jmerkey@wolfmountaingroup.com writes:

quoted text
> Results from Analysis of GCC volatile/memory barriers

So the result was that barrier()s actually worked? Great.

BTW if you did this work it might be worthwhile to go one further
step: gcc has a test suite where they run small programs and have a
simple facility to scan the resulting assembler code for specific
patterns. If you could bring your examples into that format (as in
being stand alone compiled and have a simple "yes/no" pattern to
check) and let it be included there that might make sure this always
keeps working in the future.

-Andi
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/