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

646 lines
20 KiB
TableGen

//===-- AMDGPUInstructions.td - Common instruction defs ---*- tablegen -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file contains instruction defs that are common to all hw codegen
// targets.
//
//===----------------------------------------------------------------------===//
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;
}
def FP32Denormals : Predicate<"Subtarget.hasFP32Denormals()">;
def FP64Denormals : Predicate<"Subtarget.hasFP64Denormals()">;
def UnsafeFPMath : Predicate<"TM.Options.UnsafeFPMath">;
def InstFlag : OperandWithDefaultOps <i32, (ops (i32 0))>;
def ADDRIndirect : ComplexPattern<iPTR, 2, "SelectADDRIndirect", [], []>;
let OperandType = "OPERAND_IMMEDIATE" in {
def u32imm : Operand<i32> {
let PrintMethod = "printU32ImmOperand";
}
def u16imm : Operand<i16> {
let PrintMethod = "printU16ImmOperand";
}
def u8imm : Operand<i8> {
let PrintMethod = "printU8ImmOperand";
}
} // End OperandType = "OPERAND_IMMEDIATE"
//===--------------------------------------------------------------------===//
// Custom Operands
//===--------------------------------------------------------------------===//
def brtarget : Operand<OtherVT>;
//===----------------------------------------------------------------------===//
// PatLeafs for floating-point comparisons
//===----------------------------------------------------------------------===//
def COND_OEQ : PatLeaf <
(cond),
[{return N->get() == ISD::SETOEQ || N->get() == ISD::SETEQ;}]
>;
def COND_ONE : PatLeaf <
(cond),
[{return N->get() == ISD::SETONE || N->get() == ISD::SETNE;}]
>;
def COND_OGT : PatLeaf <
(cond),
[{return N->get() == ISD::SETOGT || N->get() == ISD::SETGT;}]
>;
def COND_OGE : PatLeaf <
(cond),
[{return N->get() == ISD::SETOGE || N->get() == ISD::SETGE;}]
>;
def COND_OLT : PatLeaf <
(cond),
[{return N->get() == ISD::SETOLT || N->get() == ISD::SETLT;}]
>;
def COND_OLE : PatLeaf <
(cond),
[{return N->get() == ISD::SETOLE || N->get() == ISD::SETLE;}]
>;
def COND_O : PatLeaf <(cond), [{return N->get() == ISD::SETO;}]>;
def COND_UO : PatLeaf <(cond), [{return N->get() == ISD::SETUO;}]>;
//===----------------------------------------------------------------------===//
// PatLeafs for unsigned / unordered comparisons
//===----------------------------------------------------------------------===//
def COND_UEQ : PatLeaf <(cond), [{return N->get() == ISD::SETUEQ;}]>;
def COND_UNE : PatLeaf <(cond), [{return N->get() == ISD::SETUNE;}]>;
def COND_UGT : PatLeaf <(cond), [{return N->get() == ISD::SETUGT;}]>;
def COND_UGE : PatLeaf <(cond), [{return N->get() == ISD::SETUGE;}]>;
def COND_ULT : PatLeaf <(cond), [{return N->get() == ISD::SETULT;}]>;
def COND_ULE : PatLeaf <(cond), [{return N->get() == ISD::SETULE;}]>;
// XXX - For some reason R600 version is preferring to use unordered
// for setne?
