The impact of global routing on the performance of NoCs in FPGAs

With the over-provisioned routing resource on FPGA, the topology choice for NoC implementation on FPGA is more flexible than on ASIC. However, it is well understood that the global wire routing impacts the performance of NoC on FPGA because the topology is routed by using fixed routing fabric. An important question that arises is: will the benefit of diameter reduction by using a highly connective topology outweigh the impact of global routing? To answer this question, we investigate FPGA based packet switched NoC implementations with different sizes and topologies, and quantitatively measure the impact of global routing to each of these networks. The result shows that with sufficient routing resources on modern FPGA, the global routing is not on the critical path of the system, and thus is not a dominating factor for the performance of practical multi-hop NoC system. © 2011 IEEE.

Compact Routing Messages in Self-Healing Trees

Existing compact routing schemes, e.g., Thorup and Zwick [SPAA 2001] and Chechik [PODC 2013], often have no means to tolerate failures, once the system has been setup and started. This paper presents, to our knowledge, the first self-healing compact routing scheme. Besides, our schemes are developed for low memory nodes, i.e., nodes need only O(log2 n) memory, and are thus, compact schemes.
We introduce two algorithms of independent interest: The first is CompactFT, a novel compact version (using only O(log n) local memory) of the self-healing algorithm Forgiving Tree of Hayes et al. [PODC 2008]. The second algorithm (CompactFTZ) combines CompactFT with Thorup-Zwick’s treebased compact routing scheme [SPAA 2001] to produce a fully compact self-healing routing scheme. In the self-healing model, the adversary deletes nodes one at a time with the affected nodes self-healing locally by adding few edges. CompactFT recovers from each attack in only O(1) time and ∆ messages, with only +3 degree increase and O(log∆) graph diameter increase, over any sequence of deletions (∆ is the initial maximum degree).
Additionally, CompactFTZ guarantees delivery of a packet sent from sender s as long as the receiver has not been deleted, with only an additional O(y log ∆) latency, where y is the number of nodes that have been deleted on the path between s and t. If t has been deleted, s gets informed and the packet removed from the network.

Clustering-based Query Routing in Cooperative Semi-structured Peer to Peer Networks

We consider the problem of resource selection in clustered Peer-to-Peer Information Retrieval (P2P IR) networks with cooperative peers. The clustered P2P IR framework presents a significant departure from general P2P IR architectures by employing clustering to ensure content coherence between resources at the resource selection layer, without disturbing document allocation. We propose that such a property could be leveraged in resource selection by adapting well-studied and popular inverted lists for centralized document retrieval. Accordingly, we propose the Inverted PeerCluster Index (IPI), an approach that adapts the inverted lists, in a straightforward manner, for resource selection in clustered P2P IR. IPI also encompasses a strikingly simple peer-specific scoring mechanism that exploits the said index for resource selection. Through an extensive empirical analysis on P2P IR testbeds, we establish that IPI competes well with the sophisticated state-of-the-art methods in virtually every parameter of interest for the resource selection task, in the context of clustered P2P IR.

Impure Thinking Practices and Clinical Acts: The Sonorous Becomings of Heidi Fast

This article introduces the recent sound works of Heidi Fast, a Finnish voice and performance artist. Fast’s creative practice operates between art and philosophy, and articulates several ‘zones of becoming’: what Fast designates as ‘the clinical’, ‘the virtual’ and ‘vocal thought-material’. Using a methodology of routing, the article shows how these zones emerge as aesthetic, ethical and political concerns within Fast’s work. Since 2005, Fast’s sound works have variously taken shape as miniature concerts, social sculptures, imaginary soundscapes and environmental music performances. Drawing upon the writings of theorists who have helped shape her practice, this article argues that Fast uses sound and voice to propose an ‘actualising philosophy’. This philosophy actualises virtualities (unrealised potentials), affecting transformative shifts through tiny mutations in perceptions and behaviours.

Using smart people to form future mobile wireless networks

The concept of a body-to-body network, where smart communicating devices carried or worn by a person are used to form a wireless network with devices situated on other nearby persons. New innovations in this area will see the form factor of smart devices being modified, so that they may be worn on the human body or integrated into clothing, in the process creating a new generation of smart people. Applications of body-to-body networking will extend well beyond the support of cellular and Wi-Fi networks. They will also be used in short-range covert military applications, first responder applications, team sports and used to interconnect body area networks (BAN). Security will be a major issue as routing between multiple nodes will increase the risk of unauthorized access and compromise sensitive data. This will add complexity to the medium access layer (MAC) and network management. Antennas designed to operate in body centric communications systems may be broadly categorized as on- or off-body radiators, according to their radiation pattern characteristics when mounted on the human body.

Generic low-latency NoC router architecture for FPGA computing systems

A novel cost-effective and low-latency wormhole router for packet-switched NoC designs, tailored for FPGA, is presented. This has been designed to be scalable at system level to fully exploit the characteristics and constraints of FPGA based systems, rather than custom ASIC technology. A key feature is that it achieves a low packet propagation latency of only two cycles per hop including both router pipeline delay and link traversal delay - a significant enhancement over existing FPGA designs - whilst being very competitive in terms of performance and hardware complexity. It can also be configured in various network topologies including 1-D, 2-D, and 3-D. Detailed design-space exploration has been carried for a range of scaling parameters, with the results of various design trade-offs being presented and discussed. By taking advantage of abundant buildin reconfigurable logic and routing resources, we have been able to create a new scalable on-chip FPGA based router that exhibits high dimensionality and connectivity. The architecture proposed can be easily migrated across many FPGA families to provide flexible, robust and cost-effective NoC solutions suitable for the implementation of high-performance FPGA computing systems. © 2011 IEEE.

Integrated Low-Loss Passive SiGe Power Splitter and Combiner Operating Across 78-86 GHz Band

This paper describes the design, implementation, and characterization of a new type of passive power splitting and combining structure for use in a differential four-way power-combining amplifier operating at E-band. In order to achieve lowest insertion loss, input and output coils inductances are resonated with shunt capacitances. Simple C-L-C and L-C networks are proposed in order to compensate inductive loading due to routing line that would otherwise introduce mismatch and increase loss. Across 78-86 GHz band, measured insertion loss is about 7 dB. Measured return losses are >10 dB from 73 GHz to 94 GHz at the input port and >9 dB from 60 GHz to 94 GHz at the output port. When integrated with driver and power amplifier cells, the simulated complete circuit exhibits 18.2 dB gain and 20.3 dBm saturated output power.

Xheal: A localized self-healing algorithm using expanders

We consider the problem of self-healing in reconfigurable networks e.g., peer-to-peer and wireless mesh networks. For such networks under repeated attack by an omniscient adversary, we propose a fully distributed algorithm, Xheal, that maintains good expansion and spectral properties of the network, while keeping the network connected. Moreover, Xheal does this while allowing only low stretch and degree increase per node. The algorithm heals global properties like expansion and stretch while only doing local changes and using only local information. We also provide bounds on the second smallest eigenvalue of the Laplacian which captures key properties such as mixing time, conductance, congestion in routing etc. Xheal has low amortized latency and bandwidth requirements. Our work improves over the self-healing algorithms Forgiving tree [PODC 2008] andForgiving graph [PODC 2009] in that we are able to give guarantees on degree and stretch, while at the same time preserving the expansion and spectral properties of the network.