[User-committee] [scientific-wg] a summary of activities

David F Flanders dff.openstack at gmail.com
Sun Apr 24 17:35:48 UTC 2016


Dear Fellow Working Groups and User-Committee,

I'd like to quickly draw your attention to this email announcement which a
member of the scientific-wg wrote for wide spread awareness about the
upcoming launch.  A handy summary of all the scientific-wg activities below
as well.

Thank you Khalil!


OpenStack Scientific Working GroupOpenStack Summit, Austin, TX.April 25th-27
th, 2016Background

Cloud Computing represents one of the most significant shifts in
information technology many of us are likely to see in our lifetimes. The
massive scale and global availability of cloud-based services have spawned
an entirely new generation of services that for practical purposes had
been well out of reach for individual institutions and researchers. In
effect, this necessary sharing of services has the consequence of bringing
researchers previously working in isolated islands of activity into close
proximity to one another and opening the doors to new levels of interaction
and collaboration.

While otherwise comfortable with the notion of “shared” or “utility”
infrastructure – such is the attraction of working at a large R1 or
research institute – for good scientific reasons, the research community is
wary of any limiting consequences of standards when using shared technology
resources and where the precise and complete control over the technology
architecture is critical to the science itself. Such concerns aside, there
is much promise in having computing services available as a utility for
many areas of scientific research where compute standards and form are not
immediately impactful on research outcomes – but availability and ease of
use are.

While offering great potential for game-changing innovation, current cloud
computing platforms have performance and capability limitations that reduce
their effectiveness as alternatives to highly configurable on premise
resources. As the scientific community adopts cloud infrastructure,
application mobility, portability, security, and ubiquitous availability
become increasingly important to support the democratization of research
capability and access to research computing resources.

One important consequence of moving to the effective commoditization of
research cloud computing is that increasing portions of on premise research
computing resources can be allocated towards more innovative research
computing architectures. As the migration to cloud services is also
accelerating the translation of new innovation into large-scale
availability, any effort to enhance the pathway for translation would be
highly beneficial.

As such, it is simple prudence that suggests that both on premise and
provider resources must be cultivated and nurtured. Rather than selecting
one or the other it seems beneficial for these systems to converge over
time, resulting in a hybrid architecture that has the key benefits of both
approaches.


Context

In response to the demands of the research community, the OpenStack
Foundation has started up a Scientific Working Group that will have its
inaugural meeting at the OpenStack Summit in Austin later this month. The
program also includes several panels sessions and networking opportunities
for academics, researchers, scientists and research computing professionals
to discuss a wide range of topics.


Goals

The driver for this new initiative is to bring together key stakeholders
and computation center decision makers from the research community and
industry supporting cloud-based cyber-infrastructure to surface
unmet needs, identify current and near-term solutions that would provide
value-added services and with an eye towards balancing utility vs. creative
– and hence, non-standard – uses, and to explore the scope of areas where
community based standards are called for.

Through an open and thoughtful exchange, we intend to begin developing a
shared understanding and vision of how open computing solutions can best
support existing and emerging uses in a range of research disciplines. It
is intended that this initial workshop serve as a planning session and
kick-off for a series of workshops that would include coverage of topics
such as:


*Further planning and notes ongoing via this etherpad: *


https://etherpad.openstack.org/p/scientific-wg-austin-summit-agenda


Planned sessions and events

*Operations Track: Scientific Working Group Meetup*

Monday, April 25, 2:00pm-3:30pm



*Scientific Working Group Inaugural Meeting*

Tuesday, April 26, 11:15am-11:55am

https://www.openstack.org/summit/austin-2016/summit-schedule/events/7755

Draft agenda for the session under development here:

https://etherpad.openstack.org/p/scientific-wg-austin-summit-agenda



*Luncheon Scientific Cloud Directors Panel*

Tuesday, April 26, Noon to 2pm

(TABLES WILL BE RESERVED VIA SIGNAGE)



*Scientific Community Cloud Directors*:

Scientific Community Clouds: five directors of community clouds responsible
for a quarter million cores worldwide

Tuesday, April 26, 3:40pm-4:20pm

https://www.openstack.org/summit/austin-2016/summit-schedule/events/9076



*Tuesday Evening - StackCity Community Festival*

*HPC Track:*

*Deploying OpenStack for the National Science Foundation's newest
supercomputers*

Wednesday, April 27, 9:00am-9:40am

https://www.openstack.org/summit/austin-2016/summit-schedule/events/7221?goback=1

*High-Performance OpenStack for Science and Data Analytics in a Hybrid
Cloud Environment*

Wednesday, April 27, 9:50am-10:30am

https://www.openstack.org/summit/austin-2016/summit-schedule/events/8480?goback=1

*Glance and SLURM: User-Defined Image Management on HPC Clusters*

Wednesday, April 27, 11:00am-11:40am

https://www.openstack.org/summit/austin-2016/summit-schedule/events/7822?goback=1

*Chasing the Rainbow – National Computational Infrastructure’s Pursuit of
High-Performance OpenStack Cloud*

Wednesday, April 27, 11:00am-11:40am

https://www.openstack.org/summit/austin-2016/summit-schedule/events/8527?goback=1

*Bending Ironic for Big Iron*

Wednesday, April 27, 11:50am-12:30pm

https://www.openstack.org/summit/austin-2016/summit-schedule/events/8385?goback=1

*Synch&Share into Swift -- A User-Friendly Gateway into Swift Storage Using
an Owncloud Frontend*

Wednesday, April 27, 1:50pm-2:30pm

https://www.openstack.org/summit/austin-2016/summit-schedule/events/7260?goback=1

*Cloud Infrastructure to Help Researchers Build 21st Century Microscopes*

Wednesday, April 27, 2:40pm-3:20pm

https://www.openstack.org/summit/austin-2016/summit-schedule/events/7498?goback=1

*Chameleon: An experimental Testbed for Computer Science as Application of
Cloud Computing*

Wednesday, April 27, 3:30pm-4:10pm

https://www.openstack.org/summit/austin-2016/summit-schedule/events/9035?goback=1

*Building Efficient HPC Clouds with MVAPICH2 and OpenStack over SR-IOV
enabled InfiniBand Clusters* Wednesday, April 27, 3:30pm-4:10pm

https://www.openstack.org/summit/austin-2016/summit-schedule/events/7308?goback=1

*OpenStack for High-Performance Bioinformatics*

Wednesday, April 27, 4:30pm-5:10pm

https://www.openstack.org/summit/austin-2016/summit-schedule/events/8518?goback=1


-- 
=================
Twitter: @DFFlanders <https://twitter.com/dfflanders>
Skype: david.flanders
Based in Melbourne, Australia
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openstack.org/pipermail/user-committee/attachments/20160425/e31f29ed/attachment-0001.html>


More information about the User-committee mailing list