llvm-project/llvm/lib/Target/AMDGPU/SIInstrInfo.td

3696 lines
131 KiB
TableGen
Raw Normal View History

//===-- SIInstrInfo.td - SI Instruction Infos -------------*- tablegen -*--===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
def isCI : Predicate<"Subtarget->getGeneration() "
">= SISubtarget::SEA_ISLANDS">;
def isCIOnly : Predicate<"Subtarget->getGeneration() =="
"SISubtarget::SEA_ISLANDS">,
AssemblerPredicate <"FeatureSeaIslands">;
def DisableInst : Predicate <"false">, AssemblerPredicate<"FeatureDisable">;
class vop {
field bits<9> SI3;
field bits<10> VI3;
}
class vopc <bits<8> si, bits<8> vi = !add(0x40, si)> : vop {
field bits<8> SI = si;
field bits<8> VI = vi;
field bits<9> SI3 = {0, si{7-0}};
field bits<10> VI3 = {0, 0, vi{7-0}};
}
class vop1 <bits<8> si, bits<8> vi = si> : vop {
field bits<8> SI = si;
field bits<8> VI = vi;
field bits<9> SI3 = {1, 1, si{6-0}};
field bits<10> VI3 = !add(0x140, vi);
}
class vop2 <bits<6> si, bits<6> vi = si> : vop {
field bits<6> SI = si;
field bits<6> VI = vi;
field bits<9> SI3 = {1, 0, 0, si{5-0}};
field bits<10> VI3 = {0, 1, 0, 0, vi{5-0}};
}
// Specify a VOP2 opcode for SI and VOP3 opcode for VI
// that doesn't have VOP2 encoding on VI
class vop23 <bits<6> si, bits<10> vi> : vop2 <si> {
let VI3 = vi;
}
class vop3 <bits<9> si, bits<10> vi = {0, si}> : vop {
let SI3 = si;
let VI3 = vi;
}
class sop1 <bits<8> si, bits<8> vi = si> {
field bits<8> SI = si;
field bits<8> VI = vi;
}
class sop2 <bits<7> si, bits<7> vi = si> {
field bits<7> SI = si;
field bits<7> VI = vi;
}
class sopk <bits<5> si, bits<5> vi = si> {
field bits<5> SI = si;
field bits<5> VI = vi;
}
class dsop <bits<8> si, bits<8> vi = si> {
field bits<8> SI = si;
field bits<8> VI = vi;
}
// Specify an SMRD opcode for SI and SMEM opcode for VI
// FIXME: This should really be bits<5> si, Tablegen crashes if
// parameter default value is other parameter with different bit size
class smrd<bits<8> si, bits<8> vi = si> {
field bits<5> SI = si{4-0};
field bits<8> VI = vi;
}
// Execpt for the NONE field, this must be kept in sync with the
// SIEncodingFamily enum in AMDGPUInstrInfo.cpp
def SIEncodingFamily {
int NONE = -1;
int SI = 0;
int VI = 1;
}
//===----------------------------------------------------------------------===//
// SI DAG Nodes
//===----------------------------------------------------------------------===//
def SIload_constant : SDNode<"AMDGPUISD::LOAD_CONSTANT",
SDTypeProfile<1, 2, [SDTCisVT<0, f32>, SDTCisVT<1, v4i32>, SDTCisVT<2, i32>]>,
[SDNPMayLoad, SDNPMemOperand]
>;
def SIatomic_inc : SDNode<"AMDGPUISD::ATOMIC_INC", SDTAtomic2,
[SDNPMayLoad, SDNPMayStore, SDNPMemOperand, SDNPHasChain]
>;
def SIatomic_dec : SDNode<"AMDGPUISD::ATOMIC_DEC", SDTAtomic2,
[SDNPMayLoad, SDNPMayStore, SDNPMemOperand, SDNPHasChain]
>;
def SItbuffer_store : SDNode<"AMDGPUISD::TBUFFER_STORE_FORMAT",
SDTypeProfile<0, 13,
[SDTCisVT<0, v4i32>, // rsrc(SGPR)
SDTCisVT<1, iAny>, // vdata(VGPR)
SDTCisVT<2, i32>, // num_channels(imm)
SDTCisVT<3, i32>, // vaddr(VGPR)
SDTCisVT<4, i32>, // soffset(SGPR)
SDTCisVT<5, i32>, // inst_offset(imm)
SDTCisVT<6, i32>, // dfmt(imm)
SDTCisVT<7, i32>, // nfmt(imm)
SDTCisVT<8, i32>, // offen(imm)
SDTCisVT<9, i32>, // idxen(imm)
SDTCisVT<10, i32>, // glc(imm)
SDTCisVT<11, i32>, // slc(imm)
SDTCisVT<12, i32> // tfe(imm)
]>,
[SDNPMayStore, SDNPMemOperand, SDNPHasChain]
>;
def SIload_input : SDNode<"AMDGPUISD::LOAD_INPUT",
SDTypeProfile<1, 3, [SDTCisVT<0, v4f32>, SDTCisVT<1, v4i32>, SDTCisVT<2, i16>,
SDTCisVT<3, i32>]>
>;
class SDSample<string opcode> : SDNode <opcode,
SDTypeProfile<1, 4, [SDTCisVT<0, v4f32>, SDTCisVT<2, v8i32>,
SDTCisVT<3, v4i32>, SDTCisVT<4, i32>]>
>;
def SIsample : SDSample<"AMDGPUISD::SAMPLE">;
def SIsampleb : SDSample<"AMDGPUISD::SAMPLEB">;
def SIsampled : SDSample<"AMDGPUISD::SAMPLED">;
def SIsamplel : SDSample<"AMDGPUISD::SAMPLEL">;
def SIpc_add_rel_offset : SDNode<"AMDGPUISD::PC_ADD_REL_OFFSET",
SDTypeProfile<1, 1, [SDTCisVT<0, iPTR>, SDTCisSameAs<0,1>]>
>;
//===----------------------------------------------------------------------===//
// PatFrags for FLAT instructions
//===----------------------------------------------------------------------===//
class flat_ld <SDPatternOperator ld> : PatFrag<(ops node:$ptr),
(ld node:$ptr), [{
const MemSDNode *LD = cast<MemSDNode>(N);
return LD->getAddressSpace() == AMDGPUAS::FLAT_ADDRESS ||
LD->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS ||
LD->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS;
}]>;
def flat_load : flat_ld <load>;
def atomic_flat_load : flat_ld<atomic_load>;
def flat_az_extloadi8 : flat_ld <az_extloadi8>;
def flat_sextloadi8 : flat_ld <sextloadi8>;
def flat_az_extloadi16 : flat_ld <az_extloadi16>;
def flat_sextloadi16 : flat_ld <sextloadi16>;
class flat_st <SDPatternOperator st> : PatFrag<(ops node:$val, node:$ptr),
(st node:$val, node:$ptr), [{
const MemSDNode *ST = cast<MemSDNode>(N);
return ST->getAddressSpace() == AMDGPUAS::FLAT_ADDRESS ||
ST->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
}]>;
def flat_store: flat_st <store>;
def atomic_flat_store: flat_st <atomic_store>;
def flat_truncstorei8 : flat_st <truncstorei8>;
def flat_truncstorei16 : flat_st <truncstorei16>;
class MubufLoad <SDPatternOperator op> : PatFrag <
(ops node:$ptr), (op node:$ptr), [{
const MemSDNode *LD = cast<MemSDNode>(N);
return LD->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS ||
LD->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS;
}]>;
def mubuf_load : MubufLoad <load>;
def mubuf_az_extloadi8 : MubufLoad <az_extloadi8>;
def mubuf_sextloadi8 : MubufLoad <sextloadi8>;
def mubuf_az_extloadi16 : MubufLoad <az_extloadi16>;
def mubuf_sextloadi16 : MubufLoad <sextloadi16>;
def mubuf_load_atomic : MubufLoad <atomic_load>;
def smrd_load : PatFrag <(ops node:$ptr), (load node:$ptr), [{
auto Ld = cast<LoadSDNode>(N);
return Ld->getAlignment() >= 4 &&
Ld->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS &&
static_cast<const SITargetLowering *>(getTargetLowering())->isMemOpUniform(N);
}]>;
//===----------------------------------------------------------------------===//
// PatFrags for global memory operations
//===----------------------------------------------------------------------===//
def atomic_inc_global : global_binary_atomic_op<SIatomic_inc>;
def atomic_dec_global : global_binary_atomic_op<SIatomic_dec>;
def atomic_inc_flat : flat_binary_atomic_op<SIatomic_inc>;
def atomic_dec_flat : flat_binary_atomic_op<SIatomic_dec>;
//===----------------------------------------------------------------------===//
// SDNodes and PatFrag for local loads and stores to enable s_mov_b32 m0, -1
// to be glued to the memory instructions.
//===----------------------------------------------------------------------===//
def SIld_local : SDNode <"ISD::LOAD", SDTLoad,
[SDNPHasChain, SDNPMayLoad, SDNPMemOperand, SDNPInGlue]
>;
def si_ld_local : PatFrag <(ops node:$ptr), (SIld_local node:$ptr), [{
return cast<LoadSDNode>(N)->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
}]>;
def si_load_local : PatFrag <(ops node:$ptr), (si_ld_local node:$ptr), [{
return cast<LoadSDNode>(N)->getAddressingMode() == ISD::UNINDEXED &&
cast<LoadSDNode>(N)->getExtensionType() == ISD::NON_EXTLOAD;
}]>;
def si_load_local_align8 : Aligned8Bytes <
(ops node:$ptr), (si_load_local node:$ptr)
>;
def si_sextload_local : PatFrag <(ops node:$ptr), (si_ld_local node:$ptr), [{
return cast<LoadSDNode>(N)->getExtensionType() == ISD::SEXTLOAD;
}]>;
def si_az_extload_local : AZExtLoadBase <si_ld_local>;
multiclass SIExtLoadLocal <PatFrag ld_node> {
def _i8 : PatFrag <(ops node:$ptr), (ld_node node:$ptr),
[{return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i8;}]
>;
def _i16 : PatFrag <(ops node:$ptr), (ld_node node:$ptr),
[{return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i16;}]
>;
}
defm si_sextload_local : SIExtLoadLocal <si_sextload_local>;
defm si_az_extload_local : SIExtLoadLocal <si_az_extload_local>;
def SIst_local : SDNode <"ISD::STORE", SDTStore,
[SDNPHasChain, SDNPMayStore, SDNPMemOperand, SDNPInGlue]
>;
def si_st_local : PatFrag <
(ops node:$val, node:$ptr), (SIst_local node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
}]>;
def si_store_local : PatFrag <
(ops node:$val, node:$ptr), (si_st_local node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->getAddressingMode() == ISD::UNINDEXED &&
!cast<StoreSDNode>(N)->isTruncatingStore();
}]>;
def si_store_local_align8 : Aligned8Bytes <
(ops node:$val, node:$ptr), (si_store_local node:$val, node:$ptr)
>;
def si_truncstore_local : PatFrag <
(ops node:$val, node:$ptr), (si_st_local node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->isTruncatingStore();
}]>;
def si_truncstore_local_i8 : PatFrag <
(ops node:$val, node:$ptr), (si_truncstore_local node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->getMemoryVT() == MVT::i8;
}]>;
def si_truncstore_local_i16 : PatFrag <
(ops node:$val, node:$ptr), (si_truncstore_local node:$val, node:$ptr), [{
return cast<StoreSDNode>(N)->getMemoryVT() == MVT::i16;
}]>;
def si_setcc_uniform : PatFrag <
(ops node:$lhs, node:$rhs, node:$cond),
(setcc node:$lhs, node:$rhs, node:$cond), [{
for (SDNode *Use : N->uses()) {
if (Use->isMachineOpcode() || Use->getOpcode() != ISD::CopyToReg)
return false;
unsigned Reg = cast<RegisterSDNode>(Use->getOperand(1))->getReg();
if (Reg != AMDGPU::SCC)
return false;
}
return true;
}]>;
def si_uniform_br : PatFrag <
(ops node:$cond, node:$bb), (brcond node:$cond, node:$bb), [{
return isUniformBr(N);
}]>;
def si_uniform_br_scc : PatFrag <
(ops node:$cond, node:$bb), (si_uniform_br node:$cond, node:$bb), [{
return isCBranchSCC(N);
}]>;
multiclass SIAtomicM0Glue2 <string op_name, bit is_amdgpu = 0> {
def _glue : SDNode <
!if(is_amdgpu, "AMDGPUISD", "ISD")#"::ATOMIC_"#op_name, SDTAtomic2,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad, SDNPMemOperand, SDNPInGlue]
>;
def _local : local_binary_atomic_op <!cast<SDNode>(NAME#"_glue")>;
}
defm si_atomic_load_add : SIAtomicM0Glue2 <"LOAD_ADD">;
defm si_atomic_load_sub : SIAtomicM0Glue2 <"LOAD_SUB">;
defm si_atomic_inc : SIAtomicM0Glue2 <"INC", 1>;
defm si_atomic_dec : SIAtomicM0Glue2 <"DEC", 1>;
defm si_atomic_load_and : SIAtomicM0Glue2 <"LOAD_AND">;
defm si_atomic_load_min : SIAtomicM0Glue2 <"LOAD_MIN">;
defm si_atomic_load_max : SIAtomicM0Glue2 <"LOAD_MAX">;
defm si_atomic_load_or : SIAtomicM0Glue2 <"LOAD_OR">;
defm si_atomic_load_xor : SIAtomicM0Glue2 <"LOAD_XOR">;
defm si_atomic_load_umin : SIAtomicM0Glue2 <"LOAD_UMIN">;
defm si_atomic_load_umax : SIAtomicM0Glue2 <"LOAD_UMAX">;
defm si_atomic_swap : SIAtomicM0Glue2 <"SWAP">;
def si_atomic_cmp_swap_glue : SDNode <"ISD::ATOMIC_CMP_SWAP", SDTAtomic3,
[SDNPHasChain, SDNPMayStore, SDNPMayLoad, SDNPMemOperand, SDNPInGlue]
>;
defm si_atomic_cmp_swap : AtomicCmpSwapLocal <si_atomic_cmp_swap_glue>;
// Transformation function, extract the lower 32bit of a 64bit immediate
def LO32 : SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getZExtValue() & 0xffffffff, SDLoc(N),
MVT::i32);
}]>;
def LO32f : SDNodeXForm<fpimm, [{
APInt V = N->getValueAPF().bitcastToAPInt().trunc(32);
return CurDAG->getTargetConstantFP(APFloat(APFloat::IEEEsingle, V), MVT::f32);
}]>;
// Transformation function, extract the upper 32bit of a 64bit immediate
def HI32 : SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getZExtValue() >> 32, SDLoc(N), MVT::i32);
}]>;
def HI32f : SDNodeXForm<fpimm, [{
APInt V = N->getValueAPF().bitcastToAPInt().lshr(32).trunc(32);
return CurDAG->getTargetConstantFP(APFloat(APFloat::IEEEsingle, V), SDLoc(N),
MVT::f32);
}]>;
def IMM8bitDWORD : PatLeaf <(imm),
[{return (N->getZExtValue() & ~0x3FC) == 0;}]
>;
def as_dword_i32imm : SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getZExtValue() >> 2, SDLoc(N), MVT::i32);
}]>;
def as_i1imm : SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getZExtValue(), SDLoc(N), MVT::i1);
}]>;
def as_i8imm : SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getZExtValue(), SDLoc(N), MVT::i8);
}]>;
def as_i16imm : SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getSExtValue(), SDLoc(N), MVT::i16);
}]>;
def as_i32imm: SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getSExtValue(), SDLoc(N), MVT::i32);
}]>;
def as_i64imm: SDNodeXForm<imm, [{
return CurDAG->getTargetConstant(N->getSExtValue(), SDLoc(N), MVT::i64);
}]>;
// Copied from the AArch64 backend:
def bitcast_fpimm_to_i32 : SDNodeXForm<fpimm, [{
return CurDAG->getTargetConstant(
N->getValueAPF().bitcastToAPInt().getZExtValue(), SDLoc(N), MVT::i32);
}]>;
// Copied from the AArch64 backend:
def bitcast_fpimm_to_i64 : SDNodeXForm<fpimm, [{
return CurDAG->getTargetConstant(
N->getValueAPF().bitcastToAPInt().getZExtValue(), SDLoc(N), MVT::i64);
}]>;
def IMM8bit : PatLeaf <(imm),
[{return isUInt<8>(N->getZExtValue());}]
>;
def IMM12bit : PatLeaf <(imm),
[{return isUInt<12>(N->getZExtValue());}]
>;
def IMM16bit : PatLeaf <(imm),
[{return isUInt<16>(N->getZExtValue());}]
>;
def SIMM16bit : PatLeaf <(imm),
[{return isInt<16>(N->getSExtValue());}]
>;
def IMM20bit : PatLeaf <(imm),
[{return isUInt<20>(N->getZExtValue());}]
>;
def IMM32bit : PatLeaf <(imm),
[{return isUInt<32>(N->getZExtValue());}]
>;
def mubuf_vaddr_offset : PatFrag<
(ops node:$ptr, node:$offset, node:$imm_offset),
(add (add node:$ptr, node:$offset), node:$imm_offset)
>;
class InlineImm <ValueType vt> : PatLeaf <(vt imm), [{
return isInlineImmediate(N);
}]>;
class InlineFPImm <ValueType vt> : PatLeaf <(vt fpimm), [{
return isInlineImmediate(N);
}]>;
class SGPRImm <dag frag> : PatLeaf<frag, [{
if (Subtarget->getGeneration() < SISubtarget::SOUTHERN_ISLANDS) {
return false;
}
const SIRegisterInfo *SIRI =
static_cast<const SIRegisterInfo *>(Subtarget->getRegisterInfo());
for (SDNode::use_iterator U = N->use_begin(), E = SDNode::use_end();
U != E; ++U) {
const TargetRegisterClass *RC = getOperandRegClass(*U, U.getOperandNo());
if (RC && SIRI->isSGPRClass(RC))
return true;
}
return false;
}]>;
//===----------------------------------------------------------------------===//
// Custom Operands
//===----------------------------------------------------------------------===//
def FRAMEri32 : Operand<iPTR> {
let MIOperandInfo = (ops i32:$ptr, i32imm:$index);
}
def SoppBrTarget : AsmOperandClass {
let Name = "SoppBrTarget";
let ParserMethod = "parseSOppBrTarget";
}
def sopp_brtarget : Operand<OtherVT> {
let EncoderMethod = "getSOPPBrEncoding";
let OperandType = "OPERAND_PCREL";
let ParserMatchClass = SoppBrTarget;
}
def si_ga : Operand<iPTR>;
def InterpSlot : Operand<i32> {
let PrintMethod = "printInterpSlot";
}
def SendMsgMatchClass : AsmOperandClass {
let Name = "SendMsg";
let PredicateMethod = "isSendMsg";
let ParserMethod = "parseSendMsgOp";
let RenderMethod = "addImmOperands";
}
def SendMsgImm : Operand<i32> {
let PrintMethod = "printSendMsg";
let ParserMatchClass = SendMsgMatchClass;
}
def SWaitMatchClass : AsmOperandClass {
let Name = "SWaitCnt";
let RenderMethod = "addImmOperands";
let ParserMethod = "parseSWaitCntOps";
}
def WAIT_FLAG : Operand <i32> {
let ParserMatchClass = SWaitMatchClass;
let PrintMethod = "printWaitFlag";
}
include "SIInstrFormats.td"
include "VIInstrFormats.td"
class NamedMatchClass<string CName, bit Optional = 1> : AsmOperandClass {
let Name = "Imm"#CName;
let PredicateMethod = "is"#CName;
let ParserMethod = !if(Optional, "parseOptionalOperand", "parse"#CName);
let RenderMethod = "addImmOperands";
let IsOptional = Optional;
let DefaultMethod = !if(Optional, "default"#CName, ?);
}
class NamedOperandBit<string Name, AsmOperandClass MatchClass> : Operand<i1> {
