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

1715 lines
60 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">;
// 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 SDTBufferLoad : SDTypeProfile<1, 5,
[ // vdata
SDTCisVT<1, v4i32>, // rsrc
SDTCisVT<2, i32>, // vindex
SDTCisVT<3, i32>, // offset
SDTCisVT<4, i1>, // glc
SDTCisVT<5, i1>]>; // slc
def SIbuffer_load : SDNode <"AMDGPUISD::BUFFER_LOAD", SDTBufferLoad,
[SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
def SIbuffer_load_format : SDNode <"AMDGPUISD::BUFFER_LOAD_FORMAT", SDTBufferLoad,
[SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
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, 2, [SDTCisVT<0, iPTR>, SDTCisSameAs<0,1>, SDTCisSameAs<0,2>]>
>;
//===----------------------------------------------------------------------===//
// PatFrags for global memory operations
//===----------------------------------------------------------------------===//
defm atomic_inc_global : global_binary_atomic_op<SIatomic_inc>;
defm atomic_dec_global : global_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() == AMDGPUASI.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() == AMDGPUASI.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);
}]>;
def lshr_rev : PatFrag <
(ops node:$src1, node:$src0),
(srl $src0, $src1)
>;
def ashr_rev : PatFrag <
(ops node:$src1, node:$src0),
(sra $src0, $src1)
>;
def lshl_rev : PatFrag <
(ops node:$src1, node:$src0),
(shl $src0, $src1)
>;
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>;
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);
}]>;
def frameindex_to_targetframeindex : SDNodeXForm<frameindex, [{
auto FI = cast<FrameIndexSDNode>(N);
return CurDAG->getTargetFrameIndex(FI->getIndex(), 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 SIMM16bit : PatLeaf <(imm),
[{return isInt<16>(N->getSExtValue());}]
>;
class InlineImm <ValueType vt> : PatLeaf <(vt imm), [{
return isInlineImmediate(N);
}]>;
class InlineFPImm <ValueType vt> : PatLeaf <(vt fpimm), [{
return isInlineImmediate(N);
}]>;
class VGPRImm <dag frag> : PatLeaf<frag, [{
if (Subtarget->getGeneration() < SISubtarget::SOUTHERN_ISLANDS) {
return false;
}
const SIRegisterInfo *SIRI =
static_cast<const SIRegisterInfo *>(Subtarget->getRegisterInfo());
unsigned Limit = 0;
for (SDNode::use_iterator U = N->use_begin(), E = SDNode::use_end();
Limit < 10 && U != E; ++U, ++Limit) {
const TargetRegisterClass *RC = getOperandRegClass(*U, U.getOperandNo());
// If the register class is unknown, it could be an unknown
// register class that needs to be an SGPR, e.g. an inline asm
// constraint
if (!RC || SIRI->isSGPRClass(RC))
return false;
}
return Limit < 10;
}]>;
def NegateImm : SDNodeXForm<imm, [{
return CurDAG->getConstant(-N->getSExtValue(), SDLoc(N), MVT::i32);
}]>;
// TODO: When FP inline imm values work?
def NegSubInlineConst32 : ImmLeaf<i32, [{
return Imm < -16 && Imm >= -64;
}], NegateImm>;
def NegSubInlineConst16 : ImmLeaf<i16, [{
return Imm < -16 && Imm >= -64;
}], NegateImm>;
//===----------------------------------------------------------------------===//
// Custom Operands
//===----------------------------------------------------------------------===//
def SoppBrTarget : AsmOperandClass {
let Name = "SoppBrTarget";
let ParserMethod = "parseSOppBrTarget";
}
def sopp_brtarget : Operand<OtherVT> {
let EncoderMethod = "getSOPPBrEncoding";
let DecoderMethod = "decodeSoppBrTarget";
let OperandType = "OPERAND_PCREL";
let ParserMatchClass = SoppBrTarget;
}
def si_ga : Operand<iPTR>;
def InterpSlotMatchClass : AsmOperandClass {
let Name = "InterpSlot";
let PredicateMethod = "isInterpSlot";
let ParserMethod = "parseInterpSlot";
let RenderMethod = "addImmOperands";
}
def InterpSlot : Operand<i32> {
let PrintMethod = "printInterpSlot";
let ParserMatchClass = InterpSlotMatchClass;
let OperandType = "OPERAND_IMMEDIATE";
}
def AttrMatchClass : AsmOperandClass {
let Name = "Attr";
let PredicateMethod = "isInterpAttr";
let ParserMethod = "parseInterpAttr";
let RenderMethod = "addImmOperands";
}
// It appears to be necessary to create a separate operand for this to
// be able to parse attr<num> with no space.
def Attr : Operand<i32> {
let PrintMethod = "printInterpAttr";
let ParserMatchClass = AttrMatchClass;
let OperandType = "OPERAND_IMMEDIATE";
}
def AttrChanMatchClass : AsmOperandClass {
let Name = "AttrChan";
let PredicateMethod = "isAttrChan";
let RenderMethod = "addImmOperands";
}
def AttrChan : Operand<i32> {
let PrintMethod = "printInterpAttrChan";
let ParserMatchClass = AttrChanMatchClass;
let OperandType = "OPERAND_IMMEDIATE";
}
def SendMsgMatchClass : AsmOperandClass {
let Name = "SendMsg";
let PredicateMethod = "isSendMsg";
let ParserMethod = "parseSendMsgOp";
let RenderMethod = "addImmOperands";
}
def SwizzleMatchClass : AsmOperandClass {
let Name = "Swizzle";
let PredicateMethod = "isSwizzle";
let ParserMethod = "parseSwizzleOp";
let RenderMethod = "addImmOperands";
let IsOptional = 1;
}
def ExpTgtMatchClass : AsmOperandClass {
let Name = "ExpTgt";
let PredicateMethod = "isExpTgt";
let ParserMethod = "parseExpTgt";
let RenderMethod = "printExpTgt";
}
def SendMsgImm : Operand<i32> {
let PrintMethod = "printSendMsg";
let ParserMatchClass = SendMsgMatchClass;
}
def SwizzleImm : Operand<i16> {
let PrintMethod = "printSwizzle";
let ParserMatchClass = SwizzleMatchClass;
}
def SWaitMatchClass : AsmOperandClass {
let Name = "SWaitCnt";
let RenderMethod = "addImmOperands";
let ParserMethod = "parseSWaitCntOps";
}
def VReg32OrOffClass : AsmOperandClass {
let Name = "VReg32OrOff";
let ParserMethod = "parseVReg32OrOff";
}
def WAIT_FLAG : Operand <i32> {
let ParserMatchClass = SWaitMatchClass;
let PrintMethod = "printWaitFlag";
}
include "SIInstrFormats.td"
include "VIInstrFormats.td"
// ===----------------------------------------------------------------------===//
// ExpSrc* Special cases for exp src operands which are printed as
// "off" depending on en operand.
