CACM logo

BLOG@CACM

Who Needs Massively Multi-core?

[article image]

Do consumers want massively multi-core?  Or would they rather have lower power consumption and better memory bandwidth?  Are we building what people want?

User Comments

 (3)

Having more cores per chip does not necessarily means we need to use them all. Here is a possible scenario. When the temperature of a core increases, usually the system will lower frequency and/or voltage of that core in order to avoid hotspots. We will feel a slowdown. On the other hand if we have idle cores, we can "migrate" the thread from the heated core to that idle one.

Maybe not 64 cores, but Intel had increased energy efficiency with the dual core tecnology. Lower clocks generate less heat.

But sometimes it looks like they forgot that some problems are intrinsically sequential.

I think the STM vs. message passing vs lock/semaphore/mutex debate is pretty unsettled. There's the STM (haskell, clojure) vs. erlang /scala message passing camps:

http://www.tbray.org/ongoing/What/Technology/Concurrency/

http://www.sauria.com/blog/2009/10/05/the-cambrian-period-of-concurrency/

http://groups.google.com/group/clojure/browse_thread/thread/5c7a962cc72c1fe7?hl=en

http://wiki.jvmlangsummit.com/pdf/36_Click_fastbcs.pdf

Post a comment...
Name: Anonymous

Signed and anonymous comments submitted to this site are moderated and will appear if they are relevant to the topic and not abusive. Your comment will appear with your username if you are signed into the site, and will be anonymous if you are not signed in. View our policy on comments

Tools For Readers

Bookmark and Share
Default Font Size Large Font Size X-Large Font Size Text Size

Related ACM Resources

Conferences:

Courses:

In The Digital Library


About Communications | Join ACM External Link | Renew External Link | Subscribe External Link | Sign In | For Authors | For Advertisers External Link | Privacy | Site Map | Help | Contact Us | Mobile Site

Copyright © 2012 by the ACM. All rights reserved.