = 1, isCodeGenOnly = 0 in
|
|
def F2_sffixupr: SInst<(outs IntRegs:$Rd), (ins IntRegs:$Rs),
|
|
"$Rd = sffixupr($Rs)",
|
|
[], "" , S_2op_tc_3or4x_SLOT23>, Requires<[HasV5T]> {
|
|
bits<5> Rd;
|
|
bits<5> Rs;
|
|
|
|
let IClass = 0b1000;
|
|
|
|
let Inst{27-21} = 0b1011101;
|
|
let Inst{20-16} = Rs;
|
|
let Inst{7-5} = 0b000;
|
|
let Inst{4-0} = Rd;
|
|
}
|
|
|
|
// F2_sffma: Floating-point fused multiply add.
|
|
let isFP = 1, hasNewValue = 1 in
|
|
class T_sfmpy_acc <bit isSub, bit isLib>
|
|
: MInst<(outs IntRegs:$Rx),
|
|
(ins IntRegs:$dst2, IntRegs:$Rs, IntRegs:$Rt),
|
|
"$Rx "#!if(isSub, "-=","+=")#" sfmpy($Rs, $Rt)"#!if(isLib, ":lib",""),
|
|
[], "$dst2 = $Rx" , M_tc_3_SLOT23 > ,
|
|
Requires<[HasV5T]> {
|
|
bits<5> Rx;
|
|
bits<5> Rs;
|
|
bits<5> Rt;
|
|
|
|
let IClass = 0b1110;
|
|
|
|
let Inst{27-21} = 0b1111000;
|
|
let Inst{20-16} = Rs;
|
|
let Inst{13} = 0b0;
|
|
let Inst{12-8} = Rt;
|
|
let Inst{7} = 0b1;
|
|
let Inst{6} = isLib;
|
|
let Inst{5} = isSub;
|
|
let Inst{4-0} = Rx;
|
|
}
|
|
|
|
let isCodeGenOnly = 0 in {
|
|
def F2_sffma: T_sfmpy_acc <0, 0>;
|
|
def F2_sffms: T_sfmpy_acc <1, 0>;
|
|
def F2_sffma_lib: T_sfmpy_acc <0, 1>;
|
|
def F2_sffms_lib: T_sfmpy_acc <1, 1>;
|
|
}
|
|
|
|
// Floating-point fused multiply add w/ additional scaling (2**pu).
|
|
let isFP = 1, hasNewValue = 1, isCodeGenOnly = 0 in
|
|
def F2_sffma_sc: MInst <
|
|
(outs IntRegs:$Rx),
|
|
(ins IntRegs:$dst2, IntRegs:$Rs, IntRegs:$Rt, PredRegs:$Pu),
|
|
"$Rx += sfmpy($Rs, $Rt, $Pu):scale" ,
|
|
[], "$dst2 = $Rx" , M_tc_3_SLOT23 > ,
|
|
Requires<[HasV5T]> {
|
|
bits<5> Rx;
|
|
bits<5> Rs;
|
|
bits<5> Rt;
|
|
bits<2> Pu;
|
|
|
|
let IClass = 0b1110;
|
|
|
|
let Inst{27-21} = 0b1111011;
|
|
let Inst{20-16} = Rs;
|
|
let Inst{13} = 0b0;
|
|
let Inst{12-8} = Rt;
|
|
let Inst{7} = 0b1;
|
|
let Inst{6-5} = Pu;
|
|
let Inst{4-0} = Rx;
|
|
}
|
|
|
|
// Classify floating-point value
|
|
let isFP = 1, isCodeGenOnly = 0 in
|
|
def F2_sfclass : T_TEST_BIT_IMM<"sfclass", 0b111>;
|
|
|
|
let isFP = 1, isCodeGenOnly = 0 in
|
|
def F2_dfclass: ALU64Inst<(outs PredRegs:$Pd), (ins DoubleRegs:$Rss, u5Imm:$u5),
|
|
"$Pd = dfclass($Rss, #$u5)",
|
|
[], "" , ALU64_tc_2early_SLOT23 > , Requires<[HasV5T]> {
|
|
bits<2> Pd;
|
|
bits<5> Rss;
|
|
bits<5> u5;
|
|
|
|
let IClass = 0b1101;
|
|
let Inst{27-21} = 0b1100100;
|
|
let Inst{20-16} = Rss;
|
|
let Inst{12-10} = 0b000;
|
|
let Inst{9-5} = u5;
|
|
let Inst{4-3} = 0b10;
|
|
let Inst{1-0} = Pd;
|
|
}
|
|
|
|
