forked from OSchip/llvm-project
583 lines
25 KiB
TableGen
583 lines
25 KiB
TableGen
//===-- MIMGInstructions.td - MIMG Instruction Defintions -----------------===//
|
|
//
|
|
// 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
|
|
class MIMGEncoding;
|
|
|
|
def MIMGEncGfx6 : MIMGEncoding;
|
|
def MIMGEncGfx8 : MIMGEncoding;
|
|
|
|
def MIMGEncoding : GenericEnum {
|
|
let FilterClass = "MIMGEncoding";
|
|
}
|
|
|
|
// Represent an ISA-level opcode, independent of the encoding and the
|
|
// vdata/vaddr size.
|
|
class MIMGBaseOpcode {
|
|
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 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", "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"];
|
|
GenericEnum TypeOf_Dim = MIMGDim;
|
|
|
|
let PrimaryKey = ["Dim"];
|
|
let PrimaryKeyName = "getMIMGDimInfo";
|
|
}
|
|
|
|
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 mimg <bits<7> si, bits<7> vi = si> {
|
|
field bits<7> SI = si;
|
|
field bits<7> VI = vi;
|
|
}
|
|
|
|
class MIMG <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 hasPostISelHook = 1;
|
|
let SchedRW = [WriteVMEM];
|
|
let UseNamedOperandTable = 1;
|
|
let hasSideEffects = 0; // XXX ????
|
|
|
|
let SubtargetPredicate = isGCN;
|
|
let DecoderNamespace = dns;
|
|
let isAsmParserOnly = !if(!eq(dns,""), 1, 0);
|
|
let AsmMatchConverter = "cvtMIMG";
|
|
let usesCustomInserter = 1;
|
|
|
|
Instruction Opcode = !cast<Instruction>(NAME);
|
|
MIMGBaseOpcode BaseOpcode;
|
|
MIMGEncoding MIMGEncoding = MIMGEncGfx6;
|
|
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"];
|
|
}
|
|
|
|
class MIMG_NoSampler_Helper <bits<7> op, string asm,
|
|
RegisterClass dst_rc,
|
|
RegisterClass addr_rc,
|
|
string dns="">
|
|
: MIMG <(outs dst_rc:$vdata), dns>,
|
|
MIMGe<op> {
|
|
let ssamp = 0;
|
|
let d16 = !if(BaseOpcode.HasD16, ?, 0);
|
|
|
|
let InOperandList = !con((ins addr_rc:$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", "");
|
|
}
|
|
|
|
multiclass MIMG_NoSampler_Src_Helper <bits<7> op, string asm,
|
|
RegisterClass dst_rc,
|
|
bit enableDisasm> {
|
|
let VAddrDwords = 1 in
|
|
def NAME # _V1 : MIMG_NoSampler_Helper <op, asm, dst_rc, VGPR_32,
|
|
!if(enableDisasm, "AMDGPU", "")>;
|
|
let VAddrDwords = 2 in
|
|
def NAME # _V2 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_64>;
|
|
let VAddrDwords = 3 in
|
|
def NAME # _V3 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_96>;
|
|
let VAddrDwords = 4 in
|
|
def NAME # _V4 : MIMG_NoSampler_Helper <op, asm, dst_rc, VReg_128>;
|
|
}
|
|
|
|
multiclass MIMG_NoSampler <bits<7> op, string asm, bit has_d16, bit mip = 0,
|
|
bit isResInfo = 0> {
|
|
def "" : MIMGBaseOpcode {
|
|
let Coordinates = !if(isResInfo, 0, 1);
|
|
let LodOrClampOrMip = mip;
|
|
let HasD16 = has_d16;
|
|
}
|
|
|
|
let BaseOpcode = !cast<MIMGBaseOpcode>(NAME),
|
|
mayLoad = !if(isResInfo, 0, 1) 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 = 8 in
|
|
defm _V8 : MIMG_NoSampler_Src_Helper <op, asm, VReg_256, 0>;
|
|
}
|
|
}
|
|
|
|
class MIMG_Store_Helper <bits<7> op, string asm,
|
|
RegisterClass data_rc,
|
|
RegisterClass addr_rc,
|
|
string dns = "">
|
|
: MIMG <(outs), dns>,
|
|
MIMGe<op> {
|
|
let ssamp = 0;
|
|
let d16 = !if(BaseOpcode.HasD16, ?, 0);
|
|
|
|
let mayLoad = 0;
|
|
let mayStore = 1;
|
|
let hasSideEffects = 0;
|
|
let hasPostISelHook = 0;
|
|
let DisableWQM = 1;
|
|
|
|
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", "");
|
|
}
|
|
|
|
multiclass MIMG_Store_Addr_Helper <bits<7> op, string asm,
|
|
RegisterClass data_rc,
|
|
bit enableDisasm> {
|
|
let VAddrDwords = 1 in
|
|
def NAME # _V1 : MIMG_Store_Helper <op, asm, data_rc, VGPR_32,
|
|
!if(enableDisasm, "AMDGPU", "")>;
|
|
let VAddrDwords = 2 in
|
|
def NAME # _V2 : MIMG_Store_Helper <op, asm, data_rc, VReg_64>;
|
|
let VAddrDwords = 3 in
|
|
def NAME # _V3 : MIMG_Store_Helper <op, asm, data_rc, VReg_96>;
|
|
let VAddrDwords = 4 in
|
|
def NAME # _V4 : MIMG_Store_Helper <op, asm, data_rc, VReg_128>;
|
|
}
|
|
|
|
multiclass MIMG_Store <bits<7> 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_Helper <string asm, RegisterClass data_rc,
|
|
RegisterClass addr_rc, string dns="",
|
|
bit enableDasm = 0>
|
|
: MIMG <(outs data_rc:$vdst), !if(enableDasm, dns, "")> {
|
|
