Login

Throughput Computing Week 2026

Jun 9 – 12, 2026
Fluno Center on the University of Wisconsin-Madison Campus
America/Chicago timezone

Questions about attending, speaking, accommodations, and other concerns

Contribution List

79 out of 79 displayed
  1. 67. Welcome and meeting Overview
    Dr Alexei Klimentov (Brookhaven National Lab), Shawn McKee (University of Michigan)
    6/9/26, 9:00 AM

    Welcome and quick preview of the next 2 days.

    Go to contribution page
  2. 64. Welcome to Throughput Computing Week
    Dr Patrick McDaniel (UW-Madison)
    6/9/26, 9:00 AM
  3. 69. ADC Priorities During LS3 and Site Procurement implications
    Ivan Glushkov (BNL)
    6/9/26, 9:05 AM

    What should be we planning on doing for infrastructure updates?
    - ARM compute servers?
    - GPU servers?
    - Storage servers, specifically what are the needed charactistics?
    - Netwoking: how do we get to 400 Gpbs links by HL-LHC startup?
    - Infrastructure: power, management, resiliency, capacity; what do we need?
    - Services: what middleware and are changes needed in services we deploy?
    ...

    Go to contribution page
  4. 46. To Be Provided
    Dr Miron Livny (UW-Center for High Throughput Computing)
    6/9/26, 9:05 AM
  5. 68. T1/T2 Priorities and Hardware Cost Mitigations
    Frederick Luehring (Indiana University), Kaushik De (University of Texas at Arlington)
    6/9/26, 9:30 AM

    We need to discuss facility priorities during the upcoming LS3.

    • US ATLAS pledge resources
    • More important: infrastructure upgrades
    • Common tools for US sites (perhaps new AI tools)

    We also need to explore our current cost environment and its implications for our facilities. With no additional "bump" of funding foreseen before HL-LHC, how can we optimize our resource...

    Go to contribution page
  6. 6. A Perspective from Smaller Institutions
    Jason Simms (Swarthmore College)
    6/9/26, 9:35 AM
  7. 71. Wrap Up Discussion
    6/9/26, 10:00 AM

    Opportunity to finish any discussion items from this session.

    Go to contribution page
  8. 43. AI Meets CI, Report from the CI Compass Community Workshop
    Ewa Deelman (USC Information Sciences Institute)
    6/9/26, 10:05 AM
  9. 73. AF Survey Results
    Dr Viviana Cavaliere (BNL)
    6/9/26, 11:00 AM

    Present the results from the recent AF survey and discuss

    Go to contribution page
  10. 65. Introduction of David Swanson Awardee
    Ronda Swanson (University of Nebraska-Lincoln)
    6/9/26, 11:00 AM
  11. 11. Justice at Scale: Leveraging High-Throughput Computing to Analyze Millions of Judicial Records - Presented by David Swanson Awardee
    Saloni Bhogale (University of Wisconsin-Madison)
    6/9/26, 11:10 AM
  12. 72. LLM Assisted Analysis at the UC AF
    Dr Giordon Stark (UCSC)
    6/9/26, 11:25 AM
  13. 9. LLM Assisted Facilitation
    Christina Koch (UW Madison)
    6/9/26, 11:45 AM
  14. 77. Towards Agentic Ops
    Ilija Vukotic (University of Chicago)
    6/9/26, 11:50 AM

    Can we as a facility define use-cases and challenges that we need to meet with AI/LLM?

    What are the options currently available in this space?

    Can we create an initiative in this area for the facility to pursue in the next year? (Has scrubbing implications)

    Go to contribution page
  15. 12. Enabling Large-Scale and Ultra-Large AlphaFold3 Predictions with Distributed High-Throughput Computing
    Daniel (Danny) Morales (UW-Center for High Throughput Computing)
    6/9/26, 12:10 PM

    AlphaFold 3 (AF3) enables atomic-resolution prediction of biomolecular complexes, driving rapidly growing demand across the life sciences. However, its ~750 GB reference database has effectively confined production deployments to systems with shared parallel filesystems, creating a major barrier for scalability. Distributed high-throughput computing (dHTC) platforms offer vast, heterogeneous...

