.. include:: crossreferences.asc

.. |title| replace:: Load Balancing in a Multi-Processor environment
.. |wp|    replace:: WP56
.. |start| replace:: M3, M4
.. |p1|    replace:: X
.. |m1|    replace:: 3
.. |p2|    replace:: Y
.. |m2|    replace:: 3
.. |p3|    replace:: Z
.. |m3|    replace:: 3
.. |p4|    replace:: |e|
.. |m4|    replace:: |e|
.. |p5|    replace:: |e|
.. |m5|    replace:: |e|
.. |p6|    replace:: |e|
.. |m6|    replace:: |e|

.. include:: wp-toptable.asc

.. include:: wp-tablebegin.asc

**Objectives**

Implement load balancing for distributed applications.

.. include:: wp-tableend.asc
.. include:: wp-tablebegin.asc

**Description of work**

- Provide decentralized network architecture for routing and processing computational tasks
- Investigate use of statistical network information for load balancing
- Compare with information obtained by probing the network
- Distribute workload accordingly to available resources
- Implement distribution on different levels (tasks, entire object spaces)
- Make network nodes attachable and detachable at runtime
- Reassign unfinished tasks to other nodes
- Study effects of different routing topologies
- Investigate restrictions on network nodes for untrusted code

.. include:: wp-tableend.asc
.. include:: wp-tablebegin.asc

**Deliverables**

- Network service running on a variatey of nodes
- PyPy runtime distributing workload on the network

.. include:: wp-tableend.asc
.. include:: wp-tablebegin.asc

**Milestones and Expected Result**

- M9

.. include:: wp-tableend.asc