Context saving and restoring for multitasking in reconfigurable systems

Abstract

Today's Field Programmable Gate Arrays (FPGAs) can be reconfigured partially, which makes it possible to share resources between various functional modules (hardware tasks) over time. This concept is well known in the area of conventional operating systems. However, in order to transfer resource sharing concepts to operating systems on FPGAs, several underlying mechanisms have to be developed. One of these mechanisms is to suspend hardware tasks and restart them at another time and/or another area of the FPGA. Addressing this problem, this paper discusses ways to save and restore the state information of a hardware task. Afterwards, an implementation of a state relocation mechanisms is presented that uses the standard configuration port. In contrast to similar approaches, we significantly reduce the amount of readback data by reading only those configuration frames that contain state information. We finally determine the time overhead for task relocation, which is essential for most multitasking concepts, like defragmentation 1 .

A Novel Framework for Effective Preemptive Hardware Multitasking on FPGAs

“…Work in [3] presents a CPA-based method for HW task preemption. It targets Xilinx Virtex-I architecture and is suitable for HW tasks which only contain FF elements.…”

“…With regard to work presented in [3], only the reconfiguration and readback speeds can be compared quantitatively. In our approach, these are about eight times higher than those presented in the previous work, excluding the latency incurred by the external memory controller.…”

“…In contrast to [3] which stores the state of separate FFs in the database, in the proposed approach, whole staterelated frames are stored in a bitstream repository. Details of the HW task's state model used in this approach can be found in Sect.…”

“…In the CPA methods [3], [4], all state-related frames which correspond to a given HW task are read from the FPGA's CM through its configuration port. Later on, they are filtered in order to retrieve the state of the HW task.…”

A Programmable Configuration Controller for fault-tolerant applications

“…• AC-ICAP [17] A number of researchers, such as [20], have worked on pure hardware-based RCs for better performance but are more expensive to implemente than combined softwarehardware approaches. Furthermore, HW-only designs are not programmable and lack the flexibility needed to develop and explore different fault detection and recovery applications.…”