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

978 lines
43 KiB
TableGen

//===-- MIMGInstructions.td - MIMG Instruction Definitions ----------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
// MIMG-specific encoding families to distinguish between semantically
// equivalent machine instructions with different encoding.
//
// - MIMGEncGfx6: encoding introduced with gfx6 (obsoleted for atomics in gfx8)
// - MIMGEncGfx8: encoding introduced with gfx8 for atomics
// - MIMGEncGfx10Default: gfx default (non-NSA) encoding
// - MIMGEncGfx10NSA: gfx10 NSA encoding
class MIMGEncoding;
def MIMGEncGfx6 : MIMGEncoding;
def MIMGEncGfx8 : MIMGEncoding;
def MIMGEncGfx10Default : MIMGEncoding;
def MIMGEncGfx10NSA : MIMGEncoding;
def MIMGEncoding : GenericEnum {
let FilterClass = "MIMGEncoding";
}
// Represent an ISA-level opcode, independent of the encoding and the
// vdata/vaddr size.
class MIMGBaseOpcode : PredicateControl {
MIMGBaseOpcode BaseOpcode = !cast<MIMGBaseOpcode>(NAME);
bit Store = 0;
bit Atomic = 0;
bit AtomicX2 = 0; // (f)cmpswap
bit Sampler = 0;
bit Gather4 = 0;
bits<8> NumExtraArgs = 0;
bit Gradients = 0;
bit G16 = 0;
bit Coordinates = 1;
bit LodOrClampOrMip = 0;
bit HasD16 = 0;
}
def MIMGBaseOpcode : GenericEnum {
let FilterClass = "MIMGBaseOpcode";
}
def MIMGBaseOpcodesTable : GenericTable {
let FilterClass = "MIMGBaseOpcode";
let CppTypeName = "MIMGBaseOpcodeInfo";
let Fields = ["BaseOpcode", "Store", "Atomic", "AtomicX2", "Sampler",
"Gather4", "NumExtraArgs", "Gradients", "G16", "Coordinates",
"LodOrClampOrMip", "HasD16"];
GenericEnum TypeOf_BaseOpcode = MIMGBaseOpcode;
let PrimaryKey = ["BaseOpcode"];
let PrimaryKeyName = "getMIMGBaseOpcodeInfo";
}
def MIMGDim : GenericEnum {
let FilterClass = "AMDGPUDimProps";
}
def MIMGDimInfoTable : GenericTable {
let FilterClass = "AMDGPUDimProps";
let CppTypeName = "MIMGDimInfo";
let Fields = ["Dim", "NumCoords", "NumGradients", "DA", "Encoding", "AsmSuffix"];
GenericEnum TypeOf_Dim = MIMGDim;
let PrimaryKey = ["Dim"];
let PrimaryKeyName = "getMIMGDimInfo";
}
def getMIMGDimInfoByEncoding : SearchIndex {
let Table = MIMGDimInfoTable;
let Key = ["Encoding"];
}
def getMIMGDimInfoByAsmSuffix : SearchIndex {
let Table = MIMGDimInfoTable;
let Key = ["AsmSuffix"];
}
class mimg <bits<8> si_gfx10, bits<8> vi = si_gfx10> {
field bits<8> SI_GFX10 = si_gfx10;
field bits<8> VI = vi;
}
class MIMGLZMapping<MIMGBaseOpcode l, MIMGBaseOpcode lz> {
MIMGBaseOpcode L = l;
MIMGBaseOpcode LZ = lz;
}
def MIMGLZMappingTable : GenericTable {
let FilterClass = "MIMGLZMapping";
let CppTypeName = "MIMGLZMappingInfo";
let Fields = ["L", "LZ"];
GenericEnum TypeOf_L = MIMGBaseOpcode;
GenericEnum TypeOf_LZ = MIMGBaseOpcode;
let PrimaryKey = ["L"];
let PrimaryKeyName = "getMIMGLZMappingInfo";
}
class MIMGMIPMapping<MIMGBaseOpcode mip, MIMGBaseOpcode nonmip> {
MIMGBaseOpcode MIP = mip;
MIMGBaseOpcode NONMIP = nonmip;
}
def MIMGMIPMappingTable : GenericTable {
let FilterClass = "MIMGMIPMapping";
let CppTypeName = "MIMGMIPMappingInfo";
let Fields = ["MIP", "NONMIP"];
GenericEnum TypeOf_MIP = MIMGBaseOpcode;
GenericEnum TypeOf_NONMIP = MIMGBaseOpcode;
let PrimaryKey = ["MIP"];
let PrimaryKeyName = "getMIMGMIPMappingInfo";
}
class MIMGG16Mapping<MIMGBaseOpcode g, MIMGBaseOpcode g16> {
MIMGBaseOpcode G = g;
MIMGBaseOpcode G16 = g16;
}
def MIMGG16MappingTable : GenericTable {
let FilterClass = "MIMGG16Mapping";
let CppTypeName = "MIMGG16MappingInfo";
let Fields = ["G", "G16"];
GenericEnum TypeOf_G = MIMGBaseOpcode;
GenericEnum TypeOf_G16 = MIMGBaseOpcode;
let PrimaryKey = ["G"];
let PrimaryKeyName = "getMIMGG16MappingInfo";
}
class MIMG_Base <dag outs, string dns = "">
: InstSI <outs, (ins), "", []> {
let VM_CNT = 1;
let EXP_CNT = 1;
let MIMG = 1;
let Uses = [EXEC];
let mayLoad = 1;
let mayStore = 0;
let SchedRW = [WriteVMEM];
let UseNamedOperandTable = 1;
let hasSideEffects = 0; // XXX ????
let DecoderNamespace = dns;
let isAsmParserOnly = !eq(dns, "");
}
class MIMG <dag outs, string dns = "">
: MIMG_Base <outs, dns> {
let hasPostISelHook = 1;
let AsmMatchConverter = "cvtMIMG";
Instruction Opcode = !cast<Instruction>(NAME);
MIMGBaseOpcode BaseOpcode;
MIMGEncoding MIMGEncoding;
bits<8> VDataDwords;
bits<8> VAddrDwords;
}
def MIMGInfoTable : GenericTable {
let FilterClass = "MIMG";
let CppTypeName = "MIMGInfo";
let Fields = ["Opcode", "BaseOpcode", "MIMGEncoding", "VDataDwords", "VAddrDwords"];
GenericEnum TypeOf_BaseOpcode = MIMGBaseOpcode;
GenericEnum TypeOf_MIMGEncoding = MIMGEncoding;
let PrimaryKey = ["BaseOpcode", "MIMGEncoding", "VDataDwords", "VAddrDwords"];
let PrimaryKeyName = "getMIMGOpcodeHelper";
}
def getMIMGInfo : SearchIndex {
let Table = MIMGInfoTable;
let Key = ["Opcode"];
}
// This class used to use !foldl to memoize the AddrAsmNames list.
