Doctor of Philosophy (PhD)
Electrical and Computer Engineering
First Committee Member
Second Committee Member
Third Committee Member
Fourth Committee Member
Fifth Committee Member
Number of Pages
Networks-on-Chip (NoCs) have emerged as the key on-chip communication architecture for multiprocessor systems-on-chip and chip multiprocessors. Single-hop non-blocking networks have the advantage of providing uniform latency and throughput, which is important for cachecoherent NoC systems. Existing work shows that Benes networks have much lower transistor count and smaller circuit area but longer delay than crossbars. To reduce the delay, we propose to design the Clos network built with larger size switches. Using less than half number of stages than the Benes network, the Clos network with 4x4 switches can significantly reduce the delay. This dissertation focuses on designing high performance Benes/Clos on-chip interconnection networks and implementing the switch setting circuits for these networks. The major contributions are summarized below:
- The circuit designs of both Benes and Clos networks in different sizes are conducted considering two types of implementation of the configurable switch: with NMOS transistors only and full transmission gates (TGs). The layout and simulation results under 45nm technology show that TG-based Benes networks have much better delay and power performance than their NMOS-based counterparts, though more transistor resources are needed in TG-based designs. Clos networks achieve average 60% lower delay than Benes networks with even smaller area and power consumption.
- The Lee’s switch setting algorithm is fully implemented in RTL and synthesized. We have refined the algorithm in data structure and initialization/updating of relation values to make it suitable for hardware implementation. The simulation and synthesis results of the switching setting circuits for 4x4 to 64x64 Benes networks under 65nm technology confirm that the trend of delay and area results of the circuit is consistent with that of the Lee’s algorithm. To the best of our knowledge, this is the first complete hardware implementation of the parallel switch setting algorithm which can handle all types of permutations including partial ones.
The results in this dissertation confirm that the Benes/Clos networks are promising solution to implement on-chip interconnection network.
Benes/Clos; Layout; Networks-on-Chip; Parallel Routing; RTL
Computer Engineering | Electrical and Computer Engineering
University of Nevada, Las Vegas
Jiang, Yikun, "Design and Implementation of Benes/Clos On-Chip Interconnection Networks" (2016). UNLV Theses, Dissertations, Professional Papers, and Capstones. 2785.
IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/