// Instructions to create floating point constant
|
|
let hasNewValue = 1, opNewValue = 0 in
|
|
class T_fimm <string mnemonic, RegisterClass RC, bits<4> RegType, bit isNeg>
|
|
: ALU64Inst<(outs RC:$dst), (ins u10Imm:$src),
|
|
"$dst = "#mnemonic#"(#$src)"#!if(isNeg, ":neg", ":pos"),
|
|
[], "", ALU64_tc_3x_SLOT23>, Requires<[HasV5T]> {
|
|
bits<5> dst;
|
|
bits<10> src;
|
|
|
|
let IClass = 0b1101;
|
|
let Inst{27-24} = RegType;
|
|
let Inst{23} = 0b0;
|
|
let Inst{22} = isNeg;
|
|
let Inst{21} = src{9};
|
|
let Inst{13-5} = src{8-0};
|
|
let Inst{4-0} = dst;
|
|
}
|
|
|
|
let isCodeGenOnly = 0 in {
|
|
def F2_sfimm_p : T_fimm <"sfmake", IntRegs, 0b0110, 0>;
|
|
def F2_sfimm_n : T_fimm <"sfmake", IntRegs, 0b0110, 1>;
|
|
def F2_dfimm_p : T_fimm <"dfmake", DoubleRegs, 0b1001, 0>;
|
|
def F2_dfimm_n : T_fimm <"dfmake", DoubleRegs, 0b1001, 1>;
|
|
}
|
|
|
|
// Add
|
|
let isCommutable = 1 in
|
|
def fADD_rr : ALU64_rr<(outs IntRegs:$dst),
|
|
(ins IntRegs:$src1, IntRegs:$src2),
|
|
"$dst = sfadd($src1, $src2)",
|
|
[(set IntRegs:$dst, (fadd IntRegs:$src1, IntRegs:$src2))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let isCommutable = 1 in
|
|
def fADD64_rr : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src1,
|
|
DoubleRegs:$src2),
|
|
"$dst = dfadd($src1, $src2)",
|
|
[(set DoubleRegs:$dst, (fadd DoubleRegs:$src1,
|
|
DoubleRegs:$src2))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def fSUB_rr : ALU64_rr<(outs IntRegs:$dst),
|
|
(ins IntRegs:$src1, IntRegs:$src2),
|
|
"$dst = sfsub($src1, $src2)",
|
|
[(set IntRegs:$dst, (fsub IntRegs:$src1, IntRegs:$src2))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def fSUB64_rr : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src1,
|
|
DoubleRegs:$src2),
|
|
"$dst = dfsub($src1, $src2)",
|
|
[(set DoubleRegs:$dst, (fsub DoubleRegs:$src1,
|
|
DoubleRegs:$src2))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let isCommutable = 1 in
|
|
def fMUL_rr : ALU64_rr<(outs IntRegs:$dst),
|
|
(ins IntRegs:$src1, IntRegs:$src2),
|
|
"$dst = sfmpy($src1, $src2)",
|
|
[(set IntRegs:$dst, (fmul IntRegs:$src1, IntRegs:$src2))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let isCommutable = 1 in
|
|
def fMUL64_rr : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src1,
|
|
DoubleRegs:$src2),
|
|
"$dst = dfmpy($src1, $src2)",
|
|
[(set DoubleRegs:$dst, (fmul DoubleRegs:$src1,
|
|
DoubleRegs:$src2))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// Compare.