    Go to contribution page
  16. 75. Testing a Hermes Agent: LLM to design web pages via natural language
    Louis Pelosi (BNL)
    6/9/26, 12:15 PM
  17. 61. Keynote Introduction
    Brian Bockelman (Morgridge Institute for Research)
    6/9/26, 1:30 PM
  18. 17. Keynote: The Present and the Future of Multi-Messenger Astrophysics
    Dr Michael Coughlin (University of Minnesota)
    6/9/26, 1:35 PM

    With the detection of compact binary coalescences and their electromagnetic counterparts by gravitational-wave detectors, a new era of multi-messenger astronomy has begun. In this talk, I will describe how data science is enabling the gravitational-wave community to make very low-latency detection and parameter estimation possible within the alert system. I will then discuss how current ground...

    Go to contribution page
  19. 76. Fabrics and Storage for USATLAS
    Oszkar Tarjan (BNL)
    6/9/26, 3:05 PM

    What are the technologies we use to interconnect our services and data?
    Are there technologies or services our sites should deploy broadly?
    What are the available storage components for USATLAS, both in-use and available? Pros/Cons?

    Go to contribution page
  20. 28. The hidden latencies in real-time astronomy
    Kendall Ackley (University of Warwick/Gravitational-wave Optical Transient Observer)
    6/9/26, 3:05 PM
  21. 29. Computing hurdles in wide-field target-of-opportunity searches with Rubin and ZTF (Remote Presentation)
    Shreya Anand (Standford University)
    6/9/26, 3:30 PM
  22. 74. Storage Policies for USATLAS Users
    Ofer Rind (BNL)
    6/9/26, 3:30 PM

    We need to discuss our plans for storage supporting the needs of our USATLAS users.

    Go to contribution page
  23. 32. On the role of multimodality for the real-time discovery and classification of transients
    Ved Shah (Northwestern University)
    6/9/26, 3:50 PM

    The Rubin Observatory is detecting an unprecedented number of transients each night, exceeding the classification capacity of all existing spectroscopic resources my several orders of magnitude. As a result, robust photometric classifications will be essential both for assembling complete samples of different transient subtypes and for identifying events that warrant spectroscopic follow-up....

    Go to contribution page
  24. 90. HTCondor Modernization at BNL
    Thomas Smith (BNL)
    6/9/26, 3:55 PM
  25. 78. USATLAS Ops & Monitoring
    Ofer Rind (BNL)
    6/9/26, 4:10 PM

    We need to discuss how we operate USATLAS with a focus on current and possible monitoring components.

    Go to contribution page
  26. 57. Ten Million Alerts a Night: Computing Bottlenecks in Real-Time Multi-Messenger Astrophysics (Remote Presentation)
    Gautham Narayan (University of Illinois Urbana-Champaign)
    6/9/26, 4:15 PM

    Real-time multi-messenger astrophysics is as much a computing problem as a telescope problem. The same event can trigger gravitational-wave, neutrino, radio, and optical alerts within seconds, but the science only happens if the infrastructure can carry, filter, and join those streams fast enough to act on them. I work on three of these systems: ANTARES, which ingests and classifies Rubin's...

    Go to contribution page
  27. 79. Discussion on Tools and R&D
    6/9/26, 4:30 PM

    Open discussion on session items.

    Need to gather scrubbing related items by WBS area.

    How will we operate during LS3?
    How will we meet ATLAS needs for HL-LHC, given our funding and cost environment?

    Go to contribution page
  28. 33. Constraining Degeneracies in Gamma-Ray Burst Simulations
    Nathan Walker (Oregon State University)
    6/9/26, 4:40 PM

    I will talk about difficulties associated with free parameters in modeling GRB emission. Without a way to constrain these parameters, inferring too much information from models can be problematic. Recent advances in the physics that can launch GRB jets, however, have the potential to enable a deep understanding of GRBs and their progenitors. My talk will address how degeneracies arise in...

    Go to contribution page
  29. 83. DC27 and Mini-Challenge Planning
    Shawn McKee (University of Michigan)
    6/10/26, 9:00 AM
  30. 49. Processing Every Image: Rubin Observatory's Data Release Production
    Colin Slater
    6/10/26, 9:00 AM
  31. 56. Of Needles and Haystacks: Lessons from the GW-MMADS follow-up campaign during the fourth LIGO/Virgo/KAGRA observing run
    Tomas Cabrera (Carnegie Mellon University)
    6/10/26, 9:25 AM

    Gravitational wave follow-up requires iterative observation, analysis, and decision-making on the order of hours in the most extreme of cases. To this extent, it is a subfield where throughput is defined not only by the amount of pertinent data, but rather the speed at which the information in the data can be synthesized into a human-digestible format. In this talk I will present the...

