Investigating Software Deployment on Heterogeneous Platforms

Devices with computing capabilities are everywhere.Physical components that once were restricted to its formsand mechanics to provide functionality have now gained anenormous number of possibilities through the implementation ofEmbedded Systems (ES). However, together with the advantagesof ES come the challenges of dealing with both the increasingcomplexity of software and the different constraints of hardware.Moreover, it is becoming a common practice to deploy softwareon computation units of different types (i.e. CPUs, GPUs andFPGAs) in order to optimize data processing and resourceutilization. This paper reports on a PhD research project inthe area of software deployment on heterogeneous platforms,focusing on how different deployment strategies contribute toachieve certain non-functional properties, such as performanceand energy efficiency. As it is important to understand previouspractices and acknowledge possible gaps in the research area,a systematic literature review is currently being conducted, andits initial/planning stages are described. Further, recent contributionsin the context of data marshalling are also discussed, aswell as the planned next steps and the impact of this project inan industrial context