26th Annual Workshop & Retreat
October 29 - 31, 2018

INFO & Agenda

Retreat Agenda


Monday, October 29: CMU/Bedford Springs Resort
8:30 am - 9:00 am Registration & Continental Breakfast
-- SINGLETON ROOM, ROBERTS HALL
9:00 am - 9:30 am Welcome -- SINGLETON ROOM

Greg Ganger - Parallel Data Lab 2018 Retreat Welcome & Overview

9:30 am - 10:30 am Speaker -- SINGLETON ROOM

Anthony Rowe – The Next Frontier of IoT: Giving the Cloud an Edge

10:30 am - 11:30 am Industry Poster Session -- ROBERTS HALL ATRIUM
11:30 am - 1:45 pm Bus Ride to Bedford Springs & Lunch -- FREW STREET
2:00 pm - 4:00 pm Session I: Starting Strong!
-- COLONNADE BALLROOM

Huanchen Zhang - SuRF: Practical Range Query Filtering with Fast Succinct Tries

Saurabh Kadekodi - Gotta have HeART: Exploiting Disk Reliability Heterogeneity in Cluster Storage Systems

Charlie McGuffey - Writeback Aware Caching

Lin Ma - Self-Driving Database Progress

4:00 pm - 4:15 pm Break -- CONSTITUTION HALL
4:15 pm - 6:15 pm Session II: Pipes and Clouds
-- COLONNADE BALLROOM

Aaron Harlap - PipeDream: Pipeline Parallelism for DNN Training

Anuj Kalia - Datacenter RPCs can be General and Fast

Andrew Chung - Stratus: Cost-aware container scheduling in the public cloud

6:15 pm - 7:15 pm Dinner -- EISENHOWER BALLROOM
7:15 pm - 8:30 pm Session III: Short Work-in-Progress Talks
-- COLONNADE BALLROOM

Dominic Chen - TardisTM: Time-Traveling Transaction Repair

Chris Canel & Thomas Kim - Scaling Video Analytics on Constrained Edge Nodes

Giulio Zhou - Finding Objects in Video with Minimal Supervision

Angela Jiang - Faster DNN Training with Selective Backpropagation

Daniel Wong - Evolutionary Weight Sharing For Neural Architecture Search

8:30 pm - 10:30 pm Reception/Poster Session I -- COLONNADE BALLROOM

Tuesday, October 30: Bedford Springs Resort

8:15 am - 9:00 am Full Breakfast -- CRYSTAL DINING ROOM
Continental Breakfast
-- CONSTITUTION HALL
9:00 am - 10:30 am Session IV: Efficiency and Scale in the Morning
-- COLONNADE BALLROOM

Prashanth Menon - Next Generation Execution Engine for the Database Formerly Known as Peloton

Qing Zheng - Scaling DeltaFS Indexed Massive Directories to 131,072 CPU Cores

10:30 am - 10:45 am Break -- CONSTITUTION HALL
10:45 am - 12:15 pm Session V: Serving Video Queries and ML Models
-- COLONNADE BALLROOM

Jack Kosaian - Resilient ML Inference via Erasure Coding

Kevin Hsieh - Querying Large Video Datasets with Low Latency and Low Cost

12:15 pm - 1:15 pm Lunch -- EISENHOWER BALLROOM
1:15 pm - 2:30 pm Socializing and Chat-filled Walk -- HOTEL GROUNDS
Wii games room available 1:00 pm to midnight --
REAGAN-B
2:30 pm - 4:00 pm Session VI: Cluster Workloads and Scheduling
-- COLONNADE BALLROOM

Junwoo Park - Distribution-based Cluster Scheduling for Uncertainty

Michael Kuchnik - Rethinking the Use of Machine Learning in Job Scheduling

Andrew Chung - Owl: Data-driven Job Utility Functions

4:00 pm - 4:15 pm Break -- CONSTITUTION HALL
4:15 pm - 6:15 pm Session VII: Memory Enhancement
-- COLONNADE BALLROOM

Rajat Kateja - NVM Storage Needs Lazy Redundancy

Nandita Vijaykumar - Expressive Memory Rethinking the Hardware-Software Contract with Rich Cross-Layer Abstractions

Charlie McGuffey - The Parallel Persistent Memory Model

6:15 pm - 7:30 pm Dinner -- EISENHOWER BALLROOM
7:30 pm - 8:30 pm Session VIII: Short Work-In-Progress Talks
-- COLONNADE BALLROOM

Qing Zheng - Future Directions for Exascale Storage with DeltaFS

Saksham Jain - Building DeltaFS Support in Scientific Libraries

Ellango Jothimurugesan - Stochastic Gradient Descent on Streaming Data

Sol Boucher - Lightweight Preemptible Functions

8:30 pm - 10:00 pm Reception/Poster Session II -- COLONNADE BALLROOM

Wednesday, October 31: Bedford Springs Resort
Morning Workshop Talks
8:45am - 9:15am Full Breakfast -- CRYSTAL DINING ROOM
Continental Breakfast
-- CONSTITUTION HALL
9:15am - 11:30am Session IX: Close Strong!
-- COLONNADE BALLROOM

Daniel Berger - RobinHood: Tail Latency Aware Caching

Jinliang Wei - Automating Dependence-aware Parallelization of Machine Learning Training on Distributed Shared Memory

Chris Fallin & Pratik Fegade - Data-Structure-Aware Program Analysis for Macro-scale Optimizations

Afternoon Feedback, Departure
11:30am - 1:15pm Lunch and Industry Feedback
1:30pm Buses depart for Pittsburgh Airport & CMU (one in each direction)
4:00pm Arrive at Airport
4:00pm
Arrive at CMU

Contacts:



    PDL Administrative Manager
    School of Computer Science
    Carnegie Mellon University
    4720 Forbes Avenue - CIC 2209
    PITTSBURGH, PA 15213-3891
    VOICE: (412)268-6716
    FAX: (412)268-3010


    Director, Parallel Data Laboratory
    Electrical and Computer Engineering
    Carnegie Mellon University
    4720 Forbes Avenue - CIC 2208
    PITTSBURGH, PA 15213-3891
    VOICE: (412)268-1297
    FAX: (412)268-6779


    PDL Executive Director
    Carnegie Mellon University
    4720 Forbes Avenue - CIC 2210
    PITTSBURGH, PA 15213-3891
    VOICE: (412) 268-5485
    FAX: (412)268-3010