Throughput Computing Week 2026

Jun 9, 2026, 12:05 AM → Jun 12, 2026, 3:20 PM America/Chicago

Howard Auditorium (Fluno Center on the University of Wisconsin-Madison Campus)

Thank you to all who participated! 

Almost all slides from HTC26 presentations have been posted on the speaker Contributions webpage on this site. (A few speakers have requested that their slides remain private). 

Videos of presentations from HTC26 will be posted in July. The presentations will be added to YouTube and linked on the Contributions page.  You will also be able to find the HTC26 video presentations organized by event and keyword on the PATh site .

We will select a date for HTC27 this June and will post that date here and send out a save the date reminders.  We hope to see you there!

 

 

Tue, June 9

6:30 AM Lakeshore Run

7:30 AM Registration, Coffee, and Light Breakfast

The PATh Forward

1 Welcome to Throughput Computing Week

Speaker: Dr Patrick McDaniel (UW-Madison)

2 TT&T - on Transition, Trust and Throughput

Speakers: Dr Miron Livny (UW-Center for High Throughput Computing), Peter Couvares (LIGO Laboratory - Caltech)

06 26 HTC26.pdf

06 26 HTC26.pptx

3 A Perspective from Smaller Institutions

Speaker: Jason Simms (Swarthmore College)

Simms-HTC26.pdf

Simms-HTC26.pptx

4 AI Meets CI, Report from the CI Compass Community Workshop

Speaker: Ewa Deelman (USC Information Sciences Institute)

HTC Week 2026 Community Pulse_ results_6_9_26.pdf

USATLAS Meeting: T1/T2 Operations & LS3 Priorities

Google doc to capture notes, action items decisions and milestones: https://docs.google.com/document/d/1_wYAVoJH2KVsOv8W5gZg9ZA2gRrj92I-RyTtLOPOyzw/edit?pli=1&tab=t.0

USATLAS Google Doc for Meeting Notes

5 Welcome and meeting Overview

Welcome and quick preview of the next 2 days.

Speakers: Dr Alexei Klimentov (Brookhaven National Lab), Shawn McKee (University of Michigan)

USATLAS F2F Meeting Introduction

USATLAS F2F Welcome.pdf

6 ADC Priorities During LS3 and Site Procurement implications

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?
- Applications: provisioning, monitoring, management, planning ?

Speaker: Ivan Glushkov (BNL)

ADC for LS3-2.pdf

7 T1/T2 Priorities and Hardware Cost Mitigations

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 expenditure to best meet (US)ATLAS needs between now and HL-LHC startup?

Speakers: Frederick Luehring (Indiana University), Kaushik De (University of Texas at Arlington)

USFac-T1T2-9Jun2026.pptx

USFac-T1T2-9Jun2026.pptx.pdf

8 Wrap Up Discussion

Opportunity to finish any discussion items from this session.

10:30 AM Break

Facilitation for HTC, AI Challenges and HTC AI Toolkit, David Swanson Awardee Researcher Talk

9 Introduction of David Swanson Awardee

Speaker: Ronda Swanson (University of Nebraska-Lincoln)

10 Justice at Scale: Leveraging High-Throughput Computing to Analyze Millions of Judicial Records - Presented by David Swanson Awardee

Speaker: Saloni Bhogale (University of Wisconsin-Madison)

bhogale_HTC26.pdf

11 Research Computing Facilitation

Speaker: Christina Koch (UW Madison)

htc26-facilitation-koch.pdf

htc26-facilitation-koch.pptx

12 Enabling Large-Scale and Ultra-Large AlphaFold3 Predictions with Distributed High-Throughput Computing

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 compute capacity but fundamentally lack the shared data infrastructure assumed by AF3. We present a data-aware deployment of AF3 for dHTC, implemented on the Center for High Throughput Computing (CHTC) and the Open Science Pool (OSPool). The workflow is decomposed into a CPU-bound data pipeline that executes on nodes with locally staged, scheduler-advertised databases, and a GPU-bound inference pipeline that opportunistically scales across distributed resources. Using CUDA Unified Virtual Memory (UVM), we extend inference beyond physical GPU limits, enabling predictions of ultra-large complexes that exceed device VRAM. By elevating dataset locality to a schedulable resource via HTCondor ClassAds, we eliminate prohibitive per-job data transfers and enable efficient, federated execution. Beyond scaling throughput, we demonstrate that dHTC can support previously infeasible workloads. Together, these results establish dHTC as a viable—and in some regimes superior—execution model for data-intensive structural biology workflows and provide a general blueprint for deploying large, data-intensive applications on distributed cyberinfrastructure.

