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] v1.0 features
From: Brice Goglin (Brice.Goglin_at_[hidden])
Date: 2009-12-14 16:21:08


Jeff Squyres wrote:
> So where do we want to draw the line for v1.0?
>
> Due to some external forces, it may be desirable to get hwloc embedded in Open MPI sooner rather than later. We can take a beta/snapshot of hwloc in Open MPI, but it would always be nicer to take an officially released version.
>
> What other things did we want to get in hwloc before v1.0?
>
> I'm about halfway through the embedding code.
>

Initially, memory binding was the main missing feature. But I'd be ok to
wait for 1.1 and just make 1.0 the first good release with a good API
and the embedding stuff.

Apart from that, from the ticket list:
* fix icc warnings -> can wait
* vsnprintf warnings -> can wait
* PLPA-like API -> will work on it soon
* user-defined processor restriction -> Samuel may know how far we are
from this
* lookup of specific PID -> not sure
* lstopo logical/physical -> will work on it soon
* use same logical/physical index bias in all CLI tools -> might be easy
from the above
* get nbprocs from the command line -> easy, just need to agree what we
actually want

Brice