// ===----------------------------------------------------------------------===//
def ExpSrc0 : RegisterOperand<VGPR_32> {
let PrintMethod = "printExpSrc0";
let ParserMatchClass = VReg32OrOffClass;
}
def ExpSrc1 : RegisterOperand<VGPR_32> {
let PrintMethod = "printExpSrc1";
let ParserMatchClass = VReg32OrOffClass;
}
def ExpSrc2 : RegisterOperand<VGPR_32> {
let PrintMethod = "printExpSrc2";
let ParserMatchClass = VReg32OrOffClass;
}
def ExpSrc3 : RegisterOperand<VGPR_32> {
let PrintMethod = "printExpSrc3";
let ParserMatchClass = VReg32OrOffClass;
}
class SDWA9Src : RegisterOperand<VS_32> {
let OperandNamespace = "AMDGPU";
let OperandType = "OPERAND_SDWA9_SRC";
let EncoderMethod = "getSDWA9SrcEncoding";
}
def SDWA9Src32 : SDWA9Src {
let DecoderMethod = "decodeSDWA9Src32";
}
def SDWA9Src16 : SDWA9Src {
let DecoderMethod = "decodeSDWA9Src16";
}
def SDWA9VopcDst : VOPDstOperand<SReg_64> {
let OperandNamespace = "AMDGPU";
let OperandType = "OPERAND_SDWA9_VOPC_DST";
let EncoderMethod = "getSDWA9VopcDstEncoding";
let DecoderMethod = "decodeSDWA9VopcDst";
}
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 NamedOperandU12<string Name, AsmOperandClass MatchClass> : Operand<i16> {
let PrintMethod = "print"#Name;
let ParserMatchClass = MatchClass;
}
class NamedOperandU16<string Name, AsmOperandClass MatchClass> : Operand<i16> {
let PrintMethod = "print"#Name;
let ParserMatchClass = MatchClass;
}
class NamedOperandS13<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;
}
class NamedOperandU32Default0<string Name, AsmOperandClass MatchClass> :
OperandWithDefaultOps<i32, (ops (i32 0))> {
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_u12 : NamedOperandU12<"Offset", NamedMatchClass<"OffsetU12">>;
def offset_s13 : NamedOperandS13<"Offset", NamedMatchClass<"OffsetS13">>;
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 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 exp_compr : NamedOperandBit<"ExpCompr", NamedMatchClass<"ExpCompr">>;
def exp_vm : NamedOperandBit<"ExpVM", NamedMatchClass<"ExpVM">>;
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 op_sel : NamedOperandU32Default0<"OpSel", NamedMatchClass<"OpSel">>;
def op_sel_hi : NamedOperandU32Default0<"OpSelHi", NamedMatchClass<"OpSelHi">>;
def neg_lo : NamedOperandU32Default0<"NegLo", NamedMatchClass<"NegLo">>;
def neg_hi : NamedOperandU32Default0<"NegHi", NamedMatchClass<"NegHi">>;
def hwreg : NamedOperandU16<"Hwreg", NamedMatchClass<"Hwreg", 0>>;
def exp_tgt : NamedOperandU8<"ExpTgt", NamedMatchClass<"ExpTgt", 0>> {
}
} // End OperandType = "OPERAND_IMMEDIATE"
class KImmMatchClass<int size> : AsmOperandClass {
let Name = "KImmFP"#size;
let PredicateMethod = "isKImmFP"#size;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
let ParserMethod = "parseImm";
let RenderMethod = "addKImmFP"#size#"Operands";
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
}
class kimmOperand<ValueType vt> : Operand<vt> {
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
let OperandNamespace = "AMDGPU";
let OperandType = "OPERAND_KIMM"#vt.Size;
let PrintMethod = "printU"#vt.Size#"ImmOperand";
let ParserMatchClass = !cast<AsmOperandClass>("KImmFP"#vt.Size#"MatchClass");
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
}
// 32-bit VALU immediate operand that uses the constant bus.
def KImmFP32MatchClass : KImmMatchClass<32>;
def f32kimm : kimmOperand<i32>;
// 32-bit VALU immediate operand with a 16-bit value that uses the
// constant bus.
