LLVM学习笔记（13）

来源：互联网发布：免费下载美图秀秀软件编辑：程序博客网时间：2024/06/04 23:24

3.3.6. 输出代码

3.3.6.1. 枚举常量

回到RegisterInfoEmitter::run，现在可以调用RegisterInfoEmitter::runEnums来向输出文件导出枚举常量了。这个输出文件被命名为TargetGenRegisterInfo.inc。以X86机器为例，产生的文件就是X86GenRegisterInfo.inc。首先，向这个文件输出的是若干枚举类型定义以标识寄存器、寄存器类，以及寄存器索引。

71 void RegisterInfoEmitter::runEnums(raw_ostream&OS,

72 CodeGenTarget &Target, CodeGenRegBank &Bank) {

73 const auto &Registers = Bank.getRegisters();

75 // Register enumsare stored as uint16_t in the tables. Make sure we'll fit.

76 assert(Registers.size()<= 0xffff && "Too many regs to fit in tables");

78 std::string Namespace =

79 Registers.front().TheDef->getValueAsString("Namespace");

81 emitSourceFileHeader("Target RegisterEnum Values", OS);

83 OS << "\n#ifdefGET_REGINFO_ENUM\n";

84 OS << "#undefGET_REGINFO_ENUM\n";

86 OS << "namespace llvm {\n\n";

88 OS << "classMCRegisterClass;\n"

89 << "extern constMCRegisterClass " << Namespace

90 <<"MCRegisterClasses[];\n\n";

92 if (!Namespace.empty())

93 OS << "namespace " <<Namespace << " {\n";

94 OS << "enum {\n NoRegister,\n";

96 for (const auto &Reg :Registers)

97 OS << " " << Reg.getName() << "= " << Reg.EnumValue << ",\n";

98 assert(Registers.size()== Registers.back().EnumValue &&

99 "Register enum valuemismatch!");

100 OS << " NUM_TARGET_REGS \t// " <<Registers.size()+1 << "\n";

101 OS << "};\n";

102 if (!Namespace.empty())

103 OS << "}\n";

104

105 const auto &RegisterClasses = Bank.getRegClasses();

106 if (!RegisterClasses.empty()) {

107

108 //RegisterClass enums are stored as uint16_t in the tables.

109 assert(RegisterClasses.size()<= 0xffff &&

110 "Too many register classes tofit in tables");

111

112 OS << "\n// Registerclasses\n";

113 if (!Namespace.empty())

114 OS << "namespace "<< Namespace << " {\n";

115 OS << "enum {\n";

116 for (const auto &RC :RegisterClasses)

117 OS << " " << RC.getName() <<"RegClassID"

118 << " = " <<RC.EnumValue << ",\n";

119 OS << "\n };\n";

120 if (!Namespace.empty())

121 OS << "}\n";

122 }

123

124 conststd::vector<Record*> &RegAltNameIndices =Target.getRegAltNameIndices();

125 // If the onlydefinition is the default NoRegAltName, we don't need to

126 // emit anything.

127 if (RegAltNameIndices.size() > 1) {

128 OS << "\n// Register alternatename indices\n";

129 if (!Namespace.empty())

130 OS << "namespace "<< Namespace << " {\n";

131 OS << "enum {\n";

132 for(unsigned i = 0, e = RegAltNameIndices.size(); i != e; ++i)

133 OS << " " <<RegAltNameIndices[i]->getName() << ",\t// " << i<< "\n";

134 OS << " NUM_TARGET_REG_ALT_NAMES = " <<RegAltNameIndices.size() << "\n";

135 OS << "};\n";

136 if (!Namespace.empty())

137 OS << "}\n";

138 }

139

140 auto &SubRegIndices= Bank.getSubRegIndices();

141 if (!SubRegIndices.empty()) {

142 OS << "\n// Subregisterindices\n";

143 std::string Namespace =SubRegIndices.front().getNamespace();

144 if (!Namespace.empty())

145 OS << "namespace "<< Namespace << " {\n";

146 OS << "enum {\n NoSubRegister,\n";

147 unsigned i = 0;

148 for (const auto &Idx :SubRegIndices)

149 OS << " " << Idx.getName() <<",\t// " << ++i << "\n";

150 OS << " NUM_TARGET_SUBREGS\n};\n";

151 if (!Namespace.empty())

152 OS << "}\n";

153 }

154

155 OS << "} // End llvmnamespace\n";

156 OS << "#endif //GET_REGINFO_ENUM\n\n";

157 }

81行的emitSourceFileHeader为文件输出了位于头部的注释。接着是输出条件控制宏指令。在LLVM里，总是这样来包括这个输出文件的（以X86为例，文件X86MCTargetDesc.h）：

#define GET_REGINFO_ENUM

#include "X86GenRegisterInfo.inc"

这是因为TargetGenRegisterInfo.inc是一个很大的文件，它包括了很多内容，而通常只需要包含其中的一部分。为此，每一部分都由类似的条件宏来包含。

TD文件里的Register类的Namespace域，作为包含寄存器枚举常量及寄存器类别枚举常量的名字空间，这里在X86GenRegisterInfo.inc文件里输出这样的语句：

classMCRegisterClass;

externconst MCRegisterClass X86MCRegisterClasses[];

比如X86MCRegisterClasses是由X86寄存器的名字空间“X86”与“MCRegisterClasses”合成的名字。这个数组定义在X86GenRegisterInfo.inc文件的下面。92~103行输出表示寄存器的枚举常量，输出的枚举常量类似于（以X86为例）：

namespace X86{

enum {

NoRegister,

AH = 1,

AL = 2,

…

NUM_TARGET_REGS // 246

};

}

这些枚举常量是以寄存器名字的顺序输出的。106~122行则输出代表寄存器类的枚举常量（以X86为例），注意CodeGenRegisterClass在容器中的索引与其EnumValue-1是一致的：

namespace X86{

enum {

GR8RegClassID =0,

GR8_NOREXRegClassID = 1,

…

VR512_with_sub_xmm_in_FR32RegClassID = 79,

};

}

X86目标机器没有使用RegAltNameIndex定义，跳过124~138行代码。余下代码则输出代表寄存器索引的枚举常量，以X86为例：

namespace X86{

enum {

NoSubRegister,

sub_8bit, // 1

sub_8bit_hi, // 2

sub_16bit, // 3

sub_32bit, // 4

sub_xmm, // 5

sub_ymm, // 6

NUM_TARGET_SUBREGS

};

}

} // End llvm namespace

#endif //GET_REGINFO_ENUM

3.3.6.2. MC使用的寄存器描述

这部分输出代码将构成新的部分，因此由宏GET_REGINFO_MC_DESC包含。MC（machinecode）使用这些代码来描述寄存器。MC是一个雄心勃勃的目标文件与汇编（object-file-and-assembly）框架。它在几年前已是LLVM的一部分，以替换之前的汇编生成器。目前MC用于所有的（或至少重要的）LLVM目标机器汇编与目标文件的生成。MC还启动了“MCJIT”，这是一个基于MC层的JIT框架。（http://blog.llvm.org/2010/04/intro-to-llvm-mc-project.html有MC子项目的一个概述）。

3.3.6.2.1. MC对寄存器的定义

MC对寄存器的封装与抽象是类MCRegisterInfo，它比较重要的成员有以下这些。如何对目标机器填充作为基类部分的MCRegisterInfo实例，正是这部分代码生成的重要任务。

135 classMCRegisterInfo {

136 public:

137 typedef const MCRegisterClass *regclass_iterator;

138

139 ///DwarfLLVMRegPair - Emitted by tablegen so Dwarf<->LLVM reg mappings canbe

140 /// performedwith a binary search.

