Research associate / PhD candidate (f/m/d) on the topic Near-Memory-Processing Architectures
Since many years, the Chair for Embedded Systems works internationally successfully in the areas of computer engineering, such as embedded system architecture. Many interesting and open problems in these areas need to be addressed to successfully deploy such systems in modern application domains. As an example, the most urgent questions about in- and near-memory computing architectures are highlighted in the following.
Future mobile networks will become more and more self-managed at the base station level, due to the need for complex but real-time decision making. Machine learning algorithms will enable this transition since they outperform classical approaches in many areas. However, the base station hardware has to be adapted to this increasing workload. Using common computer architectures will be insufficient. They will struggle to provide the performance under the given energy constraints because they separate memory and computing resources creating substantial overhead through data transfers. The near-memory-computing (NMC) paradigm tries to minimize such transfers. The in-memory-computing (INC) concept is even more embedded and places computations directly inside the memory. In the scope of this research project, possible computer architectures shall be investigated. But at which level in the memory hierarchy do changes have the biggest effect? Depending on the analysis, different research questions have to be answered. Coherence between caches and main memory has to be maintained if data is being processed directly in the main memory and not moved through the caches. This also raises the challenge to handle concurrent accesses on the same data. Additionally, the NMC and INC architectures should be as flexible as possible, e.g., by using the memory for compute and storage at the same time or by running user-provided code on small CPU cores inside the main memory. With direct access to the whole memory, this raises questions for the virtual memory management and has severe security implications. The above mentioned problems and many more have to be tackled to enable future technologies by reducing energy consumption and improving performance.
You should have a very good Master's degree (or equivalent) in CS or EE with background or specialization in the above-mentioned topics. The ideal candidate (f/m/d) shows a strong interest and motivation to deepen in these topics to a level required for a doctorate. Knowledge of computer architecture, programming skills in C/C++, and scripting languages like Python will be required. Fluency in written and spoken English is a prerequisite. We are looking for a highly motivated candidate (f/m/d) with a strong commitment to research ethics and teamwork. Good communicative skills are mandatory due to the interdisciplinary structure of the project and the team.
Salary category 13, depending on the fulfillment of professional and personal requirements.
Institute for Computer Engineering (ITEC)
as soon as possible
limited to four years with the possibility to obtain a Ph.D.
Application up to
Contact person in line-management
For further information, please contact Prof. Henkel, 0721/608-46050; topic: Application SWC_NMP.
Please apply online using the button below for this vacancy number 1062/2019.
Personnel Support is provided by
Telefon: +49 721 608-42016,
Kaiserstr. 12, 76131 Karlsruhe
We prefer to balance the number of employees (f/m/d). Therefore we kindly ask female applicants to apply for this job.
If qualified, severely disabled persons will be preferred.