A Process Network Model for Reactive Streaming Software with Deterministic Task Parallelism

Abstract

A formal semantics is introduced for a Process Network model, which combines streaming and reactive control processing with task parallelism properties suitable to exploit multi-cores. Applications that react to environment stimuli are implemented by communicating sporadic and periodic tasks, programmed independently from an execution platform. Two functionally equivalent semantics are defined, one for sequential execution and one real-time. The former ensures functional determinism by implying precedence constraints between jobs (task executions), hence, the program outputs are independent from the task scheduling. The latter specifies concurrent execution on a real-time platform, guaranteeing all model's constraints; it has been implemented in an executable formal specification language. The model's implementation runs on multi-core embedded systems, and supports integration of runtime managers for shared HW/SW resources (e.g. for controlling QoS, resource interference or power consumption). Finally, a model transformation approach has been developed, which allowed to port and statically schedule a real spacecraft on-board application on an industrial multi-core platform.

Process Network Models for Embedded System Design Based on the Real-Time BIP Execution Engine

“…This gives us a (reverse proportional) measure of a maximal throughput that the system could achieve, by reducing the period from 50 ms to 40 ms. Despite a higher parallelism compared to a scenario where three cores are utilized [7], no improvement is achieved in throughput due to the interference between P1, P4, which manifested in longer execution time of P4. A possible solution to this end is modifying the mailbox BIP implementation to reduce the interference.…”

“…The proposed design approach aims to a formal and accountable process for deriving implementations of FPPNs whose schedulability is preserved throughout the process and it is eventually guaranteed by construction on top of the real-time BIP execution engine. A series of automated model transformation steps is applied starting with the TASTE2BIP 1 transformation [7] that compiles any FPPN process network into the BIP language. The source code is parsed, searching for primitives (reads and writes from/to the data channels) that are relevant for the process interactions.…”

“…Step 2 Model transformation: FPPN model transformation into RT-BIP according to the FPPN execution semantics in [7]. If WCETs are known, the task graph is also generated.…”

“…In [7], we introduced the formal semantics of a new process network model that combines streaming and reactive control processing with task parallelism. The so-called FPPNs (Fixed Priority Process Networks) enable the design of applications that react to environment stimuli through the definition of communicating tasks that are programmed independently from the execution platform.…”

“…The FPPN semantics is defined in [7] by compilation into RT-BIP [2], an executable formal language for modeling networks of connected timed automata. In present paper, we utilize the results from [7], [17] and [15] to propose a design flow based on the principles of rigorous system design [20].…”