30th Annual Workshop & Retreat
October 14 - 16, 2024
INFO & Agenda
We are pleased to welcome our PDL Consortium Member Companies to the 30th Annual Parallel Data Lab Workshop and Retreat.
Please keep the dates in October open! More information on location, registration, etc. will be added here soon!
GENERAL INFORMATION
SECURE ONLINE REGISTRATION FORM FOR INDUSTRY VISITORS
SECURE ONLINE REGISTRATION FORM FOR CMU ATTENDEES
2024 RETREAT RESOURCES - Event talks, posters, and papers
OUR NEWSLETTER
RETREAT AGENDA
| Monday, October 14, 2024: Omni Bedford Springs Resort | |
| 8:30 am - 9:15 am | Registration & Continental Breakfast |
| 9:15 am - 10:00 am | Welcome
Greg Ganger - Parallel Data Lab 2024 Retreat Welcome & Overview |
| 10:00 am - 10:40 am | Morning Talk
Andy Pavlo - The Next Chapter in the Sordid Love/Hate Relationship Between Databases and Operating Systems |
| 10:40 am - 12:00 pm | Industry Poster Session |
| 12:00 pm - 1:15 pm | Lunch |
| 1:15 pm - 3:30 pm | Session I: Orchestrating Data Access Sara McAllister - Scaling the bandwidth-per-TB wall with Declarative Storage Interfaces Wan Shen Lim - Accelerating Machine Learning for Database Systems Hojin Park - Reducing Cross-Cloud/Region Costs with the Auto-Configuring MACARON Cache |
| 3:30 pm - 4:00 pm | Break |
| 4:00 pm - 6:00 pm | Session II: Optimizing in Big Systems Jaylen Wang - Designing Cloud Servers for Lower Carbon Tim Kim - Morph: Efficient File Lifetime Redundancy Management Kaiyang Zhao - Multi-Tenant Memory Tiering on CXL Memory Val Choung - Compiler-assisted Memory Allocation |
| 6:00 pm - 7:30 pm | Dinner |
| 7:30 pm - 8:30 pm | Session III: Short Work-in-Progress Talks + Poster Previews Sara McAllister - A Call for Research on Storage Emissions Sophia Cao - Possum: A Tail of Dynamic Flash Capacity for Sustainability Deepanjali Mishra - Optimizing Key Instruction Sequences in Data Center Processors |
| 8:30 pm - 10:30 pm | Reception/Poster Session I |
| Tuesday, October 15, 2024: Omni Bedford Springs Resort | |
| 8:30 am - 9:15 am | Breakfast |
| 9:15 am - 10:45 am | Session IV: Exploiting Hardware Resources Effectively Jignesh Patel - Data Analytics in a Disaggregated World NJ Mukherjee - Transparent Block-Level Near-Data Computation |
| 10:45 am - 11:00 am | Break |
| 11:00 am - 12:30 pm | Session V: Partitioning Data and Work Ziyue Qiu - Moirai: Optimizing Placement of Data and Compute in Hybrid Clouds Yiwei Zhao - Fast and Principled Techniques for Heterogeneous Compute and Memory |
| 12:30 pm - 1:30 pm | Lunch |
| 1:30 pm - 2:45 pm | Social activities or personal time |
| 2:45 pm - 4:15 pm | Session VI: Database Tuning Sam Arch - The Key to Effective UDF Optimization: Before Inlining, First Perform Outlining William Zhang - Holons: Holistic Tuning in a Self-Driving DBMS |
| 4:15 pm - 4:30 pm | Break |
| 4:30 pm - 6:00 pm | Session VII: Optimizating at Scale Ankush Jain - Telemetry-Guided Placement in Adaptive Parallel Codes Suhas Jayaram Subramanya - Efficient Resource Scheduling at Scale via Continuous Optimization |
| 6:00 pm - 7:30 pm | Dinner |
| 7:30 pm - 8:15 pm | Session VIII: Short Work-In-Progress Talks Ankush Jain - NetSketch: Enabling Rapid Feedback for Parallel Apps Sara Mahdizadeh Shahri - Studying Demographic Bias in Web Scheduling Systems Hyoungjoo Kim - OLTPIM: An Efficient Transactional Database using Processing-in-Memory Siyuan Chen - Towards Compound LLM As-a-Service: Enhancing the Security of LLM “Apps" |
| 8:15 pm - 10:00 pm | Reception/Poster Session II |
| Wednesday, October 16, 2024: Omni Bedford Springs Resort | |
| 8:45 am - 9:30 am | Breakfast |