141 structDwarfLLVMRegPair {

142 unsigned FromReg;

143 unsigned ToReg;

144

145 bool operator<(DwarfLLVMRegPairRHS) const { returnFromReg < RHS.FromReg; }

146 };

147

148 ///SubRegCoveredBits - Emitted by tablegen: bit range covered by a subreg

149 /// index, -1 inany being invalid.

150 structSubRegCoveredBits {

151 uint16_t Offset;

152 uint16_t Size;

153 };

154 private:

155 constMCRegisterDesc *Desc; // Pointer to the descriptor array

156 unsigned NumRegs; // Number of entries in the array

157 unsigned RAReg; // Return address register

158 unsigned PCReg; // Program counter register

159 constMCRegisterClass *Classes; // Pointer to the regclass array

160 unsigned NumClasses; // Number of entries in the array

161 unsigned NumRegUnits; //Number of regunits.

162 constMCPhysReg (*RegUnitRoots)[2]; // Pointer to regunit root table.

163 constMCPhysReg *DiffLists; // Pointer to the difflists array

164 constunsigned *RegUnitMaskSequences; // Pointer to lane mask sequences

165 // for register units.

166 const char*RegStrings; // Pointer to the string table.

167 const char*RegClassStrings; // Pointer to the class strings.

168 constuint16_t *SubRegIndices; // Pointer to the subreg lookup

169 // array.

170 constSubRegCoveredBits *SubRegIdxRanges; // Pointer to the subreg covered

171 // bit ranges array.

172 unsigned NumSubRegIndices; //Number of subreg indices.

173 constuint16_t *RegEncodingTable; // Pointer to array of register

174 // encodings.

175

176 unsigned L2DwarfRegsSize;

177 unsigned EHL2DwarfRegsSize;

178 unsigned Dwarf2LRegsSize;

179 unsigned EHDwarf2LRegsSize;

180 constDwarfLLVMRegPair *L2DwarfRegs; // LLVM to Dwarf regs mapping

181 constDwarfLLVMRegPair *EHL2DwarfRegs; // LLVM to Dwarf regs mapping EH

182 constDwarfLLVMRegPair *Dwarf2LRegs; // Dwarf to LLVM regs mapping

183 constDwarfLLVMRegPair *EHDwarf2LRegs; // Dwarf to LLVM regs mapping EH

184 DenseMap<unsigned, int> L2SEHRegs; // LLVMto SEH regs mapping

185

186 public:

187 ///DiffListIterator - Base iterator class that can traverse the

188 ///differentially encoded register and regunit lists in DiffLists.

189 /// Don't usethis class directly, use one of the specialized sub-classes

190 /// definedbelow.

191 classDiffListIterator {

192 uint16_t Val;

193 constMCPhysReg *List;

194

195 protected:

196 /// Create aninvalid iterator. Call init() to point to something useful.

197 DiffListIterator() : Val(0), List(nullptr){}

198

199 /// init -Point the iterator to InitVal, decoding subsequent values from

200 /// DiffList.The iterator will initially point to InitVal, sub-classes are

201 /// responsiblefor skipping the seed value if it is not part of the list.

202 void init(MCPhysReg InitVal,const MCPhysReg *DiffList) {

203 Val = InitVal;

204 List = DiffList;

205 }

206

207 /// advance -Move to the next list position, return the applied

208 ///differential. This function does not detect the end of the list, that

209 /// is thecaller's responsibility (by checking for a 0 return value).

210 unsigned advance() {

211 assert(isValid()&& "Cannot move off the end of the list.");

212 MCPhysReg D = *List++;

213 Val += D;

214 return D;

215 }

216

217 public:

218

219 /// isValid -returns true if this iterator is not yet at the end.

220 bool isValid() const{ return List; }

221

222 /// Dereferencethe iterator to get the value at the current position.

223 unsigned operator*()const { returnVal; }

224

225 /// Pre-incrementto move to the next position.

226 void operator++(){

227 // The end ofthe list is encoded as a 0 differential.

228 if (!advance())

229 List = nullptr;

230 }

231 };

232

233 // Theseiterators are allowed to sub-class DiffListIterator and access

234 // internal listpointers.

235 friend class MCSubRegIterator;

236 friend class MCSubRegIndexIterator;

237 friend class MCSuperRegIterator;

238 friend class MCRegUnitIterator;

239 friend class MCRegUnitMaskIterator;

240 friend class MCRegUnitRootIterator;

下面我们将要看到，在寄存器可以通过唯一的数值区分时（CodeGenRegister中的EnumValue）。寄存器间的关系就可以通过一系列的数值数组来表示。因此，上面的MCPhysReg实际上是uint16_t的typedef。

为了使这些数值表示有较小的冗余度，而且有高的访问效率，TableGen使用差分编码表来记录这些关系，155行MCRegisterDesc类型的Desc成员将记录这些差分表的使用情况。191行的嵌套类DiffListIterator为各个差分表的迭代器（235~240行的迭代器）提供了基类与基本的差分表遍历实现。

类似的，MC使用类MCRegisterClass来描述寄存器类。MCRegisterClass包含的数据成员有这些：

30 classMCRegisterClass {

31 public:

32 typedef const MCPhysReg* iterator;

33 typedef const MCPhysReg* const_iterator;

35 constiterator RegsBegin;

36 const uint8_t*const RegSet;

37 constuint32_t NameIdx;

38 constuint16_t RegsSize;

39 constuint16_t RegSetSize;

40 constuint16_t ID;

41 constuint16_t RegSize, Alignment; // Size &Alignment of register in bytes

42 const int8_tCopyCost;

43 const boolAllocatable;

这里的代码生成将为目标机器产生MCRegisterClass所需的内容，并生成对应的MCRegisterClass数组。

1.3.6.2.2. 差分编码

因为寄存器、寄存器索引及寄存器类的EnumValue都是连续的正整数，那么使用遵循一定顺序（即尽量与EnumValue的分配次序一致）的差分编码将能得到很好的编码效率。差分编码是这样的一个序列：d1,d2, d3, …, dn。给定一个初始值Init，将得到这样一个序列：Init+d1, Init+d1+d2,Init+d1+d2+d3, …, Init+d1+d2+..+dn。

进一步的，我们也可以不从序列的头部开始，比如给定另一个初始值init2，并指定从差分序列的偏移3处开始，那么可以得到序列：Init2+d3,Init2+d3+d4, Init2+d3+d4+…+dn。

这样，使用不同的操作数，不同的偏移，若干序列可以通过同一个差分序列生成。因此，只要编码得当，就可以得到可观的压缩率。下面RegisterInfoEmitter::runMCDesc的主要工作就是生成合适的（多个）差分序列。

782 void

783 RegisterInfoEmitter::runMCDesc(raw_ostream&OS, CodeGenTarget &Target,

784 CodeGenRegBank&RegBank) {

785 emitSourceFileHeader("MC RegisterInformation", OS);

786

787 OS << "\n#ifdefGET_REGINFO_MC_DESC\n";

788 OS << "#undef GET_REGINFO_MC_DESC\n";

789

790 const auto &Regs = RegBank.getRegisters();

791

792 auto&SubRegIndices = RegBank.getSubRegIndices();

793 // The lists ofsub-registers and super-registers go in the same array. That

794 // allows us toshare suffixes.

795 typedef std::vector<const CodeGenRegister*> RegVec;

796

797 // Differentiallyencoded lists.

798 SequenceToOffsetTable<DiffVec>DiffSeqs;

799 SmallVector<DiffVec, 4>SubRegLists(Regs.size());

800 SmallVector<DiffVec, 4>SuperRegLists(Regs.size());

801 SmallVector<DiffVec, 4>RegUnitLists(Regs.size());

802 SmallVector<unsigned, 4>RegUnitInitScale(Regs.size());

803

804 // List of lanemasks accompanying register unit sequences.