Speaker: Daniel (Danny) Morales (UW-Center for High Throughput Computing)

Morales_HTC26_Slides.pdf

Morales_HTC26_Slides.pptx

USATLAS Meeting: AF and AI: Tools and Policies

Google doc to capture notes, action items decisions and milestones: https://docs.google.com/document/d/1_wYAVoJH2KVsOv8W5gZg9ZA2gRrj92I-RyTtLOPOyzw/edit?pli=1&tab=t.0

USATLAS Google Doc for Meeting Notes

13 AF Survey Results

Present the results from the recent AF survey and discuss

Speaker: Dr Viviana Cavaliere (BNL)

14 LLM Assisted Analysis at the UC AF

Speakers: Dr Giordon Stark (UCSC), Giordon Stark (SCIPP, UC Santa Cruz)

Slides (PDF export)

Slides (reveal.js)

15 Towards Agentic Ops

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)

Speaker: Ilija Vukotic (University of Chicago)

Towards Agentic Ops

16 Testing a Hermes Agent: LLM to design web pages via natural language

Speaker: Louis Pelosi (BNL)

Testing a Hermes Agent_ LLM to design web pages via natural language.pdf

12:30 PM Lunch

The Promise of Multi-Messenger Astronomy: Transforming Research (Keynote)

17 Keynote Introduction

Speaker: Brian Bockelman (Morgridge Institute for Research)

18 Keynote: The Present and the Future of Multi-Messenger Astrophysics

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 based optical surveys and dedicated follow-up systems are integrating machine learning into their standard work flows, with examples from both current and near future surveys. We will close with near-term prospects for the field.

Speaker: Dr Michael Coughlin (University of Minnesota)

Coughlin-keynote-HTC26.pdf

Coughlin-keynote-HTC26.pptx

2:35 PM Break

Multi-Messenger Astrophysics Computing Challenges

19 The hidden latencies in real-time astronomy

Speaker: Kendall Ackley (University of Warwick/Gravitational-wave Optical Transient Observer)

Ackley_HTC26_Slides.pdf

20 Computing hurdles in wide-field target-of-opportunity searches with Rubin and ZTF (Remote Presentation)

Speaker: Shreya Anand (Standford University)

Anand_HTC26_Slides.pdf

21 On the role of multimodality for the real-time discovery and classification of transients

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.

In this talk, we introduce a family of highly performant, real-time hierarchical classifiers designed for ZTF and LSST alert streams. These models incorporate images, multi-band light curves, and contextual metadata, to deliver reliable, high-level classifications within seconds of the first alert. Our hierarchical approach is unique in its ability to make classifications at several levels of granularity based on the available information, making it possible, for the first time, to produce high-level classifications at early times, and refine those classifications as more observations become available.

Our models achieve strong performance on real ZTF data, reaching >95% accuracy on binary Transient vs Persistent classification after the first day. For a more granular task distinguishing CVs, AGNs, and supernova subtypes, our models achieve >85% accuracy 128 days after first detection with our multimodal model delivering performance that far exceeds the light-curve only models, especially at early times. On the ELAsTiCC datasets of simulated LSST observations, we achieve state-of-the-art performance with a macro F1 score of 0.88. These results demonstrate that multi-modal, hierarchical classifiers can deliver classifications at LSST scale, supporting both real-time triaging and population studies from the earliest alerts.

