forked from OSchip/llvm-project
909 lines
29 KiB
TableGen
909 lines
29 KiB
TableGen
//===-- AMDGPUInstructions.td - Common instruction defs ---*- tablegen -*-===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file contains instruction defs that are common to all hw codegen
|
|
// targets.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class AddressSpacesImpl {
|
|
int Flat = 0;
|
|
int Global = 1;
|
|
int Region = 2;
|
|
int Local = 3;
|
|
int Constant = 4;
|
|
int Private = 5;
|
|
}
|
|
|
|
def AddrSpaces : AddressSpacesImpl;
|
|
|
|
|
|
class AMDGPUInst <dag outs, dag ins, string asm = "",
|
|
list<dag> pattern = []> : Instruction {
|
|
field bit isRegisterLoad = 0;
|
|
field bit isRegisterStore = 0;
|
|
|
|
let Namespace = "AMDGPU";
|
|
let OutOperandList = outs;
|
|
let InOperandList = ins;
|
|
let AsmString = asm;
|
|
let Pattern = pattern;
|
|
let Itinerary = NullALU;
|
|
|
|
// SoftFail is a field the disassembler can use to provide a way for
|
|
// instructions to not match without killing the whole decode process. It is
|
|
// mainly used for ARM, but Tablegen expects this field to exist or it fails
|
|
// to build the decode table.
|
|
field bits<64> SoftFail = 0;
|
|
|
|
let DecoderNamespace = Namespace;
|
|
|
|
let TSFlags{63} = isRegisterLoad;
|
|
let TSFlags{62} = isRegisterStore;
|
|
}
|
|
|
|
class AMDGPUShaderInst <dag outs, dag ins, string asm = "",
|
|
list<dag> pattern = []> : AMDGPUInst<outs, ins, asm, pattern> {
|
|
|
|
field bits<32> Inst = 0xffffffff;
|
|
}
|
|
|
|
//===---------------------------------------------------------------------===//
|
|
// Return instruction
|
|
//===---------------------------------------------------------------------===//
|
|
|
|
class ILFormat<dag outs, dag ins, string asmstr, list<dag> pattern>
|
|
: Instruction {
|
|
|
|
let Namespace = "AMDGPU";
|
|
dag OutOperandList = outs;
|
|
dag InOperandList = ins;
|
|
let Pattern = pattern;
|
|
let AsmString = !strconcat(asmstr, "\n");
|
|
let isPseudo = 1;
|
|
let Itinerary = NullALU;
|
|
bit hasIEEEFlag = 0;
|
|
bit hasZeroOpFlag = 0;
|
|
let mayLoad = 0;
|
|
let mayStore = 0;
|
|
let hasSideEffects = 0;
|
|
let isCodeGenOnly = 1;
|
|
}
|
|
|
|
def TruePredicate : Predicate<"true">;
|
|
|
|
class PredicateControl {
|
|
Predicate SubtargetPredicate = TruePredicate;
|
|
list<Predicate> AssemblerPredicates = [];
|
|
Predicate AssemblerPredicate = TruePredicate;
|
|
Predicate WaveSizePredicate = TruePredicate;
|
|
list<Predicate> OtherPredicates = [];
|
|
list<Predicate> Predicates = !listconcat([SubtargetPredicate,
|
|
AssemblerPredicate,
|
|
WaveSizePredicate],
|
|
AssemblerPredicates,
|
|
OtherPredicates);
|
|
}
|
|
class AMDGPUPat<dag pattern, dag result> : Pat<pattern, result>,
|
|
PredicateControl;
|
|
|
|
def FP16Denormals : Predicate<"Subtarget->hasFP16Denormals()">;
|
|
def FP32Denormals : Predicate<"Subtarget->hasFP32Denormals()">;
|
|
def FP64Denormals : Predicate<"Subtarget->hasFP64Denormals()">;
|
|
def NoFP16Denormals : Predicate<"!Subtarget->hasFP16Denormals()">;
|
|
def NoFP32Denormals : Predicate<"!Subtarget->hasFP32Denormals()">;
|
|
def NoFP64Denormals : Predicate<"!Subtarget->hasFP64Denormals()">;
|
|
def UnsafeFPMath : Predicate<"TM.Options.UnsafeFPMath">;
|
|
def FMA : Predicate<"Subtarget->hasFMA()">;
|
|
|
|
def InstFlag : OperandWithDefaultOps <i32, (ops (i32 0))>;
|
|
|
|
def u16ImmTarget : AsmOperandClass {
|
|
let Name = "U16Imm";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
def s16ImmTarget : AsmOperandClass {
|
|
let Name = "S16Imm";
|
|
let RenderMethod = "addImmOperands";
|
|
}
|
|
|
|
let OperandType = "OPERAND_IMMEDIATE" in {
|
|
|
|
def u32imm : Operand<i32> {
|
|
let PrintMethod = "printU32ImmOperand";
|
|
}
|
|
|
|
def u16imm : Operand<i16> {
|
|
let PrintMethod = "printU16ImmOperand";
|
|
let ParserMatchClass = u16ImmTarget;
|
|
}
|
|
|
|
def s16imm : Operand<i16> {
|
|
