[PATCH] [AtomicExpand] Set branch weights when new basic blocks are created

[Akira Hatanaka]

Sorry for not replying soon.

I wrote several mirco-benchmarks and compiled and ran them to evaluate the impact of my patch on performance. For most of the benchmarks, my patch made no difference in the generated code or made no measurable difference in performance, but there was one benchmark that showed degradation in performance when a large number of threads (16 threads) were contending for access to a atomic variable.

Given that I couldn't demonstrate optimizing for the low-contention case generates code that is at least as fast as the code currently generated, I think I should retract this patch for now and resubmit it later when I figure out a way to set the weights that makes the code run faster.


http://reviews.llvm.org/D7804

EMAIL PREFERENCES
  http://reviews.llvm.org/settings/panel/emailpreferences/