def KImmFP16MatchClass : KImmMatchClass<16>;
def f16kimm : kimmOperand<i16>;
def VOPDstS64 : VOPDstOperand <SReg_64>;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
class FPInputModsMatchClass <int opSize> : AsmOperandClass {
let Name = "RegOrImmWithFP"#opSize#"InputMods";
let ParserMethod = "parseRegOrImmWithFPInputMods";
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
let PredicateMethod = "isRegOrImmWithFP"#opSize#"InputMods";
}
def FP16InputModsMatchClass : FPInputModsMatchClass<16>;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
def FP32InputModsMatchClass : FPInputModsMatchClass<32>;
def FP64InputModsMatchClass : FPInputModsMatchClass<64>;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
class InputMods <AsmOperandClass matchClass> : Operand <i32> {
let OperandNamespace = "AMDGPU";
let OperandType = "OPERAND_INPUT_MODS";
let ParserMatchClass = matchClass;
}
class FPInputMods <FPInputModsMatchClass matchClass> : InputMods <matchClass> {
let PrintMethod = "printOperandAndFPInputMods";
}
def FP16InputMods : FPInputMods<FP16InputModsMatchClass>;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
def FP32InputMods : FPInputMods<FP32InputModsMatchClass>;
def FP64InputMods : FPInputMods<FP64InputModsMatchClass>;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
class IntInputModsMatchClass <int opSize> : AsmOperandClass {
let Name = "RegOrImmWithInt"#opSize#"InputMods";
let ParserMethod = "parseRegOrImmWithIntInputMods";
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
let PredicateMethod = "isRegOrImmWithInt"#opSize#"InputMods";
}
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
def Int32InputModsMatchClass : IntInputModsMatchClass<32>;
def Int64InputModsMatchClass : IntInputModsMatchClass<64>;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
class IntInputMods <IntInputModsMatchClass matchClass> : InputMods <matchClass> {
let PrintMethod = "printOperandAndIntInputMods";
}
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
def Int32InputMods : IntInputMods<Int32InputModsMatchClass>;
def Int64InputMods : IntInputMods<Int64InputModsMatchClass>;
def FPRegInputModsMatchClass : AsmOperandClass {
let Name = "RegWithFPInputMods";
let ParserMethod = "parseRegWithFPInputMods";
let PredicateMethod = "isRegKind";
}
def FPRegInputMods : InputMods <FPRegInputModsMatchClass> {
let PrintMethod = "printOperandAndFPInputMods";
}
def FPVRegInputModsMatchClass : AsmOperandClass {
let Name = "VRegWithFPInputMods";
let ParserMethod = "parseRegWithFPInputMods";
let PredicateMethod = "isVReg";
}
def FPVRegInputMods : InputMods <FPVRegInputModsMatchClass> {
let PrintMethod = "printOperandAndFPInputMods";
}
def IntRegInputModsMatchClass : AsmOperandClass {
let Name = "RegWithIntInputMods";
let ParserMethod = "parseRegWithIntInputMods";
let PredicateMethod = "isRegKind";
}
def IntRegInputMods : InputMods <IntRegInputModsMatchClass> {
let PrintMethod = "printOperandAndIntInputMods";
}
def IntVRegInputModsMatchClass : AsmOperandClass {
let Name = "VRegWithIntInputMods";
let ParserMethod = "parseRegWithIntInputMods";
let PredicateMethod = "isVReg";
}
def IntVRegInputMods : InputMods <IntVRegInputModsMatchClass> {
let PrintMethod = "printOperandAndIntInputMods";
}
class PackedFPInputModsMatchClass <int opSize> : AsmOperandClass {
let Name = "PackedFP"#opSize#"InputMods";
let ParserMethod = "parseRegOrImm";
let PredicateMethod = "isRegOrImm";
// let PredicateMethod = "isPackedFP"#opSize#"InputMods";
}
class PackedIntInputModsMatchClass <int opSize> : AsmOperandClass {
let Name = "PackedInt"#opSize#"InputMods";
let ParserMethod = "parseRegOrImm";
let PredicateMethod = "isRegOrImm";
// let PredicateMethod = "isPackedInt"#opSize#"InputMods";
}
def PackedF16InputModsMatchClass : PackedFPInputModsMatchClass<16>;
def PackedI16InputModsMatchClass : PackedIntInputModsMatchClass<16>;
class PackedFPInputMods <PackedFPInputModsMatchClass matchClass> : InputMods <matchClass> {
// let PrintMethod = "printPackedFPInputMods";
}
class PackedIntInputMods <PackedIntInputModsMatchClass matchClass> : InputMods <matchClass> {
//let PrintMethod = "printPackedIntInputMods";
}
def PackedF16InputMods : PackedFPInputMods<PackedF16InputModsMatchClass>;
def PackedI16InputMods : PackedIntInputMods<PackedI16InputModsMatchClass>;
//===----------------------------------------------------------------------===//
// Complex patterns
//===----------------------------------------------------------------------===//
def DS1Addr1Offset : ComplexPattern<i32, 2, "SelectDS1Addr1Offset">;
def DS64Bit4ByteAligned : ComplexPattern<i32, 3, "SelectDS64Bit4ByteAligned">;
def MOVRELOffset : ComplexPattern<i32, 2, "SelectMOVRELOffset">;
def VOP3Mods0 : ComplexPattern<untyped, 4, "SelectVOP3Mods0">;
def VOP3Mods0Clamp : ComplexPattern<untyped, 3, "SelectVOP3Mods0Clamp">;
def VOP3Mods0Clamp0OMod : ComplexPattern<untyped, 4, "SelectVOP3Mods0Clamp0OMod">;
def VOP3Mods : ComplexPattern<untyped, 2, "SelectVOP3Mods">;
def VOP3NoMods : ComplexPattern<untyped, 1, "SelectVOP3NoMods">;
// VOP3Mods, but the input source is known to never be NaN.
def VOP3Mods_nnan : ComplexPattern<fAny, 2, "SelectVOP3Mods_NNaN">;
def VOP3OMods : ComplexPattern<untyped, 3, "SelectVOP3OMods">;
def VOP3PMods : ComplexPattern<untyped, 2, "SelectVOP3PMods">;
def VOP3PMods0 : ComplexPattern<untyped, 3, "SelectVOP3PMods0">;
//===----------------------------------------------------------------------===//
// SI assembler operands
//===----------------------------------------------------------------------===//
def SIOperand {
int ZERO = 0x80;
int VCC = 0x6A;
int FLAT_SCR = 0x68;
}
// This should be kept in sync with SISrcMods enum
def SRCMODS {
int NONE = 0;
int NEG = 1;
int ABS = 2;
int NEG_ABS = 3;
int NEG_HI = ABS;
int OP_SEL_0 = 4;
int OP_SEL_1 = 8;
}
def DSTCLAMP {
int NONE = 0;
int ENABLE = 1;
}
def DSTOMOD {
int NONE = 0;
}
def TRAPID{
int LLVM_TRAP = 2;
int LLVM_DEBUG_TRAP = 3;
}
//===----------------------------------------------------------------------===//
//
// 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 EXP_Helper<bit done, SDPatternOperator node = null_frag> : EXPCommon<
(outs),
(ins exp_tgt:$tgt,
ExpSrc0:$src0, ExpSrc1:$src1, ExpSrc2:$src2, ExpSrc3:$src3,
exp_vm:$vm, exp_compr:$compr, i8imm:$en),
"exp$tgt $src0, $src1, $src2, $src3"#!if(done, " done", "")#"$compr$vm",
[(node (i8 timm:$tgt), (i8 timm:$en),
f32:$src0, f32:$src1, f32:$src2, f32:$src3,
(i1 timm:$compr), (i1 timm:$vm))]> {
let AsmMatchConverter = "cvtExp";
}
// Split EXP instruction into EXP and EXP_DONE so we can set
// mayLoad for done=1.
