In a large class of embedded systems, dynamic multitasking using traditional OS techniques is infeasible because of memory and processing overheads or lack of operating systems availability for the target embedded processor. Serializing compilers have been proposed as an alternative solution, enabling a designer to develop multitasking applications without the need of OS support. A serializing compiler is a source-to-source translator that takes a POSIX compliant multitasking C program as input and generates an equivalent, embedded processor independent, singlethreaded ANSI C program, to be compiled using the embedded processor-specific tool chain. Such serializing compilers work by partitioning each task into blocks of code and synthesizing a scheduler that dynamically switches among these blocks. The quality of the compiled code in terms of multitasking overhead and task latency is highly dependent on the partitioning algorithm. In this work, we give our solution to the partitioning problem in the context of serializing compilers. We show that it is possible to provide the designer with a set of Pareto-Optimal solutions that trade off multitasking overhead for task latency.

No abstract

Given a set of real-time tasks scheduled using the earliest deadline first (EDF

No abstract

In an era of powerful general-purpose embedded compute platforms, the migration of system functionality from application specific integrated circuits (ASICs) to software has become a promising trend toward addressing the system complexity and shrinking timeto-market window challenges. Hence, in modern embedded systems, software development plays an increasingly vital role. On the other hand, the real-time concurrent programming model provides the high level abstractions necessary to effectively design complex software. Support for real-time concurrent programming is typically provided by a realtime operating system. We propose an alternate solution, the Phantom serializing compiler, to support the real-time concurrent programming model. The Phantom serializing compiler generates a single-threaded monolithic executable, from the multi-threaded application software, capable of directly executing on the underlying embedded compute platform. Further, the generated executable is tuned for maximum performance and efficiency, yielding an application-specific solution. In this paper, we give an overview of the Phantom serializing compiler and demonstrate its feasibility with some experimental results.