Pith. sign in

REVIEW

Supporting Massive DLRM Inference Through Software Defined Memory

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.11489 v2 pith:GQAP472C submitted 2021-10-21 cs.AR cs.LG

Ehsan K. Ardestani , Changkyu Kim , Seung Jae Lee , Luoshang Pan , Valmiki Rampersad , Jens Axboe , Banit Agrawal , Fuxun Yu
show 12 more authors
Ansha Yu Trung Le Hector Yuen Shishir Juluri Akshat Nanda Manoj Wodekar Dheevatsa Mudigere Krishnakumar Nair Maxim Naumov Chris Peterson Mikhail Smelyanskiy Vijay Rao
This is my paper · ORCID
classification cs.ARcs.LG
keywords dlrmmemorydefinedinferencepowersoftwareaccountcenter
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep Learning Recommendation Models (DLRM) are widespread, account for a considerable data center footprint, and grow by more than 1.5x per year. With model size soon to be in terabytes range, leveraging Storage ClassMemory (SCM) for inference enables lower power consumption and cost. This paper evaluates the major challenges in extending the memory hierarchy to SCM for DLRM, and presents different techniques to improve performance through a Software Defined Memory. We show how underlying technologies such as Nand Flash and 3DXP differentiate, and relate to real world scenarios, enabling from 5% to 29% power savings.

Discussion (0). Continue with ORCID to comment.

Pith tools