let PrintMethod = "print"#Name;
let ParserMatchClass = MatchClass;
}
class NamedOperandU8<string Name, AsmOperandClass MatchClass> : Operand<i8> {
let PrintMethod = "print"#Name;
let ParserMatchClass = MatchClass;
}
class NamedOperandU16<string Name, AsmOperandClass MatchClass> : Operand<i16> {
let PrintMethod = "print"#Name;
let ParserMatchClass = MatchClass;
}
class NamedOperandU32<string Name, AsmOperandClass MatchClass> : Operand<i32> {
let PrintMethod = "print"#Name;
let ParserMatchClass = MatchClass;
}
let OperandType = "OPERAND_IMMEDIATE" in {
def offen : NamedOperandBit<"Offen", NamedMatchClass<"Offen">>;
def idxen : NamedOperandBit<"Idxen", NamedMatchClass<"Idxen">>;
def addr64 : NamedOperandBit<"Addr64", NamedMatchClass<"Addr64">>;
def offset : NamedOperandU16<"Offset", NamedMatchClass<"Offset">>;
def offset0 : NamedOperandU8<"Offset0", NamedMatchClass<"Offset0">>;
def offset1 : NamedOperandU8<"Offset1", NamedMatchClass<"Offset1">>;
def gds : NamedOperandBit<"GDS", NamedMatchClass<"GDS">>;
def omod : NamedOperandU32<"OModSI", NamedMatchClass<"OModSI">>;
def clampmod : NamedOperandBit<"ClampSI", NamedMatchClass<"ClampSI">>;
def smrd_offset : NamedOperandU32<"SMRDOffset", NamedMatchClass<"SMRDOffset">>;
def smrd_literal_offset : NamedOperandU32<"SMRDLiteralOffset", NamedMatchClass<"SMRDLiteralOffset">>;
def glc : NamedOperandBit<"GLC", NamedMatchClass<"GLC">>;
def slc : NamedOperandBit<"SLC", NamedMatchClass<"SLC">>;
def tfe : NamedOperandBit<"TFE", NamedMatchClass<"TFE">>;
def unorm : NamedOperandBit<"UNorm", NamedMatchClass<"UNorm">>;
def da : NamedOperandBit<"DA", NamedMatchClass<"DA">>;
def r128 : NamedOperandBit<"R128", NamedMatchClass<"R128">>;
def lwe : NamedOperandBit<"LWE", NamedMatchClass<"LWE">>;
def dmask : NamedOperandU16<"DMask", NamedMatchClass<"DMask">>;
def dpp_ctrl : NamedOperandU32<"DPPCtrl", NamedMatchClass<"DPPCtrl", 0>>;
def row_mask : NamedOperandU32<"RowMask", NamedMatchClass<"RowMask">>;
def bank_mask : NamedOperandU32<"BankMask", NamedMatchClass<"BankMask">>;
def bound_ctrl : NamedOperandBit<"BoundCtrl", NamedMatchClass<"BoundCtrl">>;
def dst_sel : NamedOperandU32<"SDWADstSel", NamedMatchClass<"SDWADstSel">>;
def src0_sel : NamedOperandU32<"SDWASrc0Sel", NamedMatchClass<"SDWASrc0Sel">>;
def src1_sel : NamedOperandU32<"SDWASrc1Sel", NamedMatchClass<"SDWASrc1Sel">>;
def dst_unused : NamedOperandU32<"SDWADstUnused", NamedMatchClass<"SDWADstUnused">>;
def hwreg : NamedOperandU16<"Hwreg", NamedMatchClass<"Hwreg", 0>>;
} // End OperandType = "OPERAND_IMMEDIATE"
def VOPDstS64 : VOPDstOperand <SReg_64>;
def FPInputModsMatchClass : AsmOperandClass {
let Name = "RegOrImmWithFPInputMods";
let ParserMethod = "parseRegOrImmWithFPInputMods";
let PredicateMethod = "isRegOrImmWithInputMods";
}
def FPInputMods : Operand <i32> {
let PrintMethod = "printOperandAndFPInputMods";
let ParserMatchClass = FPInputModsMatchClass;
}
def IntInputModsMatchClass : AsmOperandClass {
let Name = "RegOrImmWithIntInputMods";
let ParserMethod = "parseRegOrImmWithIntInputMods";
let PredicateMethod = "isRegOrImmWithInputMods";
}
def IntInputMods: Operand <i32> {
let PrintMethod = "printOperandAndIntInputMods";
let ParserMatchClass = IntInputModsMatchClass;
}
//===----------------------------------------------------------------------===//
// Complex patterns
//===----------------------------------------------------------------------===//
def DS1Addr1Offset : ComplexPattern<i32, 2, "SelectDS1Addr1Offset">;
def DS64Bit4ByteAligned : ComplexPattern<i32, 3, "SelectDS64Bit4ByteAligned">;
def MUBUFAddr32 : ComplexPattern<i64, 9, "SelectMUBUFAddr32">;
def MUBUFAddr64 : ComplexPattern<i64, 7, "SelectMUBUFAddr64">;
def MUBUFAddr64Atomic : ComplexPattern<i64, 5, "SelectMUBUFAddr64">;
def FLATAtomic : ComplexPattern<i64, 3, "SelectFlat">;
def MUBUFScratch : ComplexPattern<i64, 4, "SelectMUBUFScratch">;
def MUBUFOffset : ComplexPattern<i64, 6, "SelectMUBUFOffset">;
def MUBUFOffsetNoGLC : ComplexPattern<i64, 3, "SelectMUBUFOffset">;
def MUBUFOffsetAtomic : ComplexPattern<i64, 4, "SelectMUBUFOffset">;
def MUBUFIntrinsicOffset : ComplexPattern<i32, 2, "SelectMUBUFIntrinsicOffset">;
def MUBUFIntrinsicVOffset : ComplexPattern<i32, 3, "SelectMUBUFIntrinsicVOffset">;
def SMRDImm : ComplexPattern<i64, 2, "SelectSMRDImm">;
def SMRDImm32 : ComplexPattern<i64, 2, "SelectSMRDImm32">;
def SMRDSgpr : ComplexPattern<i64, 2, "SelectSMRDSgpr">;
def SMRDBufferImm : ComplexPattern<i32, 1, "SelectSMRDBufferImm">;
def SMRDBufferImm32 : ComplexPattern<i32, 1, "SelectSMRDBufferImm32">;
def SMRDBufferSgpr : ComplexPattern<i32, 1, "SelectSMRDBufferSgpr">;
def MOVRELOffset : ComplexPattern<i32, 2, "SelectMOVRELOffset">;
def VOP3Mods0 : ComplexPattern<untyped, 4, "SelectVOP3Mods0">;
def VOP3NoMods0 : ComplexPattern<untyped, 4, "SelectVOP3NoMods0">;
def VOP3Mods0Clamp : ComplexPattern<untyped, 3, "SelectVOP3Mods0Clamp">;
def VOP3Mods0Clamp0OMod : ComplexPattern<untyped, 4, "SelectVOP3Mods0Clamp0OMod">;
def VOP3Mods : ComplexPattern<untyped, 2, "SelectVOP3Mods">;
def VOP3NoMods : ComplexPattern<untyped, 2, "SelectVOP3NoMods">;
//===----------------------------------------------------------------------===//
// SI assembler operands
//===----------------------------------------------------------------------===//
def SIOperand {
int ZERO = 0x80;
int VCC = 0x6A;
int FLAT_SCR = 0x68;
}
def SRCMODS {
int NONE = 0;
int NEG = 1;
}
def DSTCLAMP {
int NONE = 0;
}
def DSTOMOD {
int NONE = 0;
}
//===----------------------------------------------------------------------===//
//
// SI Instruction multiclass helpers.
//
// Instructions with _32 take 32-bit operands.
// Instructions with _64 take 64-bit operands.
//
// VOP_* instructions can use either a 32-bit or 64-bit encoding. The 32-bit
// encoding is the standard encoding, but instruction that make use of
// any of the instruction modifiers must use the 64-bit encoding.
//
// Instructions with _e32 use the 32-bit encoding.
// Instructions with _e64 use the 64-bit encoding.
//
//===----------------------------------------------------------------------===//
class SIMCInstr <string pseudo, int subtarget> {
string PseudoInstr = pseudo;
int Subtarget = subtarget;
}
//===----------------------------------------------------------------------===//
// EXP classes
//===----------------------------------------------------------------------===//
class EXPCommon : InstSI<
(outs),
(ins i32imm:$en, i32imm:$tgt, i32imm:$compr, i32imm:$done, i32imm:$vm,
VGPR_32:$src0, VGPR_32:$src1, VGPR_32:$src2, VGPR_32:$src3),
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
"exp $en, $tgt, $compr, $done, $vm, $src0, $src1, $src2, $src3",
[] > {
let EXP_CNT = 1;
let Uses = [EXEC];
let SchedRW = [WriteExport];
}
multiclass EXP_m {
let isPseudo = 1, isCodeGenOnly = 1 in {
def "" : EXPCommon, SIMCInstr <"exp", SIEncodingFamily.NONE> ;
}
def _si : EXPCommon, SIMCInstr <"exp", SIEncodingFamily.SI>, EXPe {
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="SICI";
let DisableDecoder = DisableSIDecoder;
}
def _vi : EXPCommon, SIMCInstr <"exp", SIEncodingFamily.VI>, EXPe_vi {
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="VI";
let DisableDecoder = DisableVIDecoder;
}
}
//===----------------------------------------------------------------------===//
// Scalar classes
//===----------------------------------------------------------------------===//
class SOP1_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
SOP1 <outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class SOP1_Real_si <sop1 op, string opName, dag outs, dag ins, string asm> :
SOP1 <outs, ins, asm, []>,
SOP1e <op.SI>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let isCodeGenOnly = 0;
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class SOP1_Real_vi <sop1 op, string opName, dag outs, dag ins, string asm> :
SOP1 <outs, ins, asm, []>,
SOP1e <op.VI>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let isCodeGenOnly = 0;
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass SOP1_m <sop1 op, string opName, dag outs, dag ins, string asm,
list<dag> pattern> {
def "" : SOP1_Pseudo <opName, outs, ins, pattern>;
def _si : SOP1_Real_si <op, opName, outs, ins, asm>;
def _vi : SOP1_Real_vi <op, opName, outs, ins, asm>;
}
multiclass SOP1_32 <sop1 op, string opName, list<dag> pattern> : SOP1_m <
op, opName, (outs SReg_32:$sdst), (ins SSrc_32:$src0),
opName#" $sdst, $src0", pattern
>;
multiclass SOP1_64 <sop1 op, string opName, list<dag> pattern> : SOP1_m <
op, opName, (outs SReg_64:$sdst), (ins SSrc_64:$src0),
opName#" $sdst, $src0", pattern
>;
// no input, 64-bit output.
multiclass SOP1_64_0 <sop1 op, string opName, list<dag> pattern> {
def "" : SOP1_Pseudo <opName, (outs SReg_64:$sdst), (ins), pattern>;
def _si : SOP1_Real_si <op, opName, (outs SReg_64:$sdst), (ins),
opName#" $sdst"> {
let src0 = 0;
}
def _vi : SOP1_Real_vi <op, opName, (outs SReg_64:$sdst), (ins),
opName#" $sdst"> {
let src0 = 0;
}
}
// 64-bit input, no output
multiclass SOP1_1 <sop1 op, string opName, list<dag> pattern> {
def "" : SOP1_Pseudo <opName, (outs), (ins SReg_64:$src0), pattern>;
def _si : SOP1_Real_si <op, opName, (outs), (ins SReg_64:$src0),
opName#" $src0"> {
let sdst = 0;
}
def _vi : SOP1_Real_vi <op, opName, (outs), (ins SReg_64:$src0),
opName#" $src0"> {
let sdst = 0;
}
}
// 64-bit input, 32-bit output.
multiclass SOP1_32_64 <sop1 op, string opName, list<dag> pattern> : SOP1_m <
op, opName, (outs SReg_32:$sdst), (ins SSrc_64:$src0),
opName#" $sdst, $src0", pattern
>;
// 32-bit input, 64-bit output.
multiclass SOP1_64_32 <sop1 op, string opName, list<dag> pattern> : SOP1_m <
op, opName, (outs SReg_64:$sdst), (ins SSrc_32:$src0),
opName#" $sdst, $src0", pattern
>;
class SOP2_Pseudo<string opName, dag outs, dag ins, list<dag> pattern> :
SOP2<outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
let Size = 4;
// 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;
}
class SOP2_Real_si<sop2 op, string opName, dag outs, dag ins, string asm> :
SOP2<outs, ins, asm, []>,
SOP2e<op.SI>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class SOP2_Real_vi<sop2 op, string opName, dag outs, dag ins, string asm> :
SOP2<outs, ins, asm, []>,
SOP2e<op.VI>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass SOP2_m <sop2 op, string opName, dag outs, dag ins, string asm,
list<dag> pattern> {
def "" : SOP2_Pseudo <opName, outs, ins, pattern>;
def _si : SOP2_Real_si <op, opName, outs, ins, asm>;
def _vi : SOP2_Real_vi <op, opName, outs, ins, asm>;
}
multiclass SOP2_32 <sop2 op, string opName, list<dag> pattern> : SOP2_m <
op, opName, (outs SReg_32:$sdst), (ins SSrc_32:$src0, SSrc_32:$src1),
opName#" $sdst, $src0, $src1", pattern
>;
multiclass SOP2_64 <sop2 op, string opName, list<dag> pattern> : SOP2_m <
op, opName, (outs SReg_64:$sdst), (ins SSrc_64:$src0, SSrc_64:$src1),
opName#" $sdst, $src0, $src1", pattern
>;
multiclass SOP2_64_32 <sop2 op, string opName, list<dag> pattern> : SOP2_m <
op, opName, (outs SReg_64:$sdst), (ins SSrc_64:$src0, SSrc_32:$src1),
opName#" $sdst, $src0, $src1", pattern
>;
multiclass SOP2_64_32_32 <sop2 op, string opName, list<dag> pattern> : SOP2_m <
op, opName, (outs SReg_64:$sdst), (ins SSrc_32:$src0, SSrc_32:$src1),
opName#" $sdst, $src0, $src1", pattern
>;
class SOPC_Base <bits<7> op, RegisterOperand rc0, RegisterOperand rc1,
string opName, list<dag> pattern = []> : SOPC <
op, (outs), (ins rc0:$src0, rc1:$src1),
opName#" $src0, $src1", pattern > {
let Defs = [SCC];
}
class SOPC_Helper <bits<7> op, RegisterOperand rc, ValueType vt,
string opName, PatLeaf cond> : SOPC_Base <
op, rc, rc, opName,
[(set SCC, (si_setcc_uniform vt:$src0, vt:$src1, cond))] > {
}
class SOPC_CMP_32<bits<7> op, string opName, PatLeaf cond = COND_NULL>
: SOPC_Helper<op, SSrc_32, i32, opName, cond>;
class SOPC_32<bits<7> op, string opName, list<dag> pattern = []>
: SOPC_Base<op, SSrc_32, SSrc_32, opName, pattern>;
class SOPC_64_32<bits<7> op, string opName, list<dag> pattern = []>
: SOPC_Base<op, SSrc_64, SSrc_32, opName, pattern>;
class SOPK_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
SOPK <outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class SOPK_Real_si <sopk op, string opName, dag outs, dag ins, string asm> :
SOPK <outs, ins, asm, []>,
SOPKe <op.SI>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
let isCodeGenOnly = 0;
}
class SOPK_Real_vi <sopk op, string opName, dag outs, dag ins, string asm> :
SOPK <outs, ins, asm, []>,
SOPKe <op.VI>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
let isCodeGenOnly = 0;
}
multiclass SOPK_m <sopk op, string opName, dag outs, dag ins, string opAsm,
string asm = opName#opAsm> {
def "" : SOPK_Pseudo <opName, outs, ins, []>;
def _si : SOPK_Real_si <op, opName, outs, ins, asm>;
def _vi : SOPK_Real_vi <op, opName, outs, ins, asm>;
}
multiclass SOPK_32 <sopk op, string opName, list<dag> pattern> {
def "" : SOPK_Pseudo <opName, (outs SReg_32:$sdst), (ins u16imm:$simm16),
pattern>;
def _si : SOPK_Real_si <op, opName, (outs SReg_32:$sdst), (ins u16imm:$simm16),
opName#" $sdst, $simm16">;
def _vi : SOPK_Real_vi <op, opName, (outs SReg_32:$sdst), (ins u16imm:$simm16),
opName#" $sdst, $simm16">;
}
multiclass SOPK_SCC <sopk op, string opName, list<dag> pattern> {
def "" : SOPK_Pseudo <opName, (outs),
(ins SReg_32:$src0, u16imm:$src1), pattern> {
let Defs = [SCC];
}
def _si : SOPK_Real_si <op, opName, (outs),
(ins SReg_32:$sdst, u16imm:$simm16), opName#" $sdst, $simm16"> {
let Defs = [SCC];
}
def _vi : SOPK_Real_vi <op, opName, (outs),
(ins SReg_32:$sdst, u16imm:$simm16), opName#" $sdst, $simm16"> {
let Defs = [SCC];
}
}
multiclass SOPK_32TIE <sopk op, string opName, list<dag> pattern> : SOPK_m <
op, opName, (outs SReg_32:$sdst), (ins SReg_32:$src0, u16imm:$simm16),
" $sdst, $simm16"
>;
multiclass SOPK_IMM32 <sopk op, string opName, dag outs, dag ins,
string argAsm, string asm = opName#argAsm> {
def "" : SOPK_Pseudo <opName, outs, ins, []>;
def _si : SOPK <outs, ins, asm, []>,
SOPK64e <op.SI>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
let isCodeGenOnly = 0;
}
def _vi : SOPK <outs, ins, asm, []>,
SOPK64e <op.VI>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
let isCodeGenOnly = 0;
}
}
//===----------------------------------------------------------------------===//
// SMRD classes
//===----------------------------------------------------------------------===//
class SMRD_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
SMRD <outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class SMRD_IMM_Real_si <bits<5> op, string opName, dag outs, dag ins,
string asm> :
SMRD <outs, ins, asm, []>,
SMRD_IMMe <op>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class SMRD_SOFF_Real_si <bits<5> op, string opName, dag outs, dag ins,
string asm> :
SMRD <outs, ins, asm, []>,
SMRD_SOFFe <op>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class SMRD_IMM_Real_vi <bits<8> op, string opName, dag outs, dag ins,
string asm, list<dag> pattern = []> :
SMRD <outs, ins, asm, pattern>,
SMEM_IMMe_vi <op>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
class SMRD_SOFF_Real_vi <bits<8> op, string opName, dag outs, dag ins,
string asm, list<dag> pattern = []> :
SMRD <outs, ins, asm, pattern>,
SMEM_SOFFe_vi <op>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass SMRD_IMM_m <smrd op, string opName, dag outs, dag ins,
string asm, list<dag> pattern> {
def "" : SMRD_Pseudo <opName, outs, ins, pattern>;
def _si : SMRD_IMM_Real_si <op.SI, opName, outs, ins, asm>;
// glc is only applicable to scalar stores, which are not yet
// implemented.
