MétaCan
Menu
Back to cohort
Record W7030217835

METIS: a highly-robust fault-tolerant routing algorithm with a recursive-based path discovery scheme for 2d mesh network-on-chip-interconnected chip multi-processors

2014· dissertation· en· W7030217835 on OpenAlexaboutno aff

Bibliographic record

VenueKtisis at Cyprus University of Technology (Cyprus University of Technology) · 2014
Typedissertation
Languageen
FieldComputer Science
TopicInterconnection Networks and Systems
Canadian institutionsnot available
Fundersnot available
KeywordsRouting tableRouterNetwork packetEqual-cost multi-path routingInterconnectionStatic routingLink-state routing protocolRouting (electronic design automation)
DOInot available

Abstract

fetched live from OpenAlex

Unfortunately, however, CMOS technology down-scaling which has led to increasing transistor densities, has also made transistors operate unreliably, making them increasingly prone to breakdown and eventual failures. The same trend occurs in on-chip wires which interconnect tiles in a multi-processor such as a CMP. Physical effects such as electro-migration can break these wires apart, hence the on-chip interconnect which comes in the form a Network-on-Chip (NoC), a packet-based communication on-chip fabric, can become disconnected at various parts in its originally-designed topology. If no intelligent routing algorithm exists, which can bypass these hop-to-hop disconnections, in a 2D mesh, packets can no longer be delivered to their destinations, and as a result they may stall indefinitely in their router buffers, causing a protocol-induced global deadlock to cover the entire topology. Hence a CMP can no longer operate, and becomes completely unusable.
\nEven a single link failure may disable the entire on-chip interconnect system with the use of a routing algorithm which is oblivious to link faults. To alleviate this critical problem, in this Thesis we propose an adaptive fault-tolerant routing algorithm, called Metis, that can deliver packets to their destinations in a highly-disconnected on-chip network environment. Metis works in a recursive mode to discover paths that provide connectivity from any source-destination router pair in a 2D mesh NoC of any size. This connectivity information is stored in lookup tables found at every network router. It is able to create routing paths according to the current network state, i.e., the spatial distribution of faulty links in the network topology, which can take any form. Metis maintains full network communication connectivity as long as there is at least one routing path that connects two routers that request message exchange among them. This enables guaranteed message exchange between any pair of networks routers, albeit observed graceful performance degradation in terms of increasing latency and reduced throughput, as the number of faulty links increases.
\nIn addition, Metis achieves load-balancing in network areas where no faulty links exist, utilizing 01TURN routing, combining the usage of two dimension-order routing algorithms simultaneously: XY and YX, where the former routes first along the X dimension and then along the Y dimension, while the latter executed the reverse routing order.
\nMetis was simulated under uniform random and transpose synthetic traffic patterns, using wormhole flow-control, in order to determine its performance and behavior, utilizing two spatial faulty link placement scenarios: (1) random, and (2) hotspot faulty link distributions. When compared against ARIADNE, an existing state-of-the-art fault-tolerant routing algorithm, Metis demonstrated up to 180.0 % and 266.67% improvement in throughput with a random faulty link placement, while it showed up to 220.0% and 137.5% increase in throughput with a hotspot faulty link placement, under uniform random and transpose traffic pattern usages, respectively. Metis was also tested using the Netrace benchmark suite demonstrating up to 38.71% improvement in network packet delivery latency when compared to ARIADNE. Finally, Metis was simulated under a lightly-loaded network to determine its basic routing delay under “no stress” conditions, while further experiments exhibit its superior throughput attainment just before network saturation.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.665
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0040.003
Science and technology studies0.0010.001
Scholarly communication0.0000.001
Open science0.0050.001
Research integrity0.0030.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.010
GPT teacher head0.198
Teacher spread0.189 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2014
Admission routes1
Has abstractyes

Explore more

Same venueKtisis at Cyprus University of Technology (Cyprus University of Technology)Same topicInterconnection Networks and SystemsFrench-language works237,207