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] get cpu where a process/thread is executing
From: Brice Goglin (Brice.Goglin_at_[hidden])
Date: 2011-02-18 01:17:50


Le 17/02/2011 23:52, Jeff Squyres a écrit :
> On Feb 17, 2011, at 5:37 PM, Brice Goglin wrote:
>
>
>> I am waiting for this troll to settle down before pushing some related
>> changes (add a (cpubind?) support flag and a hwloc-bind option).
>> I agree that "last" is better than "current". And I agree that
>> "lastcpuexec" isn't perfect, but I didn't see anything better so far :)
>>
> hwloc_get_heisenbind()
>
> (you can't know your binding and location at the same time -- nyuk nyuk)
>
> hwloc_get_last_cpu_location()
>

This one has one advantage: if we add another function to return the
memory location, the name pattern will match (get_last_memory_location).

> hwloc_get_last_cpu_locality()
>

Could be misleading.

> hwloc_get_last_known_cpuexec()
> hwloc_get_last_seen_cpuexec()
> hwloc_get_instant_cpuexec()
> hwloc_get_cpuexec_now()
>

These are ok

> hwloc_get_my_last_cpuexec()
> ...?
>

Not "my" (we can do it for other processes too).

Brice