Memory access behavior of dynamically allocated data structures and programs with irregular access patterns

With the development of modern computers, memory latencies have become a key bottleneck for the performance of computer systems. Since then, much research work has targeted improving the performance of memory hierarchy. In this thesis, we examine the behavior of dynamically allocated data structures (DADS) and programs with irregular access patterns (PIAP). DADS and PIAP use dynamic memory management or algorithms with unpredictable behaviour. By simulating some applications of dynamically allocated data structures (DADS) and programs with irregular access patterns (PIAP), it is found that general cache management policies can not effectively use the treasurable cache resources for DADS and PIAP. We explored the use of mathematical formula applied to signal processing to improve the performance of memory hierarchy.

Memory access behavior of dynamically allocated data structures and programs with irregular access patterns

With the development of modern computers, memory latencies have become a key bottleneck for the performance of computer systems. Since then, much research work has targeted improving the performance of memory hierarchy. In this thesis, we examine the behavior of dynamically allocated data structures (DADS) and programs with irregular access patterns (PIAP). DADS and PIAP use dynamic memory management or algorithms with unpredictable behaviour. By simulating some applications of dynamically allocated data structures (DADS) and programs with irregular access patterns (PIAP), it is found that general cache management policies can not effectively use the treasurable cache resources for DADS and PIAP. We explored the use of mathematical formula applied to signal processing to improve the performance of memory hierarchy.

Hierarchical Behavior Model for Multi-Agent System with Evasion Capabilities and Dynamic Memory

The behavior of an agent may be simple or complex depending on its role. Behavioral simulation using agents can have multiple approaches that have different advantages and disadvantages. By combining different behaviors in a hierarchical model, situational inefficiencies can be compensated. This paper proposes a behavioral hierarchy model that combines different mechanisms in behavior plans. The study simulates the social behavior in an office environment during an emergency using collision avoidance, negotiation, conflict solution, and path-planning mechanisms in the same multi-agent model to find their effects and the efficiency of the combinational setups. Independent agents were designed to have memory expansion, pathfinding, and searching capabilities, and the ability to exchange information among themselves and perform evasive actions to find a way out of congestion and conflict. The designed model allows us to modify the behavioral hierarchy and action order of agents during evacuation scenarios. Moreover, each agent behavior can be enabled or disabled separately. The effects of these capabilities on escape performance were measured in terms of time required for evacuation and evacuation ratio. Test results prove that all mechanisms in the proposed model have characteristics that fit each other well in situations where different hierarchies are needed. Dynamic memory management (DMM), together with a hierarchical behavior plan, achieved a performance improvement of 23.14% in escape time without providing agents with any initial environmental information.

Efficient Dynamic Memory Management for Multiprocessor Cyber-Physical Systems

Dynamic data management for multiprocessor systems in the absence of an operating system (OS) is a challenging area of research. OSs are typically used to abstract developers from the process of managing dynamic data at runtime. However, due to the many different types of multiprocessor available, an OS is not always available, making the management of dynamic data a difficult task. In this article, we present a hardware and software co-design methodology for the management of dynamic data in multiprocessor system on chips (MPSoC) development environments without an OS. We compare and contrast the method of sharing dynamic data between cores with standard methods and also to static data management methods and find that the proposed methodology can improve the performance of dynamic memory operations by up to 72.94% with negligible power and resource consumption.