Speaker: Ved Shah (Northwestern University)

Ved Shah - ORACLE Hierarchical Classifier.pdf

22 Ten Million Alerts a Night: Computing Bottlenecks in Real-Time Multi-Messenger Astrophysics (Remote Presentation)

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 ~10 million optical alerts a night; SCIMMA's Kafka-based Hopskotch platform, which carries the full LIGO-Virgo-KAGRA gravitational-wave alert stream and rapidly triggers Rubin to follow up the most promising events as targets of opportunity; and the throughput-bound, federated analysis coordination behind LSST DESC cosmology. The classification and prioritization at the center of all three will increasingly run on foundation models we build at the NSF-Simons SkAI Institute, trained across multi-survey, multi-modal data (light curves, images, and spectra). The hard parts — real-time inference at scale, latency- and reliability-critical alert delivery, federated data movement, and GPU-scale model training — are where we could use this community's help.

Speaker: Gautham Narayan (University of Illinois Urbana-Champaign)

23 Constraining Degeneracies in Gamma-Ray Burst Simulations

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 simulations, with an emphasis on how they may be resolved.

Speaker: Nathan Walker (Oregon State University)

HTC26_NWalker[34401].pdf

HTC26_NWalker.pptx

USATLAS Meeting: Tools, R&D and Storage

Google doc to capture notes, action items decisions and milestones: https://docs.google.com/document/d/1_wYAVoJH2KVsOv8W5gZg9ZA2gRrj92I-RyTtLOPOyzw/edit?pli=1&tab=t.0

USATLAS Google Doc for Meeting Notes

24 Fabrics and Storage for USATLAS

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?

Speaker: Oszkar Tarjan (BNL)

Fabrics and storage.pptx

25 Storage Policies for USATLAS Users

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

Speaker: Ofer Rind (BNL)

Storage Policies for USATLAS Users - US ATLAS F2F, 6_9_26.pdf

26 HTCondor Modernization at BNL

Speaker: Thomas Smith (BNL)

BNL HTC26 tsmith ATLAS presentation.pdf

27 USATLAS Ops & Monitoring

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

Speaker: Ofer Rind (BNL)

US ATLAS Ops and Monitoring - US ATLAS F2F, 6_9_26.pdf

28 Discussion on Tools and R&D

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?

Closing Remarks

5:05 PM Evening on the Memorial Union Terrace

We will walk over together to the Memorial Union Terrace following the last session for dinner. At the Terrace you can purchase burgers, brats, beer, and other casual fare. The rain date will be the following day - Wednesday, June 10.

Wed, June 10

8:00 AM Coffee, Pastries and Registration

Multi-Messenger Astrophysics Computing Challenges Part 2

29 Processing Every Image: Rubin Observatory's Data Release Production

Speaker: Colin Slater

Slater HTCondor Week 2026.pdf

30 Of Needles and Haystacks: Lessons from the GW-MMADS follow-up campaign during the fourth LIGO/Virgo/KAGRA observing run

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 follow-up effort of the Gravitational Wave-MultiMessenger Astronomy DECam Survey team (PIs Andreoni+Palmese) during the fourth LIGO/Virgo/KAGRA observing run through the lens of considering the technological infrastructure required to perform effective GW follow-up. I propose that maximizing scientific yield of follow-up efforts relies on maintaining a human-centric perspective on pipeline development in which the aggregation and presentation of big data products are just as important as the analytical methods producing said products.

Speaker: Tomas Cabrera (Carnegie Mellon University)

Cabrera_HTC26_Slides.pdf

31 Radio Follow-up of GW Events: Opportunities and Challenges (Remote Presentation)

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 multi-messenger counterparts across a broad range of transients. I will also discuss challenges related to observation planning, data reduction, sensitivity limitations, and long-term monitoring requirements. I will conclude with prospects for multi-messenger astronomy in the ngVLA era.

Speaker: Alessandra Corsi (John Hopkins University)

Corsi_HTC26_Slides.pdf

32 The VLA Sky Survey and multi-messenger astronomy

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 computational challenge as the high resolution of the survey means that subtle calibration and geometric effects need to be carefully treated. In this talk I will describe both some of the multi-messegenger science enabled by VLASS and the computational and logistical challenges of processing VLASS and other NRAO data in HPC/HTC environments.