let PrintMethod = "printU16ImmOperand";
|
|
let ParserMatchClass = s16ImmTarget;
|
|
}
|
|
|
|
def u8imm : Operand<i8> {
|
|
let PrintMethod = "printU8ImmOperand";
|
|
}
|
|
|
|
} // End OperandType = "OPERAND_IMMEDIATE"
|
|
|
|
//===--------------------------------------------------------------------===//
|
|
// Custom Operands
|
|
//===--------------------------------------------------------------------===//
|
|
def brtarget : Operand<OtherVT>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Misc. PatFrags
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class HasOneUseUnaryOp<SDPatternOperator op> : PatFrag<
|
|
(ops node:$src0),
|
|
(op $src0),
|
|
[{ return N->hasOneUse(); }]
|
|
>;
|
|
|
|
class HasOneUseBinOp<SDPatternOperator op> : PatFrag<
|
|
(ops node:$src0, node:$src1),
|
|
(op $src0, $src1),
|
|
[{ return N->hasOneUse(); }]
|
|
>;
|
|
|
|
class HasOneUseTernaryOp<SDPatternOperator op> : PatFrag<
|
|
(ops node:$src0, node:$src1, node:$src2),
|
|
(op $src0, $src1, $src2),
|
|
[{ return N->hasOneUse(); }]
|
|
>;
|
|
|
|
let Properties = [SDNPCommutative, SDNPAssociative] in {
|
|
def smax_oneuse : HasOneUseBinOp<smax>;
|
|
def smin_oneuse : HasOneUseBinOp<smin>;
|
|
def umax_oneuse : HasOneUseBinOp<umax>;
|
|
def umin_oneuse : HasOneUseBinOp<umin>;
|
|
|
|
def fminnum_oneuse : HasOneUseBinOp<fminnum>;
|
|
def fmaxnum_oneuse : HasOneUseBinOp<fmaxnum>;
|
|
|
|
def fminnum_ieee_oneuse : HasOneUseBinOp<fminnum_ieee>;
|
|
def fmaxnum_ieee_oneuse : HasOneUseBinOp<fmaxnum_ieee>;
|
|
|
|
|
|
def and_oneuse : HasOneUseBinOp<and>;
|
|
def or_oneuse : HasOneUseBinOp<or>;
|
|
def xor_oneuse : HasOneUseBinOp<xor>;
|
|
} // Properties = [SDNPCommutative, SDNPAssociative]
|
|
|
|
def not_oneuse : HasOneUseUnaryOp<not>;
|
|
|
|
def add_oneuse : HasOneUseBinOp<add>;
|
|
def sub_oneuse : HasOneUseBinOp<sub>;
|
|
|
|
def srl_oneuse : HasOneUseBinOp<srl>;
|
|
def shl_oneuse : HasOneUseBinOp<shl>;
|
|
|
|
def select_oneuse : HasOneUseTernaryOp<select>;
|
|
|
|
def AMDGPUmul_u24_oneuse : HasOneUseBinOp<AMDGPUmul_u24>;
|
|
def AMDGPUmul_i24_oneuse : HasOneUseBinOp<AMDGPUmul_i24>;
|
|
|
|
def srl_16 : PatFrag<
|
|
(ops node:$src0), (srl_oneuse node:$src0, (i32 16))
|
|
>;
|
|
|
|
|
|
def hi_i16_elt : PatFrag<
|
|
(ops node:$src0), (i16 (trunc (i32 (srl_16 node:$src0))))
|
|
>;
|
|
|
|
|
|
def hi_f16_elt : PatLeaf<
|
|
(vt), [{
|
|
if (N->getOpcode() != ISD::BITCAST)
|
|
return false;
|
|
SDValue Tmp = N->getOperand(0);
|
|
|
|
if (Tmp.getOpcode() != ISD::SRL)
|
|
return false;
|
|
if (const auto *RHS = dyn_cast<ConstantSDNode>(Tmp.getOperand(1))
|
|
return RHS->getZExtValue() == 16;
|
|
return false;
|
|
}]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PatLeafs for floating-point comparisons
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def COND_OEQ : PatFrags<(ops), [(OtherVT SETOEQ), (OtherVT SETEQ)]>;
|
|
def COND_ONE : PatFrags<(ops), [(OtherVT SETONE), (OtherVT SETNE)]>;
|
|
def COND_OGT : PatFrags<(ops), [(OtherVT SETOGT), (OtherVT SETGT)]>;
|
|
def COND_OGE : PatFrags<(ops), [(OtherVT SETOGE), (OtherVT SETGE)]>;
|
|
def COND_OLT : PatFrags<(ops), [(OtherVT SETOLT), (OtherVT SETLT)]>;
|
|
def COND_OLE : PatFrags<(ops), [(OtherVT SETOLE), (OtherVT SETLE)]>;
|
|
def COND_O : PatFrags<(ops), [(OtherVT SETO)]>;
|
|
def COND_UO : PatFrags<(ops), [(OtherVT SETUO)]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PatLeafs for unsigned / unordered comparisons
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def COND_UEQ : PatFrag<(ops), (OtherVT SETUEQ)>;
|
|
def COND_UNE : PatFrag<(ops), (OtherVT SETUNE)>;
|
|
def COND_UGT : PatFrag<(ops), (OtherVT SETUGT)>;
|
|
def COND_UGE : PatFrag<(ops), (OtherVT SETUGE)>;
|
|
def COND_ULT : PatFrag<(ops), (OtherVT SETULT)>;
|
|
def COND_ULE : PatFrag<(ops), (OtherVT SETULE)>;
|
|
|
|
// XXX - For some reason R600 version is preferring to use unordered
|
|
// for setne?
