Master Thesis on FPGA resource management
FPGAs are being deployed in the data-centers to accelerate cloud applications (e.g. Bing Search). Public cloud providers are starting to offer FPGAs (e.g. Amazon F1 instance) to enable the users to generate custom hardware accelerators for their applications. The current models of executing applications on cloud-based FPGAs are typically limited to single applications, which means the FPGA resources are not shared and fully in line with original promises of cloud business models. To solve this problem, FPGA resources (logic blocks, internal memory, external memory bandwidth etc..) can be divided into multiple partitions and can thus host accelerators for multiple tenants in parallel. To get a better understanding of the problem area, please refer to “Vaishnav, A., Pham, K.D. and Koch, D., 2018. A Survey on FPGA Virtualization. 28th FPL.”
The goal of the master thesis is to develop an abstraction layer to the FPGA, which exposes the partitions as virtual FPGAs to the users and monitors their resource usage in the cloud.
The thesis work comprises several tasks
- Review existing techniques to support multi-tenancy on FPGAs
- Design resource usage monitors for virtual FPGAs
- Develop a framework that uses Partial Reconfiguration Design Flow to generate bitstreams of accelerator function units provided by multiple users.
- Integrate Virtual FPGAs in the Kubernetes container orchestration platform
- Demo and documentation of a working solution
Qualifications and Experience
- MSc Student in Computer Science/Engineering or other related fields
- Good knowledge of Xilinx Partial Reconfiguration design flow and Vivado HLS
- Working knowledge of Kubernetes and Linux environment.
- Good programing skills are required; knowledge of C/C++, Verilog, Tcl
The work is expected to start in January/February 2019. The work is proposed for one student for a duration of 6 months. Location is at Ericsson Research in Stockholm (Kista), Sweden. For informal queries, feel free to email email@example.com.
Please submit your application in English as soon as possible - we are working continuously with candidate selection.
Ericsson provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetics.
Ericsson complies with applicable country, state and all local laws governing nondiscrimination in employment in every location across the world in which the company has facilities. In addition, Ericsson supports the UN Guiding Principles for Business and Human Rights and the United Nations Global Compact.
This policy applies to all terms and conditions of employment, including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, training and development.
Ericsson expressly prohibits any form of workplace harassment based on race, color, religion, sex, sexual orientation, marital status, pregnancy, parental status, national origin, ethnic background, age, disability, political opinion, social status, veteran status, union membership or genetic information.
Primary country and city: Sweden (SE) || || Stockholm || Stud&YP
Req ID: 261492