Smart Memory Management (SaMM) For Embedded Systems without MMU
Krishnaveni Bukkapatnam, Prashant, Ch Kranthi Rekha, Eelandula Kumaraswamy, Rambabu Vatti
Abstract
Abstract In the wake of extensible usage of IOT (Internet of Things) enabled Embedded Systems, it is of great importance to find ways of using Memory in the most efficient way. Embedded Systems are also space constrained, hence at various places, it may not be possible to deploy a Hardware based–(MMU) Memory Management Units. In MMU less Embedded systems, there are various principles of DMA being applied; however, they are all constrained in one way or the other. With this backdrop, this paper is exploring opportunities to achieve higher performance and efficiency in Memory Management by using Smart and Programmable methods. Proposed methods have achieved an overall improvement in Allocation speeds to the tune of 3-4 times, however there is a marginal drop in Deallocation speed. Overall a better bargain and another very good outcome is 0 defragmented memory. This paper also presents algorithms for Allocation, Deallocation and Defragmentation processes, which can be implemented within available Application Software.