[llvm][automemcpy] Allow distribution filtering in analysis

[gchatelet]

rebase

[courbet]

libc/benchmarks/automemcpy/lib/ResultAnalyzerMain.cpp

25

keep-only ? "filter" can mean "keep" or "filter out".

[gchatelet]

• Cleanup StringSet angle brackets, they are not needed in C++17
• Rename flag so the intent is clearer

[gchatelet]

rebase and squash commits

libc/benchmarks/automemcpy/lib/CodeGen.cpp

)";
   Stream << "// Functions : " << Descriptors.size() << "\n";
 }
 
 } // namespace codegen
 
 // Stores `VolatileStr` into a cache and returns a StringRef of the cached
 // version.
 StringRef getInternalizedString(std::string VolatileStr) {
-  static llvm::StringSet<> StringCache;
+  static llvm::StringSet StringCache;
   return StringCache.insert(std::move(VolatileStr)).first->getKey();
 }
 
 static StringRef getString(FunctionType FT) {
   switch (FT) {
   case FunctionType::MEMCPY:
     return "memcpy";
   case FunctionType::MEMCMP:

libc/benchmarks/automemcpy/lib/ResultAnalyzerMain.cpp

 #include "llvm/Support/MemoryBuffer.h"
 
 namespace llvm {
 
 // User can specify one or more json filenames to process on the command line.
 static cl::list<std::string> InputFilenames(cl::Positional, cl::OneOrMore,
                                             cl::desc("<input json files>"));
 
+// User can filter the distributions to be taken into account.
+static cl::list<std::string>
+    KeepOnlyDistributions("keep-only-distributions", cl::ZeroOrMore,
+                          cl::desc("<comma separated list of distribution "
+                                   "names, keeps all if unspecified>"));
+
 namespace automemcpy {
 
 // This is defined in the autogenerated 'Implementations.cpp' file.
 extern ArrayRef<NamedFunctionDescriptor> getFunctionDescriptors();
 
 // Iterates over all functions and fills a map of function name to function
 // descriptor pointers.
 static StringMap<const FunctionDescriptor *> createFunctionDescriptorMap() {
if (!FD)
     report_fatal_error(
         Twine("No FunctionDescriptor for ").concat(FunctionName));
   return *FD;
 }
 
 // Functions and distributions names are stored quite a few times so it's more
 // efficient to internalize these strings and refer to them through 'StringRef'.
 static StringRef getInternalizedString(StringRef VolatileStr) {
-  static llvm::StringSet<> StringCache;
+  static llvm::StringSet StringCache;
   return StringCache.insert(VolatileStr).first->getKey();
 }
 
 // Helper function for the LLVM JSON API.
 bool fromJSON(const json::Value &V, Sample &Out, json::Path P) {
   std::string Label;
   json::ObjectMapper O(V, P);
   if (O && O.map("bytes_per_second", Out.BytesPerSecond) &&
int Main(int argc, char **argv) {
 
   // Reads all samples stored in the input JSON files.
   std::vector<Sample> Samples;
   for (const auto &Filename : InputFilenames) {
     auto Result = parseJsonResultFile(Filename);
     llvm::append_range(Samples, Result.Samples);
   }
 
+  if (!KeepOnlyDistributions.empty()) {
+    llvm::StringSet ValidDistributions;
+    ValidDistributions.insert(KeepOnlyDistributions.begin(),
+                              KeepOnlyDistributions.end());
+    llvm::erase_if(Samples, [&ValidDistributions](const Sample &S) {
+      return !ValidDistributions.contains(S.Id.Distribution.Name);
+    });
+  }
+
   // Extracts median of throughputs.
   std::vector<FunctionData> Functions = getThroughputs(Samples);
   fillScores(Functions);
   castVotes(Functions);
 
   // TODO: Implement tie breaking algorithm.
   std::sort(Functions.begin(), Functions.end(),
             [](const FunctionData &A, const FunctionData &B) {