[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAK4o1WwtUVy5z-0f1MDN8nNwcw=tJEjHMik4NFBbFCMHZRiYFg@mail.gmail.com>
Date: Mon, 24 Mar 2014 23:44:57 +0000
From: Justin Cormack <justin@...cialbusservice.com>
To: musl@...ts.openwall.com
Subject: Re: Transition path for removing lazy init of thread pointer
On Mon, Mar 24, 2014 at 11:04 PM, Rich Felker <dalias@...ifal.cx> wrote:
>
> At this point we now have two mandatory syscalls at startup on most
> archs (just one where setting the thread pointer is entirely a
> userspace operation). The second syscall is set_tid_address, and it
> seems like it should only be needed it pthread_create is being used
> (to that pthread_join will work), but it serves a second purpose of
> standing in for gettid() too. We could, however, eliminate it in some
> cases:x
Which archs is it userspace only?
Any idea what the performance benefit of the optimisations might be?
Static linked non threaded programs sounds like a good target.
Justin
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
