On Wed, Dec 25, 2013 at 4:23 AM, Daniel Micay <danielmi...@gmail.com> wrote: > It makes sense to allocate it up-front for some lock-free queues but > not a classical one built on a mutex and two condition variables. I > doubt that a lock-free algorithm with have any significant wins > against a Linux mutex or Windows critical section, and on Haswell lock > elision erases the theoretical benefits too.
I'm skeptical of the claim that a lock-free algorithm would not have any significant benefits. Do you have a citation? _______________________________________________ Rust-dev mailing list Rust-dev@mozilla.org https://mail.mozilla.org/listinfo/rust-dev
