[Docs] Add tablegen backend for target opcode documentation

This is a tablegen backend to generate documentation for the opcodes that exist
for each target. For each opcode, it lists the assembly string, the names and
types of all operands, and the flags and predicates that apply to the opcode.

Differential revision: https://reviews.llvm.org/D31025



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@318155 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 240 insertions, 0 deletions

diff --git a/utils/TableGen/CMakeLists.txt b/utils/TableGen/CMakeLists.txt
index e9e6dff086a..c84f4925aa7 100644
--- a/utils/TableGen/CMakeLists.txt
+++ b/utils/TableGen/CMakeLists.txt
@@ -26,6 +26,7 @@ add_tablegen(llvm-tblgen LLVM
   GlobalISelEmitter.cpp
   InfoByHwMode.cpp
   InstrInfoEmitter.cpp
+  InstrDocsEmitter.cpp
   IntrinsicEmitter.cpp
   OptParserEmitter.cpp
   PseudoLoweringEmitter.cpp
diff --git a/utils/TableGen/InstrDocsEmitter.cpp b/utils/TableGen/InstrDocsEmitter.cpp
new file mode 100644
index 00000000000..fa9ee956942
--- /dev/null
+++ b/utils/TableGen/InstrDocsEmitter.cpp
@@ -0,0 +1,232 @@
+//===- InstrDocsEmitter.cpp - Opcode Documentation Generator --------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// InstrDocsEmitter generates restructured text documentation for the opcodes
+// that can be used by MachineInstr. For each opcode, the documentation lists:
+// * Opcode name
+// * Assembly string
+// * Flags (e.g. mayLoad, isBranch, ...)
+// * Operands, including type and name
+// * Operand constraints
+// * Implicit register uses & defs
+// * Predicates
+//
+//===----------------------------------------------------------------------===//
+
+#include "CodeGenDAGPatterns.h"
+#include "CodeGenInstruction.h"
+#include "CodeGenTarget.h"
+#include "TableGenBackends.h"
+#include "llvm/TableGen/Record.h"
+#include <string>
+#include <vector>
+
+using namespace llvm;
+
+namespace llvm {
+
+void writeTitle(StringRef Str, raw_ostream &OS, char Kind = '-') {
+  OS << std::string(Str.size(), Kind) << "\n" << Str << "\n"
+     << std::string(Str.size(), Kind) << "\n";
+}
+
+void writeHeader(StringRef Str, raw_ostream &OS, char Kind = '-') {
+  OS << Str << "\n" << std::string(Str.size(), Kind) << "\n";
+}
+
+std::string escapeForRST(StringRef Str) {
+  std::string Result;
+  Result.reserve(Str.size() + 4);
+  for (char C : Str) {
+    switch (C) {
+    // We want special characters to be shown as their C escape codes.
+    case '\n': Result += "\\n"; break;
+    case '\t': Result += "\\t"; break;
+    // Underscore at the end of a line has a special meaning in rst.
+    case '_': Result += "\\_"; break;
+    default: Result += C;
+    }
+  }
+  return Result;
+}
+
+void EmitInstrDocs(RecordKeeper &RK, raw_ostream &OS) {
+  CodeGenDAGPatterns CDP(RK);
+  CodeGenTarget &Target = CDP.getTargetInfo();
+  unsigned VariantCount = Target.getAsmParserVariantCount();
+
+  // Page title.
+  std::string Title = Target.getName();
+  Title += " Instructions";
+  writeTitle(Title, OS);
+  OS << "\n";
+
+  for (const CodeGenInstruction *II : Target.getInstructionsByEnumValue()) {
+    Record *Inst = II->TheDef;
+
+    // Don't print the target-independent instructions.
+    if (II->Namespace == "TargetOpcode")
+      continue;
+
+    // Heading (instruction name).
+    writeHeader(escapeForRST(Inst->getName()), OS, '=');
+    OS << "\n";
+
+    // Assembly string(s).
