[dmd-concurrency] word tearing status in today's processors

[Sean Kelly]

On Jan 27, 2010, at 11:47 AM, Michel Fortin wrote:

> Le 2010-01-27 à 14:33, Sean Kelly a écrit :
> 
>> I'm nearly certain this works on x86 because x86 can do atomic unaligned writes, which is basically the same as byte-level atomic writes.
> 
> You're probably right. I guess I read some things wrong before.
> 
> About unaligned writes, what happens if you're crossing the boundary of a memory page?

It doesn't work.  But unaligned atomic writes are so slow anyway that you never actually want to use them, so it's not really a big deal.