search

mental2008 / awesome-papers

Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and other interesting stuffs).
https://paper.lingyunyang.com/
MIT License
38 stars 2 forks source link

ASPLOS '22 | Astraea: Towards QoS-Aware and Resource-Efficient Multi-stage GPU Services #73

Closed mental2008 closed 1 year ago

mental2008 commented 2 years ago

To appear in ASPLOS '22.

gaocegege commented 2 years ago

The paper focuses on GPU microservices. But I am not sure what the GPU microservice is. Does it include GPU encoding/decoding job, gene computing or others?

mental2008 commented 2 years ago

The paper focuses on GPU microservices. But I am not sure what the GPU microservice is. Does it include GPU encoding/decoding job, gene computing or others?

You can refer to the previous version (Section III. A) in arXiv, which may be slightly different from the camera-ready version.

As far as I know, this work mainly focuses on DL applications such as text-to-image, text-to-video, speech-to-text. It seems to only use the GPU's computing resource and memory. The encoding/decoding capability is unused.

gaocegege commented 2 years ago

Gotcha thanks!