|
|
def COND_UNE_NE : PatFrags<(ops), [(OtherVT SETUNE), (OtherVT SETNE)]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PatLeafs for signed comparisons
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def COND_SGT : PatFrag<(ops), (OtherVT SETGT)>;
|
|
def COND_SGE : PatFrag<(ops), (OtherVT SETGE)>;
|
|
def COND_SLT : PatFrag<(ops), (OtherVT SETLT)>;
|
|
def COND_SLE : PatFrag<(ops), (OtherVT SETLE)>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PatLeafs for integer equality
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def COND_EQ : PatFrags<(ops), [(OtherVT SETEQ), (OtherVT SETUEQ)]>;
|
|
def COND_NE : PatFrags<(ops), [(OtherVT SETNE), (OtherVT SETUNE)]>;
|
|
|
|
// FIXME: Should not need code predicate
|
|
//def COND_NULL : PatLeaf<(OtherVT null_frag)>;
|
|
def COND_NULL : PatLeaf <
|
|
(cond),
|
|
[{(void)N; return false;}]
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// PatLeafs for Texture Constants
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def TEX_ARRAY : PatLeaf<
|
|
(imm),
|
|
[{uint32_t TType = (uint32_t)N->getZExtValue();
|
|
return TType == 9 || TType == 10 || TType == 16;
|
|
}]
|
|
>;
|
|
|
|
def TEX_RECT : PatLeaf<
|
|
(imm),
|
|
[{uint32_t TType = (uint32_t)N->getZExtValue();
|
|
return TType == 5;
|
|
}]
|
|
>;
|
|
|
|
def TEX_SHADOW : PatLeaf<
|
|
(imm),
|
|
[{uint32_t TType = (uint32_t)N->getZExtValue();
|
|
return (TType >= 6 && TType <= 8) || TType == 13;
|
|
}]
|
|
>;
|
|
|
|
def TEX_SHADOW_ARRAY : PatLeaf<
|
|
(imm),
|
|
[{uint32_t TType = (uint32_t)N->getZExtValue();
|
|
return TType == 11 || TType == 12 || TType == 17;
|
|
}]
|
|
>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Load/Store Pattern Fragments
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class AddressSpaceList<list<int> AS> {
|
|
list<int> AddrSpaces = AS;
|
|
}
|
|
|
|
class Aligned8Bytes <dag ops, dag frag> : PatFrag <ops, frag, [{
|
|
return cast<MemSDNode>(N)->getAlignment() % 8 == 0;
|
|
}]>;
|
|
|
|
class Aligned16Bytes <dag ops, dag frag> : PatFrag <ops, frag, [{
|
|
return cast<MemSDNode>(N)->getAlignment() >= 16;
|
|
}]>;
|
|
|
|
class LoadFrag <SDPatternOperator op> : PatFrag<(ops node:$ptr), (op node:$ptr)>;
|
|
|
|
class StoreFrag<SDPatternOperator op> : PatFrag <
|
|
(ops node:$value, node:$ptr), (op node:$value, node:$ptr)
|
|
>;
|
|
|
|
class StoreHi16<SDPatternOperator op> : PatFrag <
|
|
(ops node:$value, node:$ptr), (op (srl node:$value, (i32 16)), node:$ptr)
|
|
>;
|
|
|
|
def LoadAddress_constant : AddressSpaceList<[ AddrSpaces.Constant ]>;
|
|
def LoadAddress_global : AddressSpaceList<[ AddrSpaces.Global, AddrSpaces.Constant ]>;
|
|
def StoreAddress_global : AddressSpaceList<[ AddrSpaces.Global ]>;
|
|
|
|
def LoadAddress_flat : AddressSpaceList<[ AddrSpaces.Flat,
|
|
AddrSpaces.Global,
|
|
AddrSpaces.Constant ]>;
|
|
def StoreAddress_flat : AddressSpaceList<[ AddrSpaces.Flat, AddrSpaces.Global ]>;
|
|
|
|
def LoadAddress_private : AddressSpaceList<[ AddrSpaces.Private ]>;
|
|
def StoreAddress_private : AddressSpaceList<[ AddrSpaces.Private ]>;
|
|
|
|
def LoadAddress_local : AddressSpaceList<[ AddrSpaces.Local ]>;
|
|
def StoreAddress_local : AddressSpaceList<[ AddrSpaces.Local ]>;
|
|
|
|
def LoadAddress_region : AddressSpaceList<[ AddrSpaces.Region ]>;
|
|
def StoreAddress_region : AddressSpaceList<[ AddrSpaces.Region ]>;
|
|
|
|
|
|
|
|
class GlobalLoadAddress : CodePatPred<[{
|
|
auto AS = cast<MemSDNode>(N)->getAddressSpace();
|
|
return AS == AMDGPUAS::GLOBAL_ADDRESS || AS == AMDGPUAS::CONSTANT_ADDRESS;
|
|
}]>;
|
|
|
|
class FlatLoadAddress : CodePatPred<[{
|
|
const auto AS = cast<MemSDNode>(N)->getAddressSpace();
|
|
return AS == AMDGPUAS::FLAT_ADDRESS ||
|
|
AS == AMDGPUAS::GLOBAL_ADDRESS ||
|
|
AS == AMDGPUAS::CONSTANT_ADDRESS;
|
|
}]>;
|
|
|
|
class GlobalAddress : CodePatPred<[{
|
|
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
|
|
}]>;
|
|
|
|
class PrivateAddress : CodePatPred<[{
|
|
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::PRIVATE_ADDRESS;
|
|
}]>;
|
|
|
|
class LocalAddress : CodePatPred<[{
|
|
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
|
|
}]>;
|
|
|
|
class RegionAddress : CodePatPred<[{
|
|
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::REGION_ADDRESS;
|
|
}]>;
|
|
|
|
class FlatStoreAddress : CodePatPred<[{
|
|
const auto AS = cast<MemSDNode>(N)->getAddressSpace();
|
|
return AS == AMDGPUAS::FLAT_ADDRESS ||
|
|
AS == AMDGPUAS::GLOBAL_ADDRESS;
|
|
}]>;
|
|
|
|
// TODO: Remove these when stores to new PatFrag format.
