This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH] Fix atomic_full_barrier on x86 and x86_64.
- From: Torvald Riegel <triegel at redhat dot com>
- To: "Joseph S. Myers" <joseph at codesourcery dot com>
- Cc: Rich Felker <dalias at libc dot org>, GLIBC Devel <libc-alpha at sourceware dot org>
- Date: Wed, 29 Oct 2014 23:32:17 +0100
- Subject: Re: [PATCH] Fix atomic_full_barrier on x86 and x86_64.
- Authentication-results: sourceware.org; auth=none
- References: <1414606736 dot 10085 dot 1 dot camel at triegel dot csb> <20141029203158 dot GU22465 at brightrain dot aerifal dot cx> <1414616100 dot 10085 dot 11 dot camel at triegel dot csb> <Pine dot LNX dot 4 dot 64 dot 1410292151470 dot 15119 at digraph dot polyomino dot org dot uk>
On Wed, 2014-10-29 at 21:54 +0000, Joseph S. Myers wrote:
> On Wed, 29 Oct 2014, Torvald Riegel wrote:
>
> > What's the include order on x86, counting down from the most recent
> > supported revision (ie, for an i686 machine, include sysdeps/i386/i686
> > first, then i586 and i486)?
>
> That depends on the sysdeps Implies file. For i686, it uses i386/i486 but
> *not* i386/i586.
>
> (i586 uses i486, so any files for plain i386 that are overridden for i486,
> or overridden for both i586 and i686, are dead and can be removed. It
> would also be OK to merge i486 into i386 now anything before i486 isn't
> supported.)
Thanks for the background.
So, mfence seems to have been introduced with SSE2. Should I try to
test for SSE2 specifically, or rather assume SSE2 support for i786?