let glc = 0 in {
def _vi : SMRD_IMM_Real_vi <op.VI, opName, outs, ins, asm>;
}
}
multiclass SMRD_SOFF_m <smrd op, string opName, dag outs, dag ins,
string asm, list<dag> pattern> {
def "" : SMRD_Pseudo <opName, outs, ins, pattern>;
def _si : SMRD_SOFF_Real_si <op.SI, opName, outs, ins, asm>;
// glc is only applicable to scalar stores, which are not yet
// implemented.
let glc = 0 in {
def _vi : SMRD_SOFF_Real_vi <op.VI, opName, outs, ins, asm>;
}
}
multiclass SMRD_Special <smrd op, string opName, dag outs,
int sdst_ = ?,
string opStr = "",
list<dag> pattern = []> {
let hasSideEffects = 1 in {
def "" : SMRD_Pseudo <opName, outs, (ins), pattern>;
let sbase = 0, soff = 0, sdst = sdst_ in {
def _si : SMRD_SOFF_Real_si <op.SI, opName, outs, (ins), opName#opStr>;
let glc = 0 in {
def _vi : SMRD_SOFF_Real_vi <op.VI, opName, outs, (ins), opName#opStr>;
}
}
}
}
multiclass SMRD_Inval <smrd op, string opName,
SDPatternOperator node> {
let mayStore = 1 in {
defm : SMRD_Special<op, opName, (outs), 0, "", [(node)]>;
}
}
class SMEM_Inval <bits<8> op, string opName, SDPatternOperator node> :
SMRD_SOFF_Real_vi<op, opName, (outs), (ins), opName, [(node)]> {
let hasSideEffects = 1;
let mayStore = 1;
let sbase = 0;
let sdst = 0;
let glc = 0;
let soff = 0;
}
class SMEM_Ret <bits<8> op, string opName, SDPatternOperator node> :
SMRD_SOFF_Real_vi<op, opName, (outs SReg_64:$sdst), (ins),
opName#" $sdst", [(set i64:$sdst, (node))]> {
let hasSideEffects = 1;
let mayStore = ?;
let mayLoad = ?;
let sbase = 0;
let glc = 0;
let soff = 0;
}
multiclass SMRD_Helper <smrd op, string opName, RegisterClass baseClass,
RegisterClass dstClass> {
defm _IMM : SMRD_IMM_m <
op, opName#"_IMM", (outs dstClass:$sdst),
(ins baseClass:$sbase, smrd_offset:$offset),
opName#" $sdst, $sbase, $offset", []
>;
def _IMM_ci : SMRD <
(outs dstClass:$sdst), (ins baseClass:$sbase, smrd_literal_offset:$offset),
opName#" $sdst, $sbase, $offset", []>, SMRD_IMMe_ci <op.SI> {
let AssemblerPredicates = [isCIOnly];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "CI";
}
defm _SGPR : SMRD_SOFF_m <
op, opName#"_SGPR", (outs dstClass:$sdst),
(ins baseClass:$sbase, SReg_32:$soff),
opName#" $sdst, $sbase, $soff", []
>;
}
//===----------------------------------------------------------------------===//
// Vector ALU classes
//===----------------------------------------------------------------------===//
class getNumSrcArgs<ValueType Src0, ValueType Src1, ValueType Src2> {
int ret =
!if (!eq(Src0.Value, untyped.Value), 0,
!if (!eq(Src1.Value, untyped.Value), 1, // VOP1
!if (!eq(Src2.Value, untyped.Value), 2, // VOP2
3))); // VOP3
}
// Returns the register class to use for the destination of VOP[123C]
// instructions for the given VT.
class getVALUDstForVT<ValueType VT> {
RegisterOperand ret = !if(!eq(VT.Size, 32), VOPDstOperand<VGPR_32>,
!if(!eq(VT.Size, 64), VOPDstOperand<VReg_64>,
!if(!eq(VT.Size, 16), VOPDstOperand<VGPR_32>,
VOPDstOperand<SReg_64>))); // else VT == i1
}
// Returns the register class to use for source 0 of VOP[12C]
// instructions for the given VT.
class getVOPSrc0ForVT<ValueType VT> {
RegisterOperand ret = !if(!eq(VT.Size, 64), VSrc_64, VSrc_32);
}
// Returns the vreg register class to use for source operand given VT
class getVregSrcForVT<ValueType VT> {
RegisterClass ret = !if(!eq(VT.Size, 64), VReg_64, VGPR_32);
}
// Returns the register class to use for sources of VOP3 instructions for the
// given VT.
class getVOP3SrcForVT<ValueType VT> {
RegisterOperand ret =
!if(!eq(VT.Size, 64),
VCSrc_64,
!if(!eq(VT.Value, i1.Value),
SCSrc_64,
VCSrc_32
)
);
}
// Returns 1 if the source arguments have modifiers, 0 if they do not.
// XXX - do f16 instructions?
class hasModifiers<ValueType SrcVT> {
bit ret =
!if(!eq(SrcVT.Value, f32.Value), 1,
!if(!eq(SrcVT.Value, f64.Value), 1,
0));
}
// Returns the input arguments for VOP[12C] instructions for the given SrcVT.
class getIns32 <RegisterOperand Src0RC, RegisterClass Src1RC, int NumSrcArgs> {
dag ret = !if(!eq(NumSrcArgs, 1), (ins Src0RC:$src0), // VOP1
!if(!eq(NumSrcArgs, 2), (ins Src0RC:$src0, Src1RC:$src1), // VOP2
(ins)));
}
// Returns the input arguments for VOP3 instructions for the given SrcVT.
class getIns64 <RegisterOperand Src0RC, RegisterOperand Src1RC,
RegisterOperand Src2RC, int NumSrcArgs,
bit HasModifiers> {
dag ret =
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
!if (!eq(NumSrcArgs, 0),
// VOP1 without input operands (V_NOP, V_CLREXCP)
(ins),
/* else */
!if (!eq(NumSrcArgs, 1),
!if (!eq(HasModifiers, 1),
// VOP1 with modifiers
(ins FPInputMods:$src0_modifiers, Src0RC:$src0,
clampmod:$clamp, omod:$omod)
/* else */,
// VOP1 without modifiers
(ins Src0RC:$src0)
/* endif */ ),
!if (!eq(NumSrcArgs, 2),
!if (!eq(HasModifiers, 1),
// VOP 2 with modifiers
(ins FPInputMods:$src0_modifiers, Src0RC:$src0,
FPInputMods:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp, omod:$omod)
/* else */,
// VOP2 without modifiers
(ins Src0RC:$src0, Src1RC:$src1)
/* endif */ )
/* NumSrcArgs == 3 */,
!if (!eq(HasModifiers, 1),
// VOP3 with modifiers
(ins FPInputMods:$src0_modifiers, Src0RC:$src0,
FPInputMods:$src1_modifiers, Src1RC:$src1,
FPInputMods:$src2_modifiers, Src2RC:$src2,
clampmod:$clamp, omod:$omod)
/* else */,
// VOP3 without modifiers
(ins Src0RC:$src0, Src1RC:$src1, Src2RC:$src2)
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
/* endif */ ))));
}
class getInsDPP <RegisterClass Src0RC, RegisterClass Src1RC, int NumSrcArgs,
bit HasModifiers> {
dag ret = !if (!eq(NumSrcArgs, 0),
// VOP1 without input operands (V_NOP)
(ins dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl),
!if (!eq(NumSrcArgs, 1),
!if (!eq(HasModifiers, 1),
// VOP1_DPP with modifiers
(ins FPInputMods:$src0_modifiers, Src0RC:$src0,
dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl)
/* else */,
// VOP1_DPP without modifiers
(ins Src0RC:$src0, dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl)
/* endif */)
/* NumSrcArgs == 2 */,
!if (!eq(HasModifiers, 1),
// VOP2_DPP with modifiers
(ins FPInputMods:$src0_modifiers, Src0RC:$src0,
FPInputMods:$src1_modifiers, Src1RC:$src1,
dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl)
/* else */,
// VOP2_DPP without modifiers
(ins Src0RC:$src0, Src1RC:$src1, dpp_ctrl:$dpp_ctrl,
row_mask:$row_mask, bank_mask:$bank_mask,
bound_ctrl:$bound_ctrl)
/* endif */)));
}
class getInsSDWA <RegisterClass Src0RC, RegisterClass Src1RC, int NumSrcArgs,
bit HasFloatModifiers, ValueType DstVT> {
dag ret = !if(!eq(NumSrcArgs, 0),
// VOP1 without input operands (V_NOP)
(ins),
!if(!eq(NumSrcArgs, 1),
!if(HasFloatModifiers,
// VOP1_SDWA with float modifiers
(ins FPInputMods:$src0_fmodifiers, Src0RC:$src0,
clampmod:$clamp, dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel)
/* else */,
// VOP1_SDWA with sext modifier
(ins IntInputMods:$src0_imodifiers, Src0RC:$src0,
clampmod:$clamp, dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel)
/* endif */)
/* NumSrcArgs == 2 */,
!if(HasFloatModifiers,
!if(!eq(DstVT.Size, 1),
// VOPC_SDWA with float modifiers
(ins FPInputMods:$src0_fmodifiers, Src0RC:$src0,
FPInputMods:$src1_fmodifiers, Src1RC:$src1,
clampmod:$clamp, src0_sel:$src0_sel, src1_sel:$src1_sel),
// VOP2_SDWA or VOPC_SDWA with float modifiers
(ins FPInputMods:$src0_fmodifiers, Src0RC:$src0,
FPInputMods:$src1_fmodifiers, Src1RC:$src1,
clampmod:$clamp, dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel)
),
/* else */
!if(!eq(DstVT.Size, 1),
// VOPC_SDWA with sext modifiers
(ins IntInputMods:$src0_imodifiers, Src0RC:$src0,
IntInputMods:$src1_imodifiers, Src1RC:$src1,
clampmod:$clamp, src0_sel:$src0_sel, src1_sel:$src1_sel),
// VOP2_SDWA or VOPC_SDWA with sext modifier
(ins IntInputMods:$src0_imodifiers, Src0RC:$src0,
IntInputMods:$src1_imodifiers, Src1RC:$src1,
clampmod:$clamp, dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel)
)
/* endif */)));
}
// Outs for DPP and SDWA
class getOutsExt <bit HasDst, ValueType DstVT, RegisterOperand DstRCDPP> {
dag ret = !if(HasDst,
!if(!eq(DstVT.Size, 1),
(outs), // no dst for VOPC, we use "vcc"-token as dst in SDWA VOPC instructions
(outs DstRCDPP:$vdst)),
(outs)); // V_NOP
}
// Returns the assembly string for the inputs and outputs of a VOP[12C]
// instruction. This does not add the _e32 suffix, so it can be reused
// by getAsm64.
class getAsm32 <bit HasDst, int NumSrcArgs, ValueType DstVT = i32> {
string dst = !if(!eq(DstVT.Size, 1), "$sdst", "$vdst"); // use $sdst for VOPC
string src0 = ", $src0";
string src1 = ", $src1";
string src2 = ", $src2";
string ret = !if(HasDst, dst, "") #
!if(!eq(NumSrcArgs, 1), src0, "") #
!if(!eq(NumSrcArgs, 2), src0#src1, "") #
!if(!eq(NumSrcArgs, 3), src0#src1#src2, "");
}
// Returns the assembly string for the inputs and outputs of a VOP3
// instruction.
class getAsm64 <bit HasDst, int NumSrcArgs, bit HasModifiers, ValueType DstVT = i32> {
string dst = !if(!eq(DstVT.Size, 1), "$sdst", "$vdst"); // use $sdst for VOPC
string src0 = !if(!eq(NumSrcArgs, 1), "$src0_modifiers", "$src0_modifiers,");
string src1 = !if(!eq(NumSrcArgs, 1), "",
!if(!eq(NumSrcArgs, 2), " $src1_modifiers",
" $src1_modifiers,"));
string src2 = !if(!eq(NumSrcArgs, 3), " $src2_modifiers", "");
string ret =
!if(!eq(HasModifiers, 0),
getAsm32<HasDst, NumSrcArgs, DstVT>.ret,
dst#", "#src0#src1#src2#"$clamp"#"$omod");
}
class getAsmDPP <bit HasDst, int NumSrcArgs, bit HasModifiers, ValueType DstVT = i32> {
string dst = !if(HasDst,
!if(!eq(DstVT.Size, 1),
"$sdst",
"$vdst"),
""); // use $sdst for VOPC
string src0 = !if(!eq(NumSrcArgs, 1), "$src0_modifiers", "$src0_modifiers,");
string src1 = !if(!eq(NumSrcArgs, 1), "",
!if(!eq(NumSrcArgs, 2), " $src1_modifiers",
" $src1_modifiers,"));
string args = !if(!eq(HasModifiers, 0),
getAsm32<0, NumSrcArgs, DstVT>.ret,
", "#src0#src1);
string ret = dst#args#" $dpp_ctrl$row_mask$bank_mask$bound_ctrl";
}
class getAsmSDWA <bit HasDst, int NumSrcArgs, bit HasFloatModifiers,
ValueType DstVT = i32> {
string dst = !if(HasDst,
!if(!eq(DstVT.Size, 1),
" vcc", // use vcc token as dst for VOPC instructioins
"$vdst"),
"");
string src0 = !if(HasFloatModifiers, "$src0_fmodifiers", "$src0_imodifiers");
string src1 = !if(HasFloatModifiers, "$src1_fmodifiers", "$src1_imodifiers");
string args = !if(!eq(NumSrcArgs, 0),
"",
!if(!eq(NumSrcArgs, 1),
", "#src0#"$clamp",
", "#src0#", "#src1#"$clamp"
)
);
string sdwa = !if(!eq(NumSrcArgs, 0),
"",
!if(!eq(NumSrcArgs, 1),
" $dst_sel $dst_unused $src0_sel",
!if(!eq(DstVT.Size, 1),
" $src0_sel $src1_sel", // No dst_sel and dst_unused for VOPC
" $dst_sel $dst_unused $src0_sel $src1_sel"
)
)
);
string ret = dst#args#sdwa;
}
// Function that checks if instruction supports DPP and SDWA
class getHasExt <int NumSrcArgs, ValueType DstVT = i32, ValueType Src0VT = i32,
ValueType Src1VT = i32> {
bit ret = !if(!eq(NumSrcArgs, 3),
0, // NumSrcArgs == 3 - No DPP or SDWA for VOP3
!if(!eq(DstVT.Size, 64),
0, // 64-bit dst - No DPP or SDWA for 64-bit operands
!if(!eq(Src0VT.Size, 64),
0, // 64-bit src0
!if(!eq(Src0VT.Size, 64),
0, // 64-bit src2
1
)
)
)
);
}
class VOPProfile <list<ValueType> _ArgVT> {
field list<ValueType> ArgVT = _ArgVT;
field ValueType DstVT = ArgVT[0];
field ValueType Src0VT = ArgVT[1];
field ValueType Src1VT = ArgVT[2];
field ValueType Src2VT = ArgVT[3];
field RegisterOperand DstRC = getVALUDstForVT<DstVT>.ret;
field RegisterOperand DstRCDPP = getVALUDstForVT<DstVT>.ret;
field RegisterOperand DstRCSDWA = getVALUDstForVT<DstVT>.ret;
field RegisterOperand Src0RC32 = getVOPSrc0ForVT<Src0VT>.ret;
field RegisterClass Src1RC32 = getVregSrcForVT<Src1VT>.ret;
field RegisterOperand Src0RC64 = getVOP3SrcForVT<Src0VT>.ret;
field RegisterOperand Src1RC64 = getVOP3SrcForVT<Src1VT>.ret;
field RegisterOperand Src2RC64 = getVOP3SrcForVT<Src2VT>.ret;
field RegisterClass Src0DPP = getVregSrcForVT<Src0VT>.ret;
field RegisterClass Src1DPP = getVregSrcForVT<Src1VT>.ret;
field RegisterClass Src0SDWA = getVregSrcForVT<Src0VT>.ret;
field RegisterClass Src1SDWA = getVregSrcForVT<Src1VT>.ret;
field bit HasDst = !if(!eq(DstVT.Value, untyped.Value), 0, 1);
field bit HasDst32 = HasDst;
field int NumSrcArgs = getNumSrcArgs<Src0VT, Src1VT, Src2VT>.ret;
field bit HasModifiers = hasModifiers<Src0VT>.ret;
field bit HasExt = getHasExt<NumSrcArgs, DstVT, Src0VT, Src1VT>.ret;
field dag Outs = !if(HasDst,(outs DstRC:$vdst),(outs));
// VOP3b instructions are a special case with a second explicit
// output. This is manually overridden for them.