Speaker: Mark Lacy

VLASS_CHTC2026.pdf

VLASS_CHTC2026.pptx

USATLAS Meeting: (Mini) Data Challenges and Prep for HL-LHC

Google doc to capture notes, action items decisions and milestones: https://docs.google.com/document/d/1_wYAVoJH2KVsOv8W5gZg9ZA2gRrj92I-RyTtLOPOyzw/edit?pli=1&tab=t.0

USATLAS Google Doc for Meeting Notes

33 DC27 and Mini-Challenge Planning

Brief overview of USATLAS plans for DC27 and associated mini-challenges.

Speaker: Shawn McKee (University of Michigan)

DC27 and (Mini) Data Challenge Planning

DC27 and (Mini) Data Challenge Planning.pdf

34 SENSE Rucio Discussion

Speakers: Justas Balcas (ESnet), Rafael Coelho Lopes de Sa (University of Massachusetts Amherst), Rob Gardner (University of Chicago)

SENSE in ATLAS

SENSE in ATLAS.pdf

35 Results from NET2->Prague 400 Gbps Testing

Speakers: Eduardo Bach (University of Massachusetts - Amherst), Rafael Coelho Lopes de Sa (University of Massachusetts Amherst)

NET2-PRG tests.pdf

36 RP1 Core, Open Data Facility and Implications for AFs in the HL-LHC era

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

Speaker: Aidan Rosberg (Indiana University)

HTC26-RP1-Dark.pdf

HTC26-RP1-Light.pdf

37 Discussion, Wrap-up including USATLAS Topics for WLCG-HSF November Meeting

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.

10:30 AM Break

Campus Impacts and Broader Outreach

38 Lightning Updates for the Community of OSDF and OSPool Contributors

Speaker: Tim Cartwright (University of Wisconsin–Madison, OSG)

Cartwright_HTC26_Slides.pdf

39 A Statewide Perspective from a REN (Remote Presentation)

Speaker: Dr Pierrette Dagg (MERIT)

Dagg_HTC26_Slides.pptx

40 Trends in campus resource planning and resource sharing

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 computing models continue to be a key way for campuses to provide resources in the AI era.

Speaker: Preston Smith (Purdue University)

Preston Smith HTC 2026.pptx

41 Community-Operated CI Resources for Campus Researchers

Speaker: Stephen Deems

HTC26 - Community-Operated Cyberinfrastructure (CI) Resources.pptx

Throughput Computing at Work: Reports from the Field

42 The IceCube CredMon - Going Beyond the Manual to Support Pelican

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 the way, we worked around several limitations in HTCondor and noted some things to avoid.

Speaker: David Schultz (University of Wisconsin-Madison)

HTC26 - IceCube Credmon-3.pdf

43 Rubin Observatory: Scaling towards Data Release Production using HTCondor

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 between the user and HTCondor,  a.k.a., Batch Production Service (BPS), will be introduced as well as the "allocateNodes" mechanism being used to submit user glideins to Slurm clusters.

Speaker: Greg Daues (NCSA)

HTC26-Daues.pdf

44 JAWS and the Backend Architecture: HTCondor and Pool Management for Portable Scientific Workflows

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 each site exposes a different mix of schedulers, queue policies, container runtimes, data-transfer paths, and security constraints. The JGI Analysis Workflow Service (JAWS) addresses this problem by separating the scientific workflow interface from the facility-specific execution backend. Users submit Workflow Description Language (WDL) workflows through a common client and JAWS Central service, while each JAWS Site provides the local backend configuration needed to execute those workflows on a particular compute environment.

This talk focuses on an introduction to JAWS and the backend architecture that makes that portability practical, with emphasis on HTCondor and the JAWS Pool Manager. In JAWS, Cromwell orchestrates WDL workflows, and HTCondor serves as the execution backend that receives task submissions, maintains the job queue, and dispatches work to compute pools at the target site. The JAWS Pool Manager implements the HTCondor glidein: it monitors HTCondor job queue, determines whether the pool has capacity, and provisions worker nodes from the site's native batch system (Slurm or PBS) to scale the HTCondor pool up and down with demand. The JAWS and HTCondor logs and metadata support performance reporting for CPU use, memory efficiency, runtimes, and failure modes. This design enables JAWS run task-by-task execution over heterogeneous facilities while presenting a consistent operational model to users and workflow developers.