|
|
let isCompare = 1 in {
|
|
multiclass FCMP64_rr<string OpcStr, PatFrag OpNode> {
|
|
def _rr : ALU64_rr<(outs PredRegs:$dst), (ins DoubleRegs:$b, DoubleRegs:$c),
|
|
!strconcat("$dst = ", !strconcat(OpcStr, "($b, $c)")),
|
|
[(set PredRegs:$dst,
|
|
(OpNode (f64 DoubleRegs:$b), (f64 DoubleRegs:$c)))]>,
|
|
Requires<[HasV5T]>;
|
|
}
|
|
|
|
multiclass FCMP32_rr<string OpcStr, PatFrag OpNode> {
|
|
def _rr : ALU64_rr<(outs PredRegs:$dst), (ins IntRegs:$b, IntRegs:$c),
|
|
!strconcat("$dst = ", !strconcat(OpcStr, "($b, $c)")),
|
|
[(set PredRegs:$dst,
|
|
(OpNode (f32 IntRegs:$b), (f32 IntRegs:$c)))]>,
|
|
Requires<[HasV5T]>;
|
|
}
|
|
}
|
|
|
|
defm FCMPOEQ64 : FCMP64_rr<"dfcmp.eq", setoeq>;
|
|
defm FCMPUEQ64 : FCMP64_rr<"dfcmp.eq", setueq>;
|
|
defm FCMPOGT64 : FCMP64_rr<"dfcmp.gt", setogt>;
|
|
defm FCMPUGT64 : FCMP64_rr<"dfcmp.gt", setugt>;
|
|
defm FCMPOGE64 : FCMP64_rr<"dfcmp.ge", setoge>;
|
|
defm FCMPUGE64 : FCMP64_rr<"dfcmp.ge", setuge>;
|
|
|
|
defm FCMPOEQ32 : FCMP32_rr<"sfcmp.eq", setoeq>;
|
|
defm FCMPUEQ32 : FCMP32_rr<"sfcmp.eq", setueq>;
|
|
defm FCMPOGT32 : FCMP32_rr<"sfcmp.gt", setogt>;
|
|
defm FCMPUGT32 : FCMP32_rr<"sfcmp.gt", setugt>;
|
|
defm FCMPOGE32 : FCMP32_rr<"sfcmp.ge", setoge>;
|
|
defm FCMPUGE32 : FCMP32_rr<"sfcmp.ge", setuge>;
|
|
|
|
// olt.
|
|
def : Pat <(i1 (setolt (f32 IntRegs:$src1), (f32 IntRegs:$src2))),
|
|
(i1 (FCMPOGT32_rr IntRegs:$src2, IntRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i1 (setolt (f32 IntRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPOGT32_rr (f32 (TFRI_f fpimm:$src2)), (f32 IntRegs:$src1)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i1 (setolt (f64 DoubleRegs:$src1), (f64 DoubleRegs:$src2))),
|
|
(i1 (FCMPOGT64_rr DoubleRegs:$src2, DoubleRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i1 (setolt (f64 DoubleRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPOGT64_rr (f64 (CONST64_Float_Real fpimm:$src2)),
|
|
(f64 DoubleRegs:$src1)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// gt.
|
|
def : Pat <(i1 (setugt (f64 DoubleRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPUGT64_rr (f64 DoubleRegs:$src1),
|
|
(f64 (CONST64_Float_Real fpimm:$src2))))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i1 (setugt (f32 IntRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPUGT32_rr (f32 IntRegs:$src1), (f32 (TFRI_f fpimm:$src2))))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// ult.
|
|
def : Pat <(i1 (setult (f32 IntRegs:$src1), (f32 IntRegs:$src2))),
|
|
(i1 (FCMPUGT32_rr IntRegs:$src2, IntRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i1 (setult (f32 IntRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPUGT32_rr (f32 (TFRI_f fpimm:$src2)), (f32 IntRegs:$src1)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i1 (setult (f64 DoubleRegs:$src1), (f64 DoubleRegs:$src2))),
|
|
(i1 (FCMPUGT64_rr DoubleRegs:$src2, DoubleRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i1 (setult (f64 DoubleRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPUGT64_rr (f64 (CONST64_Float_Real fpimm:$src2)),
|
|
(f64 DoubleRegs:$src1)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// le.
|
|
// rs <= rt -> rt >= rs.
|
|
def : Pat<(i1 (setole (f32 IntRegs:$src1), (f32 IntRegs:$src2))),
|
|
(i1 (FCMPOGE32_rr IntRegs:$src2, IntRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setole (f32 IntRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPOGE32_rr (f32 (TFRI_f fpimm:$src2)), IntRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
|
|
// Rss <= Rtt -> Rtt >= Rss.
|
|
def : Pat<(i1 (setole (f64 DoubleRegs:$src1), (f64 DoubleRegs:$src2))),
|
|
(i1 (FCMPOGE64_rr DoubleRegs:$src2, DoubleRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setole (f64 DoubleRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPOGE64_rr (f64 (CONST64_Float_Real fpimm:$src2)),
|
|
DoubleRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// rs <= rt -> rt >= rs.
|
|
def : Pat<(i1 (setule (f32 IntRegs:$src1), (f32 IntRegs:$src2))),
|
|
(i1 (FCMPUGE32_rr IntRegs:$src2, IntRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setule (f32 IntRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPUGE32_rr (f32 (TFRI_f fpimm:$src2)), IntRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// Rss <= Rtt -> Rtt >= Rss.
|
|
def : Pat<(i1 (setule (f64 DoubleRegs:$src1), (f64 DoubleRegs:$src2))),
|
|
(i1 (FCMPUGE64_rr DoubleRegs:$src2, DoubleRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setule (f64 DoubleRegs:$src1), (fpimm:$src2))),
|
|
(i1 (FCMPUGE64_rr (f64 (CONST64_Float_Real fpimm:$src2)),
|
|
DoubleRegs:$src1))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// ne.
|
|
def : Pat<(i1 (setone (f32 IntRegs:$src1), (f32 IntRegs:$src2))),
|
|
(i1 (C2_not (FCMPOEQ32_rr IntRegs:$src1, IntRegs:$src2)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setone (f64 DoubleRegs:$src1), (f64 DoubleRegs:$src2))),
|
|
(i1 (C2_not (FCMPOEQ64_rr DoubleRegs:$src1, DoubleRegs:$src2)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setune (f32 IntRegs:$src1), (f32 IntRegs:$src2))),
|
|
(i1 (C2_not (FCMPUEQ32_rr IntRegs:$src1, IntRegs:$src2)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setune (f64 DoubleRegs:$src1), (f64 DoubleRegs:$src2))),
|
|
(i1 (C2_not (FCMPUEQ64_rr DoubleRegs:$src1, DoubleRegs:$src2)))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setone (f32 IntRegs:$src1), (fpimm:$src2))),
|
|
(i1 (C2_not (FCMPOEQ32_rr IntRegs:$src1, (f32 (TFRI_f fpimm:$src2)))))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setone (f64 DoubleRegs:$src1), (fpimm:$src2))),
|
|
(i1 (C2_not (FCMPOEQ64_rr DoubleRegs:$src1,
|
|
(f64 (CONST64_Float_Real fpimm:$src2)))))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setune (f32 IntRegs:$src1), (fpimm:$src2))),
|
|
(i1 (C2_not (FCMPUEQ32_rr IntRegs:$src1, (f32 (TFRI_f fpimm:$src2)))))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat<(i1 (setune (f64 DoubleRegs:$src1), (fpimm:$src2))),
|
|
(i1 (C2_not (FCMPUEQ64_rr DoubleRegs:$src1,
|
|
(f64 (CONST64_Float_Real fpimm:$src2)))))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// Convert Integer to Floating Point.
