+ All Categories
Home > Documents > Static Process Scheduling

Static Process Scheduling

Date post: 22-Feb-2016
Category:
Upload: ailsa
View: 54 times
Download: 0 times
Share this document with a friend
Description:
Static Process Scheduling. Martha Garcia. Static Process scheduling. Goals of Static Process Scheduling Types of Static Process Scheduling Future Research References. Static Process scheduling. GOALS : - PowerPoint PPT Presentation
Popular Tags:
17
STATIC PROCESS SCHEDULING Martha Garcia
Transcript
Page 1: Static Process Scheduling

STATIC PROCESS SCHEDULING

Martha Garcia

Page 2: Static Process Scheduling

STATIC PROCESS SCHEDULING Goals of Static Process Scheduling Types of Static Process Scheduling Future Research References

Page 3: Static Process Scheduling

STATIC PROCESS SCHEDULINGGOALS : Given a set or partially ordered tasks, define a

mapping of processes to processors before the execution of the processes.

Cost model:CPU cost and communication cost, both should be specified in prior

Minimize the overall finish time on a non-preemptive(can not be interrupted) multiprocessor system (of identical processors)

-Except for some very restricted cases, scheduling to optimize the makespand are NP-Complete

-Heuristic solutions are usually proposed.

Page 4: Static Process Scheduling

STATIC PROCESS SCHEDULINGTwo Types :

Precedence Process Model Communication Process Model

Page 5: Static Process Scheduling

STATIC PROCESS SCHEDULING- PRECEDENCE PROCESS MODEL Precedence Process Model :

- Program is represented by a DAG(Directed Acyclic Graph). Direct edges represent the precedence relationship.

- The longest execution path in the DAG often used to compare the performance of a heuristic algorithm.

I

J

K

L

[Chow and Johnson 1997]

Page 6: Static Process Scheduling

STATIC PROCESS SCHEDULING- PRECEDENCE PROCESS MODEL

Precedence constraints among tasks in a program are explicitly specified.

Scheduling goal: minimize the makespan time

No. of messagesto communicate

Execution time

Communication overhead for A(P1) and E(P3)= 4 * 2 = 8

Communication overhead for one message

[Chow and Johnson 1997]

Page 7: Static Process Scheduling

STATIC PROCESS SCHEDULING- PRECEDENCE PROCESS MODELAlgorithms: List Scheduling (LS): Communication overhead

is not considered. Using a simple greedy heuristic: No processor remains idle if there are some tasks available that it could process.

Extended List Scheduling (ELS): the actual scheduling results of LS with communication consideration.

Earliest Task First scheduling (ETF): the earliest schedulable task (with communication delay considered) is scheduled first.

[Chow and Johnson 1997]

Page 8: Static Process Scheduling

STATIC PROCESS SCHEDULING- PRECEDENCE PROCESS MODELMakespan Calculation for LS, ELS, and ETF

[Chow and Johnson 1997]

Page 9: Static Process Scheduling

STATIC PROCESS SCHEDULING- COMMUNICATION PROCESS MODELCommunication Process Model

There are no precedence constrains among processes

modeled by a undirected graph G, node represent processes and weight on the edge is the amount of communication messages between two connected processes.

Process execution cost might be specified some times to handle more general cases.

Scheduling goal: maximize the resource utilization[Chow and Johnson 1997]

Page 10: Static Process Scheduling

STATIC PROCESS SCHEDULING- COMMUNICATION PROCESS MODEL the problem is to find an optimal assignment

of m process to P processors with respect to the target function:

P: a set of processors. ej(pi): computation cost of execution process pi in processor Pj.

ci,j(pi,pj): communication overhead between processes pi and pj.

Assume a uniform communicating speed between processors.

[Chow and Johnson 1997]

Page 11: Static Process Scheduling

STATIC PROCESS SCHEDULING- COMMUNICATION PROCESS MODEL This is referred as Module Allocation problem.

It is NP-complete except for a few cases: For P=2, Stone suggested an polynomial time

solution using Ford-Fulkerson’s maximum flow algorithm.

Known results: The mapping problem for an arbitrary number of processors is NP-complete.

[Chow and Johnson 1997]

Page 12: Static Process Scheduling

STATIC PROCESS SCHEDULING- COMMUNICATION PROCESS MODEL Stone’s two-processor model to achieve

minimum total execution and communication cost

Example: Partition the graph by drawing a line cutting through some

edges Result in two disjoint graphs, one for each process Set of removed edges cut set

Cost of cut set sum of weights of the edges Total inter-process communication cost between processors

Of course, the cost of cut sets is 0 if all processes are assigned to the same node

Computation constraints (no more k, distribute evenly…)

Example: Maximum flow and minimum cut in a commodity-flow

network Find the maximum flow from source to destination

[Chow and Johnson 1997]

Page 13: Static Process Scheduling

STATIC PROCESS SCHEDULING- COMMUNICATION PROCESS MODELMaximum Flow Algorithm in Solving the Scheduling Problem

[Chow and Johnson 1997]

Page 14: Static Process Scheduling

STATIC PROCESS SCHEDULING- COMMUNICATION PROCESS MODELMinimum-Cost Cut

Only the cuts that separate A and Bare feasible

[Chow and Johnson 1997]

Page 15: Static Process Scheduling

STATIC PROCESS SCHEDULING

Future Research :

Use AI techniques for Static Scheduling :Genetic Algorithm

Page 16: Static Process Scheduling

STATIC PROCESS SCHEDULING

References : Design Optimization of Time – and Cost – Constrained Fault –

Tolerant Distributed Embedded Systems.- Viacheslav Izosimov, Paul Pop. Petru Eles, Zebo Peng

A Static Task Scheduling Framework for Independent Tasks Accelerated using a Shared Graphics Processing Unit.- Teng Li, Vikram K.Narayana, Tarek El-Ghazawi, IEEE 2011

MAPPLE chip: a processing element for a static scheduling centric multiprocessor.- Kenta Yasufuku, Riku Ogawa, Keisure Iwai, Hideharu Amanu, IEEE 2003

Page 17: Static Process Scheduling

STATIC PROCESS SCHEDULING Thank you!!


Recommended