[Remarks] Add string deduplication using a string table

* Add support for uniquing strings in the remark streamer and emitting the string table in the remarks section.

* Add parsing support for the string table in the RemarkParser.

From this remark:

```
--- !Missed
Pass:     inline
Name:     NoDefinition
DebugLoc: { File: 'test-suite/SingleSource/UnitTests/2002-04-17-PrintfChar.c',
            Line: 7, Column: 3 }
Function: printArgsNoRet
Args:
  - Callee:   printf
  - String:   ' will not be inlined into '
  - Caller:   printArgsNoRet
    DebugLoc: { File: 'test-suite/SingleSource/UnitTests/2002-04-17-PrintfChar.c',
                Line: 6, Column: 0 }
  - String:   ' because its definition is unavailable'
...
```

to:

```
--- !Missed
Pass: 0
Name: 1
DebugLoc: { File: 3, Line: 7, Column: 3 }
Function: 2
Args:
  - Callee:   4
  - String:   5
  - Caller:   2
    DebugLoc: { File: 3, Line: 6, Column: 0 }
  - String:   6
...
```

And the string table in the .remarks/__remarks section containing:

```
inline\0NoDefinition\0printArgsNoRet\0
test-suite/SingleSource/UnitTests/2002-04-17-PrintfChar.c\0printf\0
will not be inlined into \0 because its definition is unavailable\0
```

This is mostly supposed to be used for testing purposes, but it gives us
a 2x reduction in the remark size, and is an incremental change for the
updates to the remarks file format.

Differential Revision: https://reviews.llvm.org/D60227

llvm-svn: 359050

1 files changed, 46 insertions, 11 deletions

diff --git a/llvm/lib/IR/DiagnosticInfo.cpp b/llvm/lib/IR/DiagnosticInfo.cpp
index 14bee35dc29..7c387e95724 100644
--- a/llvm/lib/IR/DiagnosticInfo.cpp
+++ b/llvm/lib/IR/DiagnosticInfo.cpp
@@ -43,6 +43,8 @@
 
 using namespace llvm;
 
+cl::opt<bool> UseStringTable("remarks-yaml-string-table", cl::init(false));
+
 int llvm::getNextAvailablePluginDiagnosticKind() {
   static std::atomic<int> PluginKindID(DK_FirstPluginKind);
   return ++PluginKindID;
@@ -373,6 +375,20 @@ std::string DiagnosticInfoOptimizationBase::getMsg() const {
 void OptimizationRemarkAnalysisFPCommute::anchor() {}
 void OptimizationRemarkAnalysisAliasing::anchor() {}
 
+template <typename T>
+static void mapRemarkHeader(
+    yaml::IO &io, T PassName, T RemarkName, DiagnosticLocation DL,
+    T FunctionName, Optional<uint64_t> Hotness,
+    SmallVectorImpl<DiagnosticInfoOptimizationBase::Argument> &Args) {
+  io.mapRequired("Pass", PassName);
+  io.mapRequired("Name", RemarkName);
+  if (!io.outputting() || DL.isValid())
+    io.mapOptional("DebugLoc", DL);
+  io.mapRequired("Function", FunctionName);
+  io.mapOptional("Hotness", Hotness);
+  io.mapOptional("Args", Args);
+}
+
 namespace llvm {
 namespace yaml {
 
@@ -413,13 +429,18 @@ void MappingTraits<DiagnosticInfoOptimizationBase *>::mapping(
       GlobalValue::dropLLVMManglingEscape(OptDiag->getFunction().getName());
 
   StringRef PassName(OptDiag->PassName);
-  io.mapRequired("Pass", PassName);
-  io.mapRequired("Name", OptDiag->RemarkName);
-  if (!io.outputting() || DL.isValid())
-    io.mapOptional("DebugLoc", DL);
-  io.mapRequired("Function", FN);
-  io.mapOptional("Hotness", OptDiag->Hotness);
-  io.mapOptional("Args", OptDiag->Args);
+  if (UseStringTable) {
+    remarks::StringTable &StrTab =
+        reinterpret_cast<RemarkStreamer *>(io.getContext())->getStringTable();
+    unsigned PassID = StrTab.add(PassName).first;
+    unsigned NameID = StrTab.add(OptDiag->RemarkName).first;
+    unsigned FunctionID = StrTab.add(FN).first;
+    mapRemarkHeader(io, PassID, NameID, DL, FunctionID, OptDiag->Hotness,
+                    OptDiag->Args);
+  } else {
+    mapRemarkHeader(io, PassName, OptDiag->RemarkName, DL, FN, OptDiag->Hotness,
+                    OptDiag->Args);
+  }
 }
 
 template <> struct MappingTraits<DiagnosticLocation> {
@@ -430,7 +451,15 @@ template <> struct MappingTraits<DiagnosticLocation> {
     unsigned Line = DL.getLine();
     unsigned Col = DL.getColumn();
 
-    io.mapRequired("File", File);
+    if (UseStringTable) {
+      remarks::StringTable &StrTab =
+          reinterpret_cast<RemarkStreamer *>(io.getContext())->getStringTable();
+      unsigned FileID = StrTab.add(File).first;
+      io.mapRequired("File", FileID);
+    } else {
+      io.mapRequired("File", File);
+    }
+
     io.mapRequired("Line", Line);
     io.mapRequired("Column", Col);
   }
@@ -459,12 +488,18 @@ template <> struct BlockScalarTraits<StringBlockVal> {
 template <> struct MappingTraits<DiagnosticInfoOptimizationBase::Argument> {
   static void mapping(IO &io, DiagnosticInfoOptimizationBase::Argument &A) {
     assert(io.outputting() && "input not yet implemented");
-    // Emit a string block scalar for multiline strings, to preserve newlines.
-    if (StringRef(A.Val).count('\n') > 1) {
+
+    if (UseStringTable) {
+      remarks::StringTable &StrTab =
+          reinterpret_cast<RemarkStreamer *>(io.getContext())->getStringTable();
+      auto ValueID = StrTab.add(A.Val).first;
+      io.mapRequired(A.Key.data(), ValueID);
+    } else if (StringRef(A.Val).count('\n') > 1) {
       StringBlockVal S(A.Val);
       io.mapRequired(A.Key.data(), S);
-    } else
+    } else {
       io.mapRequired(A.Key.data(), A.Val);
+    }
     if (A.Loc.isValid())
       io.mapOptional("DebugLoc", A.Loc);
   }