we have over 4500 KNC's and love those as well :)
The KNL's are pretty bad at normal integer workloads, but for massively
threaded and vectorised codes, they are very very fast.
On Thu, Nov 16, 2017 at 11:02 AM, Christopher Samuel
wrote:
> On 16/11/17 13:59, C Bergström wrote:
>
> > I'm torn be
On 16/11/17 13:59, C Bergström wrote:
> I'm torn between
Knowing Stu and what he does I'll take the former over the latter.. :-)
--
Christopher SamuelSenior Systems Administrator
Melbourne Bioinformatics - The University of Melbourne
Email: sam...@unimelb.edu.au Phone: +61 (0)3 903 5
On Thu, Nov 16, 2017 at 10:32 AM, Stu Midgley wrote:
> We have a few thousand KNL systems. They are amazingly fast when
> programmed correctly and can be treated as a normal x86_64 system from a
> cluster management point of view.
>
I'm torn between
The darkside runs deep in this one
or
That's
We have a few thousand KNL systems. They are amazingly fast when
programmed correctly and can be treated as a normal x86_64 system from a
cluster management point of view.
We love them.
On Thu, Nov 16, 2017 at 10:17 AM, Christopher Samuel
wrote:
> On 16/11/17 12:58, Gerald Henriksen wrote:
>
>
On 16/11/17 12:58, Gerald Henriksen wrote:
> Maybe worth pointing out that Intel has big changes in store, which
> may or may not be a factor in the Xeon Phi future:
Might be a case of history repeating itself as Xeon Phi came out of the
work Intel did on the Larrabee discreet GPU (which they kil
On Thu, 16 Nov 2017 10:45:40 +1100, you wrote:
>Interesting times (via a colleague on the Australian HPC Slack).
>
>https://www.top500.org/news/intel-dumps-knights-hill-future-of-xeon-phi-product-line-uncertain/
>
>Looks like fallout from the delayed Aurora system.
>
>Rumours flying that the Xeon
Interesting times (via a colleague on the Australian HPC Slack).
https://www.top500.org/news/intel-dumps-knights-hill-future-of-xeon-phi-product-line-uncertain/
Looks like fallout from the delayed Aurora system.
Rumours flying that the Xeon Phi family is in jeopardy, but the
article has an adden