    Go to contribution page
  32. 91. Results from NET2->Prague 400 Gbps Testing
    Eduardo Bach (University of Massachusetts - Amherst)
    6/10/26, 9:30 AM
  33. 84. RP1 Core, Open Data Facility and Implications for AFs in the HL-LHC era
    Aidan Rosberg (Indiana University)
    6/10/26, 9:45 AM

    Aidan will present on RP1 and Open Data. We can use this as a springboard to discuss needs for AFs during HL-LHC.

    Go to contribution page
  34. 44. Radio Follow-up of GW Events: Opportunities and Challenges (Remote Presentation)
    Alessandra Corsi (John Hopkins University)
    6/10/26, 9:50 AM

    In this talk, I will discuss current and future opportunities in the radio follow-up of gravitational-wave (GW) events using interferometric, PI-driven facilities such as the Karl G. Jansky Very Large Array (VLA) and the future next-generation VLA (ngVLA). I will highlight lessons learned from recent GW observing runs, and strategies for identifying and characterizing relativistic ejecta and...

    Go to contribution page
  35. 85. Discussion, Wrap-up including USATLAS Topics for WLCG-HSF November Meeting
    6/10/26, 10:05 AM

    We need to discuss what items we want to cover during the WLCG-HSF meeting in November. What are the important (to USTATLAS) topics and what our our goals for the meeting?

    We also need to wrap up items from this session.

    Go to contribution page
  36. 39. The VLA Sky Survey and multi-messenger astronomy
    Mark Lacy
    6/10/26, 10:10 AM

    The VLA Sky Survey images the whole sky at 2-4GHz in the radio with angular resolution comparable to optical telescopes, providing a unique reference survey for the radio sky. Multi-epoch data allows variable sources and transients to be found and characterized and spectral and polarimetric information is also recorded. Processing the large amount of data from this survey is a significant...

    Go to contribution page
  37. 5. Lightning Updates for the Community of OSDF and OSPool Contributors
    Tim Cartwright (University of Wisconsin–Madison, OSG)
    6/10/26, 11:00 AM
  38. 80. Review of WBS 2.3 Activities (Beyond T1/T2)
    Kaushik De (University of Texas at Arlington), Ofer Rind (BNL)
    6/10/26, 11:00 AM

    What are the activities we have been focused on recently for WBS 2.3 outside of the T1/T2s?

    Go to contribution page
  39. 2. The IceCube CredMon - Going Beyond the Manual to Support Pelican
    David Schultz (University of Wisconsin-Madison)
    6/10/26, 11:00 AM

    If the built-in HTCondor OAuth2 doesn't meet your needs, you can always choose to do your own thing. In this talk, we show how and why IceCube wrote a custom token storer and CredMon to handle OAuth2 token creation and refresh. While custom code allows exactly matching the IceCube workflow, the main defining feature is not having to ask command line users to do an additional web login. Along...

    Go to contribution page
  40. 7. A Statewide Perspective from a REN (Remote Presentation)
    Dr Pierrette Dagg (MERIT)
    6/10/26, 11:10 AM
  41. 81. Lightning Talks - What to do better for WBS 2.3?
    William Leight (University of Massachusetts), philippe Laurens (Michigan State University), wenjing wu (University of Michigan)
    6/10/26, 11:25 AM

    One or two slides each, 5 minutes

    Your thoughts on "What we could do better for WBS 2.3?"

    Zachary Booth
    Judith Stephens
    Wenjing Wu
    Andrey Zarochentsev
    Philippe Laurens
    Will Leight

    Go to contribution page
  42. 48. Rubin Observatory: Scaling towards Data Release Production using HTCondor
    Greg Daues (NCSA)
    6/10/26, 11:25 AM

    Rubin Observatory will begin conducting the Legacy Survey of Space and Time (LSST), a 10 year survey of the Southern sky. This presentation will briefly cover how the project successfully uses HTCondor based workflows for several flavors of processing, including preparations for the project's Data Release Production at the United States Data Facility.
    The project's middleware that interfaces...

