This is the mail archive of the
gcc-bugs@gcc.gnu.org
mailing list for the GCC project.
[Bug target/52080] Stores to bitfields introduce a store-data-race on adjacent data
- From: "gcc-bugs at tesarici dot cz" <gcc-bugzilla at gcc dot gnu dot org>
- To: gcc-bugs at gcc dot gnu dot org
- Date: Thu, 02 Feb 2012 12:39:25 +0000
- Subject: [Bug target/52080] Stores to bitfields introduce a store-data-race on adjacent data
- Auto-submitted: auto-generated
- References: <bug-52080-4@http.gcc.gnu.org/bugzilla/>
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52080
--- Comment #11 from Petr Tesarik <gcc-bugs at tesarici dot cz> 2012-02-02 12:39:25 UTC ---
(In reply to comment #10)
> IA64 uses
>
> .mmi
> ld8.acq r14 = [r32]
> ;;
> nop 0
> dep r14 = r15, r14, 32, 1
> ;;
> .mib
> st8.rel [r32] = r14
>
> which seems to be an attempt to work around this issue (albeit a
> possibly very slow one).
Are you referring to the ".acq" and ".rel" forms? That doesn't change the
situation at all. All it does is ensure correct memory ordering with respect to
external visibility, but it does nothing to avoid the race condition.