[PATCH] Speed up __sync_lock_test_and_set on PowerPC

[Richard Henderson]

David Edelsohn wrote:
> On Wed, Sep 3, 2008 at 3:06 AM, Anton Blanchard <anton@samba.org> wrote:
> Why does the GCC alpha port emit a memory barrier at the beginning of the
> test_and_set sync builtin sequence, which seems to be more than
> the required `acquire' semantics?

Um, that's a good question.  It doesn't have one at the end either,
which would seem to be broken...  I should move it down to the end.


r~