    Go to contribution page
  43. 26. Trends in campus resource planning and resource sharing
    Preston Smith (Purdue University)
    6/10/26, 11:35 AM

    As AI demands boom, and the market forces we all face as a side effect continue to impact campus buying power, it is more important than ever to understand how to capacity plan for your campus, and how that capacity planning fits into the larget picture of your state, region, and the nation. This presentation will share research in capacity planning for campuses, and explore how shared...

    Go to contribution page
  44. 27. JAWS and the Backend Architecture: HTCondor and Pool Management for Portable Scientific Workflows
    Seung-Jin Sul (Staff Software Engineer, U.S. Department of Energy (DOE) Joint Genome Institute (JGI), Lawrence Berkeley National Laboratory)
    6/10/26, 11:50 AM

    Authors

    Seung-Jin Sul*, Mario Melara, Ramani Kothadia, Ludovico Bianchi, Joshua Boverhof, Nick Tyler, Daniela Cassol, Mike Sneddon, Setareh Sarrafan, Kjiersten Fagnan
    Lawrence Berkeley National Laboratory, Berkeley, CA, USA

    Abstract

    Scientific workflows at the DOE Joint Genome Institute (JGI) increasingly need to run across multiple high-performance computing facilities, but...

    Go to contribution page
  45. 66. Community-Operated CI Resources for Campus Researchers
    Stephen Deems
    6/10/26, 12:00 PM
  46. 82. Scrubbing Planning and Discussion
    Shawn McKee (University of Michigan)
    6/10/26, 12:05 PM
  47. 45. Evolving the CMS Submission Infrastructure
    Marco Mascheroni (UCSD)
    6/10/26, 12:10 PM

    The CMS Submission Infrastructure (SI), based on HTCondor and GlideinWMS, operates a federated pool of resources, integrated from WLCG, HPC and cloud providers, supporting CMS offline computing needs. As CMS prepares for the High-Luminosity LHC (HL-LHC) phase, the infrastructure must continue evolving to support increasing resource scale and heterogeinity, while maintaining the stability,...

    Go to contribution page
  48. 23. Booster rockets for Birds: New Backends for the Pelican Origin
    Justin Hiemstra (Morgridge Institute for Research)
    6/10/26, 1:30 PM
  49. 86. Gather and Summarize Key Decisions
    6/10/26, 1:30 PM

    We need to summarize what we feel are the key decisions from our 2 day meeting.

    Go to contribution page
  50. 87. Create Action Items and Associated Responsibles
    6/10/26, 1:50 PM

    What are the needed action items?

    Who is assigned to each?

    Go to contribution page
  51. 24. Sharing Data: Authentication, Users, and Group Management in Pelican
    Brian Aydemir (Morgridge Institute for Research, UW–Madison)
    6/10/26, 1:55 PM
  52. 88. Next Steps and Wrapup
    6/10/26, 2:10 PM

    We need to specify next steps.

    Some of our work will provide guidance and input for scrubbing.

    What follow-on meetings are needed? Can we handle action items and next steps with our regularly scheduled facilities meetings or do we need more?

    Go to contribution page
  53. 1. Open Science data federation and National Research platform
    Fabio Andrijauskas
    6/10/26, 2:15 PM

    The Open Science Data Federation (OSDF) and the National Research Platform (NRP) represent a transformative shift toward a democratized, high-performance computational ecosystem designed to accelerate global scientific discovery. By integrating the OSDF’s robust data distribution capabilities with the NRP’s distributed, Kubernetes-based "Nautilus" infrastructure, researchers can seamlessly...