805 SequenceToOffsetTable<MaskVec>LaneMaskSeqs;

806 SmallVector<MaskVec, 4>RegUnitLaneMasks(Regs.size());

807

808 // Keep track ofsub-register names as well. These are not differentially

809 // encoded.

810 typedefSmallVector<const CodeGenSubRegIndex*, 4>SubRegIdxVec;

811 SequenceToOffsetTable<SubRegIdxVec, deref<llvm::less>>SubRegIdxSeqs;

812 SmallVector<SubRegIdxVec, 4>SubRegIdxLists(Regs.size());

813

814 SequenceToOffsetTable<std::string>RegStrings;

815

816 // Precomputeregister lists for the SequenceToOffsetTable.

817 unsigned i = 0;

818 for (auto I = Regs.begin(), E = Regs.end(); I != E; ++I,++i) {

819 const auto &Reg = *I;

820 RegStrings.add(Reg.getName());

821

822 // Compute theordered sub-register list.

823 SetVector<constCodeGenRegister*> SR;

824 Reg.addSubRegsPreOrder(SR, RegBank);

825 diffEncode(SubRegLists[i],Reg.EnumValue, SR.begin(), SR.end());

826 DiffSeqs.add(SubRegLists[i]);

827

828 // Compute thecorresponding sub-register indexes.

829 SubRegIdxVec &SRIs = SubRegIdxLists[i];

830 for(unsigned j = 0, je = SR.size(); j != je; ++j)

831 SRIs.push_back(Reg.getSubRegIndex(SR[j]));

832 SubRegIdxSeqs.add(SRIs);

833

834 //Super-registers are already computed.

835 constRegVec &SuperRegList = Reg.getSuperRegs();

836 diffEncode(SuperRegLists[i],Reg.EnumValue, SuperRegList.begin(),

837 SuperRegList.end());

838 DiffSeqs.add(SuperRegLists[i]);

839

840 //Differentially encode the register unit list, seeded by register number.

841 // Firstcompute a scale factor that allows more diff-lists to be reused:

842 //

843 // D0 -> (S0, S1)

844 // D1 -> (S2, S3)

845 //

846 // A scalefactor of 2 allows D0 and D1 to share a diff-list. The initial

847 // value forthe differential decoder is the register number multiplied by

848 // the scale.

849 //

850 // Check theneighboring registers for arithmetic progressions.

851 unsigned ScaleA = ~0u, ScaleB = ~0u;

852 SparseBitVector<> RUs =Reg.getNativeRegUnits();

853 if (I != Regs.begin() &&

854 std::prev(I)->getNativeRegUnits().count() == RUs.count())

855 ScaleB = *RUs.begin() -*std::prev(I)->getNativeRegUnits().begin();

856 if (std::next(I) != Regs.end() &&

857 std::next(I)->getNativeRegUnits().count() == RUs.count())

858 ScaleA =*std::next(I)->getNativeRegUnits().begin() - *RUs.begin();

859 unsigned Scale = std::min(ScaleB, ScaleA);

860 // Default thescale to 0 if it can't be encoded in 4 bits.

861 if (Scale >= 16)

862 Scale = 0;

863 RegUnitInitScale[i] = Scale;

864 DiffSeqs.add(diffEncode(RegUnitLists[i],Scale * Reg.EnumValue, RUs));

865

866 const auto &RUMasks = Reg.getRegUnitLaneMasks();

867 MaskVec &LaneMaskVec =RegUnitLaneMasks[i];

868 assert(LaneMaskVec.empty());

869 LaneMaskVec.insert(LaneMaskVec.begin(),RUMasks.begin(), RUMasks.end());

870 // Terminatormask should not be used inside of the list.

871 #ifndefNDEBUG

872 for(unsigned M : LaneMaskVec) {

873 assert(M!= ~0u && "terminator mask should not be part of the list");

874 }

875 #endif

876 LaneMaskSeqs.add(LaneMaskVec);

877 }

878

879 // Compute thefinal layout of the sequence table.

880 DiffSeqs.layout();

881 LaneMaskSeqs.layout();

882 SubRegIdxSeqs.layout();

模板类SequenceToOffsetTable提供差分编码的实作。因此，有几个SequenceToOffsetTable的具现类就将有几个差分编码表。这里，将用到789行的DiffSeqs（以SmallVector<uint16_t,4>，DiffVec具现），814行的RegStrings（以std::string具现），及945行的RegClassStrings（以std::string具现）。

SequenceToOffsetTable::add方法提供了向差分编码表添加序列的功能。

69 void add(constSeqT &Seq) {

70 assert(Entries== 0 && "Cannot call add() after layout()");

71 typenameSeqMap::iterator I = Seqs.lower_bound(Seq);

73 // If SeqMapcontains a sequence that has Seq as a suffix, I will be

74 // pointing toit.

75 if (I != Seqs.end() &&isSuffix(Seq, I->first))

76 return;

78 I = Seqs.insert(I, std::make_pair(Seq,0u));

80 // The entrybefore I may be a suffix of Seq that can now be erased.

81 if (I != Seqs.begin() &&isSuffix((--I)->first, Seq))

82 Seqs.erase(I);

83 }

SequenceToOffsetTable成员Seqs是类型SeqMap（std::map<SeqT,unsigned, SeqLess>，SeqT是具现时的模板实参）。71行的lower_bound返回第一个不小于Seq的迭代器，SeqLess执行比较操作：

41 struct SeqLess : publicstd::binary_function<SeqT, SeqT, bool> {

42 Less L;

43 bool operator()(const SeqT &A, constSeqT &B) const {

44 returnstd::lexicographical_compare(A.rbegin(), A.rend(),

45 B.rbegin(), B.rend(), L);

46 }

47 };

这是个嵌套在SequenceToOffsetTable定义中的仿函数，42行的Less是SequenceToOffsetTable的模板参数，缺省为std::less<typenameSeqT::value_type>（比如SeqT是DiffVec，SeqT::value_type就是uint16_t）。比较按字母、数字序，从尾到头进行。

在SequenceToOffsetTable::add的75行，如果Seq是找到的序列的后缀（即一部分），那么可以忽略Seq。否则，插入一个“ (Seq, 0) ”。另外，如果找到序列前一个序列是Seq的后缀，也要删除这个序列。这样可以保证一个最唯一大序列。isSuffix的定义是这样的：

60 static bool isSuffix(const SeqT &A,constSeqT &B) {

61 returnA.size() <= B.size() && std::equal(A.rbegin(), A.rend(),B.rbegin());

62 }

在823行开始，对子寄存器进行差分编码。首先要对寄存器DAG进行排序，以生成效果理想的差分编码表。因此函数CodeGenRegister::addSubRegsPreOrder以前序遍历当前寄存器为根的寄存器DAG，将子寄存器保存入参数OSet中。之所以要前序遍历，因为寄存器的RegUnit就是在前序遍历寄存器DAG的过程中生成的。这样能得到更高效的差分编码表。

508 void

509 CodeGenRegister::addSubRegsPreOrder(SetVector<const CodeGenRegister*> &OSet,

510 CodeGenRegBank &RegBank)const {

511 assert(SubRegsComplete&& "Must precompute sub-registers");

512 for (unsignedi = 0, e = ExplicitSubRegs.size(); i != e; ++i) {

513 CodeGenRegister *SR = ExplicitSubRegs[i];

514 if (OSet.insert(SR))

515 SR->addSubRegsPreOrder(OSet, RegBank);

516 }

517 // Add any secondarysub-registers that weren't part of the explicit tree.

