Small
n
x
n
switches are key components of multistage interconnection networks used in multiprocessors as well as in the communication coprocessors used in multicomputers. The design of the internal buffers in these switches is of critical importance for achieving high throughput low latency communication. We discuss several buffer structures and compare them in terms of implementation complexity and their ability to deal with variations in traffic patterns and message lengths. We present a new design of buffers that provide non-FIFO message handling and efficient storage allocation for variable size packets through the use of linked lists managed by a simple on-chip controller. We evaluate the new buffer design by comparing it to several alternative designs in the context of a multi-stage interconnection network. Our modeling and simulations show that the new buffer outperforms its “competition” and can thus be used to improve the performance of a wide variety of systems currently using less efficient buffers.
Small n ×n switches are key components of multistage interconnection networks used in multiprocessors as well as in the communication coprocessors used in multicomputers. The design of the internal buffers in these switches is of critical importance for achieving high throughput low latency communication. We discuss several buffer structures and compare them in terms of implementation complexity and their ability to deal with variations in traffic patterns and message lengths. We present a new design of buffers that provide non-FIFO message handling and efficient storage allocation for variable size packets through the use of linked lists managed by a simple on-chip controller. We evaluate the new buffer design by comparing it to several alternative designs in the context of a multi-stage interconnection network. Our modeling and simulations show that the new buffer outperforms its ''competition'' and can thus be used to improve the performance of a wide variety of systems currently using less efficient buffers.
The Introduction-Based Routing Protocol (IBRP) leverages implicit trust relationships and per-node discretion to create incentives to avoid associating with misbehaving network participants. Nodes exercise discretion through their policies for offering or accepting introductions. We empirically demonstrate the robustness of IBRP against different attack scenarios. We also use empirical game-theoretic techniques to assess the strategic stability of compliant policies, and find preliminary evidence that IBRP encourages the adoption of policies that limit damage from misbehaving nodes. We argue that IBRP scales to Internet-sized networks, and can be deployed as an overlay on the current Internet, requiring no modifications to applications, operating systems or core network services, thus minimizing cost of adoption.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.