A Framework for Predictable Hardware/Software Component Reconfiguration
Resumo
The current pace of innovation in computing makes it difficult to assume a fixed set of requirements for the whole life span of a system. Aggressive technology scaling also imposes additional constraints to modern hardware platforms. Field-Programmable Gate Array (FPGA) reconfiguration can help systems cope with dynamic requirements such as performance and power, hardware defects due to Negative-Bias Temperature Instability (NBTI) and Process, Voltage and Temperature (PVT) variations, or application requirements unforeseen at design time. This work proposes a framework for reconfigurable components whereby the reconfiguration of a component implementation is performed transparently without user intervention. The reconfiguration process is confined in system's idle time without interfering with or being interfered by other activities occurring in the system or even peripherals performing I/O. A telecommunications switch was used as a case study for the deployment of reconfigurable components as well as the impact I/O interference has in the process and to explore non-functional trade-offs between implementations.
Referências
Falaki, H. (2012). Automating Personalized Battery Management on Smartphones. PhD thesis, UCLA.
Fröhlich, A. A. (2001). Application-Oriented Operating Systems. Number 17 in GMD Research Series. GMD - Forschungszentrum Informationstechnik, Sankt Augustin.
Li, Y., Jia, Z., Xie, S., and Liu, F. (2013). Dynamically reconfigurable hardware with a novel scheduling strategy in energy-harvesting sensor networks. IEEE Sensors Journal, 13(5):2032–2038.
Martins, V. M. G., Villa, P. R. C., Neto, H. C. C., and Bezerra, E. A. (2015). A TMR strategy with enhanced dependability features based on a partial reconfiguration flow. In Proc. IEEE Computer Society Annual Symposium on VLSI, pages 161–166.
Pant, A., Gupta, P., and van der Schaar, M. (2012). AppAdapt: Opportunistic application adaptation to compensate hardware variation. IEEE Transactions on Very Large Scale Integration Systems, 20(11):1986–1996.
Rahimi, A., Cesarini, D., Marongiu, A., Gupta, R. K., and Benini, L. (2015). Task scheduling strategies to mitigate hardware variability in embedded shared memory clusters. In Proc. Design Automation Conference (DAC)’15, DAC’15, pages 152:1–152:6, New York, NY, USA. ACM.
Reis, J. G., Wanner, L. F., and Fröhlich, A. A. (2015). X-Ware: Mutant computing substrates. In Proc. IEEE International Symposium on Rapid System Prototyping (RSP’15), Amsterdam.
Sarma, S. and Dutt, N. (2014). FPGA emulation and prototyping of a cyberphysical-system-on-chip (cpsoc). In Proc. IEEE International Symposium on Rapid System Prototyping (RSP’14), pages 121–127.
Taylor, M. B. (2012). Is dark silicon useful? harnessing the four horsemen of the coming dark silicon apocalypse. In Proc. Design Automation Conference, pages 1131–1136.
Wanner, L. and Srivastava, M. (2014). ViRUS: Virtual function replacement under stress. In Proc. USENIX Conference on Power-Aware Computing and Systems (Hot-Power’14), HotPower’14. USENIX.