518 for(SubRegMap::const_iterator I = SubRegs.begin(), E = SubRegs.end();

519 I != E; ++I)

520 OSet.insert(I->second);

521 }

diffEncode方法输出一个差分序列，序列的初始值由第二个参数指定（对子寄存器表，初始值是寄存器的EnumValue）。这个序列通过SequenceToOffsetTable::add添加到差分表DiffSeqs。

575 static

576 DiffVec &diffEncode(DiffVec &V, unsigned InitVal,SparseBitVector<> List) {

577 assert(V.empty()&& "Clear DiffVec before diffEncode.");

578 uint16_t Val = uint16_t(InitVal);

579

580 for (uint16_tCur : List) {

581 V.push_back(Cur - Val);

582 Val = Cur;

583 }

584 return V;

585 }

接着是对寄存器索引的差分编码，差分序列保存在SubRegIdxSeqs。在836行对包含当前寄存器的寄存器集进行差分编码，结果也保存在DiffSeqs中。

接下来对寄存器单元（实际上是RegUnit的序号）进行差分编码，这里仅考虑TD文件中定义的寄存器，不包括因调整权重加入的单元。840~750行注释谈到使用比例因子可以提高差分列表的重用率，这个比例因子应用于初始值上。以843~844行的例子来说，假定D0、D1的EnumValue是相邻的，S0~S3的EnumValue也是相邻的（因为在TD文件中，它们通常是顺序定义的），如果对D0、D1进行差分编码，假定D0是5，D1是6，S0~S3分别是1~4，那么对应子寄存器的差分序列分别是-4(5-4, S0)，1(5-4+1, S1)与-3 (6-3, S2)，1 (6-3+1, S3)。而如果将初始值扩大2倍，则得到两个都是-9,1的序列，这里的2得自S3-S1。因此，853~859行分别计算该寄存器与前后寄存器第一个单元序号的差值（以D0、D1为例，就是S2-S0）。

接下来866~876行将寄存器的Lane掩码保存入另一个SequenceToOffsetTable—LaneMaskSeqs。Lane掩码都是一个向量（866行的getRegUnitLaneMasks返回一个ArrayRef<unsigned>容器）。

最后，调用SequenceToOffsetTable::layout方法使SequenceToOffsetTable对象最终定型。这个方法每个SequenceToOffsetTable实例只能调用一次。

93 void layout() {

94 assert(Entries== 0 && "Can only call layout() once");

95 // Lay out thetable in Seqs iteration order.

96 for (typename SeqMap::iterator I = Seqs.begin(), E =Seqs.end(); I != E;

97 ++I) {

98 I->second = Entries;

99 // Includespace for a terminator.

100 Entries += I->first.size() + 1;

101 }

102 }

在通过SequenceToOffsetTable::add方法添加差分序列时，上面98行的I->second设为0，现在则是差分表的当前累计大小（用于下面输出的差分表的注释里，提高生成代码的可读性）。

3.3.6.2.3. 生成的差分编码表

RegisterInfoEmitter::runMCDesc的余下部分就是输出前面准备的差分编码表。

RegisterInfoEmitter::runMCDesc（续）

884 OS <<"namespace llvm {\n\n";

885

886 conststd::string &TargetName = Target.getName();

887

888 // Emit theshared table of differential lists.

889 OS << "extern const MCPhysReg" << TargetName << "RegDiffLists[] = {\n";

890 DiffSeqs.emit(OS,printDiff16);

891 OS << "};\n\n";

892

893 // Emit theshared table of regunit lane mask sequences.

894 OS << "extern const unsigned" << TargetName << "LaneMaskLists[] = {\n";

895 LaneMaskSeqs.emit(OS, printMask,"~0u");

896 OS << "};\n\n";

897

898 // Emit the tableof sub-register indexes.

899 OS << "extern const uint16_t" << TargetName << "SubRegIdxLists[] = {\n";

900 SubRegIdxSeqs.emit(OS, printSubRegIndex);

901 OS << "};\n\n";

902

903 // Emit the tableof sub-register index sizes.

904 OS << "extern constMCRegisterInfo::SubRegCoveredBits "

905 << TargetName <<"SubRegIdxRanges[] = {\n";

906 OS << " { " << (uint16_t)-1 <<", " << (uint16_t)-1 << " },\n";

907 for (const auto &Idx :SubRegIndices) {

908 OS << " { " << Idx.Offset << "," << Idx.Size << " },\t// "

909 << Idx.getName() <<"\n";

910 }

911 OS << "};\n\n";

912

913 // Emit thestring table.

914 RegStrings.layout();

915 OS << "extern const char "<< TargetName << "RegStrings[] = {\n";

916 RegStrings.emit(OS, printChar);

917 OS << "};\n\n";

918

919 OS << "extern const MCRegisterDesc" << TargetName

920 << "RegDesc[] = { //Descriptors\n";

921 OS << " { " <<RegStrings.get("") << ", 0, 0, 0, 0, 0 },\n";

922

923 // Emit theregister descriptors now.

924 i = 0;

925 for (const auto &Reg :Regs) {

926 OS << " { " <<RegStrings.get(Reg.getName()) << ", "

927 << DiffSeqs.get(SubRegLists[i])<< ", " << DiffSeqs.get(SuperRegLists[i])

928 << ", " <<SubRegIdxSeqs.get(SubRegIdxLists[i]) << ", "

929 << (DiffSeqs.get(RegUnitLists[i])* 16 + RegUnitInitScale[i]) << ", "

930 <<LaneMaskSeqs.get(RegUnitLaneMasks[i]) << " },\n";

931 ++i;

932 }

933 OS << "};\n\n"; // End ofregister descriptors...

934

935 // Emit the tableof register unit roots. Each regunit has one or two root

936 // registers.

937 OS << "extern const MCPhysReg" << TargetName << "RegUnitRoots[][2] = {\n";

938 for (unsignedi = 0, e = RegBank.getNumNativeRegUnits(); i != e; ++i) {

939 ArrayRef<constCodeGenRegister*> Roots = RegBank.getRegUnit(i).getRoots();

940 assert(!Roots.empty()&& "All regunits must have a root register.");

941 assert(Roots.size()<= 2 && "More than two roots not supported yet.");

942 OS << " { " <<getQualifiedName(Roots.front()->TheDef);

943 for (unsigned r = 1; r != Roots.size(); ++r)

944 OS << ", " <<getQualifiedName(Roots[r]->TheDef);

945 OS << " },\n";

946 }

947 OS << "};\n\n";

948

949 const auto &RegisterClasses = RegBank.getRegClasses();

950

951 // Loop over allof the register classes... emitting each one.

952 OS << "namespace { // Register classes...\n";

953

954 SequenceToOffsetTable<std::string>RegClassStrings;

955

956 // Emit theregister enum value arrays for each RegisterClass

957 for (const auto &RC :RegisterClasses) {

958 ArrayRef<Record*> Order =RC.getOrder();

959

960 // Give theregister class a legal C name if it's anonymous.

961 std::string Name = RC.getName();

962

963 RegClassStrings.add(Name);

964

965 // Emit the registerlist now.