// It turned out that that was much slower than using !filter.
class MIMGNSAHelper<int num_addrs> {
list<string> AddrAsmNames =
!foreach(i, !filter(i, [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11],
!lt(i, num_addrs)), "vaddr" # i);
dag AddrIns = !dag(ins, !foreach(arg, AddrAsmNames, VGPR_32), AddrAsmNames);
string AddrAsm = "[$" # !interleave(AddrAsmNames, ", $") # "]";
int NSA = !if(!le(num_addrs, 1), ?,
!if(!le(num_addrs, 5), 1,
!if(!le(num_addrs, 9), 2,
!if(!le(num_addrs, 13), 3, ?))));
}
// Base class of all pre-gfx10 MIMG instructions.
class MIMG_gfx6789<bits<8> op, dag outs, string dns = "">
: MIMG<outs, dns>, MIMGe_gfx6789<op> {
let SubtargetPredicate = isGFX6GFX7GFX8GFX9;
let AssemblerPredicate = isGFX6GFX7GFX8GFX9;
let MIMGEncoding = MIMGEncGfx6;
let d16 = !if(BaseOpcode.HasD16, ?, 0);
}
// Base class of all non-NSA gfx10 MIMG instructions.
class MIMG_gfx10<int op, dag outs, string dns = "">
: MIMG<outs, dns>, MIMGe_gfx10<op> {
let SubtargetPredicate = isGFX10Plus;
let AssemblerPredicate = isGFX10Plus;
let MIMGEncoding = MIMGEncGfx10Default;
let d16 = !if(BaseOpcode.HasD16, ?, 0);
let nsa = 0;
}
// Base class for all NSA MIMG instructions. Note that 1-dword addresses always
// use non-NSA variants.
class MIMG_nsa_gfx10<int op, dag outs, int num_addrs, string dns="">
: MIMG<outs, dns>, MIMGe_gfx10<op> {
let SubtargetPredicate = isGFX10Plus;
let AssemblerPredicate = isGFX10Plus;
let MIMGEncoding = MIMGEncGfx10NSA;
MIMGNSAHelper nsah = MIMGNSAHelper<num_addrs>;
dag AddrIns = nsah.AddrIns;
string AddrAsm = nsah.AddrAsm;
let d16 = !if(BaseOpcode.HasD16, ?, 0);
let nsa = nsah.NSA;
}
class MIMG_NoSampler_Helper <bits<8> op, string asm,
RegisterClass dst_rc,
RegisterClass addr_rc,
string dns="">
: MIMG_gfx6789 <op, (outs dst_rc:$vdata), dns> {
let InOperandList = !con((ins addr_rc:$vaddr, SReg_256:$srsrc,
DMask:$dmask, UNorm:$unorm, GLC:$glc, SLC:$slc,
R128A16:$r128, TFE:$tfe, LWE:$lwe, DA:$da),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = asm#" $vdata, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da"
#!if(BaseOpcode.HasD16, "$d16", "");
}
class MIMG_NoSampler_gfx10<int op, string opcode,
RegisterClass DataRC, RegisterClass AddrRC,
string dns="">
: MIMG_gfx10<op, (outs DataRC:$vdata), dns> {
let InOperandList = !con((ins AddrRC:$vaddr0, SReg_256:$srsrc, DMask:$dmask,
Dim:$dim, UNorm:$unorm, DLC:$dlc, GLC:$glc,
SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = opcode#" $vdata, $vaddr0, $srsrc$dmask$dim$unorm$dlc$glc$slc$r128$a16$tfe$lwe"
#!if(BaseOpcode.HasD16, "$d16", "");
}
class MIMG_NoSampler_nsa_gfx10<int op, string opcode,
RegisterClass DataRC, int num_addrs,
string dns="">
: MIMG_nsa_gfx10<op, (outs DataRC:$vdata), num_addrs, dns> {
let InOperandList = !con(AddrIns,
(ins SReg_256:$srsrc, DMask:$dmask,
Dim:$dim, UNorm:$unorm, DLC:$dlc, GLC:$glc,
SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = opcode#" $vdata, "#AddrAsm#", $srsrc$dmask$dim$unorm$dlc$glc$slc$r128$a16$tfe$lwe"
#!if(BaseOpcode.HasD16, "$d16", "");
}
multiclass MIMG_NoSampler_Src_Helper <bits<8> op, string asm,
RegisterClass dst_rc,
bit enableDisasm> {
let ssamp = 0 in {
let VAddrDwords = 1 in {
def _V1 : MIMG_NoSampler_Helper <op, asm, dst_rc, VGPR_32,
!if(enableDisasm, "AMDGPU", "")>;
def _V1_gfx10 : MIMG_NoSampler_gfx10<op, asm, dst_rc, VGPR_32,
!if(enableDisasm, "AMDGPU", "")>;
}
let VAddrDwords = 2 in {
def _V2 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_64>;
def _V2_gfx10 : MIMG_NoSampler_gfx10<op, asm, dst_rc, VReg_64>;
def _V2_nsa_gfx10 : MIMG_NoSampler_nsa_gfx10<op, asm, dst_rc, 2>;
}
let VAddrDwords = 3 in {
def _V3 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_96>;
def _V3_gfx10 : MIMG_NoSampler_gfx10<op, asm, dst_rc, VReg_96>;
def _V3_nsa_gfx10 : MIMG_NoSampler_nsa_gfx10<op, asm, dst_rc, 3>;
}
let VAddrDwords = 4 in {
def _V4 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_128>;
def _V4_gfx10 : MIMG_NoSampler_gfx10<op, asm, dst_rc, VReg_128>;
def _V4_nsa_gfx10 : MIMG_NoSampler_nsa_gfx10<op, asm, dst_rc, 4,
!if(enableDisasm, "AMDGPU", "")>;
}
}
}
multiclass MIMG_NoSampler <bits<8> op, string asm, bit has_d16, bit mip = 0,
bit isResInfo = 0> {
def "" : MIMGBaseOpcode {
let Coordinates = !not(isResInfo);
let LodOrClampOrMip = mip;
let HasD16 = has_d16;
}
let BaseOpcode = !cast<MIMGBaseOpcode>(NAME),
mayLoad = !not(isResInfo) in {
let VDataDwords = 1 in
defm _V1 : MIMG_NoSampler_Src_Helper <op, asm, VGPR_32, 1>;
let VDataDwords = 2 in
defm _V2 : MIMG_NoSampler_Src_Helper <op, asm, VReg_64, 0>;
let VDataDwords = 3 in
defm _V3 : MIMG_NoSampler_Src_Helper <op, asm, VReg_96, 0>;
let VDataDwords = 4 in
defm _V4 : MIMG_NoSampler_Src_Helper <op, asm, VReg_128, 0>;
let VDataDwords = 5 in
defm _V5 : MIMG_NoSampler_Src_Helper <op, asm, VReg_160, 0>;
}
}
class MIMG_Store_Helper <bits<8> op, string asm,
RegisterClass data_rc,
RegisterClass addr_rc,
string dns = "">
: MIMG_gfx6789<op, (outs), dns> {
let InOperandList = !con((ins data_rc:$vdata, addr_rc:$vaddr, SReg_256:$srsrc,
DMask:$dmask, UNorm:$unorm, GLC:$glc, SLC:$slc,
R128A16:$r128, TFE:$tfe, LWE:$lwe, DA:$da),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = asm#" $vdata, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da"
