Generic partial dynamic reconfiguration controller for fault tolerant designs based on FPGA

Mitigation of Radiation Effects in SRAM-Based FPGAs for Space Applications

“…Straka and his colleagues at University of Brno also work on a fault tolerant framework for SRAM-based FPGAs. Very similar to the already mentioned approaches, a so-called Generic Partial Reconfiguration Controller receives error signals from reconfigurable modules and triggers ondemand scrubbing if required [Straka et al 2010b]. Azambuja et al also use majority voters as failure detection mechanisms and scrub a faulty reconfigurable module only after a failure has been detected [Azambuja et al 2008;Azambuja et al 2009].…”

“…In the course of this research, the design of online failure checkers was first proposed in [Straka et al 2007] and later extended to the overall framework [Straka et al 2010a]. The reconfiguration controller is described in [Straka et al 2010b] and a fault injection system is presented in . Finally, a dependability analysis for the framework is described in ].…”

Improving FPGA repair under real-time constraints

“…This approach consists in overwriting the memory with its desired contents, and may be applied either periodically, regardless of the presence of errors, or triggered by error detection mechanisms. This can be achieved either through concurrent error detection based on circuit redundancy [6][7][8][9][10][11][12] or through a readback of the configuration memory [13][14][15]. The repair time attainable with straightforward global scrubbing (i.e.…”

“…And, as FPGAs grow in terms of logic density, configuration memories grow accordingly. As a result, FPGA-based systems with realtime constraints require specialized repair mechanisms, usually based on partial reconfiguration [6][7][8][9][10][11][12][13][14][15][16].…”

“…This is analogous to the usual concern of meeting a given worst case execution time instead of simply minimizing the average execution time. In contrast, several previous works aim at minimizing the repair time attainable with scrubbing [6][7][8][9][10][11][12][13]. Minimizing the mean time to repair (MTTR) is useful, for example, when the goal is to maximize the availability of the system.…”