2nd S2I2 HEP/CS Workshop
→
US/Eastern
Princeton University
Princeton University
Daniel S. Katz
(University of Illinois),
Douglas Thain
(University of Notre Dame),
Jim Pivarski
(Princeton University),
Mark Neubauer
(Univ. Illinois at Urbana-Champaign (US)),
Michael David Sokoloff
(University of Cincinnati (US)),
Oliver Gutsche
(Fermi National Accelerator Lab. (US)),
Peter Elmer
(Princeton University (US)),
Robert William Gardner Jr
(University of Chicago (US)),
Sergei Gleyzer
(University of Florida (US))
Description
The worldwide particle physics community is currently planning upgrades to the Large Hadron Collider (LHC) at CERN in Geneva. The LHC today already uses a worldwide distributed computing grid to meet the needs of thousands of scientists to process and analyze some of the world's largest scientific datasets. The upgrades being planned will increase data volumes by more than two orders of magnitude and require significantly more complex data and analysis techniques.
This 2nd S2I2 HEP/CS workshop aims to bring together a diverse set of attendees from the high energy physics (HEP) and computer science (CS) communities to understand how the two communities could work together in the context of a future NSF Software Institute aimed at supporting particle physics research over the long term. We will build on the discussions which took place at the the first S2I2 HEP/CS workshop and take a fresh look at planned HEP and computer science research and brainstorm about engaging specific areas of effort, perspectives, synergies and expertise of mutual benefit to HEP and CS communities, especially as it relates to a future NSF Software Institute for HEP.
Discussions and sessions include Science Practices & Policies, Sociology and Community Issues, Machine Learning, Software Life Cycle / Software Engineering / Software/Data/Workflow Preservation & Reproducibility, Scalable Platforms, Data Management, Access, Distribution, Organization, Data Intensive Analysis Tools and Techniques, Visualization, Data Streaming and Training, Education, Professional Development, Advancement.
The meeting rooms at Princeton are:
- Monday (plenary) - Lewis Library 120 (Vidyo link)
- Tuesday (parallel sessions) - McDonnell 103, Jadwin Hall A06, Jadwin Hall 475, Jadwin Hall 111
- Wednesday (plenary) - Lewis Library 138 (Vidyo link)
Useful links:
Sponsors
This event is being organised in part by the S2I2-HEP Conceptualization project, including travel support for some participants. The S2I2-HEP project is supported by National Science Foundation grants ACI-1558216, ACI-1558219, and ACI-1558233.
-
-
12:00
→
12:45
Lunch 45m
-
12:45
→
12:55
Workshop Introduction 10m Lewis Library 120
Lewis Library 120
-
12:55
→
13:25
The S2I2-HEP Conceptualization Project 30m Lewis Library 120
Lewis Library 120
Speaker: Peter Elmer (Princeton University (US)) -
13:25
→
13:50
Summary of first S2I2 HEP/CS workshop at NCSA/UIUC 25m Lewis Library 120
Lewis Library 120
Speaker: Mark Neubauer (Univ. Illinois at Urbana-Champaign (US)) -
13:50
→
14:10
Building Communities with the Open Science Grid 20m Lewis Library 120
Lewis Library 120
Speaker: Frank Wuerthwein (Univ. of California San Diego (US)) -
14:10
→
14:30
Software and Programming Support for Computational Research at Princeton 20m Lewis Library 120
Lewis Library 120
Speaker: Ian Cosden (Princeton University) -
14:30
→
14:50
Program Director Perspectives on the High-Energy Physics Institute 20m Lewis Library 120
Lewis Library 120
Speakers: Rajiv Ramnath (National Science Foundation), Vipin Chaudhary (National Science Foundation) -
14:50
→
15:20
Coffee Break 30m
-
15:20
→
15:25
Science Practices & Policies, Sociology and Community Issues (Intro) 5m Lewis Library 120
Lewis Library 120
-
15:25
→
15:45
Understanding Scientific Collaboration 20m Lewis Library 120
Lewis Library 120
Speaker: Charlotte Lee (University of Washington) -
15:45
→
16:00
Collaborations and Communities in High Energy Physics 15m Lewis Library 120
Lewis Library 120
Speaker: Michael David Sokoloff (University of Cincinnati (US)) -
16:00
→
16:20
The Large Synoptic Survey Telescope (LSST) 20m Lewis Library 120
Lewis Library 120
Speaker: Robert Lupton (Princeton University) -
16:20
→
16:40
