[PATCH] D83625: [TSan] Optimize handling of racy address

[Joachim Protze via Phabricator via llvm-commits]

protze.joachim created this revision.
protze.joachim added reviewers: kcc, dvyukov.
protze.joachim added a project: Sanitizers.
Herald added a reviewer: jdoerfert.
Herald added subscribers: Sanitizers, sstefan1.

This patch splits the handling of racy address and racy stack into separate functions. If a race was already reported for the address, we can avoid the cost for collecting the involved stacks.

This patch also removes the race condition in storing the racy address / racy stack. This race allows all threads to report the race. Because all threads get the read lock first, it is quite probable that they all finish the lookup before one thread gets the chance to aquire the write lock.

For certain data race patterns in OpenMP programs, this patch significantly reduces the execution time. As an example the execution times for below code:
master (report_bugs=1): real	0m24s
master (report_bugs=0): real	0m0.2s
patch (report_bugs=1): real	0m0.5s
patch (report_bugs=0): real	0m0.2s

  #include <stdio.h>
  int main(void)
  {
    long sum=0;
    #pragma omp parallel num_threads(4) //reduction(+:sum)
    for(int i=0; i<1000000; i++)
    {
      sum++;
    } 
    printf("Sum: %ld\n",sum);
  }


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D83625

Files:
  compiler-rt/lib/tsan/rtl/tsan_rtl_report.cpp

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D83625.277242.patch
Type: text/x-patch
Size: 4173 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200711/4e5ae9ec/attachment.bin>