Keywords

JAWS, HTCondor, workflow management, WDL, Cromwell, pool manager, HPC, DOE computing

Acknowledgement

The work conducted by the U.S. Department of Energy Joint Genome Institute, a DOE Office of Science User Facility, is supported by the Office of Science of the U.S. Department of Energy operated under Contract No. DE-AC02-05CH11231.

Speaker: Seung-Jin Sul (Staff Software Engineer, U.S. Department of Energy (DOE) Joint Genome Institute (JGI), Lawrence Berkeley National Laboratory)

HTC26_ssul.pdf

45 Evolving the CMS Submission Infrastructure

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, flexibility, and efficiency required for large-scale distributed computing.

This contribution presents recent developments in the CMS SI, focused on improving resource utilization and scheduling efficiency. In particular, we discuss the deployment of high-IO auxiliary slots to reduce slot fragmentation caused by bursts of short single-core workloads, and the introduction of controlled pilot overloading techniques aimed at recovering otherwise unused CPU cycles from inefficient or I/O-bound payloads. These strategies have shown systematic improvements in overall CPU efficiency while preserving stable SI operations..

The talk will also cover the continued evolution of CMS resource integration strategies for heterogeneous computing environments, including GPUs, ARM processors, and HPC facilities, together with broader CMS plans for the next-generation Workflow Management system designed for HL-LHC-scale workflows and increasingly dynamic computing resources. Together, these developments represent important steps toward a more scalable, sustainable, and efficient CMS computing infrastructure, as required by the HL-LHC program.

Speaker: Marco Mascheroni (UCSD)

Mascheroni_HTC26_Slides_fixed.pdf

USATLAS Meeting: WBS 2.3 Activities Review and Planning

Google doc to capture notes, action items decisions and milestones: https://docs.google.com/document/d/1_wYAVoJH2KVsOv8W5gZg9ZA2gRrj92I-RyTtLOPOyzw/edit?pli=1&tab=t.0

USATLAS Google Doc for Meeting Notes

46 Review of WBS 2.3 Activities (Beyond T1/T2)

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

Speakers: Kaushik De (University of Texas at Arlington), Ofer Rind (BNL)

USFac-Ops-10Jun2026.pdf

47 Lightning Talks - What to do better for WBS 2.3?

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

Speakers: William Leight (University of Massachusetts), philippe Laurens (Michigan State University), wenjing wu (University of Michigan)

20260610_HTC26F2F_Lightning_Laurens.key.pdf

HTC2026-AndreyZ.pdf

HTC26 Lightning Talk - Judith.pdf

lighting talk - will.pdf

Thoughts on WBS2.3 wenjing - Google Slides.pdf

48 Scrubbing Planning and Discussion

Speaker: Shawn McKee (University of Michigan)

Scrubbing Discussion

12:30 PM Lunch

Sharing Data, Data Stores and Utilizing the OSDF

49 Booster rockets for Birds: New Backends for the Pelican Origin

Speaker: Justin Hiemstra (Morgridge Institute for Research)

New Backends for the Pelican Origin.pdf

New Backends for the Pelican Origin.pptx

50 Sharing Data: Authentication, Users, and Group Management in Pelican

Speaker: Brian Aydemir (Morgridge Institute for Research, UW–Madison)

Sharing-Data-in-Pelican.pdf

Sharing-Data-in-Pelican.pptx

51 Open Science data federation and National Research platform

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 orchestrate data-intensive workflows across a federated backbone of compute and networking resources. As a community-driven cyberinfrastructure, the combined OSDF and NRP framework provides a scalable, secure, and vendor-neutral environment that bridges the gap between heterogeneous data repositories and high-speed processing, ultimately fostering a more collaborative and efficient open science landscape.