+    if (!II->AsmString.empty()) {
+      for (unsigned VarNum = 0; VarNum < VariantCount; ++VarNum) {
+        Record *AsmVariant = Target.getAsmParserVariant(VarNum);
+        OS << "Assembly string";
+        if (VariantCount != 1)
+          OS << " (" << AsmVariant->getValueAsString("Name") << ")";
+        std::string AsmString =
+            CodeGenInstruction::FlattenAsmStringVariants(II->AsmString, VarNum);
+        // We trim spaces at each end of the asm string because rst needs the
+        // formatting backticks to be next to a non-whitespace character.
+        OS << ": ``" << escapeForRST(StringRef(AsmString).trim(" "))
+           << "``\n\n";
+      }
+    }
+
+    // Boolean flags.
+    std::vector<const char *> FlagStrings;
+#define xstr(s) str(s)
+#define str(s) #s
+#define FLAG(f) if (II->f) { FlagStrings.push_back(str(f)); }
+    FLAG(isReturn)
+    FLAG(isBranch)
+    FLAG(isIndirectBranch)
+    FLAG(isCompare)
+    FLAG(isMoveImm)
+    FLAG(isBitcast)
+    FLAG(isSelect)
+    FLAG(isBarrier)
+    FLAG(isCall)
+    FLAG(isAdd)
+    FLAG(canFoldAsLoad)
+    FLAG(mayLoad)
+    //FLAG(mayLoad_Unset) // Deliberately omitted.
+    FLAG(mayStore)
+    //FLAG(mayStore_Unset) // Deliberately omitted.
+    FLAG(isPredicable)
+    FLAG(isConvertibleToThreeAddress)
+    FLAG(isCommutable)
+    FLAG(isTerminator)
+    FLAG(isReMaterializable)
+    FLAG(hasDelaySlot)
+    FLAG(usesCustomInserter)
+    FLAG(hasPostISelHook)
+    FLAG(hasCtrlDep)
+    FLAG(isNotDuplicable)
+    FLAG(hasSideEffects)
+    //FLAG(hasSideEffects_Unset) // Deliberately omitted.
+    FLAG(isAsCheapAsAMove)
+    FLAG(hasExtraSrcRegAllocReq)
+    FLAG(hasExtraDefRegAllocReq)
+    FLAG(isCodeGenOnly)
+    FLAG(isPseudo)
+    FLAG(isRegSequence)
+    FLAG(isExtractSubreg)
+    FLAG(isInsertSubreg)
+    FLAG(isConvergent)
+    FLAG(hasNoSchedulingInfo)
+    if (!FlagStrings.empty()) {
+      OS << "Flags: ";
+      bool IsFirst = true;
+      for (auto FlagString : FlagStrings) {
+        if (!IsFirst)
+          OS << ", ";
+        OS << "``" << FlagString << "``";
+        IsFirst = false;
+      }
+      OS << "\n\n";
+    }
+
+    // Operands.
+    for (unsigned i = 0; i < II->Operands.size(); ++i) {
+      bool IsDef = i < II->Operands.NumDefs;
+      auto Op = II->Operands[i];
+
+      if (Op.MINumOperands > 1) {
+        // This operand corresponds to multiple operands on the
+        // MachineInstruction, so print all of them, showing the types and
+        // names of both the compound operand and the basic operands it
+        // contains.
+        for (unsigned SubOpIdx = 0; SubOpIdx < Op.MINumOperands; ++SubOpIdx) {
+          Record *SubRec =
+              cast<DefInit>(Op.MIOperandInfo->getArg(SubOpIdx))->getDef();
+          StringRef SubOpName = Op.MIOperandInfo->getArgNameStr(SubOpIdx);
+          StringRef SubOpTypeName = SubRec->getName();
+
+          OS << "* " << (IsDef ? "DEF" : "USE") << " ``" << Op.Rec->getName()
+             << "/" << SubOpTypeName << ":$" << Op.Name << ".";
+          // Not all sub-operands are named, make up a name for these.
+          if (SubOpName.empty())
+            OS << "anon" << SubOpIdx;
+          else
+            OS << SubOpName;
+          OS << "``\n\n";
+        }
+      } else {
+        // The operand corresponds to only one MachineInstruction operand.
