[hpc-announce] Opportunity for lightning talks at Interactive and Urgent HPC SC24 workshop

[William Arndt]

Are you undertaking work which uses HPC to address interactive and urgent
workloads such as responding to disasters, enabling live data exploration,
or coupling analysis with actively running experimental equipment?

If so, we welcome you to present a short lightning talk at the Fourth
Combined Workshop on Interactive and Urgent High-Performance Computing
(WIUHPC). This event is held in conjunction with SC 2024, on the morning of
Friday November 22nd, 2024. See https://urldefense.us/v3/__https://www.interactivehpc.com/home__;!!G_uCfscf7eWS!bM3qsm2n5SGRJjSZiO7PMaD7sYWxoeOXPIhWK8f2_Nsg1UP-8gJ2-7Rnz2bKO_0zwqdyy-uA1Claut_bj5v_gwo$  for
more information.

If this is something that you would be interested in doing then please
email William Arndt warndt at lbl.gov by the Tuesday of October 22nd with a
short one paragraph description of your proposed lightning talk.

Workshop Scope
=============
Interactivity enables users to exploit HPC resources in new and
revolutionary ways. One such area is that of urgent computing, where the
global pandemic and recent bouts of extreme climate events have
demonstrated the need to make urgent, accurate, decisions for complex
problems. Combining interactive computational modelling with the near real
time detection of unfolding disasters results in a powerful tool that can
aid emergency responders making live-critical decisions for disaster
response. Ultimately exploiting HPC to save lives and reduce economic loss.

If done right, the ability to bring the user into the loop whilst a
simulation is running opens a very wide range of opportunities. In this
workshop we are focused on how interactivity can empower HPC with a
specific focus around supporting urgent workloads. This includes responding
to human health emergencies (e.g. global pandemics – COVID, vaccines
development and distribution), natural disasters (e.g. wildfires,
hurricanes, extreme flooding, earthquakes, tsunamis, winter weather
conditions), public unrest, food and energy resource management, traffic
accidents, and space weather.

The technical challenges associated with interactivity and urgent computing
on HPC are not simple to solve, and properly supporting this requires many
technological advances across a wide range of disciplines. Whilst there are
several disjoint efforts in using HPC for disaster response, and some
advances around interactivity, much of this is currently piecemeal and done
on an institute-by-institute basis. Put simply, there is much replication
of effort, and therefore significant value can be unlocked if we work
together as the SC community on the technical and policy side.

The purpose of this workshop is to bring together stakeholders, researchers
and practitioners from across the HPC community who are working, or
interested, in the fields of interactive HPC and the use of supercomputing
for urgent decision making. Success stories, case-studies and challenges
will be shared across the interactive and urgent computing themes with a
view to enhancing the communities activities and identifying synergies.

This workshop represents a combination of the two previously successful SC
workshop series, the UrgentHPC and InteractiveHPC initiatives. As these
initiatives have grown over previous SCs we have realised that
interactivity is not only a key enabler in running urgent workloads on HPC
machines, but furthermore both these areas share many of the same
technological and policy challenges. Consequently, we feel it makes a lot
of sense to merge these complimentary activities, and by doing so will
further the impact delivered to the community.


Workshop topics
=============
* Example use-cases and case-studies that use HPC for interactivity and/or
urgent decision making
* Techniques for integrating HPC workflows with data driven approaches
* Approaches to verify and validate unreliable real-time data, for instance
from sensors, IoT, and satellites
* System design for data reduction and pre-processing at source, for
instance using edge computing and heterogeneous resources such as FPGAs
* Implementation experiences and lessons learned by staff at HPC centers
* Algorithmic techniques to guarantee result generation in specific time
frames, such as result refinement which generates more accurate results as
time progresses
* Studies of leveraging HPC for workloads with real-time time constraints
* Changes to existing HPC technologies and policies that are required to
support using HPC interactively
* The ability for HPC codes to adapt their resource requirements
dynamically, for instance via elastic compute
* Visualization and presentation techniques to support rapid and accurate
urgent decision making by the end user
* Reduction and feature extraction of results to highlight critical issues
of interest
* Complimenting results with provenance data for additional context and
certainty
* Maintaining security while providing interactivity in supercomputing
* Strategies for leveraging interactivity for reproducible science
* Impact of increased interactivity on how HPC centers operate