Speaker: Fabio Andrijauskas

Andrijauskas_HTC26_Slides.pdf

USATLAS Meeting: Closeout and Next Steps

Google doc to capture notes, action items decisions and milestones: https://docs.google.com/document/d/1_wYAVoJH2KVsOv8W5gZg9ZA2gRrj92I-RyTtLOPOyzw/edit?pli=1&tab=t.0

USATLAS Google Doc for Meeting Notes

52 Gather and Summarize Key Decisions

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

53 Create Action Items and Associated Responsibles

What are the needed action items?

Who is assigned to each?

54 Next Steps and Wrapup

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?

2:30 PM Break

Vibe-coding the future: Successes and Dramatic Failures in using Agentic AI

55 Agents and Birds - Leveraging LLMs for Throughput Computing

Speaker: Brian Bockelman (Morgridge Institute for Research)

Agents-and-Birds.pdf

56 Deploying Nextflow on CHTC: A Case Study for Serving Biology's Software Needs with AI-Assisted Engineering

Speaker: Nicholas Minor (Dave O'Connor's Laboratory/UW-Madison)

Minor_HTC26_Slides.pdf

57 The PATh to NAIRR: Heterogeneous Training of Machine Learning Models in OSPool and NAIRR

Speaker: Ian Ross (U. Wisconsin)

Ross_HTC26_Wednesday_Slides (1).pdf

Ross_HTC26_Wednesday_Slides.pptx

58 Pegasus and AI: Use a Napkin, Run a Workflow

Speaker: Dr Ewa Deelman (USC Information Sciences Institute)

deelman-Pegasus-HTC-2026-Wed.pdf

59 Heterogeneous Prompt Processing Challenges in DUNE

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 face in getting the data, code, and database information to the right kind of computer in timely fashion.

Speaker: Steven Timm (Fermilab (DUNE))

2026htcweek_sct.pdf

Closing Remarks

5:30 PM Small Group Dinners

At the close of the day's sessions, we'll announce small group dinner options to join. A couple CHTC staff members will lead each group to an area restaurant. Options are typically reasonably priced either on campus or the Capital Square.

6:00 PM Evening Bike Ride

A relaxed casual ride through the Arboretum. We will depart from the Fluno Center at 6 pm. CHTC staff will be around to assist with e-bike rentals from area stations.

7:30 PM Bonfire at Picnic Point with Smores and Hotdogs

We'll have staff available for rides to Lake Shore from Fluno. We'll have the fixins to roast hot dogs and make smores. Please bring your own water bottles or sodas, if desired No alcohol permitted.

Thu, June 11

8:00 AM Coffee, Pastries and Registration

Keeping an Eagle Eye On Things (monitoring)

60 Using OSG to enable the development of Simulation based inference for Cosmology

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 data vectors needed for building and testing the SBI method, and OSG enabled us to generate these large training and testing data sets.

Speaker: Yuanyuan Zhang (NSF NOIRLab)

2026OSG_SBI.pdf

61 OSG Security Status and The Future

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.

Speaker: Mark Krenz (Indiana University)

HTCWeek-2026-presentation-markkrenz-OSG_security_team.pdf

HTCWeek-2026-presentation-markkrenz-OSG_security_team.pptx

62 OrangeGrid Cloud Workers

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 or participating private cloud. The cloud VM joins the cluster as a regular HTCondor execute node, mounts the user's NFS home directory, authenticates with campus LDAP, and runs the job. When the spot instance is reclaimed, another worker takes over. No new tooling for users, no data migration, no second workflow.

This solves a specific problem. Campus compute is finite, demand isn't. Cloud bursting can help with this. The hard part is doing it without breaking the user facing contract around homedirs, UIDs, and job submission.

.

Speaker: Peter Pizzimenti

Pizzimenti_HTC26_Slides.pdf

Pizzimenti_HTC26_Slides.pptx

63 HTC in the Search for Very High Energy Neutrinos with the Trinity Demonstrator

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 neutrino enters Earth, interacts, and a subsequent tau emerges and decays in the lower atmosphere in an air shower, producing Cherenkov light. Cherenkov light is emitted by charged particles travelling faster than light propagates in the surrounding air. The Demonstrator, the first stage of the observatory, is located on Frisco Peak, Utah, and points towards the horizon to pick up this light. Science data began in October 2024, and nightly observations continue. The data collected by the Demonstrator is dominated by the night sky background and requires thorough image cleaning techniques to detect neutrinos. The Demonstrator takes roughly 7 hours' worth of data in 2-minute increments every night, recording events that trigger our camera’s readout. In the data taken from October 2024 through December 2025, we collected 554 hours of data equating to 735 GBs and consisting of 1.2 million events. The storage of data for processing and containers is done through OSDF. In the preparation of data and running the image cleaning, an order of 50,000 HTC jobs is run on OSPool via HTCondor. The benefit of which is clearly seen in the timely and significant rejection of background events. The complete classification of background events prepares Trinity to construct the next phase: Trinity One, the first full-scale Trinity Neutrino Observatory telescope.

Speaker: Lily Sheram (Georgia Institute of Technology)

Sheram_HTC26_Slides.pdf

10:30 AM Break

CHTC Work

64 From Per-Job Data to an Aggregated Workload Insight: A Toolkit for Profiling HTCondor Workload

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 the HTCondor suite, that bridges this gap. Given a single Cluster ID, the toolkit evaluates job status distribution, runtime patterns, hold reasons, and resource utilization, then synthesizes these into a colour-coded health summary that tells researchers and facilitators whether their Cluster is running well, and if not, why. Each analysis transforms thousands of individual job records into a concise, actionable report.

Speaker: Kashika Mahajan (UW-Center for High Throughput Computing)

Kashika Mahajan_ HTC26 Presentation.pdf

Kashika Mahajan_ HTC26 Presentation.pptx

65 The HTCon-Door: Opening Your Compute Cluster to the World

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

Speaker: Cole Bollig (UW-Center for High Throughput Computing)

HTCondor-and-Open-OnDemand.pdf

HTCondor-and-Open-OnDemand.pptx

66 Files Common Across Jobs (Part II)

What to expect in HTCondor 26 from our efforts to improve file-transfer
efficiency.

Speaker: Todd Miller (CHTC)

CommonFileTransfer-HTC26 - v06.pdf

CommonFileTransfer-HTC26 - v06.pptx

67 Authorizing Remote Placement with the PlacementD

Speaker: Matyas Selmeci (UW-Madison CHTC)

PlacementTokens2026.pdf

PlacementTokens2026.pptx

12:30 PM Lunch

Workflows, near and far

68 GlideinWMS Improvements and Challenges

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 discuss opportunities where additional collaboration with the HTCSS community could provide significant benefits.

A redesigned credential framework and new token generators simplify configuration. For example by enabling credentials and authentication options to be selected dynamically based on job ClassAds and target resources. Building on this improved infrastructure, GlideinWMS Frontend now supports automatic generation of self-signed SciTokens, providing a lightweight solution particularly well suited for testing environments and smaller virtual organizations (VOs).

Expanding access to HPC systems remains essential for maximizing available scientific computing capacity. With support and collaboration from the HTCSS community, GlideinWMS is broadening HPC integration through both established mechanisms, such as remote cluster access, and modern REST-based interfaces including SFApi and IRI Facility API. This work aims to reduce operational complexity while enabling more flexible and scalable access to heterogeneous computing resources.

Speakers: Marco Mambelli (Fermilab), Namratha Urs (Fermi National Accelerator Laboratory)

gwms-tc26.pdf

gwms-tc26.pptx

69 Auto-regulating input files that save time when jobs fail

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 proceeded. A failure-and-retry approach led to redundant computation, while simply continuing risked carrying missing or corrupted data forward into later analyses. To address this, I developed submit files that intake dynamically updated file lists, whittling down as outputs are confirmed present. This prevents the pipeline from advancing with incomplete data while also avoiding redundant reprocessing of files that completed successfully. I could also focus instead more on the pipeline itself if that would be preferred. I am available to present in person on 6/10 or 6/11.

