• Stars
    star
    224
  • Rank 177,753 (Top 4 %)
  • Language
  • Created almost 3 years ago
  • Updated 9 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Awesome-DL-Scheduling-Papers

A curated list of DL cluster scheduling papers.

Please feel free to pull requests or open an issue to add papers.

Schedulers for DL training

Scheduler Year Series Paper Objective Heter. Elastic AutoML Code
Synergy 2022 OSDI Paper ♣ - - - -
Singularity 2022 arxiv Paper ♠♣♦ - ✔ - -
GADGET 2022 INFOCOM Paper ♠♣ - ✔ - Code
EDL 2022 TPDS Paper ♠♣ - ✔ - -
Aryl 2022 arxiv Paper ♠♣ - ✔ ✔ -
AOnline 2022 TCC Paper ♠♣ - ✔ - -
Ali-MLaaS 2022 NSDI Paper ♠♣ - - - Code
SMD 2021 INFOCOM Paper ♣ - - - -
SEER 2021 SoCC Paper ▲ - ✔ ✔ -
RubberBand 2021 EuroSys Paper ♦ - ✔ ✔ -
POP 2021 SOSP Paper ♥♣ ✔ - - Code
Pollux 2021 OSDI Paper ♠♣♥ - ✔ ✔ Code
ONES 2021 SC Paper ♠♣ - ✔ - Code
Liquid 2021 TPDS Paper ♣ - - - Code
Jigsaw 2021 DistributedML Paper ♣ - - - -
Horus 2021 TPDS Paper ♠♣ - - - -
Hermes 2021 Electronics Paper ♣ - - ✔ -
Helios 2021 SC Paper ♣♦ - - - Code
DynamoML 2021 CLOSER Paper ♠♣ - ✔ - -
Chronus 2021 SoCC Paper ✿ - - - Code
Astraea 2021 TPDS Paper ♥ - - - Code
ANDREAS 2021 FCloud Paper ♦ - - - -
AFS 2021 NSDI Paper ♠♣ - ✔ - -
$DL^2$ 2021 TPDS Paper ♣ - ✔ - Code
Yeung 2020 HotCloud Paper â™  - - - -
Vaibhav et al. 2020 MASCOTS Paper ♠♣ - ✔ - -
Themis 2020 NSDI Paper ♥ - - - -
SPIN 2020 INFOCOM Paper ♣ - - - -
Salus 2020 MLSys Paper ♠♣ - - - Code
Parrot 2020 TCC Paper ♣ - - - -
Non-Intrusive 2020 SC Paper ♠♣ - ✔ - -
MLFS 2020 CoNext Paper ♣✿ - - - Code
MLCloudPrice 2020 DISPA Paper ♣♦ - - - Code
MARBLE 2020 CCGRID Paper ♠♣ - ✔ - -
HiveD 2020 OSDI Paper ♣ - - - Code
GENIE 2020 TPDS Paper ✿ - ✔ - -
Gavel 2020 OSDI Paper ♣♥ ✔ - - Code
E-LAS 2020 ICPP Paper ♣ - - - -
Elan 2020 ICDCS Paper ♠♣ - ✔ - -
Co-scheML 2020 ACSOS Paper ♣ - - - -
CODA 2020 ICDCS Paper ♣ ✔* - - -
Antman 2020 OSDI Paper ♠♣ - ✔ - Code
Ada-SRSF 2020 arxiv Paper ♣ ✔* - - -
$Gandiva_{fair}$ 2020 EuroSys Paper ♥♣ ✔ - - -
Tiresias 2019 NSDI Paper ♣ - - - Code
Philly 2019 ATC Paper ♣ - - - Code
JPAS 2019 JNCA Paper ♣▲ - - ✔ -
Jahani 2019 ICCCS Paper ♦ ✔ ✔ - -
HyperSched 2019 SoCC Paper ✿ ▲ - ✔ ✔ -
Harmony 2019 INFOCOM Paper ♣ - - - -
FfDL 2019 Middleware Paper ♣ - - - Code
Dragon 2019 CLOSER Paper ♠♣ - ✔ - -
Cynthia 2019 ICPP Paper ♦ - ✔ - -
$Sched^2$ 2019 GLOBECOM Paper ♣ - - - -
$FC^2$ 2019 CC Paper ♦ ✔* ✔ - -
Optimus 2018 EuroSys Paper ♣ - ✔ - Code
OASiS 2018 INFOCOM Paper ♠♣ - ✔ - -
Gandiva 2018 OSDI Paper ♠♣ - ✔ ✔ -
Topology-Aware 2017 SC Paper ♣ - - - Code
HyperDrive 2017 Middleware Paper ♣▲ - - ✔ -
Dorm 2017 SMARTCOMP Paper ♥ - - - -

JCT: ♣ Utilization: ♠ Cost: ♦ Fairness: ♥ DDL: ✿ Accuracy: ▲

Schedulers for DL Inference

Scheduler Year Series Paper Objective Batch Share Cloud Source Code
Cocktail 2022 NSDI Paper ♣♦♥ - - ✔ -
INFaaS 2021 ATC Paper ♦♥♠ - ✔ ✔ Code
Mendoza et al. 2021 EuroMLSys Paper ♦ - ✔ - -
Morphling 2021 SoCC Paper ♥♠ ✔ ✔ ✔ Code
Abacus 2021 SC Paper ♦♠ - ✔ - Code
MIG-SERVING 2021 CoRR Paper ♦♥ ✔ ✔ - -
GSLICE 2020 SoCC Paper ♠✿ ✔ ✔ - -
Clockwork 2020 OSDI Paper ♦♠ ✔ - - Code
CMS 2020 Future Internet Paper ♣✿ - - - -
Irina 2020 APNet Paper ♦♠✿ ✔ ✔ - -
PERSEUS 2020 IC2E Paper ♦♥♠ ✔ - ✔ Code
AutoDeep 2020 Infocom Paper ♦♥♠ - ✔ ✔ -
DyBatch 2020 CCGrid Paper ♦♠ ✔ ✔ - -
Inferline 2020 SoCC Paper ♦♥ ✔ - ✔ Code
MArk 2019 ATC Paper ♦♥ ✔ - ✔ Code
Tolerance Tiers 2019 ISPASS Paper ♣♦♥ - - ✔ -
ParM 2019 SOSP Paper ♦ ✔ - - Code
Gilman et al. 2019 DIDL Paper ♦♠ - ✔ - -
Nanily 2019 HPCC Paper ♦♠ ✔ - - -
RRL 2019 SC Paper ♦ ✔ ✔ - Code
Kube-Knots 2019 CLUSTER Paper ♦✿ ✔ ✔ - -
TrIMS 2019 CLOUD Paper ♦♠✿ ✔ ✔ ✔ Code
Ebird 2019 ICCD Paper ♦♠✿ ✔ ✔ - Code
Rafiki 2018 VLDB Paper ♣♦ ✔ - - Code
Space-Time 2018 NIPS Paper ♠✿ ✔ ✔ - -
Ease.ml 2018 VLDB Paper ♣ - - - Code
HiveMind 2018 NIPS Paper ♠ ✔ ✔ - -
Clipper 2017 NSDI Paper ♣♦♠ ✔ - - Code

Accuracy: ♣ Throughput: ♠ Latency: ♦ Cost: ♥ Utilization: ✿

Gloosary of Terms

Terminology Definition
JCT Job Completion Time (Job Finish Time - Job Submission Time)
Fairness a metric to assess whether resources are fairly shared among users or jobs
QoS Quality of Service
DDL Deadline, a time point where DL job must be completed
SLO Service Level Objective