MEMSYS 2016

Memory Systems Conference (MEMSYS)
Washington, DC, USA
IMPORTANT DATES:
Submission Deadline: March 18*, 2016
Notification: May 15, 2016
Camera-Ready: July 1, 2016
* There will be an automatic submission extension of one week
The memory system has become extremely important recently: memory is slow,
and this is the primary reason that computers don’t run significantly faster than
they do. In large-scale computer installations such as the building-sized
systems powering Google.com, Amazon.com, and the financial sector, memory is
often the largest dollar cost as well as the largest consumer of energy.
Consequently, improvements in the memory system can have significant impact on
the real world, improving power and energy, performance, and/or dollar cost.

Moreover, many of the problems we see in the memory system are
cross-disciplinary in nature—their solution would likely require work at all
levels, from applications to circuits. Thus, while the scope of the problem is
memory, the scope of the solutions will be much wider.

Areas of Interest

Previously unpublished papers containing significant novel ideas and technical
results are solicited. Papers that focus on system, software, and architecture
level concepts, outside of traditional conference scopes, will be preferred
over others (e.g., the desired focus is away from pipeline design, processor
cache design, prefetching, data prediction, etc.). Symposium topics include,
but are not limited to, the following:

– Memory system design from both hardware & software perspectives
– Operating system design for hybrid/nonvolatile memories
– Technologies including PCM, flash, DRAM, STT-RAM, 3DXP, etc.
– Data-movement issues and mitigation techniques
– Interconnects to support large-scale data movement
– Software & application techniques for distributed memories
– Software management techniques
– Near-memory computing
– Memory-centric programming models & compiler techniques
– Memory failure modes and mitigation strategies
– Memory and system security issues

To reiterate, papers that focus on topics outside of traditional conference
scopes will be preferred over others.

SUBMISSION GUIDELINES:
Our primary goal is to showcase interesting ideas that will spark conversation
between disparate groups—to get applications people and operating systems
people and system architecture people and interconnect people and circuits
people to talk to each other. We accept extended abstracts, position papers,
and/or full research papers, and each accepted submission is given a 20-minute
presentation time slot. All accepted papers will be published in the ACM
Digital Library.

Submission formats:
2 page Extended Abstracts
5–6 page Position Papers
10–12 page Research Papers

Conference paper layout, no less than 9pt font in body, two-column, blind
submission, up to 15 pages in length.

All accepted submissions will be presented, published in the ACM Digital
Library, and included in the printed conference proceedings.

Note: Submitting either Extended Abstracts or Position Papers will not
preclude an author from submitting their work, in a longer research format,
to another publication forum at a later date.

ORGANIZERS:
Bruce Jacob, U. Maryland
Kathy Smiley, Memory Systems
Ameen Akel, Micron
James Ang, Sandia National Labs
Yitzhak Birk, Technion
Bruce Childers, U. Pittsburgh
Zeshan Chishti, Intel
Chen Ding, U. Rochester
David Donofrio, Berkeley Lab
Wendy Elsasser, ARM
Maya Gokhale, LLNL
Thuc Hoang, NNSA/DOE
Hillery Hunter, IBM
Mike Ignatowski, AMD
Aamer Jaleel, NVIDIA
David Kaeli, Northeastern
Scott Lloyd, LLNL
Gabriel Loh, AMD
Kenneth Ma, Hynix
Richard Murphy, Micron
Mike O’Connor, NVIDIA
Petar Radojkovic, BSC
David Resnick, Sandia National Labs
Arun Rodrigues, Sandia National Labs
John Shalf, Berkeley Lab
Anouk Van Laer, U. College London
Jeffrey Vetter, Georgia Tech & ORNL
Robert Voigt, Northrop Grumman
David Wang, Inphi
Christian Weis, U. Kaiserslautern
Kenneth Wright, Rambus
Sudhakar Yalamanchili, Georgia Tech