|
|
class PrivateStore <SDPatternOperator op> : StoreFrag <op>, PrivateAddress;
|
|
class LocalStore <SDPatternOperator op> : StoreFrag <op>, LocalAddress;
|
|
class RegionStore <SDPatternOperator op> : StoreFrag <op>, RegionAddress;
|
|
class GlobalStore <SDPatternOperator op> : StoreFrag<op>, GlobalAddress;
|
|
class FlatStore <SDPatternOperator op> : StoreFrag <op>, FlatStoreAddress;
|
|
|
|
|
|
foreach as = [ "global", "flat", "constant", "local", "private", "region" ] in {
|
|
let AddressSpaces = !cast<AddressSpaceList>("LoadAddress_"#as).AddrSpaces in {
|
|
|
|
def load_#as : PatFrag<(ops node:$ptr), (unindexedload node:$ptr)> {
|
|
let IsLoad = 1;
|
|
let IsNonExtLoad = 1;
|
|
}
|
|
|
|
def extloadi8_#as : PatFrag<(ops node:$ptr), (extload node:$ptr)> {
|
|
let IsLoad = 1;
|
|
let MemoryVT = i8;
|
|
}
|
|
|
|
def extloadi16_#as : PatFrag<(ops node:$ptr), (extload node:$ptr)> {
|
|
let IsLoad = 1;
|
|
let MemoryVT = i16;
|
|
}
|
|
|
|
def sextloadi8_#as : PatFrag<(ops node:$ptr), (sextload node:$ptr)> {
|
|
let IsLoad = 1;
|
|
let MemoryVT = i8;
|
|
}
|
|
|
|
def sextloadi16_#as : PatFrag<(ops node:$ptr), (sextload node:$ptr)> {
|
|
let IsLoad = 1;
|
|
let MemoryVT = i16;
|
|
}
|
|
|
|
def zextloadi8_#as : PatFrag<(ops node:$ptr), (zextload node:$ptr)> {
|
|
let IsLoad = 1;
|
|
let MemoryVT = i8;
|
|
}
|
|
|
|
def zextloadi16_#as : PatFrag<(ops node:$ptr), (zextload node:$ptr)> {
|
|
let IsLoad = 1;
|
|
let MemoryVT = i16;
|
|
}
|
|
|
|
def atomic_load_32_#as : PatFrag<(ops node:$ptr), (atomic_load_32 node:$ptr)> {
|
|
let IsAtomic = 1;
|
|
let MemoryVT = i32;
|
|
}
|
|
|
|
def atomic_load_64_#as : PatFrag<(ops node:$ptr), (atomic_load_64 node:$ptr)> {
|
|
let IsAtomic = 1;
|
|
let MemoryVT = i64;
|
|
}
|
|
|
|
def store_#as : PatFrag<(ops node:$val, node:$ptr),
|
|
(unindexedstore node:$val, node:$ptr)> {
|
|
let IsStore = 1;
|
|
let IsTruncStore = 0;
|
|
}
|
|
|
|
// truncstore fragments.
|
|
def truncstore_#as : PatFrag<(ops node:$val, node:$ptr),
|
|
(unindexedstore node:$val, node:$ptr)> {
|
|
let IsStore = 1;
|
|
let IsTruncStore = 1;
|
|
}
|
|
|
|
// TODO: We don't really need the truncstore here. We can use
|
|
// unindexedstore with MemoryVT directly, which will save an
|
|
// unnecessary check that the memory size is less than the value type
|
|
// in the generated matcher table.
|
|
def truncstorei8_#as : PatFrag<(ops node:$val, node:$ptr),
|
|
(truncstore node:$val, node:$ptr)> {
|
|
let IsStore = 1;
|
|
let MemoryVT = i8;
|
|
}
|
|
|
|
def truncstorei16_#as : PatFrag<(ops node:$val, node:$ptr),
|
|
(truncstore node:$val, node:$ptr)> {
|
|
let IsStore = 1;
|
|
let MemoryVT = i16;
|
|
}
|
|
|
|
defm atomic_store_#as : binary_atomic_op<atomic_store>;
|
|
|
|
} // End let AddressSpaces = ...