#!if(BaseOpcode.HasD16, "$d16", "");
}
class MIMG_Store_gfx10<int op, string opcode,
RegisterClass DataRC, RegisterClass AddrRC,
string dns="">
: MIMG_gfx10<op, (outs), dns> {
let InOperandList = !con((ins DataRC:$vdata, AddrRC:$vaddr0, SReg_256:$srsrc,
DMask:$dmask, Dim:$dim, UNorm:$unorm, DLC:$dlc,
GLC:$glc, SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = opcode#" $vdata, $vaddr0, $srsrc$dmask$dim$unorm$dlc$glc$slc$r128$a16$tfe$lwe"
#!if(BaseOpcode.HasD16, "$d16", "");
}
class MIMG_Store_nsa_gfx10<int op, string opcode,
RegisterClass DataRC, int num_addrs,
string dns="">
: MIMG_nsa_gfx10<op, (outs), num_addrs, dns> {
let InOperandList = !con((ins DataRC:$vdata),
AddrIns,
(ins SReg_256:$srsrc, DMask:$dmask,
Dim:$dim, UNorm:$unorm, DLC:$dlc, GLC:$glc,
SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = opcode#" $vdata, "#AddrAsm#", $srsrc$dmask$dim$unorm$dlc$glc$slc$r128$a16$tfe$lwe"
#!if(BaseOpcode.HasD16, "$d16", "");
}
multiclass MIMG_Store_Addr_Helper <int op, string asm,
RegisterClass data_rc,
bit enableDisasm> {
let mayLoad = 0, mayStore = 1, hasSideEffects = 0, hasPostISelHook = 0,
DisableWQM = 1, ssamp = 0 in {
let VAddrDwords = 1 in {
def _V1 : MIMG_Store_Helper <op, asm, data_rc, VGPR_32,
!if(enableDisasm, "AMDGPU", "")>;
def _V1_gfx10 : MIMG_Store_gfx10 <op, asm, data_rc, VGPR_32,
!if(enableDisasm, "AMDGPU", "")>;
}
let VAddrDwords = 2 in {
def _V2 : MIMG_Store_Helper <op, asm, data_rc, VReg_64>;
def _V2_gfx10 : MIMG_Store_gfx10 <op, asm, data_rc, VReg_64>;
def _V2_nsa_gfx10 : MIMG_Store_nsa_gfx10 <op, asm, data_rc, 2>;
}
let VAddrDwords = 3 in {
def _V3 : MIMG_Store_Helper <op, asm, data_rc, VReg_96>;
def _V3_gfx10 : MIMG_Store_gfx10 <op, asm, data_rc, VReg_96>;
def _V3_nsa_gfx10 : MIMG_Store_nsa_gfx10 <op, asm, data_rc, 3>;
}
let VAddrDwords = 4 in {
def _V4 : MIMG_Store_Helper <op, asm, data_rc, VReg_128>;
def _V4_gfx10 : MIMG_Store_gfx10 <op, asm, data_rc, VReg_128>;
def _V4_nsa_gfx10 : MIMG_Store_nsa_gfx10 <op, asm, data_rc, 4,
!if(enableDisasm, "AMDGPU", "")>;
}
}
}
multiclass MIMG_Store <bits<8> op, string asm, bit has_d16, bit mip = 0> {
def "" : MIMGBaseOpcode {
let Store = 1;
let LodOrClampOrMip = mip;
let HasD16 = has_d16;
}
let BaseOpcode = !cast<MIMGBaseOpcode>(NAME) in {
let VDataDwords = 1 in
defm _V1 : MIMG_Store_Addr_Helper <op, asm, VGPR_32, 1>;
let VDataDwords = 2 in
defm _V2 : MIMG_Store_Addr_Helper <op, asm, VReg_64, 0>;
let VDataDwords = 3 in
defm _V3 : MIMG_Store_Addr_Helper <op, asm, VReg_96, 0>;
let VDataDwords = 4 in
defm _V4 : MIMG_Store_Addr_Helper <op, asm, VReg_128, 0>;
}
}
class MIMG_Atomic_gfx6789_base <bits<8> op, string asm, RegisterClass data_rc,
RegisterClass addr_rc, string dns="">
: MIMG_gfx6789 <op, (outs data_rc:$vdst), dns> {
let Constraints = "$vdst = $vdata";
let AsmMatchConverter = "cvtMIMGAtomic";
let InOperandList = (ins data_rc:$vdata, addr_rc:$vaddr, SReg_256:$srsrc,
DMask:$dmask, UNorm:$unorm, GLC:$glc, SLC:$slc,
R128A16:$r128, TFE:$tfe, LWE:$lwe, DA:$da);
let AsmString = asm#" $vdst, $vaddr, $srsrc$dmask$unorm$glc$slc$r128$tfe$lwe$da";
}
class MIMG_Atomic_si<mimg op, string asm, RegisterClass data_rc,
RegisterClass addr_rc, bit enableDasm = 0>
: MIMG_Atomic_gfx6789_base<op.SI_GFX10, asm, data_rc, addr_rc,
!if(enableDasm, "GFX6GFX7", "")> {
let AssemblerPredicate = isGFX6GFX7;
}
class MIMG_Atomic_vi<mimg op, string asm, RegisterClass data_rc,
RegisterClass addr_rc, bit enableDasm = 0>
: MIMG_Atomic_gfx6789_base<op.VI, asm, data_rc, addr_rc, !if(enableDasm, "GFX8", "")> {
let AssemblerPredicate = isGFX8GFX9;
let MIMGEncoding = MIMGEncGfx8;
}
class MIMG_Atomic_gfx10<mimg op, string opcode,
RegisterClass DataRC, RegisterClass AddrRC,
bit enableDisasm = 0>
: MIMG_gfx10<!cast<int>(op.SI_GFX10), (outs DataRC:$vdst),
!if(enableDisasm, "AMDGPU", "")> {
let Constraints = "$vdst = $vdata";
let AsmMatchConverter = "cvtMIMGAtomic";
let InOperandList = (ins DataRC:$vdata, AddrRC:$vaddr0, SReg_256:$srsrc,
DMask:$dmask, Dim:$dim, UNorm:$unorm, DLC:$dlc,
GLC:$glc, SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe);
let AsmString = opcode#" $vdst, $vaddr0, $srsrc$dmask$dim$unorm$dlc$glc$slc$r128$a16$tfe$lwe";
}
class MIMG_Atomic_nsa_gfx10<mimg op, string opcode,
RegisterClass DataRC, int num_addrs,
bit enableDisasm = 0>
: MIMG_nsa_gfx10<!cast<int>(op.SI_GFX10), (outs DataRC:$vdst), num_addrs,
!if(enableDisasm, "AMDGPU", "")> {
let Constraints = "$vdst = $vdata";
let AsmMatchConverter = "cvtMIMGAtomic";
let InOperandList = !con((ins DataRC:$vdata),
AddrIns,
(ins SReg_256:$srsrc, DMask:$dmask,
Dim:$dim, UNorm:$unorm, DLC:$dlc, GLC:$glc,
SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe));
let AsmString = opcode#" $vdata, "#AddrAsm#", $srsrc$dmask$dim$unorm$dlc$glc$slc$r128$a16$tfe$lwe";
}
multiclass MIMG_Atomic_Addr_Helper_m <mimg op, string asm,
RegisterClass data_rc,
bit enableDasm = 0> {
let hasSideEffects = 1, // FIXME: remove this
mayLoad = 1, mayStore = 1, hasPostISelHook = 0, DisableWQM = 1,
ssamp = 0 in {
let VAddrDwords = 1 in {
def _V1_si : MIMG_Atomic_si <op, asm, data_rc, VGPR_32, enableDasm>;
def _V1_vi : MIMG_Atomic_vi <op, asm, data_rc, VGPR_32, enableDasm>;
