English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

With relentless CMOS technology downsizing Networks-on-Chips (NoCs) areinescapably experiencing escalating susceptibility to wearout and reducedreliability. While faults in processors and memories may be masked viaredundancy, or mitigated via techniques such as task migration, NoCs areespecially vulnerable to hardware faults as a single link breakdown may causeinter-tile communication to halt indefinitely, rendering the whole multicorechip inoperable. As such, NoCs impose the risk of becoming the pivotal point offailure in chip multicores that utilize them. Aiming towards seamless NoCoperation in the presence of faulty links we propose Hermes, a near-idealfault-tolerant routing algorithm that meets the objectives of exhibiting highlevels of robustness, operating in a distributed mode, guaranteeing freedomfrom deadlocks, and evening-out traffic, among many. Hermes is alimited-overhead deadlock-free hybrid routing algorithm, utilizingload-balancing routing on fault-free paths to sustain high-throughput, whileproviding pre-reconfigured escape path selection in the vicinity of faults.Under such online mechanisms, Hermes's performance degrades gracefully withincreasing faulty link counts, a crucially desirable response lacking inprior-art. Additionally, Hermes identifies non-communicating network partitionsin scenarios where faulty links are topologically densely distributed such thatpackets being routed to physically isolated regions cause no network stagnationdue to indefinite chained blockages starting at sub-network boundaries. Anextensive experimental evaluation, including utilizing traffic workloadsgathered from full-system chip multi-processor simulations, shows that Hermesimproves network throughput by up to $3\times$ when compared against thestate-of-the-art. Further, hardware synthesis results prove Hermes's efficacy.

Design of a Near-Ideal Fault-Tolerant Routing Algorithm for Network-on-Chip-Based Multicores