Eftersom vi skapar framtidens produkter och system, kretsar en hel del av vår verksamhet kring FoU. Det är avgörande för att utveckla företaget. Vi investerar därför kontinuerligt i FoU och deltar i EU-finansierade forskningsprojekt. Dessutom samarbetar vi med universitet, högskolor och andra specialister, för att bygga en företagskultur där lärandet är en integrerad del av verksamheten. Vårt arbete med FoU ger oss möjlighet att utveckla våra kunskaper och utforska den allra senaste tekniken. Denna kunskap delar vi sedan med våra kunder och partners genom utbildningar, seminarium, artiklar och workshops.
SMECY envisions that recently emerged multicore technologies will rapidly develop to massively parallel computing environments, which due to improved performance, energy and cost properties will, in a few years, extensively penetrate the embedded system industry sectors. This will affect and shape the whole business landscape, e.g. semiconductor vendors need to be capable of offering advanced multicore platforms to diverse application sectors, Intellectual Property (IP) providers need to re-target existing and develop new solutions to be compatible with evolving multicore platforms and the need of embedded system houses, in addition to product architecture adaptations and renewing their system, architecture, software and hardware development processes.
The complexity of future smart multicore embedded systems requires holistic system integration because of strict and stringent constraints on e.g. performance and time to market that can only be mastered using a design approach that optimizes interaction between SoC design and Embedded Software approaches. Therefore, many companies that traditionally have a culture rooted in nano and microelectronics express an urgent need in acquiring know-how and competences in embedded software. Equally urgent is the need of embedded system houses to be able to transform their current product assets to use multicores and at the same time to establish development processes in order to fully exploit them.
Read more about the project and the consortium on the Artemis website an the page for SMECY.
PaPP - Portable and Predictable Performance on Heterogeneous Embedded Systems
The PaPP project aims at making performance predictable for parallel applications on heterogeneous parallel platforms. Performance should be predictable in every development phase, from the modeling of the system, over its implementation and through to its execution. This will enable the European developers to design systems and software for the complicated heterogeneous systems of the future with performance portability and reduced resource usage in cost-efficient solutions capable of competing on a worldwide market.
This will be achieved by allowing for early specification and analysis of performance of systems and its adaptation to different hardware platforms, including an adaptive runtime system. The concrete results of PaPP will be tools, software architectures and best practices guidelines for the development of software on heterogeneous manycore systems of increasing complexity.
In the project Realtime Embedded will develop a platform based on an FPGA with multiple soft Leon3-processor cores in a heterogeneous configuration and an hybrid OS solution, with a mixture of Linux and real time OS running on different cores. The flexibility of the platform makes it possible to adjust it in order to optimize inter-processor communication, power management and resource sharing. The platform can also be fitted with hardware support for performance counters, debugging and external control.
Realtime Embedded will also develop a virtual platform to facilitate effective development of software early in the design phase. This will also enable automated testing and debugging possibilities throughout the development cycle. This tool will offer a framework where it is possible to assemble virtual components (devices) to form a virtual platform which has identical software interfaces to an actual physical platform. Thus, within PaPP, Realtime Embedded will develop a virtual environment which is identical, from a software perspective, with the physical platform and which executes the same unmodified software. An elastic hardware platform together with a virtual environment will in the future allow for fast creation of flexible multicore and heterogeneous systems portable across many applications.
Read more about the project and the consortium on the Artemis website an the page for PaPP.
The EC project „DEWI - Dependable Embedded Wireless Infrastructure“ with 58 partners from 11 countries focuses on the development of wireless sensor networks, wireless communication and wireless applications. DEWI will provide key solutions for seamless wireless connectivity and interoperability in smart cities and infrastructures by considering everyday physical environments of citizens and professional users in airplanes, cars, trains as well as buildings. The results will be presented to the public via practical demonstrations in the areas of aeronautics, automotive, rail and building. Furthermore DEWI provides essential contributions to interoperability, standardization and certification of wireless sensor networks and wireless communication.
Realtime Embedded is a proud Bronze sponsor of ICES.
The guiding vision of ICES is to achieve a flourishing ecosystem for industry and academia, excelling in embedded systems education, research and innovation. ICES is established as a KTH competence centre, an organisational form used for establishing multidisciplinary cooperation across KTH schools and with industry.
Academic ICES founder members, all represented on the ICES board, come from research groups spanning 4 of the 11 KTH schools:
- Computer Science and Communications (CSC)
- Electrical Engineering (EES)
- Information and Communication Technology (ICT)
- Industrial Engineering and Management (ITM)