Center for Research in Open Source Software (CROSS) 20m Lewis Library 120
Lewis Library 120
Speaker: Carlos Maltzahn (University of California - Santa Cruz) -
16:40
→
17:00
Scientific Computing in the Clouds 20m Lewis Library 120
Lewis Library 120
Speaker: Karan Bhatia (Google) -
17:30
→
19:30
Reception - Prospect House 2h
-
12:00
→
12:45
-
-
09:00
→
10:30
Parallel Session - Data Management, Access and Organisation / Data Streaming 1h 30m Jadwin Hall 475
Jadwin Hall 475
-
Introduction 20mSpeakers: Oliver Gutsche (Fermi National Accelerator Lab. (US)), Tanu Malik (Depaul)
-
-
09:00
→
10:30
Parallel Session - Machine Learning, Algorithms 1h 30m Jadwin Hall 111
Jadwin Hall 111
-
Introduction 20mSpeaker: Sergei Gleyzer (University of Florida (US))
-
Lightning Talk: Emerging trends in software for statistics and machine learning 5mSpeaker: Kyle Stuart Cranmer (New York University (US))
-
Lightning Talk: Kalman Filter based Tracking Reconstruction 5mSpeaker: Dr Matthieu Lefebvre (Princeton University (US))
-
Lightning Talk: ML for Pattern Recognition in HEP 5mSpeaker: Paolo Calafiura (Lawrence Berkeley National Lab. (US))
-
Lightning Talk: Optimization of distributed systems from the network point of view using machine learning 5mSpeaker: Harvey Newman (California Institute of Technology (US))
-
Lighnint Talk: End-to-end reconstructon and classification in HEP with deep learning 5mSpeaker: Michael Andrews (Carnegie-Mellon University (US))
-
Lighning talk: Data Management and ML 5mSpeaker: Valentin Y Kuznetsov (Cornell University (US))
-
Lighning Talk: Learnings from Industry: Tooling, Learning from Massive Datasets, & Software Quality @SoundCloud 5mSpeaker: Meghan Kane
-
Lightning Talk: Machine Learning As a Service 5mSpeaker: Ilija Vukotic (University of Chicago (US))
-
Lightning Talk: Neural Network Optimization for Physics 5mSpeaker: Fernanda Psihas (Indiana University)
-
Lightning Talk: Edward: A library for probabilistic modeling, inference, and criticism 5mSpeaker: Dustin Tran (Columbia University)
-
-
09:00
→
10:30
Parallel Session - Software Life Cycle / Software Engineering 1h 30m McDonnell Hall 103
McDonnell Hall 103
-
Introduction 20mSpeakers: Elizabeth Sexton-Kennedy (Fermi National Accelerator Lab. (US)), Jeffrey Carver (University of Alabama)
-
Lightning Talk: An Update on Software Citation 5mSpeaker: Daniel S. Katz (University of Illinois)
-
Lightning Talk: Software Amoebas 5mSpeakers: Douglas Thain, Douglas Thain (University of Notre Dame)
-
Lightning Talk: Generating All the Things: Using Code Generation to Transform Scientific Knowledge to Software Artifacts 5mSpeaker: Spencer Smith
-
-
10:30
→
11:00
Coffee Break 30m
-
11:00
→
12:30
Parallel Session - Data Management, Access and Organisation / Data Streaming 1h 30m Jadwin Hall 475
Jadwin Hall 475
-
Discussion 1h 30m
-
-
11:00
→
12:30
Parallel Session - Machine Learning, Algorithms 1h 30m Jadwin Hall 111
Jadwin Hall 111
-
Discussion 1h 30m
-
-
11:00
→
12:30
Parallel Session - Software Life Cycle / Software Engineering 1h 30m McDonnell Hall 103
McDonnell Hall 103
-
Discussion 1h 30m
-
Lightning Talk: Static Analysis Tools 5mSpeaker: Christopher Jones (Fermi National Accelerator Lab. (US))
-
-
12:30
→
13:30
Lunch 1h
-
13:30
→
15:00
Parallel Session - Data Intensive Analysis Tools & Visualization 1h 30m Jadwin Hall 111
Jadwin Hall 111
-
Lightning Talk: Constructing a ROOT-less workflow with python and HDF5 5mSpeaker: Matthew Bellis (Siena College)
-
Lightning Talk: Machine learning pipelines with Spark ML 5mSpeaker: Dr Alexey Svyatkovskiy (Princeton University)
-
Lightning Talk: XENON1T, Open Source and Python 5mSpeaker: Christopher Tunnell (Enrico Fermi Institute-University of Chicago-Unknown)
-
Lightning Talk: Volumetric image analysis and visualization problems in neuroimaging 5mSpeaker: Lawrence Frank (UCSD)
-
13:30
→
15:00
Parallel Session - Scalable Platforms 1h 30m Jadwin Hall A06
Jadwin Hall A06
-
Introduction 20mSpeakers: Douglas Thain (University of Notre Dame), Robert William Gardner Jr (University of Chicago (US))
-
Lightning Talk: Corralling Heterogeneous Systems 5mSpeaker: Gordon Watts (University of Washington (US))
-
Lightning Talk: Distributed Scalable Platforms Issues and Approaches 5mSpeaker: Harvey Newman (California Institute of Technology (US))