def COND_UNE_NE : PatLeaf <
(cond),
[{return N->get() == ISD::SETUNE || N->get() == ISD::SETNE;}]
>;
//===----------------------------------------------------------------------===//
// PatLeafs for signed comparisons
//===----------------------------------------------------------------------===//
def COND_SGT : PatLeaf <(cond), [{return N->get() == ISD::SETGT;}]>;
def COND_SGE : PatLeaf <(cond), [{return N->get() == ISD::SETGE;}]>;
def COND_SLT : PatLeaf <(cond), [{return N->get() == ISD::SETLT;}]>;
def COND_SLE : PatLeaf <(cond), [{return N->get() == ISD::SETLE;}]>;
//===----------------------------------------------------------------------===//
// PatLeafs for integer equality
//===----------------------------------------------------------------------===//
def COND_EQ : PatLeaf <
(cond),
[{return N->get() == ISD::SETEQ || N->get() == ISD::SETUEQ;}]
>;
def COND_NE : PatLeaf <
(cond),
[{return N->get() == ISD::SETNE || N->get() == ISD::SETUNE;}]
>;
def COND_NULL : PatLeaf <
(cond),
[{(void)N; return false;}]
>;
//===----------------------------------------------------------------------===//
// Misc. PatFrags
//===----------------------------------------------------------------------===//
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, $src2),
[{ return N->hasOneUse(); }]
>;
//===----------------------------------------------------------------------===//
// Load/Store Pattern Fragments
//===----------------------------------------------------------------------===//
class PrivateMemOp <dag ops, dag frag> : PatFrag <ops, frag, [{
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::PRIVATE_ADDRESS;
}]>;
class PrivateLoad <SDPatternOperator op> : PrivateMemOp <
(ops node:$ptr), (op node:$ptr)
>;
class PrivateStore <SDPatternOperator op> : PrivateMemOp <
(ops node:$value, node:$ptr), (op node:$value, node:$ptr)
>;
def load_private : PrivateLoad <load>;
def truncstorei8_private : PrivateStore <truncstorei8>;
def truncstorei16_private : PrivateStore <truncstorei16>;
def store_private : PrivateStore <store>;
class GlobalMemOp <dag ops, dag frag> : PatFrag <ops, frag, [{
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
}]>;
// Global address space loads
class GlobalLoad <SDPatternOperator op> : GlobalMemOp <
(ops node:$ptr), (op node:$ptr)
>;
def global_load : GlobalLoad <load>;
// Global address space stores
class GlobalStore <SDPatternOperator op> : GlobalMemOp <
(ops node:$value, node:$ptr), (op node:$value, node:$ptr)
>;
def global_store : GlobalStore <store>;
def global_store_atomic : GlobalStore<atomic_store>;
class ConstantMemOp <dag ops, dag frag> : PatFrag <ops, frag, [{
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::CONSTANT_ADDRESS;
}]>;
// Constant address space loads
class ConstantLoad <SDPatternOperator op> : ConstantMemOp <
(ops node:$ptr), (op node:$ptr)
>;
def constant_load : ConstantLoad<load>;
class LocalMemOp <dag ops, dag frag> : PatFrag <ops, frag, [{
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
}]>;
// Local address space loads
class LocalLoad <SDPatternOperator op> : LocalMemOp <
(ops node:$ptr), (op node:$ptr)
>;
class LocalStore <SDPatternOperator op> : LocalMemOp <
(ops node:$value, node:$ptr), (op node:$value, node:$ptr)
>;
class FlatMemOp <dag ops, dag frag> : PatFrag <ops, frag, [{
return cast<MemSDNode>(N)->getAddressSPace() == AMDGPUAS::FLAT_ADDRESS;
}]>;
class FlatLoad <SDPatternOperator op> : FlatMemOp <
(ops node:$ptr), (op node:$ptr)
>;
class AZExtLoadBase <SDPatternOperator ld_node>: PatFrag<(ops node:$ptr),
(ld_node node:$ptr), [{
LoadSDNode *L = cast<LoadSDNode>(N);
return L->getExtensionType() == ISD::ZEXTLOAD ||
L->getExtensionType() == ISD::EXTLOAD;