| 9:30 am - 11:45 am | Session IX: Close Strong! Sanjith Athlur - Okapi: Decoupling Data Stripes and Redundancy Groups Daiyaan Arfeen - PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training Yixuan Mei - Helix: Serving LLMs over Heterogeneous GPUs and Network via Max-Flow |
| Lunch | Grab lunch and sit in meeting room |
| 11:45 am - 1:00 pm | Lunch and Industry Feedback Session |
| 1:00 pm | Informal Interactions and End of Event |
| 1:30 pm | Bus to CMU |
RETREAT Accommodations - OMNI BEDFORD SPRINGS
The entire PDL Retreat will occur at the Omni Bedford Springs Resort in Bedford Springs, PA, beginning the morning of October 14 and concluding the afternoon of October 16. Attendees are responsible for reserving their own hotel rooms at the retreat venue, and should do so no later than September 13 by 5 pm to ensure availability and pricing. Most guests should book a room for a October 13 arrival and October 16 departure. To make your reservations, contact the Omni Bedford springs using this link or call +1-877-409-6664, and reference the group's name CMU PDL Retreat (IPO Rooms) and event dates to access the special rate for the room block.
Directions
The Omni Bedford Springs resort is located in the Allegheny Mountains of Pennsylvania, just outside of the historic town of Bedford Springs. The hotel's physical address is 2138 Business 220, Bedford, Pennsylvania, 15522 (map to the property).
You may decide, based on scheduling and available flights that flying into an airport other than Pittsburgh International suits your plans better. Here is an overview map of directions and driving times from the five airports nearest to the Bedford Springs Resort.
Transportation AND Parking
Retreat attendees should plan on being present at the Omni Bedford Springs for an 8:30am start on Monday, October 14.
There are several options available for getting to and from the Omni Bedford Springs and the airport. Please make your own transportation arrangements from the airport to the Omni Bedford Springs hotel.
If you are renting a car and driving from a regional airport, you can either self park at the Omni, or use their complimentary valet parking service.
Car Services
Rental Car available at the airport from all the major companies.
Airport Sedan Service (Larry
Waite)
Advance reservations are required
Contact Larry Waite, 412-401-LIMO
(5466)
Gateway Limo
The rate for a van, a 14 passenger vehicle, is $78.00 per hour. Mention CMU when making a reservation.
Call the office at 412-782-5800 or 1-800-390-1222 (phones answered 24/7) for reservations.
Email: amydemeri@comcast.net
Harper's Transportation
Harper1084@verizon.net - 412-531-1940
Uber Pittsburgh
PITTSBURGH ACCOMMODATIONS
If you plan on extending your stay and visiting Pittsburgh before or after the retreat, the following hotels are located near CMU. Please feel free to contact any of these hotels and ask for the CMU rate, though your corporate rate may be better.
| Hilton Garden Inn - University Place 3454 Forbes Avenue Pittsburgh, Pennsylvania 15213 Phone: (412) 683-2040 FAX: (412) 688-1986 Rates on inquiry, parking extra |
Hampton
Inn - University Center 3315 Hamlet Street Pittsburgh PA 15213 Phone: 412-681-1000 FAX: 412-681-3022 Rates on inquiry, parking extra |
| Courtyard by Marriott - University Center 100 Lytton Avenue Pittsburgh PA 15213 Phone: 412-682-6200 FAX: 412-682-5745 Rates on inquiry, parking extra Mention: CMU Visitor |
Residence Inn by Marriott - Oakland/ University Place 3341 Forbes Avenue Pittsburgh, PA 15213 Phone: 412-621-5600 Rates on inquiry, parking extra Mention: CMU Visitor |
CONTACTS:
Director, Parallel Data Lab
Executive Director, Parallel Data Lab
PDL Administrative Manager
VOICE: (412) 268-6716