Code partitioning for synthesis of embedded applications with phantom

Abstract

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.

Synthesis of time-constrained multitasking embedded software

“…For a complete and detailed description, refer to the previously published work Nacul and Givargis [2004]; Nacul and Givargis [2005a].…”

“…The Phantom partitioning is central to the correctness and the performance of the generated code [Nacul and Givargis 2004]. Boundaries of AEB represent the points where tasks might be preempted or resumed for execution.…”

“…In our previous work, we have introduced the Phantom compiler, discussing the partitioning problem [Nacul and Givargis 2004] and detailing the structure of the synthesized code [Nacul and Givargis 2005a]. In the previous versions of the compiler, there was no support for automatically specifying timing constraints, and therefore influence the timing behavior of the generated code precisely.…”

A Methodology for Bridging the Gap between UML and Codesign

“…That is the case with eCos [10]. Finally, the API based description can be used as input to tools that generate a customized OS infrastructure, like Polis [2] and Phantom [12].…”

“…Software modules are generated according to the operating system support desired by the designer. At the time, our environment can generate software modules based on the POLIS framework [2], the Phantom Compiler [12] and any POSIX based operating system, like Embedded Linux [20] or eCos [10] with the POSIX adaptation layer. Software is compiled to a specific processor, which can be a NEC V850 or an ARM946.…”