multiclass EXP_m<bit done, SDPatternOperator node> {
let mayLoad = done in {
let isPseudo = 1, isCodeGenOnly = 1 in {
def "" : EXP_Helper<done, node>,
SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.NONE>;
}
let done = done in {
def _si : EXP_Helper<done>,
SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.SI>,
EXPe {
let AssemblerPredicates = [isSICI];
let DecoderNamespace = "SICI";
let DisableDecoder = DisableSIDecoder;
}
def _vi : EXP_Helper<done>,
SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.VI>,
EXPe_vi {
let AssemblerPredicates = [isVI];
let DecoderNamespace = "VI";
let DisableDecoder = DisableVIDecoder;
}
}
[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
}
}
//===----------------------------------------------------------------------===//
// 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, 128), VOPDstOperand<VReg_128>,
!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 the destination of VOP[12C]
// instructions with GFX9 SDWA extension
class getSDWA9DstForVT<ValueType VT> {
RegisterOperand ret = !if(!eq(VT.Size, 1),
SDWA9VopcDst, // VOPC
VOPDstOperand<VGPR_32>); // VOP1/2 32-bit dst
}
// Returns the register class to use for source 0 of VOP[12C]
// instructions for the given VT.
class getVOPSrc0ForVT<ValueType VT> {
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
bit isFP = !if(!eq(VT.Value, f16.Value), 1,
!if(!eq(VT.Value, v2f16.Value), 1,
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
!if(!eq(VT.Value, f32.Value), 1,
!if(!eq(VT.Value, f64.Value), 1,
0))));
RegisterOperand ret =
!if(isFP,
!if(!eq(VT.Size, 64),
VSrc_f64,
!if(!eq(VT.Value, f16.Value),
VSrc_f16,
!if(!eq(VT.Value, v2f16.Value),
VCSrc_v2f16,
VSrc_f32
)
)
),
!if(!eq(VT.Size, 64),
VSrc_b64,
!if(!eq(VT.Value, i16.Value),
VSrc_b16,
!if(!eq(VT.Value, v2i16.Value),
VCSrc_v2b16,
VSrc_b32
)
)
)
);
}
// Returns the vreg register class to use for source operand given VT
class getVregSrcForVT<ValueType VT> {
RegisterClass ret = !if(!eq(VT.Size, 128), VReg_128,
!if(!eq(VT.Size, 64), VReg_64, VGPR_32));
}
class getSDWA9SrcForVT <ValueType VT> {
RegisterOperand ret = !if(!eq(VT.Size, 16), SDWA9Src16, SDWA9Src32);
}
// Returns the register class to use for sources of VOP3 instructions for the
// given VT.
class getVOP3SrcForVT<ValueType VT> {
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
bit isFP = !if(!eq(VT.Value, f16.Value), 1,
!if(!eq(VT.Value, v2f16.Value), 1,
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
!if(!eq(VT.Value, f32.Value), 1,
!if(!eq(VT.Value, f64.Value), 1,
0))));
RegisterOperand ret =
!if(!eq(VT.Size, 128),
VSrc_128,
!if(!eq(VT.Size, 64),
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
!if(isFP,
VCSrc_f64,
VCSrc_b64),
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
!if(!eq(VT.Value, i1.Value),
SCSrc_b64,
!if(isFP,
!if(!eq(VT.Value, f16.Value),
VCSrc_f16,
!if(!eq(VT.Value, v2f16.Value),
VCSrc_v2f16,
VCSrc_f32
)
),
!if(!eq(VT.Value, i16.Value),
VCSrc_b16,
!if(!eq(VT.Value, v2i16.Value),
VCSrc_v2b16,
VCSrc_b32
)
)
)
)
)
);
}
// Returns 1 if the source arguments have modifiers, 0 if they do not.
// XXX - do f16 instructions?
class isFloatType<ValueType SrcVT> {
bit ret =
!if(!eq(SrcVT.Value, f16.Value), 1,
!if(!eq(SrcVT.Value, f32.Value), 1,
!if(!eq(SrcVT.Value, f64.Value), 1,
!if(!eq(SrcVT.Value, v2f16.Value), 1,
0))));
}
class isIntType<ValueType SrcVT> {
bit ret =
!if(!eq(SrcVT.Value, i16.Value), 1,
!if(!eq(SrcVT.Value, i32.Value), 1,
!if(!eq(SrcVT.Value, i64.Value), 1,
0)));
}
class isPackedType<ValueType SrcVT> {
bit ret =
!if(!eq(SrcVT.Value, v2i16.Value), 1,
!if(!eq(SrcVT.Value, v2f16.Value), 1, 0)
);
}
// Float or packed int
class isModifierType<ValueType SrcVT> {
bit ret =
!if(!eq(SrcVT.Value, f16.Value), 1,
!if(!eq(SrcVT.Value, f32.Value), 1,
!if(!eq(SrcVT.Value, f64.Value), 1,
!if(!eq(SrcVT.Value, v2f16.Value), 1,
!if(!eq(SrcVT.Value, v2i16.Value), 1,
0)))));
}
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
// Return type of input modifiers operand for specified input operand
class getSrcMod <ValueType VT> {
bit isFP = !if(!eq(VT.Value, f16.Value), 1,
!if(!eq(VT.Value, f32.Value), 1,
!if(!eq(VT.Value, f64.Value), 1,
0)));
bit isPacked = isPackedType<VT>.ret;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
Operand ret = !if(!eq(VT.Size, 64),
!if(isFP, FP64InputMods, Int64InputMods),
!if(isFP,
!if(!eq(VT.Value, f16.Value),
FP16InputMods,
FP32InputMods
),
Int32InputMods)
);
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
}
// Return type of input modifiers operand specified input operand for SDWA/DPP
class getSrcModExt <ValueType VT> {
bit isFP = !if(!eq(VT.Value, f16.Value), 1,
!if(!eq(VT.Value, f32.Value), 1,
!if(!eq(VT.Value, f64.Value), 1,
0)));
Operand ret = !if(isFP, FPVRegInputMods, IntVRegInputMods);
}
// Return type of input modifiers operand specified input operand for SDWA 9
class getSrcModSDWA9 <ValueType VT> {
bit isFP = !if(!eq(VT.Value, f16.Value), 1,
!if(!eq(VT.Value, f32.Value), 1,
!if(!eq(VT.Value, f64.Value), 1,
0)));
Operand ret = !if(isFP, FPRegInputMods, IntRegInputMods);
}
// 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, bit HasOMod,
Operand Src0Mod, Operand Src1Mod, Operand Src2Mod> {
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
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
clampmod:$clamp, omod:$omod)
/* else */,
// VOP1 without modifiers
(ins Src0RC:$src0)
/* endif */ ),
!if (!eq(NumSrcArgs, 2),
!if (!eq(HasModifiers, 1),
// VOP 2 with modifiers
!if( !eq(HasOMod, 1),
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp, omod:$omod),
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp))
/* else */,
// VOP2 without modifiers
(ins Src0RC:$src0, Src1RC:$src1)
/* endif */ )
/* NumSrcArgs == 3 */,
!if (!eq(HasModifiers, 1),
// VOP3 with modifiers
!if (!eq(HasOMod, 1),
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
Src2Mod:$src2_modifiers, Src2RC:$src2,
clampmod:$clamp, omod:$omod),
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
Src2Mod:$src2_modifiers, Src2RC:$src2,
clampmod:$clamp))
/* else */,
// VOP3 without modifiers
(ins Src0RC:$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 */ ))));
}
/// XXX - src1 may only allow VGPRs?