field dag Outs32 = Outs;
field dag Outs64 = Outs;
field dag OutsDPP = getOutsExt<HasDst, DstVT, DstRCDPP>.ret;
field dag OutsSDWA = getOutsExt<HasDst, DstVT, DstRCDPP>.ret;
field dag Ins32 = getIns32<Src0RC32, Src1RC32, NumSrcArgs>.ret;
field dag Ins64 = getIns64<Src0RC64, Src1RC64, Src2RC64, NumSrcArgs,
HasModifiers>.ret;
field dag InsDPP = getInsDPP<Src0DPP, Src1DPP, NumSrcArgs, HasModifiers>.ret;
field dag InsSDWA = getInsSDWA<Src0SDWA, Src1SDWA, NumSrcArgs, HasModifiers, DstVT>.ret;
field string Asm32 = getAsm32<HasDst, NumSrcArgs, DstVT>.ret;
field string Asm64 = getAsm64<HasDst, NumSrcArgs, HasModifiers, DstVT>.ret;
field string AsmDPP = getAsmDPP<HasDst, NumSrcArgs, HasModifiers, DstVT>.ret;
field string AsmSDWA = getAsmSDWA<HasDst, NumSrcArgs, HasModifiers, DstVT>.ret;
}
class VOP_NO_EXT <VOPProfile p> : VOPProfile <p.ArgVT> {
let HasExt = 0;
}
// FIXME: I think these F16/I16 profiles will need to use f16/i16 types in order
// for the instruction patterns to work.
def VOP_F16_F16 : VOPProfile <[f16, f16, untyped, untyped]>;
def VOP_F16_I16 : VOPProfile <[f16, i32, untyped, untyped]>;
def VOP_I16_F16 : VOPProfile <[i32, f16, untyped, untyped]>;
def VOP_F16_F16_F16 : VOPProfile <[f16, f16, f16, untyped]>;
def VOP_F16_F16_I16 : VOPProfile <[f16, f16, i32, untyped]>;
def VOP_I16_I16_I16 : VOPProfile <[i32, i32, i32, untyped]>;
def VOP_I16_I16_I16_I16 : VOPProfile <[i32, i32, i32, i32, untyped]>;
def VOP_F16_F16_F16_F16 : VOPProfile <[f16, f16, f16, f16, untyped]>;
def VOP_NONE : VOPProfile <[untyped, untyped, untyped, untyped]>;
def VOP_F32_F32 : VOPProfile <[f32, f32, untyped, untyped]>;
def VOP_F32_F64 : VOPProfile <[f32, f64, untyped, untyped]>;
def VOP_F32_I32 : VOPProfile <[f32, i32, untyped, untyped]>;
def VOP_F64_F32 : VOPProfile <[f64, f32, untyped, untyped]>;
def VOP_F64_F64 : VOPProfile <[f64, f64, untyped, untyped]>;
def VOP_F64_I32 : VOPProfile <[f64, i32, untyped, untyped]>;
def VOP_I32_F32 : VOPProfile <[i32, f32, untyped, untyped]>;
def VOP_I32_F64 : VOPProfile <[i32, f64, untyped, untyped]>;
def VOP_I32_I32 : VOPProfile <[i32, i32, untyped, untyped]>;
def VOP_F32_F32_F32 : VOPProfile <[f32, f32, f32, untyped]>;
def VOP_F32_F32_I32 : VOPProfile <[f32, f32, i32, untyped]>;
def VOP_F64_F64_F64 : VOPProfile <[f64, f64, f64, untyped]>;
def VOP_F64_F64_I32 : VOPProfile <[f64, f64, i32, untyped]>;
def VOP_I32_F32_F32 : VOPProfile <[i32, f32, f32, untyped]>;
def VOP_I32_F32_I32 : VOPProfile <[i32, f32, i32, untyped]>;
def VOP_I32_I32_I32 : VOPProfile <[i32, i32, i32, untyped]>;
// Write out to vcc or arbitrary SGPR.
def VOP2b_I32_I1_I32_I32 : VOPProfile<[i32, i32, i32, untyped]> {
let Asm32 = "$vdst, vcc, $src0, $src1";
let Asm64 = "$vdst, $sdst, $src0, $src1";
let Outs32 = (outs DstRC:$vdst);
let Outs64 = (outs DstRC:$vdst, SReg_64:$sdst);
}
// Write out to vcc or arbitrary SGPR and read in from vcc or
// arbitrary SGPR.
def VOP2b_I32_I1_I32_I32_I1 : VOPProfile<[i32, i32, i32, i1]> {
// We use VCSrc_32 to exclude literal constants, even though the
// encoding normally allows them since the implicit VCC use means
// using one would always violate the constant bus
// restriction. SGPRs are still allowed because it should
// technically be possible to use VCC again as src0.
let Src0RC32 = VCSrc_32;
let Asm32 = "$vdst, vcc, $src0, $src1, vcc";
let Asm64 = "$vdst, $sdst, $src0, $src1, $src2";
let Outs32 = (outs DstRC:$vdst);
let Outs64 = (outs DstRC:$vdst, SReg_64:$sdst);
// Suppress src2 implied by type since the 32-bit encoding uses an
// implicit VCC use.
let Ins32 = (ins Src0RC32:$src0, Src1RC32:$src1);
}
// Read in from vcc or arbitrary SGPR
def VOP2e_I32_I32_I32_I1 : VOPProfile<[i32, i32, i32, i1]> {
let Src0RC32 = VCSrc_32; // See comment in def VOP2b_I32_I1_I32_I32_I1 above.
let Asm32 = "$vdst, $src0, $src1, vcc";
let Asm64 = "$vdst, $src0, $src1, $src2";
let Outs32 = (outs DstRC:$vdst);
let Outs64 = (outs DstRC:$vdst);
// Suppress src2 implied by type since the 32-bit encoding uses an
// implicit VCC use.
let Ins32 = (ins Src0RC32:$src0, Src1RC32:$src1);
}
class VOP3b_Profile<ValueType vt> : VOPProfile<[vt, vt, vt, vt]> {
let Outs64 = (outs DstRC:$vdst, SReg_64:$sdst);
let Asm64 = "$vdst, $sdst, $src0_modifiers, $src1_modifiers, $src2_modifiers"#"$clamp"#"$omod";
}
def VOP3b_F32_I1_F32_F32_F32 : VOP3b_Profile<f32> {
// FIXME: Hack to stop printing _e64
let DstRC = RegisterOperand<VGPR_32>;
}
def VOP3b_F64_I1_F64_F64_F64 : VOP3b_Profile<f64> {
// FIXME: Hack to stop printing _e64
let DstRC = RegisterOperand<VReg_64>;
}
// VOPC instructions are a special case because for the 32-bit
// encoding, we want to display the implicit vcc write as if it were
// an explicit $dst.
class VOPC_Profile<ValueType vt0, ValueType vt1 = vt0> : VOPProfile <[i1, vt0, vt1, untyped]> {
let Asm32 = "vcc, $src0, $src1";
// The destination for 32-bit encoding is implicit.
let HasDst32 = 0;
let Outs64 = (outs DstRC:$sdst);
}
class VOPC_Class_Profile<ValueType vt> : VOPC_Profile<vt, i32> {
let Ins64 = (ins FPInputMods:$src0_modifiers, Src0RC64:$src0, Src1RC64:$src1);
let Asm64 = "$sdst, $src0_modifiers, $src1";
let InsSDWA = (ins FPInputMods:$src0_fmodifiers, Src0RC64:$src0,
IntInputMods:$src1_imodifiers, Src1RC64:$src1,
clampmod:$clamp, src0_sel:$src0_sel, src1_sel:$src1_sel);
let AsmSDWA = " vcc, $src0_fmodifiers, $src1_imodifiers$clamp $src0_sel $src1_sel";
}
def VOPC_I1_F32_F32 : VOPC_Profile<f32>;
def VOPC_I1_F64_F64 : VOPC_Profile<f64>;
def VOPC_I1_I32_I32 : VOPC_Profile<i32>;
def VOPC_I1_I64_I64 : VOPC_Profile<i64>;
def VOPC_I1_F32_I32 : VOPC_Class_Profile<f32>;
def VOPC_I1_F64_I32 : VOPC_Class_Profile<f64>;
def VOP_I64_I64_I32 : VOPProfile <[i64, i64, i32, untyped]>;
def VOP_I64_I32_I64 : VOPProfile <[i64, i32, i64, untyped]>;
def VOP_I64_I64_I64 : VOPProfile <[i64, i64, i64, untyped]>;
def VOP_F32_F32_F32_F32 : VOPProfile <[f32, f32, f32, f32]>;
def VOP_MADAK : VOPProfile <[f32, f32, f32, f32]> {
field dag Ins32 = (ins VCSrc_32:$src0, VGPR_32:$src1, u32kimm:$imm);
field string Asm32 = "$vdst, $src0, $src1, $imm";
field bit HasExt = 0;
}
def VOP_MADMK : VOPProfile <[f32, f32, f32, f32]> {
field dag Ins32 = (ins VCSrc_32:$src0, u32kimm:$imm, VGPR_32:$src1);
field string Asm32 = "$vdst, $src0, $imm, $src1";
field bit HasExt = 0;
}
def VOP_MAC : VOPProfile <[f32, f32, f32, f32]> {
let Ins32 = (ins Src0RC32:$src0, Src1RC32:$src1, VGPR_32:$src2);
let Ins64 = getIns64<Src0RC64, Src1RC64, RegisterOperand<VGPR_32>, 3,
HasModifiers>.ret;
let InsDPP = (ins FPInputMods:$src0_modifiers, Src0RC32:$src0,
FPInputMods:$src1_modifiers, Src1RC32:$src1,
VGPR_32:$src2, // stub argument
dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
bank_mask:$bank_mask, bound_ctrl:$bound_ctrl);
let InsSDWA = (ins FPInputMods:$src0_fmodifiers, Src0RC32:$src0,
FPInputMods:$src1_fmodifiers, Src1RC32:$src1,
VGPR_32:$src2, // stub argument
clampmod:$clamp, dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel);
let Asm32 = getAsm32<1, 2, f32>.ret;
let Asm64 = getAsm64<1, 2, HasModifiers, f32>.ret;
let AsmDPP = getAsmDPP<1, 2, HasModifiers, f32>.ret;
let AsmSDWA = getAsmSDWA<1, 2, HasModifiers, f32>.ret;
}
def VOP_F64_F64_F64_F64 : VOPProfile <[f64, f64, f64, f64]>;
def VOP_I32_I32_I32_I32 : VOPProfile <[i32, i32, i32, i32]>;
def VOP_I64_I32_I32_I64 : VOPProfile <[i64, i32, i32, i64]>;
// This class is used only with VOPC instructions. Use $sdst for out operand
class SIInstAlias <string asm, Instruction inst, VOPProfile p> :
InstAlias <asm, (inst)>, PredicateControl {
field bit isCompare;
field bit isCommutable;
let ResultInst =
!if (p.HasDst32,
!if (!eq(p.NumSrcArgs, 0),
// 1 dst, 0 src
(inst p.DstRC:$sdst),
!if (!eq(p.NumSrcArgs, 1),
// 1 dst, 1 src
(inst p.DstRC:$sdst, p.Src0RC32:$src0),
!if (!eq(p.NumSrcArgs, 2),
// 1 dst, 2 src
(inst p.DstRC:$sdst, p.Src0RC32:$src0, p.Src1RC32:$src1),
// else - unreachable
(inst)))),
// else
!if (!eq(p.NumSrcArgs, 2),
// 0 dst, 2 src
(inst p.Src0RC32:$src0, p.Src1RC32:$src1),
!if (!eq(p.NumSrcArgs, 1),
// 0 dst, 1 src
(inst p.Src0RC32:$src1),
// else
// 0 dst, 0 src
(inst))));
}
class SIInstAliasSI <string asm, string op_name, VOPProfile p> :
SIInstAlias <asm, !cast<Instruction>(op_name#"_e32_si"), p> {
let AssemblerPredicate = SIAssemblerPredicate;
}
class SIInstAliasVI <string asm, string op_name, VOPProfile p> :
SIInstAlias <asm, !cast<Instruction>(op_name#"_e32_vi"), p> {
let AssemblerPredicates = [isVI];
}
multiclass SIInstAliasBuilder <string asm, VOPProfile p> {
def : SIInstAliasSI <asm, NAME, p>;
def : SIInstAliasVI <asm, NAME, p>;
}
class VOP <string opName> {
string OpName = opName;
}
class VOP2_REV <string revOp, bit isOrig> {
string RevOp = revOp;
bit IsOrig = isOrig;
}
class AtomicNoRet <string noRetOp, bit isRet> {
string NoRetOp = noRetOp;
bit IsRet = isRet;
}
class VOP1_Pseudo <dag outs, dag ins, list<dag> pattern, string opName> :
VOP1Common <outs, ins, "", pattern>,
VOP <opName>,
SIMCInstr <opName#"_e32", SIEncodingFamily.NONE>,
MnemonicAlias<opName#"_e32", opName> {
let isPseudo = 1;
let isCodeGenOnly = 1;
field bits<8> vdst;
field bits<9> src0;
}
class VOP1_Real_si <string opName, vop1 op, dag outs, dag ins, string asm> :
VOP1<op.SI, outs, ins, asm, []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.SI> {
let AssemblerPredicate = SIAssemblerPredicate;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class VOP1_Real_vi <string opName, vop1 op, dag outs, dag ins, string asm> :
VOP1<op.VI, outs, ins, asm, []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass VOP1_m <vop1 op, string opName, VOPProfile p, list<dag> pattern,
string asm = opName#p.Asm32> {
def "" : VOP1_Pseudo <p.Outs, p.Ins32, pattern, opName>;
def _si : VOP1_Real_si <opName, op, p.Outs, p.Ins32, asm>;
def _vi : VOP1_Real_vi <opName, op, p.Outs, p.Ins32, asm>;
}
class VOP1_DPP <vop1 op, string opName, VOPProfile p> :
VOP1_DPPe <op.VI>,
VOP_DPP <p.OutsDPP, p.InsDPP, opName#p.AsmDPP, [], p.HasModifiers> {
let AssemblerPredicates = !if(p.HasExt, [isVI], [DisableInst]);
let DecoderNamespace = "DPP";
let DisableDecoder = DisableVIDecoder;
let src0_modifiers = !if(p.HasModifiers, ?, 0);
let src1_modifiers = 0;
}
class SDWADisableFields <VOPProfile p> {
bits<8> src0 = !if(!eq(p.NumSrcArgs, 0), 0, ?);
bits<3> src0_sel = !if(!eq(p.NumSrcArgs, 0), 6, ?);
bits<2> src0_fmodifiers = !if(!eq(p.NumSrcArgs, 0),
0,
!if(p.HasModifiers, ?, 0));
bits<1> src0_imodifiers = !if(!eq(p.NumSrcArgs, 0),
0,
!if(p.HasModifiers, 0, ?));
bits<3> src1_sel = !if(!eq(p.NumSrcArgs, 0), 6,
!if(!eq(p.NumSrcArgs, 1), 6,
?));
bits<2> src1_fmodifiers = !if(!eq(p.NumSrcArgs, 0), 0,
!if(!eq(p.NumSrcArgs, 1), 0,
!if(p.HasModifiers, ?, 0)));
bits<1> src1_imodifiers = !if(!eq(p.NumSrcArgs, 0), 0,
!if(!eq(p.NumSrcArgs, 1), 0,
!if(p.HasModifiers, 0, ?)));
bits<3> dst_sel = !if(p.HasDst, ?, 6);
bits<2> dst_unused = !if(p.HasDst, ?, 2);
bits<1> clamp = !if(!eq(p.NumSrcArgs, 0), 0, ?);
}
class VOP1_SDWA <vop1 op, string opName, VOPProfile p> :
VOP1_SDWAe <op.VI>,
VOP_SDWA <p.OutsSDWA, p.InsSDWA, opName#p.AsmSDWA, [], p.HasModifiers>,
SDWADisableFields <p> {
let AsmMatchConverter = "cvtSdwaVOP1";
let AssemblerPredicates = !if(p.HasExt, [isVI], [DisableInst]);
let DecoderNamespace = "SDWA";
let DisableDecoder = DisableVIDecoder;
}
multiclass VOP1SI_m <vop1 op, string opName, VOPProfile p, list<dag> pattern,
string asm = opName#p.Asm32> {
def "" : VOP1_Pseudo <p.Outs, p.Ins32, pattern, opName>;
def _si : VOP1_Real_si <opName, op, p.Outs, p.Ins32, asm>;
}
class VOP2_Pseudo <dag outs, dag ins, list<dag> pattern, string opName> :
VOP2Common <outs, ins, "", pattern>,
VOP <opName>,
SIMCInstr<opName#"_e32", SIEncodingFamily.NONE>,
MnemonicAlias<opName#"_e32", opName> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class VOP2_Real_si <string opName, vop2 op, dag outs, dag ins, string asm> :
VOP2 <op.SI, outs, ins, opName#asm, []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class VOP2_Real_vi <string opName, vop2 op, dag outs, dag ins, string asm> :
VOP2 <op.VI, outs, ins, opName#asm, []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass VOP2SI_m <vop2 op, string opName, VOPProfile p, list<dag> pattern,
string revOp> {
def "" : VOP2_Pseudo <p.Outs32, p.Ins32, pattern, opName>,
VOP2_REV<revOp#"_e32", !eq(revOp, opName)>;
def _si : VOP2_Real_si <opName, op, p.Outs32, p.Ins32, p.Asm32>;
}
multiclass VOP2_m <vop2 op, string opName, VOPProfile p, list <dag> pattern,
string revOp> {
def "" : VOP2_Pseudo <p.Outs32, p.Ins32, pattern, opName>,
VOP2_REV<revOp#"_e32", !eq(revOp, opName)>;
def _si : VOP2_Real_si <opName, op, p.Outs32, p.Ins32, p.Asm32>;
def _vi : VOP2_Real_vi <opName, op, p.Outs32, p.Ins32, p.Asm32>;
}
class VOP2_DPP <vop2 op, string opName, VOPProfile p> :
VOP2_DPPe <op.VI>,
VOP_DPP <p.OutsDPP, p.InsDPP, opName#p.AsmDPP, [], p.HasModifiers> {
let AssemblerPredicates = !if(p.HasExt, [isVI], [DisableInst]);
let DecoderNamespace = "DPP";
let DisableDecoder = DisableVIDecoder;
let src0_modifiers = !if(p.HasModifiers, ?, 0);
let src1_modifiers = !if(p.HasModifiers, ?, 0);
}
class VOP2_SDWA <vop2 op, string opName, VOPProfile p> :
VOP2_SDWAe <op.VI>,
VOP_SDWA <p.OutsSDWA, p.InsSDWA, opName#p.AsmSDWA, [], p.HasModifiers>,
SDWADisableFields <p> {
let AsmMatchConverter = "cvtSdwaVOP2";
let AssemblerPredicates = !if(p.HasExt, [isVI], [DisableInst]);
let DecoderNamespace = "SDWA";
let DisableDecoder = DisableVIDecoder;
}
class VOP3DisableFields <bit HasSrc1, bit HasSrc2, bit HasModifiers> {
bits<2> src0_modifiers = !if(HasModifiers, ?, 0);