}]>;
def az_extload : AZExtLoadBase <unindexedload>;
def az_extloadi8 : PatFrag<(ops node:$ptr), (az_extload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i8;
}]>;
def az_extloadi8_global : GlobalLoad <az_extloadi8>;
def sextloadi8_global : GlobalLoad <sextloadi8>;
def az_extloadi8_constant : ConstantLoad <az_extloadi8>;
def sextloadi8_constant : ConstantLoad <sextloadi8>;
def az_extloadi8_local : LocalLoad <az_extloadi8>;
def sextloadi8_local : LocalLoad <sextloadi8>;
def extloadi8_private : PrivateLoad <az_extloadi8>;
def sextloadi8_private : PrivateLoad <sextloadi8>;
def az_extloadi16 : PatFrag<(ops node:$ptr), (az_extload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i16;
}]>;
def az_extloadi16_global : GlobalLoad <az_extloadi16>;
def sextloadi16_global : GlobalLoad <sextloadi16>;
def az_extloadi16_constant : ConstantLoad <az_extloadi16>;
def sextloadi16_constant : ConstantLoad <sextloadi16>;
def az_extloadi16_local : LocalLoad <az_extloadi16>;
def sextloadi16_local : LocalLoad <sextloadi16>;
def extloadi16_private : PrivateLoad <az_extloadi16>;
def sextloadi16_private : PrivateLoad <sextloadi16>;
def az_extloadi32 : PatFrag<(ops node:$ptr), (az_extload node:$ptr), [{
return cast<LoadSDNode>(N)->getMemoryVT() == MVT::i32;
}]>;
def az_extloadi32_global : GlobalLoad <az_extloadi32>;
def az_extloadi32_flat : FlatLoad <az_extloadi32>;
def az_extloadi32_constant : ConstantLoad <az_extloadi32>;
def truncstorei8_global : GlobalStore <truncstorei8>;
def truncstorei16_global : GlobalStore <truncstorei16>;
def local_store : LocalStore <store>;
def truncstorei8_local : LocalStore <truncstorei8>;
def truncstorei16_local : LocalStore <truncstorei16>;
def local_load : LocalLoad <load>;
class Aligned8Bytes <dag ops, dag frag> : PatFrag <ops, frag, [{
return cast<MemSDNode>(N)->getAlignment() % 8 == 0;
}]>;
def local_load_aligned8bytes : Aligned8Bytes <
(ops node:$ptr), (local_load node:$ptr)
>;
def local_store_aligned8bytes : Aligned8Bytes <
(ops node:$val, node:$ptr), (local_store node:$val, node:$ptr)
>;
class local_binary_atomic_op<SDNode atomic_op> :
PatFrag<(ops node:$ptr, node:$value),
(atomic_op node:$ptr, node:$value), [{
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
}]>;
def atomic_swap_local : local_binary_atomic_op<atomic_swap>;
def atomic_load_add_local : local_binary_atomic_op<atomic_load_add>;
def atomic_load_sub_local : local_binary_atomic_op<atomic_load_sub>;
def atomic_load_and_local : local_binary_atomic_op<atomic_load_and>;
def atomic_load_or_local : local_binary_atomic_op<atomic_load_or>;
def atomic_load_xor_local : local_binary_atomic_op<atomic_load_xor>;
def atomic_load_nand_local : local_binary_atomic_op<atomic_load_nand>;
def atomic_load_min_local : local_binary_atomic_op<atomic_load_min>;
def atomic_load_max_local : local_binary_atomic_op<atomic_load_max>;
def atomic_load_umin_local : local_binary_atomic_op<atomic_load_umin>;
def atomic_load_umax_local : local_binary_atomic_op<atomic_load_umax>;
def mskor_global : PatFrag<(ops node:$val, node:$ptr),
(AMDGPUstore_mskor node:$val, node:$ptr), [{
return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
}]>;
multiclass AtomicCmpSwapLocal <SDNode cmp_swap_node> {
def _32_local : PatFrag <
(ops node:$ptr, node:$cmp, node:$swap),
(cmp_swap_node node:$ptr, node:$cmp, node:$swap), [{
AtomicSDNode *AN = cast<AtomicSDNode>(N);
return AN->getMemoryVT() == MVT::i32 &&
AN->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
}]>;
def _64_local : PatFrag<
(ops node:$ptr, node:$cmp, node:$swap),
(cmp_swap_node node:$ptr, node:$cmp, node:$swap), [{
AtomicSDNode *AN = cast<AtomicSDNode>(N);
return AN->getMemoryVT() == MVT::i64 &&