|
|
def CONVERT_d2sf : ALU64_rr<(outs IntRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_d2sf($src)",
|
|
[(set (f32 IntRegs:$dst), (sint_to_fp (i64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_ud2sf : ALU64_rr<(outs IntRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_ud2sf($src)",
|
|
[(set (f32 IntRegs:$dst), (uint_to_fp (i64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_uw2sf : ALU64_rr<(outs IntRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_uw2sf($src)",
|
|
[(set (f32 IntRegs:$dst), (uint_to_fp (i32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_w2sf : ALU64_rr<(outs IntRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_w2sf($src)",
|
|
[(set (f32 IntRegs:$dst), (sint_to_fp (i32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_d2df : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_d2df($src)",
|
|
[(set (f64 DoubleRegs:$dst), (sint_to_fp (i64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_ud2df : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_ud2df($src)",
|
|
[(set (f64 DoubleRegs:$dst), (uint_to_fp (i64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_uw2df : ALU64_rr<(outs DoubleRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_uw2df($src)",
|
|
[(set (f64 DoubleRegs:$dst), (uint_to_fp (i32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_w2df : ALU64_rr<(outs DoubleRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_w2df($src)",
|
|
[(set (f64 DoubleRegs:$dst), (sint_to_fp (i32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// Convert Floating Point to Integer - default.
|
|
def CONVERT_df2uw : ALU64_rr<(outs IntRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2uw($src):chop",
|
|
[(set (i32 IntRegs:$dst), (fp_to_uint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_df2w : ALU64_rr<(outs IntRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2w($src):chop",
|
|
[(set (i32 IntRegs:$dst), (fp_to_sint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_sf2uw : ALU64_rr<(outs IntRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2uw($src):chop",
|
|
[(set (i32 IntRegs:$dst), (fp_to_uint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_sf2w : ALU64_rr<(outs IntRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2w($src):chop",
|
|
[(set (i32 IntRegs:$dst), (fp_to_sint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_df2d : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2d($src):chop",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_sint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_df2ud : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2ud($src):chop",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_uint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_sf2d : ALU64_rr<(outs DoubleRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2d($src):chop",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_sint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def CONVERT_sf2ud : ALU64_rr<(outs DoubleRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2ud($src):chop",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_uint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// Convert Floating Point to Integer: non-chopped.
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_df2uw_nchop : ALU64_rr<(outs IntRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2uw($src)",
|
|
[(set (i32 IntRegs:$dst), (fp_to_uint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_df2w_nchop : ALU64_rr<(outs IntRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2w($src)",
|
|
[(set (i32 IntRegs:$dst), (fp_to_sint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_sf2uw_nchop : ALU64_rr<(outs IntRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2uw($src)",
|
|
[(set (i32 IntRegs:$dst), (fp_to_uint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_sf2w_nchop : ALU64_rr<(outs IntRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2w($src)",
|
|
[(set (i32 IntRegs:$dst), (fp_to_sint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_df2d_nchop : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2d($src)",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_sint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_df2ud_nchop : ALU64_rr<(outs DoubleRegs:$dst), (ins DoubleRegs:$src),
|
|
"$dst = convert_df2ud($src)",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_uint (f64 DoubleRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_sf2d_nchop : ALU64_rr<(outs DoubleRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2d($src)",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_sint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
let AddedComplexity = 20 in
|
|
def CONVERT_sf2ud_nchop : ALU64_rr<(outs DoubleRegs:$dst), (ins IntRegs:$src),
|
|
"$dst = convert_sf2ud($src)",
|
|
[(set (i64 DoubleRegs:$dst), (fp_to_uint (f32 IntRegs:$src)))]>,
|
|
Requires<[HasV5T, IEEERndNearV5T]>;
|
|
|
|
|
|
|
|
// Bitcast is different than [fp|sint|uint]_to_[sint|uint|fp].