// The modifiers (except clamp) are dummy operands for the benefit of
// printing and parsing. They defer their values to looking at the
// srcN_modifiers for what to print.
class getInsVOP3P <RegisterOperand Src0RC, RegisterOperand Src1RC,
RegisterOperand Src2RC, int NumSrcArgs,
bit HasClamp,
Operand Src0Mod, Operand Src1Mod, Operand Src2Mod> {
dag ret = !if (!eq(NumSrcArgs, 2),
!if (HasClamp,
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp,
op_sel:$op_sel, op_sel_hi:$op_sel_hi,
neg_lo:$neg_lo, neg_hi:$neg_hi),
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
op_sel:$op_sel, op_sel_hi:$op_sel_hi,
neg_lo:$neg_lo, neg_hi:$neg_hi)),
// else NumSrcArgs == 3
!if (HasClamp,
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
Src2Mod:$src2_modifiers, Src2RC:$src2,
clampmod:$clamp,
op_sel:$op_sel, op_sel_hi:$op_sel_hi,
neg_lo:$neg_lo, neg_hi:$neg_hi),
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
Src2Mod:$src2_modifiers, Src2RC:$src2,
op_sel:$op_sel, op_sel_hi:$op_sel_hi,
neg_lo:$neg_lo, neg_hi:$neg_hi))
);
}
class getInsDPP <RegisterClass Src0RC, RegisterClass Src1RC, int NumSrcArgs,
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
bit HasModifiers, Operand Src0Mod, Operand Src1Mod> {
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
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
(ins Src0Mod:$src0_modifiers, Src0RC:$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
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$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,
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
bit HasFloatModifiers, Operand Src0Mod, Operand Src1Mod,
ValueType DstVT> {
dag ret = !if(!eq(NumSrcArgs, 0),
// VOP1 without input operands (V_NOP)
(ins),
!if(!eq(NumSrcArgs, 1),
// VOP1_SDWA
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
clampmod:$clamp, dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel),
!if(!eq(NumSrcArgs, 2),
!if(!eq(DstVT.Size, 1),
// VOPC_SDWA with modifiers
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp, src0_sel:$src0_sel, src1_sel:$src1_sel),
// VOP2_SDWA with modifiers
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp, dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel)),
(ins)/* endif */)));
}
// Ins for GFX9 SDWA
class getInsSDWA9 <RegisterOperand Src0RC, RegisterOperand Src1RC, int NumSrcArgs,
bit HasSDWAOMod, Operand Src0Mod, Operand Src1Mod,
ValueType DstVT> {
dag ret = !if(!eq(NumSrcArgs, 0),
// VOP1 without input operands (V_NOP)
(ins),
!if(!eq(NumSrcArgs, 1),
// VOP1
!if(!eq(HasSDWAOMod, 0),
// VOP1_SDWA9 without omod
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
clampmod:$clamp,
dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel),
// VOP1_SDWA9 with omod
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
clampmod:$clamp, omod:$omod,
dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel)),
!if(!eq(NumSrcArgs, 2),
!if(!eq(DstVT.Size, 1),
// VOPC_SDWA9
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
src0_sel:$src0_sel, src1_sel:$src1_sel),
// VOP2_SDWA9
!if(!eq(HasSDWAOMod, 0),
// VOP2_SDWA9 without omod
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp,
dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel),
// VOP1_SDWA9 with omod
(ins Src0Mod:$src0_modifiers, Src0RC:$src0,
Src1Mod:$src1_modifiers, Src1RC:$src1,
clampmod:$clamp, omod:$omod,
dst_sel:$dst_sel, dst_unused:$dst_unused,
src0_sel:$src0_sel, src1_sel:$src1_sel))),
(ins)/* endif */)));
}
// Outs for DPP and SDWA
class getOutsExt <bit HasDst, ValueType DstVT, RegisterOperand DstRCExt> {
dag ret = !if(HasDst,
!if(!eq(DstVT.Size, 1),
(outs), // no dst for VOPC, we use "vcc"-token as dst in SDWA VOPC instructions
(outs DstRCExt:$vdst)),
(outs)); // V_NOP
}
// Outs for GFX9 SDWA
class getOutsSDWA9 <bit HasDst, ValueType DstVT, RegisterOperand DstRCSDWA9> {
dag ret = !if(HasDst,
!if(!eq(DstVT.Size, 1),
(outs DstRCSDWA9:$sdst),
(outs DstRCSDWA9:$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 = ", $src2";
string ret = !if(HasDst, dst, "") #
!if(!eq(NumSrcArgs, 1), src0, "") #
!if(!eq(NumSrcArgs, 2), src0#src1, "") #
!if(!eq(NumSrcArgs, 3), src0#src1#src2, "");
}
// Returns the assembly string for the inputs and outputs of a VOP3
// instruction.
