MétaCan
← tous les travaux

TIAS: Two-level Information-Agnostic Job Scheduling in GPU Clusters

2021· article· en· 2 citations· W4285337568 sur OpenAlex· 10.1109/insai54028.2021.00041

Pourquoi ce travail est-il dans la base ?

Une base qui oublie comment elle a trouvé un travail ne peut pas être vérifiée. Voici les voies qui ont admis celui-ci.

Affiliation canadienneUne personne signataire a déclaré un établissement canadien. C'est la seule voie dont dispose la base habituelle.

Le tri à trois modèles

les 1 000 travaux triés →

Les trois modèles l'ont jugé hors champ.

strate : aff_core · poids de sondage : 5595.24 (l'échantillon est stratifié ; tout taux calculé sans le poids est faux)
Claude Opus 4.8OUT
genre : empirical
porte sur le Canada: non
confiance: high

GPU cluster job scheduling algorithm for deep learning workloads; a computer systems contribution, not a study of research.

GPT-5.6 (high)OUT
genre : empirical
porte sur le Canada: non
confiance: high

The work studies GPU job scheduling for machine-learning workloads, not research as a system or practice.

Grok 4.5OUT
genre : empirical
porte sur le Canada: non
confiance: high

Systems paper on GPU-cluster job scheduling for deep learning workloads, not study of research practice.

Résumé

In recent years, deep learning algorithms have shown a trend towards larger models and larger datasets. Centralized training is unable keep up with the training requirements due to limited storage and computing resources, thus distributed learning is becoming an important area of research for improving learning efficiency. There are many studies on using the features of deep learning workload to design a central scheduler for production clusters.While existing work has been focusing on overall completion time and resource efficiency, little attention has been paid to the execution deadlines. To achieve a balance between the goals of deadline and non-deadline jobs, we design a Two-level Information-Agnostic Scheduling strategy(TIAS), which can schedule the two kinds of jobs together without knowing jobs’ training duration. In the first level, we use different priority calculation methods for the two kinds of jobs; in the second level, we design a new indicator "queue urgency" based on three observations to sort deadline jobs within the same queue. Experiments on a trace-driven simulator prove that TIAS can achieve the best trade-off between deadline miss rate and non-deadline jobs’ average job completion time(JCT) compared to existing solutions.

Conservé avec la notice de tri, où il sert de preuve aux étiquettes ci-dessus.

La notice

Revue
Thématique
Distributed and Parallel Computing Systems
Domaine
Computer Science
Établissements canadiens
University of Toronto
Organismes subventionnaires
Mots-clés
Computer scienceScheduling (production processes)Processor schedulingParallel computingGPU clusterJob schedulerCUDAOperating systemMathematical optimizationCloud computingMathematics
Résumé présent dans OpenAlex
oui