|
|
} // End foreach AddrSpace
|
|
|
|
|
|
def store_hi16_private : StoreHi16 <truncstorei16>, PrivateAddress;
|
|
def truncstorei8_hi16_private : StoreHi16<truncstorei8>, PrivateAddress;
|
|
|
|
def store_atomic_global : GlobalStore<atomic_store>;
|
|
def truncstorei8_hi16_global : StoreHi16 <truncstorei8>, GlobalAddress;
|
|
def truncstorei16_hi16_global : StoreHi16 <truncstorei16>, GlobalAddress;
|
|
|
|
def store_local_hi16 : StoreHi16 <truncstorei16>, LocalAddress;
|
|
def truncstorei8_local_hi16 : StoreHi16<truncstorei8>, LocalAddress;
|
|
def atomic_store_local : LocalStore <atomic_store>;
|
|
|
|
def load_align8_local : Aligned8Bytes <
|
|
(ops node:$ptr), (load_local node:$ptr)
|
|
>;
|
|
|
|
def load_align16_local : Aligned16Bytes <
|
|
(ops node:$ptr), (load_local node:$ptr)
|
|
>;
|
|
|
|
def store_align8_local : Aligned8Bytes <
|
|
(ops node:$val, node:$ptr), (store_local node:$val, node:$ptr)
|
|
>;
|
|
|
|
def store_align16_local : Aligned16Bytes <
|
|
(ops node:$val, node:$ptr), (store_local node:$val, node:$ptr)
|
|
>;
|
|
|
|
def atomic_store_flat : FlatStore <atomic_store>;
|
|
def truncstorei8_hi16_flat : StoreHi16<truncstorei8>, FlatStoreAddress;
|
|
def truncstorei16_hi16_flat : StoreHi16<truncstorei16>, FlatStoreAddress;
|
|
|
|
|
|
class local_binary_atomic_op<SDNode atomic_op> :
|
|
PatFrag<(ops node:$ptr, node:$value),
|
|
(atomic_op node:$ptr, node:$value), [{
|
|
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
|
|
}]>;
|
|
|
|
class region_binary_atomic_op<SDNode atomic_op> :
|
|
PatFrag<(ops node:$ptr, node:$value),
|
|
(atomic_op node:$ptr, node:$value), [{
|
|
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::REGION_ADDRESS;
|
|
}]>;
|
|
|
|
|
|
def atomic_swap_local : local_binary_atomic_op<atomic_swap>;
|
|
def atomic_load_add_local : local_binary_atomic_op<atomic_load_add>;
|
|
def atomic_load_sub_local : local_binary_atomic_op<atomic_load_sub>;
|
|
def atomic_load_and_local : local_binary_atomic_op<atomic_load_and>;
|
|
def atomic_load_or_local : local_binary_atomic_op<atomic_load_or>;
|
|
def atomic_load_xor_local : local_binary_atomic_op<atomic_load_xor>;
|
|
def atomic_load_nand_local : local_binary_atomic_op<atomic_load_nand>;
|
|
def atomic_load_min_local : local_binary_atomic_op<atomic_load_min>;
|
|
def atomic_load_max_local : local_binary_atomic_op<atomic_load_max>;
|
|
def atomic_load_umin_local : local_binary_atomic_op<atomic_load_umin>;
|
|
def atomic_load_umax_local : local_binary_atomic_op<atomic_load_umax>;
|
|
|
|
def mskor_global : PatFrag<(ops node:$val, node:$ptr),
|
|
(AMDGPUstore_mskor node:$val, node:$ptr), [{
|
|
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
|
|
}]>;
|
|
|
|
class AtomicCmpSwapLocal <SDNode cmp_swap_node> : PatFrag<
|
|
(ops node:$ptr, node:$cmp, node:$swap),
|
|
(cmp_swap_node node:$ptr, node:$cmp, node:$swap), [{
|
|
AtomicSDNode *AN = cast<AtomicSDNode>(N);
|
|
return AN->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
|
|
}]>;
|
|
|
|
class AtomicCmpSwapRegion <SDNode cmp_swap_node> : PatFrag<
|
|
(ops node:$ptr, node:$cmp, node:$swap),
|
|
(cmp_swap_node node:$ptr, node:$cmp, node:$swap), [{
|
|
AtomicSDNode *AN = cast<AtomicSDNode>(N);
|
|
return AN->getAddressSpace() == AMDGPUAS::REGION_ADDRESS;
|
|
}]>;
|
|
|
|
def atomic_cmp_swap_local : AtomicCmpSwapLocal <atomic_cmp_swap>;
|
|
|
|
class global_binary_atomic_op_frag<SDNode atomic_op> : PatFrag<
|
|
(ops node:$ptr, node:$value),
|
|
(atomic_op node:$ptr, node:$value),
|
|
[{return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;}]>;
|
|
|
|
multiclass global_binary_atomic_op<SDNode atomic_op> {
|
|
def "" : global_binary_atomic_op_frag<atomic_op>;
|
|
|
|
def _noret : PatFrag<
|
|
(ops node:$ptr, node:$value),
|
|
(atomic_op node:$ptr, node:$value),
|
|
[{return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS && (SDValue(N, 0).use_empty());}]>;
|
|
|
|
def _ret : PatFrag<
|
|
(ops node:$ptr, node:$value),
|
|
(atomic_op node:$ptr, node:$value),
|
|
[{return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS && (!SDValue(N, 0).use_empty());}]>;
|
|
}
|
|
|
|
defm atomic_swap_global : global_binary_atomic_op<atomic_swap>;
|
|
defm atomic_add_global : global_binary_atomic_op<atomic_load_add>;
|
|
defm atomic_and_global : global_binary_atomic_op<atomic_load_and>;
|
|
defm atomic_max_global : global_binary_atomic_op<atomic_load_max>;
|
|
defm atomic_min_global : global_binary_atomic_op<atomic_load_min>;
|
|
defm atomic_or_global : global_binary_atomic_op<atomic_load_or>;
|
|
defm atomic_sub_global : global_binary_atomic_op<atomic_load_sub>;
|
|
defm atomic_umax_global : global_binary_atomic_op<atomic_load_umax>;
|
|
defm atomic_umin_global : global_binary_atomic_op<atomic_load_umin>;
|
|
defm atomic_xor_global : global_binary_atomic_op<atomic_load_xor>;
|
|
|
|
// Legacy.