class getAsm64 <bit HasDst, int NumSrcArgs, bit HasModifiers,
bit HasOMod, ValueType DstVT = i32> {
string dst = !if(!eq(DstVT.Size, 1), "$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"#!if(HasOMod, "$omod", ""));
}
// Returns the assembly string for the inputs and outputs of a VOP3P
// instruction.
class getAsmVOP3P <bit HasDst, int NumSrcArgs, bit HasModifiers,
bit HasClamp, ValueType DstVT = i32> {
string dst = " $vdst";
string src0 = !if(!eq(NumSrcArgs, 1), "$src0", "$src0,");
string src1 = !if(!eq(NumSrcArgs, 1), "",
!if(!eq(NumSrcArgs, 2), " $src1",
" $src1,"));
string src2 = !if(!eq(NumSrcArgs, 3), " $src2", "");
string mods = !if(HasModifiers, "$neg_lo$neg_hi", "");
string clamp = !if(HasClamp, "$clamp", "");
// Each modifier is printed as an array of bits for each operand, so
// all operands are printed as part of src0_modifiers.
string ret = dst#", "#src0#src1#src2#"$op_sel$op_sel_hi"#mods#clamp;
}
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, ValueType DstVT = i32> {
string dst = !if(HasDst,
!if(!eq(DstVT.Size, 1),
" vcc", // use vcc token as dst for VOPC instructioins
"$vdst"),
"");
string src0 = "$src0_modifiers";
string src1 = "$src1_modifiers";
string args = !if(!eq(NumSrcArgs, 0),
"",
!if(!eq(NumSrcArgs, 1),
", "#src0#"$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 $src1_sel"
)
)
);
string ret = dst#args#sdwa;
}
class getAsmSDWA9 <bit HasDst, bit HasOMod, int NumSrcArgs,
ValueType DstVT = i32> {
string dst = !if(HasDst,
!if(!eq(DstVT.Size, 1),
"$sdst", // VOPC
"$vdst"), // VOP1/2
"");
string src0 = "$src0_modifiers";
string src1 = "$src1_modifiers";
string out_mods = !if(!eq(HasOMod, 0), "$clamp", "$clamp$omod");
string args = !if(!eq(NumSrcArgs, 0), "",
!if(!eq(NumSrcArgs, 1),
", "#src0,
", "#src0#", "#src1
)
);
string sdwa = !if(!eq(NumSrcArgs, 0), "",
!if(!eq(NumSrcArgs, 1),
out_mods#" $dst_sel $dst_unused $src0_sel",
!if(!eq(DstVT.Size, 1),
" $src0_sel $src1_sel", // No dst_sel, dst_unused and output modifiers for VOPC
out_mods#" $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 BitOr<bit a, bit b> {
bit ret = !if(a, 1, !if(b, 1, 0));
}
class BitAnd<bit a, bit b> {
bit ret = !if(a, !if(b, 1, 0), 0);
}
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 DstRCSDWA9 = getSDWA9DstForVT<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 RegisterOperand Src0SDWA9 = getSDWA9SrcForVT<Src0VT>.ret;
field RegisterOperand Src1SDWA9 = getSDWA9SrcForVT<Src0VT>.ret;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
field Operand Src0Mod = getSrcMod<Src0VT>.ret;
field Operand Src1Mod = getSrcMod<Src1VT>.ret;
field Operand Src2Mod = getSrcMod<Src2VT>.ret;
field Operand Src0ModDPP = getSrcModExt<Src0VT>.ret;
field Operand Src1ModDPP = getSrcModExt<Src1VT>.ret;
field Operand Src0ModSDWA = getSrcModExt<Src0VT>.ret;
field Operand Src1ModSDWA = getSrcModExt<Src1VT>.ret;
field Operand Src0ModSDWA9 = getSrcModSDWA9<Src0VT>.ret;
field Operand Src1ModSDWA9 = getSrcModSDWA9<Src1VT>.ret;
field bit HasDst = !if(!eq(DstVT.Value, untyped.Value), 0, 1);
field bit HasDst32 = HasDst;
field bit EmitDst = HasDst; // force dst encoding, see v_movreld_b32 special case
field int NumSrcArgs = getNumSrcArgs<Src0VT, Src1VT, Src2VT>.ret;
field bit HasSrc0 = !if(!eq(Src0VT.Value, untyped.Value), 0, 1);
field bit HasSrc1 = !if(!eq(Src1VT.Value, untyped.Value), 0, 1);
field bit HasSrc2 = !if(!eq(Src2VT.Value, untyped.Value), 0, 1);
// TODO: Modifiers logic is somewhat adhoc here, to be refined later
field bit HasModifiers = isModifierType<Src0VT>.ret;
field bit HasSrc0FloatMods = isFloatType<Src0VT>.ret;
field bit HasSrc1FloatMods = isFloatType<Src1VT>.ret;
field bit HasSrc2FloatMods = isFloatType<Src2VT>.ret;
field bit HasSrc0IntMods = isIntType<Src0VT>.ret;
field bit HasSrc1IntMods = isIntType<Src1VT>.ret;
field bit HasSrc2IntMods = isIntType<Src2VT>.ret;
field bit HasSrc0Mods = HasModifiers;
field bit HasSrc1Mods = !if(HasModifiers, BitOr<HasSrc1FloatMods, HasSrc1IntMods>.ret, 0);
field bit HasSrc2Mods = !if(HasModifiers, BitOr<HasSrc2FloatMods, HasSrc2IntMods>.ret, 0);
field bit HasClamp = HasModifiers;
field bit HasSDWAClamp = EmitDst;
field bit HasFPClamp = BitAnd<isFloatType<DstVT>.ret, HasClamp>.ret;
field bit IsPacked = isPackedType<Src0VT>.ret;
field bit HasOpSel = IsPacked;
field bit HasOMod = !if(HasOpSel, 0, HasModifiers);
field bit HasSDWAOMod = isFloatType<DstVT>.ret;
field bit HasExt = getHasExt<NumSrcArgs, DstVT, Src0VT, Src1VT>.ret;
field bit HasSDWA9 = HasExt;
field Operand Src0PackedMod = !if(HasSrc0FloatMods, PackedF16InputMods, PackedI16InputMods);
field Operand Src1PackedMod = !if(HasSrc1FloatMods, PackedF16InputMods, PackedI16InputMods);
field Operand Src2PackedMod = !if(HasSrc2FloatMods, PackedF16InputMods, PackedI16InputMods);
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, DstRCSDWA>.ret;
field dag OutsSDWA9 = getOutsSDWA9<HasDst, DstVT, DstRCSDWA9>.ret;
