Adaptive Multiprocessor Realtime Systems

1
Adaptive Multiprocessor Real-time Systems

• Jim Anderson
• Sanjoy Baruah
• in collaboration with
• Gary Bishop

2
Real-time Adaptivity on Multiprocessors

• Motivating Application Whisper acoustic tracker
  for virtual environments.

Microphones on ceiling
Speakers on hands and feet
User
TrackingComputer
3
Whisper Characteristics

• Workload requires a multiprocessor.
• Predictive techniques used in tracking.
• Time to compute next prediction depends on
  accuracy of previous prediction.
• ? computational costs will vary.
• Lots of microphones/speakers ? lots of tasks!
• Not practical to provision all tasks assuming max
  costs.
• Question How to ensure adaptive real-time
  execution on a multiprocessor?

4
Multiprocessor SchedulingPartitioning
Partition tasks so that each task always runs on
the same processor.

• Steps
• Assign tasks to processors (bin packing).
• Schedule tasks on each processor using
  uniprocessor algorithms.

5
Problems with Partitioning

• Variations in computation costs may necessitate a
  re-partitioning.
• Problematic because
• Partitioning bin packing
• an intractable problem.
• Re-partitionings may cause task migrations
• the very thing partitioning is designed to
  avoid.

6
Global SchedulingAn Alternative to Partitioning
A single scheduling algorithm is used
that schedules all tasks.

• Important Difference
• Tasks may migrate among the processors.
• Probably appropriate only on
• tightly-coupled systems.

Research Topic Global scheduling algorithms that
facilitate real-time adaptivity.
7
Vision
Want to be able perform allocations like this on
a multiprocessor
N1
S4
S5
Soft RT Tasks
S3
Task Shares
S2
S1
H4
Hard RT Tasks
H3
H2
H1
Time
without violating timing constraints, in the face
of complexities like synchronization and I/O.
8
The Periodic Task ModelThe Simplest Form of
Timing Constraint

• Periodic Tasks
• Task T (T.e, T.p) releases a job with execution
  cost T.e every T.p time units.
• Ts weight or processor share is T.wt T.e/T.p.
• Each job of T has a deadline at the next job
  release of T.

2
5
T (2,5)
U (9,15)
0
10
20
30
5
15
25
9
Job-based Scheduling Doesnt Work

• Cant consider jobs as the pieces of work to
  schedule because deadlines can be missed.
• Example Scheduling three (2,3) tasks on two
  processors.

Processor 1
Job 1 of Task 1
Job 1 of Task 3
Processor 2
Job 1 of Task 2
0
2
1
3
10
Our ApproachSchedule Smaller Pieces of Work

• Basic Ideas
• Processor time is allocated in multiples of some
  basic quantum.
• Break jobs into quantum-length subtasks.
• Assign deadlines to subtasks.

11
Student Needs

• Three new RA positions.
• Topic Adaptive scheduling and resource
  allocation in real-time multiprocessor systems.
• Issues Scheduling, synchronization, device I/O,
  managing thread migrations, feedback-control
  mechanisms,
• Applied algorithmic research.
• Must have good formal reasoning skills.
• Lots of dissertation/paper topics!

12
Having Fun doing cool research, writing
papers, and going to cool places

• Anand Srinivasan Ph.D. 2003
• Pisa, Italy Nice, France Vienna, Austria
  Montreal Delft, The Netherlands Cheju Island,
  S. Korea Stockholm, Sweden.
• Yong-Jik Kim Ph.D. 2003
• Sorrento, Italy Lisbon, Portugal Toledo, Spain
  Bratislava, Slovak Republic.
• Phil Holman Ph.D. 2004
• Toronto Porto, Portugal Vienna, Austria
  London, UK Cheju Island, S. Korea Cancun.
• Uma Devi Ph.D. expected in 2006
• Porto, Portugal Toronto Gothenburg, Sweden.
• Aaron Block P.D. expected in 2007
• Cancun.

13
The End!