Conference Program

Preconference activities (workshops, tutorials, & the doctoral symposium) will be held Dec. 7 and 8.
The main conference will be held Dec. 9-11.

  • Dec. 7
  • Dec. 8
  • Dec. 9
  • Dec. 10
  • Dec. 11

Monday, December 7

Preconference Activities

9:00 – 10:00  Session 1: Talk introducing the remote GPU virtualization technique and frameworks

10:00 – 10:30  Break

10:30 – 12:00  Session 2: Talk on advanced features of remote GPU virtualization (40 minutes) Practical demonstration about how to install and use rCUDA (50 minutes)

12:00 – 13:30  Lunch

13:30 – 15:00  Session 3: Guided exercises for the audience using rCUDA in a remote cluster

15:00 – 15:30  Break

15:30 – 17:30  Session 4: Time for attendees to freely exercise with rCUDA in the remote cluster (a set of exercises is proposed)

Tuesday, December 8

Preconference Activities

  • Full-day workshop: Workshop on Middleware for Context-Aware Applications in the IoT (M4IOT ’15) (Room: Shaughnessy I, 3rd floor)
  • Full-day workshop: Workshop on Adaptive and Reflective Middleware (ARM ’15) (Room: Shaughnessy II, 3rd floor)
  • Full day: Doctoral Symposium (Room: Ambleside I, 4th floor)
  • Half-day Tutorial (starts at 1:30 p.m.): Building and managing business resiliency on the cloud (Room: Point Grey, 3rd floor)

Wednesday, December 9

8:00 a.m.Registration
8:30 a.m.Opening Remarks
9:00 a.m.Keynote Talk: Micro Datacenter Middleware for Mobile Computing, Victor Bahl, Microsoft Research
10:00 a.m.Coffee Break
10:30 a.m.Session 1: Coordinating Publish/Subscribe

Session Chair: Peter Triantafillou

  • Graps: A Graph Publish/Subscribe Middleware
  • MERC: Match at Edge and Route intra–Cluster for Content-based Publish/Subscribe Systems
  • Efficient Key Updates through Subscription Re-encryption for Privacy-Preserving Publish/Subscribe
  • Design of Routing Protocols and Overlay Topologies for Topic-based Publish/Subscribe on Small-World Networks
12:10 p.m.Lunch
1:30 p.m.Session 2: Managing Memory

Session Chair: Bettina Kemma

  • Quartz: A Lightweight Performance Emulator for Persistent Memory Software
  • Pannier: A Container-based Flash Cache for Compound Objects
  • Enabling Cost-Effective Flash based Caching with an Array of Commodity SSDs
  • DynaCorrect: Dynamically Correcting Cache for Non-cooperative Systems
3:10 p.m.Coffee Break
3:40 p.m.Session 3: Improving Consistency

Session Chair: Binoy Ravindran

  • Write Fast, Read in the Past: Causal Consistency for Client-side Applications
  • Q-OPT: Self-tuning Quorum System for Strongly Consistent Software Defined Storage
  • EpTO: an Epidemic Total Order Algorithm for Large-Scale Distributed Systems
  • Asynchronous Complete Garbage Collection for Graph Data Stores
5:20 p.m.Posters and Demos with Reception Until 7:30 p.m.

Thursday, December 10

8:00 a.m.Registration
9:00 a.m.Keynote Talk: Social Network Data Distillation Services for Urban Spaces Tarek Abdelzaher, University of Illinois
10:00 a.m.Coffee Break
10:30 a.m.Session 4: Managing Resources Efficiently

Session Chair: Luís Veiga

  • vRead: Efficient Data Access for Hadoop in Virtualized Clouds
  • UniDrive: Synergize Multiple Consumer Cloud Storage Services
  • R-Storm - Resource Aware Scheduling in Storm
  • Apex Lake: A Framework for Enabling Smart Orchestration
12:10 p.m.Lunch
1:30 p.m.Session 5: Conquering Parallelism

Session Chair: Sonia Ben Mokhtar

  • Parallel Programming in Actor-Based Applications via OpenCL
  • Consensus-Oriented Parallelization: How to Earn Your First Million
  • Turtle Consensus: Moving Target Defense for Consensus
  • Local and Remote GPUs Perform Similar with EDR 100G InfiniBand
3:10 p.m.Coffee Break
3:40 p.m.Session 6: Checkpointing Resources

Session Chair: Aniruddha Gokhale

  • Speculative Memory Checkpointing
  • VeCycle: Recycling VM Checkpoints for Faster Migration
  • Improving Preemptive Scheduling with Application-Transparent Checkpointing in Shared Clusters
4:55 p.m.Middleware Business Meeting Until 5:30 p.m.
6:30 p.m.Conference Banquet Until 9:00 p.m.

Friday, December 11

9:00 a.m.Session 7: Increasing Efficiency

Session Chair: Davide Frey

  • Configuring Distributed Computations Using Response Surfaces
  • Scaling Out Link Prediction with SNAPLE:1 Billion Edges and Beyond
  • Managing the Energy-Delay Tradeoff in Mobile Applications with Tempus
  • Zero-Cost, Fine-Grained Power Monitoring of Datacenters Using Non-Intrusive Power Disaggregation
10:40 a.m.Coffee Break
11:10 a.m.Test-of-Time Award and Talk
11:50 a.m.Closing Remarks
12:15 p.m.Lunch
1:30 p.m.End of Middleware 2015