Volunteer Computing: Planting the Flag David P' Anderson Space Sciences Lab U'C' Berkeley March 30,

1
Volunteer ComputingPlanting the FlagDavid P.
AndersonSpace Sciences LabU.C. BerkeleyMarch
30, 2007
2
Outline

• What is volunteer computing?
• History and current status
• Some research directions
• Non-technical problems

3
What is Volunteer computing?
Volunteers
Projects
Internet

• Helps science
• Involves public in science

4
Early history

• GIMPS (1996)
• George Woltman, Scott Kurowski
• distributed.net (1997)
• Adam Beberg, Jim Lawson, ...
• SETI_at_home (1999)
• me, Eric Korpela
• Folding_at_Home (2000)
• Vijay Pande

5
Academic projects, 1996-99

• Bayanihan
• L. Sarmenta, MIT
• fault-tolerance in presence of hackers
• volunteer computing
• Popcorn
• Noam Nisan, Hebrew Univ.
• Market-based approach
• Superweb
• Charlotte
• Jet

The problem Java
6
Business attempts

• Entropia (1998)
• Popular Power
• United Devices (2000)
• Parabon
• Data Synapse

The problem no customers
7
BOINC (2002)

• Middleware for volunteer computing
• Open-source (LGPL)
• Application-driven
• Goals
• lots of independent projects
• support for diverse applications
• client participation in multiple projects

8
Volunteer computing ! Grid computing
Resource owners
identified, accountable
anonymous, unaccountable
Managed systems?
yes software stack requirements OK
no need plug play software
Clients behind firewall?
no push model
yes pull model
ISP bill?
no
yes
... nor is it peer-to-peer computing
9
Some BOINC-based projects

• Climateprediction.net
• Oxford climate change study
• Einstein_at_home
• LIGO gravitational wave astronomy
• Rosetta_at_home
• U. Washington protein study
• SETI_at_home
• U.C. Berkeley SETI
• LHC_at_home
• CERN accelerator simulation
• Africa_at_home
• STI, U. of Geneva malaria epidemiology
• IBM World Community Grid
• several biomedical applications
• ...and about 30 others

10
Computing power

• Folding_at_home
• 650 TeraFLOPS
• 200 from PCs 50 from GPUs 400 from PS3!
• BOINC-based projects

11
A sampling of research problems

• Data-intensive computing
• Low-latency computing
• Background utility compatibility
• Credit mechanism
• Efficient validation
• Game consoles and graphics chips
• Simulation

12
Data-intensive computing client limits

• Q network transfer per GFLOPS/hr
• SETI_at_home Q 0.1 MB
• but wider range is OK

13
Server-side limits
Internet


Client
Server
14
Using free networks
Server

commodity Internet
Internet2
Server


Server

Client
15
Using more free networks

Server
commodity Internet
Internet2

Server

Server

LAN
Client
Client
Client
16
Low-latency computing
job submission
deadline
2 min
4 min
time

• VC usually minimizes connection frequency
• What if you want to do 10,000 1-minute jobs in 6
  minutes of wall time?

17
Background utility compatibility

• Background utilities
• disk defrag
• disk indexing
• virus scanning
• web pre-fetch
• disk backup
• Most run only when computer is idle
• volunteer computing gt they never run
• A) ignore zero-priority CPU activity
• B) Background manager
• intelligent decision about when to run various
  activities

18
Credit mechanism

• Credit is important
• Currently based on FLOPS
• Should reflect, e.g. RAM size?
• Goal maximize utility to projects
• Project-specific pricing schedules?
• Credit for other resources
• disk usage
• network transfers

19
Efficient validation

• Job output
• results
• claimed credit
• Replicated computing
• do job N times, require quorum of M
• Dealing with numerical discrepancies
• homogeneous replication
• eliminate discrepancies
• no replication
• How to validate provably and efficiently?

20
Game consoles and graphics chips

• NVIDIA, ATI, Cell
• 10X CPU and gaining?
• Folding_at_home
• ATI version
• Sony PS3 version
• BOINC and Einstein_at_home on PS3
• How to make this available to other projects?

21
Simulating volunteer computing

• Ad-hoc development of scheduling policies
• slow, noisy
• jeopardizes running projects
• Simulation-based RD
• client simulator
• client scheduling policies
• Project simulator
• server scheduling policies
• Global simulator
• study data-intensive, low-latency, etc.

22
The hard non-technical problems

• How to increase the number of volunteers?
• currently 1 in 1000 PC owners
• How to increase the number of projects?
• currently stuck at about 50
• How to get volunteers to diversify?

23
How to attract and retain volunteers?
Active hosts

• Retention
• reminder emails
• frequent science updates
• Recruitment
• Viral
• email a friend, referral reward
• Organizational
• World Community Grid partner program
• Media coverage
• need more discoveries
• Bundling

24
Why arent there more projects?

• Lack of PR among scientists
• IT antipathy
• Creating a BOINC project is expensive

Research group
Science App development Experiment design Paper
writing
Software/IT Port/debug apps workflow
tools server admin
Communications Web site development message
board admin public relations
25
Meta-projects

• Virtual Campus Supercomputing Center
• Deployment and publicity
• PC labs, staff/faculty desktops
• students
• alumni
• public

Berkeley_at_home
Existing UCB staff
Research groups


Science App development Experiment design Paper
writing
Software/IT Port/debug apps workflow
tools server admin
Communications Web site development message
board admin public relations

• IBM World Community Grid

26
Encouraging change

• Cross-project credit system
• encourage competition in total credit, not
  per-project
• Account Managers
• Make it easier to discover/attach/detach
  projects
• GridRepublic, BAM!
• Science Stock Market?
• encourage participation in new high-potential
  projects
• Scientific Mutual Funds?
• e.g. American Cancer Society BOINC portfolio

27
Conclusion

• Volunteer computing a new paradigm
• distinct research problems, software requirements
• big accomplishments, potential
• time to plant the flag!
• Social impacts
• Contact me about
• Using BOINC
• Research based on BOINC
• Organizational use of BOINC

davea_at_ssl.berkeley.edu