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

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)]
>;