Logo des Repositoriums
 

Full-Scale File System Acceleration on GPU

dc.contributor.authorMaucher, Peter
dc.contributor.authorKittner, Lennard
dc.contributor.authorRath,Nico
dc.contributor.authorLucka,Gregor
dc.contributor.authorWerling,Lukas
dc.contributor.authorKhalil,Yussuf
dc.contributor.authorGröninger,Thorsten
dc.contributor.authorBellosa,Frank
dc.date.accessioned2024-03-15T09:53:15Z
dc.date.available2024-03-15T09:53:15Z
dc.date.issued2024
dc.description.abstractModern HPC and AI Computing solutions regularly use GPUs as their main source of computational power. This creates a significant imbalance for storage operations for GPU applications, as every such storage operation has to be signalled to and handled by the CPU. In GPU4FS, we propose a radical solution to this imbalance: Move the file system implementation to the application, and run the complete file system on the GPU. This requires multiple changes to the complete file system stack, from the actual storage layout up to the file system interface. Additionally, this approach frees the CPU from file system management tasks, which allows for more meaningful usage of the CPU. In our pre- liminary implementation, we show that a fully-featured file system running on GPU with minimal CPU interaction is possible, and even bandwidth-competitive depending on the underlying storage medium.en
dc.identifier.doi10.18420/fgbs2024f-03
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/43802
dc.language.isoen
dc.pubPlaceBonn
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofTagungsband des FG-BS Frühjahrstreffens 2024
dc.subjectFile System
dc.subjectGPU
dc.subjectDirect Storage Access
dc.subjectGPU-Acceleration
dc.subjectGPU-Offloading
dc.titleFull-Scale File System Acceleration on GPUen
dc.typeText
gi.conference.date14.-15. März 2024
gi.conference.locationBochum, Deutschland

Dateien

Originalbündel
1 - 1 von 1
Lade...
Vorschaubild
Name:
Paper03.pdf
Größe:
436.19 KB
Format:
Adobe Portable Document Format