[hpc-announce] CFP: Fourth International Workshop on Quantitative Codesign of Supercomputers

[Jones, Terry]

Fourth International Workshop on Quantitative Codesign of Supercomputers
                                  https://urldefense.us/v3/__https://quantitativecodesignsc.org__;!!G_uCfscf7eWS!bjLXW9ZhMM_D8vc9COl8m1QXC9bWvJ3yXY-IMDinKBxDRfFeaA5Lr2nZb8ICO1A78lxfzr9Oojwl-2LdkTxEkWCQ$ 

Sunday, November 17th, 2024 from 9:00 AM to noon US Eastern Time
The Georgia World Congress Center, Room B315
Atlanta, Georgia, USA

                     *** Call for Work-In-Progress Papers ***

Held in conjunction with SC24:
  The International Conference for High Performance Computing,
  Networking, Storage and Analysis

——————————————————————————-
                                      Important dates
——————————————————————————-
Submissions open: September 1, 2024
Submission deadline: October 30, 2024, AOE
Author notification: November 1st, 2023
——————————————————————————-

The 4th International Workshop on Quantitative Codesign in Supercomputers (SQCS) is
soliciting brief (around 2 pages) Work-In-Progress papers for a session of flash talks to
be held during the workshop on Sunday, Nov-17-2024 at the SC24 Conference in Atlanta.
The flash talks are intended to provide a forum for discussing early R&D progress, to
highlight emerging directions and to stimulate discussions.

SQCS considers combining two methodologies— collaborative codesign and
data-driven analysis—to realize the full potential of supercomputing. Our scope
includes applications, system software, workflows, health of hardware. Today’s HPC
centers store vast sums of information, yet using this data presents demanding
challenges. Much of the data-driven challenge has to do with discovering, accessing,
and analyzing the right data. Codesign also presents formidable challenges. For
example, how can a codesign development use the data collected on current systems
to facilitate the design of next-generation supercomputers and successfully support
our upcoming environments. Quantitative codesign offers a collaborative evidence-based
approach to address our existing needs and our upcoming ambitions. This symposium
will bring together leaders in the field to review current efforts across centers
and discuss areas that show potential.

This year, our theme is on opportunities and challenges in ADVANCED MEMORY.
There are new research topics in heterogeneous computing, energy efficient computing
performance, AI architectures, and edge computing that are driving innovations in
advanced memory technology. Generative AI, Foundation Models, and HPC are important
drivers for performance improvements in high bandwidth memory.  Growing industry
support and adoption of Compute Express Link (CXL) is driving interesting codesign
explorations with various application drivers for CXL capabilities including: multi-tiered
memory hierarchy, memory disaggregation large memory pools with global fabric attached
memory, support for heterogeneous computing with shared memory pools, and revisited
concepts for compute near memory designs.  In shared memory, application codesign
tradeoffs are raised for hardware vs software coherency and consistency management.
New codesign opportunities also arise to understand memory requirements for Federated
Learning at low power edge devices.

We anticipate notable advances related to quantitative codesign in topic areas beyond
Advanced Memory and submissions targeting other relevant themes are welcomed.
Topics of interest include (but are not limited to):

* Effective ways and new approaches to employ center-collected data in the HPC
   software stack.
* Requirements for effective codesign. What processes and strategies result in
   effective codesign collaborations?
* Finding the right set of data to collect, filter, and analyze. Efforts to address
   this problem across different groups and centers.
* Providing effective analysis in a timely manner. Efforts to address this problem
   across different groups and centers.
* Novel interactions based on data-centric analysis with multiple HPC subcommunities
   (e.g., vendors, operations staff, end users, facilities planning, security staff, …).
* Success stories involving privacy and security issues associated with data
   originating from many diverse systems.

——————————————————————————-
Paper submission and publication
——————————————————————————-
Work In Progress papers should be no more than 3 single-spaced pages (including figures, tables,
and references) using a 11-point font on 8.5×11 inch pages (US Letter).

Submissions can be made at: https://urldefense.us/v3/__https://submissions.supercomputing.org__;!!G_uCfscf7eWS!bjLXW9ZhMM_D8vc9COl8m1QXC9bWvJ3yXY-IMDinKBxDRfFeaA5Lr2nZb8ICO1A78lxfzr9Oojwl-2LdkV0BXf9W$   (look for SQCS under workshops)

Publication will be included as part of the SQCS series of annual reports.