field dag Ins32 = getIns32<Src0RC32, Src1RC32, NumSrcArgs>.ret;
field dag Ins64 = getIns64<Src0RC64, Src1RC64, Src2RC64, NumSrcArgs,
HasModifiers, HasOMod, Src0Mod, Src1Mod,
Src2Mod>.ret;
field dag InsVOP3P = getInsVOP3P<Src0RC64, Src1RC64, Src2RC64,
NumSrcArgs, HasClamp,
Src0PackedMod, Src1PackedMod, Src2PackedMod>.ret;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
field dag InsDPP = getInsDPP<Src0DPP, Src1DPP, NumSrcArgs,
HasModifiers, Src0ModDPP, Src1ModDPP>.ret;
AMDGPU] Assembler: better support for immediate literals in assembler. Summary: Prevously assembler parsed all literals as either 32-bit integers or 32-bit floating-point values. Because of this we couldn't support f64 literals. E.g. in instruction "v_fract_f64 v[0:1], 0.5", literal 0.5 was encoded as 32-bit literal 0x3f000000, which is incorrect and will be interpreted as 3.0517578125E-5 instead of 0.5. Correct encoding is inline constant 240 (optimal) or 32-bit literal 0x3FE00000 at least. With this change the way immediate literals are parsed is changed. All literals are always parsed as 64-bit values either integer or floating-point. Then we convert parsed literals to correct form based on information about type of operand parsed (was literal floating or binary) and type of expected instruction operands (is this f32/64 or b32/64 instruction). Here are rules how we convert literals: - We parsed fp literal: - Instruction expects 64-bit operand: - If parsed literal is inlinable (e.g. v_fract_f64_e32 v[0:1], 0.5) - then we do nothing this literal - Else if literal is not-inlinable but instruction requires to inline it (e.g. this is e64 encoding, v_fract_f64_e64 v[0:1], 1.5) - report error - Else literal is not-inlinable but we can encode it as additional 32-bit literal constant - If instruction expect fp operand type (f64) - Check if low 32 bits of literal are zeroes (e.g. v_fract_f64 v[0:1], 1.5) - If so then do nothing - Else (e.g. v_fract_f64 v[0:1], 3.1415) - report warning that low 32 bits will be set to zeroes and precision will be lost - set low 32 bits of literal to zeroes - Instruction expects integer operand type (e.g. s_mov_b64_e32 s[0:1], 1.5) - report error as it is unclear how to encode this literal - Instruction expects 32-bit operand: - Convert parsed 64 bit fp literal to 32 bit fp. Allow lose of precision but not overflow or underflow - Is this literal inlinable and are we required to inline literal (e.g. v_trunc_f32_e64 v0, 0.5) - do nothing - Else report error - Do nothing. We can encode any other 32-bit fp literal (e.g. v_trunc_f32 v0, 10000000.0) - Parsed binary literal: - Is this literal inlinable (e.g. v_trunc_f32_e32 v0, 35) - do nothing - Else, are we required to inline this literal (e.g. v_trunc_f32_e64 v0, 35) - report error - Else, literal is not-inlinable and we are not required to inline it - Are high 32 bit of literal zeroes or same as sign bit (32 bit) - do nothing (e.g. v_trunc_f32 v0, 0xdeadbeef) - Else - report error (e.g. v_trunc_f32 v0, 0x123456789abcdef0) For this change it is required that we know operand types of instruction (are they f32/64 or b32/64). I added several new register operands (they extend previous register operands) and set operand types to corresponding types: ''' enum OperandType { OPERAND_REG_IMM32_INT, OPERAND_REG_IMM32_FP, OPERAND_REG_INLINE_C_INT, OPERAND_REG_INLINE_C_FP, } ''' This is not working yet: - Several tests are failing - Problems with predicate methods for inline immediates - LLVM generated assembler parts try to select e64 encoding before e32. More changes are required for several AsmOperands. Reviewers: vpykhtin, tstellarAMD Subscribers: arsenm, kzhuravl, artem.tamazov Differential Revision: https://reviews.llvm.org/D22922 llvm-svn: 281050
2016-09-09 22:44:04 +08:00
field dag InsSDWA = getInsSDWA<Src0SDWA, Src1SDWA, NumSrcArgs,
HasModifiers, Src0ModSDWA, Src1ModSDWA,
DstVT>.ret;
field dag InsSDWA9 = getInsSDWA9<Src0SDWA9, Src1SDWA9, NumSrcArgs,
HasSDWAOMod, Src0ModSDWA9, Src1ModSDWA9,
DstVT>.ret;
field string Asm32 = getAsm32<HasDst, NumSrcArgs, DstVT>.ret;
field string Asm64 = getAsm64<HasDst, NumSrcArgs, HasModifiers, HasOMod, DstVT>.ret;
field string AsmVOP3P = getAsmVOP3P<HasDst, NumSrcArgs, HasModifiers, HasClamp, DstVT>.ret;
field string AsmDPP = getAsmDPP<HasDst, NumSrcArgs, HasModifiers, DstVT>.ret;
field string AsmSDWA = getAsmSDWA<HasDst, NumSrcArgs, DstVT>.ret;
field string AsmSDWA9 = getAsmSDWA9<HasDst, HasSDWAOMod, NumSrcArgs, DstVT>.ret;
}
class VOP_NO_EXT <VOPProfile p> : VOPProfile <p.ArgVT> {
let HasExt = 0;
let HasSDWA9 = 0;
}
def VOP_F16_F16 : VOPProfile <[f16, f16, untyped, untyped]>;
def VOP_F16_I16 : VOPProfile <[f16, i16, untyped, untyped]>;
def VOP_I16_F16 : VOPProfile <[i16, f16, untyped, untyped]>;
def VOP_F16_F16_F16 : VOPProfile <[f16, f16, f16, untyped]>;
def VOP_F16_F16_I16 : VOPProfile <[f16, f16, i16, untyped]>;
def VOP_F16_F16_I32 : VOPProfile <[f16, f16, i32, untyped]>;