966 OS << " // " << Name << "Register Class...\n"

967 << " const MCPhysReg " << Name

968 << "[] = {\n ";

969 for(unsigned i = 0, e = Order.size(); i != e; ++i) {

970 Record *Reg = Order[i];

971 OS << getQualifiedName(Reg)<< ", ";

972 }

973 OS << "\n };\n\n";

974

975 OS << " // " << Name << " Bitset.\n"

976 << " const uint8_t " << Name

977 << "Bits[] = {\n ";

978 BitVectorEmitter BVE;

979 for(unsigned i = 0, e = Order.size(); i != e; ++i) {

980 Record *Reg = Order[i];

981 BVE.add(Target.getRegBank().getReg(Reg)->EnumValue);

982 }

983 BVE.print(OS);

984 OS << "\n };\n\n";

985

986 }

987 OS << "}\n\n";

988

989 RegClassStrings.layout();

990 OS << "extern const char "<< TargetName << "RegClassStrings[] = {\n";

991 RegClassStrings.emit(OS, printChar);

992 OS << "};\n\n";

差分编码表通过SequenceToOffsetTable的emit方法输出。

115 void emit(raw_ostream &OS,

116 void (*Print)(raw_ostream&,ElemT),

117 constchar *Term = "0") const {

118 assert(Entries&& "Call layout() before emit()");

119 for (typename SeqMap::const_iterator I = Seqs.begin(), E =Seqs.end();

120 I != E; ++I) {

121 OS << " /* " << I->second <<" */ ";

122 for (typename SeqT::const_iterator SI =I->first.begin(),

123 SE = I->first.end(); SI != SE;++SI) {

124 Print(OS, *SI);

125 OS << ", ";

126 }

127 OS << Term <<",\n";

128 }

129 }

X96目标机器的寄存器编码差分表的内容如下。它包含了这几部分内容：子寄存器、上级寄存器、寄存器单元列表。

externconst MCPhysReg X86RegDiffLists[] = {

/* 0 */ 0, 1, 0,

/* 3 */ 2, 1, 0,

/* 6 */ 5, 1, 0,

/* 9 */ 65522, 16, 1, 0,

/* 13 */65522, 17, 1, 0,

/* 17 */65427, 1, 0,

/* 20 */65475, 1, 0,

/* 23 */65520, 65522, 1, 0,

/* 27 */65520, 65527, 1, 0,

/* 31 */8, 2, 0,

/* 34 */4, 0,

/* 36 */65521, 8, 0,

/* 39 */9, 0,

/* 41 */13, 0,

/* 43 */65535, 65519, 14, 0,

/* 47 */65535, 65520, 14, 0,

/* 51 */65528, 15, 0,

/* 54 */2, 6, 16, 0,

/* 58 */5, 6, 16, 0,

/* 62 */65535, 9, 16, 0,

/* 66 */2, 10, 16, 0,

/* 70 */3, 10, 16, 0,

/* 74 */3, 13, 16, 0,

/* 78 */4, 13, 16, 0,

/* 82 */65535, 14, 16, 0,

/* 86 */1, 16, 16, 0,

/* 90 */2, 16, 16, 0,

/* 94 */ 17, 0,

/* 96 */32, 32, 0,

/* 99 */65221, 0,

/* 101 */65381, 0,

/* 103 */65389, 0,

/* 105 */65397, 0,

/* 107 */16, 65528, 65416, 0,

/* 111 */65445, 0,

/* 113 */ 65477, 0,

/* 115 */65504, 65504, 0,

/* 118 */65509, 0,

/* 120 */120, 8, 65520, 0,

/* 124 */65523, 0,

/* 126 */65530, 0,

/* 128 */ 65531,0,

/* 130 */65532, 0,

/* 132 */65520, 65530, 65534, 65533, 0,

/* 137 */65534, 0,

/* 139 */65520, 65523, 65533, 65535, 0,

/* 144 */65520, 65526, 65534, 65535, 0,

/* 149 */65520, 65520, 65535, 65535, 0,

};

注意，这些序列都是以0结尾，因此利用这个差分表的序列不能出现重复的元素（因为重复元素的差分是0）。另外该数组的类型是uint16_t，因此数组内超过32767的实际上都是负数。

X86目标机器的寄存器Lane掩码差分表则包含如下内容：

externconst unsigned X86LaneMaskLists[] = {

/* 0 */ 0x00000000, ~0u,

/* 2 */ 0x00000002,0x00000001, ~0u,

/* 5 */ 0x00000003, ~0u,

/* 7 */ 0x00000004, ~0u,

};

因为存在差分0，这些序列以~0u结尾。差分表的内容总是最长的序列，在序列重复后缀多的情形下，这个表就会很小，比如这个Lane掩码差分表。

第三张差分表是寄存器索引表。

externconst uint16_t X86SubRegIdxLists[] = {

/* 0 */ 4, 3, 1, 0,

/* 4 */ 4, 3, 1, 2, 0,

/* 9 */ 4, 3, 0,

/* 12 */6, 5, 0,

};

X86目标机器的寄存器相当有规律，因此这张表也是很小的（上面的Lane掩码也是这个原因）。下一张表给出则是所有寄存器索引的位置与大小。注意！这张表不是差分表，其中第一项是保留不用的。其他项中第1个数字是该索引对应子寄存器的偏移，第2个数字则是该子寄存器的大小。

externconst MCRegisterInfo::SubRegCoveredBitsX86SubRegIdxRanges[] = {

{ 65535, 65535},

{ 0, 8 }, //sub_8bit

{ 8, 8 }, //sub_8bit_hi

{ 0, 16 }, //sub_16bit

{ 0, 32 }, //sub_32bit

{ 0, 128 }, //sub_xmm

{ 0, 256 }, //sub_ymm

};

可见X86目标机器使用的寄存器索引并不多。

最后的表X86RegStrings也是一张差分表，内容是组成寄存器名字的字符（一共219行）：

externconst char X86RegStrings[] = {

/* 0 */ 'X', 'M','M', '1', '0', 0,

/* 6 */ 'Y', 'M', 'M', '1', '0', 0,

/* 12 */ 'Z', 'M','M', '1', '0', 0,

/* 18 */'C', 'R', '1', '0', 0,

…

/* 1051 */'R', 'I', 'Z', 0,

};

现在对寄存器的各种描述变成了对这些差分表内容的援引，类MCRegisterDesc就是这样的一个定义：

105 structMCRegisterDesc {

106 uint32_t Name; // Printablename for the reg (for debugging)

107 uint32_t SubRegs; // Sub-registerset, described above

108 uint32_t SuperRegs; //Super-register set, described above

109

110 // Offset intoMCRI::SubRegIndices of a list of sub-register indices for each

111 // sub-registerin SubRegs.

112 uint32_t SubRegIndices;

113

114 // RegUnits -Points to the list of register units. The low 4 bits holds the

115 // Scale, thehigh bits hold an offset into DiffLists. See MCRegUnitIterator.

116 uint32_t RegUnits;

117

118 /// Index intolist with lane mask sequences. The sequence contains a lanemask

119 /// for everyregister unit.