def _V1_gfx10 : MIMG_Atomic_gfx10 <op, asm, data_rc, VGPR_32, enableDasm>;
}
let VAddrDwords = 2 in {
def _V2_si : MIMG_Atomic_si <op, asm, data_rc, VReg_64, 0>;
def _V2_vi : MIMG_Atomic_vi <op, asm, data_rc, VReg_64, 0>;
def _V2_gfx10 : MIMG_Atomic_gfx10 <op, asm, data_rc, VReg_64, 0>;
def _V2_nsa_gfx10 : MIMG_Atomic_nsa_gfx10 <op, asm, data_rc, 2, 0>;
}
let VAddrDwords = 3 in {
def _V3_si : MIMG_Atomic_si <op, asm, data_rc, VReg_96, 0>;
def _V3_vi : MIMG_Atomic_vi <op, asm, data_rc, VReg_96, 0>;
def _V3_gfx10 : MIMG_Atomic_gfx10 <op, asm, data_rc, VReg_96, 0>;
def _V3_nsa_gfx10 : MIMG_Atomic_nsa_gfx10 <op, asm, data_rc, 3, 0>;
}
let VAddrDwords = 4 in {
def _V4_si : MIMG_Atomic_si <op, asm, data_rc, VReg_128, 0>;
def _V4_vi : MIMG_Atomic_vi <op, asm, data_rc, VReg_128, 0>;
def _V4_gfx10 : MIMG_Atomic_gfx10 <op, asm, data_rc, VReg_128, 0>;
def _V4_nsa_gfx10 : MIMG_Atomic_nsa_gfx10 <op, asm, data_rc, 4, enableDasm>;
}
}
}
multiclass MIMG_Atomic <mimg op, string asm, bit isCmpSwap = 0> { // 64-bit atomics
def "" : MIMGBaseOpcode {
let Atomic = 1;
let AtomicX2 = isCmpSwap;
}
let BaseOpcode = !cast<MIMGBaseOpcode>(NAME) in {
// _V* variants have different dst size, but the size is encoded implicitly,
// using dmask and tfe. Only 32-bit variant is registered with disassembler.
// Other variants are reconstructed by disassembler using dmask and tfe.
let VDataDwords = !if(isCmpSwap, 2, 1) in
defm _V1 : MIMG_Atomic_Addr_Helper_m <op, asm, !if(isCmpSwap, VReg_64, VGPR_32), 1>;
let VDataDwords = !if(isCmpSwap, 4, 2) in
defm _V2 : MIMG_Atomic_Addr_Helper_m <op, asm, !if(isCmpSwap, VReg_128, VReg_64)>;
}
}
class MIMG_Sampler_Helper <bits<8> op, string asm, RegisterClass dst_rc,
RegisterClass src_rc, string dns="">
: MIMG_gfx6789 <op, (outs dst_rc:$vdata), dns> {
let InOperandList = !con((ins src_rc:$vaddr, SReg_256:$srsrc, SReg_128:$ssamp,
DMask:$dmask, UNorm:$unorm, GLC:$glc, SLC:$slc,
R128A16:$r128, TFE:$tfe, LWE:$lwe, DA:$da),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = asm#" $vdata, $vaddr, $srsrc, $ssamp$dmask$unorm$glc$slc$r128$tfe$lwe$da"
#!if(BaseOpcode.HasD16, "$d16", "");
}
class MIMG_Sampler_gfx10<int op, string opcode,
RegisterClass DataRC, RegisterClass AddrRC,
string dns="">
: MIMG_gfx10<op, (outs DataRC:$vdata), dns> {
let InOperandList = !con((ins AddrRC:$vaddr0, SReg_256:$srsrc, SReg_128:$ssamp,
DMask:$dmask, Dim:$dim, UNorm:$unorm, DLC:$dlc,
GLC:$glc, SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = opcode#" $vdata, $vaddr0, $srsrc, $ssamp$dmask$dim$unorm"
#"$dlc$glc$slc$r128$a16$tfe$lwe"
#!if(BaseOpcode.HasD16, "$d16", "");
}
class MIMG_Sampler_nsa_gfx10<int op, string opcode,
RegisterClass DataRC, int num_addrs,
string dns="">
: MIMG_nsa_gfx10<op, (outs DataRC:$vdata), num_addrs, dns> {
let InOperandList = !con(AddrIns,
(ins SReg_256:$srsrc, SReg_128:$ssamp, DMask:$dmask,
Dim:$dim, UNorm:$unorm, DLC:$dlc, GLC:$glc,
SLC:$slc, R128A16:$r128, GFX10A16:$a16, TFE:$tfe, LWE:$lwe),
!if(BaseOpcode.HasD16, (ins D16:$d16), (ins)));
let AsmString = opcode#" $vdata, "#AddrAsm#", $srsrc, $ssamp$dmask$dim$unorm"
#"$dlc$glc$slc$r128$a16$tfe$lwe"
#!if(BaseOpcode.HasD16, "$d16", "");
}
class MIMGAddrSize<int dw, bit enable_disasm> {
int NumWords = dw;
RegisterClass RegClass = !if(!le(NumWords, 0), ?,
!if(!eq(NumWords, 1), VGPR_32,
!if(!eq(NumWords, 2), VReg_64,
!if(!eq(NumWords, 3), VReg_96,
!if(!eq(NumWords, 4), VReg_128,
!if(!le(NumWords, 8), VReg_256,
!if(!le(NumWords, 16), VReg_512, ?)))))));
// Whether the instruction variant with this vaddr size should be enabled for
// the auto-generated disassembler.
bit Disassemble = enable_disasm;
}
// Return whether x is in lst.
class isIntInList<int x, list<int> lst> {
bit ret = !foldl(0, lst, lhs, y, !or(lhs, !eq(x, y)));
}
// Return whether a value inside the range [min, max] (endpoints inclusive)
// is in the given list.
class isRangeInList<int min, int max, list<int> lst> {
bit ret = !foldl(0, lst, lhs, y, !or(lhs, !and(!le(min, y), !le(y, max))));
}
class MIMGAddrSizes_tmp<list<MIMGAddrSize> lst, int min> {
list<MIMGAddrSize> List = lst;
int Min = min;
}
class MIMG_Sampler_AddrSizes<AMDGPUSampleVariant sample> {
// List of all possible numbers of address words, taking all combinations of
// A16 and image dimension into account (note: no MSAA, since this is for
// sample/gather ops).
list<int> AllNumAddrWords =
!foreach(dw, !if(sample.Gradients,
!if(!eq(sample.LodOrClamp, ""),
[2, 3, 4, 5, 6, 7, 9],
[2, 3, 4, 5, 7, 8, 10]),
!if(!eq(sample.LodOrClamp, ""),
[1, 2, 3],
[1, 2, 3, 4])),
!add(dw, !size(sample.ExtraAddrArgs)));
// Generate machine instructions based on possible register classes for the
// required numbers of address words. The disassembler defaults to the
// smallest register class.
list<MIMGAddrSize> MachineInstrs =
!foldl(MIMGAddrSizes_tmp<[], 0>, [1, 2, 3, 4, 8, 16], lhs, dw,
!if(isRangeInList<lhs.Min, dw, AllNumAddrWords>.ret,
MIMGAddrSizes_tmp<
!listconcat(lhs.List, [MIMGAddrSize<dw, !empty(lhs.List)>]),
!if(!eq(dw, 3), 3, !add(dw, 1))>, // we still need _V4 for codegen w/ 3 dwords
lhs)).List;
// For NSA, generate machine instructions for all possible numbers of words
// except 1 (which is already covered by the non-NSA case).