    Go to contribution page
  54. 20. Agents and Birds - Leveraging LLMs for Throughput Computing
    Brian Bockelman (Morgridge Institute for Research)
    6/10/26, 3:00 PM
  55. 35. Deploying Nextflow on CHTC: A Case Study for Serving Biology's Software Needs with AI-Assisted Engineering
    Nicholas Minor (Dave O'Connor's Laboratory/UW-Madison)
    6/10/26, 3:25 PM
  56. 15. A Tale of Two Ecosystems: Model Training in the OSPool and NAIRR
    Ian Ross (U. Wisconsin)
    6/10/26, 3:50 PM
  57. 22. Pegasus and AI: Use a Napkin, Run a Workflow
    Dr Ewa Deelman (USC Information Sciences Institute)
    6/10/26, 4:10 PM
  58. 38. Heterogeneous Prompt Processing Challenges in DUNE
    Steven Timm (Fermilab (DUNE))
    6/10/26, 4:35 PM

    DUNE faces unique challenges for data management and movement due to its very large event record size, needs for immediate prompt processing, and requirements for heterogeneous computing across an internationally distributed compute and storage system. We describe DUNE's current use of high throughput and high performance computing, including the growing AI/ML component, and the challenges we...

    Go to contribution page
  59. 55. Using OSG to enable the development of Simulation based inference for Cosmology
    Yuanyuan Zhang (NSF NOIRLab)
    6/11/26, 9:00 AM

    I will describe how OSG has enabled us to develop a simulation-based inference (SBI) method for cosmology analysis. For this application, we train an SBI model, based on a mixture density network (MDN), to derive posteriors for cosmological parameters from a data vector that describe observations of galaxy clusters in the universe. We use analytic models to generate mocks of the observational...

    Go to contribution page
  60. 34. OSG Security Status and The Future
    Mark Krenz (Indiana University)
    6/11/26, 9:25 AM

    This will be a high level overview of the security team's activities on OSG, what we're responsible for, and where we're going. It will provide summary metrics of what we've done, a short overview of the security exercise we've performed for US CMS and US ATLAS, and talk about us preparing for the coming wave of super AI that will discover all the zero days all at once.

    Go to contribution page
  61. 19. OrangeGrid Cloud Workers
    Peter Pizzimenti
    6/11/26, 9:50 AM

    OrangeGrid Cloud Workers is the infrastructure that lets Syracuse University's on premises HTCondor cluster overflow into public cloud spot instances when campus capacity runs out. A researcher submits a job the same way they always have, condor_submit my.sub from a campus submit host, and if the job opts in with +WantCloudBurst = "...", it can land on an ephemeral VM running in any public...

    Go to contribution page
  62. 47. HTC in the Search for Very High Energy Neutrinos with the Trinity Demonstrator
    Lily Sheram (Georgia Institute of Technology)
    6/11/26, 10:15 AM

    The Trinity Demonstrator is a one square meter imaging atmospheric Cherenkov telescope intended to validate the proposed technique for the Trinity Neutrino Observatory and search for high-energy neutrinos. Weakly interacting and chargeless, these elusive particles deliver data directly from their extragalactic sources to Earth. Trinity telescopes use Earth-Skimming, a detection method where a...

    Go to contribution page
  63. 50. From Per-Job Data to an Aggregated Workload Insight: A Toolkit for Profiling HTCondor Workload
    Kashika Mahajan (UW-Center for High Throughput Computing)
    6/11/26, 11:00 AM

    Researchers using HTCondor for high-throughput computing routinely submit groups of related jobs, known as Clusters, ranging from hundreds to tens of thousands of jobs each. Current tools report per-job data, making it difficult to diagnose Cluster-wide issues such as jobs stuck on hold, poor resource utilization, or unexpected failures. We present a Python toolkit, to be included as a part of...

    Go to contribution page
  64. 60. The HTCon-Door: Opening Your Compute Cluster to the World
    Cole Bollig (UW-Center for High Throughput Computing)
    6/11/26, 11:25 AM

    Connecting High Throughput batch resources to Open OnDemand for access via a web browser anywhere/anytime.

    Go to contribution page
  65. 62. Common Input Files
    Todd Miller (CHTC)
    6/11/26, 11:50 AM
  66. 63. Authorizing Remote Placement with the PlacementD
    Matyas Selmeci (UW-Madison CHTC)
    6/11/26, 12:15 PM
  67. 40. GlideinWMS Improvements and Challenges
    Marco Mambelli (Fermilab), Namratha Urs (Fermi National Accelerator Laboratory)
    6/11/26, 1:30 PM

    GlideinWMS is a workload management and resource provisioning system widely used for distributed scientific computing. Recent development efforts have focused on simplifying token-based authentication which is finally starting to be adopted in production and improving support for High Performance Computing (HPC) resources. This presentation will highlight recent progress in these areas and...

