No abstract

No abstract

Recent research has recognised the potential of coupling ADLs with underlying runtime environments to support systematic and integrated "specification-todeployment" architectures. However, while some promising results have been obtained, much of this research has not considered the crucial issue of causally-connected dynamic reconfiguration and has considered only domain-specific areas. In this paper we discuss a specification-to-deployment architecture called Plastik that employs an extended generalpurpose ADL and is underpinned by an efficient runtime that is suited both for high-level application development and low-level systems development (e.g. embedded systems). Runtime reconfiguration is supported both at the ADL level and at the runtime level, and both programmed reconfiguration and adhoc reconfiguration are supported. The paper focuses on the mapping of ADL-level specifications to runtime instantiations and on the necessary runtime support for causally-connected dynamic reconfiguration.

No abstract

Abstract-Network Processors (NPs) are emerging as cost effective networking elements that can be more readily updated and evolved than custom hardware or ASIC-based designs. Moreover, NPs promise support for run-time reconfiguration of low-level networking software. However, it is notoriously difficult to develop software for NPs because of their complex design, architectural heterogeneity, and demanding performance constraints. In this paper we present a runtime componentbased approach to programming NPs. The approach promotes conceptual uniformity and design portability across a wide variety of NP types while simultaneously exploiting hardware assists that are specific to individual NPs. To show how our approach can be applied in a wide range of types of NPs we characterise the design space of NPs and demonstrate the applicability of our concepts to the various classes identified. Then, as a detailed case study, we focus on programming the Intel IXP1200 NP. This demonstrates that our approach can be effectively applied, e.g. in terms of performance, in a demanding real-world NP environment.