// The disassembler defaults to the largest number of arguments among the
// variants with the same number of NSA words, and custom code then derives
// the exact variant based on the sample variant and the image dimension.
list<MIMGAddrSize> NSAInstrs =
!foldl([]<MIMGAddrSize>, [[12, 11, 10], [9, 8, 7, 6], [5, 4, 3, 2]], prev, nsa_group,
!listconcat(prev,
!foldl([]<MIMGAddrSize>, nsa_group, lhs, dw,
!if(isIntInList<dw, AllNumAddrWords>.ret,
!listconcat(lhs, [MIMGAddrSize<dw, !empty(lhs)>]),
lhs))));
}
multiclass MIMG_Sampler_Src_Helper <bits<8> op, string asm,
AMDGPUSampleVariant sample, RegisterClass dst_rc,
bit enableDisasm = 0> {
foreach addr = MIMG_Sampler_AddrSizes<sample>.MachineInstrs in {
let VAddrDwords = addr.NumWords in {
def _V # addr.NumWords
: MIMG_Sampler_Helper <op, asm, dst_rc, addr.RegClass,
!if(!and(enableDisasm, addr.Disassemble), "AMDGPU", "")>;
def _V # addr.NumWords # _gfx10
: MIMG_Sampler_gfx10 <op, asm, dst_rc, addr.RegClass,
!if(!and(enableDisasm, addr.Disassemble), "AMDGPU", "")>;
}
}
foreach addr = MIMG_Sampler_AddrSizes<sample>.NSAInstrs in {
let VAddrDwords = addr.NumWords in {
def _V # addr.NumWords # _nsa_gfx10
: MIMG_Sampler_nsa_gfx10<op, asm, dst_rc, addr.NumWords,
!if(!and(enableDisasm, addr.Disassemble), "AMDGPU", "")>;
}
}
}
class MIMG_Sampler_BaseOpcode<AMDGPUSampleVariant sample>
: MIMGBaseOpcode {
let Sampler = 1;
let NumExtraArgs = !size(sample.ExtraAddrArgs);
let Gradients = sample.Gradients;
let LodOrClampOrMip = !ne(sample.LodOrClamp, "");
}
multiclass MIMG_Sampler <bits<8> op, AMDGPUSampleVariant sample, bit wqm = 0,
bit isG16 = 0, bit isGetLod = 0,
string asm = "image_sample"#sample.LowerCaseMod#!if(isG16, "_g16", "")> {
def "" : MIMG_Sampler_BaseOpcode<sample> {
let HasD16 = !not(isGetLod);
let G16 = isG16;
}
let BaseOpcode = !cast<MIMGBaseOpcode>(NAME), WQM = wqm,
mayLoad = !not(isGetLod) in {
let VDataDwords = 1 in
defm _V1 : MIMG_Sampler_Src_Helper<op, asm, sample, VGPR_32, 1>;
let VDataDwords = 2 in
defm _V2 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_64>;
let VDataDwords = 3 in
defm _V3 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_96>;
let VDataDwords = 4 in
defm _V4 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_128>;
let VDataDwords = 5 in
defm _V5 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_160>;
}
}
multiclass MIMG_Sampler_WQM <bits<8> op, AMDGPUSampleVariant sample>
: MIMG_Sampler<op, sample, 1>;
multiclass MIMG_Gather <bits<8> op, AMDGPUSampleVariant sample, bit wqm = 0,
string asm = "image_gather4"#sample.LowerCaseMod> {
def "" : MIMG_Sampler_BaseOpcode<sample> {
let HasD16 = 1;
let Gather4 = 1;
}
let BaseOpcode = !cast<MIMGBaseOpcode>(NAME), WQM = wqm,
Gather4 = 1, hasPostISelHook = 0 in {
let VDataDwords = 2 in
defm _V2 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_64>; /* for packed D16 only */
let VDataDwords = 4 in
defm _V4 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_128, 1>;
let VDataDwords = 5 in
defm _V5 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_160>;
}
}
multiclass MIMG_Gather_WQM <bits<8> op, AMDGPUSampleVariant sample>
: MIMG_Gather<op, sample, 1>;
class MIMG_IntersectRay_gfx10<int op, string opcode, RegisterClass AddrRC, bit A16>
: MIMG_gfx10<op, (outs VReg_128:$vdata), "AMDGPU"> {
let InOperandList = !con((ins AddrRC:$vaddr0, SReg_128:$srsrc),
!if(A16, (ins GFX10A16:$a16), (ins)));
let AsmString = opcode#" $vdata, $vaddr0, $srsrc"#!if(A16, "$a16", "");
let nsa = 0;
}
class MIMG_IntersectRay_nsa_gfx10<int op, string opcode, int num_addrs, bit A16>
: MIMG_nsa_gfx10<op, (outs VReg_128:$vdata), num_addrs, "AMDGPU"> {
let InOperandList = !con(nsah.AddrIns,
(ins SReg_128:$srsrc),
!if(A16, (ins GFX10A16:$a16), (ins)));
let AsmString = opcode#" $vdata, "#nsah.AddrAsm#", $srsrc"#!if(A16, "$a16", "");
}
multiclass MIMG_IntersectRay<int op, string opcode, int num_addrs, bit A16> {
def "" : MIMGBaseOpcode;
let SubtargetPredicate = HasGFX10_BEncoding,
AssemblerPredicate = HasGFX10_BEncoding,
AsmMatchConverter = !if(A16, "cvtIntersectRay", ""),
dmask = 0xf,
unorm = 1,
d16 = 0,
glc = 0,
slc = 0,
dlc = 0,
tfe = 0,
lwe = 0,
r128 = 1,
ssamp = 0,
dim = {0, 0, 0},
a16 = A16,
d16 = 0,
BaseOpcode = !cast<MIMGBaseOpcode>(NAME),
VDataDwords = 4 in {
// TODO: MIMGAddrSize will choose VReg_512 which is a 16 register tuple,
// when we only need 9, 11 or 12 depending on A16 field and ptr size.