def VOP_I16_I16_I16 : VOPProfile <[i16, i16, i16, untyped]>;
def VOP_I16_I16_I16_I16 : VOPProfile <[i16, i16, i16, i16, untyped]>;
def VOP_F16_F16_F16_F16 : VOPProfile <[f16, f16, f16, f16, untyped]>;
def VOP_V2F16_V2F16_V2F16 : VOPProfile <[v2f16, v2f16, v2f16, untyped]>;
def VOP_V2I16_V2I16_V2I16 : VOPProfile <[v2i16, v2i16, v2i16, untyped]>;
def VOP_B32_F16_F16 : VOPProfile <[i32, f16, f16, untyped]>;
def VOP_V2F16_V2F16_V2F16_V2F16 : VOPProfile <[v2f16, v2f16, v2f16, v2f16]>;
def VOP_V2I16_V2I16_V2I16_V2I16 : VOPProfile <[v2i16, v2i16, v2i16, v2i16]>;
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_F16_F32 : VOPProfile <[f16, f32, untyped, untyped]>;
def VOP_F32_F16 : VOPProfile <[f32, f16, untyped, untyped]>;
def VOP_F32_F32_F16 : VOPProfile <[f32, f32, f16, 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]>;
def VOP_V2F16_F32_F32 : VOPProfile <[v2f16, f32, f32, untyped]>;
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_F16_F32_F16_F32 : VOPProfile <[f16, f32, f16, f32]>;
def VOP_F32_F32_F16_F16 : VOPProfile <[f32, f32, f16, f16]>;
def VOP_F32_F32_F32_F32 : VOPProfile <[f32, f32, f32, f32]>;
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]>;
def VOP_I32_F32_I32_I32 : VOPProfile <[i32, f32, i32, i32]>;
def VOP_I64_I64_I32_I64 : VOPProfile <[i64, i64, i32, i64]>;
def VOP_V4I32_I64_I32_V4I32 : VOPProfile <[v4i32, i64, i32, v4i32]>;
class Commutable_REV <string revOp, bit isOrig> {
string RevOp = revOp;
bit IsOrig = isOrig;
}
class AtomicNoRet <string noRetOp, bit isRet> {
string NoRetOp = noRetOp;
bit IsRet = isRet;
}
//===----------------------------------------------------------------------===//
// 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 instruction mappings
//===----------------------------------------------------------------------===//
// Maps an opcode in e32 form to its e64 equivalent
def getVOPe64 : InstrMapping {
let FilterClass = "VOP";
let RowFields = ["OpName"];
let ColFields = ["Size", "VOP3"];
let KeyCol = ["4", "0"];
let ValueCols = [["8", "1"]];
}
// Maps an opcode in e64 form to its e32 equivalent
def getVOPe32 : InstrMapping {
let FilterClass = "VOP";
let RowFields = ["OpName"];
let ColFields = ["Size", "VOP3"];
let KeyCol = ["8", "1"];
let ValueCols = [["4", "0"]];
}
[ADMGPU] SDWA peephole optimization pass. Summary: First iteration of SDWA peephole. This pass tries to combine several instruction into one SDWA instruction. E.g. it converts: ''' V_LSHRREV_B32_e32 %vreg0, 16, %vreg1 V_ADD_I32_e32 %vreg2, %vreg0, %vreg3 V_LSHLREV_B32_e32 %vreg4, 16, %vreg2 ''' Into: ''' V_ADD_I32_sdwa %vreg4, %vreg1, %vreg3 dst_sel:WORD_1 dst_unused:UNUSED_PAD src0_sel:WORD_1 src1_sel:DWORD ''' Pass structure: 1. Iterate over machine instruction in basic block and try to apply "SDWA patterns" to each of them. SDWA patterns match machine instruction into either source or destination SDWA operand. E.g. ''' V_LSHRREV_B32_e32 %vreg0, 16, %vreg1''' is matched to source SDWA operand '''%vreg1 src_sel:WORD_1'''. 2. Iterate over found SDWA operands and find instruction that could be potentially coverted into SDWA. E.g. for source SDWA operand potential instruction are all instruction in this basic block that uses '''%vreg0''' 3. Iterate over all potential instructions and check if they can be converted into SDWA. 4. Convert instructions to SDWA. This review contains basic implementation of SDWA peephole pass. This pass requires additional testing fot both correctness and performance (no performance testing done). There are several ways this pass can be improved: 1. Make this pass work on whole function not only basic block. As I can see this can be done right now without changes to pass. 2. Introduce more SDWA patterns 3. Introduce mnemonics to limit when SDWA patterns should apply Reviewers: vpykhtin, alex-t, arsenm, rampitec Subscribers: wdng, nhaehnle, mgorny Differential Revision: https://reviews.llvm.org/D30038 llvm-svn: 298365
2017-03-21 20:51:34 +08:00
// Maps ordinary instructions to their SDWA counterparts
def getSDWAOp : InstrMapping {
let FilterClass = "VOP";
let RowFields = ["OpName"];
let ColFields = ["AsmVariantName"];
let KeyCol = ["Default"];
let ValueCols = [["SDWA"]];
}
// Maps ordinary instructions to their SDWA GFX9 counterparts
def getSDWA9Op : InstrMapping {
let FilterClass = "VOP";
let RowFields = ["OpName"];
let ColFields = ["AsmVariantName"];
let KeyCol = ["Default"];
let ValueCols = [["SDWA9"]];
}
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 = "Commutable_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 = "Commutable_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)]];
}
// Get equivalent SOPK instruction.
def getSOPKOp : InstrMapping {
let FilterClass = "SOPKInstTable";
let RowFields = ["BaseCmpOp"];
let ColFields = ["IsSOPK"];
let KeyCol = ["0"];
let ValueCols = [["1"]];
}
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 "DSInstructions.td"
include "MIMGInstructions.td"