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
Notice bibliographique
Résumé
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.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction distillée sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Apprise à partir de 10 348 étiquettes directes de Codex et de 10 348 étiquettes directes de Gemma. Le mode candidate est l'union des têtes enseignantes seuillées; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont ni des étiquettes humaines ni des étiquettes directes de modèles de pointe.
Scores Codex et Gemma par catégorie
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,001 | 0,000 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,002 | 0,001 |
| Bibliométrie | 0,004 | 0,003 |
| Études des sciences et des technologies | 0,001 | 0,001 |
| Communication savante | 0,000 | 0,001 |
| Science ouverte | 0,005 | 0,001 |
| Intégrité de la recherche | 0,003 | 0,001 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,000 | 0,000 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule tête enseignante, pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».