def "_sa" : MIMG_IntersectRay_gfx10<op, opcode, MIMGAddrSize<num_addrs, 0>.RegClass, A16> {
let VAddrDwords = !srl(MIMGAddrSize<num_addrs, 0>.RegClass.Size, 5);
}
def _nsa : MIMG_IntersectRay_nsa_gfx10<op, opcode, num_addrs, A16> {
let VAddrDwords = num_addrs;
}
}
}
//===----------------------------------------------------------------------===//
// MIMG Instructions
//===----------------------------------------------------------------------===//
defm IMAGE_LOAD : MIMG_NoSampler <0x00000000, "image_load", 1>;
defm IMAGE_LOAD_MIP : MIMG_NoSampler <0x00000001, "image_load_mip", 1, 1>;
defm IMAGE_LOAD_PCK : MIMG_NoSampler <0x00000002, "image_load_pck", 0>;
defm IMAGE_LOAD_PCK_SGN : MIMG_NoSampler <0x00000003, "image_load_pck_sgn", 0>;
defm IMAGE_LOAD_MIP_PCK : MIMG_NoSampler <0x00000004, "image_load_mip_pck", 0, 1>;
defm IMAGE_LOAD_MIP_PCK_SGN : MIMG_NoSampler <0x00000005, "image_load_mip_pck_sgn", 0, 1>;
defm IMAGE_STORE : MIMG_Store <0x00000008, "image_store", 1>;
defm IMAGE_STORE_MIP : MIMG_Store <0x00000009, "image_store_mip", 1, 1>;
defm IMAGE_STORE_PCK : MIMG_Store <0x0000000a, "image_store_pck", 0>;
defm IMAGE_STORE_MIP_PCK : MIMG_Store <0x0000000b, "image_store_mip_pck", 0, 1>;
defm IMAGE_GET_RESINFO : MIMG_NoSampler <0x0000000e, "image_get_resinfo", 0, 1, 1>;
defm IMAGE_ATOMIC_SWAP : MIMG_Atomic <mimg<0x0f, 0x10>, "image_atomic_swap">;
defm IMAGE_ATOMIC_CMPSWAP : MIMG_Atomic <mimg<0x10, 0x11>, "image_atomic_cmpswap", 1>;
defm IMAGE_ATOMIC_ADD : MIMG_Atomic <mimg<0x11, 0x12>, "image_atomic_add">;
defm IMAGE_ATOMIC_SUB : MIMG_Atomic <mimg<0x12, 0x13>, "image_atomic_sub">;
//def IMAGE_ATOMIC_RSUB : MIMG_NoPattern_ <"image_atomic_rsub", 0x00000013>; -- not on VI
defm IMAGE_ATOMIC_SMIN : MIMG_Atomic <mimg<0x14>, "image_atomic_smin">;
defm IMAGE_ATOMIC_UMIN : MIMG_Atomic <mimg<0x15>, "image_atomic_umin">;
defm IMAGE_ATOMIC_SMAX : MIMG_Atomic <mimg<0x16>, "image_atomic_smax">;
defm IMAGE_ATOMIC_UMAX : MIMG_Atomic <mimg<0x17>, "image_atomic_umax">;
defm IMAGE_ATOMIC_AND : MIMG_Atomic <mimg<0x18>, "image_atomic_and">;
defm IMAGE_ATOMIC_OR : MIMG_Atomic <mimg<0x19>, "image_atomic_or">;
defm IMAGE_ATOMIC_XOR : MIMG_Atomic <mimg<0x1a>, "image_atomic_xor">;
defm IMAGE_ATOMIC_INC : MIMG_Atomic <mimg<0x1b>, "image_atomic_inc">;
defm IMAGE_ATOMIC_DEC : MIMG_Atomic <mimg<0x1c>, "image_atomic_dec">;
//let FPAtomic = 1 in {
//def IMAGE_ATOMIC_FCMPSWAP : MIMG_NoPattern_ <"image_atomic_fcmpswap", 0x0000001d, 1>; -- not on VI
//def IMAGE_ATOMIC_FMIN : MIMG_NoPattern_ <"image_atomic_fmin", 0x0000001e>; -- not on VI
//def IMAGE_ATOMIC_FMAX : MIMG_NoPattern_ <"image_atomic_fmax", 0x0000001f>; -- not on VI
//} // End let FPAtomic = 1
defm IMAGE_SAMPLE : MIMG_Sampler_WQM <0x00000020, AMDGPUSample>;
defm IMAGE_SAMPLE_CL : MIMG_Sampler_WQM <0x00000021, AMDGPUSample_cl>;
defm IMAGE_SAMPLE_D : MIMG_Sampler <0x00000022, AMDGPUSample_d>;
defm IMAGE_SAMPLE_D_CL : MIMG_Sampler <0x00000023, AMDGPUSample_d_cl>;
defm IMAGE_SAMPLE_D_G16 : MIMG_Sampler <0x000000a2, AMDGPUSample_d, 0, 1>;
defm IMAGE_SAMPLE_D_CL_G16 : MIMG_Sampler <0x000000a3, AMDGPUSample_d_cl, 0, 1>;
defm IMAGE_SAMPLE_L : MIMG_Sampler <0x00000024, AMDGPUSample_l>;
defm IMAGE_SAMPLE_B : MIMG_Sampler_WQM <0x00000025, AMDGPUSample_b>;
defm IMAGE_SAMPLE_B_CL : MIMG_Sampler_WQM <0x00000026, AMDGPUSample_b_cl>;
defm IMAGE_SAMPLE_LZ : MIMG_Sampler <0x00000027, AMDGPUSample_lz>;
defm IMAGE_SAMPLE_C : MIMG_Sampler_WQM <0x00000028, AMDGPUSample_c>;
defm IMAGE_SAMPLE_C_CL : MIMG_Sampler_WQM <0x00000029, AMDGPUSample_c_cl>;
defm IMAGE_SAMPLE_C_D : MIMG_Sampler <0x0000002a, AMDGPUSample_c_d>;
defm IMAGE_SAMPLE_C_D_CL : MIMG_Sampler <0x0000002b, AMDGPUSample_c_d_cl>;
defm IMAGE_SAMPLE_C_D_G16 : MIMG_Sampler <0x000000aa, AMDGPUSample_c_d, 0, 1>;
defm IMAGE_SAMPLE_C_D_CL_G16 : MIMG_Sampler <0x000000ab, AMDGPUSample_c_d_cl, 0, 1>;
defm IMAGE_SAMPLE_C_L : MIMG_Sampler <0x0000002c, AMDGPUSample_c_l>;
defm IMAGE_SAMPLE_C_B : MIMG_Sampler_WQM <0x0000002d, AMDGPUSample_c_b>;
defm IMAGE_SAMPLE_C_B_CL : MIMG_Sampler_WQM <0x0000002e, AMDGPUSample_c_b_cl>;
defm IMAGE_SAMPLE_C_LZ : MIMG_Sampler <0x0000002f, AMDGPUSample_c_lz>;
defm IMAGE_SAMPLE_O : MIMG_Sampler_WQM <0x00000030, AMDGPUSample_o>;
defm IMAGE_SAMPLE_CL_O : MIMG_Sampler_WQM <0x00000031, AMDGPUSample_cl_o>;
defm IMAGE_SAMPLE_D_O : MIMG_Sampler <0x00000032, AMDGPUSample_d_o>;
defm IMAGE_SAMPLE_D_CL_O : MIMG_Sampler <0x00000033, AMDGPUSample_d_cl_o>;
defm IMAGE_SAMPLE_D_O_G16 : MIMG_Sampler <0x000000b2, AMDGPUSample_d_o, 0, 1>;
defm IMAGE_SAMPLE_D_CL_O_G16 : MIMG_Sampler <0x000000b3, AMDGPUSample_d_cl_o, 0, 1>;