bits<2> src1_modifiers = !if(HasModifiers, !if(HasSrc1, ?, 0), 0);
bits<2> src2_modifiers = !if(HasModifiers, !if(HasSrc2, ?, 0), 0);
bits<2> omod = !if(HasModifiers, ?, 0);
bits<1> clamp = !if(HasModifiers, ?, 0);
bits<9> src1 = !if(HasSrc1, ?, 0);
bits<9> src2 = !if(HasSrc2, ?, 0);
}
class VOP3DisableModFields <bit HasSrc0Mods,
bit HasSrc1Mods = 0,
bit HasSrc2Mods = 0,
bit HasOutputMods = 0> {
bits<2> src0_modifiers = !if(HasSrc0Mods, ?, 0);
bits<2> src1_modifiers = !if(HasSrc1Mods, ?, 0);
bits<2> src2_modifiers = !if(HasSrc2Mods, ?, 0);
bits<2> omod = !if(HasOutputMods, ?, 0);
bits<1> clamp = !if(HasOutputMods, ?, 0);
}
class VOP3_Pseudo <dag outs, dag ins, list<dag> pattern, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, "", pattern, HasMods, VOP3Only>,
VOP <opName>,
SIMCInstr<opName#"_e64", SIEncodingFamily.NONE>,
MnemonicAlias<opName#"_e64", opName> {
let isPseudo = 1;
let isCodeGenOnly = 1;
field bit vdst;
field bit src0;
}
class VOP3_Real_si <bits<9> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3e <op>,
SIMCInstr<opName#"_e64", SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class VOP3_Real_vi <bits<10> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3e_vi <op>,
SIMCInstr <opName#"_e64", SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
class VOP3_C_Real_si <bits<9> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3ce <op>,
SIMCInstr<opName#"_e64", SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class VOP3_C_Real_vi <bits<10> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3ce_vi <op>,
SIMCInstr <opName#"_e64", SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
class VOP3b_Real_si <bits<9> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3be <op>,
SIMCInstr<opName#"_e64", SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class VOP3b_Real_vi <bits<10> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3be_vi <op>,
SIMCInstr <opName#"_e64", SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
class VOP3e_Real_si <bits<9> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3e <op>,
SIMCInstr<opName#"_e64", SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class VOP3e_Real_vi <bits<10> op, dag outs, dag ins, string asm, string opName,
bit HasMods = 0, bit VOP3Only = 0> :
VOP3Common <outs, ins, asm, [], HasMods, VOP3Only>,
VOP3e_vi <op>,
SIMCInstr <opName#"_e64", SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass VOP3_m <vop op, dag outs, dag ins, string asm, list<dag> pattern,
string opName, int NumSrcArgs, bit HasMods = 1, bit VOP3Only = 0> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName>;
def _si : VOP3_Real_si <op.SI3, outs, ins, asm, opName, HasMods, VOP3Only>,
VOP3DisableFields<!if(!eq(NumSrcArgs, 1), 0, 1),
!if(!eq(NumSrcArgs, 2), 0, 1),
HasMods>;
def _vi : VOP3_Real_vi <op.VI3, outs, ins, asm, opName, HasMods, VOP3Only>,
VOP3DisableFields<!if(!eq(NumSrcArgs, 1), 0, 1),
!if(!eq(NumSrcArgs, 2), 0, 1),
HasMods>;
}
multiclass VOP3_1_m <vop op, dag outs, dag ins, string asm,
list<dag> pattern, string opName, bit HasMods = 1> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName, HasMods>;
def _si : VOP3_Real_si <op.SI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<0, 0, HasMods>;
def _vi : VOP3_Real_vi <op.VI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<0, 0, HasMods>;
}
multiclass VOP3SI_1_m <vop op, dag outs, dag ins, string asm,
list<dag> pattern, string opName, bit HasMods = 1> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName, HasMods>;
def _si : VOP3_Real_si <op.SI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<0, 0, HasMods>;
// No VI instruction. This class is for SI only.
}
multiclass VOP3_2_m <vop op, dag outs, dag ins, string asm,
list<dag> pattern, string opName, string revOp,
bit HasMods = 1> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName, HasMods>,
VOP2_REV<revOp#"_e64", !eq(revOp, opName)>;
def _si : VOP3_Real_si <op.SI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<1, 0, HasMods>;
def _vi : VOP3_Real_vi <op.VI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<1, 0, HasMods>;
}
multiclass VOP3SI_2_m <vop op, dag outs, dag ins, string asm,
list<dag> pattern, string opName, string revOp,
bit HasMods = 1> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName, HasMods>,
VOP2_REV<revOp#"_e64", !eq(revOp, opName)>;
def _si : VOP3_Real_si <op.SI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<1, 0, HasMods>;
// No VI instruction. This class is for SI only.
}
// Two operand VOP3b instruction that may have a 3rd SGPR bool operand
// instead of an implicit VCC as in the VOP2b format.
multiclass VOP3b_2_3_m <vop op, dag outs, dag ins, string asm,
list<dag> pattern, string opName, string revOp,
bit HasMods = 1, bit useSrc2Input = 0, bit VOP3Only = 0> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName, HasMods, VOP3Only>;
def _si : VOP3b_Real_si <op.SI3, outs, ins, asm, opName, HasMods, VOP3Only>,
VOP3DisableFields<1, useSrc2Input, HasMods>;
def _vi : VOP3b_Real_vi <op.VI3, outs, ins, asm, opName, HasMods, VOP3Only>,
VOP3DisableFields<1, useSrc2Input, HasMods>;
}
// Same as VOP3b_2_3_m but no 2nd destination (sdst), e.g. v_cndmask_b32.
multiclass VOP3e_2_3_m <vop op, dag outs, dag ins, string asm,
list<dag> pattern, string opName, string revOp,
bit HasMods = 1, bit useSrc2Input = 0, bit VOP3Only = 0> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName, HasMods, VOP3Only>;
def _si : VOP3e_Real_si <op.SI3, outs, ins, asm, opName, HasMods, VOP3Only>,
VOP3DisableFields<1, useSrc2Input, HasMods>;
def _vi : VOP3e_Real_vi <op.VI3, outs, ins, asm, opName, HasMods, VOP3Only>,
VOP3DisableFields<1, useSrc2Input, HasMods>;
}
multiclass VOP3_C_m <vop op, dag outs, dag ins, string asm,
list<dag> pattern, string opName,
bit HasMods, bit defExec,
string revOp, list<SchedReadWrite> sched> {
def "" : VOP3_Pseudo <outs, ins, pattern, opName, HasMods>,
VOP2_REV<revOp#"_e64", !eq(revOp, opName)> {
let Defs = !if(defExec, [EXEC], []);
let SchedRW = sched;
}
def _si : VOP3_C_Real_si <op.SI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<1, 0, HasMods> {
let Defs = !if(defExec, [EXEC], []);
let SchedRW = sched;
}
def _vi : VOP3_C_Real_vi <op.VI3, outs, ins, asm, opName, HasMods>,
VOP3DisableFields<1, 0, HasMods> {
let Defs = !if(defExec, [EXEC], []);
let SchedRW = sched;
}
}
// An instruction that is VOP2 on SI and VOP3 on VI, no modifiers.
multiclass VOP2SI_3VI_m <vop3 op, string opName, dag outs, dag ins,
string asm, list<dag> pattern = []> {
let isPseudo = 1, isCodeGenOnly = 1 in {
def "" : VOPAnyCommon <outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE>;
}
def _si : VOP2 <op.SI3{5-0}, outs, ins, asm, []>,
SIMCInstr <opName, SIEncodingFamily.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
def _vi : VOP3Common <outs, ins, asm, []>,
VOP3e_vi <op.VI3>,
VOP3DisableFields <1, 0, 0>,
SIMCInstr <opName, SIEncodingFamily.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
}
multiclass VOP1_Helper <vop1 op, string opName, VOPProfile p, list<dag> pat32,
list<dag> pat64> {
defm _e32 : VOP1_m <op, opName, p, pat32>;
defm _e64 : VOP3_1_m <op, p.Outs, p.Ins64, opName#p.Asm64, pat64, opName,
p.HasModifiers>;
def _dpp : VOP1_DPP <op, opName, p>;
def _sdwa : VOP1_SDWA <op, opName, p>;
}
multiclass VOP1Inst <vop1 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag> : VOP1_Helper <
op, opName, P, [],
!if(P.HasModifiers,
[(set P.DstVT:$vdst, (node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0,
i32:$src0_modifiers, i1:$clamp, i32:$omod))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0))])
>;
multiclass VOP1InstSI <vop1 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag> {
defm _e32 : VOP1SI_m <op, opName, P, []>;
defm _e64 : VOP3SI_1_m <op, P.Outs, P.Ins64, opName#P.Asm64,
!if(P.HasModifiers,
[(set P.DstVT:$vdst, (node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0,
i32:$src0_modifiers, i1:$clamp, i32:$omod))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0))]),
opName, P.HasModifiers>;
}
multiclass VOP2_Helper <vop2 op, string opName, VOPProfile p, list<dag> pat32,
list<dag> pat64, string revOp> {
defm _e32 : VOP2_m <op, opName, p, pat32, revOp>;
defm _e64 : VOP3_2_m <op, p.Outs, p.Ins64, opName#p.Asm64, pat64, opName,
revOp, p.HasModifiers>;
def _dpp : VOP2_DPP <op, opName, p>;
def _sdwa : VOP2_SDWA <op, opName, p>;
}
multiclass VOP2Inst <vop2 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName> : VOP2_Helper <
op, opName, P, [],
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))]),
revOp
>;
multiclass VOP2InstSI <vop2 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName> {
defm _e32 : VOP2SI_m <op, opName, P, [], revOp>;
defm _e64 : VOP3SI_2_m <op, P.Outs, P.Ins64, opName#P.Asm64,
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))]),
opName, revOp, P.HasModifiers>;
}
multiclass VOP2e_Helper <vop2 op, string opName, VOPProfile p,
list<dag> pat32, list<dag> pat64,
string revOp, bit useSGPRInput> {
let SchedRW = [Write32Bit] in {
let Uses = !if(useSGPRInput, [VCC, EXEC], [EXEC]) in {
defm _e32 : VOP2_m <op, opName, p, pat32, revOp>;
}
defm _e64 : VOP3e_2_3_m <op, p.Outs64, p.Ins64, opName#p.Asm64, pat64,
opName, revOp, p.HasModifiers, useSGPRInput>;
}
}
multiclass VOP2eInst <vop2 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName> : VOP2e_Helper <
op, opName, P, [],
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))]),
revOp, !eq(P.NumSrcArgs, 3)
>;
multiclass VOP2b_Helper <vop2 op, string opName, VOPProfile p,
list<dag> pat32, list<dag> pat64,
string revOp, bit useSGPRInput> {
let SchedRW = [Write32Bit, WriteSALU] in {
let Uses = !if(useSGPRInput, [VCC, EXEC], [EXEC]), Defs = [VCC] in {
defm _e32 : VOP2_m <op, opName, p, pat32, revOp>;
}
defm _e64 : VOP3b_2_3_m <op, p.Outs64, p.Ins64, opName#p.Asm64, pat64,
opName, revOp, p.HasModifiers, useSGPRInput>;
}
}
multiclass VOP2bInst <vop2 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName> : VOP2b_Helper <
op, opName, P, [],
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))]),
revOp, !eq(P.NumSrcArgs, 3)
>;
// A VOP2 instruction that is VOP3-only on VI.
multiclass VOP2_VI3_Helper <vop23 op, string opName, VOPProfile p,
list<dag> pat32, list<dag> pat64, string revOp> {
defm _e32 : VOP2SI_m <op, opName, p, pat32, revOp>;
defm _e64 : VOP3_2_m <op, p.Outs, p.Ins64, opName#p.Asm64, pat64, opName,
revOp, p.HasModifiers>;
}
multiclass VOP2_VI3_Inst <vop23 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag,
string revOp = opName>
: VOP2_VI3_Helper <
op, opName, P, [],
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))]),
revOp
>;
multiclass VOP2MADK <vop2 op, string opName, VOPProfile P, list<dag> pattern = []> {
def "" : VOP2_Pseudo <P.Outs, P.Ins32, pattern, opName>;
let isCodeGenOnly = 0 in {
def _si : VOP2Common <P.Outs, P.Ins32,
!strconcat(opName, P.Asm32), []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.SI>,
VOP2_MADKe <op.SI> {
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
def _vi : VOP2Common <P.Outs, P.Ins32,
!strconcat(opName, P.Asm32), []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.VI>,
VOP2_MADKe <op.VI> {
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
} // End isCodeGenOnly = 0
}
class VOPC_Pseudo <dag ins, list<dag> pattern, string opName> :
VOPCCommon <ins, "", pattern>,
VOP <opName>,
SIMCInstr<opName#"_e32", SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class VOPC_SDWA <vopc op, string opName, bit DefExec, VOPProfile p> :
VOPC_SDWAe <op.VI>,
VOP_SDWA <p.OutsSDWA, p.InsSDWA, opName#p.AsmSDWA, [], p.HasModifiers>,
SDWADisableFields <p> {
let Defs = !if(DefExec, [VCC, EXEC], [VCC]);
let hasSideEffects = DefExec;
let AsmMatchConverter = "cvtSdwaVOPC";
let AssemblerPredicates = !if(p.HasExt, [isVI], [DisableInst]);
let DecoderNamespace = "SDWA";
let DisableDecoder = DisableVIDecoder;
}
multiclass VOPC_m <vopc op, dag ins, string op_asm, list<dag> pattern,
string opName, bit DefExec, VOPProfile p,
list<SchedReadWrite> sched,
string revOpName = "", string asm = opName#"_e32 "#op_asm,
string alias_asm = opName#" "#op_asm> {
def "" : VOPC_Pseudo <ins, pattern, opName>,
VOP2_REV<revOpName#"_e32", !eq(revOpName, opName)> {
let Defs = !if(DefExec, [VCC, EXEC], [VCC]);
let SchedRW = sched;
let isConvergent = DefExec;
}
let AssemblerPredicates = [isSICI] in {
def _si : VOPC<op.SI, ins, asm, []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.SI> {
let Defs = !if(DefExec, [VCC, EXEC], [VCC]);
let isConvergent = DefExec;
let SchedRW = sched;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
} // End AssemblerPredicates = [isSICI]
let AssemblerPredicates = [isVI] in {
def _vi : VOPC<op.VI, ins, asm, []>,
SIMCInstr <opName#"_e32", SIEncodingFamily.VI> {
let Defs = !if(DefExec, [VCC, EXEC], [VCC]);
let isConvergent = DefExec;
let SchedRW = sched;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
} // End AssemblerPredicates = [isVI]
defm : SIInstAliasBuilder<alias_asm, p>;
}
multiclass VOPC_Helper <vopc op, string opName, list<dag> pat32,
list<dag> pat64, bit DefExec, string revOp,
VOPProfile p, list<SchedReadWrite> sched> {
defm _e32 : VOPC_m <op, p.Ins32, p.Asm32, pat32, opName, DefExec, p, sched,
revOp>;
defm _e64 : VOP3_C_m <op, (outs VOPDstS64:$sdst), p.Ins64, opName#p.Asm64, pat64,
opName, p.HasModifiers, DefExec, revOp, sched>;
def _sdwa : VOPC_SDWA <op, opName, DefExec, p>;
}
// Special case for class instructions which only have modifiers on
// the 1st source operand.