|
|
def AMDGPUatomic_cmp_swap_global : PatFrag<
|
|
(ops node:$ptr, node:$value),
|
|
(AMDGPUatomic_cmp_swap node:$ptr, node:$value)>, GlobalAddress;
|
|
|
|
def atomic_cmp_swap_global : PatFrag<
|
|
(ops node:$ptr, node:$cmp, node:$value),
|
|
(atomic_cmp_swap node:$ptr, node:$cmp, node:$value)>, GlobalAddress;
|
|
|
|
|
|
def atomic_cmp_swap_global_noret : PatFrag<
|
|
(ops node:$ptr, node:$cmp, node:$value),
|
|
(atomic_cmp_swap node:$ptr, node:$cmp, node:$value),
|
|
[{return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS && (SDValue(N, 0).use_empty());}]>;
|
|
|
|
def atomic_cmp_swap_global_ret : PatFrag<
|
|
(ops node:$ptr, node:$cmp, node:$value),
|
|
(atomic_cmp_swap node:$ptr, node:$cmp, node:$value),
|
|
[{return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS && (!SDValue(N, 0).use_empty());}]>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Misc Pattern Fragments
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class Constants {
|
|
int TWO_PI = 0x40c90fdb;
|
|
int PI = 0x40490fdb;
|
|
int TWO_PI_INV = 0x3e22f983;
|
|
int FP_UINT_MAX_PLUS_1 = 0x4f800000; // 1 << 32 in floating point encoding
|
|
int FP16_ONE = 0x3C00;
|
|
int FP16_NEG_ONE = 0xBC00;
|
|
int FP32_ONE = 0x3f800000;
|
|
int FP32_NEG_ONE = 0xbf800000;
|
|
int FP64_ONE = 0x3ff0000000000000;
|
|
int FP64_NEG_ONE = 0xbff0000000000000;
|
|
}
|
|
def CONST : Constants;
|
|
|
|
def FP_ZERO : PatLeaf <
|
|
(fpimm),
|
|
[{return N->getValueAPF().isZero();}]
|
|
>;
|
|
|
|
def FP_ONE : PatLeaf <
|
|
(fpimm),
|
|
[{return N->isExactlyValue(1.0);}]
|
|
>;
|
|
|
|
def FP_HALF : PatLeaf <
|
|
(fpimm),
|
|
[{return N->isExactlyValue(0.5);}]
|
|
>;
|
|
|
|
/* Generic helper patterns for intrinsics */
|
|
/* -------------------------------------- */
|
|
|
|
class POW_Common <AMDGPUInst log_ieee, AMDGPUInst exp_ieee, AMDGPUInst mul>
|
|
: AMDGPUPat <
|
|
(fpow f32:$src0, f32:$src1),
|
|
(exp_ieee (mul f32:$src1, (log_ieee f32:$src0)))
|
|
>;
|
|
|
|
/* Other helper patterns */
|
|
/* --------------------- */
|
|
|
|
/* Extract element pattern */
|
|
class Extract_Element <ValueType sub_type, ValueType vec_type, int sub_idx,
|
|
SubRegIndex sub_reg>
|
|
: AMDGPUPat<
|
|
(sub_type (extractelt vec_type:$src, sub_idx)),
|
|
(EXTRACT_SUBREG $src, sub_reg)
|
|
>;
|
|
|
|
/* Insert element pattern */
|
|
class Insert_Element <ValueType elem_type, ValueType vec_type,
|
|
int sub_idx, SubRegIndex sub_reg>
|
|
: AMDGPUPat <
|
|
(insertelt vec_type:$vec, elem_type:$elem, sub_idx),
|
|
(INSERT_SUBREG $vec, $elem, sub_reg)
|
|
>;
|
|
|
|
// XXX: Convert to new syntax and use COPY_TO_REG, once the DFAPacketizer
|
|
// can handle COPY instructions.
|
|
// bitconvert pattern
|
|
class BitConvert <ValueType dt, ValueType st, RegisterClass rc> : AMDGPUPat <
|
|
(dt (bitconvert (st rc:$src0))),
|
|
(dt rc:$src0)
|
|
>;
|
|
|
|
// XXX: Convert to new syntax and use COPY_TO_REG, once the DFAPacketizer
|
|
// can handle COPY instructions.