defm IMAGE_SAMPLE_L_O : MIMG_Sampler <0x00000034, AMDGPUSample_l_o>;
defm IMAGE_SAMPLE_B_O : MIMG_Sampler_WQM <0x00000035, AMDGPUSample_b_o>;
defm IMAGE_SAMPLE_B_CL_O : MIMG_Sampler_WQM <0x00000036, AMDGPUSample_b_cl_o>;
defm IMAGE_SAMPLE_LZ_O : MIMG_Sampler <0x00000037, AMDGPUSample_lz_o>;
defm IMAGE_SAMPLE_C_O : MIMG_Sampler_WQM <0x00000038, AMDGPUSample_c_o>;
defm IMAGE_SAMPLE_C_CL_O : MIMG_Sampler_WQM <0x00000039, AMDGPUSample_c_cl_o>;
defm IMAGE_SAMPLE_C_D_O : MIMG_Sampler <0x0000003a, AMDGPUSample_c_d_o>;
defm IMAGE_SAMPLE_C_D_CL_O : MIMG_Sampler <0x0000003b, AMDGPUSample_c_d_cl_o>;
defm IMAGE_SAMPLE_C_D_O_G16 : MIMG_Sampler <0x000000ba, AMDGPUSample_c_d_o, 0, 1>;
defm IMAGE_SAMPLE_C_D_CL_O_G16 : MIMG_Sampler <0x000000bb, AMDGPUSample_c_d_cl_o, 0, 1>;
defm IMAGE_SAMPLE_C_L_O : MIMG_Sampler <0x0000003c, AMDGPUSample_c_l_o>;
defm IMAGE_SAMPLE_C_B_CL_O : MIMG_Sampler_WQM <0x0000003e, AMDGPUSample_c_b_cl_o>;
defm IMAGE_SAMPLE_C_B_O : MIMG_Sampler_WQM <0x0000003d, AMDGPUSample_c_b_o>;
defm IMAGE_SAMPLE_C_LZ_O : MIMG_Sampler <0x0000003f, AMDGPUSample_c_lz_o>;
defm IMAGE_GATHER4 : MIMG_Gather_WQM <0x00000040, AMDGPUSample>;
defm IMAGE_GATHER4_CL : MIMG_Gather_WQM <0x00000041, AMDGPUSample_cl>;
defm IMAGE_GATHER4_L : MIMG_Gather <0x00000044, AMDGPUSample_l>;
defm IMAGE_GATHER4_B : MIMG_Gather_WQM <0x00000045, AMDGPUSample_b>;
defm IMAGE_GATHER4_B_CL : MIMG_Gather_WQM <0x00000046, AMDGPUSample_b_cl>;
defm IMAGE_GATHER4_LZ : MIMG_Gather <0x00000047, AMDGPUSample_lz>;
defm IMAGE_GATHER4_C : MIMG_Gather_WQM <0x00000048, AMDGPUSample_c>;
defm IMAGE_GATHER4_C_CL : MIMG_Gather_WQM <0x00000049, AMDGPUSample_c_cl>;
defm IMAGE_GATHER4_C_L : MIMG_Gather <0x0000004c, AMDGPUSample_c_l>;
defm IMAGE_GATHER4_C_B : MIMG_Gather_WQM <0x0000004d, AMDGPUSample_c_b>;
defm IMAGE_GATHER4_C_B_CL : MIMG_Gather_WQM <0x0000004e, AMDGPUSample_c_b_cl>;
defm IMAGE_GATHER4_C_LZ : MIMG_Gather <0x0000004f, AMDGPUSample_c_lz>;
defm IMAGE_GATHER4_O : MIMG_Gather_WQM <0x00000050, AMDGPUSample_o>;
defm IMAGE_GATHER4_CL_O : MIMG_Gather_WQM <0x00000051, AMDGPUSample_cl_o>;
defm IMAGE_GATHER4_L_O : MIMG_Gather <0x00000054, AMDGPUSample_l_o>;
defm IMAGE_GATHER4_B_O : MIMG_Gather_WQM <0x00000055, AMDGPUSample_b_o>;
defm IMAGE_GATHER4_B_CL_O : MIMG_Gather <0x00000056, AMDGPUSample_b_cl_o>;
defm IMAGE_GATHER4_LZ_O : MIMG_Gather <0x00000057, AMDGPUSample_lz_o>;
defm IMAGE_GATHER4_C_O : MIMG_Gather_WQM <0x00000058, AMDGPUSample_c_o>;
defm IMAGE_GATHER4_C_CL_O : MIMG_Gather_WQM <0x00000059, AMDGPUSample_c_cl_o>;
defm IMAGE_GATHER4_C_L_O : MIMG_Gather <0x0000005c, AMDGPUSample_c_l_o>;
defm IMAGE_GATHER4_C_B_O : MIMG_Gather_WQM <0x0000005d, AMDGPUSample_c_b_o>;
defm IMAGE_GATHER4_C_B_CL_O : MIMG_Gather_WQM <0x0000005e, AMDGPUSample_c_b_cl_o>;
defm IMAGE_GATHER4_C_LZ_O : MIMG_Gather <0x0000005f, AMDGPUSample_c_lz_o>;
defm IMAGE_GET_LOD : MIMG_Sampler <0x00000060, AMDGPUSample, 1, 0, 1, "image_get_lod">;
defm IMAGE_SAMPLE_CD : MIMG_Sampler <0x00000068, AMDGPUSample_cd>;
defm IMAGE_SAMPLE_CD_CL : MIMG_Sampler <0x00000069, AMDGPUSample_cd_cl>;
defm IMAGE_SAMPLE_C_CD : MIMG_Sampler <0x0000006a, AMDGPUSample_c_cd>;
defm IMAGE_SAMPLE_C_CD_CL : MIMG_Sampler <0x0000006b, AMDGPUSample_c_cd_cl>;
defm IMAGE_SAMPLE_CD_O : MIMG_Sampler <0x0000006c, AMDGPUSample_cd_o>;
defm IMAGE_SAMPLE_CD_CL_O : MIMG_Sampler <0x0000006d, AMDGPUSample_cd_cl_o>;
defm IMAGE_SAMPLE_C_CD_O : MIMG_Sampler <0x0000006e, AMDGPUSample_c_cd_o>;
defm IMAGE_SAMPLE_C_CD_CL_O : MIMG_Sampler <0x0000006f, AMDGPUSample_c_cd_cl_o>;
defm IMAGE_SAMPLE_CD_G16 : MIMG_Sampler <0x000000e8, AMDGPUSample_cd, 0, 1>;
defm IMAGE_SAMPLE_CD_CL_G16 : MIMG_Sampler <0x000000e9, AMDGPUSample_cd_cl, 0, 1>;
defm IMAGE_SAMPLE_C_CD_G16 : MIMG_Sampler <0x000000ea, AMDGPUSample_c_cd, 0, 1>;
defm IMAGE_SAMPLE_C_CD_CL_G16 : MIMG_Sampler <0x000000eb, AMDGPUSample_c_cd_cl, 0, 1>;
defm IMAGE_SAMPLE_CD_O_G16 : MIMG_Sampler <0x000000ec, AMDGPUSample_cd_o, 0, 1>;
defm IMAGE_SAMPLE_CD_CL_O_G16 : MIMG_Sampler <0x000000ed, AMDGPUSample_cd_cl_o, 0, 1>;
defm IMAGE_SAMPLE_C_CD_O_G16 : MIMG_Sampler <0x000000ee, AMDGPUSample_c_cd_o, 0, 1>;
defm IMAGE_SAMPLE_C_CD_CL_O_G16 : MIMG_Sampler <0x000000ef, AMDGPUSample_c_cd_cl_o, 0, 1>;
//def IMAGE_RSRC256 : MIMG_NoPattern_RSRC256 <"image_rsrc256", 0x0000007e>;
//def IMAGE_SAMPLER : MIMG_NoPattern_ <"image_sampler", 0x0000007f>;
let SubtargetPredicate = HasGFX10_BEncoding in
defm IMAGE_MSAA_LOAD : MIMG_NoSampler <0x00000080, "image_msaa_load", 1>;
defm IMAGE_BVH_INTERSECT_RAY : MIMG_IntersectRay<0xe6, "image_bvh_intersect_ray", 11, 0>;