    Go to contribution page
  68. 42. Auto-regulating input files that save time when jobs fail
    Benjamin FitzGerald (University of Wisconsin-Madison)
    6/11/26, 1:55 PM

    I use CHTC and OSPool to run a rainfall frequency analysis pipeline across 200+ watersheds as part of FEMA's National Flood Insurance Program work. DAGMan was essential for automating job submission and output processing at this scale, but managing pipeline failures proved challenging -- specifically, ensuring that every daily precipitation file was properly analyzed before downstream steps...

    Go to contribution page
  69. 58. Wrangling Massive Task Graphs with VineReduce
    Douglas Thain (University of Notre Dame)
    6/11/26, 2:15 PM

    A number of modern programming frameworks encourage end users to write concurrent functional programs that are expanded into task graphs, and then executed using local parallelism. While providing an elegant user experience, these systems struggle when presented with large programs that generate million-node graphs and must run on heterogeneous systems. We demonstrate a new framework,...

    Go to contribution page
  70. 52. HTCondor Flight Path
    Todd Tannenbaum (University of Wisconsin)
    6/11/26, 3:30 PM

    HTCondor discussion of what's new and what coming up.

    Go to contribution page
  71. 25. Todd or Bot Game Show
    Greg Thain (Center for High Throughput Computing), Todd Tannenbaum (University of Wisconsin)
    6/11/26, 4:15 PM
  72. 37. INK (Interactive aNalysis worKbench) : Progress and AI Exploration (Remote Presentation)
    Jingyan Shi (INSTITUTE OF HIGH ENERGY PHYSICS, Chinese Academy of Science)
    6/12/26, 9:00 AM

    The INK has been deployed at IHEP as a unified scientist workbench, providing HTCondor-driven job submission, interactive analysis environments, and cross-cluster resource access under a single entry point. Since its release, user feedback has been quite positive.
    This talk presents recent main progress and optimizations: (1) per-experiment customization to meet diverse collaboration needs;...

    Go to contribution page
  73. 3. Climate Policy Modeling with HTCondor
    Ken Judd (Stanford University)
    6/12/26, 9:20 AM

    HTCondor was used to develop DPSOL, a framework for solving dynamic programming problems. It was the foundation for DSICE which merged dynamic and stochastic factors in economics and the climate, and analyzed the social cost of carbon, the cost of a two-degree target and the value of carbon capture and sequestration.

    Go to contribution page
  74. 16. Where's the Big Data for Protein Dynamics?
    Hannah Wayment-Steele (UW-Madison)
    6/12/26, 9:45 AM
  75. 21. YOL-No: Guiding Agent Usage on the Access point
    Ian Ross (U. Wisconsin)
    6/12/26, 10:10 AM
  76. 89. Analyzing and Optimizing Machine Timeout Duration Using AI (Remote Presentation)
    Khyathi Vagolu (UW-Madison)
    6/12/26, 11:00 AM

    When network disruptions or worker node failures occur, HTCondor relies on a static lease timeout, traditionally 40 minutes, before abandoning a job. This static window creates a costly trade-off: waiting too long causes massive machine idle time on unrecoverable failures, while cutting it too short prematurely kills jobs that could have successfully reconnected. Can we use AI to solve this?...

    Go to contribution page
  77. 18. MCP for HTCondor Admins
    Ilija Vukotic (University of Chicago)
    6/12/26, 11:25 AM
  78. 13. Cluster Metrics for External Services
    Ron Tapia (Penn State University)
    6/12/26, 11:50 AM

    Discussion of metrics that Condor can provide about the performance of external services. Condor has a unique view of the performance of the services that it uses on behalf of jobs. Examples of external services include file transfer plugins and credmons. Individual failures are not very interesting to cluster administrators, but widespread failures affecting many jobs are. What sort of...

    Go to contribution page
  79. 70. Hardware Cost Analysis and Mitigation Strategies
    Frederick Luehring (Indiana University)

    We need to explore our current cost environment and its implications for our facilities. With no additional "bump" of funding foreseen before HL-LHC, how can we optimize our resource expenditure to best meet (US)ATLAS needs between now and HL-LHC startup?

    Go to contribution page