[PATCH] D54889: Fiber support for thread sanitizer

[Dmitry Vyukov via Phabricator via llvm-commits]

dvyukov added a comment.

> Now, when all performance issues are resolved, what else should be done to complete the review?

Just me finding time to review it.
I need to put together all numbers. Is it faster than it was (that is, new optimizations outweigh the change to cur_thread)? Or the change to cur_thread makes it faster by itself? I am somewhat concerned by the "cheating", I understand that it's you who found these potential additional optimizations, but these still unrelated to the cur_thread change. Thousands of existing tsan users don't use fibers at all today.
Thanks for your persistence btw.


Repository:
  rCRT Compiler Runtime

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D54889/new/

https://reviews.llvm.org/D54889