multiclass VOPC_Class_Helper <vopc op, string opName, list<dag> pat32,
list<dag> pat64, bit DefExec, string revOp,
VOPProfile p, list<SchedReadWrite> sched> {
defm _e32 : VOPC_m <op, p.Ins32, p.Asm32, pat32, opName, DefExec, p, sched>;
defm _e64 : VOP3_C_m <op, (outs VOPDstS64:$sdst), p.Ins64, opName#p.Asm64, pat64,
opName, p.HasModifiers, DefExec, revOp, sched>,
VOP3DisableModFields<1, 0, 0>;
def _sdwa : VOPC_SDWA <op, opName, DefExec, p> {
let src1_fmodifiers = 0;
let src1_imodifiers = ?;
}
}
multiclass VOPCInst <vopc op, string opName,
VOPProfile P, PatLeaf cond = COND_NULL,
string revOp = opName,
bit DefExec = 0,
list<SchedReadWrite> sched = [Write32Bit]> :
VOPC_Helper <
op, opName, [],
!if(P.HasModifiers,
[(set i1:$sdst,
(setcc (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers)),
cond))],
[(set i1:$sdst, (setcc P.Src0VT:$src0, P.Src1VT:$src1, cond))]),
DefExec, revOp, P, sched
>;
multiclass VOPCClassInst <vopc op, string opName, VOPProfile P,
bit DefExec = 0,
list<SchedReadWrite> sched> : VOPC_Class_Helper <
op, opName, [],
!if(P.HasModifiers,
[(set i1:$sdst,
(AMDGPUfp_class (P.Src0VT (VOP3Mods0Clamp0OMod P.Src0VT:$src0, i32:$src0_modifiers)), P.Src1VT:$src1))],
[(set i1:$sdst, (AMDGPUfp_class P.Src0VT:$src0, P.Src1VT:$src1))]),
DefExec, opName, P, sched
>;
multiclass VOPC_F32 <vopc op, string opName, PatLeaf cond = COND_NULL, string revOp = opName> :
VOPCInst <op, opName, VOPC_I1_F32_F32, cond, revOp>;
multiclass VOPC_F64 <vopc op, string opName, PatLeaf cond = COND_NULL, string revOp = opName> :
VOPCInst <op, opName, VOPC_I1_F64_F64, cond, revOp, 0, [WriteDoubleAdd]>;
multiclass VOPC_I32 <vopc op, string opName, PatLeaf cond = COND_NULL, string revOp = opName> :
VOPCInst <op, opName, VOPC_I1_I32_I32, cond, revOp>;
multiclass VOPC_I64 <vopc op, string opName, PatLeaf cond = COND_NULL, string revOp = opName> :
VOPCInst <op, opName, VOPC_I1_I64_I64, cond, revOp, 0, [Write64Bit]>;
multiclass VOPCX <vopc op, string opName, VOPProfile P,
PatLeaf cond = COND_NULL,
list<SchedReadWrite> sched,
string revOp = "">
: VOPCInst <op, opName, P, cond, revOp, 1, sched>;
multiclass VOPCX_F32 <vopc op, string opName, string revOp = opName> :
VOPCX <op, opName, VOPC_I1_F32_F32, COND_NULL, [Write32Bit], revOp>;
multiclass VOPCX_F64 <vopc op, string opName, string revOp = opName> :
VOPCX <op, opName, VOPC_I1_F64_F64, COND_NULL, [WriteDoubleAdd], revOp>;
multiclass VOPCX_I32 <vopc op, string opName, string revOp = opName> :
VOPCX <op, opName, VOPC_I1_I32_I32, COND_NULL, [Write32Bit], revOp>;
multiclass VOPCX_I64 <vopc op, string opName, string revOp = opName> :
VOPCX <op, opName, VOPC_I1_I64_I64, COND_NULL, [Write64Bit], revOp>;
multiclass VOPC_CLASS_F32 <vopc op, string opName> :
VOPCClassInst <op, opName, VOPC_I1_F32_I32, 0, [Write32Bit]>;
multiclass VOPCX_CLASS_F32 <vopc op, string opName> :
VOPCClassInst <op, opName, VOPC_I1_F32_I32, 1, [Write32Bit]>;
multiclass VOPC_CLASS_F64 <vopc op, string opName> :
VOPCClassInst <op, opName, VOPC_I1_F64_I32, 0, [WriteDoubleAdd]>;
multiclass VOPCX_CLASS_F64 <vopc op, string opName> :
VOPCClassInst <op, opName, VOPC_I1_F64_I32, 1, [WriteDoubleAdd]>;
multiclass VOP3_Helper <vop3 op, string opName, dag outs, dag ins, string asm,
list<dag> pat, int NumSrcArgs, bit HasMods,
bit VOP3Only = 0> : VOP3_m <
op, outs, ins, opName#" "#asm, pat, opName, NumSrcArgs, HasMods, VOP3Only
>;
multiclass VOP3Inst <vop3 op, string opName, VOPProfile P,
SDPatternOperator node = null_frag, bit VOP3Only = 0> :
VOP3_Helper <
op, opName, (outs P.DstRC.RegClass:$vdst), P.Ins64, P.Asm64,
!if(!eq(P.NumSrcArgs, 3),
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers)),
(P.Src2VT (VOP3Mods P.Src2VT:$src2, i32:$src2_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1,
P.Src2VT:$src2))]),
!if(!eq(P.NumSrcArgs, 2),
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))])
/* P.NumSrcArgs == 1 */,
!if(P.HasModifiers,
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod))))],
[(set P.DstVT:$vdst, (node P.Src0VT:$src0))]))),
P.NumSrcArgs, P.HasModifiers, VOP3Only
>;
// Special case for v_div_fmas_{f32|f64}, since it seems to be the
// only VOP instruction that implicitly reads VCC.
multiclass VOP3_VCC_Inst <vop3 op, string opName,
VOPProfile P,
SDPatternOperator node = null_frag> : VOP3_Helper <
op, opName,
(outs P.DstRC.RegClass:$vdst),
(ins FPInputMods:$src0_modifiers, P.Src0RC64:$src0,
FPInputMods:$src1_modifiers, P.Src1RC64:$src1,
FPInputMods:$src2_modifiers, P.Src2RC64:$src2,
clampmod:$clamp,
omod:$omod),
"$vdst, $src0_modifiers, $src1_modifiers, $src2_modifiers"#"$clamp"#"$omod",
[(set P.DstVT:$vdst,
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers)),
(P.Src2VT (VOP3Mods P.Src2VT:$src2, i32:$src2_modifiers)),
(i1 VCC)))],
3, 1
>;
multiclass VOP3bInst <vop op, string opName, VOPProfile P, list<dag> pattern = [], bit VOP3Only = 0> :
VOP3b_2_3_m <
op, P.Outs64, P.Ins64,
opName#" "#P.Asm64, pattern,
opName, "", 1, 1, VOP3Only
>;
class Vop3ModPat<Instruction Inst, VOPProfile P, SDPatternOperator node> : Pat<
(node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers, i1:$clamp, i32:$omod)),
(P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers)),
(P.Src2VT (VOP3Mods P.Src2VT:$src2, i32:$src2_modifiers))),
(Inst i32:$src0_modifiers, P.Src0VT:$src0,
i32:$src1_modifiers, P.Src1VT:$src1,
i32:$src2_modifiers, P.Src2VT:$src2,
i1:$clamp,
i32:$omod)>;
//===----------------------------------------------------------------------===//
// Interpolation opcodes
//===----------------------------------------------------------------------===//
class VINTRP_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
VINTRPCommon <outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class VINTRP_Real_si <bits <2> op, string opName, dag outs, dag ins,
string asm> :
VINTRPCommon <outs, ins, asm, []>,
VINTRPe <op>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let AssemblerPredicate = SIAssemblerPredicate;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class VINTRP_Real_vi <bits <2> op, string opName, dag outs, dag ins,
string asm> :
VINTRPCommon <outs, ins, asm, []>,
VINTRPe_vi <op>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let AssemblerPredicate = VIAssemblerPredicate;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass VINTRP_m <bits <2> op, dag outs, dag ins, string asm,
list<dag> pattern = []> {
def "" : VINTRP_Pseudo <NAME, outs, ins, pattern>;
def _si : VINTRP_Real_si <op, NAME, outs, ins, asm>;
def _vi : VINTRP_Real_vi <op, NAME, outs, ins, asm>;
}
//===----------------------------------------------------------------------===//
// Vector I/O classes
//===----------------------------------------------------------------------===//
class DS_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
DS <outs, ins, "", pattern>,
SIMCInstr <opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class DS_Real_si <bits<8> op, string opName, dag outs, dag ins, string asm> :
DS <outs, ins, asm, []>,
DSe <op>,
SIMCInstr <opName, SIEncodingFamily.SI> {
let isCodeGenOnly = 0;
let AssemblerPredicates = [isSICI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="SICI";
let DisableDecoder = DisableSIDecoder;
}
class DS_Real_vi <bits<8> op, string opName, dag outs, dag ins, string asm> :
DS <outs, ins, asm, []>,
DSe_vi <op>,
SIMCInstr <opName, SIEncodingFamily.VI> {
let isCodeGenOnly = 0;
let AssemblerPredicates = [isVI];
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="VI";
let DisableDecoder = DisableVIDecoder;
}
class DS_Off16_Real_si <bits<8> op, string opName, dag outs, dag ins, string asm> :
DS_Real_si <op,opName, outs, ins, asm> {
// Single load interpret the 2 i8imm operands as a single i16 offset.
bits<16> offset;
let offset0 = offset{7-0};
let offset1 = offset{15-8};
}
class DS_Off16_Real_vi <bits<8> op, string opName, dag outs, dag ins, string asm> :
DS_Real_vi <op, opName, outs, ins, asm> {
// Single load interpret the 2 i8imm operands as a single i16 offset.
bits<16> offset;
let offset0 = offset{7-0};
let offset1 = offset{15-8};
}
multiclass DS_1A_RET_ <dsop op, string opName, RegisterClass rc,
dag outs = (outs rc:$vdst),
dag ins = (ins VGPR_32:$addr, offset:$offset, gds:$gds),
string asm = opName#" $vdst, $addr"#"$offset$gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>;
let data0 = 0, data1 = 0 in {
def _si : DS_Off16_Real_si <op.SI, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op.VI, opName, outs, ins, asm>;
}
}
// TODO: DS_1A_RET can be inherited from DS_1A_RET_ but its not working
// for some reason. In fact we can remove this class if use dsop everywhere
multiclass DS_1A_RET <bits<8> op, string opName, RegisterClass rc,
dag outs = (outs rc:$vdst),
dag ins = (ins VGPR_32:$addr, offset:$offset, gds:$gds),
string asm = opName#" $vdst, $addr"#"$offset$gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>;
let data0 = 0, data1 = 0 in {
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass DS_1A_Off8_RET <bits<8> op, string opName, RegisterClass rc,
dag outs = (outs rc:$vdst),
dag ins = (ins VGPR_32:$addr, offset0:$offset0, offset1:$offset1,
gds:$gds),
string asm = opName#" $vdst, $addr"#"$offset0"#"$offset1$gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>;
let data0 = 0, data1 = 0, AsmMatchConverter = "cvtDSOffset01" in {
def _si : DS_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass DS_1A1D_NORET <bits<8> op, string opName, RegisterClass rc,
dag outs = (outs),
dag ins = (ins VGPR_32:$addr, rc:$data0, offset:$offset, gds:$gds),
string asm = opName#" $addr, $data0"#"$offset$gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>,
AtomicNoRet<opName, 0>;
let data1 = 0, vdst = 0 in {
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass DS_1A_Off8_NORET <bits<8> op, string opName,
dag outs = (outs),
dag ins = (ins VGPR_32:$addr,
offset0:$offset0, offset1:$offset1, gds:$gds),
string asm = opName#" $addr $offset0"#"$offset1$gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>;
let data0 = 0, data1 = 0, vdst = 0, AsmMatchConverter = "cvtDSOffset01" in {
def _si : DS_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass DS_1A2D_Off8_NORET <bits<8> op, string opName, RegisterClass rc,
dag outs = (outs),
dag ins = (ins VGPR_32:$addr, rc:$data0, rc:$data1,
offset0:$offset0, offset1:$offset1, gds:$gds),
string asm = opName#" $addr, $data0, $data1$offset0$offset1$gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>;
let vdst = 0, AsmMatchConverter = "cvtDSOffset01" in {
def _si : DS_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass DS_1A1D_RET <bits<8> op, string opName, RegisterClass rc,
string noRetOp = "",
dag outs = (outs rc:$vdst),
dag ins = (ins VGPR_32:$addr, rc:$data0, offset:$offset, gds:$gds),
string asm = opName#" $vdst, $addr, $data0"#"$offset$gds"> {
let hasPostISelHook = 1 in {
def "" : DS_Pseudo <opName, outs, ins, []>,
AtomicNoRet<noRetOp, 1>;
let data1 = 0 in {
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
}
}
}
multiclass DS_1A1D_PERMUTE <bits<8> op, string opName, RegisterClass rc,
SDPatternOperator node = null_frag,
dag outs = (outs rc:$vdst),
dag ins = (ins VGPR_32:$addr, rc:$data0, offset:$offset),
string asm = opName#" $vdst, $addr, $data0"#"$offset"> {
let mayLoad = 0, mayStore = 0, isConvergent = 1 in {
def "" : DS_Pseudo <opName, outs, ins,
[(set i32:$vdst,
(node (DS1Addr1Offset i32:$addr, i16:$offset), i32:$data0))]>;
let data1 = 0, gds = 0 in {
def "_vi" : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
}
}
}
multiclass DS_1A2D_RET_m <bits<8> op, string opName, RegisterClass rc,
string noRetOp = "", dag ins,
dag outs = (outs rc:$vdst),
string asm = opName#" $vdst, $addr, $data0, $data1"#"$offset"#"$gds"> {
let hasPostISelHook = 1 in {
def "" : DS_Pseudo <opName, outs, ins, []>,
AtomicNoRet<noRetOp, 1>;
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass DS_1A2D_RET <bits<8> op, string asm, RegisterClass rc,
string noRetOp = "", RegisterClass src = rc> :
DS_1A2D_RET_m <op, asm, rc, noRetOp,
(ins VGPR_32:$addr, src:$data0, src:$data1,
offset:$offset, gds:$gds)
>;
multiclass DS_1A2D_NORET <bits<8> op, string opName, RegisterClass rc,
string noRetOp = opName,
dag outs = (outs),
dag ins = (ins VGPR_32:$addr, rc:$data0, rc:$data1,
offset:$offset, gds:$gds),
string asm = opName#" $addr, $data0, $data1"#"$offset"#"$gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>,
AtomicNoRet<noRetOp, 0>;
let vdst = 0 in {
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass DS_0A_RET <bits<8> op, string opName,
dag outs = (outs VGPR_32:$vdst),
dag ins = (ins offset:$offset, gds:$gds),
string asm = opName#" $vdst"#"$offset"#"$gds"> {
let mayLoad = 1, mayStore = 1 in {
def "" : DS_Pseudo <opName, outs, ins, []>;
let addr = 0, data0 = 0, data1 = 0 in {
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
} // end addr = 0, data0 = 0, data1 = 0
} // end mayLoad = 1, mayStore = 1
}
multiclass DS_1A_RET_GDS <bits<8> op, string opName,
dag outs = (outs VGPR_32:$vdst),
dag ins = (ins VGPR_32:$addr, offset:$offset),
string asm = opName#" $vdst, $addr"#"$offset gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>;
let data0 = 0, data1 = 0, gds = 1 in {
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
} // end data0 = 0, data1 = 0, gds = 1
}
multiclass DS_1A_GDS <bits<8> op, string opName,
dag outs = (outs),
dag ins = (ins VGPR_32:$addr),
string asm = opName#" $addr gds"> {
def "" : DS_Pseudo <opName, outs, ins, []>;
let vdst = 0, data0 = 0, data1 = 0, offset0 = 0, offset1 = 0, gds = 1 in {
def _si : DS_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Real_vi <op, opName, outs, ins, asm>;
} // end vdst = 0, data = 0, data1 = 0, gds = 1
}
multiclass DS_1A <bits<8> op, string opName,
dag outs = (outs),
dag ins = (ins VGPR_32:$addr, offset:$offset, gds:$gds),
string asm = opName#" $addr"#"$offset"#"$gds"> {
let mayLoad = 1, mayStore = 1 in {
def "" : DS_Pseudo <opName, outs, ins, []>;
let vdst = 0, data0 = 0, data1 = 0 in {
def _si : DS_Off16_Real_si <op, opName, outs, ins, asm>;
def _vi : DS_Off16_Real_vi <op, opName, outs, ins, asm>;
} // let vdst = 0, data0 = 0, data1 = 0
} // end mayLoad = 1, mayStore = 1
}
//===----------------------------------------------------------------------===//
// MTBUF classes
//===----------------------------------------------------------------------===//
class MTBUF_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
MTBUF <outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class MTBUF_Real_si <bits<3> op, string opName, dag outs, dag ins,
string asm> :
MTBUF <outs, ins, asm, []>,
MTBUFe <op>,
SIMCInstr<opName, SIEncodingFamily.SI> {
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="SICI";
let DisableDecoder = DisableSIDecoder;
}
class MTBUF_Real_vi <bits<4> op, string opName, dag outs, dag ins, string asm> :
MTBUF <outs, ins, asm, []>,
MTBUFe_vi <op>,
SIMCInstr <opName, SIEncodingFamily.VI> {
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass MTBUF_m <bits<3> op, string opName, dag outs, dag ins, string asm,
list<dag> pattern> {
def "" : MTBUF_Pseudo <opName, outs, ins, pattern>;
def _si : MTBUF_Real_si <op, opName, outs, ins, asm>;
def _vi : MTBUF_Real_vi <{0, op{2}, op{1}, op{0}}, opName, outs, ins, asm>;
}
let mayStore = 1, mayLoad = 0 in {
multiclass MTBUF_Store_Helper <bits<3> op, string opName,
RegisterClass regClass> : MTBUF_m <
op, opName, (outs),
(ins regClass:$vdata, u16imm:$offset, i1imm:$offen, i1imm:$idxen, i1imm:$glc,
i1imm:$addr64, i8imm:$dfmt, i8imm:$nfmt, VGPR_32:$vaddr,
SReg_128:$srsrc, i1imm:$slc, i1imm:$tfe, SCSrc_32:$soffset),
opName#" $vdata, $offset, $offen, $idxen, $glc, $addr64, $dfmt,"
#" $nfmt, $vaddr, $srsrc, $slc, $tfe, $soffset", []
>;
} // mayStore = 1, mayLoad = 0
let mayLoad = 1, mayStore = 0 in {
multiclass MTBUF_Load_Helper <bits<3> op, string opName,
RegisterClass regClass> : MTBUF_m <
op, opName, (outs regClass:$dst),
(ins u16imm:$offset, i1imm:$offen, i1imm:$idxen, i1imm:$glc, i1imm:$addr64,
i8imm:$dfmt, i8imm:$nfmt, VGPR_32:$vaddr, SReg_128:$srsrc,
i1imm:$slc, i1imm:$tfe, SCSrc_32:$soffset),
opName#" $dst, $offset, $offen, $idxen, $glc, $addr64, $dfmt,"
#" $nfmt, $vaddr, $srsrc, $slc, $tfe, $soffset", []
>;
} // mayLoad = 1, mayStore = 0
//===----------------------------------------------------------------------===//
// MUBUF classes
//===----------------------------------------------------------------------===//
class mubuf <bits<7> si, bits<7> vi = si> {
field bits<7> SI = si;
field bits<7> VI = vi;
}
let isCodeGenOnly = 0 in {
class MUBUF_si <bits<7> op, dag outs, dag ins, string asm, list<dag> pattern> :
MUBUF <outs, ins, asm, pattern>, MUBUFe <op> {
let lds = 0;
}
} // End let isCodeGenOnly = 0
class MUBUF_vi <bits<7> op, dag outs, dag ins, string asm, list<dag> pattern> :
MUBUF <outs, ins, asm, pattern>, MUBUFe_vi <op> {
let lds = 0;
}
class MUBUFAddr64Table <bit is_addr64, string suffix = ""> {
bit IsAddr64 = is_addr64;
string OpName = NAME # suffix;
}
class MUBUF_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
MUBUF <outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
// dummy fields, so that we can use let statements around multiclasses
bits<1> offen;
bits<1> idxen;
bits<8> vaddr;
bits<1> glc;
bits<1> slc;
bits<1> tfe;
bits<8> soffset;
}
class MUBUF_Real_si <mubuf op, string opName, dag outs, dag ins,
string asm> :
MUBUF <outs, ins, asm, []>,
MUBUFe <op.SI>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let lds = 0;
let AssemblerPredicate = SIAssemblerPredicate;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="SICI";
let DisableDecoder = DisableSIDecoder;
}
class MUBUF_Real_vi <mubuf op, string opName, dag outs, dag ins,
string asm> :
MUBUF <outs, ins, asm, []>,
MUBUFe_vi <op.VI>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let lds = 0;
let AssemblerPredicate = VIAssemblerPredicate;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass MUBUF_m <mubuf op, string opName, dag outs, dag ins, string asm,
list<dag> pattern> {
def "" : MUBUF_Pseudo <opName, outs, ins, pattern>,
MUBUFAddr64Table <0>;
let addr64 = 0, isCodeGenOnly = 0 in {
def _si : MUBUF_Real_si <op, opName, outs, ins, asm>;
}
def _vi : MUBUF_Real_vi <op, opName, outs, ins, asm>;
}
multiclass MUBUFAddr64_m <mubuf op, string opName, dag outs,
dag ins, string asm, list<dag> pattern> {
def "" : MUBUF_Pseudo <opName, outs, ins, pattern>,
MUBUFAddr64Table <1>;
let addr64 = 1, isCodeGenOnly = 0 in {
def _si : MUBUF_Real_si <op, opName, outs, ins, asm>;
}
// There is no VI version. If the pseudo is selected, it should be lowered
// for VI appropriately.
