The Ampere Project, funded by the European Union, recently culminated on June 30th by introducing a software framework that utilizes high-performance computing (HPC) parallel programming models.
This solution aims to streamline the development and deployment of intricate cyber-physical systems (CPS) in the automotive and railway sectors, leading to a potential decrease in software development and deployment costs of up to 30%.
The Ampere project tackles the challenge of managing increasing software architecture complexity by integrating functional and non-functional requirements. It achieves real-time operations while considering energy, time, security and resilience. Notably, it successfully bridges the gap between rail (Capella) and automotive (Amalthea) domain-specific modeling languages (DSML) with parallel execution.
Eduardo Quiñones, the Ampere coordinator and Group Leader of the Predictable Parallel Computing Group at the Barcelona Supercomputing Center, lauds the project:
“The Ampere project provides a leap forward in the cyber-physical computing domain by enabling HPC parallel programming models to offer a faster and more reliable and resource-efficient development and deployment of systems, like rail and automotive,” he states.
The project expanded the OpenMP parallel programming model and the LLVM compilation framework used in the HPC domain. It unlocked parallel opportunities while meeting non-functional requirements. Ampere’s runtime parallel frameworks provide a modular approach, allowing users to choose components that meet their needs.
The Ampere project focuses on redefining HPC programming models for cyber-physical systems (CPS) to streamline development and reduce time-to-market. It enables the transformation of Domain-Specific Modeling Languages into the OpenMP programming model for efficient parallel resource utilization.
The project also addresses non-functional requirements for CPS’s resilience, safety and security. With safety and security mechanisms, such as the hypervisor and operating systems PikeOS and OpenERIKA, the project efficiently supports a parallel execution model.
The practical applications of the Ampere software framework were evaluated through two separate use cases: automotive and rail. In the automotive use case, the Predictive Cruise Control (PCC) feature, which extends adaptive cruise control by calculating future vehicle velocity using electronic horizon data, was implemented to enhance fuel efficiency.
The rail industry use case evaluated Ampere’s technology by implementing Thales’ Obstacle Detection and Avoidance System (ODAS). Using the Ampere synthesis tools, the model was transformed into OpenMP, harnessing the parallel potential of heterogeneous platforms and ensuring the system met non-functional requirements.
“The applications of the Ampere software framework could potentially revolutionize a wide array of industries that require the use of sophisticated parallel and heterogeneous computing technologies,” Quiñones adds.
For three and a half years, nine EU partners collaborated to achieve the project’s goals. The combined expertise from academic institutions and industrial partners contributed to developing this framework and its application in various use cases.
automotive | cyber-physical systems | HPC