Uncertainty Model for Configurable Hardware/Software and Resource Partitioning
This work was supported by the International Cooperation Program on Science and Technology (2010DFB10930, 2011DFG13000), the National Natural Science Foundation of China (61170304, 61104035, 61303014).
IEEE Transactions on Computers
Automatic hardware/software partitioning relies on characterization, estimation and design space exploration of the system performance and cost metrics. In real world situations, such estimates are complicated and cannot be 100 percent accurate. Furthermore, hardware/software co-design is so complicated nowadays that simply considering the bipartitioning between hardware and software is not sufficient. It is important to consider some of the other key design parameters and resource sharing together with the hardware/software partitioning problem. Under variable requirements of smart systems, more flexibility on the resource usage should be incorporated in system modelling. This paper considers uncertainty modeling for system partitioning with an enhanced set of parameters for hardware/software resource sharing. We harness state-of-the-art uncertainty theory for linear uncertain distribution and normal uncertain distribution. Our derivations convert the uncertainty model back to a regular constraint optimization problem. Experimental results show the effectiveness of our approach.
Locate the Document
PSU affiliates use Find in PSU library link at top.
Unaffiliated researchers can access the work here: http://dx.doi.org/10.1109/TC.2016.2519895
R. Wang, W. N. N. Hung, G. Yang and X. Song, "Uncertainty Model for Configurable Hardware/Software and Resource Partitioning," in IEEE Transactions on Computers, vol. 65, no. 10, pp. 3217-3223, Oct. 1 2016.