kth.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Improving Cloud Storage Network Bandwidth Utilization of Scientific Applications
University of Edinburgh, United Kingdom.
RIKEN Center for Computational Science Japan.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Datavetenskap, Programvaruteknik och datorsystem, SCS.ORCID-id: 0000-0001-5452-6794
KTH, Skolan för elektroteknik och datavetenskap (EECS), Centra, Parallelldatorcentrum, PDC.ORCID-id: 0000-0002-5020-1631
Visa övriga samt affilieringar
2023 (Engelska)Ingår i: Proceedings of the 7th Asia-Pacific Workshop on Networking, APNET 2023, Association for Computing Machinery (ACM) , 2023, s. 172-173Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Cloud providers began to provide managed services to attract scientific applications, which have been traditionally executed on supercomputers. One example is AWS FSx for Lustre, a fully managed parallel file system (PFS) released in 2018. However, due to the nature of scientific applications, the frontend storage network bandwidth is left completely idle for the majority of its lifetime. Furthermore, the pricing model does not match the scalability requirement. We propose iFast, a novel host-side caching mechanism for scientific applications that improves storage bandwidth utilization and end-to-end application performance: by overlapping compute and data writeback through inexpensive local storage. iFast supports the Massage Passing Interface (MPI) library that is widely used by scientific applications and is implemented as a preloaded library. It requires no change to applications, the MPI library, or support from cloud operators. We demonstrate how iFast can accelerate the end-to-end time of a representative scientific application Neko, by 13-40%.

Ort, förlag, år, upplaga, sidor
Association for Computing Machinery (ACM) , 2023. s. 172-173
Nationell ämneskategori
Datorsystem Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:kth:diva-338993DOI: 10.1145/3600061.3603122ISI: 001147804500029Scopus ID: 2-s2.0-85173833099OAI: oai:DiVA.org:kth-338993DiVA, id: diva2:1808729
Konferens
7th Asia-Pacific Workshop on Networking, APNET 2023, Jun 29 - Jun 30 2023, Hong Kong, China,
Anmärkning

Part of ISBN 9798400707827

QC 20231101

Tillgänglig från: 2023-11-01 Skapad: 2023-11-01 Senast uppdaterad: 2024-02-27Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Podobas, ArturJansson, NiclasMarkidis, Stefano

Sök vidare i DiVA

Av författaren/redaktören
Podobas, ArturJansson, NiclasMarkidis, Stefano
Av organisationen
Programvaruteknik och datorsystem, SCSParallelldatorcentrum, PDCBeräkningsvetenskap och beräkningsteknik (CST)
DatorsystemDatavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 43 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf