forked from OSchip/llvm-project
2648 lines
83 KiB
TableGen
2648 lines
83 KiB
TableGen
//===-- SIInstructions.td - SI 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
// This file was originally auto-generated from a GPU register header file and
|
|
// all the instruction definitions were originally commented out. Instructions
|
|
// that are not yet supported remain commented out.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class GCNPat<dag pattern, dag result> : Pat<pattern, result>, GCNPredicateControl {
|
|
|
|
}
|
|
|
|
include "SOPInstructions.td"
|
|
include "VOPInstructions.td"
|
|
include "SMInstructions.td"
|
|
include "FLATInstructions.td"
|
|
include "BUFInstructions.td"
|
|
include "EXPInstructions.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VINTRP Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Used to inject printing of "_e32" suffix for VI (there are "_e64" variants for VI)
|
|
def VINTRPDst : VINTRPDstOperand <VGPR_32>;
|
|
|
|
let Uses = [MODE, M0, EXEC] in {
|
|
|
|
// FIXME: Specify SchedRW for VINTRP instructions.
|
|
|
|
multiclass V_INTERP_P1_F32_m : VINTRP_m <
|
|
0x00000000,
|
|
(outs VINTRPDst:$vdst),
|
|
(ins VGPR_32:$vsrc, Attr:$attr, AttrChan:$attrchan),
|
|
"v_interp_p1_f32$vdst, $vsrc, $attr$attrchan",
|
|
[(set f32:$vdst, (int_amdgcn_interp_p1 f32:$vsrc,
|
|
(i32 timm:$attrchan), (i32 timm:$attr), M0))]
|
|
>;
|
|
|
|
let OtherPredicates = [has32BankLDS] in {
|
|
|
|
defm V_INTERP_P1_F32 : V_INTERP_P1_F32_m;
|
|
|
|
} // End OtherPredicates = [has32BankLDS]
|
|
|
|
let OtherPredicates = [has16BankLDS], Constraints = "@earlyclobber $vdst", isAsmParserOnly=1 in {
|
|
|
|
defm V_INTERP_P1_F32_16bank : V_INTERP_P1_F32_m;
|
|
|
|
} // End OtherPredicates = [has32BankLDS], Constraints = "@earlyclobber $vdst", isAsmParserOnly=1
|
|
|
|
let DisableEncoding = "$src0", Constraints = "$src0 = $vdst" in {
|
|
|
|
defm V_INTERP_P2_F32 : VINTRP_m <
|
|
0x00000001,
|
|
(outs VINTRPDst:$vdst),
|
|
(ins VGPR_32:$src0, VGPR_32:$vsrc, Attr:$attr, AttrChan:$attrchan),
|
|
"v_interp_p2_f32$vdst, $vsrc, $attr$attrchan",
|
|
[(set f32:$vdst, (int_amdgcn_interp_p2 f32:$src0, f32:$vsrc,
|
|
(i32 timm:$attrchan), (i32 timm:$attr), M0))]>;
|
|
|
|
} // End DisableEncoding = "$src0", Constraints = "$src0 = $vdst"
|
|
|
|
defm V_INTERP_MOV_F32 : VINTRP_m <
|
|
0x00000002,
|
|
(outs VINTRPDst:$vdst),
|
|
(ins InterpSlot:$vsrc, Attr:$attr, AttrChan:$attrchan),
|
|
"v_interp_mov_f32$vdst, $vsrc, $attr$attrchan",
|
|
[(set f32:$vdst, (int_amdgcn_interp_mov (i32 timm:$vsrc),
|
|
(i32 timm:$attrchan), (i32 timm:$attr), M0))]>;
|
|
|
|
} // End Uses = [MODE, M0, EXEC]
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Pseudo Instructions
|
|
//===----------------------------------------------------------------------===//
|
|
def ATOMIC_FENCE : SPseudoInstSI<
|
|
(outs), (ins i32imm:$ordering, i32imm:$scope),
|
|
[(atomic_fence (i32 timm:$ordering), (i32 timm:$scope))],
|
|
"ATOMIC_FENCE $ordering, $scope"> {
|
|
let hasSideEffects = 1;
|
|
let maybeAtomic = 1;
|
|
}
|
|
|
|
def VOP_I64_I64_DPP : VOPProfile <[i64, i64, untyped, untyped]> {
|
|
let HasExt = 1;
|
|
let HasExtDPP = 1;
|
|
}
|
|
|
|
let hasSideEffects = 0, mayLoad = 0, mayStore = 0, Uses = [EXEC] in {
|
|
|
|
// For use in patterns
|
|
def V_CNDMASK_B64_PSEUDO : VOP3Common <(outs VReg_64:$vdst),
|
|
(ins VSrc_b64:$src0, VSrc_b64:$src1, SSrc_b64:$src2), "", []> {
|
|
let isPseudo = 1;
|
|
let isCodeGenOnly = 1;
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
// 64-bit vector move instruction. This is mainly used by the
|
|
// SIFoldOperands pass to enable folding of inline immediates.
|
|
def V_MOV_B64_PSEUDO : VPseudoInstSI <(outs VReg_64:$vdst),
|
|
(ins VSrc_b64:$src0)>;
|
|
|
|
// 64-bit vector move with dpp. Expanded post-RA.
|
|
def V_MOV_B64_DPP_PSEUDO : VOP_DPP_Pseudo <"v_mov_b64_dpp", VOP_I64_I64_DPP> {
|
|
let Size = 16; // Requires two 8-byte v_mov_b32_dpp to complete.
|
|
}
|
|
|
|
// Pseudoinstruction for @llvm.amdgcn.wqm. It is turned into a copy after the
|
|
// WQM pass processes it.
|
|
def WQM : PseudoInstSI <(outs unknown:$vdst), (ins unknown:$src0)>;
|
|
|
|
// Pseudoinstruction for @llvm.amdgcn.softwqm. Like @llvm.amdgcn.wqm it is
|
|
// turned into a copy by WQM pass, but does not seed WQM requirements.
|
|
def SOFT_WQM : PseudoInstSI <(outs unknown:$vdst), (ins unknown:$src0)>;
|
|
|
|
// Pseudoinstruction for @llvm.amdgcn.wwm. It is turned into a copy post-RA, so
|
|
// that the @earlyclobber is respected. The @earlyclobber is to make sure that
|
|
// the instruction that defines $src0 (which is run in WWM) doesn't
|
|
// accidentally clobber inactive channels of $vdst.
|
|
let Constraints = "@earlyclobber $vdst" in {
|
|
def WWM : PseudoInstSI <(outs unknown:$vdst), (ins unknown:$src0)>;
|
|
}
|
|
|
|
} // End let hasSideEffects = 0, mayLoad = 0, mayStore = 0, Uses = [EXEC]
|
|
|
|
def ENTER_WWM : SPseudoInstSI <(outs SReg_1:$sdst), (ins i64imm:$src0)> {
|
|
let Uses = [EXEC];
|
|
let Defs = [EXEC, SCC];
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
}
|
|
|
|
def EXIT_WWM : SPseudoInstSI <(outs SReg_1:$sdst), (ins SReg_1:$src0)> {
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
}
|
|
|
|
// Invert the exec mask and overwrite the inactive lanes of dst with inactive,
|
|
// restoring it after we're done.
|
|
def V_SET_INACTIVE_B32 : VPseudoInstSI <(outs VGPR_32:$vdst),
|
|
(ins VGPR_32: $src, VSrc_b32:$inactive),
|
|
[(set i32:$vdst, (int_amdgcn_set_inactive i32:$src, i32:$inactive))]> {
|
|
let Constraints = "$src = $vdst";
|
|
}
|
|
|
|
def V_SET_INACTIVE_B64 : VPseudoInstSI <(outs VReg_64:$vdst),
|
|
(ins VReg_64: $src, VSrc_b64:$inactive),
|
|
[(set i64:$vdst, (int_amdgcn_set_inactive i64:$src, i64:$inactive))]> {
|
|
let Constraints = "$src = $vdst";
|
|
}
|
|
|
|
let usesCustomInserter = 1, Defs = [VCC, EXEC] in {
|
|
def V_ADD_U64_PSEUDO : VPseudoInstSI <
|
|
(outs VReg_64:$vdst), (ins VSrc_b64:$src0, VSrc_b64:$src1),
|
|
[(set VReg_64:$vdst, (getDivergentFrag<add>.ret i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def V_SUB_U64_PSEUDO : VPseudoInstSI <
|
|
(outs VReg_64:$vdst), (ins VSrc_b64:$src0, VSrc_b64:$src1),
|
|
[(set VReg_64:$vdst, (getDivergentFrag<sub>.ret i64:$src0, i64:$src1))]
|
|
>;
|
|
} // End usesCustomInserter = 1, Defs = [VCC, EXEC]
|
|
|
|
let usesCustomInserter = 1, Defs = [SCC] in {
|
|
def S_ADD_U64_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_64:$sdst), (ins SSrc_b64:$src0, SSrc_b64:$src1),
|
|
[(set SReg_64:$sdst, (UniformBinFrag<add> i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def S_SUB_U64_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_64:$sdst), (ins SSrc_b64:$src0, SSrc_b64:$src1),
|
|
[(set SReg_64:$sdst, (UniformBinFrag<sub> i64:$src0, i64:$src1))]
|
|
>;
|
|
|
|
def S_ADD_U64_CO_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_64:$vdst, VOPDstS64orS32:$sdst), (ins SSrc_b64:$src0, SSrc_b64:$src1)
|
|
>;
|
|
|
|
def S_SUB_U64_CO_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_64:$vdst, VOPDstS64orS32:$sdst), (ins SSrc_b64:$src0, SSrc_b64:$src1)
|
|
>;
|
|
|
|
def S_ADD_CO_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_32:$sdst, SSrc_i1:$scc_out), (ins SSrc_b32:$src0, SSrc_b32:$src1, SSrc_i1:$scc_in)
|
|
>;
|
|
|
|
def S_SUB_CO_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_32:$sdst, SSrc_i1:$scc_out), (ins SSrc_b32:$src0, SSrc_b32:$src1, SSrc_i1:$scc_in)
|
|
>;
|
|
|
|
def S_UADDO_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_32:$sdst, SSrc_i1:$scc_out), (ins SSrc_b32:$src0, SSrc_b32:$src1)
|
|
>;
|
|
|
|
def S_USUBO_PSEUDO : SPseudoInstSI <
|
|
(outs SReg_32:$sdst, SSrc_i1:$scc_out), (ins SSrc_b32:$src0, SSrc_b32:$src1)
|
|
>;
|
|
|
|
} // End usesCustomInserter = 1, Defs = [SCC]
|
|
|
|
let usesCustomInserter = 1 in {
|
|
def GET_GROUPSTATICSIZE : SPseudoInstSI <(outs SReg_32:$sdst), (ins),
|
|
[(set SReg_32:$sdst, (int_amdgcn_groupstaticsize))]>;
|
|
} // End let usesCustomInserter = 1, SALU = 1
|
|
|
|
// Wrap an instruction by duplicating it, except for setting isTerminator.
|
|
class WrapTerminatorInst<SOP_Pseudo base_inst> : SPseudoInstSI<
|
|
base_inst.OutOperandList,
|
|
base_inst.InOperandList> {
|
|
let Uses = base_inst.Uses;
|
|
let Defs = base_inst.Defs;
|
|
let isTerminator = 1;
|
|
let isAsCheapAsAMove = base_inst.isAsCheapAsAMove;
|
|
let hasSideEffects = base_inst.hasSideEffects;
|
|
let UseNamedOperandTable = base_inst.UseNamedOperandTable;
|
|
let CodeSize = base_inst.CodeSize;
|
|
let SchedRW = base_inst.SchedRW;
|
|
}
|
|
|
|
let WaveSizePredicate = isWave64 in {
|
|
def S_MOV_B64_term : WrapTerminatorInst<S_MOV_B64>;
|
|
def S_XOR_B64_term : WrapTerminatorInst<S_XOR_B64>;
|
|
def S_OR_B64_term : WrapTerminatorInst<S_OR_B64>;
|
|
def S_ANDN2_B64_term : WrapTerminatorInst<S_ANDN2_B64>;
|
|
}
|
|
|
|
let WaveSizePredicate = isWave32 in {
|
|
def S_MOV_B32_term : WrapTerminatorInst<S_MOV_B32>;
|
|
def S_XOR_B32_term : WrapTerminatorInst<S_XOR_B32>;
|
|
def S_OR_B32_term : WrapTerminatorInst<S_OR_B32>;
|
|
def S_ANDN2_B32_term : WrapTerminatorInst<S_ANDN2_B32>;
|
|
}
|
|
|
|
|
|
def WAVE_BARRIER : SPseudoInstSI<(outs), (ins),
|
|
[(int_amdgcn_wave_barrier)]> {
|
|
let SchedRW = [];
|
|
let hasNoSchedulingInfo = 1;
|
|
let hasSideEffects = 1;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
let isConvergent = 1;
|
|
let FixedSize = 1;
|
|
let Size = 0;
|
|
}
|
|
|
|
// SI pseudo instructions. These are used by the CFG structurizer pass
|
|
// and should be lowered to ISA instructions prior to codegen.
|
|
|
|
// Dummy terminator instruction to use after control flow instructions
|
|
// replaced with exec mask operations.
|
|
def SI_MASK_BRANCH : VPseudoInstSI <
|
|
(outs), (ins brtarget:$target)> {
|
|
let isBranch = 0;
|
|
let isTerminator = 1;
|
|
let isBarrier = 0;
|
|
let SchedRW = [];
|
|
let hasNoSchedulingInfo = 1;
|
|
let FixedSize = 1;
|
|
let Size = 0;
|
|
}
|
|
|
|
let isTerminator = 1 in {
|
|
|
|
let OtherPredicates = [EnableLateCFGStructurize] in {
|
|
def SI_NON_UNIFORM_BRCOND_PSEUDO : CFPseudoInstSI <
|
|
(outs),
|
|
(ins SReg_1:$vcc, brtarget:$target),
|
|
[(brcond i1:$vcc, bb:$target)]> {
|
|
let Size = 12;
|
|
}
|
|
}
|
|
|
|
def SI_IF: CFPseudoInstSI <
|
|
(outs SReg_1:$dst), (ins SReg_1:$vcc, brtarget:$target),
|
|
[(set i1:$dst, (AMDGPUif i1:$vcc, bb:$target))], 1, 1> {
|
|
let Constraints = "";
|
|
let Size = 12;
|
|
let hasSideEffects = 1;
|
|
}
|
|
|
|
def SI_ELSE : CFPseudoInstSI <
|
|
(outs SReg_1:$dst),
|
|
(ins SReg_1:$src, brtarget:$target), [], 1, 1> {
|
|
let Size = 12;
|
|
let hasSideEffects = 1;
|
|
}
|
|
|
|
def SI_LOOP : CFPseudoInstSI <
|
|
(outs), (ins SReg_1:$saved, brtarget:$target),
|
|
[(AMDGPUloop i1:$saved, bb:$target)], 1, 1> {
|
|
let Size = 8;
|
|
let isBranch = 1;
|
|
let hasSideEffects = 1;
|
|
}
|
|
|
|
} // End isTerminator = 1
|
|
|
|
def SI_END_CF : CFPseudoInstSI <
|
|
(outs), (ins SReg_1:$saved), [], 1, 1> {
|
|
let Size = 4;
|
|
let isAsCheapAsAMove = 1;
|
|
let isReMaterializable = 1;
|
|
let hasSideEffects = 1;
|
|
let mayLoad = 1; // FIXME: Should not need memory flags
|
|
let mayStore = 1;
|
|
}
|
|
|
|
def SI_IF_BREAK : CFPseudoInstSI <
|
|
(outs SReg_1:$dst), (ins SReg_1:$vcc, SReg_1:$src), []> {
|
|
let Size = 4;
|
|
let isAsCheapAsAMove = 1;
|
|
let isReMaterializable = 1;
|
|
}
|
|
|
|
let Uses = [EXEC] in {
|
|
|
|
multiclass PseudoInstKill <dag ins> {
|
|
// Even though this pseudo can usually be expanded without an SCC def, we
|
|
// conservatively assume that it has an SCC def, both because it is sometimes
|
|
// required in degenerate cases (when V_CMPX cannot be used due to constant
|
|
// bus limitations) and because it allows us to avoid having to track SCC
|
|
// liveness across basic blocks.
|
|
let Defs = [EXEC,VCC,SCC] in
|
|
def _PSEUDO : PseudoInstSI <(outs), ins> {
|
|
let isConvergent = 1;
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
let Defs = [EXEC,VCC,SCC] in
|
|
def _TERMINATOR : SPseudoInstSI <(outs), ins> {
|
|
let isTerminator = 1;
|
|
}
|
|
}
|
|
|
|
defm SI_KILL_I1 : PseudoInstKill <(ins SCSrc_i1:$src, i1imm:$killvalue)>;
|
|
defm SI_KILL_F32_COND_IMM : PseudoInstKill <(ins VSrc_b32:$src0, i32imm:$src1, i32imm:$cond)>;
|
|
|
|
let Defs = [EXEC] in
|
|
def SI_KILL_CLEANUP : SPseudoInstSI <(outs), (ins)>;
|
|
|
|
let Defs = [EXEC,VCC] in
|
|
def SI_ILLEGAL_COPY : SPseudoInstSI <
|
|
(outs unknown:$dst), (ins unknown:$src),
|
|
[], " ; illegal copy $src to $dst">;
|
|
|
|
} // End Uses = [EXEC], Defs = [EXEC,VCC]
|
|
|
|
// Branch on undef scc. Used to avoid intermediate copy from
|
|
// IMPLICIT_DEF to SCC.
|
|
def SI_BR_UNDEF : SPseudoInstSI <(outs), (ins sopp_brtarget:$simm16)> {
|
|
let isTerminator = 1;
|
|
let usesCustomInserter = 1;
|
|
let isBranch = 1;
|
|
}
|
|
|
|
def SI_PS_LIVE : PseudoInstSI <
|
|
(outs SReg_1:$dst), (ins),
|
|
[(set i1:$dst, (int_amdgcn_ps_live))]> {
|
|
let SALU = 1;
|
|
}
|
|
|
|
def SI_MASKED_UNREACHABLE : SPseudoInstSI <(outs), (ins),
|
|
[(int_amdgcn_unreachable)],
|
|
"; divergent unreachable"> {
|
|
let Size = 0;
|
|
let hasNoSchedulingInfo = 1;
|
|
let FixedSize = 1;
|
|
}
|
|
|
|
// Used as an isel pseudo to directly emit initialization with an
|
|
// s_mov_b32 rather than a copy of another initialized
|
|
// register. MachineCSE skips copies, and we don't want to have to
|
|
// fold operands before it runs.
|
|
def SI_INIT_M0 : SPseudoInstSI <(outs), (ins SSrc_b32:$src)> {
|
|
let Defs = [M0];
|
|
let usesCustomInserter = 1;
|
|
let isAsCheapAsAMove = 1;
|
|
let isReMaterializable = 1;
|
|
}
|
|
|
|
def SI_INIT_EXEC : SPseudoInstSI <
|
|
(outs), (ins i64imm:$src),
|
|
[(int_amdgcn_init_exec (i64 timm:$src))]> {
|
|
let Defs = [EXEC];
|
|
let usesCustomInserter = 1;
|
|
let isAsCheapAsAMove = 1;
|
|
let WaveSizePredicate = isWave64;
|
|
}
|
|
|
|
// FIXME: Intrinsic should be mangled for wave size.
|
|
def SI_INIT_EXEC_LO : SPseudoInstSI <
|
|
(outs), (ins i32imm:$src), []> {
|
|
let Defs = [EXEC_LO];
|
|
let usesCustomInserter = 1;
|
|
let isAsCheapAsAMove = 1;
|
|
let WaveSizePredicate = isWave32;
|
|
}
|
|
|
|
// FIXME: Wave32 version
|
|
def SI_INIT_EXEC_FROM_INPUT : SPseudoInstSI <
|
|
(outs), (ins SSrc_b32:$input, i32imm:$shift),
|
|
[(int_amdgcn_init_exec_from_input i32:$input, (i32 timm:$shift))]> {
|
|
let Defs = [EXEC];
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
def : GCNPat <
|
|
(int_amdgcn_init_exec timm:$src),
|
|
(SI_INIT_EXEC_LO (as_i32timm timm:$src))> {
|
|
let WaveSizePredicate = isWave32;
|
|
}
|
|
|
|
// Return for returning shaders to a shader variant epilog.
|
|
def SI_RETURN_TO_EPILOG : SPseudoInstSI <
|
|
(outs), (ins variable_ops), [(AMDGPUreturn_to_epilog)]> {
|
|
let isTerminator = 1;
|
|
let isBarrier = 1;
|
|
let isReturn = 1;
|
|
let hasNoSchedulingInfo = 1;
|
|
let DisableWQM = 1;
|
|
let FixedSize = 1;
|
|
}
|
|
|
|
// Return for returning function calls.
|
|
def SI_RETURN : SPseudoInstSI <
|
|
(outs), (ins), [],
|
|
"; return"> {
|
|
let isTerminator = 1;
|
|
let isBarrier = 1;
|
|
let isReturn = 1;
|
|
let SchedRW = [WriteBranch];
|
|
}
|
|
|
|
// Return for returning function calls without output register.
|
|
//
|
|
// This version is only needed so we can fill in the output register
|
|
// in the custom inserter.
|
|
def SI_CALL_ISEL : SPseudoInstSI <
|
|
(outs), (ins SSrc_b64:$src0, unknown:$callee),
|
|
[(AMDGPUcall i64:$src0, tglobaladdr:$callee)]> {
|
|
let Size = 4;
|
|
let isCall = 1;
|
|
let SchedRW = [WriteBranch];
|
|
let usesCustomInserter = 1;
|
|
// TODO: Should really base this on the call target
|
|
let isConvergent = 1;
|
|
}
|
|
|
|
def : GCNPat<
|
|
(AMDGPUcall i64:$src0, (i64 0)),
|
|
(SI_CALL_ISEL $src0, (i64 0))
|
|
>;
|
|
|
|
// Wrapper around s_swappc_b64 with extra $callee parameter to track
|
|
// the called function after regalloc.
|
|
def SI_CALL : SPseudoInstSI <
|
|
(outs SReg_64:$dst), (ins SSrc_b64:$src0, unknown:$callee)> {
|
|
let Size = 4;
|
|
let isCall = 1;
|
|
let UseNamedOperandTable = 1;
|
|
let SchedRW = [WriteBranch];
|
|
// TODO: Should really base this on the call target
|
|
let isConvergent = 1;
|
|
}
|
|
|
|
// Tail call handling pseudo
|
|
def SI_TCRETURN : SPseudoInstSI <(outs),
|
|
(ins SSrc_b64:$src0, unknown:$callee, i32imm:$fpdiff),
|
|
[(AMDGPUtc_return i64:$src0, tglobaladdr:$callee, i32:$fpdiff)]> {
|
|
let Size = 4;
|
|
let isCall = 1;
|
|
let isTerminator = 1;
|
|
let isReturn = 1;
|
|
let isBarrier = 1;
|
|
let UseNamedOperandTable = 1;
|
|
let SchedRW = [WriteBranch];
|
|
// TODO: Should really base this on the call target
|
|
let isConvergent = 1;
|
|
}
|
|
|
|
|
|
def ADJCALLSTACKUP : SPseudoInstSI<
|
|
(outs), (ins i32imm:$amt0, i32imm:$amt1),
|
|
[(callseq_start timm:$amt0, timm:$amt1)],
|
|
"; adjcallstackup $amt0 $amt1"> {
|
|
let Size = 8; // Worst case. (s_add_u32 + constant)
|
|
let FixedSize = 1;
|
|
let hasSideEffects = 1;
|
|
let usesCustomInserter = 1;
|
|
let SchedRW = [WriteSALU];
|
|
let Defs = [SCC];
|
|
}
|
|
|
|
def ADJCALLSTACKDOWN : SPseudoInstSI<
|
|
(outs), (ins i32imm:$amt1, i32imm:$amt2),
|
|
[(callseq_end timm:$amt1, timm:$amt2)],
|
|
"; adjcallstackdown $amt1"> {
|
|
let Size = 8; // Worst case. (s_add_u32 + constant)
|
|
let hasSideEffects = 1;
|
|
let usesCustomInserter = 1;
|
|
let SchedRW = [WriteSALU];
|
|
let Defs = [SCC];
|
|
}
|
|
|
|
let Defs = [M0, EXEC, SCC],
|
|
UseNamedOperandTable = 1 in {
|
|
|
|
// SI_INDIRECT_SRC/DST are only used by legacy SelectionDAG indirect
|
|
// addressing implementation.
|
|
class SI_INDIRECT_SRC<RegisterClass rc> : VPseudoInstSI <
|
|
(outs VGPR_32:$vdst),
|
|
(ins rc:$src, VS_32:$idx, i32imm:$offset)> {
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
class SI_INDIRECT_DST<RegisterClass rc> : VPseudoInstSI <
|
|
(outs rc:$vdst),
|
|
(ins rc:$src, VS_32:$idx, i32imm:$offset, VGPR_32:$val)> {
|
|
let Constraints = "$src = $vdst";
|
|
let usesCustomInserter = 1;
|
|
}
|
|
|
|
def SI_INDIRECT_SRC_V1 : SI_INDIRECT_SRC<VGPR_32>;
|
|
def SI_INDIRECT_SRC_V2 : SI_INDIRECT_SRC<VReg_64>;
|
|
def SI_INDIRECT_SRC_V4 : SI_INDIRECT_SRC<VReg_128>;
|
|
def SI_INDIRECT_SRC_V8 : SI_INDIRECT_SRC<VReg_256>;
|
|
def SI_INDIRECT_SRC_V16 : SI_INDIRECT_SRC<VReg_512>;
|
|
def SI_INDIRECT_SRC_V32 : SI_INDIRECT_SRC<VReg_1024>;
|
|
|
|
def SI_INDIRECT_DST_V1 : SI_INDIRECT_DST<VGPR_32>;
|
|
def SI_INDIRECT_DST_V2 : SI_INDIRECT_DST<VReg_64>;
|
|
def SI_INDIRECT_DST_V4 : SI_INDIRECT_DST<VReg_128>;
|
|
def SI_INDIRECT_DST_V8 : SI_INDIRECT_DST<VReg_256>;
|
|
def SI_INDIRECT_DST_V16 : SI_INDIRECT_DST<VReg_512>;
|
|
def SI_INDIRECT_DST_V32 : SI_INDIRECT_DST<VReg_1024>;
|
|
|
|
} // End Uses = [EXEC], Defs = [M0, EXEC]
|
|
|
|
|
|
// This is a pseudo variant of the v_movreld_b32 (or v_mov_b32
|
|
// expecting to be executed with gpr indexing mode enabled)
|
|
// instruction in which the vector operand appears only twice, once as
|
|
// def and once as use. Using this pseudo avoids problems with the Two
|
|
// Address instructions pass.
|
|
class INDIRECT_REG_WRITE_pseudo<RegisterClass rc,
|
|
RegisterOperand val_ty> : PseudoInstSI <
|
|
(outs rc:$vdst), (ins rc:$vsrc, val_ty:$val, i32imm:$subreg)> {
|
|
let Constraints = "$vsrc = $vdst";
|
|
let Uses = [M0];
|
|
}
|
|
|
|
class V_INDIRECT_REG_WRITE_B32_pseudo<RegisterClass rc> :
|
|
INDIRECT_REG_WRITE_pseudo<rc, VSrc_b32> {
|
|
let VALU = 1;
|
|
let VOP1 = 1;
|
|
let Uses = [M0, EXEC];
|
|
}
|
|
|
|
class S_INDIRECT_REG_WRITE_pseudo<RegisterClass rc,
|
|
RegisterOperand val_ty> :
|
|
INDIRECT_REG_WRITE_pseudo<rc, val_ty> {
|
|
let SALU = 1;
|
|
let SOP1 = 1;
|
|
let Uses = [M0];
|
|
}
|
|
|
|
class S_INDIRECT_REG_WRITE_B32_pseudo<RegisterClass rc> :
|
|
S_INDIRECT_REG_WRITE_pseudo<rc, SSrc_b32>;
|
|
class S_INDIRECT_REG_WRITE_B64_pseudo<RegisterClass rc> :
|
|
S_INDIRECT_REG_WRITE_pseudo<rc, SSrc_b64>;
|
|
|
|
|
|
def V_INDIRECT_REG_WRITE_B32_V1 : V_INDIRECT_REG_WRITE_B32_pseudo<VGPR_32>;
|
|
def V_INDIRECT_REG_WRITE_B32_V2 : V_INDIRECT_REG_WRITE_B32_pseudo<VReg_64>;
|
|
def V_INDIRECT_REG_WRITE_B32_V3 : V_INDIRECT_REG_WRITE_B32_pseudo<VReg_96>;
|
|
def V_INDIRECT_REG_WRITE_B32_V4 : V_INDIRECT_REG_WRITE_B32_pseudo<VReg_128>;
|
|
def V_INDIRECT_REG_WRITE_B32_V5 : V_INDIRECT_REG_WRITE_B32_pseudo<VReg_160>;
|
|
def V_INDIRECT_REG_WRITE_B32_V8 : V_INDIRECT_REG_WRITE_B32_pseudo<VReg_256>;
|
|
def V_INDIRECT_REG_WRITE_B32_V16 : V_INDIRECT_REG_WRITE_B32_pseudo<VReg_512>;
|
|
def V_INDIRECT_REG_WRITE_B32_V32 : V_INDIRECT_REG_WRITE_B32_pseudo<VReg_1024>;
|
|
|
|
def S_INDIRECT_REG_WRITE_B32_V1 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_32>;
|
|
def S_INDIRECT_REG_WRITE_B32_V2 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_64>;
|
|
def S_INDIRECT_REG_WRITE_B32_V3 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_96>;
|
|
def S_INDIRECT_REG_WRITE_B32_V4 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_128>;
|
|
def S_INDIRECT_REG_WRITE_B32_V5 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_160>;
|
|
def S_INDIRECT_REG_WRITE_B32_V8 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_256>;
|
|
def S_INDIRECT_REG_WRITE_B32_V16 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_512>;
|
|
def S_INDIRECT_REG_WRITE_B32_V32 : S_INDIRECT_REG_WRITE_B32_pseudo<SReg_1024>;
|
|
|
|
def S_INDIRECT_REG_WRITE_B64_V1 : S_INDIRECT_REG_WRITE_B64_pseudo<SReg_64>;
|
|
def S_INDIRECT_REG_WRITE_B64_V2 : S_INDIRECT_REG_WRITE_B64_pseudo<SReg_128>;
|
|
def S_INDIRECT_REG_WRITE_B64_V4 : S_INDIRECT_REG_WRITE_B64_pseudo<SReg_256>;
|
|
def S_INDIRECT_REG_WRITE_B64_V8 : S_INDIRECT_REG_WRITE_B64_pseudo<SReg_512>;
|
|
def S_INDIRECT_REG_WRITE_B64_V16 : S_INDIRECT_REG_WRITE_B64_pseudo<SReg_1024>;
|
|
|
|
|
|
multiclass SI_SPILL_SGPR <RegisterClass sgpr_class> {
|
|
let UseNamedOperandTable = 1, SGPRSpill = 1, Uses = [EXEC] in {
|
|
def _SAVE : PseudoInstSI <
|
|
(outs),
|
|
(ins sgpr_class:$data, i32imm:$addr)> {
|
|
let mayStore = 1;
|
|
let mayLoad = 0;
|
|
}
|
|
|
|
def _RESTORE : PseudoInstSI <
|
|
(outs sgpr_class:$data),
|
|
(ins i32imm:$addr)> {
|
|
let mayStore = 0;
|
|
let mayLoad = 1;
|
|
}
|
|
} // End UseNamedOperandTable = 1
|
|
}
|
|
|
|
// You cannot use M0 as the output of v_readlane_b32 instructions or
|
|
// use it in the sdata operand of SMEM instructions. We still need to
|
|
// be able to spill the physical register m0, so allow it for
|
|
// SI_SPILL_32_* instructions.
|
|
defm SI_SPILL_S32 : SI_SPILL_SGPR <SReg_32>;
|
|
defm SI_SPILL_S64 : SI_SPILL_SGPR <SReg_64>;
|
|
defm SI_SPILL_S96 : SI_SPILL_SGPR <SReg_96>;
|
|
defm SI_SPILL_S128 : SI_SPILL_SGPR <SReg_128>;
|
|
defm SI_SPILL_S160 : SI_SPILL_SGPR <SReg_160>;
|
|
defm SI_SPILL_S192 : SI_SPILL_SGPR <SReg_192>;
|
|
defm SI_SPILL_S256 : SI_SPILL_SGPR <SReg_256>;
|
|
defm SI_SPILL_S512 : SI_SPILL_SGPR <SReg_512>;
|
|
defm SI_SPILL_S1024 : SI_SPILL_SGPR <SReg_1024>;
|
|
|
|
// VGPR or AGPR spill instructions. In case of AGPR spilling a temp register
|
|
// needs to be used and an extra instruction to move between VGPR and AGPR.
|
|
// UsesTmp adds to the total size of an expanded spill in this case.
|
|
multiclass SI_SPILL_VGPR <RegisterClass vgpr_class, bit UsesTmp = 0> {
|
|
let UseNamedOperandTable = 1, VGPRSpill = 1,
|
|
SchedRW = [WriteVMEM] in {
|
|
def _SAVE : VPseudoInstSI <
|
|
(outs),
|
|
(ins vgpr_class:$vdata, i32imm:$vaddr,
|
|
SReg_32:$soffset, i32imm:$offset)> {
|
|
let mayStore = 1;
|
|
let mayLoad = 0;
|
|
// (2 * 4) + (8 * num_subregs) bytes maximum
|
|
int MaxSize = !add(!shl(!srl(vgpr_class.Size, 5), !add(UsesTmp, 3)), 8);
|
|
// Size field is unsigned char and cannot fit more.
|
|
let Size = !if(!le(MaxSize, 256), MaxSize, 252);
|
|
}
|
|
|
|
def _RESTORE : VPseudoInstSI <
|
|
(outs vgpr_class:$vdata),
|
|
(ins i32imm:$vaddr,
|
|
SReg_32:$soffset, i32imm:$offset)> {
|
|
let mayStore = 0;
|
|
let mayLoad = 1;
|
|
|
|
// (2 * 4) + (8 * num_subregs) bytes maximum
|
|
int MaxSize = !add(!shl(!srl(vgpr_class.Size, 5), !add(UsesTmp, 3)), 8);
|
|
// Size field is unsigned char and cannot fit more.
|
|
let Size = !if(!le(MaxSize, 256), MaxSize, 252);
|
|
}
|
|
} // End UseNamedOperandTable = 1, VGPRSpill = 1, SchedRW = [WriteVMEM]
|
|
}
|
|
|
|
defm SI_SPILL_V32 : SI_SPILL_VGPR <VGPR_32>;
|
|
defm SI_SPILL_V64 : SI_SPILL_VGPR <VReg_64>;
|
|
defm SI_SPILL_V96 : SI_SPILL_VGPR <VReg_96>;
|
|
defm SI_SPILL_V128 : SI_SPILL_VGPR <VReg_128>;
|
|
defm SI_SPILL_V160 : SI_SPILL_VGPR <VReg_160>;
|
|
defm SI_SPILL_V192 : SI_SPILL_VGPR <VReg_192>;
|
|
defm SI_SPILL_V256 : SI_SPILL_VGPR <VReg_256>;
|
|
defm SI_SPILL_V512 : SI_SPILL_VGPR <VReg_512>;
|
|
defm SI_SPILL_V1024 : SI_SPILL_VGPR <VReg_1024>;
|
|
|
|
defm SI_SPILL_A32 : SI_SPILL_VGPR <AGPR_32, 1>;
|
|
defm SI_SPILL_A64 : SI_SPILL_VGPR <AReg_64, 1>;
|
|
defm SI_SPILL_A96 : SI_SPILL_VGPR <AReg_96, 1>;
|
|
defm SI_SPILL_A128 : SI_SPILL_VGPR <AReg_128, 1>;
|
|
defm SI_SPILL_A160 : SI_SPILL_VGPR <AReg_160, 1>;
|
|
defm SI_SPILL_A192 : SI_SPILL_VGPR <AReg_192, 1>;
|
|
defm SI_SPILL_A256 : SI_SPILL_VGPR <AReg_256, 1>;
|
|
defm SI_SPILL_A512 : SI_SPILL_VGPR <AReg_512, 1>;
|
|
defm SI_SPILL_A1024 : SI_SPILL_VGPR <AReg_1024, 1>;
|
|
|
|
def SI_PC_ADD_REL_OFFSET : SPseudoInstSI <
|
|
(outs SReg_64:$dst),
|
|
(ins si_ga:$ptr_lo, si_ga:$ptr_hi),
|
|
[(set SReg_64:$dst,
|
|
(i64 (SIpc_add_rel_offset tglobaladdr:$ptr_lo, tglobaladdr:$ptr_hi)))]> {
|
|
let Defs = [SCC];
|
|
}
|
|
|
|
def : GCNPat <
|
|
(SIpc_add_rel_offset tglobaladdr:$ptr_lo, 0),
|
|
(SI_PC_ADD_REL_OFFSET $ptr_lo, (i32 0))
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(AMDGPUtrap timm:$trapid),
|
|
(S_TRAP $trapid)
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(AMDGPUelse i1:$src, bb:$target),
|
|
(SI_ELSE $src, $target)
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_amdgcn_kill i1:$src),
|
|
(SI_KILL_I1_PSEUDO SCSrc_i1:$src, 0)
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_amdgcn_kill (i1 (not i1:$src))),
|
|
(SI_KILL_I1_PSEUDO SCSrc_i1:$src, -1)
|
|
>;
|
|
|
|
def : Pat <
|
|
(int_amdgcn_kill (i1 (setcc f32:$src, InlineImmFP32:$imm, cond:$cond))),
|
|
(SI_KILL_F32_COND_IMM_PSEUDO VSrc_b32:$src, (bitcast_fpimm_to_i32 $imm), (cond_as_i32imm $cond))
|
|
>;
|
|
|
|
// TODO: we could add more variants for other types of conditionals
|
|
|
|
def : Pat <
|
|
(i64 (int_amdgcn_icmp i1:$src, (i1 0), (i32 33))),
|
|
(COPY $src) // Return the SGPRs representing i1 src
|
|
>;
|
|
|
|
def : Pat <
|
|
(i32 (int_amdgcn_icmp i1:$src, (i1 0), (i32 33))),
|
|
(COPY $src) // Return the SGPRs representing i1 src
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP1 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let OtherPredicates = [UnsafeFPMath] in {
|
|
|
|
//def : RcpPat<V_RCP_F64_e32, f64>;
|
|
//defm : RsqPat<V_RSQ_F64_e32, f64>;
|
|
//defm : RsqPat<V_RSQ_F32_e32, f32>;
|
|
|
|
def : RsqPat<V_RSQ_F32_e32, f32>;
|
|
def : RsqPat<V_RSQ_F64_e32, f64>;
|
|
|
|
// Convert (x - floor(x)) to fract(x)
|
|
def : GCNPat <
|
|
(f32 (fsub (f32 (VOP3Mods f32:$x, i32:$mods)),
|
|
(f32 (ffloor (f32 (VOP3Mods f32:$x, i32:$mods)))))),
|
|
(V_FRACT_F32_e64 $mods, $x)
|
|
>;
|
|
|
|
// Convert (x + (-floor(x))) to fract(x)
|
|
def : GCNPat <
|
|
(f64 (fadd (f64 (VOP3Mods f64:$x, i32:$mods)),
|
|
(f64 (fneg (f64 (ffloor (f64 (VOP3Mods f64:$x, i32:$mods)))))))),
|
|
(V_FRACT_F64_e64 $mods, $x)
|
|
>;
|
|
|
|
} // End OtherPredicates = [UnsafeFPMath]
|
|
|
|
|
|
// f16_to_fp patterns
|
|
def : GCNPat <
|
|
(f32 (f16_to_fp i32:$src0)),
|
|
(V_CVT_F32_F16_e64 SRCMODS.NONE, $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f32 (f16_to_fp (and_oneuse i32:$src0, 0x7fff))),
|
|
(V_CVT_F32_F16_e64 SRCMODS.ABS, $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f32 (f16_to_fp (i32 (srl_oneuse (and_oneuse i32:$src0, 0x7fff0000), (i32 16))))),
|
|
(V_CVT_F32_F16_e64 SRCMODS.ABS, (i32 (V_LSHRREV_B32_e64 (i32 16), i32:$src0)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f32 (f16_to_fp (or_oneuse i32:$src0, 0x8000))),
|
|
(V_CVT_F32_F16_e64 SRCMODS.NEG_ABS, $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f32 (f16_to_fp (xor_oneuse i32:$src0, 0x8000))),
|
|
(V_CVT_F32_F16_e64 SRCMODS.NEG, $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f64 (fpextend f16:$src)),
|
|
(V_CVT_F64_F32_e32 (V_CVT_F32_F16_e32 $src))
|
|
>;
|
|
|
|
// fp_to_fp16 patterns
|
|
def : GCNPat <
|
|
(i32 (AMDGPUfp_to_f16 (f32 (VOP3Mods f32:$src0, i32:$src0_modifiers)))),
|
|
(V_CVT_F16_F32_e64 $src0_modifiers, f32:$src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i32 (fp_to_sint f16:$src)),
|
|
(V_CVT_I32_F32_e32 (V_CVT_F32_F16_e32 VSrc_b32:$src))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i32 (fp_to_uint f16:$src)),
|
|
(V_CVT_U32_F32_e32 (V_CVT_F32_F16_e32 VSrc_b32:$src))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f16 (sint_to_fp i32:$src)),
|
|
(V_CVT_F16_F32_e32 (V_CVT_F32_I32_e32 VSrc_b32:$src))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f16 (uint_to_fp i32:$src)),
|
|
(V_CVT_F16_F32_e32 (V_CVT_F32_U32_e32 VSrc_b32:$src))
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP2 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// NoMods pattern used for mac. If there are any source modifiers then it's
|
|
// better to select mad instead of mac.
|
|
class FMADPat <ValueType vt, Instruction inst, SDPatternOperator node>
|
|
: GCNPat <(vt (node (vt (VOP3NoMods vt:$src0)),
|
|
(vt (VOP3NoMods vt:$src1)),
|
|
(vt (VOP3NoMods vt:$src2)))),
|
|
(inst SRCMODS.NONE, $src0, SRCMODS.NONE, $src1,
|
|
SRCMODS.NONE, $src2, DSTCLAMP.NONE, DSTOMOD.NONE)
|
|
>;
|
|
|
|
// Prefer mac form when there are no modifiers.
|
|
let AddedComplexity = 9 in {
|
|
let OtherPredicates = [HasMadMacF32Insts] in {
|
|
def : FMADPat <f32, V_MAC_F32_e64, fmad>;
|
|
def : FMADPat <f32, V_MAC_F32_e64, AMDGPUfmad_ftz>;
|
|
} // OtherPredicates = [HasMadMacF32Insts]
|
|
|
|
// Don't allow source modifiers. If there are any source modifiers then it's
|
|
// better to select mad instead of mac.
|
|
let SubtargetPredicate = isGFX6GFX7GFX10,
|
|
OtherPredicates = [HasMadMacF32Insts, NoFP32Denormals] in
|
|
def : GCNPat <
|
|
(f32 (fadd (AMDGPUfmul_legacy (VOP3NoMods f32:$src0),
|
|
(VOP3NoMods f32:$src1)),
|
|
(VOP3NoMods f32:$src2))),
|
|
(V_MAC_LEGACY_F32_e64 SRCMODS.NONE, $src0, SRCMODS.NONE, $src1,
|
|
SRCMODS.NONE, $src2, DSTCLAMP.NONE, DSTOMOD.NONE)
|
|
>;
|
|
|
|
// Don't allow source modifiers. If there are any source modifiers then it's
|
|
// better to select fma instead of fmac.
|
|
let SubtargetPredicate = HasFmaLegacy32 in
|
|
def : GCNPat <
|
|
(f32 (int_amdgcn_fma_legacy (VOP3NoMods f32:$src0),
|
|
(VOP3NoMods f32:$src1),
|
|
(VOP3NoMods f32:$src2))),
|
|
(V_FMAC_LEGACY_F32_e64 SRCMODS.NONE, $src0, SRCMODS.NONE, $src1,
|
|
SRCMODS.NONE, $src2, DSTCLAMP.NONE, DSTOMOD.NONE)
|
|
>;
|
|
|
|
let SubtargetPredicate = Has16BitInsts in {
|
|
def : FMADPat <f16, V_MAC_F16_e64, fmad>;
|
|
def : FMADPat <f16, V_MAC_F16_e64, AMDGPUfmad_ftz>;
|
|
} // SubtargetPredicate = Has16BitInsts
|
|
} // AddedComplexity = 9
|
|
|
|
class FMADModsPat<ValueType Ty, Instruction inst, SDPatternOperator mad_opr>
|
|
: GCNPat<
|
|
(Ty (mad_opr (Ty (VOP3Mods Ty:$src0, i32:$src0_mod)),
|
|
(Ty (VOP3Mods Ty:$src1, i32:$src1_mod)),
|
|
(Ty (VOP3Mods Ty:$src2, i32:$src2_mod)))),
|
|
(inst $src0_mod, $src0, $src1_mod, $src1,
|
|
$src2_mod, $src2, DSTCLAMP.NONE, DSTOMOD.NONE)
|
|
>;
|
|
|
|
let OtherPredicates = [HasMadMacF32Insts] in
|
|
def : FMADModsPat<f32, V_MAD_F32, AMDGPUfmad_ftz>;
|
|
|
|
let OtherPredicates = [HasMadMacF32Insts, NoFP32Denormals] in
|
|
def : GCNPat <
|
|
(f32 (fadd (AMDGPUfmul_legacy (VOP3Mods f32:$src0, i32:$src0_mod),
|
|
(VOP3Mods f32:$src1, i32:$src1_mod)),
|
|
(VOP3Mods f32:$src2, i32:$src2_mod))),
|
|
(V_MAD_LEGACY_F32 $src0_mod, $src0, $src1_mod, $src1,
|
|
$src2_mod, $src2, DSTCLAMP.NONE, DSTOMOD.NONE)
|
|
>;
|
|
|
|
let SubtargetPredicate = Has16BitInsts in
|
|
def : FMADModsPat<f16, V_MAD_F16, AMDGPUfmad_ftz>;
|
|
|
|
class VOPSelectModsPat <ValueType vt> : GCNPat <
|
|
(vt (select i1:$src0, (VOP3Mods vt:$src1, i32:$src1_mods),
|
|
(VOP3Mods vt:$src2, i32:$src2_mods))),
|
|
(V_CNDMASK_B32_e64 FP32InputMods:$src2_mods, VSrc_b32:$src2,
|
|
FP32InputMods:$src1_mods, VSrc_b32:$src1, SSrc_i1:$src0)
|
|
>;
|
|
|
|
class VOPSelectPat <ValueType vt> : GCNPat <
|
|
(vt (select i1:$src0, vt:$src1, vt:$src2)),
|
|
(V_CNDMASK_B32_e64 0, VSrc_b32:$src2, 0, VSrc_b32:$src1, SSrc_i1:$src0)
|
|
>;
|
|
|
|
def : VOPSelectModsPat <i32>;
|
|
def : VOPSelectModsPat <f32>;
|
|
def : VOPSelectPat <f16>;
|
|
def : VOPSelectPat <i16>;
|
|
|
|
let AddedComplexity = 1 in {
|
|
def : GCNPat <
|
|
(i32 (add (i32 (getDivergentFrag<ctpop>.ret i32:$popcnt)), i32:$val)),
|
|
(V_BCNT_U32_B32_e64 $popcnt, $val)
|
|
>;
|
|
}
|
|
|
|
def : GCNPat <
|
|
(i32 (ctpop i32:$popcnt)),
|
|
(V_BCNT_U32_B32_e64 VSrc_b32:$popcnt, (i32 0))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i16 (add (i16 (trunc (i32 (getDivergentFrag<ctpop>.ret i32:$popcnt)))), i16:$val)),
|
|
(V_BCNT_U32_B32_e64 $popcnt, $val)
|
|
>;
|
|
|
|
/********** ============================================ **********/
|
|
/********** Extraction, Insertion, Building and Casting **********/
|
|
/********** ============================================ **********/
|
|
|
|
foreach Index = 0-2 in {
|
|
def Extract_Element_v2i32_#Index : Extract_Element <
|
|
i32, v2i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v2i32_#Index : Insert_Element <
|
|
i32, v2i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v2f32_#Index : Extract_Element <
|
|
f32, v2f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v2f32_#Index : Insert_Element <
|
|
f32, v2f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-2 in {
|
|
def Extract_Element_v3i32_#Index : Extract_Element <
|
|
i32, v3i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v3i32_#Index : Insert_Element <
|
|
i32, v3i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v3f32_#Index : Extract_Element <
|
|
f32, v3f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v3f32_#Index : Insert_Element <
|
|
f32, v3f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-3 in {
|
|
def Extract_Element_v4i32_#Index : Extract_Element <
|
|
i32, v4i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v4i32_#Index : Insert_Element <
|
|
i32, v4i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v4f32_#Index : Extract_Element <
|
|
f32, v4f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v4f32_#Index : Insert_Element <
|
|
f32, v4f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-4 in {
|
|
def Extract_Element_v5i32_#Index : Extract_Element <
|
|
i32, v5i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v5i32_#Index : Insert_Element <
|
|
i32, v5i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v5f32_#Index : Extract_Element <
|
|
f32, v5f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v5f32_#Index : Insert_Element <
|
|
f32, v5f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-7 in {
|
|
def Extract_Element_v8i32_#Index : Extract_Element <
|
|
i32, v8i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v8i32_#Index : Insert_Element <
|
|
i32, v8i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v8f32_#Index : Extract_Element <
|
|
f32, v8f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v8f32_#Index : Insert_Element <
|
|
f32, v8f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
foreach Index = 0-15 in {
|
|
def Extract_Element_v16i32_#Index : Extract_Element <
|
|
i32, v16i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v16i32_#Index : Insert_Element <
|
|
i32, v16i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v16f32_#Index : Extract_Element <
|
|
f32, v16f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
def Insert_Element_v16f32_#Index : Insert_Element <
|
|
f32, v16f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
|
|
def : Pat <
|
|
(extract_subvector v4i16:$vec, (i32 0)),
|
|
(v2i16 (EXTRACT_SUBREG v4i16:$vec, sub0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(extract_subvector v4i16:$vec, (i32 2)),
|
|
(v2i16 (EXTRACT_SUBREG v4i16:$vec, sub1))
|
|
>;
|
|
|
|
def : Pat <
|
|
(extract_subvector v4f16:$vec, (i32 0)),
|
|
(v2f16 (EXTRACT_SUBREG v4f16:$vec, sub0))
|
|
>;
|
|
|
|
def : Pat <
|
|
(extract_subvector v4f16:$vec, (i32 2)),
|
|
(v2f16 (EXTRACT_SUBREG v4f16:$vec, sub1))
|
|
>;
|
|
|
|
foreach Index = 0-31 in {
|
|
def Extract_Element_v32i32_#Index : Extract_Element <
|
|
i32, v32i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Insert_Element_v32i32_#Index : Insert_Element <
|
|
i32, v32i32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Extract_Element_v32f32_#Index : Extract_Element <
|
|
f32, v32f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
|
|
def Insert_Element_v32f32_#Index : Insert_Element <
|
|
f32, v32f32, Index, !cast<SubRegIndex>(sub#Index)
|
|
>;
|
|
}
|
|
|
|
// FIXME: Why do only some of these type combinations for SReg and
|
|
// VReg?
|
|
// 16-bit bitcast
|
|
def : BitConvert <i16, f16, VGPR_32>;
|
|
def : BitConvert <f16, i16, VGPR_32>;
|
|
def : BitConvert <i16, f16, SReg_32>;
|
|
def : BitConvert <f16, i16, SReg_32>;
|
|
|
|
// 32-bit bitcast
|
|
def : BitConvert <i32, f32, VGPR_32>;
|
|
def : BitConvert <f32, i32, VGPR_32>;
|
|
def : BitConvert <i32, f32, SReg_32>;
|
|
def : BitConvert <f32, i32, SReg_32>;
|
|
def : BitConvert <v2i16, i32, SReg_32>;
|
|
def : BitConvert <i32, v2i16, SReg_32>;
|
|
def : BitConvert <v2f16, i32, SReg_32>;
|
|
def : BitConvert <i32, v2f16, SReg_32>;
|
|
def : BitConvert <v2i16, v2f16, SReg_32>;
|
|
def : BitConvert <v2f16, v2i16, SReg_32>;
|
|
def : BitConvert <v2f16, f32, SReg_32>;
|
|
def : BitConvert <f32, v2f16, SReg_32>;
|
|
def : BitConvert <v2i16, f32, SReg_32>;
|
|
def : BitConvert <f32, v2i16, SReg_32>;
|
|
|
|
// 64-bit bitcast
|
|
def : BitConvert <i64, f64, VReg_64>;
|
|
def : BitConvert <f64, i64, VReg_64>;
|
|
def : BitConvert <v2i32, v2f32, VReg_64>;
|
|
def : BitConvert <v2f32, v2i32, VReg_64>;
|
|
def : BitConvert <i64, v2i32, VReg_64>;
|
|
def : BitConvert <v2i32, i64, VReg_64>;
|
|
def : BitConvert <i64, v2f32, VReg_64>;
|
|
def : BitConvert <v2f32, i64, VReg_64>;
|
|
def : BitConvert <f64, v2f32, VReg_64>;
|
|
def : BitConvert <v2f32, f64, VReg_64>;
|
|
def : BitConvert <f64, v2i32, VReg_64>;
|
|
def : BitConvert <v2i32, f64, VReg_64>;
|
|
def : BitConvert <v4i16, v4f16, VReg_64>;
|
|
def : BitConvert <v4f16, v4i16, VReg_64>;
|
|
|
|
// FIXME: Make SGPR
|
|
def : BitConvert <v2i32, v4f16, VReg_64>;
|
|
def : BitConvert <v4f16, v2i32, VReg_64>;
|
|
def : BitConvert <v2i32, v4f16, VReg_64>;
|
|
def : BitConvert <v2i32, v4i16, VReg_64>;
|
|
def : BitConvert <v4i16, v2i32, VReg_64>;
|
|
def : BitConvert <v2f32, v4f16, VReg_64>;
|
|
def : BitConvert <v4f16, v2f32, VReg_64>;
|
|
def : BitConvert <v2f32, v4i16, VReg_64>;
|
|
def : BitConvert <v4i16, v2f32, VReg_64>;
|
|
def : BitConvert <v4i16, f64, VReg_64>;
|
|
def : BitConvert <v4f16, f64, VReg_64>;
|
|
def : BitConvert <f64, v4i16, VReg_64>;
|
|
def : BitConvert <f64, v4f16, VReg_64>;
|
|
def : BitConvert <v4i16, i64, VReg_64>;
|
|
def : BitConvert <v4f16, i64, VReg_64>;
|
|
def : BitConvert <i64, v4i16, VReg_64>;
|
|
def : BitConvert <i64, v4f16, VReg_64>;
|
|
|
|
def : BitConvert <v4i32, v4f32, VReg_128>;
|
|
def : BitConvert <v4f32, v4i32, VReg_128>;
|
|
|
|
// 96-bit bitcast
|
|
def : BitConvert <v3i32, v3f32, SGPR_96>;
|
|
def : BitConvert <v3f32, v3i32, SGPR_96>;
|
|
|
|
// 128-bit bitcast
|
|
def : BitConvert <v2i64, v4i32, SReg_128>;
|
|
def : BitConvert <v4i32, v2i64, SReg_128>;
|
|
def : BitConvert <v2f64, v4f32, VReg_128>;
|
|
def : BitConvert <v2f64, v4i32, VReg_128>;
|
|
def : BitConvert <v4f32, v2f64, VReg_128>;
|
|
def : BitConvert <v4i32, v2f64, VReg_128>;
|
|
def : BitConvert <v2i64, v2f64, VReg_128>;
|
|
def : BitConvert <v2f64, v2i64, VReg_128>;
|
|
def : BitConvert <v4f32, v2i64, VReg_128>;
|
|
def : BitConvert <v2i64, v4f32, VReg_128>;
|
|
|
|
// 160-bit bitcast
|
|
def : BitConvert <v5i32, v5f32, SGPR_160>;
|
|
def : BitConvert <v5f32, v5i32, SGPR_160>;
|
|
|
|
// 256-bit bitcast
|
|
def : BitConvert <v8i32, v8f32, SReg_256>;
|
|
def : BitConvert <v8f32, v8i32, SReg_256>;
|
|
def : BitConvert <v8i32, v8f32, VReg_256>;
|
|
def : BitConvert <v8f32, v8i32, VReg_256>;
|
|
def : BitConvert <v4i64, v4f64, VReg_256>;
|
|
def : BitConvert <v4f64, v4i64, VReg_256>;
|
|
def : BitConvert <v4i64, v8i32, VReg_256>;
|
|
def : BitConvert <v4i64, v8f32, VReg_256>;
|
|
def : BitConvert <v4f64, v8i32, VReg_256>;
|
|
def : BitConvert <v4f64, v8f32, VReg_256>;
|
|
def : BitConvert <v8i32, v4i64, VReg_256>;
|
|
def : BitConvert <v8f32, v4i64, VReg_256>;
|
|
def : BitConvert <v8i32, v4f64, VReg_256>;
|
|
def : BitConvert <v8f32, v4f64, VReg_256>;
|
|
|
|
|
|
// 512-bit bitcast
|
|
def : BitConvert <v16i32, v16f32, VReg_512>;
|
|
def : BitConvert <v16f32, v16i32, VReg_512>;
|
|
def : BitConvert <v8i64, v8f64, VReg_512>;
|
|
def : BitConvert <v8f64, v8i64, VReg_512>;
|
|
def : BitConvert <v8i64, v16i32, VReg_512>;
|
|
def : BitConvert <v8f64, v16i32, VReg_512>;
|
|
def : BitConvert <v16i32, v8i64, VReg_512>;
|
|
def : BitConvert <v16i32, v8f64, VReg_512>;
|
|
def : BitConvert <v8i64, v16f32, VReg_512>;
|
|
def : BitConvert <v8f64, v16f32, VReg_512>;
|
|
def : BitConvert <v16f32, v8i64, VReg_512>;
|
|
def : BitConvert <v16f32, v8f64, VReg_512>;
|
|
|
|
// 1024-bit bitcast
|
|
def : BitConvert <v32i32, v32f32, VReg_1024>;
|
|
def : BitConvert <v32f32, v32i32, VReg_1024>;
|
|
def : BitConvert <v16i64, v16f64, VReg_1024>;
|
|
def : BitConvert <v16f64, v16i64, VReg_1024>;
|
|
def : BitConvert <v16i64, v32i32, VReg_1024>;
|
|
def : BitConvert <v32i32, v16i64, VReg_1024>;
|
|
def : BitConvert <v16f64, v32f32, VReg_1024>;
|
|
def : BitConvert <v32f32, v16f64, VReg_1024>;
|
|
def : BitConvert <v16i64, v32f32, VReg_1024>;
|
|
def : BitConvert <v32i32, v16f64, VReg_1024>;
|
|
def : BitConvert <v16f64, v32i32, VReg_1024>;
|
|
def : BitConvert <v32f32, v16i64, VReg_1024>;
|
|
|
|
|
|
/********** =================== **********/
|
|
/********** Src & Dst modifiers **********/
|
|
/********** =================== **********/
|
|
|
|
|
|
// If denormals are not enabled, it only impacts the compare of the
|
|
// inputs. The output result is not flushed.
|
|
class ClampPat<Instruction inst, ValueType vt> : GCNPat <
|
|
(vt (AMDGPUclamp (VOP3Mods vt:$src0, i32:$src0_modifiers))),
|
|
(inst i32:$src0_modifiers, vt:$src0,
|
|
i32:$src0_modifiers, vt:$src0, DSTCLAMP.ENABLE, DSTOMOD.NONE)
|
|
>;
|
|
|
|
def : ClampPat<V_MAX_F32_e64, f32>;
|
|
def : ClampPat<V_MAX_F64, f64>;
|
|
def : ClampPat<V_MAX_F16_e64, f16>;
|
|
|
|
let SubtargetPredicate = HasVOP3PInsts in {
|
|
def : GCNPat <
|
|
(v2f16 (AMDGPUclamp (VOP3PMods v2f16:$src0, i32:$src0_modifiers))),
|
|
(V_PK_MAX_F16 $src0_modifiers, $src0,
|
|
$src0_modifiers, $src0, DSTCLAMP.ENABLE)
|
|
>;
|
|
}
|
|
|
|
/********** ================================ **********/
|
|
/********** Floating point absolute/negative **********/
|
|
/********** ================================ **********/
|
|
|
|
// Prevent expanding both fneg and fabs.
|
|
// TODO: Add IgnoredBySelectionDAG bit?
|
|
let AddedComplexity = 1 in { // Prefer SALU to VALU patterns for DAG
|
|
|
|
def : GCNPat <
|
|
(fneg (fabs (f32 SReg_32:$src))),
|
|
(S_OR_B32 SReg_32:$src, (S_MOV_B32 (i32 0x80000000))) // Set sign bit
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fabs (f32 SReg_32:$src)),
|
|
(S_AND_B32 SReg_32:$src, (S_MOV_B32 (i32 0x7fffffff)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (f32 SReg_32:$src)),
|
|
(S_XOR_B32 SReg_32:$src, (S_MOV_B32 (i32 0x80000000)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (f16 SReg_32:$src)),
|
|
(S_XOR_B32 SReg_32:$src, (S_MOV_B32 (i32 0x00008000)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (f16 VGPR_32:$src)),
|
|
(V_XOR_B32_e32 (S_MOV_B32 (i32 0x00008000)), VGPR_32:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fabs (f16 SReg_32:$src)),
|
|
(S_AND_B32 SReg_32:$src, (S_MOV_B32 (i32 0x00007fff)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (fabs (f16 SReg_32:$src))),
|
|
(S_OR_B32 SReg_32:$src, (S_MOV_B32 (i32 0x00008000))) // Set sign bit
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (fabs (f16 VGPR_32:$src))),
|
|
(V_OR_B32_e32 (S_MOV_B32 (i32 0x00008000)), VGPR_32:$src) // Set sign bit
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (v2f16 SReg_32:$src)),
|
|
(S_XOR_B32 SReg_32:$src, (S_MOV_B32 (i32 0x80008000)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fabs (v2f16 SReg_32:$src)),
|
|
(S_AND_B32 SReg_32:$src, (S_MOV_B32 (i32 0x7fff7fff)))
|
|
>;
|
|
|
|
// This is really (fneg (fabs v2f16:$src))
|
|
//
|
|
// fabs is not reported as free because there is modifier for it in
|
|
// VOP3P instructions, so it is turned into the bit op.
|
|
def : GCNPat <
|
|
(fneg (v2f16 (bitconvert (and_oneuse (i32 SReg_32:$src), 0x7fff7fff)))),
|
|
(S_OR_B32 SReg_32:$src, (S_MOV_B32 (i32 0x80008000))) // Set sign bit
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (v2f16 (fabs SReg_32:$src))),
|
|
(S_OR_B32 SReg_32:$src, (S_MOV_B32 (i32 0x80008000))) // Set sign bit
|
|
>;
|
|
|
|
// FIXME: The implicit-def of scc from S_[X]OR/AND_B32 is mishandled
|
|
// def : GCNPat <
|
|
// (fneg (f64 SReg_64:$src)),
|
|
// (REG_SEQUENCE SReg_64,
|
|
// (i32 (EXTRACT_SUBREG SReg_64:$src, sub0)),
|
|
// sub0,
|
|
// (S_XOR_B32 (i32 (EXTRACT_SUBREG SReg_64:$src, sub1)),
|
|
// (i32 (S_MOV_B32 (i32 0x80000000)))),
|
|
// sub1)
|
|
// >;
|
|
|
|
// def : GCNPat <
|
|
// (fneg (fabs (f64 SReg_64:$src))),
|
|
// (REG_SEQUENCE SReg_64,
|
|
// (i32 (EXTRACT_SUBREG SReg_64:$src, sub0)),
|
|
// sub0,
|
|
// (S_OR_B32 (i32 (EXTRACT_SUBREG SReg_64:$src, sub1)),
|
|
// (S_MOV_B32 (i32 0x80000000))), // Set sign bit.
|
|
// sub1)
|
|
// >;
|
|
|
|
// FIXME: Use S_BITSET0_B32/B64?
|
|
// def : GCNPat <
|
|
// (fabs (f64 SReg_64:$src)),
|
|
// (REG_SEQUENCE SReg_64,
|
|
// (i32 (EXTRACT_SUBREG SReg_64:$src, sub0)),
|
|
// sub0,
|
|
// (S_AND_B32 (i32 (EXTRACT_SUBREG SReg_64:$src, sub1)),
|
|
// (i32 (S_MOV_B32 (i32 0x7fffffff)))),
|
|
// sub1)
|
|
// >;
|
|
|
|
} // End let AddedComplexity = 1
|
|
|
|
def : GCNPat <
|
|
(fabs (f32 VGPR_32:$src)),
|
|
(V_AND_B32_e32 (S_MOV_B32 (i32 0x7fffffff)), VGPR_32:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (f32 VGPR_32:$src)),
|
|
(V_XOR_B32_e32 (S_MOV_B32 (i32 0x80000000)), VGPR_32:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fabs (f16 VGPR_32:$src)),
|
|
(V_AND_B32_e32 (S_MOV_B32 (i32 0x00007fff)), VGPR_32:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (v2f16 VGPR_32:$src)),
|
|
(V_XOR_B32_e32 (S_MOV_B32 (i32 0x80008000)), VGPR_32:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fabs (v2f16 VGPR_32:$src)),
|
|
(V_AND_B32_e32 (S_MOV_B32 (i32 0x7fff7fff)), VGPR_32:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fneg (v2f16 (fabs VGPR_32:$src))),
|
|
(V_OR_B32_e32 (S_MOV_B32 (i32 0x80008000)), VGPR_32:$src) // Set sign bit
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fabs (f64 VReg_64:$src)),
|
|
(REG_SEQUENCE VReg_64,
|
|
(i32 (EXTRACT_SUBREG VReg_64:$src, sub0)),
|
|
sub0,
|
|
(V_AND_B32_e64 (i32 (EXTRACT_SUBREG VReg_64:$src, sub1)),
|
|
(V_MOV_B32_e32 (i32 0x7fffffff))), // Set sign bit.
|
|
sub1)
|
|
>;
|
|
|
|
// TODO: Use SGPR for constant
|
|
def : GCNPat <
|
|
(fneg (f64 VReg_64:$src)),
|
|
(REG_SEQUENCE VReg_64,
|
|
(i32 (EXTRACT_SUBREG VReg_64:$src, sub0)),
|
|
sub0,
|
|
(V_XOR_B32_e32 (i32 (EXTRACT_SUBREG VReg_64:$src, sub1)),
|
|
(i32 (V_MOV_B32_e32 (i32 0x80000000)))),
|
|
sub1)
|
|
>;
|
|
|
|
// TODO: Use SGPR for constant
|
|
def : GCNPat <
|
|
(fneg (fabs (f64 VReg_64:$src))),
|
|
(REG_SEQUENCE VReg_64,
|
|
(i32 (EXTRACT_SUBREG VReg_64:$src, sub0)),
|
|
sub0,
|
|
(V_OR_B32_e32 (i32 (EXTRACT_SUBREG VReg_64:$src, sub1)),
|
|
(V_MOV_B32_e32 (i32 0x80000000))), // Set sign bit.
|
|
sub1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fcopysign f16:$src0, f16:$src1),
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x00007fff)), $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fcopysign f32:$src0, f16:$src1),
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x7fffffff)), $src0,
|
|
(V_LSHLREV_B32_e64 (i32 16), $src1))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fcopysign f64:$src0, f16:$src1),
|
|
(REG_SEQUENCE SReg_64,
|
|
(i32 (EXTRACT_SUBREG $src0, sub0)), sub0,
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x7fffffff)), (i32 (EXTRACT_SUBREG $src0, sub1)),
|
|
(V_LSHLREV_B32_e64 (i32 16), $src1)), sub1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fcopysign f16:$src0, f32:$src1),
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x00007fff)), $src0,
|
|
(V_LSHRREV_B32_e64 (i32 16), $src1))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(fcopysign f16:$src0, f64:$src1),
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x00007fff)), $src0,
|
|
(V_LSHRREV_B32_e64 (i32 16), (EXTRACT_SUBREG $src1, sub1)))
|
|
>;
|
|
|
|
/********** ================== **********/
|
|
/********** Immediate Patterns **********/
|
|
/********** ================== **********/
|
|
|
|
def : GCNPat <
|
|
(VGPRImm<(i32 imm)>:$imm),
|
|
(V_MOV_B32_e32 imm:$imm)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(VGPRImm<(f32 fpimm)>:$imm),
|
|
(V_MOV_B32_e32 (f32 (bitcast_fpimm_to_i32 $imm)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i32 imm:$imm),
|
|
(S_MOV_B32 imm:$imm)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(VGPRImm<(SIlds tglobaladdr:$ga)>),
|
|
(V_MOV_B32_e32 $ga)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(SIlds tglobaladdr:$ga),
|
|
(S_MOV_B32 $ga)
|
|
>;
|
|
|
|
// FIXME: Workaround for ordering issue with peephole optimizer where
|
|
// a register class copy interferes with immediate folding. Should
|
|
// use s_mov_b32, which can be shrunk to s_movk_i32
|
|
def : GCNPat <
|
|
(VGPRImm<(f16 fpimm)>:$imm),
|
|
(V_MOV_B32_e32 (f16 (bitcast_fpimm_to_i32 $imm)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f32 fpimm:$imm),
|
|
(S_MOV_B32 (f32 (bitcast_fpimm_to_i32 $imm)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f16 fpimm:$imm),
|
|
(S_MOV_B32 (i32 (bitcast_fpimm_to_i32 $imm)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(p5 frameindex:$fi),
|
|
(V_MOV_B32_e32 (p5 (frameindex_to_targetframeindex $fi)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(p5 frameindex:$fi),
|
|
(S_MOV_B32 (p5 (frameindex_to_targetframeindex $fi)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 InlineImm64:$imm),
|
|
(S_MOV_B64 InlineImm64:$imm)
|
|
>;
|
|
|
|
// XXX - Should this use a s_cmp to set SCC?
|
|
|
|
// Set to sign-extended 64-bit value (true = -1, false = 0)
|
|
def : GCNPat <
|
|
(i1 imm:$imm),
|
|
(S_MOV_B64 (i64 (as_i64imm $imm)))
|
|
> {
|
|
let WaveSizePredicate = isWave64;
|
|
}
|
|
|
|
def : GCNPat <
|
|
(i1 imm:$imm),
|
|
(S_MOV_B32 (i32 (as_i32imm $imm)))
|
|
> {
|
|
let WaveSizePredicate = isWave32;
|
|
}
|
|
|
|
def : GCNPat <
|
|
(f64 InlineImmFP64:$imm),
|
|
(S_MOV_B64 (f64 (bitcast_fpimm_to_i64 InlineImmFP64:$imm)))
|
|
>;
|
|
|
|
/********** ================== **********/
|
|
/********** Intrinsic Patterns **********/
|
|
/********** ================== **********/
|
|
|
|
// FIXME: Should use _e64 and select source modifiers.
|
|
def : POW_Common <V_LOG_F32_e32, V_EXP_F32_e32, V_MUL_LEGACY_F32_e32>;
|
|
|
|
def : GCNPat <
|
|
(i32 (sext i1:$src0)),
|
|
(V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 -1), $src0)
|
|
>;
|
|
|
|
class Ext32Pat <SDNode ext> : GCNPat <
|
|
(i32 (ext i1:$src0)),
|
|
(V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 1), $src0)
|
|
>;
|
|
|
|
def : Ext32Pat <zext>;
|
|
def : Ext32Pat <anyext>;
|
|
|
|
// The multiplication scales from [0,1) to the unsigned integer range,
|
|
// rounding down a bit to avoid unwanted overflow.
|
|
def : GCNPat <
|
|
(AMDGPUurecip i32:$src0),
|
|
(V_CVT_U32_F32_e32
|
|
(V_MUL_F32_e32 (i32 CONST.FP_4294966784),
|
|
(V_RCP_IFLAG_F32_e32 (V_CVT_F32_U32_e32 $src0))))
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// VOP3 Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : IMad24Pat<V_MAD_I32_I24, 1>;
|
|
def : UMad24Pat<V_MAD_U32_U24, 1>;
|
|
|
|
// BFI patterns
|
|
|
|
def BFIImm32 : PatFrag<
|
|
(ops node:$x, node:$y, node:$z),
|
|
(i32 (DivergentBinFrag<or> (and node:$y, node:$x), (and node:$z, imm))),
|
|
[{
|
|
auto *X = dyn_cast<ConstantSDNode>(N->getOperand(0)->getOperand(1));
|
|
auto *NotX = dyn_cast<ConstantSDNode>(N->getOperand(1)->getOperand(1));
|
|
return X && NotX &&
|
|
~(unsigned)X->getZExtValue() == (unsigned)NotX->getZExtValue();
|
|
}]
|
|
>;
|
|
|
|
// Definition from ISA doc:
|
|
// (y & x) | (z & ~x)
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<or> (and i32:$y, i32:$x), (and i32:$z, (not i32:$x))),
|
|
(V_BFI_B32 $x, $y, $z)
|
|
>;
|
|
|
|
// (y & C) | (z & ~C)
|
|
def : AMDGPUPat <
|
|
(BFIImm32 i32:$x, i32:$y, i32:$z),
|
|
(V_BFI_B32 $x, $y, $z)
|
|
>;
|
|
|
|
// 64-bit version
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<or> (and i64:$y, i64:$x), (and i64:$z, (not i64:$x))),
|
|
(REG_SEQUENCE SReg_64,
|
|
(V_BFI_B32 (i32 (EXTRACT_SUBREG SReg_64:$x, sub0)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub0)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$z, sub0))), sub0,
|
|
(V_BFI_B32 (i32 (EXTRACT_SUBREG SReg_64:$x, sub1)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub1)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$z, sub1))), sub1)
|
|
>;
|
|
|
|
// SHA-256 Ch function
|
|
// z ^ (x & (y ^ z))
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<xor> i32:$z, (and i32:$x, (xor i32:$y, i32:$z))),
|
|
(V_BFI_B32 $x, $y, $z)
|
|
>;
|
|
|
|
// 64-bit version
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<xor> i64:$z, (and i64:$x, (xor i64:$y, i64:$z))),
|
|
(REG_SEQUENCE SReg_64,
|
|
(V_BFI_B32 (i32 (EXTRACT_SUBREG SReg_64:$x, sub0)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub0)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$z, sub0))), sub0,
|
|
(V_BFI_B32 (i32 (EXTRACT_SUBREG SReg_64:$x, sub1)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub1)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$z, sub1))), sub1)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(fcopysign f32:$src0, f32:$src1),
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x7fffffff)), $src0, $src1)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(fcopysign f32:$src0, f64:$src1),
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x7fffffff)), $src0,
|
|
(i32 (EXTRACT_SUBREG SReg_64:$src1, sub1)))
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(fcopysign f64:$src0, f64:$src1),
|
|
(REG_SEQUENCE SReg_64,
|
|
(i32 (EXTRACT_SUBREG $src0, sub0)), sub0,
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x7fffffff)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$src0, sub1)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$src1, sub1))), sub1)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(fcopysign f64:$src0, f32:$src1),
|
|
(REG_SEQUENCE SReg_64,
|
|
(i32 (EXTRACT_SUBREG $src0, sub0)), sub0,
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x7fffffff)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$src0, sub1)),
|
|
$src1), sub1)
|
|
>;
|
|
|
|
def : ROTRPattern <V_ALIGNBIT_B32>;
|
|
|
|
def : GCNPat<(i32 (trunc (srl i64:$src0, (and i32:$src1, (i32 31))))),
|
|
(V_ALIGNBIT_B32 (i32 (EXTRACT_SUBREG (i64 $src0), sub1)),
|
|
(i32 (EXTRACT_SUBREG (i64 $src0), sub0)), $src1)>;
|
|
|
|
def : GCNPat<(i32 (trunc (srl i64:$src0, (i32 ShiftAmt32Imm:$src1)))),
|
|
(V_ALIGNBIT_B32 (i32 (EXTRACT_SUBREG (i64 $src0), sub1)),
|
|
(i32 (EXTRACT_SUBREG (i64 $src0), sub0)), $src1)>;
|
|
|
|
/********** ====================== **********/
|
|
/********** Indirect addressing **********/
|
|
/********** ====================== **********/
|
|
|
|
multiclass SI_INDIRECT_Pattern <ValueType vt, ValueType eltvt, string VecSize> {
|
|
// Extract with offset
|
|
def : GCNPat<
|
|
(eltvt (extractelt vt:$src, (MOVRELOffset i32:$idx, (i32 imm:$offset)))),
|
|
(!cast<Instruction>("SI_INDIRECT_SRC_"#VecSize) $src, $idx, imm:$offset)
|
|
>;
|
|
|
|
// Insert with offset
|
|
def : GCNPat<
|
|
(insertelt vt:$src, eltvt:$val, (MOVRELOffset i32:$idx, (i32 imm:$offset))),
|
|
(!cast<Instruction>("SI_INDIRECT_DST_"#VecSize) $src, $idx, imm:$offset, $val)
|
|
>;
|
|
}
|
|
|
|
defm : SI_INDIRECT_Pattern <v2f32, f32, "V2">;
|
|
defm : SI_INDIRECT_Pattern <v4f32, f32, "V4">;
|
|
defm : SI_INDIRECT_Pattern <v8f32, f32, "V8">;
|
|
defm : SI_INDIRECT_Pattern <v16f32, f32, "V16">;
|
|
defm : SI_INDIRECT_Pattern <v32f32, f32, "V32">;
|
|
|
|
defm : SI_INDIRECT_Pattern <v2i32, i32, "V2">;
|
|
defm : SI_INDIRECT_Pattern <v4i32, i32, "V4">;
|
|
defm : SI_INDIRECT_Pattern <v8i32, i32, "V8">;
|
|
defm : SI_INDIRECT_Pattern <v16i32, i32, "V16">;
|
|
defm : SI_INDIRECT_Pattern <v32i32, i32, "V32">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// SAD Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : GCNPat <
|
|
(add (sub_oneuse (umax i32:$src0, i32:$src1),
|
|
(umin i32:$src0, i32:$src1)),
|
|
i32:$src2),
|
|
(V_SAD_U32 $src0, $src1, $src2, (i1 0))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(add (select_oneuse (i1 (setugt i32:$src0, i32:$src1)),
|
|
(sub i32:$src0, i32:$src1),
|
|
(sub i32:$src1, i32:$src0)),
|
|
i32:$src2),
|
|
(V_SAD_U32 $src0, $src1, $src2, (i1 0))
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Conversion Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def : GCNPat<(i32 (sext_inreg i32:$src, i1)),
|
|
(S_BFE_I32 i32:$src, (i32 65536))>; // 0 | 1 << 16
|
|
|
|
// Handle sext_inreg in i64
|
|
def : GCNPat <
|
|
(i64 (sext_inreg i64:$src, i1)),
|
|
(S_BFE_I64 i64:$src, (i32 0x10000)) // 0 | 1 << 16
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i16 (sext_inreg i16:$src, i1)),
|
|
(S_BFE_I32 $src, (i32 0x00010000)) // 0 | 1 << 16
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i16 (sext_inreg i16:$src, i8)),
|
|
(S_BFE_I32 $src, (i32 0x80000)) // 0 | 8 << 16
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (sext_inreg i64:$src, i8)),
|
|
(S_BFE_I64 i64:$src, (i32 0x80000)) // 0 | 8 << 16
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (sext_inreg i64:$src, i16)),
|
|
(S_BFE_I64 i64:$src, (i32 0x100000)) // 0 | 16 << 16
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (sext_inreg i64:$src, i32)),
|
|
(S_BFE_I64 i64:$src, (i32 0x200000)) // 0 | 32 << 16
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (zext i32:$src)),
|
|
(REG_SEQUENCE SReg_64, $src, sub0, (S_MOV_B32 (i32 0)), sub1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (anyext i32:$src)),
|
|
(REG_SEQUENCE SReg_64, $src, sub0, (i32 (IMPLICIT_DEF)), sub1)
|
|
>;
|
|
|
|
class ZExt_i64_i1_Pat <SDNode ext> : GCNPat <
|
|
(i64 (ext i1:$src)),
|
|
(REG_SEQUENCE VReg_64,
|
|
(V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 1), $src),
|
|
sub0, (S_MOV_B32 (i32 0)), sub1)
|
|
>;
|
|
|
|
|
|
def : ZExt_i64_i1_Pat<zext>;
|
|
def : ZExt_i64_i1_Pat<anyext>;
|
|
|
|
// FIXME: We need to use COPY_TO_REGCLASS to work-around the fact that
|
|
// REG_SEQUENCE patterns don't support instructions with multiple outputs.
|
|
def : GCNPat <
|
|
(i64 (sext i32:$src)),
|
|
(REG_SEQUENCE SReg_64, $src, sub0,
|
|
(i32 (COPY_TO_REGCLASS (S_ASHR_I32 $src, (i32 31)), SReg_32_XM0)), sub1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (sext i1:$src)),
|
|
(REG_SEQUENCE VReg_64,
|
|
(V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 -1), $src), sub0,
|
|
(V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 -1), $src), sub1)
|
|
>;
|
|
|
|
class FPToI1Pat<Instruction Inst, int KOne, ValueType kone_type, ValueType vt, SDPatternOperator fp_to_int> : GCNPat <
|
|
(i1 (fp_to_int (vt (VOP3Mods vt:$src0, i32:$src0_modifiers)))),
|
|
(i1 (Inst 0, (kone_type KOne), $src0_modifiers, $src0, DSTCLAMP.NONE))
|
|
>;
|
|
|
|
def : FPToI1Pat<V_CMP_EQ_F32_e64, CONST.FP32_ONE, i32, f32, fp_to_uint>;
|
|
def : FPToI1Pat<V_CMP_EQ_F32_e64, CONST.FP32_NEG_ONE, i32, f32, fp_to_sint>;
|
|
def : FPToI1Pat<V_CMP_EQ_F64_e64, CONST.FP64_ONE, i64, f64, fp_to_uint>;
|
|
def : FPToI1Pat<V_CMP_EQ_F64_e64, CONST.FP64_NEG_ONE, i64, f64, fp_to_sint>;
|
|
|
|
// If we need to perform a logical operation on i1 values, we need to
|
|
// use vector comparisons since there is only one SCC register. Vector
|
|
// comparisons may write to a pair of SGPRs or a single SGPR, so treat
|
|
// these as 32 or 64-bit comparisons. When legalizing SGPR copies,
|
|
// instructions resulting in the copies from SCC to these instructions
|
|
// will be moved to the VALU.
|
|
|
|
let WaveSizePredicate = isWave64 in {
|
|
def : GCNPat <
|
|
(i1 (and i1:$src0, i1:$src1)),
|
|
(S_AND_B64 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (or i1:$src0, i1:$src1)),
|
|
(S_OR_B64 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (xor i1:$src0, i1:$src1)),
|
|
(S_XOR_B64 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (add i1:$src0, i1:$src1)),
|
|
(S_XOR_B64 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (sub i1:$src0, i1:$src1)),
|
|
(S_XOR_B64 $src0, $src1)
|
|
>;
|
|
|
|
let AddedComplexity = 1 in {
|
|
def : GCNPat <
|
|
(i1 (add i1:$src0, (i1 -1))),
|
|
(S_NOT_B64 $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (sub i1:$src0, (i1 -1))),
|
|
(S_NOT_B64 $src0)
|
|
>;
|
|
}
|
|
} // end isWave64
|
|
|
|
let WaveSizePredicate = isWave32 in {
|
|
def : GCNPat <
|
|
(i1 (and i1:$src0, i1:$src1)),
|
|
(S_AND_B32 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (or i1:$src0, i1:$src1)),
|
|
(S_OR_B32 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (xor i1:$src0, i1:$src1)),
|
|
(S_XOR_B32 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (add i1:$src0, i1:$src1)),
|
|
(S_XOR_B32 $src0, $src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (sub i1:$src0, i1:$src1)),
|
|
(S_XOR_B32 $src0, $src1)
|
|
>;
|
|
|
|
let AddedComplexity = 1 in {
|
|
def : GCNPat <
|
|
(i1 (add i1:$src0, (i1 -1))),
|
|
(S_NOT_B32 $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (sub i1:$src0, (i1 -1))),
|
|
(S_NOT_B32 $src0)
|
|
>;
|
|
}
|
|
} // end isWave32
|
|
|
|
def : GCNPat <
|
|
(f16 (sint_to_fp i1:$src)),
|
|
(V_CVT_F16_F32_e32 (
|
|
V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 CONST.FP32_NEG_ONE),
|
|
SSrc_i1:$src))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f16 (uint_to_fp i1:$src)),
|
|
(V_CVT_F16_F32_e32 (
|
|
V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 CONST.FP32_ONE),
|
|
SSrc_i1:$src))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f32 (sint_to_fp i1:$src)),
|
|
(V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 CONST.FP32_NEG_ONE),
|
|
SSrc_i1:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f32 (uint_to_fp i1:$src)),
|
|
(V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 CONST.FP32_ONE),
|
|
SSrc_i1:$src)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f64 (sint_to_fp i1:$src)),
|
|
(V_CVT_F64_I32_e32 (V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 -1),
|
|
SSrc_i1:$src))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(f64 (uint_to_fp i1:$src)),
|
|
(V_CVT_F64_U32_e32 (V_CNDMASK_B32_e64 /*src0mod*/(i32 0), /*src0*/(i32 0),
|
|
/*src1mod*/(i32 0), /*src1*/(i32 1),
|
|
SSrc_i1:$src))
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Miscellaneous Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
def : GCNPat <
|
|
(i32 (AMDGPUfp16_zext f16:$src)),
|
|
(COPY $src)
|
|
>;
|
|
|
|
|
|
def : GCNPat <
|
|
(i32 (trunc i64:$a)),
|
|
(EXTRACT_SUBREG $a, sub0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (trunc i32:$a)),
|
|
(V_CMP_EQ_U32_e64 (S_AND_B32 (i32 1), $a), (i32 1))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (trunc i16:$a)),
|
|
(V_CMP_EQ_U32_e64 (S_AND_B32 (i32 1), $a), (i32 1))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i1 (trunc i64:$a)),
|
|
(V_CMP_EQ_U32_e64 (S_AND_B32 (i32 1),
|
|
(i32 (EXTRACT_SUBREG $a, sub0))), (i32 1))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i32 (bswap i32:$a)),
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x00ff00ff)),
|
|
(V_ALIGNBIT_B32 VSrc_b32:$a, VSrc_b32:$a, (i32 24)),
|
|
(V_ALIGNBIT_B32 VSrc_b32:$a, VSrc_b32:$a, (i32 8)))
|
|
>;
|
|
|
|
// FIXME: This should have been narrowed to i32 during legalization.
|
|
// This pattern should also be skipped for GlobalISel
|
|
def : GCNPat <
|
|
(i64 (bswap i64:$a)),
|
|
(REG_SEQUENCE VReg_64,
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x00ff00ff)),
|
|
(V_ALIGNBIT_B32 (i32 (EXTRACT_SUBREG VReg_64:$a, sub1)),
|
|
(i32 (EXTRACT_SUBREG VReg_64:$a, sub1)),
|
|
(i32 24)),
|
|
(V_ALIGNBIT_B32 (i32 (EXTRACT_SUBREG VReg_64:$a, sub1)),
|
|
(i32 (EXTRACT_SUBREG VReg_64:$a, sub1)),
|
|
(i32 8))),
|
|
sub0,
|
|
(V_BFI_B32 (S_MOV_B32 (i32 0x00ff00ff)),
|
|
(V_ALIGNBIT_B32 (i32 (EXTRACT_SUBREG VReg_64:$a, sub0)),
|
|
(i32 (EXTRACT_SUBREG VReg_64:$a, sub0)),
|
|
(i32 24)),
|
|
(V_ALIGNBIT_B32 (i32 (EXTRACT_SUBREG VReg_64:$a, sub0)),
|
|
(i32 (EXTRACT_SUBREG VReg_64:$a, sub0)),
|
|
(i32 8))),
|
|
sub1)
|
|
>;
|
|
|
|
// FIXME: The AddedComplexity should not be needed, but in GlobalISel
|
|
// the BFI pattern ends up taking precedence without it.
|
|
let SubtargetPredicate = isGFX8Plus, AddedComplexity = 1 in {
|
|
// Magic number: 3 | (2 << 8) | (1 << 16) | (0 << 24)
|
|
//
|
|
// My reading of the manual suggests we should be using src0 for the
|
|
// register value, but this is what seems to work.
|
|
def : GCNPat <
|
|
(i32 (bswap i32:$a)),
|
|
(V_PERM_B32 (i32 0), VSrc_b32:$a, (S_MOV_B32 (i32 0x00010203)))
|
|
>;
|
|
|
|
// FIXME: This should have been narrowed to i32 during legalization.
