Internet-Based TSP Computation with Javelin Michael Neary

1
Internet-Based TSP Computation with Javelin
Michael Neary Peter CappelloComputer Science,
UCSB
2
IntroductionGoals

• Service parallel applications that are
• Large too big for a cluster
• Coarse-grain to hide communication latency
• Simplicity of use
• Design focus decomposition composition of
  computation.
• Scalable high performance
• despite large communication latency
• Fault-tolerance
• 1000s of hosts, each dynamically disassociates.

3
IntroductionSome Related Work
4
IntroductionSome Applications

• Search for extra-terrestrial life
• Computer-generated animation
• Computer modeling of drugs for
• Influenza
• Cancer
• Reducing chemotherapys side-effects
• Financial modeling
• Storing nuclear waste

5
Outline

• Architecture
• Model of Computation
• API
• Scalable Computation
• Experimental Results
• Conclusions Future Work

6
Architecture Basic Components
Clients
Brokers
Hosts
7
Architecture Broker Discovery
B
B
B
Broker Naming System
B
B
B
H
B
B
B
8
Architecture Broker Discovery
B
B
B
Broker Naming System
B
B
B
H
B
B
B
9
Architecture Broker Discovery
B
B
B
Broker Naming System
B
B
B
H
B
B
B
10
Architecture Broker Discovery
B
B
B
Broker Naming System
B
B
B
H
B
B
B
PING (BID?)
11
Architecture Broker Discovery
B
B
B
Broker Naming System
B
B
B
H
B
B
B
12
ArchitectureNetwork of Broker-Managed Host Trees

• Each broker manages a tree of hosts

13
ArchitectureNetwork of Broker-Managed Host Trees

• Brokers form a network

14
ArchitectureNetwork of Broker-Managed Host Trees

• Brokers form a network
• Client contacts broker

15
ArchitectureNetwork of Broker-Managed Host Trees

• Brokers form a network
• Client contacts broker
• Client gets host trees

16
Scalable ComputationDeterministic Work-Stealing
Scheduler
addTask( task )
getTask( )
Task container
stealTask( )
HOST
17
Scalable ComputationDeterministic Work-Stealing
Scheduler

• Task getWork( )
• if ( my deque has a task )
• return task
• else if ( any child has a task )
• return childs task
• else
• return parent.getWork( )

CLIENT
HOSTS
18
Models of Computation

• Master-slave
• AFAIK all proposed commercial applications
• Branch--bound optimization
• A generalization of master-slave.

19
Models of ComputationBranch Bound
UPPER ? LOWER 0
0
20
Models of ComputationBranch Bound
UPPER ? LOWER 2
0
2
21
Models of ComputationBranch Bound
UPPER ? LOWER 3
0
2
3
22
Models of ComputationBranch Bound
UPPER 4 LOWER 4
0
2
3
4
23
Models of ComputationBranch Bound
UPPER 3 LOWER 3
0
2
3
3
4
24
Models of ComputationBranch Bound
UPPER 3 LOWER 6
0
2
3
6
3
4
25
Models of ComputationBranch Bound
UPPER 3 LOWER 7
26
Models of ComputationBranch Bound

• Tasks created dynamically
• Upper bound is shared
• To detect termination scheduler detects tasks
  that have been
• Completed
• Killed (bounded)

27
API

• public class Host implements Runnable
• . . .
• public void run()
• while ( (node jDM.getWork()) ! null )
• if ( isAtomic() )
• compute() // search space return result
• else
• child node.branch() // put children in
  child array
• for (int i 0 i lt node.numChildren
  i)
• if ( childi.setLowerBound() lt
  UpperBound )
• jDM.addWork( childi )
• //else child is killed implicitly

28
API

• private void compute()
• . . .
• boolean newBest false
• while ( (node stack.pop()) ! null )
• if ( node.isComplete() )
• if ( node.getCost() lt UpperBound )
• newBest true
• UpperBound node.getCost()
• jDM.propagateValue( UpperBound )
• best Node( childi )
• else
• child node.branch()
• for (int i 0 i lt node.numChildren
  i)
• if ( childi.setLowerBound() lt
  UpperBound )
• stack.push( childi )
• //else child is killed implicitly

29
Scalable ComputationWeak Shared Memory Model

• Slow propagation of bound affects performance not
  correctness.

Propagate bound
30
Scalable ComputationWeak Shared Memory Model

• Slow propagation of bound affects performance not
  correctness.

Propagate bound
31
Scalable ComputationWeak Shared Memory Model

• Slow propagation of bound affects performance not
  correctness.

Propagate bound
32
Scalable ComputationWeak Shared Memory Model

• Slow propagation of bound affects performance not
  correctness.

Propagate bound
33
Scalable ComputationWeak Shared Memory Model

• Slow propagation of bound affects performance not
  correctness.

Propagate bound
34
Scalable ComputationFault Tolerance via Eager
Scheduling

• When
• All tasks have been assigned
• Some results have not been reported
• A host wants a new task
• Re-assign a task!
• Eager scheduling tolerates faults balances the
  load.
• Computation completes, if at least 1 host
  communicates with client.

35
Scalable ComputationFault Tolerance via Eager
Scheduling

• Scheduler must know which
• Tasks have completed
• Nodes have been killed
• Performance ? balance
• Centralized schedule info
• Decentralized computation

36
Experimental Results
37
Experimental Results
Example of a bad graph
38
Conclusions

• Javelin 2 relieves designer/programmer managing a
  set of Inter- networked processors that is
• Dynamic
• Faulty
• A wide set of applications is covered by
• Master-slave model
• Branch bound model
• Weak shared memory performs well.
• Use multicast (?) for
• Code distribution
• Propagating values

39
Future Work

• Improve support for long-lived computation
• Do not require that the client run continuously.
• A dag model of computation
• with limited weak shared memory.

40
Future WorkJini/JavaSpaces Technology
Continuously disperse Tasks among brokers via
a physics model
H
H
H
TaskManager aka Broker
H
H
H
H
H
41
Future WorkJini/JavaSpaces Technology

• TaskManager uses persistent JavaSpace
• Host management trivial
• Eager scheduling simple
• No single point of failure
• Fat tree topology

42
Future WorkAdvanced Issues

• Privacy of data algorithm
• Algorithms
• New computational complexity model
• Minimize communication between machines
• N-body problem,
• Accounting Associate specific work with specific
  host
• Correctness
• Compensation (how to quantify?)
• Create international open source organization
• System infrastructure
• Application codes

43
(No Transcript)
44
Models of ComputationBranch Bound
UPPER 3 LOWER 0
45
ArchitectureBroker Name Service (BNS)
BNS
1. Register with BNS
BROKER
HOST
46
ArchitectureBroker Name Service (BNS)
BNS
1. Register with BNS
BROKER
2. Get broker list
HOST
47
ArchitectureBroker Name Service (BNS)
BNS
1. Register with BNS
BROKER
2. Get broker list
HOST
3. Ping brokers on list
48
ArchitectureBroker Name Service (BNS)
BNS
1. Register with BNS
BROKER
2. Get broker list
4. Connect to selected broker
HOST
3. Ping brokers on list