}
multiclass MUBUFAtomicOffset_m <mubuf op, string opName, dag outs, dag ins,
string asm, list<dag> pattern, bit is_return> {
def "" : MUBUF_Pseudo <opName, outs, ins, pattern>,
MUBUFAddr64Table <0, !if(is_return, "_RTN", "")>,
AtomicNoRet<NAME#"_OFFSET", is_return>;
let offen = 0, idxen = 0, tfe = 0, vaddr = 0 in {
let addr64 = 0 in {
def _si : MUBUF_Real_si <op, opName, outs, ins, asm>;
}
def _vi : MUBUF_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass MUBUFAtomicAddr64_m <mubuf op, string opName, dag outs, dag ins,
string asm, list<dag> pattern, bit is_return> {
def "" : MUBUF_Pseudo <opName, outs, ins, pattern>,
MUBUFAddr64Table <1, !if(is_return, "_RTN", "")>,
AtomicNoRet<NAME#"_ADDR64", is_return>;
let offen = 0, idxen = 0, addr64 = 1, tfe = 0 in {
def _si : MUBUF_Real_si <op, opName, outs, ins, asm>;
}
// There is no VI version. If the pseudo is selected, it should be lowered
// for VI appropriately.
}
multiclass MUBUFAtomicOther_m <mubuf op, string opName, dag outs, dag ins,
string asm, list<dag> pattern, bit is_return> {
def "" : MUBUF_Pseudo <opName, outs, ins, pattern>,
AtomicNoRet<opName, is_return>;
let tfe = 0 in {
let addr64 = 0 in {
def _si : MUBUF_Real_si <op, opName, outs, ins, asm>;
}
def _vi : MUBUF_Real_vi <op, opName, outs, ins, asm>;
}
}
multiclass MUBUF_Atomic <mubuf op, string name, RegisterClass rc,
ValueType vt, SDPatternOperator atomic> {
let mayStore = 1, mayLoad = 1, hasPostISelHook = 1, hasSideEffects = 1 in {
// No return variants
let glc = 0, AsmMatchConverter = "cvtMubufAtomic" in {
defm _ADDR64 : MUBUFAtomicAddr64_m <
op, name#"_addr64", (outs),
(ins rc:$vdata, VReg_64:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset, offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset addr64$offset$slc", [], 0
>;
defm _OFFSET : MUBUFAtomicOffset_m <
op, name#"_offset", (outs),
(ins rc:$vdata, SReg_128:$srsrc, SCSrc_32:$soffset, offset:$offset,
slc:$slc),
name#" $vdata, off, $srsrc, $soffset$offset$slc", [], 0
>;
let offen = 1, idxen = 0 in {
defm _OFFEN : MUBUFAtomicOther_m <
op, name#"_offen", (outs),
(ins rc:$vdata, VGPR_32:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset offen$offset$slc", [], 0
>;
}
let offen = 0, idxen = 1 in {
defm _IDXEN : MUBUFAtomicOther_m <
op, name#"_idxen", (outs),
(ins rc:$vdata, VGPR_32:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset idxen$offset$slc", [], 0
>;
}
let offen = 1, idxen = 1 in {
defm _BOTHEN : MUBUFAtomicOther_m <
op, name#"_bothen", (outs),
(ins rc:$vdata, VReg_64:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset idxen offen$offset$slc",
[], 0
>;
}
} // glc = 0
// Variant that return values
let glc = 1, Constraints = "$vdata = $vdata_in",
AsmMatchConverter = "cvtMubufAtomicReturn",
DisableEncoding = "$vdata_in" in {
defm _RTN_ADDR64 : MUBUFAtomicAddr64_m <
op, name#"_rtn_addr64", (outs rc:$vdata),
(ins rc:$vdata_in, VReg_64:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset, offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset addr64$offset glc$slc",
[(set vt:$vdata,
(atomic (MUBUFAddr64Atomic v4i32:$srsrc, i64:$vaddr, i32:$soffset,
i16:$offset, i1:$slc), vt:$vdata_in))], 1
>;
defm _RTN_OFFSET : MUBUFAtomicOffset_m <
op, name#"_rtn_offset", (outs rc:$vdata),
(ins rc:$vdata_in, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, slc:$slc),
name#" $vdata, off, $srsrc, $soffset$offset glc$slc",
[(set vt:$vdata,
(atomic (MUBUFOffsetAtomic v4i32:$srsrc, i32:$soffset, i16:$offset,
i1:$slc), vt:$vdata_in))], 1
>;
let offen = 1, idxen = 0 in {
defm _RTN_OFFEN : MUBUFAtomicOther_m <
op, name#"_rtn_offen", (outs rc:$vdata),
(ins rc:$vdata_in, VGPR_32:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset offen$offset glc$slc",
[], 1
>;
}
let offen = 0, idxen = 1 in {
defm _RTN_IDXEN : MUBUFAtomicOther_m <
op, name#"_rtn_idxen", (outs rc:$vdata),
(ins rc:$vdata_in, VGPR_32:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset idxen$offset glc$slc",
[], 1
>;
}
let offen = 1, idxen = 1 in {
defm _RTN_BOTHEN : MUBUFAtomicOther_m <
op, name#"_rtn_bothen", (outs rc:$vdata),
(ins rc:$vdata_in, VReg_64:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, slc:$slc),
name#" $vdata, $vaddr, $srsrc, $soffset idxen offen$offset glc$slc",
[], 1
>;
}
} // glc = 1
} // mayStore = 1, mayLoad = 1, hasPostISelHook = 1
}
// FIXME: tfe can't be an operand because it requires a separate
// opcode because it needs an N+1 register class dest register.
multiclass MUBUF_Load_Helper <mubuf op, string name, RegisterClass regClass,
ValueType load_vt = i32,
SDPatternOperator ld = null_frag> {
let mayLoad = 1, mayStore = 0 in {
let offen = 0, idxen = 0, vaddr = 0 in {
defm _OFFSET : MUBUF_m <op, name#"_offset", (outs regClass:$vdata),
(ins SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, glc:$glc, slc:$slc, tfe:$tfe),
name#" $vdata, off, $srsrc, $soffset$offset$glc$slc$tfe",
[(set load_vt:$vdata, (ld (MUBUFOffset v4i32:$srsrc,
i32:$soffset, i16:$offset,
i1:$glc, i1:$slc, i1:$tfe)))]>;
}
let offen = 1, idxen = 0 in {
defm _OFFEN : MUBUF_m <op, name#"_offen", (outs regClass:$vdata),
(ins VGPR_32:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset, offset:$offset, glc:$glc, slc:$slc,
tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset offen$offset$glc$slc$tfe", []>;
}
let offen = 0, idxen = 1 in {
defm _IDXEN : MUBUF_m <op, name#"_idxen", (outs regClass:$vdata),
(ins VGPR_32:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset, offset:$offset, glc:$glc,
slc:$slc, tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset idxen$offset$glc$slc$tfe", []>;
}
let offen = 1, idxen = 1 in {
defm _BOTHEN : MUBUF_m <op, name#"_bothen", (outs regClass:$vdata),
(ins VReg_64:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, glc:$glc, slc:$slc, tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset idxen offen$offset$glc$slc$tfe", []>;
}
let offen = 0, idxen = 0 in {
defm _ADDR64 : MUBUFAddr64_m <op, name#"_addr64", (outs regClass:$vdata),
(ins VReg_64:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset, offset:$offset,
glc:$glc, slc:$slc, tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset addr64$offset$glc$slc$tfe",
[(set load_vt:$vdata, (ld (MUBUFAddr64 v4i32:$srsrc,
i64:$vaddr, i32:$soffset,
i16:$offset, i1:$glc, i1:$slc,
i1:$tfe)))]>;
}
}
}
multiclass MUBUF_Store_Helper <mubuf op, string name, RegisterClass vdataClass,
ValueType store_vt = i32, SDPatternOperator st = null_frag> {
let mayLoad = 0, mayStore = 1 in {
let offen = 0, idxen = 0, vaddr = 0 in {
defm _OFFSET : MUBUF_m <op, name#"_offset",(outs),
(ins vdataClass:$vdata, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, glc:$glc, slc:$slc, tfe:$tfe),
name#" $vdata, off, $srsrc, $soffset$offset$glc$slc$tfe",
[(st store_vt:$vdata, (MUBUFOffset v4i32:$srsrc, i32:$soffset,
i16:$offset, i1:$glc, i1:$slc, i1:$tfe))]>;
} // offen = 0, idxen = 0, vaddr = 0
let offen = 1, idxen = 0 in {
defm _OFFEN : MUBUF_m <op, name#"_offen", (outs),
(ins vdataClass:$vdata, VGPR_32:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset, offset:$offset, glc:$glc,
slc:$slc, tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset offen"#
"$offset$glc$slc$tfe", []>;
} // end offen = 1, idxen = 0
let offen = 0, idxen = 1 in {
defm _IDXEN : MUBUF_m <op, name#"_idxen", (outs),
(ins vdataClass:$vdata, VGPR_32:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset, offset:$offset, glc:$glc,
slc:$slc, tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset idxen$offset$glc$slc$tfe", []>;
}
let offen = 1, idxen = 1 in {
defm _BOTHEN : MUBUF_m <op, name#"_bothen", (outs),
(ins vdataClass:$vdata, VReg_64:$vaddr, SReg_128:$srsrc, SCSrc_32:$soffset,
offset:$offset, glc:$glc, slc:$slc, tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset idxen offen$offset$glc$slc$tfe", []>;
}
let offen = 0, idxen = 0 in {
defm _ADDR64 : MUBUFAddr64_m <op, name#"_addr64", (outs),
(ins vdataClass:$vdata, VReg_64:$vaddr, SReg_128:$srsrc,
SCSrc_32:$soffset,
offset:$offset, glc:$glc, slc:$slc,
tfe:$tfe),
name#" $vdata, $vaddr, $srsrc, $soffset addr64"#
"$offset$glc$slc$tfe",
[(st store_vt:$vdata,
(MUBUFAddr64 v4i32:$srsrc, i64:$vaddr,
i32:$soffset, i16:$offset,
i1:$glc, i1:$slc, i1:$tfe))]>;
}
} // End mayLoad = 0, mayStore = 1
}
// For cache invalidation instructions.
multiclass MUBUF_Invalidate <mubuf op, string opName, SDPatternOperator node> {
let hasSideEffects = 1, mayStore = 1, AsmMatchConverter = "" in {
def "" : MUBUF_Pseudo <opName, (outs), (ins), [(node)]>;
// Set everything to 0.