+        OS << "* " << (IsDef ? "DEF" : "USE") << " ``" << Op.Rec->getName()
+           << ":$" << Op.Name << "``\n\n";
+      }
+    }
+
+    // Constraints.
+    StringRef Constraints = Inst->getValueAsString("Constraints");
+    if (!Constraints.empty()) {
+      OS << "Constraints: ``" << Constraints << "``\n\n";
+    }
+
+    // Implicit definitions.
+    if (!II->ImplicitDefs.empty()) {
+      OS << "Implicit defs: ";
+      bool IsFirst = true;
+      for (Record *Def : II->ImplicitDefs) {
+        if (!IsFirst)
+          OS << ", ";
+        OS << "``" << Def->getName() << "``";
+        IsFirst = false;
+      }
+      OS << "\n\n";
+    }
+
+    // Implicit uses.
+    if (!II->ImplicitUses.empty()) {
+      OS << "Implicit uses: ";
+      bool IsFirst = true;
+      for (Record *Use : II->ImplicitUses) {
+        if (!IsFirst)
+          OS << ", ";
+        OS << "``" << Use->getName() << "``";
+        IsFirst = false;
+      }
+      OS << "\n\n";
+    }
+
+    // Predicates.
+    std::vector<Record *> Predicates =
+        II->TheDef->getValueAsListOfDefs("Predicates");
+    if (!Predicates.empty()) {
+      OS << "Predicates: ";
+      bool IsFirst = true;
+      for (Record *P : Predicates) {
+        if (!IsFirst)
+          OS << ", ";
+        OS << "``" << P->getName() << "``";
+        IsFirst = false;
+      }
+      OS << "\n\n";
+    }
+  }
+}
+
+} // end llvm namespace
diff --git a/utils/TableGen/TableGen.cpp b/utils/TableGen/TableGen.cpp
index 7353c538270..debc7717afc 100644
--- a/utils/TableGen/TableGen.cpp
+++ b/utils/TableGen/TableGen.cpp
@@ -28,6 +28,7 @@ enum ActionType {
   GenEmitter,
   GenRegisterInfo,
   GenInstrInfo,
+  GenInstrDocs,
   GenAsmWriter,
   GenAsmMatcher,
   GenDisassembler,
@@ -62,6 +63,8 @@ namespace {
                                "Generate registers and register classes info"),
                     clEnumValN(GenInstrInfo, "gen-instr-info",
                                "Generate instruction descriptions"),
+                    clEnumValN(GenInstrDocs, "gen-instr-docs",
+                               "Generate instruction documentation"),
                     clEnumValN(GenCallingConv, "gen-callingconv",
                                "Generate calling convention descriptions"),
                     clEnumValN(GenAsmWriter, "gen-asm-writer",
@@ -124,6 +127,9 @@ bool LLVMTableGenMain(raw_ostream &OS, RecordKeeper &Records) {
   case GenInstrInfo:
     EmitInstrInfo(Records, OS);
     break;
+  case GenInstrDocs:
+    EmitInstrDocs(Records, OS);
+    break;
   case GenCallingConv:
     EmitCallingConv(Records, OS);
     break;
diff --git a/utils/TableGen/TableGenBackends.h b/utils/TableGen/TableGenBackends.h
index 73c3b486d16..914cd5a1fc9 100644
--- a/utils/TableGen/TableGenBackends.h
+++ b/utils/TableGen/TableGenBackends.h
@@ -72,6 +72,7 @@ void EmitDFAPacketizer(RecordKeeper &RK, raw_ostream &OS);
 void EmitDisassembler(RecordKeeper &RK, raw_ostream &OS);
 void EmitFastISel(RecordKeeper &RK, raw_ostream &OS);
 void EmitInstrInfo(RecordKeeper &RK, raw_ostream &OS);
+void EmitInstrDocs(RecordKeeper &RK, raw_ostream &OS);
 void EmitPseudoLowering(RecordKeeper &RK, raw_ostream &OS);
 void EmitRegisterInfo(RecordKeeper &RK, raw_ostream &OS);
 void EmitSubtarget(RecordKeeper &RK, raw_ostream &OS);