CnC 2018: The Tenth Annual Concurrent Collections Workshop
November 29–30, 2018 at Stony Brook University (Stony Brook, NY)
The annual Concurrent Collections (CnC) workshop is as a forum
for researchers and developers of parallel programs to
interact on a variety of issues related to next-generation
parallel programming models. The focus is on fostering a
community around
the
CnC
programming model; however, we also strongly encourage
participation by anyone with an interest programming models
inspired by dataflow and/or tuple space ideas as well as
current or emerging applications of such models.
Online Registration
Thanks to the generous donations from our sponsors,
we will not require a registration fee for workshop attendance this year.
However, we still require online registration to ensure we have sufficient seating and
refreshments.
If you plan to attend all or part of the workshop this year,
please register online by Monday November 12, 2018:
Registration form to come soon.
Participation and call for abstracts
The workshop agenda includes a CnC tutorial on current
and future trends and talks selected from contributed
abstracts. Topics of interest include, but are not
limited to: language design and implementation,
semantics and theory, application experiences, and teaching CnC.
If you are interested in giving a talk, please submit a
short abstract (between 200–500 words in length) to the
workshop chairs at
cnc.workshop.committee@gmail.com
no later than Friday, November 2, 2018. Please include:
- Name
- Affiliation
- Abstract of the work to be presented (please limit to a maximum of 500 words)
Workshop Agenda - Thursday (Tutorials)
14:00
- Introduction to CnC: A dependence programming model
- Kath Knobe
- Rice University
14:45
- Introduction to Intel Concurrent Collections
- Frank Schlimbach
- Intel
15:30
- Polyhedral Optimization of CnC Programs
- Martin Kong and Louis
- Noel Pouchet
- Colorado State University
Workshop Agenda - Friday (Technical Talks)
9:00
- Welcome
- Robert Harrison and Martin Kong
9:15 (Keynote)
- Barbara Chapman
- Tasking in the Future
- Stony Brook University and Brookhaven National Laboratory
10:00 (Technical Talk #1)
- Tiles optimization in the application of Inner Product
- Dejan Grubišić, Srđan Milanković, Zoran Budimlić
- Rice University
10:30 (Technical Talk #2)
- Hierarchical CnC and Related Topics
- Kath Knobe
- Rice University
11:15 (Technical Talk #3)
- Updates on Regularity Detection and Pattern
- Matching for CnC Programs
- Gabriel Rodriguez and Louis-Noel Pouchet
11:45 (Serving food break)
12:00 (Technical Talk #4)
- Cache Analysis and Optimization Based on Reuse-time Distribution
- Chen Ding
- University of Rochester
12:30 (Technical Talk #5)
- Runtime Support for Tiled CnC Execution
- Srđan Milakovic, Zoran Budimlic
- Rice University
13:00 (Technical Talk #6)
- Automatic Code Generation to Dynamic Task Based Runtimes: Recent Results
- Charles Jin
- Reservoir Labs
13:30 (Technical Talk #7)
- Dependence Programming and Tiling for Irregular Numerical Applications
- Mahdi Javanmard and Robert Harrison
- Stony Brook University
14:00
- Workshop closure
- Robert Harrison and Martin Kong
Background on CnC
CnC is a parallel programming model for mainstream programmers
that philosophically differs from other approaches.
CnC programmers do not specify parallel operations. Instead,
they only specify semantic ordering constraints. This provides
a separation of concerns between the domain expert and tuning expert,
simplifying the domain expert’s job while providing more flexibility
to the tuning expert. Details on CnC and related research can be
found at:
https://icnc.github.io
and
https://habanero.rice.edu/cnc
Prior workshops have served as a forum for users and potential
users of Concurrent Collections (CnC), to discuss experiences
with CnC and a range of topics, including developments for the
language, applications, usability, performance, semantics, and
teaching of CnC.