A methodology to automatically optimize dynamic memory managers applying grammatical evolution

•In this paper, we present a new multi-objective optimization method based on genetic programming that can be used to optimize the complex DMMs implementations for highly dynamic applications. This method largely simplifies the exploration effort of multi-layered DMMs for designers and enables the refinement of DMM implementations in an automated way.•The proposed approach leads to important savings in overall system integration time for dynamic applications. In addition, the method obtains optimal implementations of DMMs structures with respect to key designer's metrics.•Our experimental results with six benchmarks and five general-purpose DMMs show that the presented optimization approach significantly reduce the execution time and memory usage up to 59.27% on average when comparing the global fitness.•The results obtained so far have outlined other interesting future research lines in the area of DMM implementation optimizations using grammatical evolution. Initially, the grammar can be extended in order to obtain more and more DMM candidates.

Modern consumer devices must execute multimedia applications that exhibit high resource utilization. In order to efficiently execute these applications, the dynamic memory subsystem needs to be optimized. This complex task can be tackled in two complementary ways: optimizing the application source code or designing custom dynamic memory management mechanisms. Currently, the first approach has been well established, and several automatic methodologies have been proposed. Regarding the second approach, software engineers often write custom dynamic memory managers from scratch, which is a difficult and error-prone work. This paper presents a novel way to automatically generate custom dynamic memory managers optimizing both performance and memory usage of the target application. The design space is pruned using grammatical evolution converging to the best dynamic memory manager implementation for the target application. Our methodology achieves important improvements (62.55% and 30.62% better on average in performance and memory usage, respectively) when its results are compared to five different general-purpose dynamic memory managers.