|
|
class DwordAddrPat<ValueType vt, RegisterClass rc> : AMDGPUPat <
|
|
(vt (AMDGPUdwordaddr (vt rc:$addr))),
|
|
(vt rc:$addr)
|
|
>;
|
|
|
|
// BFI_INT patterns
|
|
|
|
multiclass BFIPatterns <Instruction BFI_INT,
|
|
Instruction LoadImm32,
|
|
RegisterClass RC64> {
|
|
// Definition from ISA doc:
|
|
// (y & x) | (z & ~x)
|
|
def : AMDGPUPat <
|
|
(or (and i32:$y, i32:$x), (and i32:$z, (not i32:$x))),
|
|
(BFI_INT $x, $y, $z)
|
|
>;
|
|
|
|
// 64-bit version
|
|
def : AMDGPUPat <
|
|
(or (and i64:$y, i64:$x), (and i64:$z, (not i64:$x))),
|
|
(REG_SEQUENCE RC64,
|
|
(BFI_INT (i32 (EXTRACT_SUBREG $x, sub0)),
|
|
(i32 (EXTRACT_SUBREG $y, sub0)),
|
|
(i32 (EXTRACT_SUBREG $z, sub0))), sub0,
|
|
(BFI_INT (i32 (EXTRACT_SUBREG $x, sub1)),
|
|
(i32 (EXTRACT_SUBREG $y, sub1)),
|
|
(i32 (EXTRACT_SUBREG $z, sub1))), sub1)
|
|
>;
|
|
|
|
// SHA-256 Ch function
|
|
// z ^ (x & (y ^ z))
|
|
def : AMDGPUPat <
|
|
(xor i32:$z, (and i32:$x, (xor i32:$y, i32:$z))),
|
|
(BFI_INT $x, $y, $z)
|
|
>;
|
|
|
|
// 64-bit version
|
|
def : AMDGPUPat <
|
|
(xor i64:$z, (and i64:$x, (xor i64:$y, i64:$z))),
|
|
(REG_SEQUENCE RC64,
|
|
(BFI_INT (i32 (EXTRACT_SUBREG $x, sub0)),
|
|
(i32 (EXTRACT_SUBREG $y, sub0)),
|
|
(i32 (EXTRACT_SUBREG $z, sub0))), sub0,
|
|
(BFI_INT (i32 (EXTRACT_SUBREG $x, sub1)),
|
|
(i32 (EXTRACT_SUBREG $y, sub1)),
|
|
(i32 (EXTRACT_SUBREG $z, sub1))), sub1)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(fcopysign f32:$src0, f32:$src1),
|
|
(BFI_INT (LoadImm32 (i32 0x7fffffff)), $src0, $src1)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(f32 (fcopysign f32:$src0, f64:$src1)),
|
|
(BFI_INT (LoadImm32 (i32 0x7fffffff)), $src0,
|
|
(i32 (EXTRACT_SUBREG $src1, sub1)))
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(f64 (fcopysign f64:$src0, f64:$src1)),
|
|
(REG_SEQUENCE RC64,
|
|
(i32 (EXTRACT_SUBREG $src0, sub0)), sub0,
|
|
(BFI_INT (LoadImm32 (i32 0x7fffffff)),
|
|
(i32 (EXTRACT_SUBREG $src0, sub1)),
|
|
(i32 (EXTRACT_SUBREG $src1, sub1))), sub1)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(f64 (fcopysign f64:$src0, f32:$src1)),
|
|
(REG_SEQUENCE RC64,
|
|
(i32 (EXTRACT_SUBREG $src0, sub0)), sub0,
|
|
(BFI_INT (LoadImm32 (i32 0x7fffffff)),
|
|
(i32 (EXTRACT_SUBREG $src0, sub1)),
|
|
$src1), sub1)
|
|
>;
|
|
}
|
|
|
|
// SHA-256 Ma patterns
|
|
|
|
// ((x & z) | (y & (x | z))) -> BFI_INT (XOR x, y), z, y
|
|
multiclass SHA256MaPattern <Instruction BFI_INT, Instruction XOR, RegisterClass RC64> {
|
|
def : AMDGPUPat <
|
|
(or (and i32:$x, i32:$z), (and i32:$y, (or i32:$x, i32:$z))),
|
|
(BFI_INT (XOR i32:$x, i32:$y), i32:$z, i32:$y)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(or (and i64:$x, i64:$z), (and i64:$y, (or i64:$x, i64:$z))),
|
|
(REG_SEQUENCE RC64,
|
|
(BFI_INT (XOR (i32 (EXTRACT_SUBREG $x, sub0)),
|
|
(i32 (EXTRACT_SUBREG $y, sub0))),
|
|
(i32 (EXTRACT_SUBREG $z, sub0)),
|
|
(i32 (EXTRACT_SUBREG $y, sub0))), sub0,
|
|
(BFI_INT (XOR (i32 (EXTRACT_SUBREG $x, sub1)),
|
|
(i32 (EXTRACT_SUBREG $y, sub1))),
|
|
(i32 (EXTRACT_SUBREG $z, sub1)),
|
|
(i32 (EXTRACT_SUBREG $y, sub1))), sub1)
|
|
>;
|
|
}
|
|
|
|
// Bitfield extract patterns
|
|
|
|
def IMMZeroBasedBitfieldMask : PatLeaf <(imm), [{
|
|
return isMask_32(N->getZExtValue());
|
|
}]>;
|
|
|
|
def IMMPopCount : SDNodeXForm<imm, [{
|
|
return CurDAG->getTargetConstant(countPopulation(N->getZExtValue()), SDLoc(N),
|
|
MVT::i32);
|
|
}]>;
|
|
|
|
multiclass BFEPattern <Instruction UBFE, Instruction SBFE, Instruction MOV> {
|
|
def : AMDGPUPat <
|
|
(i32 (and (i32 (srl i32:$src, i32:$rshift)), IMMZeroBasedBitfieldMask:$mask)),
|
|
(UBFE $src, $rshift, (MOV (i32 (IMMPopCount $mask))))