AN->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS;
}]>;
}
defm atomic_cmp_swap : AtomicCmpSwapLocal <atomic_cmp_swap>;
class global_binary_atomic_op<SDNode atomic_op> : PatFrag<
(ops node:$ptr, node:$value),
(atomic_op node:$ptr, node:$value),
[{return cast<MemSDNode>(N)->getAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;}]
>;
def atomic_swap_global : global_binary_atomic_op<atomic_swap>;
def atomic_add_global : global_binary_atomic_op<atomic_load_add>;
def atomic_and_global : global_binary_atomic_op<atomic_load_and>;
def atomic_max_global : global_binary_atomic_op<atomic_load_max>;
def atomic_min_global : global_binary_atomic_op<atomic_load_min>;
def atomic_or_global : global_binary_atomic_op<atomic_load_or>;
def atomic_sub_global : global_binary_atomic_op<atomic_load_sub>;
def atomic_umax_global : global_binary_atomic_op<atomic_load_umax>;
def atomic_umin_global : global_binary_atomic_op<atomic_load_umin>;
def atomic_xor_global : global_binary_atomic_op<atomic_load_xor>;
def atomic_cmp_swap_global : global_binary_atomic_op<AMDGPUatomic_cmp_swap>;
//===----------------------------------------------------------------------===//
// Misc Pattern Fragments
//===----------------------------------------------------------------------===//
class Constants {
int TWO_PI = 0x40c90fdb;
int PI = 0x40490fdb;
int TWO_PI_INV = 0x3e22f983;
int FP_UINT_MAX_PLUS_1 = 0x4f800000; // 1 << 32 in floating point encoding
int FP32_ONE = 0x3f800000;
int FP32_NEG_ONE = 0xbf800000;
int FP64_ONE = 0x3ff0000000000000;
int FP64_NEG_ONE = 0xbff0000000000000;
}
def CONST : Constants;
def FP_ZERO : PatLeaf <
(fpimm),
[{return N->getValueAPF().isZero();}]
>;
def FP_ONE : PatLeaf <
(fpimm),
[{return N->isExactlyValue(1.0);}]
>;
def FP_HALF : PatLeaf <
(fpimm),
[{return N->isExactlyValue(0.5);}]
>;
let isCodeGenOnly = 1, isPseudo = 1 in {
let usesCustomInserter = 1 in {
class CLAMP <RegisterClass rc> : AMDGPUShaderInst <
(outs rc:$dst),
(ins rc:$src0),
"CLAMP $dst, $src0",
[(set f32:$dst, (AMDGPUclamp f32:$src0, (f32 FP_ZERO), (f32 FP_ONE)))]
>;
class FABS <RegisterClass rc> : AMDGPUShaderInst <
(outs rc:$dst),
(ins rc:$src0),
"FABS $dst, $src0",
[(set f32:$dst, (fabs f32:$src0))]
>;
class FNEG <RegisterClass rc> : AMDGPUShaderInst <
(outs rc:$dst),
(ins rc:$src0),
"FNEG $dst, $src0",
[(set f32:$dst, (fneg f32:$src0))]
>;
} // usesCustomInserter = 1
multiclass RegisterLoadStore <RegisterClass dstClass, Operand addrClass,
ComplexPattern addrPat> {
let UseNamedOperandTable = 1 in {
def RegisterLoad : AMDGPUShaderInst <
(outs dstClass:$dst),
(ins addrClass:$addr, i32imm:$chan),
"RegisterLoad $dst, $addr",
[(set i32:$dst, (AMDGPUregister_load addrPat:$addr, (i32 timm:$chan)))]
> {
let isRegisterLoad = 1;
}
def RegisterStore : AMDGPUShaderInst <
(outs),
(ins dstClass:$val, addrClass:$addr, i32imm:$chan),
"RegisterStore $val, $addr",
[(AMDGPUregister_store i32:$val, addrPat:$addr, (i32 timm:$chan))]
> {
let isRegisterStore = 1;
}
}
}
} // End isCodeGenOnly = 1, isPseudo = 1
/* Generic helper patterns for intrinsics */
/* -------------------------------------- */
class POW_Common <AMDGPUInst log_ieee, AMDGPUInst exp_ieee, AMDGPUInst mul>
: Pat <
(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>
: Pat<
(sub_type (extractelt vec_type:$src, sub_idx)),
(EXTRACT_SUBREG $src, sub_reg)
>;
/* Insert element pattern */
class Insert_Element <ValueType elem_type, ValueType vec_type,
int sub_idx, SubRegIndex sub_reg>
: Pat <
(insertelt vec_type:$vec, elem_type:$elem, sub_idx),
(INSERT_SUBREG $vec, $elem, sub_reg)
>;
// XXX: Convert to new syntax and use COPY_TO_REG, once the DFAPacketizer
// can handle COPY instructions.