defm IMAGE_BVH_INTERSECT_RAY_a16 : MIMG_IntersectRay<0xe6, "image_bvh_intersect_ray", 8, 1>;
defm IMAGE_BVH64_INTERSECT_RAY : MIMG_IntersectRay<0xe7, "image_bvh64_intersect_ray", 12, 0>;
defm IMAGE_BVH64_INTERSECT_RAY_a16 : MIMG_IntersectRay<0xe7, "image_bvh64_intersect_ray", 9, 1>;
/********** ========================================= **********/
/********** Table of dimension-aware image intrinsics **********/
/********** ========================================= **********/
class ImageDimIntrinsicInfo<AMDGPUImageDimIntrinsic I> {
Intrinsic Intr = I;
MIMGBaseOpcode BaseOpcode = !cast<MIMGBaseOpcode>(!strconcat("IMAGE_", I.P.OpMod));
AMDGPUDimProps Dim = I.P.Dim;
AMDGPUImageDimIntrinsicEval DimEval = AMDGPUImageDimIntrinsicEval<I.P>;
bits<8> NumGradients = DimEval.NumGradientArgs;
bits<8> NumDmask = DimEval.NumDmaskArgs;
bits<8> NumData = DimEval.NumDataArgs;
bits<8> NumVAddrs = DimEval.NumVAddrArgs;
bits<8> NumArgs = !add(DimEval.CachePolicyArgIndex, 1);
bits<8> DMaskIndex = DimEval.DmaskArgIndex;
bits<8> VAddrStart = DimEval.VAddrArgIndex;
bits<8> GradientStart = DimEval.GradientArgIndex;
bits<8> CoordStart = DimEval.CoordArgIndex;
bits<8> LodIndex = DimEval.LodArgIndex;
bits<8> MipIndex = DimEval.MipArgIndex;
bits<8> VAddrEnd = !add(DimEval.VAddrArgIndex, DimEval.NumVAddrArgs);
bits<8> RsrcIndex = DimEval.RsrcArgIndex;
bits<8> SampIndex = DimEval.SampArgIndex;
bits<8> UnormIndex = DimEval.UnormArgIndex;
bits<8> TexFailCtrlIndex = DimEval.TexFailCtrlArgIndex;
bits<8> CachePolicyIndex = DimEval.CachePolicyArgIndex;
bits<8> GradientTyArg = !add(I.P.NumRetAndDataAnyTypes,
!foldl(0, I.P.ExtraAddrArgs, cnt, arg, !add(cnt, arg.Type.isAny)));
bits<8> CoordTyArg = !add(GradientTyArg, !if(I.P.Gradients, 1, 0));
}
def ImageDimIntrinsicTable : GenericTable {
let FilterClass = "ImageDimIntrinsicInfo";
let Fields = ["Intr", "BaseOpcode", "Dim", "NumGradients", "NumDmask", "NumData", "NumVAddrs", "NumArgs",
"DMaskIndex", "VAddrStart", "GradientStart", "CoordStart", "LodIndex", "MipIndex", "VAddrEnd",
"RsrcIndex", "SampIndex", "UnormIndex", "TexFailCtrlIndex", "CachePolicyIndex",
"GradientTyArg", "CoordTyArg"];
GenericEnum TypeOf_BaseOpcode = MIMGBaseOpcode;
GenericEnum TypeOf_Dim = MIMGDim;
let PrimaryKey = ["Intr"];
let PrimaryKeyName = "getImageDimIntrinsicInfo";
let PrimaryKeyEarlyOut = 1;
}
def getImageDimInstrinsicByBaseOpcode : SearchIndex {
let Table = ImageDimIntrinsicTable;
let Key = ["BaseOpcode", "Dim"];
}
foreach intr = !listconcat(AMDGPUImageDimIntrinsics,
AMDGPUImageDimAtomicIntrinsics) in {
def : ImageDimIntrinsicInfo<intr>;
}
// L to LZ Optimization Mapping
def : MIMGLZMapping<IMAGE_SAMPLE_L, IMAGE_SAMPLE_LZ>;
def : MIMGLZMapping<IMAGE_SAMPLE_C_L, IMAGE_SAMPLE_C_LZ>;
def : MIMGLZMapping<IMAGE_SAMPLE_L_O, IMAGE_SAMPLE_LZ_O>;
def : MIMGLZMapping<IMAGE_SAMPLE_C_L_O, IMAGE_SAMPLE_C_LZ_O>;
def : MIMGLZMapping<IMAGE_GATHER4_L, IMAGE_GATHER4_LZ>;
def : MIMGLZMapping<IMAGE_GATHER4_C_L, IMAGE_GATHER4_C_LZ>;
def : MIMGLZMapping<IMAGE_GATHER4_L_O, IMAGE_GATHER4_LZ_O>;
def : MIMGLZMapping<IMAGE_GATHER4_C_L_O, IMAGE_GATHER4_C_LZ_O>;
// MIP to NONMIP Optimization Mapping
def : MIMGMIPMapping<IMAGE_LOAD_MIP, IMAGE_LOAD>;
def : MIMGMIPMapping<IMAGE_STORE_MIP, IMAGE_STORE>;
// G to G16 Optimization Mapping
def : MIMGG16Mapping<IMAGE_SAMPLE_D, IMAGE_SAMPLE_D_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_D_CL, IMAGE_SAMPLE_D_CL_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_D, IMAGE_SAMPLE_C_D_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_D_CL, IMAGE_SAMPLE_C_D_CL_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_D_O, IMAGE_SAMPLE_D_O_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_D_CL_O, IMAGE_SAMPLE_D_CL_O_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_D_O, IMAGE_SAMPLE_C_D_O_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_D_CL_O, IMAGE_SAMPLE_C_D_CL_O_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_CD, IMAGE_SAMPLE_CD_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_CD_CL, IMAGE_SAMPLE_CD_CL_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_CD, IMAGE_SAMPLE_C_CD_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_CD_CL, IMAGE_SAMPLE_C_CD_CL_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_CD_O, IMAGE_SAMPLE_CD_O_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_CD_CL_O, IMAGE_SAMPLE_CD_CL_O_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_CD_O, IMAGE_SAMPLE_C_CD_O_G16>;
def : MIMGG16Mapping<IMAGE_SAMPLE_C_CD_CL_O, IMAGE_SAMPLE_C_CD_CL_O_G16>;