120 uint16_t RegUnitLaneMasks;

121 };

每一个寄存器（包含子寄存器）都对应一个MCRegisterDesc对象，这个对象给出在上述表中的偏移，根据这些偏移就可以获取这个寄存器的相关信息。

由SequenceToOffsetTable::get方法向每个MCRegisterDesc实例给出这些偏移值。

105 unsigned get(constSeqT &Seq) const {

106 assert(Entries&& "Call layout() before get()");

107 typenameSeqMap::const_iterator I = Seqs.lower_bound(Seq);

108 assert(I !=Seqs.end() && isSuffix(Seq, I->first) &&

109 "get() called with sequencethat wasn't added first");

100 returnI->second + (I->first.size() - Seq.size());

101 }

因为SequenceToOffsetTable的编码方式是保留最长序列，较短但是最长序列后缀的序列由最长序列来表示，因此104行的I->first.size()- Seq.size()是使用最长序列所需要的、必要的调整。因此会导出这样的数组。第一行是保留不用的，因为这个数组的下标实际上是寄存器的EnumValue（从1开始）。这张表的有效项有245个。

externconst MCRegisterDesc X86RegDesc[] = { // Descriptors

{ 5, 0, 0, 0,0, 0 },

{ 870, 2, 90,3, 2273, 0 },

{ 898, 2, 86,3, 2273, 0 },

{ 1016, 151,87, 6, 0, 2 },

…

{ 997, 122,108, 2, 1617, 3 },

};

以第二行为例。X86RegStrings的偏移870是“AH”。X86RegDiffLists的偏移2是终结符，表示没有子寄存器。X86RegDiffLists的偏移90是：2, 16,16, 0。还原差分后，得到的寄存器EnumValue是1+2=3 (AX)，1+2+16=19(EAX)，1+2+16+16=35(RAX)。X86SubRegIdxLists的偏移3也是终结符。2273除以16后得142余1（起始值是1*EnumValue），142仍然是X86RegDiffLists的偏移，对应65535，由RegUnit-1*EnumValue得到，因此RegUnit=0。最后的0是在X86LaneMaskLists的偏移。

在第三行，898对应“AL”。2对应没有子寄存器。86得到寄存器2+1=3(AX)，2+1+16=19(EAX)，2+1+16+16=35(RAX)。X86SubRegIdxLists的偏移3也是终结符。第5个数仍然是2273，但RegUnit-1*EnumValue中EnumValue=2，所以RegUnit=1。最后的0是在X86LaneMaskLists的偏移。

在第四行，1016指向X86RegStrings中的“AX”，151在X86RegDiffLists对应序列：65535,65535。得到寄存器的EnumValue：3-1=2 (AL)，3-1-1=1(AH)。87对应X86RegDiffLists序列：16,16。得到寄存器的EnumValue：3+16=19(EAX)，3+16+16=35(RAX)。6对应X86SubRegIdxLists序列：1, 2。即子寄存器索引的编号。0对应X86RegDiffLists序列：0, 1。起始值为0（0*EnumValue），则第一个RegUnit是0，第二个RegUnit是1。

这里2~4行正好描述了两个子寄存器与包含它们的上级寄存器。

在CodeGen时，MCRegisterInfo需要这样解读X86RegDesc，这些操作由迭代器MCSubRegIterator，MCSubRegIndexIterator，MCSuperRegIterator，MCRegUnitIterator，MCRegUnitMaskIterator，MCRegUnitRootIterator，MCRegAliasIterator来实现。

接下来输出描述每个RegUnit所在DAG跟的数组，当前版本LLVM不支持超过1个根的DAG（但更早的版本是支持的）。对X86目标机器，这个数组包含100个项。

externconst MCPhysReg X86RegUnitRoots[][2] = {

{ X86::AH },

{ X86::AL },

{ X86::BH },

{ X86::BL },

{ X86::BPL },

…

{ X86::XMM30 },

{ X86::XMM31 },

};

接着，输出描述各个寄存器类别的数组。RegisterClass中的Order容器规定了这个类别中寄存器的分配（使用）次序。下面的GR8是其中一个例子：

const uint16_t GR8[] = {

X86::AL,X86::CL, X86::DL, X86::AH, X86::CH, X86::DH, X86::BL, X86::BH, X86::SIL,X86::DIL, X86::BPL, X86::SPL, X86::R8B, X86::R9B, X86::R10B, X86::R11B,X86::R14B, X86::R15B, X86::R12B, X86::R13B,

};

这些数组封装在一个匿名名字空间内。X86::AL等都是由前面的RegisterInfoEmitter::runEnums输出的代表寄存器ID的枚举常量（CodeGenRegister的EnumValue）。

另外还有一个数组，这个数组也是定义了寄存器类中寄存器的分配（使用）顺序，不过它是这样的格式：将数组视为连续的内存，第一个元素位于低址，最后的元素位于内存高址。对某一寄存器，将该数组第EnumValue/8字节的第EnumValue%8比特置为1：

const uint8_t GR8Bits[] = {

0xb6, 0xa6,0x01, 0x00, 0x00, 0x40, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xc0,0x3f,

};

以第一个字节为例，它的二进制形式是：10110110 (0xb6)，代表寄存器X86::AH，X86::AL，X86::BL，X86::BH，X86::BPL（EnumValue分别是1，2，4，5，7）。

每个寄存器类别都会输出这样两个数组。

跟着输出的是保存了寄存器类名字的字符数组X86RegClassStrings。

externconst char X86RegClassStrings[] = {

/* 0 */ 'R', 'F', 'P', '8', '0', 0,

/* 6 */ 'V', 'K','1', 0,

/* 10 */'V', 'R', '5', '1', '2', 0,

/* 16 */'V', 'K', '3', '2', 0,

…

/* 912 */'G', 'R', '6', '4', '_', 'w', 'i', 't','h', '_', 's', 'u', 'b', '_', '8', 'b', 'i', 't', 0,

};

RegisterInfoEmitter::runMCDesc（续）

994 OS <<"extern const MCRegisterClass " << TargetName

995 << "MCRegisterClasses[] ={\n";

996

997 for (const auto &RC :RegisterClasses) {

998 // Asserts tomake sure values will fit in table assuming types from

999 //MCRegisterInfo.h

1000 assert((RC.SpillSize/8)<= 0xffff && "SpillSize too large.");

1001 assert((RC.SpillAlignment/8)<= 0xffff && "SpillAlignment too large.");

1002 assert(RC.CopyCost>= -128 && RC.CopyCost <= 127 && "Copy cost toolarge.");

1003

1004 OS << " { " << RC.getName() <<", " << RC.getName() << "Bits, "

1005 <<RegClassStrings.get(RC.getName()) << ", "

1006 << RC.getOrder().size() <<", sizeof(" << RC.getName() << "Bits), "

1007 << RC.getQualifiedName() +"RegClassID" << ", "

1008 << RC.SpillSize/8 << ","

1009 << RC.SpillAlignment/8 <<", "

1010 << RC.CopyCost << ","

1011 << RC.Allocatable << "},\n";

1012 }

1013

1014 OS << "};\n\n";

1015

1016 EmitRegMappingTables(OS,Regs, false);

1017

1018 // Emit Regencoding table

1019 OS << "extern const uint16_t" << TargetName;

1020 OS << "RegEncodingTable[] ={\n";

1021 // Add entry forNoRegister

1022 OS << " 0,\n";

1023 for (const auto &RE :Regs) {

1024 Record *Reg = RE.TheDef;

1025 BitsInit *BI =Reg->getValueAsBitsInit("HWEncoding");

1026 uint64_t Value = 0;

1027 for (unsignedb = 0, be = BI->getNumBits(); b != be; ++b) {

1028 if (BitInit *B =dyn_cast<BitInit>(BI->getBit(b)))

1029 Value |= (uint64_t)B->getValue()<< b;

1030 }

1031 OS << " " << Value <<",\n";

1032 }

1033 OS << "};\n"; // End of HWencoding table

1034

1035 // MCRegisterInfoinitialization routine.

