forked from OSchip/llvm-project
1977 lines
72 KiB
TableGen
1977 lines
72 KiB
TableGen
//===-- SOPInstructions.td - SOP Instruction Definitions ------------------===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def GPRIdxModeMatchClass : AsmOperandClass {
|
|
let Name = "GPRIdxMode";
|
|
let PredicateMethod = "isGPRIdxMode";
|
|
let ParserMethod = "parseGPRIdxMode";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def GPRIdxMode : Operand<i32> {
|
|
let PrintMethod = "printVGPRIndexMode";
|
|
let ParserMatchClass = GPRIdxModeMatchClass;
|
|
let OperandType = "OPERAND_IMMEDIATE";
|
|
}
|
|
|
|
class SOP_Pseudo<string opName, dag outs, dag ins, string asmOps,
|
|
list<dag> pattern=[]> :
|
|
InstSI<outs, ins, "", pattern>,
|
|
SIMCInstr<opName, SIEncodingFamily.NONE> {
|
|
|
|
let isPseudo = 1;
|
|
let isCodeGenOnly = 1;
|
|
|
|
string Mnemonic = opName;
|
|
string AsmOperands = asmOps;
|
|
|
|
bits<1> has_sdst = 0;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP1 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class SOP1_Pseudo <string opName, dag outs, dag ins,
|
|
string asmOps, list<dag> pattern=[]> :
|
|
SOP_Pseudo<opName, outs, ins, asmOps, pattern> {
|
|
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
let hasSideEffects = 0;
|
|
let SALU = 1;
|
|
let SOP1 = 1;
|
|
let SchedRW = [WriteSALU];
|
|
let Size = 4;
|
|
let UseNamedOperandTable = 1;
|
|
|
|
bits<1> has_src0 = 1;
|
|
bits<1> has_sdst = 1;
|
|
}
|
|
|
|
class SOP1_Real<bits<8> op, SOP1_Pseudo ps, string real_name = ps.Mnemonic> :
|
|
InstSI <ps.OutOperandList, ps.InOperandList,
|
|
real_name # " " # ps.AsmOperands, []>,
|
|
Enc32 {
|
|
|
|
let isPseudo = 0;
|
|
let isCodeGenOnly = 0;
|
|
let Size = 4;
|
|
|
|
// copy relevant pseudo op flags
|
|
let SubtargetPredicate = ps.SubtargetPredicate;
|
|
let AsmMatchConverter = ps.AsmMatchConverter;
|
|
|
|
// encoding
|
|
bits<7> sdst;
|
|
bits<8> src0;
|
|
|
|
let Inst{7-0} = !if(ps.has_src0, src0, ?);
|
|
let Inst{15-8} = op;
|
|
let Inst{22-16} = !if(ps.has_sdst, sdst, ?);
|
|
let Inst{31-23} = 0x17d; //encoding;
|
|
}
|
|
|
|
class SOP1_32 <string opName, list<dag> pattern=[], bit tied_in = 0> : SOP1_Pseudo <
|
|
opName, (outs SReg_32:$sdst),
|
|
!if(tied_in, (ins SSrc_b32:$src0, SReg_32:$sdst_in),
|
|
(ins SSrc_b32:$src0)),
|
|
"$sdst, $src0", pattern> {
|
|
let Constraints = !if(tied_in, "$sdst = $sdst_in", "");
|
|
}
|
|
|
|
// Only register input allowed.
|
|
class SOP1_32R <string opName, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs SReg_32:$sdst), (ins SReg_32:$src0),
|
|
"$sdst, $src0", pattern>;
|
|
|
|
// 32-bit input, no output.
|
|
class SOP1_0_32 <string opName, list<dag> pattern = []> : SOP1_Pseudo <
|
|
opName, (outs), (ins SSrc_b32:$src0),
|
|
"$src0", pattern> {
|
|
let has_sdst = 0;
|
|
}
|
|
|
|
// Special case for movreld where sdst is treated as a use operand.
|
|
class SOP1_32_movreld <string opName, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs), (ins SReg_32:$sdst, SSrc_b32:$src0),
|
|
"$sdst, $src0", pattern>;
|
|
|
|
// Special case for movreld where sdst is treated as a use operand.
|
|
class SOP1_64_movreld <string opName, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs), (ins SReg_64:$sdst, SSrc_b64:$src0),
|
|
"$sdst, $src0", pattern
|
|
>;
|
|
|
|
class SOP1_0_32R <string opName, list<dag> pattern = []> : SOP1_Pseudo <
|
|
opName, (outs), (ins SReg_32:$src0),
|
|
"$src0", pattern> {
|
|
let has_sdst = 0;
|
|
}
|
|
|
|
class SOP1_64 <string opName, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs SReg_64:$sdst), (ins SSrc_b64:$src0),
|
|
"$sdst, $src0", pattern
|
|
>;
|
|
|
|
// Only register input allowed.
|
|
class SOP1_64R <string opName, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs SReg_64:$sdst), (ins SReg_64:$src0),
|
|
"$sdst, $src0", pattern
|
|
>;
|
|
|
|
// 64-bit input, 32-bit output.
|
|
class SOP1_32_64 <string opName, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs SReg_32:$sdst), (ins SSrc_b64:$src0),
|
|
"$sdst, $src0", pattern
|
|
>;
|
|
|
|
// 32-bit input, 64-bit output.
|
|
class SOP1_64_32 <string opName, list<dag> pattern=[], bit tied_in = 0> : SOP1_Pseudo <
|
|
opName, (outs SReg_64:$sdst),
|
|
!if(tied_in, (ins SSrc_b32:$src0, SReg_64:$sdst_in),
|
|
(ins SSrc_b32:$src0)),
|
|
"$sdst, $src0", pattern> {
|
|
let Constraints = !if(tied_in, "$sdst = $sdst_in", "");
|
|
}
|
|
|
|
// no input, 64-bit output.
|
|
class SOP1_64_0 <string opName, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs SReg_64:$sdst), (ins), "$sdst", pattern> {
|
|
let has_src0 = 0;
|
|
}
|
|
|
|
// 64-bit input, no output
|
|
class SOP1_1 <string opName, RegisterClass rc = SReg_64, list<dag> pattern=[]> : SOP1_Pseudo <
|
|
opName, (outs), (ins rc:$src0), "$src0", pattern> {
|
|
let has_sdst = 0;
|
|
}
|
|
|
|
|
|
let isMoveImm = 1 in {
|
|
let isReMaterializable = 1, isAsCheapAsAMove = 1 in {
|
|
def S_MOV_B32 : SOP1_32 <"s_mov_b32">;
|
|
def S_MOV_B64 : SOP1_64 <"s_mov_b64">;
|
|
} // End isRematerializeable = 1
|
|
|
|
let Uses = [SCC] in {
|
|
def S_CMOV_B32 : SOP1_32 <"s_cmov_b32">;
|
|
def S_CMOV_B64 : SOP1_64 <"s_cmov_b64">;
|
|
} // End Uses = [SCC]
|
|
} // End isMoveImm = 1
|
|
|
|
let Defs = [SCC] in {
|
|
def S_NOT_B32 : SOP1_32 <"s_not_b32",
|
|
[(set i32:$sdst, (not i32:$src0))]
|
|
>;
|
|
|
|
def S_NOT_B64 : SOP1_64 <"s_not_b64",
|
|
[(set i64:$sdst, (not i64:$src0))]
|
|
>;
|
|
def S_WQM_B32 : SOP1_32 <"s_wqm_b32">;
|
|
def S_WQM_B64 : SOP1_64 <"s_wqm_b64">;
|
|
} // End Defs = [SCC]
|
|
|
|
|
|
let WaveSizePredicate = isWave32 in {
|
|
def : GCNPat <
|
|
(int_amdgcn_wqm_vote i1:$src0),
|
|
(S_WQM_B32 SSrc_b32:$src0)
|
|
>;
|
|
}
|
|
|
|
let WaveSizePredicate = isWave64 in {
|
|
def : GCNPat <
|
|
(int_amdgcn_wqm_vote i1:$src0),
|
|
(S_WQM_B64 SSrc_b64:$src0)
|
|
>;
|
|
}
|
|
|
|
def S_BREV_B32 : SOP1_32 <"s_brev_b32",
|
|
[(set i32:$sdst, (bitreverse i32:$src0))]
|
|
>;
|
|
def S_BREV_B64 : SOP1_64 <"s_brev_b64">;
|
|
|
|
let Defs = [SCC] in {
|
|
def S_BCNT0_I32_B32 : SOP1_32 <"s_bcnt0_i32_b32">;
|
|
def S_BCNT0_I32_B64 : SOP1_32_64 <"s_bcnt0_i32_b64">;
|
|
def S_BCNT1_I32_B32 : SOP1_32 <"s_bcnt1_i32_b32",
|
|
[(set i32:$sdst, (ctpop i32:$src0))]
|
|
>;
|
|
def S_BCNT1_I32_B64 : SOP1_32_64 <"s_bcnt1_i32_b64",
|
|
[(set i32:$sdst, (ctpop i64:$src0))]
|
|
>;
|
|
} // End Defs = [SCC]
|
|
|
|
def S_FF0_I32_B32 : SOP1_32 <"s_ff0_i32_b32">;
|
|
def S_FF0_I32_B64 : SOP1_32_64 <"s_ff0_i32_b64">;
|
|
def S_FF1_I32_B64 : SOP1_32_64 <"s_ff1_i32_b64",
|
|
[(set i32:$sdst, (AMDGPUffbl_b32 i64:$src0))]
|
|
>;
|
|
|
|
def S_FF1_I32_B32 : SOP1_32 <"s_ff1_i32_b32",
|
|
[(set i32:$sdst, (AMDGPUffbl_b32 i32:$src0))]
|
|
>;
|
|
|
|
def S_FLBIT_I32_B32 : SOP1_32 <"s_flbit_i32_b32",
|
|
[(set i32:$sdst, (AMDGPUffbh_u32 i32:$src0))]
|
|
>;
|
|
|
|
def S_FLBIT_I32_B64 : SOP1_32_64 <"s_flbit_i32_b64",
|
|
[(set i32:$sdst, (AMDGPUffbh_u32 i64:$src0))]
|
|
>;
|
|
def S_FLBIT_I32 : SOP1_32 <"s_flbit_i32",
|
|
[(set i32:$sdst, (AMDGPUffbh_i32 i32:$src0))]
|
|
>;
|
|
def S_FLBIT_I32_I64 : SOP1_32_64 <"s_flbit_i32_i64">;
|
|
def S_SEXT_I32_I8 : SOP1_32 <"s_sext_i32_i8",
|
|
[(set i32:$sdst, (sext_inreg i32:$src0, i8))]
|
|
>;
|
|
def S_SEXT_I32_I16 : SOP1_32 <"s_sext_i32_i16",
|
|
[(set i32:$sdst, (sext_inreg i32:$src0, i16))]
|
|
>;
|
|
|
|
def S_BITSET0_B32 : SOP1_32 <"s_bitset0_b32", [], 1>;
|
|
def S_BITSET0_B64 : SOP1_64_32 <"s_bitset0_b64", [], 1>;
|
|
def S_BITSET1_B32 : SOP1_32 <"s_bitset1_b32", [], 1>;
|
|
def S_BITSET1_B64 : SOP1_64_32 <"s_bitset1_b64", [], 1>;
|
|
def S_GETPC_B64 : SOP1_64_0 <"s_getpc_b64",
|
|
[(set i64:$sdst, (int_amdgcn_s_getpc))]
|
|
>;
|
|
|
|
let isTerminator = 1, isBarrier = 1, SchedRW = [WriteBranch] in {
|
|
|
|
let isBranch = 1, isIndirectBranch = 1 in {
|
|
def S_SETPC_B64 : SOP1_1 <"s_setpc_b64">;
|
|
} // End isBranch = 1, isIndirectBranch = 1
|
|
|
|
let isReturn = 1 in {
|
|
// Define variant marked as return rather than branch.
|
|
def S_SETPC_B64_return : SOP1_1<"", CCR_SGPR_64, [(AMDGPUret_flag i64:$src0)]>;
|
|
}
|
|
} // End isTerminator = 1, isBarrier = 1
|
|
|
|
let isCall = 1 in {
|
|
def S_SWAPPC_B64 : SOP1_64 <"s_swappc_b64"
|
|
>;
|
|
}
|
|
|
|
def S_RFE_B64 : SOP1_1 <"s_rfe_b64">;
|
|
|
|
let hasSideEffects = 1, Uses = [EXEC], Defs = [EXEC, SCC] in {
|
|
|
|
def S_AND_SAVEEXEC_B64 : SOP1_64 <"s_and_saveexec_b64">;
|
|
def S_OR_SAVEEXEC_B64 : SOP1_64 <"s_or_saveexec_b64">;
|
|
def S_XOR_SAVEEXEC_B64 : SOP1_64 <"s_xor_saveexec_b64">;
|
|
def S_ANDN2_SAVEEXEC_B64 : SOP1_64 <"s_andn2_saveexec_b64">;
|
|
def S_ORN2_SAVEEXEC_B64 : SOP1_64 <"s_orn2_saveexec_b64">;
|
|
def S_NAND_SAVEEXEC_B64 : SOP1_64 <"s_nand_saveexec_b64">;
|
|
def S_NOR_SAVEEXEC_B64 : SOP1_64 <"s_nor_saveexec_b64">;
|
|
def S_XNOR_SAVEEXEC_B64 : SOP1_64 <"s_xnor_saveexec_b64">;
|
|
|
|
} // End hasSideEffects = 1, Uses = [EXEC], Defs = [EXEC, SCC]
|
|
|
|
def S_QUADMASK_B32 : SOP1_32 <"s_quadmask_b32">;
|
|
def S_QUADMASK_B64 : SOP1_64 <"s_quadmask_b64">;
|
|
|
|
let Uses = [M0] in {
|
|
def S_MOVRELS_B32 : SOP1_32R <"s_movrels_b32">;
|
|
def S_MOVRELS_B64 : SOP1_64R <"s_movrels_b64">;
|
|
def S_MOVRELD_B32 : SOP1_32_movreld <"s_movreld_b32">;
|
|
def S_MOVRELD_B64 : SOP1_64_movreld <"s_movreld_b64">;
|
|
} // End Uses = [M0]
|
|
|
|
let SubtargetPredicate = isGFX6GFX7GFX8GFX9 in {
|
|
def S_CBRANCH_JOIN : SOP1_0_32R <"s_cbranch_join">;
|
|
} // End SubtargetPredicate = isGFX6GFX7GFX8GFX9
|
|
|
|
let Defs = [SCC] in {
|
|
def S_ABS_I32 : SOP1_32 <"s_abs_i32">;
|
|
} // End Defs = [SCC]
|
|
|
|
let SubtargetPredicate = HasVGPRIndexMode in {
|
|
def S_SET_GPR_IDX_IDX : SOP1_0_32<"s_set_gpr_idx_idx"> {
|
|
let Uses = [M0, MODE];
|
|
let Defs = [M0, MODE];
|
|
}
|
|
}
|
|
|
|
let SubtargetPredicate = isGFX9Plus in {
|
|
let hasSideEffects = 1, Defs = [EXEC, SCC], Uses = [EXEC] in {
|
|
def S_ANDN1_SAVEEXEC_B64 : SOP1_64<"s_andn1_saveexec_b64">;
|
|
def S_ORN1_SAVEEXEC_B64 : SOP1_64<"s_orn1_saveexec_b64">;
|
|
def S_ANDN1_WREXEC_B64 : SOP1_64<"s_andn1_wrexec_b64">;
|
|
def S_ANDN2_WREXEC_B64 : SOP1_64<"s_andn2_wrexec_b64">;
|
|
} // End hasSideEffects = 1, Defs = [EXEC, SCC], Uses = [EXEC]
|
|
|
|
def S_BITREPLICATE_B64_B32 : SOP1_64_32<"s_bitreplicate_b64_b32">;
|
|
} // End SubtargetPredicate = isGFX9Plus
|
|
|
|
let SubtargetPredicate = isGFX10Plus in {
|
|
let hasSideEffects = 1, Defs = [EXEC, SCC], Uses = [EXEC] in {
|
|
def S_AND_SAVEEXEC_B32 : SOP1_32<"s_and_saveexec_b32">;
|
|
def S_OR_SAVEEXEC_B32 : SOP1_32<"s_or_saveexec_b32">;
|
|
def S_XOR_SAVEEXEC_B32 : SOP1_32<"s_xor_saveexec_b32">;
|
|
def S_ANDN2_SAVEEXEC_B32 : SOP1_32<"s_andn2_saveexec_b32">;
|
|
def S_ORN2_SAVEEXEC_B32 : SOP1_32<"s_orn2_saveexec_b32">;
|
|
def S_NAND_SAVEEXEC_B32 : SOP1_32<"s_nand_saveexec_b32">;
|
|
def S_NOR_SAVEEXEC_B32 : SOP1_32<"s_nor_saveexec_b32">;
|
|
def S_XNOR_SAVEEXEC_B32 : SOP1_32<"s_xnor_saveexec_b32">;
|
|
def S_ANDN1_SAVEEXEC_B32 : SOP1_32<"s_andn1_saveexec_b32">;
|
|
def S_ORN1_SAVEEXEC_B32 : SOP1_32<"s_orn1_saveexec_b32">;
|
|
def S_ANDN1_WREXEC_B32 : SOP1_32<"s_andn1_wrexec_b32">;
|
|
def S_ANDN2_WREXEC_B32 : SOP1_32<"s_andn2_wrexec_b32">;
|
|
} // End hasSideEffects = 1, Defs = [EXEC, SCC], Uses = [EXEC]
|
|
|
|
let Uses = [M0] in {
|
|
def S_MOVRELSD_2_B32 : SOP1_32<"s_movrelsd_2_b32">;
|
|
} // End Uses = [M0]
|
|
} // End SubtargetPredicate = isGFX10Plus
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP2 Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class SOP2_Pseudo<string opName, dag outs, dag ins,
|
|
string asmOps, list<dag> pattern=[]> :
|
|
SOP_Pseudo<opName, outs, ins, asmOps, pattern> {
|
|
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
let hasSideEffects = 0;
|
|
let SALU = 1;
|
|
let SOP2 = 1;
|
|
let SchedRW = [WriteSALU];
|
|
let UseNamedOperandTable = 1;
|
|
|
|
let has_sdst = 1;
|
|
|
|
// Pseudo instructions have no encodings, but adding this field here allows
|
|
// us to do:
|
|
// let sdst = xxx in {
|
|
// for multiclasses that include both real and pseudo instructions.
|
|
// field bits<7> sdst = 0;
|
|
// let Size = 4; // Do we need size here?
|
|
}
|
|
|
|
class SOP2_Real<bits<7> op, SOP_Pseudo ps, string real_name = ps.Mnemonic> :
|
|
InstSI <ps.OutOperandList, ps.InOperandList,
|
|
real_name # " " # ps.AsmOperands, []>,
|
|
Enc32 {
|
|
let isPseudo = 0;
|
|
let isCodeGenOnly = 0;
|
|
|
|
// copy relevant pseudo op flags
|
|
let SubtargetPredicate = ps.SubtargetPredicate;
|
|
let AsmMatchConverter = ps.AsmMatchConverter;
|
|
let UseNamedOperandTable = ps.UseNamedOperandTable;
|
|
let TSFlags = ps.TSFlags;
|
|
|
|
// encoding
|
|
bits<7> sdst;
|
|
bits<8> src0;
|
|
bits<8> src1;
|
|
|
|
let Inst{7-0} = src0;
|
|
let Inst{15-8} = src1;
|
|
let Inst{22-16} = !if(ps.has_sdst, sdst, ?);
|
|
let Inst{29-23} = op;
|
|
let Inst{31-30} = 0x2; // encoding
|
|
}
|
|
|
|
|
|
class SOP2_32 <string opName, list<dag> pattern=[]> : SOP2_Pseudo <
|
|
opName, (outs SReg_32:$sdst), (ins SSrc_b32:$src0, SSrc_b32:$src1),
|
|
"$sdst, $src0, $src1", pattern
|
|
>;
|
|
|
|
class SOP2_64 <string opName, list<dag> pattern=[]> : SOP2_Pseudo <
|
|
opName, (outs SReg_64:$sdst), (ins SSrc_b64:$src0, SSrc_b64:$src1),
|
|
"$sdst, $src0, $src1", pattern
|
|
>;
|
|
|
|
class SOP2_64_32 <string opName, list<dag> pattern=[]> : SOP2_Pseudo <
|
|
opName, (outs SReg_64:$sdst), (ins SSrc_b64:$src0, SSrc_b32:$src1),
|
|
"$sdst, $src0, $src1", pattern
|
|
>;
|
|
|
|
class SOP2_64_32_32 <string opName, list<dag> pattern=[]> : SOP2_Pseudo <
|
|
opName, (outs SReg_64:$sdst), (ins SSrc_b32:$src0, SSrc_b32:$src1),
|
|
"$sdst, $src0, $src1", pattern
|
|
>;
|
|
|
|
class UniformUnaryFrag<SDPatternOperator Op> : PatFrag <
|
|
(ops node:$src0),
|
|
(Op $src0),
|
|
[{ return !N->isDivergent(); }]> {
|
|
// This check is unnecessary as it's captured by the result register
|
|
// bank constraint.
|
|
//
|
|
// FIXME: Should add a way for the emitter to recognize this is a
|
|
// trivially true predicate to eliminate the check.
|
|
let GISelPredicateCode = [{return true;}];
|
|
}
|
|
|
|
class UniformBinFrag<SDPatternOperator Op> : PatFrag <
|
|
(ops node:$src0, node:$src1),
|
|
(Op $src0, $src1),
|
|
[{ return !N->isDivergent(); }]> {
|
|
// This check is unnecessary as it's captured by the result register
|
|
// bank constraint.
|
|
//
|
|
// FIXME: Should add a way for the emitter to recognize this is a
|
|
// trivially true predicate to eliminate the check.
|
|
let GISelPredicateCode = [{return true;}];
|
|
}
|
|
|
|
class DivergentBinFrag<SDPatternOperator Op> : PatFrag <
|
|
(ops node:$src0, node:$src1),
|
|
(Op $src0, $src1),
|
|
[{ return N->isDivergent(); }]> {
|
|
// This check is unnecessary as it's captured by the result register
|
|
// bank constraint.
|
|
//
|
|
// FIXME: Should add a way for the emitter to recognize this is a
|
|
// trivially true predicate to eliminate the check.
|
|
let GISelPredicateCode = [{return true;}];
|
|
}
|
|
|
|
let Defs = [SCC] in { // Carry out goes to SCC
|
|
let isCommutable = 1 in {
|
|
def S_ADD_U32 : SOP2_32 <"s_add_u32">;
|
|
def S_ADD_I32 : SOP2_32 <"s_add_i32",
|
|
[(set i32:$sdst, (UniformBinFrag<add> SSrc_b32:$src0, SSrc_b32:$src1))]
|
|
>;
|
|
} // End isCommutable = 1
|
|
|
|
def S_SUB_U32 : SOP2_32 <"s_sub_u32">;
|
|
def S_SUB_I32 : SOP2_32 <"s_sub_i32",
|
|
[(set i32:$sdst, (UniformBinFrag<sub> SSrc_b32:$src0, SSrc_b32:$src1))]
|
|
>;
|
|
|
|
let Uses = [SCC] in { // Carry in comes from SCC
|
|
let isCommutable = 1 in {
|
|
def S_ADDC_U32 : SOP2_32 <"s_addc_u32",
|
|
[(set i32:$sdst, (UniformBinFrag<adde> (i32 SSrc_b32:$src0), (i32 SSrc_b32:$src1)))]>;
|
|
} // End isCommutable = 1
|
|
|
|
def S_SUBB_U32 : SOP2_32 <"s_subb_u32",
|
|
[(set i32:$sdst, (UniformBinFrag<sube> (i32 SSrc_b32:$src0), (i32 SSrc_b32:$src1)))]>;
|
|
} // End Uses = [SCC]
|
|
|
|
|
|
let isCommutable = 1 in {
|
|
def S_MIN_I32 : SOP2_32 <"s_min_i32",
|
|
[(set i32:$sdst, (smin i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_MIN_U32 : SOP2_32 <"s_min_u32",
|
|
[(set i32:$sdst, (umin i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_MAX_I32 : SOP2_32 <"s_max_i32",
|
|
[(set i32:$sdst, (smax i32:$src0, i32:$src1))]
|
|
>;
|
|
def S_MAX_U32 : SOP2_32 <"s_max_u32",
|
|
[(set i32:$sdst, (umax i32:$src0, i32:$src1))]
|
|
>;
|
|
} // End isCommutable = 1
|
|
} // End Defs = [SCC]
|
|
|
|
// This pattern is restricted to certain subtargets (practically GFX8Plus)
|
|
// because isel sometimes produces an sreg_64 copy to SCC as a by-product
|
|
// of this pattern, and only for subtargets with hasScalarCompareEq64
|
|
// is it possible to map such copy to a single instruction (S_CMP_LG_U64).
|
|
class SelectPat<SDPatternOperator select> : PatFrag <
|
|
(ops node:$src1, node:$src2),
|
|
(select SCC, $src1, $src2),
|
|
[{ return Subtarget->hasScalarCompareEq64() &&
|
|
N->getOperand(0)->hasOneUse() && !N->isDivergent(); }]
|
|
>;
|
|
|
|
let Uses = [SCC] in {
|
|
let AddedComplexity = 20 in {
|
|
def S_CSELECT_B32 : SOP2_32 <"s_cselect_b32",
|
|
[(set i32:$sdst, (SelectPat<select> i32:$src0, i32:$src1))]
|
|
>;
|
|
}
|
|
|
|
def S_CSELECT_B64 : SOP2_64 <"s_cselect_b64">;
|
|
} // End Uses = [SCC]
|
|
|
|
let Defs = [SCC] in {
|
|
let isCommutable = 1 in {
|
|
def S_AND_B32 : SOP2_32 <"s_and_b32",
|
|
[(set i32:$sdst, (UniformBinFrag<and> i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
def S_AND_B64 : SOP2_64 <"s_and_b64",
|
|
[(set i64:$sdst, (UniformBinFrag<and> i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def S_OR_B32 : SOP2_32 <"s_or_b32",
|
|
[(set i32:$sdst, (UniformBinFrag<or> i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
def S_OR_B64 : SOP2_64 <"s_or_b64",
|
|
[(set i64:$sdst, (UniformBinFrag<or> i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def S_XOR_B32 : SOP2_32 <"s_xor_b32",
|
|
[(set i32:$sdst, (UniformBinFrag<xor> i32:$src0, i32:$src1))]
|
|
>;
|
|
|
|
def S_XOR_B64 : SOP2_64 <"s_xor_b64",
|
|
[(set i64:$sdst, (UniformBinFrag<xor> i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def S_XNOR_B32 : SOP2_32 <"s_xnor_b32",
|
|
[(set i32:$sdst, (not (xor_oneuse i32:$src0, i32:$src1)))]
|
|
>;
|
|
|
|
def S_XNOR_B64 : SOP2_64 <"s_xnor_b64",
|
|
[(set i64:$sdst, (not (xor_oneuse i64:$src0, i64:$src1)))]
|
|
>;
|
|
|
|
def S_NAND_B32 : SOP2_32 <"s_nand_b32",
|
|
[(set i32:$sdst, (not (and_oneuse i32:$src0, i32:$src1)))]
|
|
>;
|
|
|
|
def S_NAND_B64 : SOP2_64 <"s_nand_b64",
|
|
[(set i64:$sdst, (not (and_oneuse i64:$src0, i64:$src1)))]
|
|
>;
|
|
|
|
def S_NOR_B32 : SOP2_32 <"s_nor_b32",
|
|
[(set i32:$sdst, (not (or_oneuse i32:$src0, i32:$src1)))]
|
|
>;
|
|
|
|
def S_NOR_B64 : SOP2_64 <"s_nor_b64",
|
|
[(set i64:$sdst, (not (or_oneuse i64:$src0, i64:$src1)))]
|
|
>;
|
|
} // End isCommutable = 1
|
|
|
|
// There are also separate patterns for types other than i32
|
|
def S_ANDN2_B32 : SOP2_32 <"s_andn2_b32",
|
|
[(set i32:$sdst, (UniformBinFrag<and> i32:$src0, (UniformUnaryFrag<not> i32:$src1)))]
|
|
>;
|
|
|
|
def S_ANDN2_B64 : SOP2_64 <"s_andn2_b64",
|
|
[(set i64:$sdst, (UniformBinFrag<and> i64:$src0, (UniformUnaryFrag<not> i64:$src1)))]
|
|
>;
|
|
|
|
def S_ORN2_B32 : SOP2_32 <"s_orn2_b32",
|
|
[(set i32:$sdst, (UniformBinFrag<or> i32:$src0, (UniformUnaryFrag<not> i32:$src1)))]
|
|
>;
|
|
|
|
def S_ORN2_B64 : SOP2_64 <"s_orn2_b64",
|
|
[(set i64:$sdst, (UniformBinFrag<or> i64:$src0, (UniformUnaryFrag<not> i64:$src1)))]
|
|
>;
|
|
} // End Defs = [SCC]
|
|
|
|
// Use added complexity so these patterns are preferred to the VALU patterns.
|
|
let AddedComplexity = 1 in {
|
|
|
|
let Defs = [SCC] in {
|
|
// TODO: b64 versions require VOP3 change since v_lshlrev_b64 is VOP3
|
|
def S_LSHL_B32 : SOP2_32 <"s_lshl_b32",
|
|
[(set SReg_32:$sdst, (UniformBinFrag<shl> (i32 SSrc_b32:$src0), (i32 SSrc_b32:$src1)))]
|
|
>;
|
|
def S_LSHL_B64 : SOP2_64_32 <"s_lshl_b64",
|
|
[(set SReg_64:$sdst, (UniformBinFrag<shl> (i64 SSrc_b64:$src0), (i32 SSrc_b32:$src1)))]
|
|
>;
|
|
def S_LSHR_B32 : SOP2_32 <"s_lshr_b32",
|
|
[(set SReg_32:$sdst, (UniformBinFrag<srl> (i32 SSrc_b32:$src0), (i32 SSrc_b32:$src1)))]
|
|
>;
|
|
def S_LSHR_B64 : SOP2_64_32 <"s_lshr_b64",
|
|
[(set SReg_64:$sdst, (UniformBinFrag<srl> (i64 SSrc_b64:$src0), (i32 SSrc_b32:$src1)))]
|
|
>;
|
|
def S_ASHR_I32 : SOP2_32 <"s_ashr_i32",
|
|
[(set SReg_32:$sdst, (UniformBinFrag<sra> (i32 SSrc_b32:$src0), (i32 SSrc_b32:$src1)))]
|
|
>;
|
|
def S_ASHR_I64 : SOP2_64_32 <"s_ashr_i64",
|
|
[(set SReg_64:$sdst, (UniformBinFrag<sra> (i64 SSrc_b64:$src0), (i32 SSrc_b32:$src1)))]
|
|
>;
|
|
} // End Defs = [SCC]
|
|
|
|
def S_BFM_B32 : SOP2_32 <"s_bfm_b32",
|
|
[(set i32:$sdst, (UniformBinFrag<AMDGPUbfm> i32:$src0, i32:$src1))]>;
|
|
def S_BFM_B64 : SOP2_64_32_32 <"s_bfm_b64">;
|
|
|
|
// TODO: S_MUL_I32 require V_MUL_LO_I32 from VOP3 change
|
|
def S_MUL_I32 : SOP2_32 <"s_mul_i32",
|
|
[(set i32:$sdst, (mul i32:$src0, i32:$src1))]> {
|
|
let isCommutable = 1;
|
|
}
|
|
|
|
} // End AddedComplexity = 1
|
|
|
|
let Defs = [SCC] in {
|
|
def S_BFE_U32 : SOP2_32 <"s_bfe_u32">;
|
|
def S_BFE_I32 : SOP2_32 <"s_bfe_i32">;
|
|
def S_BFE_U64 : SOP2_64_32 <"s_bfe_u64">;
|
|
def S_BFE_I64 : SOP2_64_32 <"s_bfe_i64">;
|
|
} // End Defs = [SCC]
|
|
|
|
def S_CBRANCH_G_FORK : SOP2_Pseudo <
|
|
"s_cbranch_g_fork", (outs),
|
|
(ins SCSrc_b64:$src0, SCSrc_b64:$src1),
|
|
"$src0, $src1"
|
|
> {
|
|
let has_sdst = 0;
|
|
let SubtargetPredicate = isGFX6GFX7GFX8GFX9;
|
|
}
|
|
|
|
let Defs = [SCC] in {
|
|
def S_ABSDIFF_I32 : SOP2_32 <"s_absdiff_i32">;
|
|
} // End Defs = [SCC]
|
|
|
|
let SubtargetPredicate = isGFX8GFX9 in {
|
|
def S_RFE_RESTORE_B64 : SOP2_Pseudo <
|
|
"s_rfe_restore_b64", (outs),
|
|
(ins SSrc_b64:$src0, SSrc_b32:$src1),
|
|
"$src0, $src1"
|
|
> {
|
|
let hasSideEffects = 1;
|
|
let has_sdst = 0;
|
|
}
|
|
}
|
|
|
|
let SubtargetPredicate = isGFX9Plus in {
|
|
def S_PACK_LL_B32_B16 : SOP2_32<"s_pack_ll_b32_b16">;
|
|
def S_PACK_LH_B32_B16 : SOP2_32<"s_pack_lh_b32_b16">;
|
|
def S_PACK_HH_B32_B16 : SOP2_32<"s_pack_hh_b32_b16">;
|
|
|
|
let Defs = [SCC] in {
|
|
def S_LSHL1_ADD_U32 : SOP2_32<"s_lshl1_add_u32",
|
|
[(set i32:$sdst, (shl1_add SSrc_b32:$src0, SSrc_b32:$src1))]
|
|
>;
|
|
def S_LSHL2_ADD_U32 : SOP2_32<"s_lshl2_add_u32",
|
|
[(set i32:$sdst, (shl2_add SSrc_b32:$src0, SSrc_b32:$src1))]
|
|
>;
|
|
def S_LSHL3_ADD_U32 : SOP2_32<"s_lshl3_add_u32",
|
|
[(set i32:$sdst, (shl3_add SSrc_b32:$src0, SSrc_b32:$src1))]
|
|
>;
|
|
def S_LSHL4_ADD_U32 : SOP2_32<"s_lshl4_add_u32",
|
|
[(set i32:$sdst, (shl4_add SSrc_b32:$src0, SSrc_b32:$src1))]
|
|
>;
|
|
} // End Defs = [SCC]
|
|
|
|
let isCommutable = 1 in {
|
|
def S_MUL_HI_U32 : SOP2_32<"s_mul_hi_u32",
|
|
[(set i32:$sdst, (UniformBinFrag<mulhu> SSrc_b32:$src0, SSrc_b32:$src1))]>;
|
|
def S_MUL_HI_I32 : SOP2_32<"s_mul_hi_i32",
|
|
[(set i32:$sdst, (UniformBinFrag<mulhs> SSrc_b32:$src0, SSrc_b32:$src1))]>;
|
|
}
|
|
} // End SubtargetPredicate = isGFX9Plus
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPK Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class SOPK_Pseudo <string opName, dag outs, dag ins,
|
|
string asmOps, list<dag> pattern=[]> :
|
|
InstSI <outs, ins, "", pattern>,
|
|
SIMCInstr<opName, SIEncodingFamily.NONE> {
|
|
let isPseudo = 1;
|
|
let isCodeGenOnly = 1;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
let hasSideEffects = 0;
|
|
let SALU = 1;
|
|
let SOPK = 1;
|
|
let SchedRW = [WriteSALU];
|
|
let UseNamedOperandTable = 1;
|
|
string Mnemonic = opName;
|
|
string AsmOperands = asmOps;
|
|
|
|
bits<1> has_sdst = 1;
|
|
}
|
|
|
|
class SOPK_Real<bits<5> op, SOPK_Pseudo ps> :
|
|
InstSI <ps.OutOperandList, ps.InOperandList,
|
|
ps.Mnemonic # " " # ps.AsmOperands, []> {
|
|
let isPseudo = 0;
|
|
let isCodeGenOnly = 0;
|
|
|
|
// copy relevant pseudo op flags
|
|
let SubtargetPredicate = ps.SubtargetPredicate;
|
|
let AsmMatchConverter = ps.AsmMatchConverter;
|
|
let DisableEncoding = ps.DisableEncoding;
|
|
let Constraints = ps.Constraints;
|
|
|
|
// encoding
|
|
bits<7> sdst;
|
|
bits<16> simm16;
|
|
bits<32> imm;
|
|
}
|
|
|
|
class SOPK_Real32<bits<5> op, SOPK_Pseudo ps> :
|
|
SOPK_Real <op, ps>,
|
|
Enc32 {
|
|
let Inst{15-0} = simm16;
|
|
let Inst{22-16} = !if(ps.has_sdst, sdst, ?);
|
|
let Inst{27-23} = op;
|
|
let Inst{31-28} = 0xb; //encoding
|
|
}
|
|
|
|
class SOPK_Real64<bits<5> op, SOPK_Pseudo ps> :
|
|
SOPK_Real<op, ps>,
|
|
Enc64 {
|
|
let Inst{15-0} = simm16;
|
|
let Inst{22-16} = !if(ps.has_sdst, sdst, ?);
|
|
let Inst{27-23} = op;
|
|
let Inst{31-28} = 0xb; //encoding
|
|
let Inst{63-32} = imm;
|
|
}
|
|
|
|
class SOPKInstTable <bit is_sopk, string cmpOp = ""> {
|
|
bit IsSOPK = is_sopk;
|
|
string BaseCmpOp = cmpOp;
|
|
}
|
|
|
|
class SOPK_32 <string opName, list<dag> pattern=[]> : SOPK_Pseudo <
|
|
opName,
|
|
(outs SReg_32:$sdst),
|
|
(ins s16imm:$simm16),
|
|
"$sdst, $simm16",
|
|
pattern>;
|
|
|
|
class SOPK_32_BR <string opName, list<dag> pattern=[]> : SOPK_Pseudo <
|
|
opName,
|
|
(outs),
|
|
(ins sopp_brtarget:$simm16, SReg_32:$sdst),
|
|
"$sdst, $simm16",
|
|
pattern> {
|
|
let Defs = [EXEC];
|
|
let Uses = [EXEC];
|
|
let isBranch = 1;
|
|
let isTerminator = 1;
|
|
let SchedRW = [WriteBranch];
|
|
}
|
|
|
|
class SOPK_SCC <string opName, string base_op, bit isSignExt> : SOPK_Pseudo <
|
|
opName,
|
|
(outs),
|
|
!if(isSignExt,
|
|
(ins SReg_32:$sdst, s16imm:$simm16),
|
|
(ins SReg_32:$sdst, u16imm:$simm16)),
|
|
"$sdst, $simm16", []>,
|
|
SOPKInstTable<1, base_op>{
|
|
let Defs = [SCC];
|
|
}
|
|
|
|
class SOPK_32TIE <string opName, list<dag> pattern=[]> : SOPK_Pseudo <
|
|
opName,
|
|
(outs SReg_32:$sdst),
|
|
(ins SReg_32:$src0, s16imm:$simm16),
|
|
"$sdst, $simm16",
|
|
pattern
|
|
>;
|
|
|
|
let isReMaterializable = 1, isMoveImm = 1 in {
|
|
def S_MOVK_I32 : SOPK_32 <"s_movk_i32">;
|
|
} // End isReMaterializable = 1
|
|
let Uses = [SCC] in {
|
|
def S_CMOVK_I32 : SOPK_32 <"s_cmovk_i32">;
|
|
}
|
|
|
|
let isCompare = 1 in {
|
|
|
|
// This instruction is disabled for now until we can figure out how to teach
|
|
// the instruction selector to correctly use the S_CMP* vs V_CMP*
|
|
// instructions.
|
|
//
|
|
// When this instruction is enabled the code generator sometimes produces this
|
|
// invalid sequence:
|
|
//
|
|
// SCC = S_CMPK_EQ_I32 SGPR0, imm
|
|
// VCC = COPY SCC
|
|
// VGPR0 = V_CNDMASK VCC, VGPR0, VGPR1
|
|
//
|
|
// def S_CMPK_EQ_I32 : SOPK_SCC <"s_cmpk_eq_i32",
|
|
// [(set i1:$dst, (setcc i32:$src0, imm:$src1, SETEQ))]
|
|
// >;
|
|
|
|
def S_CMPK_EQ_I32 : SOPK_SCC <"s_cmpk_eq_i32", "s_cmp_eq_i32", 1>;
|
|
def S_CMPK_LG_I32 : SOPK_SCC <"s_cmpk_lg_i32", "s_cmp_lg_i32", 1>;
|
|
def S_CMPK_GT_I32 : SOPK_SCC <"s_cmpk_gt_i32", "s_cmp_gt_i32", 1>;
|
|
def S_CMPK_GE_I32 : SOPK_SCC <"s_cmpk_ge_i32", "s_cmp_ge_i32", 1>;
|
|
def S_CMPK_LT_I32 : SOPK_SCC <"s_cmpk_lt_i32", "s_cmp_lt_i32", 1>;
|
|
def S_CMPK_LE_I32 : SOPK_SCC <"s_cmpk_le_i32", "s_cmp_le_i32", 1>;
|
|
|
|
let SOPKZext = 1 in {
|
|
def S_CMPK_EQ_U32 : SOPK_SCC <"s_cmpk_eq_u32", "s_cmp_eq_u32", 0>;
|
|
def S_CMPK_LG_U32 : SOPK_SCC <"s_cmpk_lg_u32", "s_cmp_lg_u32", 0>;
|
|
def S_CMPK_GT_U32 : SOPK_SCC <"s_cmpk_gt_u32", "s_cmp_gt_u32", 0>;
|
|
def S_CMPK_GE_U32 : SOPK_SCC <"s_cmpk_ge_u32", "s_cmp_ge_u32", 0>;
|
|
def S_CMPK_LT_U32 : SOPK_SCC <"s_cmpk_lt_u32", "s_cmp_lt_u32", 0>;
|
|
def S_CMPK_LE_U32 : SOPK_SCC <"s_cmpk_le_u32", "s_cmp_le_u32", 0>;
|
|
} // End SOPKZext = 1
|
|
} // End isCompare = 1
|
|
|
|
let Defs = [SCC], isCommutable = 1, DisableEncoding = "$src0",
|
|
Constraints = "$sdst = $src0" in {
|
|
def S_ADDK_I32 : SOPK_32TIE <"s_addk_i32">;
|
|
def S_MULK_I32 : SOPK_32TIE <"s_mulk_i32">;
|
|
}
|
|
|
|
let SubtargetPredicate = isGFX6GFX7GFX8GFX9 in
|
|
def S_CBRANCH_I_FORK : SOPK_Pseudo <
|
|
"s_cbranch_i_fork",
|
|
(outs), (ins SReg_64:$sdst, sopp_brtarget:$simm16),
|
|
"$sdst, $simm16"
|
|
>;
|
|
|
|
let mayLoad = 1 in {
|
|
// s_getreg_b32 should use hasSideEffects = 1 for tablegen to allow
|
|
// its use in the readcyclecounter selection.
|
|
// FIXME: Need to truncate immediate to 16-bits.
|
|
def S_GETREG_B32 : SOPK_Pseudo <
|
|
"s_getreg_b32",
|
|
(outs SReg_32:$sdst), (ins hwreg:$simm16),
|
|
"$sdst, $simm16",
|
|
[(set i32:$sdst, (int_amdgcn_s_getreg (i32 timm:$simm16)))]> {
|
|
let SOPKZext = 1;
|
|
let hasSideEffects = 1;
|
|
}
|
|
} // End mayLoad = 1
|
|
|
|
let mayLoad = 0, mayStore = 0, Defs = [MODE], Uses = [MODE] in {
|
|
|
|
// FIXME: Need to truncate immediate to 16-bits.
|
|
class S_SETREG_B32_Pseudo <list<dag> pattern=[]> : SOPK_Pseudo <
|
|
"s_setreg_b32",
|
|
(outs), (ins SReg_32:$sdst, hwreg:$simm16),
|
|
"$simm16, $sdst",
|
|
pattern>;
|
|
|
|
def S_SETREG_B32 : S_SETREG_B32_Pseudo <
|
|
[(int_amdgcn_s_setreg (i32 timm:$simm16), i32:$sdst)]> {
|
|
// Use custom inserter to optimize some cases to
|
|
// S_DENORM_MODE/S_ROUND_MODE/S_SETREG_B32_mode.
|
|
let usesCustomInserter = 1;
|
|
let hasSideEffects = 1;
|
|
}
|
|
|
|
// Variant of SETREG that is guaranteed to only touch FP bits in the MODE
|
|
// register, so doesn't have unmodeled side effects.
|
|
def S_SETREG_B32_mode : S_SETREG_B32_Pseudo {
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
// FIXME: Not on SI?
|
|
//def S_GETREG_REGRD_B32 : SOPK_32 <sopk<0x14, 0x13>, "s_getreg_regrd_b32">;
|
|
|
|
class S_SETREG_IMM32_B32_Pseudo : SOPK_Pseudo <
|
|
"s_setreg_imm32_b32",
|
|
(outs), (ins i32imm:$imm, hwreg:$simm16),
|
|
"$simm16, $imm"> {
|
|
let Size = 8; // Unlike every other SOPK instruction.
|
|
let has_sdst = 0;
|
|
}
|
|
|
|
def S_SETREG_IMM32_B32 : S_SETREG_IMM32_B32_Pseudo {
|
|
let hasSideEffects = 1;
|
|
}
|
|
|
|
// Variant of SETREG_IMM32 that is guaranteed to only touch FP bits in the MODE
|
|
// register, so doesn't have unmodeled side effects.
|
|
def S_SETREG_IMM32_B32_mode : S_SETREG_IMM32_B32_Pseudo {
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
} // End mayLoad = 0, mayStore = 0, Defs = [MODE], Uses = [MODE]
|
|
|
|
class SOPK_WAITCNT<string opName, list<dag> pat=[]> :
|
|
SOPK_Pseudo<
|
|
opName,
|
|
(outs),
|
|
(ins SReg_32:$sdst, s16imm:$simm16),
|
|
"$sdst, $simm16",
|
|
pat> {
|
|
let hasSideEffects = 1;
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
let has_sdst = 1; // First source takes place of sdst in encoding
|
|
}
|
|
|
|
let SubtargetPredicate = isGFX9Plus in {
|
|
def S_CALL_B64 : SOPK_Pseudo<
|
|
"s_call_b64",
|
|
(outs SReg_64:$sdst),
|
|
(ins sopp_brtarget:$simm16),
|
|
"$sdst, $simm16"> {
|
|
let isCall = 1;
|
|
}
|
|
} // End SubtargetPredicate = isGFX9Plus
|
|
|
|
let SubtargetPredicate = isGFX10Plus in {
|
|
def S_VERSION : SOPK_Pseudo<
|
|
"s_version",
|
|
(outs),
|
|
(ins s16imm:$simm16),
|
|
"$simm16"> {
|
|
let has_sdst = 0;
|
|
}
|
|
|
|
def S_SUBVECTOR_LOOP_BEGIN : SOPK_32_BR<"s_subvector_loop_begin">;
|
|
def S_SUBVECTOR_LOOP_END : SOPK_32_BR<"s_subvector_loop_end">;
|
|
|
|
def S_WAITCNT_VSCNT : SOPK_WAITCNT<"s_waitcnt_vscnt">;
|
|
def S_WAITCNT_VMCNT : SOPK_WAITCNT<"s_waitcnt_vmcnt">;
|
|
def S_WAITCNT_EXPCNT : SOPK_WAITCNT<"s_waitcnt_expcnt">;
|
|
def S_WAITCNT_LGKMCNT : SOPK_WAITCNT<"s_waitcnt_lgkmcnt">;
|
|
} // End SubtargetPredicate = isGFX10Plus
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPC Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class SOPC_Pseudo<string opName, dag outs, dag ins,
|
|
string asmOps, list<dag> pattern=[]> :
|
|
SOP_Pseudo<opName, outs, ins, asmOps, pattern> {
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
let hasSideEffects = 0;
|
|
let SALU = 1;
|
|
let SOPC = 1;
|
|
let Defs = [SCC];
|
|
let SchedRW = [WriteSALU];
|
|
let UseNamedOperandTable = 1;
|
|
}
|
|
|
|
class SOPC_Real<bits<7> op, SOPC_Pseudo ps, string real_name = ps.Mnemonic> :
|
|
InstSI <ps.OutOperandList, ps.InOperandList,
|
|
real_name # " " # ps.AsmOperands, []>,
|
|
Enc32 {
|
|
let isPseudo = 0;
|
|
let isCodeGenOnly = 0;
|
|
|
|
// copy relevant pseudo op flags
|
|
let SubtargetPredicate = ps.SubtargetPredicate;
|
|
let OtherPredicates = ps.OtherPredicates;
|
|
let AsmMatchConverter = ps.AsmMatchConverter;
|
|
let UseNamedOperandTable = ps.UseNamedOperandTable;
|
|
let TSFlags = ps.TSFlags;
|
|
|
|
// encoding
|
|
bits<8> src0;
|
|
bits<8> src1;
|
|
|
|
let Inst{7-0} = src0;
|
|
let Inst{15-8} = src1;
|
|
let Inst{22-16} = op;
|
|
let Inst{31-23} = 0x17e;
|
|
}
|
|
|
|
class SOPC_Base <RegisterOperand rc0, RegisterOperand rc1,
|
|
string opName, list<dag> pattern = []> : SOPC_Pseudo <
|
|
opName, (outs), (ins rc0:$src0, rc1:$src1),
|
|
"$src0, $src1", pattern > {
|
|
}
|
|
|
|
class SOPC_Helper <RegisterOperand rc, ValueType vt,
|
|
string opName, SDPatternOperator cond> : SOPC_Base <
|
|
rc, rc, opName,
|
|
[(set SCC, (si_setcc_uniform vt:$src0, vt:$src1, cond))] > {
|
|
}
|
|
|
|
class SOPC_CMP_32<string opName,
|
|
SDPatternOperator cond = COND_NULL, string revOp = opName>
|
|
: SOPC_Helper<SSrc_b32, i32, opName, cond>,
|
|
Commutable_REV<revOp, !eq(revOp, opName)>,
|
|
SOPKInstTable<0, opName> {
|
|
let isCompare = 1;
|
|
let isCommutable = 1;
|
|
}
|
|
|
|
class SOPC_CMP_64<string opName,
|
|
SDPatternOperator cond = COND_NULL, string revOp = opName>
|
|
: SOPC_Helper<SSrc_b64, i64, opName, cond>,
|
|
Commutable_REV<revOp, !eq(revOp, opName)> {
|
|
let isCompare = 1;
|
|
let isCommutable = 1;
|
|
}
|
|
|
|
class SOPC_32<string opName, list<dag> pattern = []>
|
|
: SOPC_Base<SSrc_b32, SSrc_b32, opName, pattern>;
|
|
|
|
class SOPC_64_32<string opName, list<dag> pattern = []>
|
|
: SOPC_Base<SSrc_b64, SSrc_b32, opName, pattern>;
|
|
|
|
def S_CMP_EQ_I32 : SOPC_CMP_32 <"s_cmp_eq_i32">;
|
|
def S_CMP_LG_I32 : SOPC_CMP_32 <"s_cmp_lg_i32">;
|
|
def S_CMP_GT_I32 : SOPC_CMP_32 <"s_cmp_gt_i32", COND_SGT>;
|
|
def S_CMP_GE_I32 : SOPC_CMP_32 <"s_cmp_ge_i32", COND_SGE>;
|
|
def S_CMP_LT_I32 : SOPC_CMP_32 <"s_cmp_lt_i32", COND_SLT, "s_cmp_gt_i32">;
|
|
def S_CMP_LE_I32 : SOPC_CMP_32 <"s_cmp_le_i32", COND_SLE, "s_cmp_ge_i32">;
|
|
def S_CMP_EQ_U32 : SOPC_CMP_32 <"s_cmp_eq_u32", COND_EQ>;
|
|
def S_CMP_LG_U32 : SOPC_CMP_32 <"s_cmp_lg_u32", COND_NE>;
|
|
def S_CMP_GT_U32 : SOPC_CMP_32 <"s_cmp_gt_u32", COND_UGT>;
|
|
def S_CMP_GE_U32 : SOPC_CMP_32 <"s_cmp_ge_u32", COND_UGE>;
|
|
def S_CMP_LT_U32 : SOPC_CMP_32 <"s_cmp_lt_u32", COND_ULT, "s_cmp_gt_u32">;
|
|
def S_CMP_LE_U32 : SOPC_CMP_32 <"s_cmp_le_u32", COND_ULE, "s_cmp_ge_u32">;
|
|
|
|
def S_BITCMP0_B32 : SOPC_32 <"s_bitcmp0_b32">;
|
|
def S_BITCMP1_B32 : SOPC_32 <"s_bitcmp1_b32">;
|
|
def S_BITCMP0_B64 : SOPC_64_32 <"s_bitcmp0_b64">;
|
|
def S_BITCMP1_B64 : SOPC_64_32 <"s_bitcmp1_b64">;
|
|
let SubtargetPredicate = isGFX6GFX7GFX8GFX9 in
|
|
def S_SETVSKIP : SOPC_32 <"s_setvskip">;
|
|
|
|
let SubtargetPredicate = isGFX8Plus in {
|
|
def S_CMP_EQ_U64 : SOPC_CMP_64 <"s_cmp_eq_u64", COND_EQ>;
|
|
def S_CMP_LG_U64 : SOPC_CMP_64 <"s_cmp_lg_u64", COND_NE>;
|
|
} // End SubtargetPredicate = isGFX8Plus
|
|
|
|
let SubtargetPredicate = HasVGPRIndexMode in {
|
|
// Setting the GPR index mode is really writing the fields in the mode
|
|
// register. We don't want to add mode register uses to every
|
|
// instruction, and it's too complicated to deal with anyway. This is
|
|
// modeled just as a side effect.
|
|
def S_SET_GPR_IDX_ON : SOPC_Pseudo <
|
|
"s_set_gpr_idx_on" ,
|
|
(outs),
|
|
(ins SSrc_b32:$src0, GPRIdxMode:$src1),
|
|
"$src0, $src1"> {
|
|
let Defs = [M0, MODE]; // No scc def
|
|
let Uses = [M0, MODE]; // Other bits of mode, m0 unmodified.
|
|
let hasSideEffects = 1; // Sets mode.gpr_idx_en
|
|
let FixedSize = 1;
|
|
}
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPP Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class SOPP_Pseudo<string opName, dag ins,
|
|
string asmOps = "", list<dag> pattern=[], string keyName = opName> :
|
|
SOP_Pseudo<opName, (outs), ins, asmOps, pattern> {
|
|
let isPseudo = 1;
|
|
let isCodeGenOnly = 1;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
let hasSideEffects = 0;
|
|
let SALU = 1;
|
|
let SOPP = 1;
|
|
let FixedSize = 1;
|
|
let SchedRW = [WriteSALU];
|
|
let UseNamedOperandTable = 1;
|
|
bits <16> simm16;
|
|
bits <1> fixed_imm = 0;
|
|
string KeyName = keyName;
|
|
}
|
|
|
|
class SOPPRelaxTable <bit isRelaxed, string keyName, string gfxip> {
|
|
bit IsRelaxed = isRelaxed;
|
|
string KeyName = keyName # gfxip;
|
|
}
|
|
|
|
//spaces inserted in realname on instantiation of this record to allow s_endpgm to omit whitespace
|
|
class SOPP_Real<bits<7> op, SOPP_Pseudo ps, string real_name = ps.Mnemonic> :
|
|
InstSI <ps.OutOperandList, ps.InOperandList,
|
|
real_name # ps.AsmOperands, []> {
|
|
let isPseudo = 0;
|
|
let isCodeGenOnly = 0;
|
|
|
|
// copy relevant pseudo op flags
|
|
let SubtargetPredicate = ps.SubtargetPredicate;
|
|
let OtherPredicates = ps.OtherPredicates;
|
|
let AsmMatchConverter = ps.AsmMatchConverter;
|
|
let UseNamedOperandTable = ps.UseNamedOperandTable;
|
|
let TSFlags = ps.TSFlags;
|
|
bits <16> simm16;
|
|
}
|
|
|
|
class SOPP_Real_32 <bits<7> op, SOPP_Pseudo ps, string real_name = ps.Mnemonic> : SOPP_Real<op, ps, real_name>,
|
|
Enc32 {
|
|
let Inst{15-0} = !if(ps.fixed_imm, ps.simm16, simm16);
|
|
let Inst{22-16} = op;
|
|
let Inst{31-23} = 0x17f;
|
|
}
|
|
|
|
class SOPP_Real_64 <bits<7> op, SOPP_Pseudo ps, string real_name = ps.Mnemonic> : SOPP_Real<op, ps, real_name>,
|
|
Enc64 {
|
|
// encoding
|
|
let Inst{15-0} = !if(ps.fixed_imm, ps.simm16, simm16);
|
|
let Inst{22-16} = op;
|
|
let Inst{31-23} = 0x17f;
|
|
//effectively a nop
|
|
let Inst{47-32} = 0x0;
|
|
let Inst{54-48} = 0x0;
|
|
let Inst{63-55} = 0x17f;
|
|
}
|
|
|
|
multiclass SOPP_With_Relaxation <string opName, dag ins,
|
|
string asmOps, list<dag> pattern=[]> {
|
|
def "" : SOPP_Pseudo <opName, ins, asmOps, pattern>;
|
|
def _pad_s_nop : SOPP_Pseudo <opName # "_pad_s_nop", ins, asmOps, pattern, opName>;
|
|
}
|
|
|
|
def S_NOP : SOPP_Pseudo<"s_nop" , (ins i16imm:$simm16), "$simm16">;
|
|
|
|
let isTerminator = 1 in {
|
|
def S_ENDPGM : SOPP_Pseudo<"s_endpgm", (ins EndpgmImm:$simm16), "$simm16"> {
|
|
let isBarrier = 1;
|
|
let isReturn = 1;
|
|
let hasSideEffects = 1;
|
|
}
|
|
|
|
def S_ENDPGM_SAVED : SOPP_Pseudo<"s_endpgm_saved", (ins)> {
|
|
let SubtargetPredicate = isGFX8Plus;
|
|
let simm16 = 0;
|
|
let fixed_imm = 1;
|
|
let isBarrier = 1;
|
|
let isReturn = 1;
|
|
}
|
|
|
|
let SubtargetPredicate = isGFX9Plus in {
|
|
let isBarrier = 1, isReturn = 1, simm16 = 0, fixed_imm = 1 in {
|
|
def S_ENDPGM_ORDERED_PS_DONE :
|
|
SOPP_Pseudo<"s_endpgm_ordered_ps_done", (ins)>;
|
|
} // End isBarrier = 1, isReturn = 1, simm16 = 0, fixed_imm = 1
|
|
} // End SubtargetPredicate = isGFX9Plus
|
|
|
|
let SubtargetPredicate = isGFX10Plus in {
|
|
let isBarrier = 1, isReturn = 1, simm16 = 0, fixed_imm = 1 in {
|
|
def S_CODE_END :
|
|
SOPP_Pseudo<"s_code_end", (ins)>;
|
|
} // End isBarrier = 1, isReturn = 1, simm16 = 0, fixed_imm = 1
|
|
} // End SubtargetPredicate = isGFX10Plus
|
|
|
|
let isBranch = 1, SchedRW = [WriteBranch] in {
|
|
let isBarrier = 1 in {
|
|
defm S_BRANCH : SOPP_With_Relaxation<
|
|
"s_branch" , (ins sopp_brtarget:$simm16), "$simm16",
|
|
[(br bb:$simm16)]>;
|
|
}
|
|
|
|
let Uses = [SCC] in {
|
|
defm S_CBRANCH_SCC0 : SOPP_With_Relaxation<
|
|
"s_cbranch_scc0" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
defm S_CBRANCH_SCC1 : SOPP_With_Relaxation <
|
|
"s_cbranch_scc1" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
} // End Uses = [SCC]
|
|
|
|
let Uses = [VCC] in {
|
|
defm S_CBRANCH_VCCZ : SOPP_With_Relaxation <
|
|
"s_cbranch_vccz" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
defm S_CBRANCH_VCCNZ : SOPP_With_Relaxation <
|
|
"s_cbranch_vccnz" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
} // End Uses = [VCC]
|
|
|
|
let Uses = [EXEC] in {
|
|
defm S_CBRANCH_EXECZ : SOPP_With_Relaxation <
|
|
"s_cbranch_execz" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
defm S_CBRANCH_EXECNZ : SOPP_With_Relaxation <
|
|
"s_cbranch_execnz" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
} // End Uses = [EXEC]
|
|
|
|
defm S_CBRANCH_CDBGSYS : SOPP_With_Relaxation <
|
|
"s_cbranch_cdbgsys" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
|
|
defm S_CBRANCH_CDBGSYS_AND_USER : SOPP_With_Relaxation <
|
|
"s_cbranch_cdbgsys_and_user" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
|
|
defm S_CBRANCH_CDBGSYS_OR_USER : SOPP_With_Relaxation <
|
|
"s_cbranch_cdbgsys_or_user" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
|
|
defm S_CBRANCH_CDBGUSER : SOPP_With_Relaxation <
|
|
"s_cbranch_cdbguser" , (ins sopp_brtarget:$simm16),
|
|
"$simm16"
|
|
>;
|
|
|
|
} // End isBranch = 1
|
|
} // End isTerminator = 1
|
|
|
|
let hasSideEffects = 1 in {
|
|
def S_BARRIER : SOPP_Pseudo <"s_barrier", (ins), "",
|
|
[(int_amdgcn_s_barrier)]> {
|
|
let SchedRW = [WriteBarrier];
|
|
let simm16 = 0;
|
|
let fixed_imm = 1;
|
|
let isConvergent = 1;
|
|
}
|
|
|
|
def S_WAKEUP : SOPP_Pseudo <"s_wakeup", (ins) > {
|
|
let SubtargetPredicate = isGFX8Plus;
|
|
let simm16 = 0;
|
|
let fixed_imm = 1;
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
|
|
def S_WAITCNT : SOPP_Pseudo <"s_waitcnt" , (ins WAIT_FLAG:$simm16), "$simm16",
|
|
[(int_amdgcn_s_waitcnt timm:$simm16)]>;
|
|
def S_SETHALT : SOPP_Pseudo <"s_sethalt" , (ins i16imm:$simm16), "$simm16">;
|
|
def S_SETKILL : SOPP_Pseudo <"s_setkill" , (ins i16imm:$simm16), "$simm16">;
|
|
|
|
// On SI the documentation says sleep for approximately 64 * low 2
|
|
// bits, consistent with the reported maximum of 448. On VI the
|
|
// maximum reported is 960 cycles, so 960 / 64 = 15 max, so is the
|
|
// maximum really 15 on VI?
|
|
def S_SLEEP : SOPP_Pseudo <"s_sleep", (ins i32imm:$simm16),
|
|
"$simm16", [(int_amdgcn_s_sleep timm:$simm16)]> {
|
|
let hasSideEffects = 1;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
}
|
|
|
|
def S_SETPRIO : SOPP_Pseudo <"s_setprio" , (ins i16imm:$simm16), "$simm16">;
|
|
|
|
let Uses = [EXEC, M0] in {
|
|
// FIXME: Should this be mayLoad+mayStore?
|
|
def S_SENDMSG : SOPP_Pseudo <"s_sendmsg" , (ins SendMsgImm:$simm16), "$simm16",
|
|
[(int_amdgcn_s_sendmsg (i32 timm:$simm16), M0)]>;
|
|
|
|
def S_SENDMSGHALT : SOPP_Pseudo <"s_sendmsghalt" , (ins SendMsgImm:$simm16), "$simm16",
|
|
[(int_amdgcn_s_sendmsghalt (i32 timm:$simm16), M0)]>;
|
|
|
|
} // End Uses = [EXEC, M0]
|
|
|
|
def S_TRAP : SOPP_Pseudo <"s_trap" , (ins i16imm:$simm16), "$simm16"> {
|
|
let isTrap = 1;
|
|
}
|
|
|
|
def S_ICACHE_INV : SOPP_Pseudo <"s_icache_inv", (ins)> {
|
|
let simm16 = 0;
|
|
let fixed_imm = 1;
|
|
}
|
|
def S_INCPERFLEVEL : SOPP_Pseudo <"s_incperflevel", (ins i32imm:$simm16), "$simm16",
|
|
[(int_amdgcn_s_incperflevel timm:$simm16)]> {
|
|
let hasSideEffects = 1;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
}
|
|
def S_DECPERFLEVEL : SOPP_Pseudo <"s_decperflevel", (ins i32imm:$simm16), "$simm16",
|
|
[(int_amdgcn_s_decperflevel timm:$simm16)]> {
|
|
let hasSideEffects = 1;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
}
|
|
def S_TTRACEDATA : SOPP_Pseudo <"s_ttracedata", (ins)> {
|
|
let simm16 = 0;
|
|
let fixed_imm = 1;
|
|
}
|
|
|
|
let SubtargetPredicate = HasVGPRIndexMode in {
|
|
def S_SET_GPR_IDX_OFF : SOPP_Pseudo<"s_set_gpr_idx_off", (ins) > {
|
|
let simm16 = 0;
|
|
let fixed_imm = 1;
|
|
let Defs = [MODE];
|
|
let Uses = [MODE];
|
|
}
|
|
}
|
|
} // End hasSideEffects
|
|
|
|
let SubtargetPredicate = HasVGPRIndexMode in {
|
|
def S_SET_GPR_IDX_MODE : SOPP_Pseudo<"s_set_gpr_idx_mode", (ins GPRIdxMode:$simm16),
|
|
"$simm16"> {
|
|
let Defs = [M0, MODE];
|
|
let Uses = [MODE];
|
|
}
|
|
}
|
|
|
|
let SubtargetPredicate = isGFX10Plus in {
|
|
def S_INST_PREFETCH :
|
|
SOPP_Pseudo<"s_inst_prefetch", (ins s16imm:$simm16), "$simm16">;
|
|
def S_CLAUSE :
|
|
SOPP_Pseudo<"s_clause", (ins s16imm:$simm16), "$simm16">;
|
|
def S_WAIT_IDLE :
|
|
SOPP_Pseudo <"s_wait_idle", (ins), ""> {
|
|
let simm16 = 0;
|
|
let fixed_imm = 1;
|
|
}
|
|
def S_WAITCNT_DEPCTR :
|
|
SOPP_Pseudo <"s_waitcnt_depctr" , (ins s16imm:$simm16), "$simm16">;
|
|
|
|
let hasSideEffects = 0, Uses = [MODE], Defs = [MODE] in {
|
|
def S_ROUND_MODE :
|
|
SOPP_Pseudo<"s_round_mode", (ins s16imm:$simm16), "$simm16">;
|
|
def S_DENORM_MODE :
|
|
SOPP_Pseudo<"s_denorm_mode", (ins i32imm:$simm16), "$simm16",
|
|
[(SIdenorm_mode (i32 timm:$simm16))]>;
|
|
}
|
|
|
|
def S_TTRACEDATA_IMM :
|
|
SOPP_Pseudo<"s_ttracedata_imm", (ins s16imm:$simm16), "$simm16">;
|
|
} // End SubtargetPredicate = isGFX10Plus
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP1 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : GCNPat <
|
|
(AMDGPUendpgm),
|
|
(S_ENDPGM (i16 0))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(int_amdgcn_endpgm),
|
|
(S_ENDPGM (i16 0))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (ctpop i64:$src)),
|
|
(i64 (REG_SEQUENCE SReg_64,
|
|
(i32 (COPY_TO_REGCLASS (S_BCNT1_I32_B64 $src), SReg_32)), sub0,
|
|
(S_MOV_B32 (i32 0)), sub1))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i32 (smax i32:$x, (i32 (ineg i32:$x)))),
|
|
(S_ABS_I32 SReg_32:$x)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i16 imm:$imm),
|
|
(S_MOV_B32 imm:$imm)
|
|
>;
|
|
|
|
// Same as a 32-bit inreg
|
|
def : GCNPat<
|
|
(i32 (UniformUnaryFrag<sext> i16:$src)),
|
|
(S_SEXT_I32_I16 $src)
|
|
>;
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP2 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// V_ADD_I32_e32/S_ADD_U32 produces carry in VCC/SCC. For the vector
|
|
// case, the sgpr-copies pass will fix this to use the vector version.
|
|
def : GCNPat <
|
|
(i32 (addc i32:$src0, i32:$src1)),
|
|
(S_ADD_U32 $src0, $src1)
|
|
>;
|
|
|
|
// FIXME: We need to use COPY_TO_REGCLASS to work-around the fact that
|
|
// REG_SEQUENCE patterns don't support instructions with multiple
|
|
// outputs.
|
|
def : GCNPat<
|
|
(i64 (zext i16:$src)),
|
|
(REG_SEQUENCE SReg_64,
|
|
(i32 (COPY_TO_REGCLASS (S_AND_B32 $src, (S_MOV_B32 (i32 0xffff))), SGPR_32)), sub0,
|
|
(S_MOV_B32 (i32 0)), sub1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (UniformUnaryFrag<sext> i16:$src)),
|
|
(REG_SEQUENCE SReg_64, (i32 (S_SEXT_I32_I16 $src)), sub0,
|
|
(i32 (COPY_TO_REGCLASS (S_ASHR_I32 (i32 (S_SEXT_I32_I16 $src)), (S_MOV_B32 (i32 31))), SGPR_32)), sub1)
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(i32 (zext i16:$src)),
|
|
(S_AND_B32 (S_MOV_B32 (i32 0xffff)), $src)
|
|
>;
|
|
|
|
// FIXME: ValueType should have isVector field
|
|
class ScalarNot2Pat<Instruction inst, SDPatternOperator op, ValueType vt,
|
|
bit isVector = 1> : GCNPat<
|
|
(UniformBinFrag<op> vt:$src0, (UniformUnaryFrag<!if(isVector, vnot, not)> vt:$src1)),
|
|
(inst getSOPSrcForVT<vt>.ret:$src0, getSOPSrcForVT<vt>.ret:$src1)
|
|
>;
|
|
|
|
// Match these for some more types
|
|
// TODO: i1
|
|
def : ScalarNot2Pat<S_ANDN2_B32, and, i16, 0>;
|
|
def : ScalarNot2Pat<S_ANDN2_B32, and, v2i16>;
|
|
def : ScalarNot2Pat<S_ANDN2_B64, and, v4i16>;
|
|
def : ScalarNot2Pat<S_ANDN2_B64, and, v2i32>;
|
|
|
|
def : ScalarNot2Pat<S_ORN2_B32, or, i16, 0>;
|
|
def : ScalarNot2Pat<S_ORN2_B32, or, v2i16>;
|
|
def : ScalarNot2Pat<S_ORN2_B64, or, v4i16>;
|
|
def : ScalarNot2Pat<S_ORN2_B64, or, v2i32>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Target-specific instruction encodings.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class Select_gfx10<string opName> : SIMCInstr<opName, SIEncodingFamily.GFX10> {
|
|
Predicate AssemblerPredicate = isGFX10Plus;
|
|
string DecoderNamespace = "GFX10";
|
|
}
|
|
|
|
class Select_vi<string opName> : SIMCInstr<opName, SIEncodingFamily.VI> {
|
|
Predicate AssemblerPredicate = isGFX8GFX9;
|
|
string DecoderNamespace = "GFX8";
|
|
}
|
|
|
|
class Select_gfx6_gfx7<string opName> : SIMCInstr<opName, SIEncodingFamily.SI> {
|
|
Predicate AssemblerPredicate = isGFX6GFX7;
|
|
string DecoderNamespace = "GFX6GFX7";
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP1 - GFX10.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SOP1_Real_gfx10<bits<8> op> {
|
|
def _gfx10 : SOP1_Real<op, !cast<SOP1_Pseudo>(NAME)>,
|
|
Select_gfx10<!cast<SOP1_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
defm S_ANDN1_SAVEEXEC_B64 : SOP1_Real_gfx10<0x037>;
|
|
defm S_ORN1_SAVEEXEC_B64 : SOP1_Real_gfx10<0x038>;
|
|
defm S_ANDN1_WREXEC_B64 : SOP1_Real_gfx10<0x039>;
|
|
defm S_ANDN2_WREXEC_B64 : SOP1_Real_gfx10<0x03a>;
|
|
defm S_BITREPLICATE_B64_B32 : SOP1_Real_gfx10<0x03b>;
|
|
defm S_AND_SAVEEXEC_B32 : SOP1_Real_gfx10<0x03c>;
|
|
defm S_OR_SAVEEXEC_B32 : SOP1_Real_gfx10<0x03d>;
|
|
defm S_XOR_SAVEEXEC_B32 : SOP1_Real_gfx10<0x03e>;
|
|
defm S_ANDN2_SAVEEXEC_B32 : SOP1_Real_gfx10<0x03f>;
|
|
defm S_ORN2_SAVEEXEC_B32 : SOP1_Real_gfx10<0x040>;
|
|
defm S_NAND_SAVEEXEC_B32 : SOP1_Real_gfx10<0x041>;
|
|
defm S_NOR_SAVEEXEC_B32 : SOP1_Real_gfx10<0x042>;
|
|
defm S_XNOR_SAVEEXEC_B32 : SOP1_Real_gfx10<0x043>;
|
|
defm S_ANDN1_SAVEEXEC_B32 : SOP1_Real_gfx10<0x044>;
|
|
defm S_ORN1_SAVEEXEC_B32 : SOP1_Real_gfx10<0x045>;
|
|
defm S_ANDN1_WREXEC_B32 : SOP1_Real_gfx10<0x046>;
|
|
defm S_ANDN2_WREXEC_B32 : SOP1_Real_gfx10<0x047>;
|
|
defm S_MOVRELSD_2_B32 : SOP1_Real_gfx10<0x049>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP1 - GFX6, GFX7.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
|
multiclass SOP1_Real_gfx6_gfx7<bits<8> op> {
|
|
def _gfx6_gfx7 : SOP1_Real<op, !cast<SOP1_Pseudo>(NAME)>,
|
|
Select_gfx6_gfx7<!cast<SOP1_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOP1_Real_gfx6_gfx7_gfx10<bits<8> op> :
|
|
SOP1_Real_gfx6_gfx7<op>, SOP1_Real_gfx10<op>;
|
|
|
|
defm S_CBRANCH_JOIN : SOP1_Real_gfx6_gfx7<0x032>;
|
|
|
|
defm S_MOV_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x003>;
|
|
defm S_MOV_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x004>;
|
|
defm S_CMOV_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x005>;
|
|
defm S_CMOV_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x006>;
|
|
defm S_NOT_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x007>;
|
|
defm S_NOT_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x008>;
|
|
defm S_WQM_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x009>;
|
|
defm S_WQM_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x00a>;
|
|
defm S_BREV_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x00b>;
|
|
defm S_BREV_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x00c>;
|
|
defm S_BCNT0_I32_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x00d>;
|
|
defm S_BCNT0_I32_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x00e>;
|
|
defm S_BCNT1_I32_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x00f>;
|
|
defm S_BCNT1_I32_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x010>;
|
|
defm S_FF0_I32_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x011>;
|
|
defm S_FF0_I32_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x012>;
|
|
defm S_FF1_I32_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x013>;
|
|
defm S_FF1_I32_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x014>;
|
|
defm S_FLBIT_I32_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x015>;
|
|
defm S_FLBIT_I32_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x016>;
|
|
defm S_FLBIT_I32 : SOP1_Real_gfx6_gfx7_gfx10<0x017>;
|
|
defm S_FLBIT_I32_I64 : SOP1_Real_gfx6_gfx7_gfx10<0x018>;
|
|
defm S_SEXT_I32_I8 : SOP1_Real_gfx6_gfx7_gfx10<0x019>;
|
|
defm S_SEXT_I32_I16 : SOP1_Real_gfx6_gfx7_gfx10<0x01a>;
|
|
defm S_BITSET0_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x01b>;
|
|
defm S_BITSET0_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x01c>;
|
|
defm S_BITSET1_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x01d>;
|
|
defm S_BITSET1_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x01e>;
|
|
defm S_GETPC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x01f>;
|
|
defm S_SETPC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x020>;
|
|
defm S_SWAPPC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x021>;
|
|
defm S_RFE_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x022>;
|
|
defm S_AND_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x024>;
|
|
defm S_OR_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x025>;
|
|
defm S_XOR_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x026>;
|
|
defm S_ANDN2_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x027>;
|
|
defm S_ORN2_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x028>;
|
|
defm S_NAND_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x029>;
|
|
defm S_NOR_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x02a>;
|
|
defm S_XNOR_SAVEEXEC_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x02b>;
|
|
defm S_QUADMASK_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x02c>;
|
|
defm S_QUADMASK_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x02d>;
|
|
defm S_MOVRELS_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x02e>;
|
|
defm S_MOVRELS_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x02f>;
|
|
defm S_MOVRELD_B32 : SOP1_Real_gfx6_gfx7_gfx10<0x030>;
|
|
defm S_MOVRELD_B64 : SOP1_Real_gfx6_gfx7_gfx10<0x031>;
|
|
defm S_ABS_I32 : SOP1_Real_gfx6_gfx7_gfx10<0x034>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP2 - GFX10.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SOP2_Real_gfx10<bits<7> op> {
|
|
def _gfx10 : SOP2_Real<op, !cast<SOP2_Pseudo>(NAME)>,
|
|
Select_gfx10<!cast<SOP2_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
defm S_LSHL1_ADD_U32 : SOP2_Real_gfx10<0x02e>;
|
|
defm S_LSHL2_ADD_U32 : SOP2_Real_gfx10<0x02f>;
|
|
defm S_LSHL3_ADD_U32 : SOP2_Real_gfx10<0x030>;
|
|
defm S_LSHL4_ADD_U32 : SOP2_Real_gfx10<0x031>;
|
|
defm S_PACK_LL_B32_B16 : SOP2_Real_gfx10<0x032>;
|
|
defm S_PACK_LH_B32_B16 : SOP2_Real_gfx10<0x033>;
|
|
defm S_PACK_HH_B32_B16 : SOP2_Real_gfx10<0x034>;
|
|
defm S_MUL_HI_U32 : SOP2_Real_gfx10<0x035>;
|
|
defm S_MUL_HI_I32 : SOP2_Real_gfx10<0x036>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP2 - GFX6, GFX7.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SOP2_Real_gfx6_gfx7<bits<7> op> {
|
|
def _gfx6_gfx7 : SOP2_Real<op, !cast<SOP_Pseudo>(NAME)>,
|
|
Select_gfx6_gfx7<!cast<SOP_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOP2_Real_gfx6_gfx7_gfx10<bits<7> op> :
|
|
SOP2_Real_gfx6_gfx7<op>, SOP2_Real_gfx10<op>;
|
|
|
|
defm S_CBRANCH_G_FORK : SOP2_Real_gfx6_gfx7<0x02b>;
|
|
|
|
defm S_ADD_U32 : SOP2_Real_gfx6_gfx7_gfx10<0x000>;
|
|
defm S_SUB_U32 : SOP2_Real_gfx6_gfx7_gfx10<0x001>;
|
|
defm S_ADD_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x002>;
|
|
defm S_SUB_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x003>;
|
|
defm S_ADDC_U32 : SOP2_Real_gfx6_gfx7_gfx10<0x004>;
|
|
defm S_SUBB_U32 : SOP2_Real_gfx6_gfx7_gfx10<0x005>;
|
|
defm S_MIN_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x006>;
|
|
defm S_MIN_U32 : SOP2_Real_gfx6_gfx7_gfx10<0x007>;
|
|
defm S_MAX_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x008>;
|
|
defm S_MAX_U32 : SOP2_Real_gfx6_gfx7_gfx10<0x009>;
|
|
defm S_CSELECT_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x00a>;
|
|
defm S_CSELECT_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x00b>;
|
|
defm S_AND_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x00e>;
|
|
defm S_AND_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x00f>;
|
|
defm S_OR_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x010>;
|
|
defm S_OR_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x011>;
|
|
defm S_XOR_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x012>;
|
|
defm S_XOR_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x013>;
|
|
defm S_ANDN2_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x014>;
|
|
defm S_ANDN2_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x015>;
|
|
defm S_ORN2_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x016>;
|
|
defm S_ORN2_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x017>;
|
|
defm S_NAND_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x018>;
|
|
defm S_NAND_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x019>;
|
|
defm S_NOR_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x01a>;
|
|
defm S_NOR_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x01b>;
|
|
defm S_XNOR_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x01c>;
|
|
defm S_XNOR_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x01d>;
|
|
defm S_LSHL_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x01e>;
|
|
defm S_LSHL_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x01f>;
|
|
defm S_LSHR_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x020>;
|
|
defm S_LSHR_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x021>;
|
|
defm S_ASHR_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x022>;
|
|
defm S_ASHR_I64 : SOP2_Real_gfx6_gfx7_gfx10<0x023>;
|
|
defm S_BFM_B32 : SOP2_Real_gfx6_gfx7_gfx10<0x024>;
|
|
defm S_BFM_B64 : SOP2_Real_gfx6_gfx7_gfx10<0x025>;
|
|
defm S_MUL_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x026>;
|
|
defm S_BFE_U32 : SOP2_Real_gfx6_gfx7_gfx10<0x027>;
|
|
defm S_BFE_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x028>;
|
|
defm S_BFE_U64 : SOP2_Real_gfx6_gfx7_gfx10<0x029>;
|
|
defm S_BFE_I64 : SOP2_Real_gfx6_gfx7_gfx10<0x02a>;
|
|
defm S_ABSDIFF_I32 : SOP2_Real_gfx6_gfx7_gfx10<0x02c>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPK - GFX10.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SOPK_Real32_gfx10<bits<5> op> {
|
|
def _gfx10 : SOPK_Real32<op, !cast<SOPK_Pseudo>(NAME)>,
|
|
Select_gfx10<!cast<SOPK_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOPK_Real64_gfx10<bits<5> op> {
|
|
def _gfx10 : SOPK_Real64<op, !cast<SOPK_Pseudo>(NAME)>,
|
|
Select_gfx10<!cast<SOPK_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
defm S_VERSION : SOPK_Real32_gfx10<0x001>;
|
|
defm S_CALL_B64 : SOPK_Real32_gfx10<0x016>;
|
|
defm S_WAITCNT_VSCNT : SOPK_Real32_gfx10<0x017>;
|
|
defm S_WAITCNT_VMCNT : SOPK_Real32_gfx10<0x018>;
|
|
defm S_WAITCNT_EXPCNT : SOPK_Real32_gfx10<0x019>;
|
|
defm S_WAITCNT_LGKMCNT : SOPK_Real32_gfx10<0x01a>;
|
|
defm S_SUBVECTOR_LOOP_BEGIN : SOPK_Real32_gfx10<0x01b>;
|
|
defm S_SUBVECTOR_LOOP_END : SOPK_Real32_gfx10<0x01c>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPK - GFX6, GFX7.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SOPK_Real32_gfx6_gfx7<bits<5> op> {
|
|
def _gfx6_gfx7 : SOPK_Real32<op, !cast<SOPK_Pseudo>(NAME)>,
|
|
Select_gfx6_gfx7<!cast<SOPK_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOPK_Real64_gfx6_gfx7<bits<5> op> {
|
|
def _gfx6_gfx7 : SOPK_Real64<op, !cast<SOPK_Pseudo>(NAME)>,
|
|
Select_gfx6_gfx7<!cast<SOPK_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOPK_Real32_gfx6_gfx7_gfx10<bits<5> op> :
|
|
SOPK_Real32_gfx6_gfx7<op>, SOPK_Real32_gfx10<op>;
|
|
|
|
multiclass SOPK_Real64_gfx6_gfx7_gfx10<bits<5> op> :
|
|
SOPK_Real64_gfx6_gfx7<op>, SOPK_Real64_gfx10<op>;
|
|
|
|
defm S_CBRANCH_I_FORK : SOPK_Real32_gfx6_gfx7<0x011>;
|
|
|
|
defm S_MOVK_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x000>;
|
|
defm S_CMOVK_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x002>;
|
|
defm S_CMPK_EQ_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x003>;
|
|
defm S_CMPK_LG_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x004>;
|
|
defm S_CMPK_GT_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x005>;
|
|
defm S_CMPK_GE_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x006>;
|
|
defm S_CMPK_LT_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x007>;
|
|
defm S_CMPK_LE_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x008>;
|
|
defm S_CMPK_EQ_U32 : SOPK_Real32_gfx6_gfx7_gfx10<0x009>;
|
|
defm S_CMPK_LG_U32 : SOPK_Real32_gfx6_gfx7_gfx10<0x00a>;
|
|
defm S_CMPK_GT_U32 : SOPK_Real32_gfx6_gfx7_gfx10<0x00b>;
|
|
defm S_CMPK_GE_U32 : SOPK_Real32_gfx6_gfx7_gfx10<0x00c>;
|
|
defm S_CMPK_LT_U32 : SOPK_Real32_gfx6_gfx7_gfx10<0x00d>;
|
|
defm S_CMPK_LE_U32 : SOPK_Real32_gfx6_gfx7_gfx10<0x00e>;
|
|
defm S_ADDK_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x00f>;
|
|
defm S_MULK_I32 : SOPK_Real32_gfx6_gfx7_gfx10<0x010>;
|
|
defm S_GETREG_B32 : SOPK_Real32_gfx6_gfx7_gfx10<0x012>;
|
|
defm S_SETREG_B32 : SOPK_Real32_gfx6_gfx7_gfx10<0x013>;
|
|
defm S_SETREG_IMM32_B32 : SOPK_Real64_gfx6_gfx7_gfx10<0x015>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPP - GFX6, GFX7, GFX8, GFX9, GFX10
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SOPP_Real_32_gfx6_gfx7<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic> {
|
|
def _gfx6_gfx7 : SOPP_Real_32<op, !cast<SOPP_Pseudo>(NAME), real_name>,
|
|
Select_gfx6_gfx7<!cast<SOPP_Pseudo>(NAME).Mnemonic>,
|
|
SOPPRelaxTable<0, !cast<SOPP_Pseudo>(NAME).KeyName, "_gfx6_gfx7">;
|
|
}
|
|
|
|
multiclass SOPP_Real_32_gfx8_gfx9<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> {
|
|
def _vi : SOPP_Real_32<op, !cast<SOPP_Pseudo>(NAME), real_name>,
|
|
Select_vi<!cast<SOPP_Pseudo>(NAME).Mnemonic>,
|
|
SOPPRelaxTable<0, !cast<SOPP_Pseudo>(NAME).KeyName, "_vi">;
|
|
}
|
|
|
|
multiclass SOPP_Real_32_gfx10<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> {
|
|
def _gfx10 : SOPP_Real_32<op, !cast<SOPP_Pseudo>(NAME), real_name>,
|
|
Select_gfx10<!cast<SOPP_Pseudo>(NAME).Mnemonic>,
|
|
SOPPRelaxTable<0, !cast<SOPP_Pseudo>(NAME).KeyName, "_gfx10">;
|
|
}
|
|
|
|
multiclass SOPP_Real_32_gfx8_gfx9_gfx10<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> :
|
|
SOPP_Real_32_gfx8_gfx9<op, real_name>, SOPP_Real_32_gfx10<op, real_name>;
|
|
|
|
multiclass SOPP_Real_32_gfx6_gfx7_gfx8_gfx9<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> :
|
|
SOPP_Real_32_gfx6_gfx7<op, real_name>, SOPP_Real_32_gfx8_gfx9<op, real_name>;
|
|
|
|
multiclass SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> :
|
|
SOPP_Real_32_gfx6_gfx7_gfx8_gfx9<op, real_name>, SOPP_Real_32_gfx10<op, real_name>;
|
|
|
|
//64 bit encodings, for Relaxation
|
|
multiclass SOPP_Real_64_gfx6_gfx7<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> {
|
|
def _gfx6_gfx7 : SOPP_Real_64<op, !cast<SOPP_Pseudo>(NAME), real_name>,
|
|
Select_gfx6_gfx7<!cast<SOPP_Pseudo>(NAME).Mnemonic>,
|
|
SOPPRelaxTable<1, !cast<SOPP_Pseudo>(NAME).KeyName, "_gfx6_gfx7">;
|
|
}
|
|
|
|
multiclass SOPP_Real_64_gfx8_gfx9<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> {
|
|
def _vi : SOPP_Real_64<op, !cast<SOPP_Pseudo>(NAME), real_name>,
|
|
Select_vi<!cast<SOPP_Pseudo>(NAME).Mnemonic>,
|
|
SOPPRelaxTable<1, !cast<SOPP_Pseudo>(NAME).KeyName, "_vi">;
|
|
}
|
|
|
|
multiclass SOPP_Real_64_gfx10<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> {
|
|
def _gfx10 : SOPP_Real_64<op, !cast<SOPP_Pseudo>(NAME), real_name>,
|
|
Select_gfx10<!cast<SOPP_Pseudo>(NAME).Mnemonic>,
|
|
SOPPRelaxTable<1, !cast<SOPP_Pseudo>(NAME).KeyName, "_gfx10">;
|
|
}
|
|
|
|
multiclass SOPP_Real_64_gfx8_gfx9_gfx10<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> :
|
|
SOPP_Real_64_gfx8_gfx9<op, real_name>, SOPP_Real_64_gfx10<op, real_name>;
|
|
|
|
multiclass SOPP_Real_64_gfx6_gfx7_gfx8_gfx9<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> :
|
|
SOPP_Real_64_gfx6_gfx7<op, real_name>, SOPP_Real_64_gfx8_gfx9<op, real_name>;
|
|
|
|
multiclass SOPP_Real_64_gfx6_gfx7_gfx8_gfx9_gfx10<bits<7> op, string real_name = !cast<SOPP_Pseudo>(NAME).Mnemonic # " "> :
|
|
SOPP_Real_64_gfx6_gfx7_gfx8_gfx9<op, real_name>, SOPP_Real_64_gfx10<op, real_name>;
|
|
|
|
//relaxation for insts with no operands not implemented
|
|
multiclass SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<bits<7> op> {
|
|
defm "" : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<op>;
|
|
defm _pad_s_nop : SOPP_Real_64_gfx6_gfx7_gfx8_gfx9_gfx10<op>;
|
|
}
|
|
|
|
defm S_NOP : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x000>;
|
|
defm S_ENDPGM : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x001, "s_endpgm">;
|
|
defm S_BRANCH : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x002>;
|
|
defm S_WAKEUP : SOPP_Real_32_gfx8_gfx9_gfx10<0x003>;
|
|
defm S_CBRANCH_SCC0 : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x004>;
|
|
defm S_CBRANCH_SCC1 : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x005>;
|
|
defm S_CBRANCH_VCCZ : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x006>;
|
|
defm S_CBRANCH_VCCNZ : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x007>;
|
|
defm S_CBRANCH_EXECZ : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x008>;
|
|
defm S_CBRANCH_EXECNZ : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x009>;
|
|
defm S_CBRANCH_CDBGSYS : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x017>;
|
|
defm S_CBRANCH_CDBGUSER : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x018>;
|
|
defm S_CBRANCH_CDBGSYS_OR_USER : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x019>;
|
|
defm S_CBRANCH_CDBGSYS_AND_USER : SOPP_Real_With_Relaxation_gfx6_gfx7_gfx8_gfx9_gfx10<0x01A>;
|
|
defm S_BARRIER : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x00a>;
|
|
defm S_WAITCNT : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x00c>;
|
|
defm S_SETHALT : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x00d>;
|
|
defm S_SETKILL : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x00b>;
|
|
defm S_SLEEP : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x00e>;
|
|
defm S_SETPRIO : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x00f>;
|
|
defm S_SENDMSG : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x010>;
|
|
defm S_SENDMSGHALT : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x011>;
|
|
defm S_TRAP : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x012>;
|
|
defm S_ICACHE_INV : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x013>;
|
|
defm S_INCPERFLEVEL : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x014>;
|
|
defm S_DECPERFLEVEL : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x015>;
|
|
defm S_TTRACEDATA : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x016>;
|
|
defm S_ENDPGM_SAVED : SOPP_Real_32_gfx6_gfx7_gfx8_gfx9_gfx10<0x01B>;
|
|
defm S_SET_GPR_IDX_OFF : SOPP_Real_32_gfx8_gfx9<0x01c>;
|
|
defm S_SET_GPR_IDX_MODE : SOPP_Real_32_gfx8_gfx9<0x01d>;
|
|
defm S_ENDPGM_ORDERED_PS_DONE : SOPP_Real_32_gfx8_gfx9_gfx10<0x01e>;
|
|
defm S_CODE_END : SOPP_Real_32_gfx10<0x01f>;
|
|
defm S_INST_PREFETCH : SOPP_Real_32_gfx10<0x020>;
|
|
defm S_CLAUSE : SOPP_Real_32_gfx10<0x021>;
|
|
defm S_WAIT_IDLE : SOPP_Real_32_gfx10<0x022>;
|
|
defm S_WAITCNT_DEPCTR : SOPP_Real_32_gfx10<0x023>;
|
|
defm S_ROUND_MODE : SOPP_Real_32_gfx10<0x024>;
|
|
defm S_DENORM_MODE : SOPP_Real_32_gfx10<0x025>;
|
|
defm S_TTRACEDATA_IMM : SOPP_Real_32_gfx10<0x028>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOPC - GFX6, GFX7, GFX8, GFX9, GFX10
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
multiclass SOPC_Real_gfx6_gfx7<bits<7> op> {
|
|
def _gfx6_gfx7 : SOPC_Real<op, !cast<SOPC_Pseudo>(NAME)>,
|
|
Select_gfx6_gfx7<!cast<SOPC_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOPC_Real_gfx8_gfx9<bits<7> op> {
|
|
def _vi : SOPC_Real<op, !cast<SOPC_Pseudo>(NAME)>,
|
|
Select_vi<!cast<SOPC_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOPC_Real_gfx10<bits<7> op> {
|
|
def _gfx10 : SOPC_Real<op, !cast<SOPC_Pseudo>(NAME)>,
|
|
Select_gfx10<!cast<SOPC_Pseudo>(NAME).Mnemonic>;
