On May 9, 2012, at 11:33 AM, wrote:
> Well, looking at the libverbs sources, it seems that there is a patch for
> devinfo (cf below).
>
> Thus, the correct speeds, according to the libibverbs patch. And, if I
> understand well, they must be
> multiplied by the coding ratio to get the real lin
Well, looking at the libverbs sources, it seems that there is a patch for
devinfo (cf below).
Thus, the correct speeds, according to the libibverbs patch. And, if I
understand well, they must be
multiplied by the coding ratio to get the real link speed.
I joined another patch. I don't know if
On Wednesday 09 May 2012 10.20.47 Jeff Squyres wrote:
...
> I don't have any QDR or FDR equipment -- what's the typical active_width for
> QDR and FDR?
>
> QDR is 32000, so is that active_speed of 4 and active_width of 4? (8000 * 4
> = 32000)?
>
> FDR is 56000 (right?
Pretty much all IB is 4x to
On May 9, 2012, at 9:52 AM, wrote:
> About changeset 26385: ompi/mca/btl/openib/btl_openib_component.c
>
> I might be wrong but I think that the speed we put in
> openib_btl->super.btl_bandwidth is the speed of one link. It will be multiply
> by the number of links (*4, ib_port_attr->active_wi
Thanks!
On Wed, May 9, 2012 at 9:52 AM, Ralph Castain wrote:
> Sure! See attached the original note to the libevent folks
>
>
> Hi folks
>
> I'm working with priorities in events using libevent 2.0.13. Since I'm not
> using the most current release, I thought I'd ask about a behavior we are
> s
Hi,
About changeset 26385: ompi/mca/btl/openib/btl_openib_component.c
I might be wrong but I think that the speed we put in
openib_btl->super.btl_bandwidth is the speed of one link. It will be multiply
by the number of links (*4, ib_port_attr->active_width) to obtain the correct
speed.
Thus,
Sure! See attached the original note to the libevent folks
--- Begin Message ---
Hi folks
I'm working with priorities in events using libevent 2.0.13. Since I'm not
using the most current release, I thought I'd ask about a behavior we are
seeing that might be a potential bug.
I have attached a
Ralph,
Can you point me to the small reproducer for the libevent bug that was
fixed? I'm just curious.
Thanks,
Josh
On Fri, May 4, 2012 at 4:09 PM, Ralph Castain wrote:
> FYI: 2.0.19-stable was released yesterday. I have a Mercurial repo all set to
> go:
>
> https://bitbucket.org/rhc/ompi-libe
1.6rc3 represents one trivial change over rc2; it is expected to be the last
rc. It's in the usual location:
http://www.open-mpi.org/software/ompi/v1.6/
The change is:
- Added support for FDR InfiniBand detection
--
Jeff Squyres
jsquy...@cisco.com
For corporate legal information go to:
