LDMSCON2023 attendees will enjoy:

• Tutorials on LDMS related topics:

  • Basic LDMS Configuration 

  • Deployment of LDMS Monitoring System Using Containers 

  • LDMS Monitoring Infrastructure Load Balancing and Configuration with Maestro 

  • Analysis and Visualization for System and Application Improvement

  • LDMS Metric Set Decomposition for Storage 

  • Provisioning the LDMS Monitoring Infrastructure on Large-scale Systems 

  • Distributing LDMS Metric Data Using Avro on the Kafka Bus 

• Developer and User networking

• LDMS release and feature development roadmap

• User and developer presentations

Schedule is in US Eastern Time Zone (Boston, MA)

AGENDA

Tuesday, June 13, 2023 – Day 1:

7:30 - 8:00am

• Light breakfast – Baked goods, fruits, and coffee 

8:00 - 8:30am 

• Check-In (please have your e-ticket with you for check-in)

8:30 - 9:30 am 

• Welcome/Keynote

9:30 - 10:00 am 

• Lightning Talk: ANL Site Status -- Ben Lenard

• Lightning Talk: NCSA Site Status -- Mike Showerman

10:00 -10:30 am 

• Break

10:30 am - 12:00 pm

• User Presentation: Kokkos Tools Sampler for Data Order Reduction in HPC Systems Monitoring -- Vivek Kale, Vanessa Surjadidjaja, Christian Trott and Jim Brandt

• User Presentation: Using Darshan-LDMS for Analyzing and Diagnosing I/O Performance in HPC Systems -- Ana Solorzano, Sara Walton, Ben Schwaller, Jim Brandt, Devesh Tiwari and Rhan Basu Roy

• Lightning Talk: Process Event Monitoring and Application Identification with LDMS -- Ben Allan

12:00 - 1:00 pm

• Lunch

1:00 - 2:30 pm

• Tutorial: Basic LDMS Configuration -- Sara Walton

2:30 - 3:00 pm

• Break

3:00 - 4:30 pm

• Tutorial: LDMS Monitoring Infrastructure Load Balancing and Configuration with Maestro -- Nick Tucker

4:30 - 5:00 pm

• End-of-Day Group Discussions

Wednesday, June 14, 2023 – Day 2:

7:30 - 8:30am

• Light breakfast – Baked goods, fruits, and coffee 

8:30 - 10:00 am

• Demo: Analysis and Visualization for System and Application Improvement -- Ben Schwaller

10:00 - 10:30 am

• Break

10:30 - 12:00 am

• Tutorial: Deployment of LDMS Monitoring System Using Containers -- Narate Taerat

12:00 am - 1:00 pm

• Lunch

1:00 - 2:30 pm

• User Presentation: Towards Performance Anomaly Diagnosis in Production HPC Systems using Machine Learning -- Burak Aksar, Efe Sencan, Ben Schwaller, Vitus Leung, Jim Brandt, Brian Kulis, Manuel Egele and Ayse Coskun

• User Presentation: Lessons from Monitoring AI-workload Driven Supercomputers -- Devesh Tiwari

• User Presentation: Dynamic Time Warping (DTW) and HPC Monitoring Data Clustering and Anomaly Detection -- Ben Schwaller, Solji Shin and Mueen Abdullah

2:30 - 3:00 pm

• Break

3:00 - 4:00 pm

• Tutorial: Provisioning the LDMS Monitoring Infrastructure on Large-scale Systems -- Jim Brandt

4:00 - 4:30pm

• LDMS-UG Introduction -- Jim Brandt

4:30 - 5:00 pm

• End-of-Day Group Discussions

Thursday, June 15, 2023 – Day 3:

7:30 - 8:00am

• Light breakfast – Baked goods, fruits, and coffee 

8:00 - 8:30am

• Lightning talk: LRZ's HPC Monitoring -- Michael Ott

8:30 - 10:00am

• Tutorial: LDMS Metric Set Recomposition for Storage -- Nichamon Naksinehaboon

10:00 - 10:30 am

• Break

10:30 - 11:00 am

• User Presentation: LLNL Site Update -- Christ Morrone

11:00 - 12:00pm

• Demo: Distributing LDMS Metric Data Using Avro on the Kafka Bus -- Tom Tucker

12: 00 - 1:00 pm

• Lunch

1:00 - 2:30 pm

• Round-Table Development Discussions

2:30 - 3:00 pm

• Break

3:00 - 5:00 pm

• Open Interaction & Troubleshooting/Discussion Sessions/Breakouts