Speaker: Benjamin FitzGerald (University of Wisconsin-Madison)

FitzGerald_HTC26_Slides (1).pdf

FitzGerald_HTC26_Slides.pptx

70 Wrangling Massive Task Graphs with VineReduce

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, VineReduce, that allows for the transformation of these programs into an adaptive hierarchy that can effectively harness distributed, heterogeneous HTCondor pools.

Speaker: Douglas Thain (University of Notre Dame)

DougThain_HTC26_Slides (1).pdf

DougThain_HTC26_Slides.pptx

CHTC Fellows Lightning Talks

Daniella Lightning Talk HTC26

Snikitha Lightning Talk HTC26

3:00 PM Break

HTCSS - the Migratory Path: Where We Have Been, and Where We are Going

71 HTCondor Flight Path

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

Speaker: Todd Tannenbaum (University of Wisconsin)

WhatsNew2026_upload.pdf

WhatsNew2026_upload.pptx

72 Todd or Bot Game Show

Speakers: Greg Thain (Center for High Throughput Computing), Todd Tannenbaum (University of Wisconsin)

ToddOrBot.pdf

ToddOrBot.pptx

Closing Remarks

5:00 PM Small Group Dinners

6:00 PM Sunset Kayak or Paddleboard

6:20 PM 80's Tribute Night at the Monona Terrace rooftop featuring the band Sixteen Candles

Todd Tannenbaum is leading a group to this event. PLEASE NOTE YOU MUST RESERVE TICKETS. The event is free. Gates & Cash Bars Open at 5:30. Performance Time: 7:00 - 9:00 PM. Tickets can be reserved online via Eventbrite(https://www.eventbrite.com/e/concerts-on-the-rooftop-sixteen-candles-80s-tribute-tickets-1987934688166) or by calling 608-261-4062. Logistics: Rally at 6:20 at Fluno, leave at 6:25pm. (There is a bus, with minimal walking, which we can catch if we leave Fluno by 6:30pm latest... bus may be best if it is raining).

8:45 PM Karaoke Night

Aaron Moate will lead a group across the street from Fluno's to Mom's Bar, one of the best Karaoke Bar's in the area. If you are joining late from another event, the Bar is right across the street from Fluno at 614 University Ave.

Fri, June 12

8:00 AM Coffee, Pastries, and Registration

AI Facilitation, User Challenges, and best practices. + AI driven Research

73 INK (Interactive aNalysis worKbench) : Progress and AI Exploration (Remote Presentation)

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; (2) a job tracking function providing real-time monitoring for HTCondor jobs; and (3) a one-click deployment pipeline.
We also share early exploration of AI-enhanced operations.

Speaker: Jingyan Shi (INSTITUTE OF HIGH ENERGY PHYSICS, Chinese Academy of Science)

HTC26_final.pdf

74 Climate Policy Modeling with HTCondor

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.

Speaker: Ken Judd (Stanford University)

Climate Policy Modeling with HTCondor.pdf

75 Where's the Big Data for Protein Dynamics?

Speaker: Hannah Wayment-Steele (UW-Madison)

76 YOL-No: Guiding Agent Usage on the Access point

Speaker: Ian Ross (U. Wisconsin)

Ross_Friday_HTC26_Slides.pdf

Ross_Friday_HTC26_Slides.pptx

10:30 AM Break

Is AI for The Birds? Using AI tools to understand and debug HTCondor and Pelican

77 Analyzing and Optimizing Machine Timeout Duration Using AI (Remote Presentation)

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? This talk explores how we can dynamically predict an optimal timeout duration by training a simple ML model!

Speaker: Khyathi Vagolu (UW-Madison)

Vagolu_HTC26_Slides 2.pdf

Vagolu_HTC26_Slides 2.pptx

78 MCP for HTCondor Admins

Speaker: Ilija Vukotic (University of Chicago)

MCP for HTCondor admins

79 HTCondor operational improvement efforts @ BNL

Speaker: Tom Smith (Brookhaven National Laboratory)

tsmith_BNL_HTC26_presentation.pdf

Closing Remarks

12:30 PM Lunch

No Session