Yield Maximization for System-level Task Assignment and Configuration Selection of Configurable MultiProcessors

Configurable multiprocessor system is a promising design alter-native because of its high degree of flexibility, short development time, and potentially high performance under constraints and chal-lenges driven by applications. An important design challenge at 45nm for multi-core system is manufacturing process variation. Due to increasing concern of WID variation, designers will have to choose configurations of processing cores that maximize yield of the system while not affecting performance and throughput con-straints. Due to interdependency between processor configuration selection and task allocation and its impact on yield and latency constraints, we tackle both problems simultaneously. In this paper, we propose the problem of task allocation and configuration selec-tion for yield optimization. We prove the problem is NP-hard and propose an optimal pseudo-polynomial on Serial-Parallel graphs. We target streaming applications in pipelined reconfigurable multi-processor systems. We provide a case study of configurable Leon processors as the cores implemented on FPGA. Results show that proposed problem could result in significant improvement of the timing yield of the system by exploiting extra slack on tasks. Categories and Subject Descriptors: C.4 [Performance of Sys-tems]: Reliability, availability, and serviceability; C.3 [Special-Purpose and Application-Based Systems]: Real-time and embed-ded system