Dynamic task allocation in networks-on-chip

0Citations
Citations of this article
3Readers
Mendeley users who have this article in their library.
Get full text

Abstract

The run-time strategy for allocating the application tasks to platform resources in homogeneous Networks-on-Chip (NoCs) is enhanced with respect to minimising the communication energy consumption. As novel contribution, the entity Life-Time (LT) is incorporated to a node of an application characteristics graph (ACG), used for describing an incoming application. Several algorithms are then modified for solving the task allocation problem, while minimizing the communication energy consumption and network contention. If Life-Time(LT) is taken into consideration, it is observed that after each allocation, the nodes having lower value of life-time contains more available neighbors, compared to the existing solution, hence helps in allocation of an application as the system load increases, whereas the existing solution may fail to allocate the new application onto the current system configuration. Again, a node(used to describe a task in an application) belonging to an ACG is deallocated when its Life-Time expires which results in minimizing the communication energy consumption. © 2011 Springer-Verlag Berlin Heidelberg.

Cite

CITATION STYLE

APA

Bindu, A., & Kumar, D. J. (2011). Dynamic task allocation in networks-on-chip. In Communications in Computer and Information Science (Vol. 154 CCIS, pp. 158–170). https://doi.org/10.1007/978-3-642-21153-9_15

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free