// bitconvert pattern
class BitConvert <ValueType dt, ValueType st, RegisterClass rc> : Pat <
(dt (bitconvert (st rc:$src0))),
(dt rc:$src0)
>;
// XXX: Convert to new syntax and use COPY_TO_REG, once the DFAPacketizer
// can handle COPY instructions.
class DwordAddrPat<ValueType vt, RegisterClass rc> : Pat <
(vt (AMDGPUdwordaddr (vt rc:$addr))),
(vt rc:$addr)
>;
// BFI_INT patterns
multiclass BFIPatterns <Instruction BFI_INT,
Instruction LoadImm32,
RegisterClass RC64> {
// Definition from ISA doc:
// (y & x) | (z & ~x)
def : Pat <
(or (and i32:$y, i32:$x), (and i32:$z, (not i32:$x))),
(BFI_INT $x, $y, $z)
>;
// SHA-256 Ch function
// z ^ (x & (y ^ z))
def : Pat <
(xor i32:$z, (and i32:$x, (xor i32:$y, i32:$z))),
(BFI_INT $x, $y, $z)
>;
def : Pat <
(fcopysign f32:$src0, f32:$src1),
(BFI_INT (LoadImm32 (i32 0x7fffffff)), $src0, $src1)
>;
def : Pat <
(f64 (fcopysign f64:$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 $src1, sub1))), sub1)
>;
def : Pat <
(f64 (fcopysign f64:$src0, f32:$src1)),
(REG_SEQUENCE RC64,
(i32 (EXTRACT_SUBREG $src0, sub0)), sub0,
(BFI_INT (LoadImm32 (i32 0x7fffffff)),
(i32 (EXTRACT_SUBREG $src0, sub1)),
$src1), sub1)
>;
}
// SHA-256 Ma patterns
// ((x & z) | (y & (x | z))) -> BFI_INT (XOR x, y), z, y
class SHA256MaPattern <Instruction BFI_INT, Instruction XOR> : Pat <
(or (and i32:$x, i32:$z), (and i32:$y, (or i32:$x, i32:$z))),
(BFI_INT (XOR i32:$x, i32:$y), i32:$z, i32:$y)
>;
// 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);
}]>;
class BFEPattern <Instruction BFE, Instruction MOV> : Pat <
(i32 (and (i32 (srl i32:$src, i32:$rshift)), IMMZeroBasedBitfieldMask:$mask)),
(BFE $src, $rshift, (MOV (i32 (IMMPopCount $mask))))
>;
// rotr pattern
class ROTRPattern <Instruction BIT_ALIGN> : Pat <
(rotr i32:$src0, i32:$src1),
(BIT_ALIGN $src0, $src0, $src1)
>;
// This matches 16 permutations of
// max(min(x, y), min(max(x, y), z))
class IntMed3Pat<Instruction med3Inst,
SDPatternOperator max,
SDPatternOperator max_oneuse,
SDPatternOperator min_oneuse> : Pat<
(max (min_oneuse i32:$src0, i32:$src1),
(min_oneuse (max_oneuse i32:$src0, i32:$src1), i32:$src2)),
(med3Inst $src0, $src1, $src2)
>;
let Properties = [SDNPCommutative, SDNPAssociative] in {
def smax_oneuse : HasOneUseBinOp<smax>;
def smin_oneuse : HasOneUseBinOp<smin>;
def umax_oneuse : HasOneUseBinOp<umax>;
def umin_oneuse : HasOneUseBinOp<umin>;
def sub_oneuse : HasOneUseBinOp<sub>;
} // Properties = [SDNPCommutative, SDNPAssociative]
def select_oneuse : HasOneUseTernaryOp<select>;
// Special conversion patterns
def cvt_rpi_i32_f32 : PatFrag <
(ops node:$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 $src)),
[{ (void)N; return TM.Options.NoNaNsFPMath; }]
>;
class IMad24Pat<Instruction Inst> : Pat <
(add (AMDGPUmul_i24 i32:$src0, i32:$src1), i32:$src2),
(Inst $src0, $src1, $src2)
>;
class UMad24Pat<Instruction Inst> : Pat <
(add (AMDGPUmul_u24 i32:$src0, i32:$src1), i32:$src2),
(Inst $src0, $src1, $src2)
>;
class RcpPat<Instruction RcpInst, ValueType vt> : Pat <
(fdiv FP_ONE, vt:$src),
(RcpInst $src)
>;
class RsqPat<Instruction RsqInst, ValueType vt> : Pat <
(AMDGPUrcp (fsqrt vt:$src)),
(RsqInst $src)
>;
include "R600Instructions.td"
include "R700Instructions.td"
include "EvergreenInstructions.td"
include "CaymanInstructions.td"
include "SIInstrInfo.td"