let mayLoad = 1;
|
|
let mayStore = 1;
|
|
let hasSideEffects = 1; // FIXME: Remove this
|
|
let hasPostISelHook = 0;
|
|
let DisableWQM = 1;
|
|
let Constraints = "$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";
|
|
}
|
|
|
|
multiclass MIMG_Atomic_Helper_m <mimg op, string asm, RegisterClass data_rc,
|
|
RegisterClass addr_rc, bit enableDasm = 0> {
|
|
let ssamp = 0, d16 = 0 in {
|
|
def _si : MIMG_Atomic_Helper<asm, data_rc, addr_rc, "SICI", enableDasm>,
|
|
SIMCInstr<NAME, SIEncodingFamily.SI>,
|
|
MIMGe<op.SI> {
|
|
let AssemblerPredicates = [isSICI];
|
|
let DisableDecoder = DisableSIDecoder;
|
|
}
|
|
|
|
def _vi : MIMG_Atomic_Helper<asm, data_rc, addr_rc, "VI", enableDasm>,
|
|
SIMCInstr<NAME, SIEncodingFamily.VI>,
|
|
MIMGe<op.VI> {
|
|
let AssemblerPredicates = [isVI];
|
|
let DisableDecoder = DisableVIDecoder;
|
|
let MIMGEncoding = MIMGEncGfx8;
|
|
}
|
|
}
|
|
}
|
|
|
|
multiclass MIMG_Atomic_Addr_Helper_m <mimg op, string asm,
|
|
RegisterClass data_rc,
|
|
bit enableDasm = 0> {
|
|
// _V* variants have different address size, but the size is not encoded.
|
|
// So only one variant can be disassembled. V1 looks the safest to decode.
|
|
let VAddrDwords = 1 in
|
|
defm _V1 : MIMG_Atomic_Helper_m <op, asm, data_rc, VGPR_32, enableDasm>;
|
|
let VAddrDwords = 2 in
|
|
defm _V2 : MIMG_Atomic_Helper_m <op, asm, data_rc, VReg_64>;
|
|
let VAddrDwords = 3 in
|
|
defm _V3 : MIMG_Atomic_Helper_m <op, asm, data_rc, VReg_96>;
|
|
let VAddrDwords = 4 in
|
|
defm _V4 : MIMG_Atomic_Helper_m <op, asm, data_rc, VReg_128>;
|
|
}
|
|
|
|
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<7> op, string asm, RegisterClass dst_rc,
|
|
RegisterClass src_rc, string dns="">
|
|
: MIMG <(outs dst_rc:$vdata), dns>,
|
|
MIMGe<op> {
|
|
let d16 = !if(BaseOpcode.HasD16, ?, 0);
|
|
|
|
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 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 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;
|
|
}
|
|
|
|
multiclass MIMG_Sampler_Src_Helper <bits<7> 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", "")>;
|
|
}
|
|
}
|
|
|
|
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<7> op, AMDGPUSampleVariant sample, bit wqm = 0,
|
|
bit isGetLod = 0,
|
|
string asm = "image_sample"#sample.LowerCaseMod> {
|
|
def "" : MIMG_Sampler_BaseOpcode<sample> {
|
|
let HasD16 = !if(isGetLod, 0, 1);
|
|
}
|
|
|
|
let BaseOpcode = !cast<MIMGBaseOpcode>(NAME), WQM = wqm,
|
|
mayLoad = !if(isGetLod, 0, 1) 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 = 8 in
|
|
defm _V8 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_256>;
|
|
}
|
|
}
|
|
|
|
multiclass MIMG_Sampler_WQM <bits<7> op, AMDGPUSampleVariant sample>
|
|
: MIMG_Sampler<op, sample, 1>;
|
|
|
|
multiclass MIMG_Gather <bits<7> 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 = 8 in
|
|
defm _V8 : MIMG_Sampler_Src_Helper<op, asm, sample, VReg_256>;
|
|
}
|
|
}
|
|
|
|
multiclass MIMG_Gather_WQM <bits<7> op, AMDGPUSampleVariant sample>
|
|
: MIMG_Gather<op, sample, 1>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// 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">;
|
|
//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
|
|
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_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_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_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_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, 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>;
|
|
//def IMAGE_RSRC256 : MIMG_NoPattern_RSRC256 <"image_rsrc256", 0x0000007e>;
|
|
//def IMAGE_SAMPLER : MIMG_NoPattern_ <"image_sampler", 0x0000007f>;
|
|
|
|
/********** ========================================= **********/
|
|
/********** 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;
|
|
}
|
|
|
|
def ImageDimIntrinsicTable : GenericTable {
|
|
let FilterClass = "ImageDimIntrinsicInfo";
|
|
let Fields = ["Intr", "BaseOpcode", "Dim"];
|
|
GenericEnum TypeOf_BaseOpcode = MIMGBaseOpcode;
|
|
GenericEnum TypeOf_Dim = MIMGDim;
|
|
|
|
let PrimaryKey = ["Intr"];
|
|
let PrimaryKeyName = "getImageDimIntrinsicInfo";
|
|
let PrimaryKeyEarlyOut = 1;
|
|
}
|
|
|
|
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>;
|