Comparison of Different Thread Scheduling Strategies for Asymmetric Chip MultiThreading Architectures in Embedded Systems

Future embedded systems will have to support multiple and concurrent dynamic compute-intensive applications. These variable workloads can be handled by an efficient asymmetric MPSoC architecture, which integrates multithreaded processors as key processing elements. In this paper, we consider an asymmetric MPSoC architecture with a centralized controller and multiple multithreaded processors, which we call A-CMT (Asymmetric Chip Multi Threading). The centralized controller can implement 2 main types of thread scheduler architectures: VSMP (Virtual Symmetric Multi Processing), and SMTC (Symmetric Multi-Thread-Context). Each type can have a static or dynamic allocation. We show that static scheduling for the A-CMT with dynamic applications (such as connected component labeling) can become a bottleneck for the overall architecture´s performance, which leverages the use of dynamic scheduling for VSMP and SMTC. The dynamic SMTC gave a maximum of 51% and 11% speedup compared to the static SMTC and dynamic VSMP respectively.