|
|
def : Pat <(i32 (bitconvert (f32 IntRegs:$src))),
|
|
(i32 (A2_tfr IntRegs:$src))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(f32 (bitconvert (i32 IntRegs:$src))),
|
|
(f32 (A2_tfr IntRegs:$src))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(i64 (bitconvert (f64 DoubleRegs:$src))),
|
|
(i64 (A2_tfrp DoubleRegs:$src))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(f64 (bitconvert (i64 DoubleRegs:$src))),
|
|
(f64 (A2_tfrp DoubleRegs:$src))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def FMADD_sp : ALU64_acc<(outs IntRegs:$dst),
|
|
(ins IntRegs:$src1, IntRegs:$src2, IntRegs:$src3),
|
|
"$dst += sfmpy($src2, $src3)",
|
|
[(set (f32 IntRegs:$dst),
|
|
(fma IntRegs:$src2, IntRegs:$src3, IntRegs:$src1))],
|
|
"$src1 = $dst">,
|
|
Requires<[HasV5T]>;
|
|
|
|
|
|
// Floating point max/min.
|
|
|
|
let AddedComplexity = 100 in
|
|
def FMAX_sp : ALU64_rr<(outs IntRegs:$dst),
|
|
(ins IntRegs:$src1, IntRegs:$src2),
|
|
"$dst = sfmax($src1, $src2)",
|
|
[(set IntRegs:$dst, (f32 (select (i1 (setolt IntRegs:$src2,
|
|
IntRegs:$src1)),
|
|
IntRegs:$src1,
|
|
IntRegs:$src2)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let AddedComplexity = 100 in
|
|
def FMIN_sp : ALU64_rr<(outs IntRegs:$dst),
|
|
(ins IntRegs:$src1, IntRegs:$src2),
|
|
"$dst = sfmin($src1, $src2)",
|
|
[(set IntRegs:$dst, (f32 (select (i1 (setogt IntRegs:$src2,
|
|
IntRegs:$src1)),
|
|
IntRegs:$src1,
|
|
IntRegs:$src2)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
// Pseudo instruction to encode a set of conditional transfers.
|
|
// This instruction is used instead of a mux and trades-off codesize
|
|
// for performance. We conduct this transformation optimistically in
|
|
// the hope that these instructions get promoted to dot-new transfers.
|
|
let AddedComplexity = 100, isPredicated = 1 in
|
|
def TFR_condset_rr_f : ALU32_rr<(outs IntRegs:$dst), (ins PredRegs:$src1,
|
|
IntRegs:$src2,
|
|
IntRegs:$src3),
|
|
"Error; should not emit",
|
|
[(set IntRegs:$dst, (f32 (select PredRegs:$src1,
|
|
IntRegs:$src2,
|
|
IntRegs:$src3)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let AddedComplexity = 100, isPredicated = 1 in
|
|
def TFR_condset_rr64_f : ALU32_rr<(outs DoubleRegs:$dst), (ins PredRegs:$src1,
|
|
DoubleRegs:$src2,
|
|
DoubleRegs:$src3),
|
|
"Error; should not emit",
|
|
[(set DoubleRegs:$dst, (f64 (select PredRegs:$src1,
|
|
DoubleRegs:$src2,
|
|
DoubleRegs:$src3)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
|
|
|
|
let AddedComplexity = 100, isPredicated = 1 in
|
|
def TFR_condset_ri_f : ALU32_rr<(outs IntRegs:$dst),
|
|
(ins PredRegs:$src1, IntRegs:$src2, f32imm:$src3),
|
|
"Error; should not emit",
|
|
[(set IntRegs:$dst,
|
|