1036 OS << "static inline voidInit" << TargetName

1037 <<"MCRegisterInfo(MCRegisterInfo *RI, unsigned RA, "

1038 << "unsigned DwarfFlavour = 0,unsigned EHFlavour = 0, unsigned PC = 0) "

1039 "{\n"

1040 << " RI->InitMCRegisterInfo(" <<TargetName << "RegDesc, "

1041 << Regs.size() + 1 << ",RA, PC, " << TargetName << "MCRegisterClasses, "

1042 << RegisterClasses.size() <<", " << TargetName << "RegUnitRoots, "

1043 << RegBank.getNumNativeRegUnits()<< ", " << TargetName << "RegDiffLists, "

1044 << TargetName <<"LaneMaskLists, " << TargetName << "RegStrings,"

1045 << TargetName <<"RegClassStrings, " << TargetName << "SubRegIdxLists,"

1046 <<(std::distance(SubRegIndices.begin(), SubRegIndices.end()) + 1) <<",\n"

1047 << TargetName <<"SubRegIdxRanges, " << TargetName

1048 <<"RegEncodingTable);\n\n";

1049

1050 EmitRegMapping(OS,Regs, false);

1051

1052 OS << "}\n\n";

1053

1054 OS << "} // End llvmnamespace\n";

1055 OS << "#endif //GET_REGINFO_MC_DESC\n\n";

1056 }

997行循环输出的寄存器类描述数组大致上是这样：

externconst MCRegisterClass X86MCRegisterClasses[] = {

{ GR8, GR8Bits,130, 20, sizeof(GR8Bits), X86::GR8RegClassID,1, 1, 1, 1 },

{ GR8_NOREX,GR8_NOREXBits, 902, 8, sizeof(GR8_NOREXBits),X86::GR8_NOREXRegClassID, 1, 1, 1, 1 },

{ VK1, VK1Bits,6, 8, sizeof(VK1Bits), X86::VK1RegClassID, 1,1, 1, 1 },

…

{VR512_with_sub_xmm_in_FR32, VR512_with_sub_xmm_in_FR32Bits, 27, 16,sizeof (VR512_with_sub_xmm_in_FR32Bits),X86::VR512_with_sub_xmm_in_FR32RegClassID, 64, 64, 1, 1 },

};

GR8与GR8Bits都是前面842~874行输出的数组，GR8RegClassID等则是由RegisterInfoEmitter::runEnums输出的枚举常量。每组中第三个输出的数字是RegClassStrings差分表中的偏移。

3.3.6.2.4. 与GCC/GDB编号间的映射

在TableGen的Register定义中，存在一个DwarfNumbers域（list<int>类型），不过这没有不使用。TableGen另外定义了一个DwarfRegNum类，它也提供了一个DwarfNumbers域（list<int>类型），以实现从llvm的寄存器编号到gcc/gdb寄存器编号的映射。需要使用这个功能的寄存器需要同时从Register及DwarfRegNum派生。

这些映射表由RegisterInfoEmitter::EmitRegMappingTables输出。

320 void RegisterInfoEmitter::EmitRegMappingTables(

321 raw_ostream &OS, const std::deque<CodeGenRegister> &Regs,bool isCtor) {

322 // Collect allinformation about dwarf register numbers

323 typedefstd::map<Record*, std::vector<int64_t>, LessRecordRegister>DwarfRegNumsMapTy;

324 DwarfRegNumsMapTy DwarfRegNums;

325

326 // First, justpull all provided information to the map

327 unsigned maxLength = 0;

328 for (auto &RE : Regs) {

329 Record *Reg = RE.TheDef;

330 std::vector<int64_t> RegNums =Reg->getValueAsListOfInts("DwarfNumbers");

331 maxLength = std::max((size_t)maxLength, RegNums.size());

332 if (DwarfRegNums.count(Reg))

333 PrintWarning(Reg->getLoc(),Twine("DWARF numbers for register ") +

334 getQualifiedName(Reg) +"specified multiple times");

335 DwarfRegNums[Reg] = RegNums;

336 }

337

338 if (!maxLength)

339 return;

340

341 // Now we knowmaximal length of number list. Append -1's, where needed

342 for(DwarfRegNumsMapTy::iterator

343 I = DwarfRegNums.begin(), E =DwarfRegNums.end(); I != E; ++I)

344 for(unsigned i = I->second.size(), e = maxLength; i != e; ++i)

345 I->second.push_back(-1);

346

347 std::string Namespace =Regs.front().TheDef->getValueAsString("Namespace");

348

349 OS << "// " <<Namespace << " Dwarf<->LLVM register mappings.\n";

350

351 // Emit reverseinformation about the dwarf register numbers.

352 for (unsignedj = 0; j < 2; ++j) {

353 for(unsigned i = 0, e = maxLength; i != e; ++i) {

354 OS << "extern constMCRegisterInfo::DwarfLLVMRegPair " << Namespace;

355 OS << (j == 0 ? "DwarfFlavour": "EHFlavour");

356 OS << i <<"Dwarf2L[]";

357

358 if (!isCtor) {

359 OS << " = {\n";

360

361 // Storethe mapping sorted by the LLVM reg num so lookup can be done

362 // with abinary search.

363 std::map<uint64_t, Record*>Dwarf2LMap;

364 for(DwarfRegNumsMapTy::iterator

365 I = DwarfRegNums.begin(), E =DwarfRegNums.end(); I != E; ++I) {

366 int DwarfRegNo = I->second[i];

367 if (DwarfRegNo < 0)

368 continue;

369 Dwarf2LMap[DwarfRegNo] = I->first;

370 }

371

372 for(std::map<uint64_t, Record*>::iterator

373 I = Dwarf2LMap.begin(), E =Dwarf2LMap.end(); I != E; ++I)

374 OS << " { " << I->first <<"U, " << getQualifiedName(I->second)

375 << " },\n";

376

377 OS << "};\n";

378 } else {

379 OS << ";\n";

380 }

381

382 // We have tostore the size in a const global, it's used in multiple

383 // places.

384 OS << "extern const unsigned" << Namespace

385 << (j == 0 ?"DwarfFlavour" : "EHFlavour") << i <<"Dwarf2LSize";

386 if (!isCtor)

387 OS << " =array_lengthof(" << Namespace

388 << (j == 0 ?"DwarfFlavour" : "EHFlavour") << i

389 << "Dwarf2L);\n\n";

390 else

391 OS << ";\n\n";

392 }

393 }

394

395 for (auto &RE : Regs) {

396 Record *Reg = RE.TheDef;

397 constRecordVal *V = Reg->getValue("DwarfAlias");

398 if (!V || !V->getValue())

399 continue;

400

401 DefInit *DI =cast<DefInit>(V->getValue());

402 Record *Alias = DI->getDef();

403 DwarfRegNums[Reg] = DwarfRegNums[Alias];

404 }

405

406 // Emitinformation about the dwarf register numbers.

407 for (unsignedj = 0; j < 2; ++j) {

408 for(unsigned i = 0, e = maxLength; i != e; ++i) {

409 OS << "extern constMCRegisterInfo::DwarfLLVMRegPair " << Namespace;

410 OS << (j == 0 ?"DwarfFlavour" : "EHFlavour");

411 OS << i << "L2Dwarf[]";

412 if (!isCtor) {

413 OS << " = {\n";

414 // Storethe mapping sorted by the Dwarf reg num so lookup can be done

415 // with abinary search.

416 for(DwarfRegNumsMapTy::iterator

417 I = DwarfRegNums.begin(), E =DwarfRegNums.end(); I != E; ++I) {

418 int RegNo = I->second[i];

419 if (RegNo == -1)// -1 is the default value, don't emit a mapping.

420 continue;

421

422 OS << " { " << getQualifiedName(I->first)<< ", " << RegNo

423 << "U },\n";

424 }

425 OS << "};\n";

426 } else {

427 OS << ";\n";

428 }

429

430 // We have tostore the size in a const global, it's used in multiple

431 // places.

432 OS << "extern const unsigned" << Namespace

433 << (j == 0 ?"DwarfFlavour" : "EHFlavour") << i <<"L2DwarfSize";

434 if (!isCtor)

435 OS << " =array_lengthof(" << Namespace

436 << (j == 0 ?"DwarfFlavour" : "EHFlavour") << i <<"L2Dwarf);\n\n";

437 else

438 OS << ";\n\n";

439 }

440 }

441 }

328行循环获取寄存器的DwarfNumbers列表保存入DwarfRegNums容器，获取DwarfNumbers列表的最大尺寸。在目前的LLVM中，对于X86机器，这个列表对应3种Dwarf变种。第一列是X86_64，第二列是X86_32_DarwinEH，第三列是X86_32_Generic。在342行的循环将DwarfRegNums所有的元素都调整为相同大小，多出部分由-1填充（-1表示gcc的编号未定义）。

352行循环对X86机器输出数组X86DwarfFlavour0Dwarf2L，X86DwarfFlavour1Dwarf2L，X86DwarfFlavour2Dwarf2L，X86EHFlavour0Dwarf2L，X86EHFlavour1Dwarf2L及X86EHFlavour2Dwarf2L（其中*EHFlavour*数组的使用对象是DarwinEH系统，它与对应的*DwarfFlavour*数组内容没有差别），它们的类型都是DwarfLLVMRegPair，实现从dwarf到llvm的映射。DwarfLLVMRegPair的定义是：

141 struct DwarfLLVMRegPair {

142 unsigned FromReg;

143 unsigned ToReg;

144

145 bool operator<(DwarfLLVMRegPairRHS) const { returnFromReg < RHS.FromReg; }

146 };

358行的isCtor是EmitRegMappingTables的最后一个参数，在这里的调用上下文里是false，表示不是为目标机器的TargetGenRegisterInfo构造函数生成代码。363行的Dwarf2LMap与DwarfRegNums相反，它把Dwarf数（由i下标指定）映射到LLVM的寄存器编号，注释说这样可以进行二分查找。接着在372行的循环输出Dwarf2LMap的内容。输出的数组大致是这个样子：

externconst MCRegisterInfo::DwarfLLVMRegPairX86DwarfFlavour1Dwarf2L[] = {

{ 0U, X86::EAX},

{ 1U, X86::ECX},

{ 2U, X86::EDX},

…

{ 36U, X86::MM7},

};

384~391行则输出一个全局常量，其值是对应数组的大小。比如：

externconst unsignedX86DwarfFlavour1Dwarf2LSize = array_lengthof(X86DwarfFlavour1Dwarf2L);

接下来，DwarfAlias提供了一个方式，使得两个Register可以共享相同的dwarf编号。需要的寄存器必须从DwarfAlias派生，并指定共享的寄存器（由这个寄存器来提供DwarfNumbers定义，参考下面的403行）。

407行的循环输出另一个方向的映射数组（从LLVM到DWARF）。类似地它会输出数组X86DwarfFlavour0L2Dwarf，X86DwarfFlavour1L2Dwarf，X86DwarfFlavour2L2Dwarf，X86EHFlavour0L2Dwarf，X86EHFlavour1L2Dwarf及X86EHFlavour2L2Dwarf。同样，431~439行会输出一个全局常量，值是对应数组的大小。

注意，在这些数组中，-1是不输出内容的，因为它表示gcc的编号没有定义。但会输出-2，像这样（-2表示这个寄存器编号对于该模式/变种是无效的）：

externconst MCRegisterInfo::DwarfLLVMRegPairX86EHFlavour0L2Dwarf[] = {

{ X86::EAX, -2U},

{ X86::EBP, -2U},

{ X86::EBX, -2U},

…

{ X86::ZMM31,75U },

};

回到RegisterInfoEmitter::runMCDesc。跟着是输出寄存器在目标机器上的硬件编码表。1025行的HWEncoding就是在TD文件里定义寄存器必须要填写的域。这个数组的内容是小端序的（当前版本有246项，每项对应一个寄存器）：

externconst uint16_t X86RegEncodingTable[] = {

…

15,

};

这些数值在汇编指令中用于指定寄存器（目前数组中最大的值是31）。

1036~1048行输出函数InitX86MCRegisterInfo的定义的第一部分。

staticinlinevoid InitX86MCRegisterInfo(MCRegisterInfo*RI, unsigned RA, unsigned DwarfFlavour = 0, unsigned EHFlavour = 0, unsignedPC = 0) {

RI->InitMCRegisterInfo(X86RegDesc, 161,RA, PC, X86MCRegisterClasses, 59, X86RegUnitRoots, 87, X86RegDiffLists,X86RegStrings, X86SubRegIdxLists, 6,

X86RegEncodingTable);

InitMCRegisterInfo是平台通用的初始化函数，它将目标机器所要使用的寄存器描述以及差分表保存到相应的MCRegisterInfo（基类）对象中。InitX86MCRegisterInfo在其基础上进行额外的初始化工作，这部分代码由下面的函数输出。

443 void RegisterInfoEmitter::EmitRegMapping(

444 raw_ostream &OS, const std::deque<CodeGenRegister> &Regs,bool isCtor) {

445 // Emit theinitializer so the tables from EmitRegMappingTables get wired up

446 // to theMCRegisterInfo object.

447 unsigned maxLength = 0;

448 for (auto &RE : Regs) {

449 Record *Reg = RE.TheDef;

450 maxLength = std::max((size_t)maxLength,

451 Reg->getValueAsListOfInts("DwarfNumbers").size());

452 }

453

454 if (!maxLength)

455 return;

456

457 std::string Namespace =Regs.front().TheDef->getValueAsString("Namespace");

458

459 // Emit reverseinformation about the dwarf register numbers.

460 for (unsignedj = 0; j < 2; ++j) {

461 OS << " switch (";

462 if (j== 0)

463 OS << "DwarfFlavour";

464 else

465 OS << "EHFlavour";

466 OS << ") {\n"

467 << " default:\n"

468 << " llvm_unreachable(\"Unknown DWARFflavour\");\n";

469

470 for(unsigned i = 0, e = maxLength; i != e; ++i) {

471 OS << " case " << i <<":\n";

472 OS << " ";

473 if (!isCtor)

474 OS << "RI->";

475 std::string Tmp;

476 raw_string_ostream(Tmp) <<Namespace

477 << (j == 0? "DwarfFlavour" : "EHFlavour") << i

478 <<"Dwarf2L";

479 OS <<"mapDwarfRegsToLLVMRegs(" << Tmp << ", "<< Tmp << "Size, ";

480 if (j == 0)

481 OS << "false";

482 else

483 OS << "true";

484 OS << ");\n";

485 OS << " break;\n";

486 }

487 OS << " }\n";

488 }

489

490 // Emitinformation about the dwarf register numbers.

491 for (unsignedj = 0; j < 2; ++j) {

492 OS << " switch (";

493 if (j == 0)

494 OS << "DwarfFlavour";

495 else

496 OS << "EHFlavour";

497 OS << ") {\n"

498 << " default:\n"

499 << " llvm_unreachable(\"Unknown DWARFflavour\");\n";

500

501 for(unsigned i = 0, e = maxLength; i != e; ++i) {

502 OS << " case " << i <<":\n";

503 OS << " ";

504 if (!isCtor)

505 OS << "RI->";

506 std::string Tmp;

507 raw_string_ostream(Tmp) <<Namespace

508 << (j == 0? "DwarfFlavour" : "EHFlavour") << i

509 <<"L2Dwarf";

510 OS <<"mapLLVMRegsToDwarfRegs(" << Tmp << ", "<< Tmp << "Size, ";

511 if (j == 0)

512 OS << "false";

513 else

514 OS << "true";

515 OS << ");\n";

516 OS << " break;\n";

517 }

518 OS << " }\n";

519 }

520 }

输出的将是两组switch case语句，分别根据DwarfFlavour来调用mapDwarfRegsToLLVMRegs或者mapLLVMRegsToDwarfRegs，把上述的映射表关联到MCRegisterInfo对象相应的成员。

阅读全文

0 0