> This seems to imply that we need the lock prefix even when updating > different bits within the same long (not just the same byte). Is this > interpretation correct?
Yes, that is what I said. The consistency applies to loads/stores (so e.g. for 128bit SSE2 load/stores too), not bytes. The current IA32 manuals have a more detailed description of the rules in volume 3 -Andi - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/