let offset = 0, offen = 0, idxen = 0, glc = 0, vaddr = 0,
vdata = 0, srsrc = 0, slc = 0, tfe = 0, soffset = 0 in {
let addr64 = 0 in {
def _si : MUBUF_Real_si <op, opName, (outs), (ins), opName>;
}
def _vi : MUBUF_Real_vi <op, opName, (outs), (ins), opName>;
}
} // End hasSideEffects = 1, mayStore = 1, AsmMatchConverter = ""
}
//===----------------------------------------------------------------------===//
// FLAT classes
//===----------------------------------------------------------------------===//
class flat <bits<7> ci, bits<7> vi = ci> {
field bits<7> CI = ci;
field bits<7> VI = vi;
}
class FLAT_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
FLAT <0, outs, ins, "", pattern>,
SIMCInstr<opName, SIEncodingFamily.NONE> {
let isPseudo = 1;
let isCodeGenOnly = 1;
}
class FLAT_Real_ci <bits<7> op, string opName, dag outs, dag ins, string asm> :
FLAT <op, outs, ins, asm, []>,
SIMCInstr<opName, SIEncodingFamily.SI> {
let AssemblerPredicate = isCIOnly;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="CI";
}
class FLAT_Real_vi <bits<7> op, string opName, dag outs, dag ins, string asm> :
FLAT <op, outs, ins, asm, []>,
SIMCInstr<opName, SIEncodingFamily.VI> {
let AssemblerPredicate = VIAssemblerPredicate;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let DecoderNamespace="VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass FLAT_AtomicRet_m <flat op, dag outs, dag ins, string asm,
list<dag> pattern> {
def "" : FLAT_Pseudo <NAME#"_RTN", outs, ins, pattern>,
AtomicNoRet <NAME, 1>;
def _ci : FLAT_Real_ci <op.CI, NAME#"_RTN", outs, ins, asm>;
def _vi : FLAT_Real_vi <op.VI, NAME#"_RTN", outs, ins, asm>;
}
multiclass FLAT_Load_Helper <flat op, string asm_name,
RegisterClass regClass,
dag outs = (outs regClass:$vdst),
dag ins = (ins VReg_64:$addr, glc:$glc, slc:$slc, tfe:$tfe),
string asm = asm_name#" $vdst, $addr$glc$slc$tfe"> {
let data = 0, mayLoad = 1 in {
def "" : FLAT_Pseudo <NAME, outs, ins, []>;
def _ci : FLAT_Real_ci <op.CI, NAME, outs, ins, asm>;
def _vi : FLAT_Real_vi <op.VI, NAME, outs, ins, asm>;
}
}
multiclass FLAT_Store_Helper <flat op, string asm_name,
RegisterClass vdataClass,
dag outs = (outs),
dag ins = (ins VReg_64:$addr, vdataClass:$data, glc:$glc,
slc:$slc, tfe:$tfe),
string asm = asm_name#" $addr, $data$glc$slc$tfe"> {
let mayLoad = 0, mayStore = 1, vdst = 0 in {
def "" : FLAT_Pseudo <NAME, outs, ins, []>;
def _ci : FLAT_Real_ci <op.CI, NAME, outs, ins, asm>;
def _vi : FLAT_Real_vi <op.VI, NAME, outs, ins, asm>;
}
}
multiclass FLAT_ATOMIC <flat op, string asm_name, RegisterClass vdst_rc,
ValueType vt, SDPatternOperator atomic = null_frag,
ValueType data_vt = vt,
RegisterClass data_rc = vdst_rc,
string asm_noret = asm_name#" $addr, $data"#"$slc"#"$tfe"> {
let mayLoad = 1, mayStore = 1, glc = 0, vdst = 0 in {
def "" : FLAT_Pseudo <NAME, (outs),
(ins VReg_64:$addr, data_rc:$data,
slc:$slc, tfe:$tfe), []>,
AtomicNoRet <NAME, 0>;
def _ci : FLAT_Real_ci <op.CI, NAME, (outs),
(ins VReg_64:$addr, data_rc:$data,
slc:$slc, tfe:$tfe),
asm_noret>;
def _vi : FLAT_Real_vi <op.VI, NAME, (outs),
(ins VReg_64:$addr, data_rc:$data,
slc:$slc, tfe:$tfe),
asm_noret>;
}
let glc = 1, hasPostISelHook = 1 in {
defm _RTN : FLAT_AtomicRet_m <
op, (outs vdst_rc:$vdst),
(ins VReg_64:$addr, data_rc:$data, slc:$slc, tfe:$tfe),
asm_name#" $vdst, $addr, $data glc$slc$tfe",
[(set vt:$vdst,
(atomic (FLATAtomic i64:$addr, i1:$slc, i1:$tfe), data_vt:$data))]
>;
}
}
class MIMG_Mask <string op, int channels> {
string Op = op;
int Channels = channels;
}
class mimg <bits<7> si, bits<7> vi = si> {
field bits<7> SI = si;
field bits<7> VI = vi;
}
class MIMG_Helper <dag outs, dag ins, string asm,
string dns=""> : MIMG<outs, ins, asm,[]> {
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let mayLoad = 1;
let mayStore = 0;
let hasPostISelHook = 1;
let DecoderNamespace = dns;
let isAsmParserOnly = !if(!eq(dns,""), 1, 0);
let AsmMatchConverter = "cvtMIMG";
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
}
class MIMG_NoSampler_Helper <bits<7> op, string asm,
RegisterClass dst_rc,
RegisterClass addr_rc,
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
string dns=""> : MIMG_Helper <
(outs dst_rc:$vdata),
(ins addr_rc:$vaddr, SReg_256:$srsrc,
dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
asm#" $vdata, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da",
dns>, MIMGe<op> {
let ssamp = 0;
}
multiclass MIMG_NoSampler_Src_Helper <bits<7> op, string asm,
RegisterClass dst_rc,
int channels> {
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
def _V1 : MIMG_NoSampler_Helper <op, asm, dst_rc, VGPR_32,
!if(!eq(channels, 1), "AMDGPU", "")>,
MIMG_Mask<asm#"_V1", channels>;
def _V2 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_64>,
MIMG_Mask<asm#"_V2", channels>;
def _V4 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_128>,
MIMG_Mask<asm#"_V4", channels>;
}
multiclass MIMG_NoSampler <bits<7> op, string asm> {
defm _V1 : MIMG_NoSampler_Src_Helper <op, asm, VGPR_32, 1>;
defm _V2 : MIMG_NoSampler_Src_Helper <op, asm, VReg_64, 2>;
defm _V3 : MIMG_NoSampler_Src_Helper <op, asm, VReg_96, 3>;
defm _V4 : MIMG_NoSampler_Src_Helper <op, asm, VReg_128, 4>;
}
class MIMG_Store_Helper <bits<7> op, string asm,
RegisterClass data_rc,
RegisterClass addr_rc> : MIMG_Helper <
(outs),
(ins data_rc:$vdata, addr_rc:$vaddr, SReg_256:$srsrc,
dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
asm#" $vdata, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da"
>, MIMGe<op> {
let ssamp = 0;
let mayLoad = 1; // TableGen requires this for matching with the intrinsics
let mayStore = 1;
let hasSideEffects = 1;
let hasPostISelHook = 0;
}
multiclass MIMG_Store_Addr_Helper <bits<7> op, string asm,
RegisterClass data_rc,
int channels> {
def _V1 : MIMG_Store_Helper <op, asm, data_rc, VGPR_32>,
MIMG_Mask<asm#"_V1", channels>;
def _V2 : MIMG_Store_Helper <op, asm, data_rc, VReg_64>,
MIMG_Mask<asm#"_V2", channels>;
def _V4 : MIMG_Store_Helper <op, asm, data_rc, VReg_128>,
MIMG_Mask<asm#"_V4", channels>;
}
multiclass MIMG_Store <bits<7> op, string asm> {
defm _V1 : MIMG_Store_Addr_Helper <op, asm, VGPR_32, 1>;
defm _V2 : MIMG_Store_Addr_Helper <op, asm, VReg_64, 2>;
defm _V3 : MIMG_Store_Addr_Helper <op, asm, VReg_96, 3>;
defm _V4 : MIMG_Store_Addr_Helper <op, asm, VReg_128, 4>;
}
class MIMG_Atomic_Helper <string asm, RegisterClass data_rc,
RegisterClass addr_rc> : MIMG_Helper <
(outs data_rc:$vdst),
(ins data_rc:$vdata, addr_rc:$vaddr, SReg_256:$srsrc,
dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
asm#" $vdst, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da"
> {
let mayStore = 1;
let hasSideEffects = 1;
let hasPostISelHook = 0;
let Constraints = "$vdst = $vdata";
let AsmMatchConverter = "cvtMIMGAtomic";
}
class MIMG_Atomic_Real_si<mimg op, string name, string asm,
RegisterClass data_rc, RegisterClass addr_rc> :
MIMG_Atomic_Helper<asm, data_rc, addr_rc>,
SIMCInstr<name, SIEncodingFamily.SI>,
MIMGe<op.SI> {
let isCodeGenOnly = 0;
let AssemblerPredicates = [isSICI];
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
class MIMG_Atomic_Real_vi<mimg op, string name, string asm,
RegisterClass data_rc, RegisterClass addr_rc> :
MIMG_Atomic_Helper<asm, data_rc, addr_rc>,
SIMCInstr<name, SIEncodingFamily.VI>,
MIMGe<op.VI> {
let isCodeGenOnly = 0;
let AssemblerPredicates = [isVI];
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
multiclass MIMG_Atomic_Helper_m <mimg op, string name, string asm,
RegisterClass data_rc, RegisterClass addr_rc> {
let isPseudo = 1, isCodeGenOnly = 1 in {
def "" : MIMG_Atomic_Helper<asm, data_rc, addr_rc>,
SIMCInstr<name, SIEncodingFamily.NONE>;
}
let ssamp = 0 in {
def _si : MIMG_Atomic_Real_si<op, name, asm, data_rc, addr_rc>;
def _vi : MIMG_Atomic_Real_vi<op, name, asm, data_rc, addr_rc>;
}
}
multiclass MIMG_Atomic <mimg op, string asm, RegisterClass data_rc = VGPR_32> {
defm _V1 : MIMG_Atomic_Helper_m <op, asm # "_V1", asm, data_rc, VGPR_32>;
defm _V2 : MIMG_Atomic_Helper_m <op, asm # "_V2", asm, data_rc, VReg_64>;
defm _V4 : MIMG_Atomic_Helper_m <op, asm # "_V3", asm, data_rc, VReg_128>;
}
class MIMG_Sampler_Helper <bits<7> op, string asm,
RegisterClass dst_rc,
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
RegisterClass src_rc,
int wqm,
string dns=""> : MIMG_Helper <
(outs dst_rc:$vdata),
(ins src_rc:$vaddr, SReg_256:$srsrc, SReg_128:$ssamp,
dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
asm#" $vdata, $vaddr, $srsrc, $ssamp$dmask$unorm$glc$slc$r128$tfe$lwe$da",
dns>, MIMGe<op> {
let WQM = wqm;
}
multiclass MIMG_Sampler_Src_Helper <bits<7> op, string asm,
RegisterClass dst_rc,
int channels, int wqm> {
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
def _V1 : MIMG_Sampler_Helper <op, asm, dst_rc, VGPR_32, wqm,
!if(!eq(channels, 1), "AMDGPU", "")>,
MIMG_Mask<asm#"_V1", channels>;
def _V2 : MIMG_Sampler_Helper <op, asm, dst_rc, VReg_64, wqm>,
MIMG_Mask<asm#"_V2", channels>;
def _V4 : MIMG_Sampler_Helper <op, asm, dst_rc, VReg_128, wqm>,
MIMG_Mask<asm#"_V4", channels>;
def _V8 : MIMG_Sampler_Helper <op, asm, dst_rc, VReg_256, wqm>,
MIMG_Mask<asm#"_V8", channels>;
def _V16 : MIMG_Sampler_Helper <op, asm, dst_rc, VReg_512, wqm>,
MIMG_Mask<asm#"_V16", channels>;
}
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
multiclass MIMG_Sampler <bits<7> op, string asm, int wqm=0> {
defm _V1 : MIMG_Sampler_Src_Helper<op, asm, VGPR_32, 1, wqm>;
defm _V2 : MIMG_Sampler_Src_Helper<op, asm, VReg_64, 2, wqm>;
defm _V3 : MIMG_Sampler_Src_Helper<op, asm, VReg_96, 3, wqm>;
defm _V4 : MIMG_Sampler_Src_Helper<op, asm, VReg_128, 4, wqm>;
}
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
multiclass MIMG_Sampler_WQM <bits<7> op, string asm> : MIMG_Sampler<op, asm, 1>;
class MIMG_Gather_Helper <bits<7> op, string asm,
RegisterClass dst_rc,
RegisterClass src_rc, int wqm> : MIMG <
(outs dst_rc:$vdata),
(ins src_rc:$vaddr, SReg_256:$srsrc, SReg_128:$ssamp,
dmask:$dmask, unorm:$unorm, glc:$glc, slc:$slc,
r128:$r128, tfe:$tfe, lwe:$lwe, da:$da),
asm#" $vdata, $vaddr, $srsrc, $ssamp$dmask$unorm$glc$slc$r128$tfe$lwe$da",
[]>, MIMGe<op> {
let mayLoad = 1;
let mayStore = 0;
// DMASK was repurposed for GATHER4. 4 components are always
// returned and DMASK works like a swizzle - it selects
// the component to fetch. The only useful DMASK values are
// 1=red, 2=green, 4=blue, 8=alpha. (e.g. 1 returns
// (red,red,red,red) etc.) The ISA document doesn't mention
// this.
// Therefore, disable all code which updates DMASK by setting this:
let Gather4 = 1;
let hasPostISelHook = 0;
let WQM = wqm;
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
let isAsmParserOnly = 1; // TBD: fix it later
}
multiclass MIMG_Gather_Src_Helper <bits<7> op, string asm,
RegisterClass dst_rc,
int channels, int wqm> {
def _V1 : MIMG_Gather_Helper <op, asm, dst_rc, VGPR_32, wqm>,
MIMG_Mask<asm#"_V1", channels>;
def _V2 : MIMG_Gather_Helper <op, asm, dst_rc, VReg_64, wqm>,
MIMG_Mask<asm#"_V2", channels>;
def _V4 : MIMG_Gather_Helper <op, asm, dst_rc, VReg_128, wqm>,
MIMG_Mask<asm#"_V4", channels>;
def _V8 : MIMG_Gather_Helper <op, asm, dst_rc, VReg_256, wqm>,
MIMG_Mask<asm#"_V8", channels>;
def _V16 : MIMG_Gather_Helper <op, asm, dst_rc, VReg_512, wqm>,
MIMG_Mask<asm#"_V16", channels>;
}
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
multiclass MIMG_Gather <bits<7> op, string asm, int wqm=0> {
defm _V1 : MIMG_Gather_Src_Helper<op, asm, VGPR_32, 1, wqm>;
defm _V2 : MIMG_Gather_Src_Helper<op, asm, VReg_64, 2, wqm>;
defm _V3 : MIMG_Gather_Src_Helper<op, asm, VReg_96, 3, wqm>;
defm _V4 : MIMG_Gather_Src_Helper<op, asm, VReg_128, 4, wqm>;
}
[AMDGPU] Disassembler: Added basic disassembler for AMDGPU target Changes: - Added disassembler project - Fixed all decoding conflicts in .td files - Added DecoderMethod=“NONE” option to Target.td that allows to disable decoder generation for an instruction. - Created decoding functions for VS_32 and VReg_32 register classes. - Added stubs for decoding all register classes. - Added several tests for disassembler Disassembler only supports: - VI subtarget - VOP1 instruction encoding - 32-bit register operands and inline constants [Valery] One of the point that requires to pay attention to is how decoder conflicts were resolved: - Groups of target instructions were separated by using different DecoderNamespace (SICI, VI, CI) using similar to AssemblerPredicate approach. - There were conflicts in IMAGE_<> instructions caused by two different reasons: 1. dmask wasn’t specified for the output (fixed) 2. There are image instructions that differ only by the number of the address components but have the same encoding by the HW spec. The actual number of address components is determined by the HW at runtime using image resource descriptor starting from the VGPR encoded in an IMAGE instruction. This means that we should choose only one instruction from conflicting group to be the rule for decoder. I didn’t find the way to disable decoder generation for an arbitrary instruction and therefore made a onelinear fix to tablegen generator that would suppress decoder generation when DecoderMethod is set to “NONE”. This is a change that should be reviewed and submitted first. Otherwise I would need to specify different DecoderNamespace for every instruction in the conflicting group. I haven’t checked yet if DecoderMethod=“NONE” is not used in other targets. 3. IMAGE_GATHER decoder generation is for now disabled and to be done later. [/Valery] Patch By: Sam Kolton Differential Revision: http://reviews.llvm.org/D16723 llvm-svn: 261185
2016-02-18 11:42:32 +08:00
multiclass MIMG_Gather_WQM <bits<7> op, string asm> : MIMG_Gather<op, asm, 1>;
//===----------------------------------------------------------------------===//
// Vector instruction mappings
//===----------------------------------------------------------------------===//
// Maps an opcode in e32 form to its e64 equivalent
def getVOPe64 : InstrMapping {
let FilterClass = "VOP";
let RowFields = ["OpName"];
let ColFields = ["Size"];
let KeyCol = ["4"];
let ValueCols = [["8"]];
}
// Maps an opcode in e64 form to its e32 equivalent
def getVOPe32 : InstrMapping {
let FilterClass = "VOP";
let RowFields = ["OpName"];
let ColFields = ["Size"];
let KeyCol = ["8"];
let ValueCols = [["4"]];
}
def getMaskedMIMGOp : InstrMapping {
let FilterClass = "MIMG_Mask";
let RowFields = ["Op"];
let ColFields = ["Channels"];
let KeyCol = ["4"];
let ValueCols = [["1"], ["2"], ["3"] ];
}
// Maps an commuted opcode to its original version
def getCommuteOrig : InstrMapping {
let FilterClass = "VOP2_REV";
let RowFields = ["RevOp"];
let ColFields = ["IsOrig"];
let KeyCol = ["0"];
let ValueCols = [["1"]];
}
// Maps an original opcode to its commuted version
def getCommuteRev : InstrMapping {
let FilterClass = "VOP2_REV";
let RowFields = ["RevOp"];
let ColFields = ["IsOrig"];
let KeyCol = ["1"];
let ValueCols = [["0"]];
}
def getCommuteCmpOrig : InstrMapping {
let FilterClass = "VOP2_REV";
let RowFields = ["RevOp"];
let ColFields = ["IsOrig"];
let KeyCol = ["0"];
let ValueCols = [["1"]];
}
// Maps an original opcode to its commuted version
def getCommuteCmpRev : InstrMapping {
let FilterClass = "VOP2_REV";
let RowFields = ["RevOp"];
let ColFields = ["IsOrig"];
let KeyCol = ["1"];
let ValueCols = [["0"]];
}
def getMCOpcodeGen : InstrMapping {
let FilterClass = "SIMCInstr";
let RowFields = ["PseudoInstr"];
let ColFields = ["Subtarget"];
let KeyCol = [!cast<string>(SIEncodingFamily.NONE)];
let ValueCols = [[!cast<string>(SIEncodingFamily.SI)],
[!cast<string>(SIEncodingFamily.VI)]];
}
def getAddr64Inst : InstrMapping {
let FilterClass = "MUBUFAddr64Table";
let RowFields = ["OpName"];
let ColFields = ["IsAddr64"];
let KeyCol = ["0"];
let ValueCols = [["1"]];
}
// Maps an atomic opcode to its version with a return value.
def getAtomicRetOp : InstrMapping {
let FilterClass = "AtomicNoRet";
let RowFields = ["NoRetOp"];
let ColFields = ["IsRet"];
let KeyCol = ["0"];
let ValueCols = [["1"]];
}
// Maps an atomic opcode to its returnless version.
def getAtomicNoRetOp : InstrMapping {
let FilterClass = "AtomicNoRet";
let RowFields = ["NoRetOp"];
let ColFields = ["IsRet"];
let KeyCol = ["1"];
let ValueCols = [["0"]];
}
include "SIInstructions.td"
include "CIInstructions.td"
include "VIInstructions.td"