On 4/29/2016 2:33 PM, Bill Bogstad wrote:
> make it not work.  I suspect that if they hadn't insisted on making
> the differences in latency completely invisible to applications, it is
> possible that it would have worked better.   A way for a program to

Certainly, but but they already had low latency, multi-node memory
sharing with Memory Channel. They were trying something new with Galaxy.
Sometimes new things don't work out. That's what R&D is all about.

-- 
Rich P.
_______________________________________________
Discuss mailing list
[email protected]
http://lists.blu.org/mailman/listinfo/discuss

Reply via email to