Good diasnosys, wrong conclusion
Posted Oct 2, 2007 13:01 UTC (Tue) by khim
In reply to: Should disclose: x86 specific
Parent article: Memory part 2: CPU caches
Conventional testing may never detect the bugs; they might be identified only through inspection of the code.
And this basically means that this approach will not be used in practice. Most programs will just never work correctly in this type of environment so it'll be a niche segment in the future. I think the problem will be solved by small changes to x86 which will allow it to optionally forgone sequential consistency where it's really needed (0.01% of cases), not by switch to some other architecture. It's telling that one of your "extant machines" is not longer "extant": Apple threw away G5 with all these problems and switched to Xeons which actually work.
to post comments)