Open MPI logo

Hardware Locality Development Mailing List Archives

  |   Home   |   Support   |   FAQ   |  

This web mail archive is frozen.

This page is part of a frozen web archive of this mailing list.

You can still navigate around this archive, but know that no new mails have been added to it since July of 2016.

Click here to be taken to the new web archives of this list; it includes all the mails that are in this frozen archive plus all new mails that have been sent to the list since it was migrated to the new archives.

Subject: Re: [hwloc-devel] release status
From: Fawzi Mohamed (fawzi_at_[hidden])
Date: 2009-10-05 10:07:49


On 5-ott-09, at 15:31, Samuel Thibault wrote:

> Fawzi Mohamed, le Mon 05 Oct 2009 15:23:23 +0200, a écrit :
>> well you assume you have a single copy of the whole system structure,
>> I am not sure that would be the case, and while the memory per core
>> is
>> growing, the memory per thread is not growing much,... but anyway
>> that
>> is not the important point...
>
> Threads share the cache levels, so it would be useless to keep a copy
> per thread. A copy per NUMA node should be far enough.

well thread don't necessarily share caches, but you are right, one
copy per NUMA node should be enough, if someone uses one process per
thread then it is its fault... ;)

Fawzi