(f32 (select PredRegs:$src1, IntRegs:$src2, fpimm:$src3)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let AddedComplexity = 100, isPredicated = 1 in
|
|
def TFR_condset_ir_f : ALU32_rr<(outs IntRegs:$dst),
|
|
(ins PredRegs:$src1, f32imm:$src2, IntRegs:$src3),
|
|
"Error; should not emit",
|
|
[(set IntRegs:$dst,
|
|
(f32 (select PredRegs:$src1, fpimm:$src2, IntRegs:$src3)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
let AddedComplexity = 100, isPredicated = 1 in
|
|
def TFR_condset_ii_f : ALU32_rr<(outs IntRegs:$dst),
|
|
(ins PredRegs:$src1, f32imm:$src2, f32imm:$src3),
|
|
"Error; should not emit",
|
|
[(set IntRegs:$dst, (f32 (select PredRegs:$src1,
|
|
fpimm:$src2,
|
|
fpimm:$src3)))]>,
|
|
Requires<[HasV5T]>;
|
|
|
|
|
|
def : Pat <(select (i1 (setult (f32 IntRegs:$src1), (f32 IntRegs:$src2))),
|
|
(f32 IntRegs:$src3),
|
|
(f32 IntRegs:$src4)),
|
|
(TFR_condset_rr_f (FCMPUGT32_rr IntRegs:$src2, IntRegs:$src1), IntRegs:$src4,
|
|
IntRegs:$src3)>, Requires<[HasV5T]>;
|
|
|
|
def : Pat <(select (i1 (setult (f64 DoubleRegs:$src1), (f64 DoubleRegs:$src2))),
|
|
(f64 DoubleRegs:$src3),
|
|
(f64 DoubleRegs:$src4)),
|
|
(TFR_condset_rr64_f (FCMPUGT64_rr DoubleRegs:$src2, DoubleRegs:$src1),
|
|
DoubleRegs:$src4, DoubleRegs:$src3)>, Requires<[HasV5T]>;
|
|
|
|
// Map from p0 = pnot(p0); r0 = mux(p0, #i, #j) => r0 = mux(p0, #j, #i).
|
|
def : Pat <(select (not PredRegs:$src1), fpimm:$src2, fpimm:$src3),
|
|
(TFR_condset_ii_f PredRegs:$src1, fpimm:$src3, fpimm:$src2)>;
|
|
|
|
// Map from p0 = pnot(p0); r0 = select(p0, #i, r1)
|
|
// => r0 = TFR_condset_ri(p0, r1, #i)
|
|
def : Pat <(select (not PredRegs:$src1), fpimm:$src2, IntRegs:$src3),
|
|
(TFR_condset_ri_f PredRegs:$src1, IntRegs:$src3, fpimm:$src2)>;
|
|
|
|
// Map from p0 = pnot(p0); r0 = mux(p0, r1, #i)
|
|
// => r0 = TFR_condset_ir(p0, #i, r1)
|
|
def : Pat <(select (not PredRegs:$src1), IntRegs:$src2, fpimm:$src3),
|
|
(TFR_condset_ir_f PredRegs:$src1, fpimm:$src3, IntRegs:$src2)>;
|
|
|
|
def : Pat <(i32 (fp_to_sint (f64 DoubleRegs:$src1))),
|
|
(i32 (EXTRACT_SUBREG (i64 (CONVERT_df2d (f64 DoubleRegs:$src1))), subreg_loreg))>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(fabs (f32 IntRegs:$src1)),
|
|
(S2_clrbit_i (f32 IntRegs:$src1), 31)>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(fneg (f32 IntRegs:$src1)),
|
|
(S2_togglebit_i (f32 IntRegs:$src1), 31)>,
|
|
Requires<[HasV5T]>;
|
|
|
|
/*
|
|
def : Pat <(fabs (f64 DoubleRegs:$src1)),
|
|
(S2_clrbit_i (f32 (EXTRACT_SUBREG DoubleRegs:$src1, subreg_hireg)), 31)>,
|
|
Requires<[HasV5T]>;
|
|
|
|
def : Pat <(fabs (f64 DoubleRegs:$src1)),
|
|
(S2_clrbit_i (f32 (EXTRACT_SUBREG DoubleRegs:$src1, subreg_hireg)), 31)>,
|
|
Requires<[HasV5T]>;
|
|
*/
|