-
Lightning Talk: Services at the Edge 5mSpeaker: Robert William Gardner Jr (University of Chicago (US))
-
Lightning Talk: Towards 1000x with Heterogeneous, Programmable Hardware Datacenter 5mSpeaker: Anton Burtsev (University of California - Irvine)
-
Lightning Talk: Non-determinism in applications at the exascale: impact on debugging and numerical reproducibility 5mSpeaker: Michela Taufer (University of Delaware)
-
Lightning Talk: Exploiting node-level parallelism at exascale 5mSpeaker: Prof. Sunita Chandrasekaran (University of Delaware)
-
Lightning Talk: Missing Abstractions 5mSpeaker: Daniel S. Katz (University of Illinois)
-
Lightning Talk: Do we need distributed computing? 5mSpeaker: Kaushik De (University of Texas at Arlington (US))
-
Lightning Talk: Developing non-LHC software and our Services-based infrastructure dream 5mSpeaker: Christopher Tunnell (Enrico Fermi Institute-University of Chicago-Unknown)
-
Lightning Talk: Fundamental Problems of Distributed Systems 5mSpeaker: Douglas Thain
-
Lightning Talk: Learnings from Industry: Tooling, Datasets, Productivity, & Software Quality @SoundCloud 5mSpeaker: Meghan Kane (SoundCloud)
-
-
13:30
→
15:00
Parallel Session - Software/Data/Workflow Preservation & Reproducibility 1h 30m Jadwin Hall 475
Jadwin Hall 475
-
Introduction 20mSpeakers: Carlos Maltzahn (University of California - Santa Cruz), Mike Hildreth (University of Notre Dame (US))
-
Lightning Talk: Non-determinism in applications at the exascale: impact on debugging and numerical reproducibility 10mSpeaker: Michela Taufer (University of Delaware)
-
Lightning Talk: Recast, Reana, and HepData: infrastructure for reproducibility and reinterpretation 5mSpeaker: Lukas Alexander Heinrich (New York University (US))
-
Lightning Talk: The Popper Framework 20mSpeaker: Carlos Maltzahn (University of California - Santa Cruz)
-
-
15:00
→
15:30
Coffee Break 30m
-
15:30
→
17:00
Parallel Session - Data Intensive Analysis Tools, Visualization 1h 30m Jadwin Hall 111
Jadwin Hall 111
-
Discussion 1h 30m
-
-
15:30
→
17:00
Parallel Session - Scalable Platforms 1h 30m Jadwin Hall A06
Jadwin Hall A06
-
Discussion 1h 30m
-
-
15:30
→
17:00
Parallel Session - Software/Data/Workflow Preservation & Reproducibility 1h 30m Jadwin Hall 475
Jadwin Hall 475
-
Swift Workflows at Argonne 10mSpeaker: Justin Wozniak (Argonne National Lab)
-
CI for High Level Science Goals 20mSpeaker: Kyle Stuart Cranmer (New York University (US))
-
Discussion 1h 30m
-
-
09:00
→
10:30
-
-
09:00
→
09:05
Training, Education, Professional Development, Advancement 5m Lewis Library 138
Lewis Library 138
-
09:05
→
09:25
Physics Analysis Training Model at the CMS Experiment 20m Lewis Library 138
Lewis Library 138
Speaker: Sudhir Malik (University of Puerto Rico (PR)) -
09:25
→
09:45
Discussion - Training 20m Lewis Library 138
Lewis Library 138
-
09:45
→
10:00
Summary - Software Life Cycle / Software Engineering 15m Lewis Library 138
Lewis Library 138
Speakers: Elizabeth Sexton-Kennedy (Fermi National Accelerator Lab. (US)), Jeffrey Carver (University of Alabama) -
10:00
→
10:15
Summary - Software/Data/Workflow Preservation & Reproducibility 15m Lewis Library 138
Lewis Library 138
Speakers: Carlos Maltzahn (University of California - Santa Cruz), Mike Hildreth (University of Notre Dame (US)) -
10:15
→
10:30
Summary - Machine Learning, Algorithms 15m Lewis Library 138
Lewis Library 138
Speaker: Sergei Gleyzer (University of Florida (US)) -
10:30
→
11:00
Coffee Break 30m
-
11:00
→
11:15
Summary - Data Intensive Analysis Tools, Visualization 15m Lewis Library 138
Lewis Library 138
Speaker: Fernanda Psihas (Indiana University) -
11:15
→
11:30
Summary - Scalable Platforms 15m Lewis Library 138
Lewis Library 138
Speakers: Douglas Thain (University of Notre Dame), Robert William Gardner Jr (University of Chicago (US)) -
11:30
→
11:45
Summary - Data Management, Access and Organisation/Data Streaming 15m Lewis Library 138
Lewis Library 138
Speakers: Oliver Gutsche (Fermi National Accelerator Lab. (US)), Tanu Malik (Depaul) -
11:45
→
12:55
Discussion - Next Steps 1h 10m Lewis Library 138
Lewis Library 138
-
12:55
→
13:00
Closeout 5m Lewis Library 138
Lewis Library 138
-
13:00
→
13:15
Take-Away Lunch 15m
-
09:00
→
09:05