[llvm-profgen] Clean up unnecessary memory reservations between phases.

htyu · htyu · commit 057e784b0962 · 2022-02-01T12:48:08.000-08:00
Cleaning up data structures that are not used after a certain point. This further brings down peak memory usage by 15% for a large benchmark. Before: note: Before parsePerfTraces note: VM: 40.73 GB RSS: 39.18 GB note: Before parseAndAggregateTrace note: VM: 40.73 GB RSS: 39.18 GB note: After parseAndAggregateTrace note: VM: 88.93 GB RSS: 87.97 GB note: Before generateUnsymbolizedProfile note: VM: 88.95 GB RSS: 87.99 GB note: After generateUnsymbolizedProfile note: VM: 93.50 GB RSS: 92.53 GB note: After computeSizeForProfiledFunctions note: VM: 101.13 GB RSS: 99.36 GB note: After generateProbeBasedProfile note: VM: 215.61 GB RSS: 210.88 GB note: After postProcessProfiles note: VM: 237.48 GB RSS: 212.50 GB After: note: Before parsePerfTraces note: VM: 40.73 GB RSS: 39.18 GB note: Before parseAndAggregateTrace note: VM: 40.73 GB RSS: 39.18 GB note: After parseAndAggregateTrace note: VM: 88.93 GB RSS: 87.96 GB note: Before generateUnsymbolizedProfile note: VM: 88.95 GB RSS: 87.97 GB note: After generateUnsymbolizedProfile note: VM: 93.50 GB RSS: 92.51 GB note: After computeSizeForProfiledFunctions note: VM: 93.50 GB RSS: 92.53 GB note: After generateProbeBasedProfile note: VM: 164.87 GB RSS: 163.55 GB note: After postProcessProfiles note: VM: 182.28 GB RSS: 179.43 GB Reviewed By: wenlei, wlei Differential Revision: https://reviews.llvm.org/D118677
diff --git a/llvm/tools/llvm-profgen/PerfReader.cpp b/llvm/tools/llvm-profgen/PerfReader.cpp
@@ -1212,6 +1212,7 @@ void PerfScriptReader::parsePerfTraces() {
   warnTruncatedStack();
   warnInvalidRange();
   generateUnsymbolizedProfile();
+  AggregatedSamples.clear();
 
   if (SkipSymbolization)
     writeUnsymbolizedProfile(OutputFilename);
diff --git a/llvm/tools/llvm-profgen/llvm-profgen.cpp b/llvm/tools/llvm-profgen/llvm-profgen.cpp
@@ -158,6 +158,9 @@ int main(int argc, const char *argv[]) {
       ProfileGeneratorBase::create(Binary.get(), Reader->getSampleCounters(),
                                    Reader->profileIsCSFlat());
   Generator->generateProfile();
+  // The Reader object, espcially its SampleCounters field, is not needed at
+  // this point, so releasing it to reduce peak memory usage.
+  Reader.release();
   Generator->write();
 
   return EXIT_SUCCESS;