|
|
}
|
|
|
|
multiclass SOPC_Real_gfx8_gfx9_gfx10<bits<7> op> :
|
|
SOPC_Real_gfx8_gfx9<op>, SOPC_Real_gfx10<op>;
|
|
|
|
multiclass SOPC_Real_gfx6_gfx7_gfx8_gfx9<bits<7> op> :
|
|
SOPC_Real_gfx6_gfx7<op>, SOPC_Real_gfx8_gfx9<op>;
|
|
|
|
multiclass SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<bits<7> op> :
|
|
SOPC_Real_gfx6_gfx7_gfx8_gfx9<op>, SOPC_Real_gfx10<op>;
|
|
|
|
defm S_CMP_EQ_I32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x00>;
|
|
defm S_CMP_LG_I32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x01>;
|
|
defm S_CMP_GT_I32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x02>;
|
|
defm S_CMP_GE_I32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x03>;
|
|
defm S_CMP_LT_I32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x04>;
|
|
defm S_CMP_LE_I32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x05>;
|
|
defm S_CMP_EQ_U32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x06>;
|
|
defm S_CMP_LG_U32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x07>;
|
|
defm S_CMP_GT_U32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x08>;
|
|
defm S_CMP_GE_U32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x09>;
|
|
defm S_CMP_LT_U32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x0a>;
|
|
defm S_CMP_LE_U32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x0b>;
|
|
defm S_BITCMP0_B32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x0c>;
|
|
defm S_BITCMP1_B32 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x0d>;
|
|
defm S_BITCMP0_B64 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x0e>;
|
|
defm S_BITCMP1_B64 : SOPC_Real_gfx6_gfx7_gfx8_gfx9_gfx10<0x0f>;
|
|
defm S_SETVSKIP : SOPC_Real_gfx6_gfx7_gfx8_gfx9<0x10>;
|
|
defm S_SET_GPR_IDX_ON : SOPC_Real_gfx8_gfx9<0x11>;
|
|
defm S_CMP_EQ_U64 : SOPC_Real_gfx8_gfx9_gfx10<0x12>;
|
|
defm S_CMP_LG_U64 : SOPC_Real_gfx8_gfx9_gfx10<0x13>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// GFX8 (VI), GFX9.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class SOP1_Real_vi<bits<8> op, SOP1_Pseudo ps> :
|
|
SOP1_Real<op, ps>,
|
|
Select_vi<ps.Mnemonic>;
|
|
|
|
|
|
class SOP2_Real_vi<bits<7> op, SOP2_Pseudo ps> :
|
|
SOP2_Real<op, ps>,
|
|
Select_vi<ps.Mnemonic>;
|
|
|
|
class SOPK_Real_vi<bits<5> op, SOPK_Pseudo ps> :
|
|
SOPK_Real32<op, ps>,
|
|
Select_vi<ps.Mnemonic>;
|
|
|
|
def S_MOV_B32_vi : SOP1_Real_vi <0x00, S_MOV_B32>;
|
|
def S_MOV_B64_vi : SOP1_Real_vi <0x01, S_MOV_B64>;
|
|
def S_CMOV_B32_vi : SOP1_Real_vi <0x02, S_CMOV_B32>;
|
|
def S_CMOV_B64_vi : SOP1_Real_vi <0x03, S_CMOV_B64>;
|
|
def S_NOT_B32_vi : SOP1_Real_vi <0x04, S_NOT_B32>;
|
|
def S_NOT_B64_vi : SOP1_Real_vi <0x05, S_NOT_B64>;
|
|
def S_WQM_B32_vi : SOP1_Real_vi <0x06, S_WQM_B32>;
|
|
def S_WQM_B64_vi : SOP1_Real_vi <0x07, S_WQM_B64>;
|
|
def S_BREV_B32_vi : SOP1_Real_vi <0x08, S_BREV_B32>;
|
|
def S_BREV_B64_vi : SOP1_Real_vi <0x09, S_BREV_B64>;
|
|
def S_BCNT0_I32_B32_vi : SOP1_Real_vi <0x0a, S_BCNT0_I32_B32>;
|
|
def S_BCNT0_I32_B64_vi : SOP1_Real_vi <0x0b, S_BCNT0_I32_B64>;
|
|
def S_BCNT1_I32_B32_vi : SOP1_Real_vi <0x0c, S_BCNT1_I32_B32>;
|
|
def S_BCNT1_I32_B64_vi : SOP1_Real_vi <0x0d, S_BCNT1_I32_B64>;
|
|
def S_FF0_I32_B32_vi : SOP1_Real_vi <0x0e, S_FF0_I32_B32>;
|
|
def S_FF0_I32_B64_vi : SOP1_Real_vi <0x0f, S_FF0_I32_B64>;
|
|
def S_FF1_I32_B32_vi : SOP1_Real_vi <0x10, S_FF1_I32_B32>;
|
|
def S_FF1_I32_B64_vi : SOP1_Real_vi <0x11, S_FF1_I32_B64>;
|
|
def S_FLBIT_I32_B32_vi : SOP1_Real_vi <0x12, S_FLBIT_I32_B32>;
|
|
def S_FLBIT_I32_B64_vi : SOP1_Real_vi <0x13, S_FLBIT_I32_B64>;
|
|
def S_FLBIT_I32_vi : SOP1_Real_vi <0x14, S_FLBIT_I32>;
|
|
def S_FLBIT_I32_I64_vi : SOP1_Real_vi <0x15, S_FLBIT_I32_I64>;
|
|
def S_SEXT_I32_I8_vi : SOP1_Real_vi <0x16, S_SEXT_I32_I8>;
|
|
def S_SEXT_I32_I16_vi : SOP1_Real_vi <0x17, S_SEXT_I32_I16>;
|
|
def S_BITSET0_B32_vi : SOP1_Real_vi <0x18, S_BITSET0_B32>;
|
|
def S_BITSET0_B64_vi : SOP1_Real_vi <0x19, S_BITSET0_B64>;
|
|
def S_BITSET1_B32_vi : SOP1_Real_vi <0x1a, S_BITSET1_B32>;
|
|
def S_BITSET1_B64_vi : SOP1_Real_vi <0x1b, S_BITSET1_B64>;
|
|
def S_GETPC_B64_vi : SOP1_Real_vi <0x1c, S_GETPC_B64>;
|
|
def S_SETPC_B64_vi : SOP1_Real_vi <0x1d, S_SETPC_B64>;
|
|
def S_SWAPPC_B64_vi : SOP1_Real_vi <0x1e, S_SWAPPC_B64>;
|
|
def S_RFE_B64_vi : SOP1_Real_vi <0x1f, S_RFE_B64>;
|
|
def S_AND_SAVEEXEC_B64_vi : SOP1_Real_vi <0x20, S_AND_SAVEEXEC_B64>;
|
|
def S_OR_SAVEEXEC_B64_vi : SOP1_Real_vi <0x21, S_OR_SAVEEXEC_B64>;
|
|
def S_XOR_SAVEEXEC_B64_vi : SOP1_Real_vi <0x22, S_XOR_SAVEEXEC_B64>;
|
|
def S_ANDN2_SAVEEXEC_B64_vi: SOP1_Real_vi <0x23, S_ANDN2_SAVEEXEC_B64>;
|
|
def S_ORN2_SAVEEXEC_B64_vi : SOP1_Real_vi <0x24, S_ORN2_SAVEEXEC_B64>;
|
|
def S_NAND_SAVEEXEC_B64_vi : SOP1_Real_vi <0x25, S_NAND_SAVEEXEC_B64>;
|
|
def S_NOR_SAVEEXEC_B64_vi : SOP1_Real_vi <0x26, S_NOR_SAVEEXEC_B64>;
|
|
def S_XNOR_SAVEEXEC_B64_vi : SOP1_Real_vi <0x27, S_XNOR_SAVEEXEC_B64>;
|
|
def S_QUADMASK_B32_vi : SOP1_Real_vi <0x28, S_QUADMASK_B32>;
|
|
def S_QUADMASK_B64_vi : SOP1_Real_vi <0x29, S_QUADMASK_B64>;
|
|
def S_MOVRELS_B32_vi : SOP1_Real_vi <0x2a, S_MOVRELS_B32>;
|
|
def S_MOVRELS_B64_vi : SOP1_Real_vi <0x2b, S_MOVRELS_B64>;
|
|
def S_MOVRELD_B32_vi : SOP1_Real_vi <0x2c, S_MOVRELD_B32>;
|
|
def S_MOVRELD_B64_vi : SOP1_Real_vi <0x2d, S_MOVRELD_B64>;
|
|
def S_CBRANCH_JOIN_vi : SOP1_Real_vi <0x2e, S_CBRANCH_JOIN>;
|
|
def S_ABS_I32_vi : SOP1_Real_vi <0x30, S_ABS_I32>;
|
|
def S_SET_GPR_IDX_IDX_vi : SOP1_Real_vi <0x32, S_SET_GPR_IDX_IDX>;
|
|
|
|
def S_ADD_U32_vi : SOP2_Real_vi <0x00, S_ADD_U32>;
|
|
def S_ADD_I32_vi : SOP2_Real_vi <0x02, S_ADD_I32>;
|
|
def S_SUB_U32_vi : SOP2_Real_vi <0x01, S_SUB_U32>;
|
|
def S_SUB_I32_vi : SOP2_Real_vi <0x03, S_SUB_I32>;
|
|
def S_ADDC_U32_vi : SOP2_Real_vi <0x04, S_ADDC_U32>;
|
|
def S_SUBB_U32_vi : SOP2_Real_vi <0x05, S_SUBB_U32>;
|
|
def S_MIN_I32_vi : SOP2_Real_vi <0x06, S_MIN_I32>;
|
|
def S_MIN_U32_vi : SOP2_Real_vi <0x07, S_MIN_U32>;
|
|
def S_MAX_I32_vi : SOP2_Real_vi <0x08, S_MAX_I32>;
|
|
def S_MAX_U32_vi : SOP2_Real_vi <0x09, S_MAX_U32>;
|
|
def S_CSELECT_B32_vi : SOP2_Real_vi <0x0a, S_CSELECT_B32>;
|
|
def S_CSELECT_B64_vi : SOP2_Real_vi <0x0b, S_CSELECT_B64>;
|
|
def S_AND_B32_vi : SOP2_Real_vi <0x0c, S_AND_B32>;
|
|
def S_AND_B64_vi : SOP2_Real_vi <0x0d, S_AND_B64>;
|
|
def S_OR_B32_vi : SOP2_Real_vi <0x0e, S_OR_B32>;
|
|
def S_OR_B64_vi : SOP2_Real_vi <0x0f, S_OR_B64>;
|
|
def S_XOR_B32_vi : SOP2_Real_vi <0x10, S_XOR_B32>;
|
|
def S_XOR_B64_vi : SOP2_Real_vi <0x11, S_XOR_B64>;
|
|
def S_ANDN2_B32_vi : SOP2_Real_vi <0x12, S_ANDN2_B32>;
|
|
def S_ANDN2_B64_vi : SOP2_Real_vi <0x13, S_ANDN2_B64>;
|
|
def S_ORN2_B32_vi : SOP2_Real_vi <0x14, S_ORN2_B32>;
|
|
def S_ORN2_B64_vi : SOP2_Real_vi <0x15, S_ORN2_B64>;
|
|
def S_NAND_B32_vi : SOP2_Real_vi <0x16, S_NAND_B32>;
|
|
def S_NAND_B64_vi : SOP2_Real_vi <0x17, S_NAND_B64>;
|
|
def S_NOR_B32_vi : SOP2_Real_vi <0x18, S_NOR_B32>;
|
|
def S_NOR_B64_vi : SOP2_Real_vi <0x19, S_NOR_B64>;
|
|
def S_XNOR_B32_vi : SOP2_Real_vi <0x1a, S_XNOR_B32>;
|
|
def S_XNOR_B64_vi : SOP2_Real_vi <0x1b, S_XNOR_B64>;
|
|
def S_LSHL_B32_vi : SOP2_Real_vi <0x1c, S_LSHL_B32>;
|
|
def S_LSHL_B64_vi : SOP2_Real_vi <0x1d, S_LSHL_B64>;
|
|
def S_LSHR_B32_vi : SOP2_Real_vi <0x1e, S_LSHR_B32>;
|
|
def S_LSHR_B64_vi : SOP2_Real_vi <0x1f, S_LSHR_B64>;
|
|
def S_ASHR_I32_vi : SOP2_Real_vi <0x20, S_ASHR_I32>;
|
|
def S_ASHR_I64_vi : SOP2_Real_vi <0x21, S_ASHR_I64>;
|
|
def S_BFM_B32_vi : SOP2_Real_vi <0x22, S_BFM_B32>;
|
|
def S_BFM_B64_vi : SOP2_Real_vi <0x23, S_BFM_B64>;
|
|
def S_MUL_I32_vi : SOP2_Real_vi <0x24, S_MUL_I32>;
|
|
def S_BFE_U32_vi : SOP2_Real_vi <0x25, S_BFE_U32>;
|
|
def S_BFE_I32_vi : SOP2_Real_vi <0x26, S_BFE_I32>;
|
|
def S_BFE_U64_vi : SOP2_Real_vi <0x27, S_BFE_U64>;
|
|
def S_BFE_I64_vi : SOP2_Real_vi <0x28, S_BFE_I64>;
|
|
def S_CBRANCH_G_FORK_vi : SOP2_Real_vi <0x29, S_CBRANCH_G_FORK>;
|
|
def S_ABSDIFF_I32_vi : SOP2_Real_vi <0x2a, S_ABSDIFF_I32>;
|
|
def S_PACK_LL_B32_B16_vi : SOP2_Real_vi <0x32, S_PACK_LL_B32_B16>;
|
|
def S_PACK_LH_B32_B16_vi : SOP2_Real_vi <0x33, S_PACK_LH_B32_B16>;
|
|
def S_PACK_HH_B32_B16_vi : SOP2_Real_vi <0x34, S_PACK_HH_B32_B16>;
|
|
def S_RFE_RESTORE_B64_vi : SOP2_Real_vi <0x2b, S_RFE_RESTORE_B64>;
|
|
|
|
def S_MOVK_I32_vi : SOPK_Real_vi <0x00, S_MOVK_I32>;
|
|
def S_CMOVK_I32_vi : SOPK_Real_vi <0x01, S_CMOVK_I32>;
|
|
def S_CMPK_EQ_I32_vi : SOPK_Real_vi <0x02, S_CMPK_EQ_I32>;
|
|
def S_CMPK_LG_I32_vi : SOPK_Real_vi <0x03, S_CMPK_LG_I32>;
|
|
def S_CMPK_GT_I32_vi : SOPK_Real_vi <0x04, S_CMPK_GT_I32>;
|
|
def S_CMPK_GE_I32_vi : SOPK_Real_vi <0x05, S_CMPK_GE_I32>;
|
|
def S_CMPK_LT_I32_vi : SOPK_Real_vi <0x06, S_CMPK_LT_I32>;
|
|
def S_CMPK_LE_I32_vi : SOPK_Real_vi <0x07, S_CMPK_LE_I32>;
|
|
def S_CMPK_EQ_U32_vi : SOPK_Real_vi <0x08, S_CMPK_EQ_U32>;
|
|
def S_CMPK_LG_U32_vi : SOPK_Real_vi <0x09, S_CMPK_LG_U32>;
|
|
def S_CMPK_GT_U32_vi : SOPK_Real_vi <0x0A, S_CMPK_GT_U32>;
|
|
def S_CMPK_GE_U32_vi : SOPK_Real_vi <0x0B, S_CMPK_GE_U32>;
|
|
def S_CMPK_LT_U32_vi : SOPK_Real_vi <0x0C, S_CMPK_LT_U32>;
|
|
def S_CMPK_LE_U32_vi : SOPK_Real_vi <0x0D, S_CMPK_LE_U32>;
|
|
def S_ADDK_I32_vi : SOPK_Real_vi <0x0E, S_ADDK_I32>;
|
|
def S_MULK_I32_vi : SOPK_Real_vi <0x0F, S_MULK_I32>;
|
|
def S_CBRANCH_I_FORK_vi : SOPK_Real_vi <0x10, S_CBRANCH_I_FORK>;
|
|
def S_GETREG_B32_vi : SOPK_Real_vi <0x11, S_GETREG_B32>;
|
|
def S_SETREG_B32_vi : SOPK_Real_vi <0x12, S_SETREG_B32>;
|
|
//def S_GETREG_REGRD_B32_vi : SOPK_Real_vi <0x13, S_GETREG_REGRD_B32>; // see pseudo for comments
|
|
def S_SETREG_IMM32_B32_vi : SOPK_Real64<0x14, S_SETREG_IMM32_B32>,
|
|
Select_vi<S_SETREG_IMM32_B32.Mnemonic>;
|
|
|
|
def S_CALL_B64_vi : SOPK_Real_vi <0x15, S_CALL_B64>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP1 - GFX9.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def S_ANDN1_SAVEEXEC_B64_vi : SOP1_Real_vi<0x33, S_ANDN1_SAVEEXEC_B64>;
|
|
def S_ORN1_SAVEEXEC_B64_vi : SOP1_Real_vi<0x34, S_ORN1_SAVEEXEC_B64>;
|
|
def S_ANDN1_WREXEC_B64_vi : SOP1_Real_vi<0x35, S_ANDN1_WREXEC_B64>;
|
|
def S_ANDN2_WREXEC_B64_vi : SOP1_Real_vi<0x36, S_ANDN2_WREXEC_B64>;
|
|
def S_BITREPLICATE_B64_B32_vi : SOP1_Real_vi<0x37, S_BITREPLICATE_B64_B32>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SOP2 - GFX9.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def S_LSHL1_ADD_U32_vi : SOP2_Real_vi<0x2e, S_LSHL1_ADD_U32>;
|
|
def S_LSHL2_ADD_U32_vi : SOP2_Real_vi<0x2f, S_LSHL2_ADD_U32>;
|
|
def S_LSHL3_ADD_U32_vi : SOP2_Real_vi<0x30, S_LSHL3_ADD_U32>;
|
|
def S_LSHL4_ADD_U32_vi : SOP2_Real_vi<0x31, S_LSHL4_ADD_U32>;
|
|
def S_MUL_HI_U32_vi : SOP2_Real_vi<0x2c, S_MUL_HI_U32>;
|
|
def S_MUL_HI_I32_vi : SOP2_Real_vi<0x2d, S_MUL_HI_I32>;
|