|
|
// This pattern should also be skipped for GlobalISel
|
|
def : GCNPat <
|
|
(i64 (bswap i64:$a)),
|
|
(REG_SEQUENCE VReg_64,
|
|
(V_PERM_B32 (i32 0), (EXTRACT_SUBREG VReg_64:$a, sub1),
|
|
(S_MOV_B32 (i32 0x00010203))),
|
|
sub0,
|
|
(V_PERM_B32 (i32 0), (EXTRACT_SUBREG VReg_64:$a, sub0),
|
|
(S_MOV_B32 (i32 0x00010203))),
|
|
sub1)
|
|
>;
|
|
|
|
// Magic number: 1 | (0 << 8) | (12 << 16) | (12 << 24)
|
|
// The 12s emit 0s.
|
|
def : GCNPat <
|
|
(i16 (bswap i16:$a)),
|
|
(V_PERM_B32 (i32 0), VSrc_b32:$a, (S_MOV_B32 (i32 0x0c0c0001)))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i32 (zext (bswap i16:$a))),
|
|
(V_PERM_B32 (i32 0), VSrc_b32:$a, (S_MOV_B32 (i32 0x0c0c0001)))
|
|
>;
|
|
|
|
// Magic number: 1 | (0 << 8) | (3 << 16) | (2 << 24)
|
|
def : GCNPat <
|
|
(v2i16 (bswap v2i16:$a)),
|
|
(V_PERM_B32 (i32 0), VSrc_b32:$a, (S_MOV_B32 (i32 0x02030001)))
|
|
>;
|
|
|
|
}
|
|
|
|
|
|
// Prefer selecting to max when legal, but using mul is always valid.
|
|
let AddedComplexity = -5 in {
|
|
def : GCNPat<
|
|
(fcanonicalize (f16 (VOP3Mods f16:$src, i32:$src_mods))),
|
|
(V_MUL_F16_e64 0, (i32 CONST.FP16_ONE), $src_mods, $src)
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(fcanonicalize (f16 (fneg (VOP3Mods f16:$src, i32:$src_mods)))),
|
|
(V_MUL_F16_e64 0, (i32 CONST.FP16_NEG_ONE), $src_mods, $src)
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(fcanonicalize (v2f16 (VOP3PMods v2f16:$src, i32:$src_mods))),
|
|
(V_PK_MUL_F16 0, (i32 CONST.FP16_ONE), $src_mods, $src, DSTCLAMP.NONE)
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(fcanonicalize (f32 (VOP3Mods f32:$src, i32:$src_mods))),
|
|
(V_MUL_F32_e64 0, (i32 CONST.FP32_ONE), $src_mods, $src)
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(fcanonicalize (f32 (fneg (VOP3Mods f32:$src, i32:$src_mods)))),
|
|
(V_MUL_F32_e64 0, (i32 CONST.FP32_NEG_ONE), $src_mods, $src)
|
|
>;
|
|
|
|
// TODO: Handle fneg like other types.
|
|
def : GCNPat<
|
|
(fcanonicalize (f64 (VOP3Mods f64:$src, i32:$src_mods))),
|
|
(V_MUL_F64 0, CONST.FP64_ONE, $src_mods, $src)
|
|
>;
|
|
} // End AddedComplexity = -5
|
|
|
|
multiclass SelectCanonicalizeAsMax<
|
|
list<Predicate> f32_preds = [],
|
|
list<Predicate> f64_preds = [],
|
|
list<Predicate> f16_preds = []> {
|
|
def : GCNPat<
|
|
(fcanonicalize (f32 (VOP3Mods f32:$src, i32:$src_mods))),
|
|
(V_MAX_F32_e64 $src_mods, $src, $src_mods, $src)> {
|
|
let OtherPredicates = f32_preds;
|
|
}
|
|
|
|
def : GCNPat<
|
|
(fcanonicalize (f64 (VOP3Mods f64:$src, i32:$src_mods))),
|
|
(V_MAX_F64 $src_mods, $src, $src_mods, $src)> {
|
|
let OtherPredicates = f64_preds;
|
|
}
|
|
|
|
def : GCNPat<
|
|
(fcanonicalize (f16 (VOP3Mods f16:$src, i32:$src_mods))),
|
|
(V_MAX_F16_e64 $src_mods, $src, $src_mods, $src, 0, 0)> {
|
|
// FIXME: Should have 16-bit inst subtarget predicate
|
|
let OtherPredicates = f16_preds;
|
|
}
|
|
|
|
def : GCNPat<
|
|
(fcanonicalize (v2f16 (VOP3PMods v2f16:$src, i32:$src_mods))),
|
|
(V_PK_MAX_F16 $src_mods, $src, $src_mods, $src, DSTCLAMP.NONE)> {
|
|
// FIXME: Should have VOP3P subtarget predicate
|
|
let OtherPredicates = f16_preds;
|
|
}
|
|
}
|
|
|
|
// On pre-gfx9 targets, v_max_*/v_min_* did not respect the denormal
|
|
// mode, and would never flush. For f64, it's faster to do implement
|
|
// this with a max. For f16/f32 it's a wash, but prefer max when
|
|
// valid.
|
|
//
|
|
// FIXME: Lowering f32/f16 with max is worse since we can use a
|
|
// smaller encoding if the input is fneg'd. It also adds an extra
|
|
// register use.
|
|
let SubtargetPredicate = HasMinMaxDenormModes in {
|
|
defm : SelectCanonicalizeAsMax<[], [], []>;
|
|
} // End SubtargetPredicate = HasMinMaxDenormModes
|
|
|
|
let SubtargetPredicate = NotHasMinMaxDenormModes in {
|
|
// Use the max lowering if we don't need to flush.
|
|
|
|
// FIXME: We don't do use this for f32 as a workaround for the
|
|
// library being compiled with the default ieee mode, but
|
|
// potentially being called from flushing kernels. Really we should
|
|
// not be mixing code expecting different default FP modes, but mul
|
|
// works in any FP environment.
|
|
defm : SelectCanonicalizeAsMax<[FalsePredicate], [FP64Denormals], [FP16Denormals]>;
|
|
} // End SubtargetPredicate = NotHasMinMaxDenormModes
|
|
|
|
|
|
let OtherPredicates = [HasDLInsts] in {
|
|
def : GCNPat <
|
|
(fma (f32 (VOP3Mods f32:$src0, i32:$src0_modifiers)),
|
|
(f32 (VOP3Mods f32:$src1, i32:$src1_modifiers)),
|
|
(f32 (VOP3NoMods f32:$src2))),
|
|
(V_FMAC_F32_e64 $src0_modifiers, $src0, $src1_modifiers, $src1,
|
|
SRCMODS.NONE, $src2)
|
|
>;
|
|
} // End OtherPredicates = [HasDLInsts]
|
|
|
|
let SubtargetPredicate = isGFX10Plus in
|
|
def : GCNPat <
|
|
(fma (f16 (VOP3Mods f32:$src0, i32:$src0_modifiers)),
|
|
(f16 (VOP3Mods f32:$src1, i32:$src1_modifiers)),
|
|
(f16 (VOP3NoMods f32:$src2))),
|
|
(V_FMAC_F16_e64 $src0_modifiers, $src0, $src1_modifiers, $src1,
|
|
SRCMODS.NONE, $src2)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 0), (i16 SReg_32:$src1))),
|
|
(S_LSHL_B32 SReg_32:$src1, (i16 16))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 SReg_32:$src1), (i16 0))),
|
|
(S_AND_B32 (S_MOV_B32 (i32 0xffff)), SReg_32:$src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2f16 (build_vector (f16 SReg_32:$src1), (f16 FP_ZERO))),
|
|
(S_AND_B32 (S_MOV_B32 (i32 0xffff)), SReg_32:$src1)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 SReg_32:$src0), (i16 undef))),
|
|
(COPY_TO_REGCLASS SReg_32:$src0, SReg_32)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 VGPR_32:$src0), (i16 undef))),
|
|
(COPY_TO_REGCLASS VGPR_32:$src0, VGPR_32)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2f16 (build_vector f16:$src0, (f16 undef))),
|
|
(COPY $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 undef), (i16 SReg_32:$src1))),
|
|
(S_LSHL_B32 SReg_32:$src1, (i32 16))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2f16 (build_vector (f16 undef), (f16 SReg_32:$src1))),
|
|
(S_LSHL_B32 SReg_32:$src1, (i32 16))
|
|
>;
|
|
|
|
let SubtargetPredicate = HasVOP3PInsts in {
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 SReg_32:$src0), (i16 SReg_32:$src1))),
|
|
(S_PACK_LL_B32_B16 SReg_32:$src0, SReg_32:$src1)
|
|
>;
|
|
|
|
// With multiple uses of the shift, this will duplicate the shift and
|
|
// increase register pressure.
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 SReg_32:$src0), (i16 (trunc (srl_oneuse SReg_32:$src1, (i32 16)))))),
|
|
(v2i16 (S_PACK_LH_B32_B16 SReg_32:$src0, SReg_32:$src1))
|
|
>;
|
|
|
|
|
|
def : GCNPat <
|
|
(v2i16 (build_vector (i16 (trunc (srl_oneuse SReg_32:$src0, (i32 16)))),
|
|
(i16 (trunc (srl_oneuse SReg_32:$src1, (i32 16)))))),
|
|
(S_PACK_HH_B32_B16 SReg_32:$src0, SReg_32:$src1)
|
|
>;
|
|
|
|
// TODO: Should source modifiers be matched to v_pack_b32_f16?
|
|
def : GCNPat <
|
|
(v2f16 (build_vector (f16 SReg_32:$src0), (f16 SReg_32:$src1))),
|
|
(S_PACK_LL_B32_B16 SReg_32:$src0, SReg_32:$src1)
|
|
>;
|
|
|
|
} // End SubtargetPredicate = HasVOP3PInsts
|
|
|
|
|
|
def : GCNPat <
|
|
(v2f16 (scalar_to_vector f16:$src0)),
|
|
(COPY $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v2i16 (scalar_to_vector i16:$src0)),
|
|
(COPY $src0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v4i16 (scalar_to_vector i16:$src0)),
|
|
(INSERT_SUBREG (IMPLICIT_DEF), $src0, sub0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(v4f16 (scalar_to_vector f16:$src0)),
|
|
(INSERT_SUBREG (IMPLICIT_DEF), $src0, sub0)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (int_amdgcn_mov_dpp i64:$src, timm:$dpp_ctrl, timm:$row_mask,
|
|
timm:$bank_mask, timm:$bound_ctrl)),
|
|
(V_MOV_B64_DPP_PSEUDO VReg_64:$src, VReg_64:$src,
|
|
(as_i32timm $dpp_ctrl), (as_i32timm $row_mask),
|
|
(as_i32timm $bank_mask),
|
|
(as_i1timm $bound_ctrl))
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(i64 (int_amdgcn_update_dpp i64:$old, i64:$src, timm:$dpp_ctrl, timm:$row_mask,
|
|
timm:$bank_mask, timm:$bound_ctrl)),
|
|
(V_MOV_B64_DPP_PSEUDO VReg_64:$old, VReg_64:$src, (as_i32timm $dpp_ctrl),
|
|
(as_i32timm $row_mask), (as_i32timm $bank_mask),
|
|
(as_i1timm $bound_ctrl))
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Fract Patterns
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
let SubtargetPredicate = isGFX6 in {
|
|
|
|
// V_FRACT is buggy on SI, so the F32 version is never used and (x-floor(x)) is
|
|
// used instead. However, SI doesn't have V_FLOOR_F64, so the most efficient
|
|
// way to implement it is using V_FRACT_F64.
|
|
// The workaround for the V_FRACT bug is:
|
|
// fract(x) = isnan(x) ? x : min(V_FRACT(x), 0.99999999999999999)
|
|
|
|
// Convert floor(x) to (x - fract(x))
|
|
|
|
// Don't bother handling this for GlobalISel, it's handled during
|
|
// lowering.
|
|
//
|
|
// FIXME: DAG should also custom lower this.
|
|
def : GCNPat <
|
|
(f64 (ffloor (f64 (VOP3Mods f64:$x, i32:$mods)))),
|
|
(V_ADD_F64
|
|
$mods,
|
|
$x,
|
|
SRCMODS.NEG,
|
|
(V_CNDMASK_B64_PSEUDO
|
|
(V_MIN_F64
|
|
SRCMODS.NONE,
|
|
(V_FRACT_F64_e64 $mods, $x),
|
|
SRCMODS.NONE,
|
|
(V_MOV_B64_PSEUDO 0x3fefffffffffffff)),
|
|
$x,
|
|
(V_CMP_CLASS_F64_e64 SRCMODS.NONE, $x, (i32 3 /*NaN*/))))
|
|
>;
|
|
|
|
} // End SubtargetPredicates = isGFX6
|
|
|
|
//============================================================================//
|
|
// Miscellaneous Optimization Patterns
|
|
//============================================================================//
|
|
|
|
// Undo sub x, c -> add x, -c canonicalization since c is more likely
|
|
// an inline immediate than -c.
|
|
// TODO: Also do for 64-bit.
|
|
def : GCNPat<
|
|
(add i32:$src0, (i32 NegSubInlineConst32:$src1)),
|
|
(S_SUB_I32 SReg_32:$src0, NegSubInlineConst32:$src1)
|
|
>;
|
|
|
|
def : GCNPat<
|
|
(add i32:$src0, (i32 NegSubInlineConst32:$src1)),
|
|
(V_SUB_U32_e64 VS_32:$src0, NegSubInlineConst32:$src1)> {
|
|
let SubtargetPredicate = HasAddNoCarryInsts;
|
|
}
|
|
|
|
def : GCNPat<
|
|
(add i32:$src0, (i32 NegSubInlineConst32:$src1)),
|
|
(V_SUB_CO_U32_e64 VS_32:$src0, NegSubInlineConst32:$src1)> {
|
|
let SubtargetPredicate = NotHasAddNoCarryInsts;
|
|
}
|
|
|
|
|
|
// Avoid pointlessly materializing a constant in VGPR.
|
|
// FIXME: Should also do this for readlane, but tablegen crashes on
|
|
// the ignored src1.