|
|
>;
|
|
|
|
// x & ((1 << y) - 1)
|
|
def : AMDGPUPat <
|
|
(and i32:$src, (add_oneuse (shl_oneuse 1, i32:$width), -1)),
|
|
(UBFE $src, (MOV (i32 0)), $width)
|
|
>;
|
|
|
|
// x & ~(-1 << y)
|
|
def : AMDGPUPat <
|
|
(and i32:$src, (xor_oneuse (shl_oneuse -1, i32:$width), -1)),
|
|
(UBFE $src, (MOV (i32 0)), $width)
|
|
>;
|
|
|
|
// x & (-1 >> (bitwidth - y))
|
|
def : AMDGPUPat <
|
|
(and i32:$src, (srl_oneuse -1, (sub 32, i32:$width))),
|
|
(UBFE $src, (MOV (i32 0)), $width)
|
|
>;
|
|
|
|
// x << (bitwidth - y) >> (bitwidth - y)
|
|
def : AMDGPUPat <
|
|
(srl (shl_oneuse i32:$src, (sub 32, i32:$width)), (sub 32, i32:$width)),
|
|
(UBFE $src, (MOV (i32 0)), $width)
|
|
>;
|
|
|
|
def : AMDGPUPat <
|
|
(sra (shl_oneuse i32:$src, (sub 32, i32:$width)), (sub 32, i32:$width)),
|
|
(SBFE $src, (MOV (i32 0)), $width)
|
|
>;
|
|
}
|
|
|
|
// rotr pattern
|
|
class ROTRPattern <Instruction BIT_ALIGN> : AMDGPUPat <
|
|
(rotr i32:$src0, i32:$src1),
|
|
(BIT_ALIGN $src0, $src0, $src1)
|
|
>;
|
|
|
|
multiclass IntMed3Pat<Instruction med3Inst,
|
|
SDPatternOperator min,
|
|
SDPatternOperator max,
|
|
SDPatternOperator min_oneuse,
|
|
SDPatternOperator max_oneuse,
|
|
ValueType vt = i32> {
|
|
|
|
// This matches 16 permutations of
|
|
// min(max(a, b), max(min(a, b), c))
|
|
def : AMDGPUPat <
|
|
(min (max_oneuse vt:$src0, vt:$src1),
|
|
(max_oneuse (min_oneuse vt:$src0, vt:$src1), vt:$src2)),
|
|
(med3Inst vt:$src0, vt:$src1, vt:$src2)
|
|
>;
|
|
|
|
// This matches 16 permutations of
|
|
// max(min(x, y), min(max(x, y), z))
|
|
def : AMDGPUPat <
|
|
(max (min_oneuse vt:$src0, vt:$src1),
|
|
(min_oneuse (max_oneuse vt:$src0, vt:$src1), vt:$src2)),
|
|
(med3Inst $src0, $src1, $src2)
|
|
>;
|
|
}
|
|
|
|
// Special conversion patterns
|
|
|
|
def cvt_rpi_i32_f32 : PatFrag <
|
|
(ops node:$src),
|
|
(fp_to_sint (ffloor (fadd $src, FP_HALF))),
|
|
[{ (void) N; return TM.Options.NoNaNsFPMath; }]
|
|
>;
|
|
|
|
def cvt_flr_i32_f32 : PatFrag <
|
|
(ops node:$src),
|
|
(fp_to_sint (ffloor $src)),
|
|
[{ (void)N; return TM.Options.NoNaNsFPMath; }]
|
|
>;
|
|
|
|
let AddedComplexity = 2 in {
|
|
class IMad24Pat<Instruction Inst, bit HasClamp = 0> : AMDGPUPat <
|
|
(add (AMDGPUmul_i24 i32:$src0, i32:$src1), i32:$src2),
|
|
!if(HasClamp, (Inst $src0, $src1, $src2, (i1 0)),
|
|
(Inst $src0, $src1, $src2))
|
|
>;
|
|
|
|
class UMad24Pat<Instruction Inst, bit HasClamp = 0> : AMDGPUPat <
|
|
(add (AMDGPUmul_u24 i32:$src0, i32:$src1), i32:$src2),
|
|
!if(HasClamp, (Inst $src0, $src1, $src2, (i1 0)),
|
|
(Inst $src0, $src1, $src2))
|
|
>;
|
|
} // AddedComplexity.
|
|
|
|
class RcpPat<Instruction RcpInst, ValueType vt> : AMDGPUPat <
|
|
(fdiv FP_ONE, vt:$src),
|
|
(RcpInst $src)
|
|
>;
|
|
|
|
class RsqPat<Instruction RsqInst, ValueType vt> : AMDGPUPat <
|
|
(AMDGPUrcp (fsqrt vt:$src)),
|
|
(RsqInst $src)
|
|
>;
|
|
|
|
// Instructions which select to the same v_min_f*
|
|
def fminnum_like : PatFrags<(ops node:$src0, node:$src1),
|
|
[(fminnum_ieee node:$src0, node:$src1),
|
|
(fminnum node:$src0, node:$src1)]
|
|
>;
|
|
|
|
// Instructions which select to the same v_max_f*
|
|
def fmaxnum_like : PatFrags<(ops node:$src0, node:$src1),
|
|
[(fmaxnum_ieee node:$src0, node:$src1),
|
|
(fmaxnum node:$src0, node:$src1)]
|
|
>;
|
|
|
|
def fminnum_like_oneuse : PatFrags<(ops node:$src0, node:$src1),
|
|
[(fminnum_ieee_oneuse node:$src0, node:$src1),
|
|
(fminnum_oneuse node:$src0, node:$src1)]
|
|
>;
|
|
|
|
def fmaxnum_like_oneuse : PatFrags<(ops node:$src0, node:$src1),
|
|
[(fmaxnum_ieee_oneuse node:$src0, node:$src1),
|
|
(fmaxnum_oneuse node:$src0, node:$src1)]
|
|
>;
|