Title: | Integrating the self-healing mechanism into heterogeneous systems |
Subject: | Computer science, Embedded systems, Dependable Aeronautics and aerospace |
Level: | Advanced |
Description: |
A heterogeneous system might include various processing elements such as CPU, FPGA, and GPU. The number of each of these resources may vary. For instance, a system may include eight CPUs, four FPGAs, and two GPUs. A self-healing mechanism enables a system to stay alive and working despite possible (mostly transient) failures, for example, because of external radiations. It is vital for many real-life systems such as hospital facilities, aircrafts, and satellite systems. This thesis aims at analyzing, design space exploration, and integrating a self-healing mechanism into a heterogeneous system. To put it simply, a self-healing mechanism in this scenario disables and enables the processing elements and reroutes the processes to intact elements. This is an industrial thesis in collaboration with the Unibap company (unibap.com). This project can be done by one or two students. Supervisor(s): Mohammad Riazati Examiner: |
Start date: | |
End date: | |
Prerequisites: | This thesis is primarily intended for Advanced Level student(s) with good knowledge on C/C++, VHDL, FPGA design. Intermediate knowledge of Neural Network architecture would be a plus. |
IDT supervisors: | |
Examiner: | |
Comments: | |
Company contact: |