|
|
def : GCNPat<
|
|
(int_amdgcn_readfirstlane (i32 imm:$src)),
|
|
(S_MOV_B32 SReg_32:$src)
|
|
>;
|
|
|
|
multiclass BFMPatterns <ValueType vt, InstSI BFM, InstSI MOV> {
|
|
def : GCNPat <
|
|
(vt (shl (vt (add (vt (shl 1, vt:$a)), -1)), vt:$b)),
|
|
(BFM $a, $b)
|
|
>;
|
|
|
|
def : GCNPat <
|
|
(vt (add (vt (shl 1, vt:$a)), -1)),
|
|
(BFM $a, (MOV (i32 0)))
|
|
>;
|
|
}
|
|
|
|
defm : BFMPatterns <i32, S_BFM_B32, S_MOV_B32>;
|
|
// FIXME: defm : BFMPatterns <i64, S_BFM_B64, S_MOV_B64>;
|
|
|
|
// Bitfield extract patterns
|
|
|
|
def IMMZeroBasedBitfieldMask : ImmLeaf <i32, [{
|
|
return isMask_32(Imm);
|
|
}]>;
|
|
|
|
def IMMPopCount : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(countPopulation(N->getZExtValue()), SDLoc(N),
|
|
MVT::i32);
|
|
}]>;
|
|
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<and> (i32 (srl i32:$src, i32:$rshift)),
|
|
IMMZeroBasedBitfieldMask:$mask),
|
|
(V_BFE_U32 $src, $rshift, (i32 (IMMPopCount $mask)))
|
|
>;
|
|
|
|
// x & ((1 << y) - 1)
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<and> i32:$src, (add_oneuse (shl_oneuse 1, i32:$width), -1)),
|
|
(V_BFE_U32 $src, (i32 0), $width)
|
|
>;
|
|
|
|
// x & ~(-1 << y)
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<and> i32:$src,
|
|
(xor_oneuse (shl_oneuse -1, i32:$width), -1)),
|
|
(V_BFE_U32 $src, (i32 0), $width)
|
|
>;
|
|
|
|
// x & (-1 >> (bitwidth - y))
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<and> i32:$src, (srl_oneuse -1, (sub 32, i32:$width))),
|
|
(V_BFE_U32 $src, (i32 0), $width)
|
|
>;
|
|
|
|
// x << (bitwidth - y) >> (bitwidth - y)
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<srl> (shl_oneuse i32:$src, (sub 32, i32:$width)),
|
|
(sub 32, i32:$width)),
|
|
(V_BFE_U32 $src, (i32 0), $width)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<sra> (shl_oneuse i32:$src, (sub 32, i32:$width)),
|
|
(sub 32, i32:$width)),
|
|
(V_BFE_I32 $src, (i32 0), $width)
|
|
>;
|
|
|
|
// SHA-256 Ma patterns
|
|
|
|
// ((x & z) | (y & (x | z))) -> BFI (XOR x, y), z, y
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<or> (and i32:$x, i32:$z),
|
|
(and i32:$y, (or i32:$x, i32:$z))),
|
|
(V_BFI_B32 (V_XOR_B32_e64 i32:$x, i32:$y), i32:$z, i32:$y)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(DivergentBinFrag<or> (and i64:$x, i64:$z),
|
|
(and i64:$y, (or i64:$x, i64:$z))),
|
|
(REG_SEQUENCE SReg_64,
|
|
(V_BFI_B32 (V_XOR_B32_e64 (i32 (EXTRACT_SUBREG SReg_64:$x, sub0)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub0))),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$z, sub0)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub0))), sub0,
|
|
(V_BFI_B32 (V_XOR_B32_e64 (i32 (EXTRACT_SUBREG SReg_64:$x, sub1)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub1))),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$z, sub1)),
|
|
(i32 (EXTRACT_SUBREG SReg_64:$y, sub1))), sub1)
|
|
>;
|
|
|
|
multiclass IntMed3Pat<Instruction med3Inst,
|
|
SDPatternOperator min,
|
|
SDPatternOperator max,
|
|
SDPatternOperator min_oneuse,
|
|
SDPatternOperator max_oneuse> {
|
|
|
|
// This matches 16 permutations of
|
|
// min(max(a, b), max(min(a, b), c))
|
|
def : AMDGPUPat <
|
|
(min (max_oneuse i32:$src0, i32:$src1),
|
|
(max_oneuse (min_oneuse i32:$src0, i32:$src1), i32:$src2)),
|
|
(med3Inst VSrc_b32:$src0, VSrc_b32:$src1, VSrc_b32:$src2)
|
|
>;
|
|
|
|
// This matches 16 permutations of
|
|
// max(min(x, y), min(max(x, y), z))
|
|
def : AMDGPUPat <
|
|
(max (min_oneuse i32:$src0, i32:$src1),
|
|
(min_oneuse (max_oneuse i32:$src0, i32:$src1), i32:$src2)),
|
|
(med3Inst VSrc_b32:$src0, VSrc_b32:$src1, VSrc_b32:$src2)
|
|
>;
|
|
}
|
|
|
|
defm : IntMed3Pat<V_MED3_I32, smin, smax, smin_oneuse, smax_oneuse>;
|
|
defm : IntMed3Pat<V_MED3_U32, umin, umax, umin_oneuse, umax_oneuse>;
|
|
|
|
// This matches 16 permutations of
|
|
// max(min(x, y), min(max(x, y), z))
|
|
class FPMed3Pat<ValueType vt,
|
|
//SDPatternOperator max, SDPatternOperator min,
|
|
Instruction med3Inst> : GCNPat<
|
|
(fmaxnum_like (fminnum_like_oneuse (VOP3Mods_nnan vt:$src0, i32:$src0_mods),
|
|
(VOP3Mods_nnan vt:$src1, i32:$src1_mods)),
|
|
(fminnum_like_oneuse (fmaxnum_like_oneuse (VOP3Mods_nnan vt:$src0, i32:$src0_mods),
|
|
(VOP3Mods_nnan vt:$src1, i32:$src1_mods)),
|
|
(vt (VOP3Mods_nnan vt:$src2, i32:$src2_mods)))),
|
|
(med3Inst $src0_mods, $src0, $src1_mods, $src1, $src2_mods, $src2, DSTCLAMP.NONE, DSTOMOD.NONE)
|
|
>;
|
|
|
|
class FP16Med3Pat<ValueType vt,
|
|
Instruction med3Inst> : GCNPat<
|
|
(fmaxnum_like (fminnum_like_oneuse (VOP3Mods_nnan vt:$src0, i32:$src0_mods),
|
|
(VOP3Mods_nnan vt:$src1, i32:$src1_mods)),
|
|
(fminnum_like_oneuse (fmaxnum_like_oneuse (VOP3Mods_nnan vt:$src0, i32:$src0_mods),
|
|
(VOP3Mods_nnan vt:$src1, i32:$src1_mods)),
|
|
(vt (VOP3Mods_nnan vt:$src2, i32:$src2_mods)))),
|
|
(med3Inst $src0_mods, $src0, $src1_mods, $src1, $src2_mods, $src2, DSTCLAMP.NONE)
|
|
>;
|
|
|
|
multiclass Int16Med3Pat<Instruction med3Inst,
|
|
SDPatternOperator min,
|
|
SDPatternOperator max,
|
|
SDPatternOperator max_oneuse,
|
|
SDPatternOperator min_oneuse> {
|
|
// This matches 16 permutations of
|
|
// max(min(x, y), min(max(x, y), z))
|
|
def : GCNPat <
|
|
(max (min_oneuse i16:$src0, i16:$src1),
|
|
(min_oneuse (max_oneuse i16:$src0, i16:$src1), i16:$src2)),
|
|
(med3Inst SRCMODS.NONE, VSrc_b16:$src0, SRCMODS.NONE, VSrc_b16:$src1, SRCMODS.NONE, VSrc_b16:$src2, DSTCLAMP.NONE)
|
|
>;
|
|
|
|
// This matches 16 permutations of
|
|
// min(max(a, b), max(min(a, b), c))
|
|
def : GCNPat <
|
|
(min (max_oneuse i16:$src0, i16:$src1),
|
|
(max_oneuse (min_oneuse i16:$src0, i16:$src1), i16:$src2)),
|
|
(med3Inst SRCMODS.NONE, VSrc_b16:$src0, SRCMODS.NONE, VSrc_b16:$src1, SRCMODS.NONE, VSrc_b16:$src2, DSTCLAMP.NONE)
|
|
>;
|
|
}
|
|
|
|
def : FPMed3Pat<f32, V_MED3_F32>;
|
|
|
|
let OtherPredicates = [isGFX9Plus] in {
|
|
def : FP16Med3Pat<f16, V_MED3_F16>;
|
|
defm : Int16Med3Pat<V_MED3_I16, smin, smax, smax_oneuse, smin_oneuse>;
|
|
defm : Int16Med3Pat<V_MED3_U16, umin, umax, umax_oneuse, umin_oneuse>;
|
|
} // End Predicates = [isGFX9Plus]
|
|
|
|
class AMDGPUGenericInstruction : GenericInstruction {
|
|
let Namespace = "AMDGPU";
|
|
}
|
|
|
|
def G_AMDGPU_FFBH_U32 : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type1:$src);
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
def G_AMDGPU_RCP_IFLAG : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type1:$src);
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
class BufferLoadGenericInstruction : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type1:$rsrc, type2:$vindex, type2:$voffset,
|
|
type2:$soffset, untyped_imm_0:$offset,
|
|
untyped_imm_0:$cachepolicy, untyped_imm_0:$idxen);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
}
|
|
|
|
class TBufferLoadGenericInstruction : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type1:$rsrc, type2:$vindex, type2:$voffset,
|
|
type2:$soffset, untyped_imm_0:$offset, untyped_imm_0:$format,
|
|
untyped_imm_0:$cachepolicy, untyped_imm_0:$idxen);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
}
|
|
|
|
def G_AMDGPU_BUFFER_LOAD_UBYTE : BufferLoadGenericInstruction;
|
|
def G_AMDGPU_BUFFER_LOAD_SBYTE : BufferLoadGenericInstruction;
|
|
def G_AMDGPU_BUFFER_LOAD_USHORT : BufferLoadGenericInstruction;
|
|
def G_AMDGPU_BUFFER_LOAD_SSHORT : BufferLoadGenericInstruction;
|
|
def G_AMDGPU_BUFFER_LOAD : BufferLoadGenericInstruction;
|
|
def G_AMDGPU_BUFFER_LOAD_FORMAT : BufferLoadGenericInstruction;
|
|
def G_AMDGPU_BUFFER_LOAD_FORMAT_D16 : BufferLoadGenericInstruction;
|
|
def G_AMDGPU_TBUFFER_LOAD_FORMAT : TBufferLoadGenericInstruction;
|
|
def G_AMDGPU_TBUFFER_LOAD_FORMAT_D16 : TBufferLoadGenericInstruction;
|
|
|
|
class BufferStoreGenericInstruction : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs);
|
|
let InOperandList = (ins type0:$vdata, type1:$rsrc, type2:$vindex, type2:$voffset,
|
|
type2:$soffset, untyped_imm_0:$offset,
|
|
untyped_imm_0:$cachepolicy, untyped_imm_0:$idxen);
|
|
let hasSideEffects = 0;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
class TBufferStoreGenericInstruction : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs);
|
|
let InOperandList = (ins type0:$vdata, type1:$rsrc, type2:$vindex, type2:$voffset,
|
|
type2:$soffset, untyped_imm_0:$offset,
|
|
untyped_imm_0:$format,
|
|
untyped_imm_0:$cachepolicy, untyped_imm_0:$idxen);
|
|
let hasSideEffects = 0;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
def G_AMDGPU_BUFFER_STORE : BufferStoreGenericInstruction;
|
|
def G_AMDGPU_BUFFER_STORE_BYTE : BufferStoreGenericInstruction;
|
|
def G_AMDGPU_BUFFER_STORE_SHORT : BufferStoreGenericInstruction;
|
|
def G_AMDGPU_BUFFER_STORE_FORMAT : BufferStoreGenericInstruction;
|
|
def G_AMDGPU_BUFFER_STORE_FORMAT_D16 : BufferStoreGenericInstruction;
|
|
def G_AMDGPU_TBUFFER_STORE_FORMAT : TBufferStoreGenericInstruction;
|
|
def G_AMDGPU_TBUFFER_STORE_FORMAT_D16 : TBufferStoreGenericInstruction;
|
|
|
|
def G_AMDGPU_FMIN_LEGACY : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type0:$src0, type0:$src1);
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
def G_AMDGPU_FMAX_LEGACY : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type0:$src0, type0:$src1);
|
|
let hasSideEffects = 0;
|
|
}
|
|
|
|
foreach N = 0-3 in {
|
|
def G_AMDGPU_CVT_F32_UBYTE#N : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type0:$src0);
|
|
let hasSideEffects = 0;
|
|
}
|
|
}
|
|
|
|
// Atomic cmpxchg. $cmpval ad $newval are packed in a single vector
|
|
// operand Expects a MachineMemOperand in addition to explicit
|
|
// operands.
|
|
def G_AMDGPU_ATOMIC_CMPXCHG : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$oldval);
|
|
let InOperandList = (ins ptype1:$addr, type0:$cmpval_newval);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
let Namespace = "AMDGPU" in {
|
|
def G_AMDGPU_ATOMIC_INC : G_ATOMICRMW_OP;
|
|
def G_AMDGPU_ATOMIC_DEC : G_ATOMICRMW_OP;
|
|
def G_AMDGPU_ATOMIC_FMIN : G_ATOMICRMW_OP;
|
|
def G_AMDGPU_ATOMIC_FMAX : G_ATOMICRMW_OP;
|
|
}
|
|
|
|
class BufferAtomicGenericInstruction<bit NoRtn = 0> : AMDGPUGenericInstruction {
|
|
let OutOperandList = !if(NoRtn, (outs), (outs type0:$dst));
|
|
let InOperandList = (ins type0:$vdata, type1:$rsrc, type2:$vindex, type2:$voffset,
|
|
type2:$soffset, untyped_imm_0:$offset,
|
|
untyped_imm_0:$cachepolicy, untyped_imm_0:$idxen);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
def G_AMDGPU_BUFFER_ATOMIC_SWAP : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_ADD : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_SUB : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_SMIN : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_UMIN : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_SMAX : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_UMAX : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_AND : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_OR : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_XOR : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_INC : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_DEC : BufferAtomicGenericInstruction;
|
|
def G_AMDGPU_BUFFER_ATOMIC_FADD : BufferAtomicGenericInstruction;
|
|
|
|
def G_AMDGPU_BUFFER_ATOMIC_CMPSWAP : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type0:$vdata, type0:$cmp, type1:$rsrc, type2:$vindex,
|
|
type2:$voffset, type2:$soffset, untyped_imm_0:$offset,
|
|
untyped_imm_0:$cachepolicy, untyped_imm_0:$idxen);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
// Wrapper around llvm.amdgcn.s.buffer.load. This is mostly needed as
|
|
// a workaround for the intrinsic being defined as readnone, but
|
|
// really needs a memory operand.
|
|
def G_AMDGPU_S_BUFFER_LOAD : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins type1:$rsrc, type2:$offset, untyped_imm_0:$cachepolicy);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
let mayStore = 0;
|
|
}
|
|
|
|
// This is equivalent to the G_INTRINSIC*, but the operands may have
|
|
// been legalized depending on the subtarget requirements.
|
|
def G_AMDGPU_INTRIN_IMAGE_LOAD : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins unknown:$intrin, variable_ops);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
|
|
// FIXME: Use separate opcode for atomics.
|
|
let mayStore = 1;
|
|
}
|
|
|
|
// This is equivalent to the G_INTRINSIC*, but the operands may have
|
|
// been legalized depending on the subtarget requirements.
|
|
def G_AMDGPU_INTRIN_IMAGE_STORE : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs);
|
|
let InOperandList = (ins unknown:$intrin, variable_ops);
|
|
let hasSideEffects = 0;
|
|
let mayStore = 1;
|
|
}
|
|
|
|
def G_AMDGPU_INTRIN_BVH_INTERSECT_RAY : AMDGPUGenericInstruction {
|
|
let OutOperandList = (outs type0:$dst);
|
|
let InOperandList = (ins unknown:$intrin, variable_ops);
|
|
let hasSideEffects = 0;
|
|
let mayLoad = 1;
|
|
let mayStore = 0;
|
|
}
|