DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kwon, Youngeun | ko |
dc.contributor.author | Lee, Yunjae | ko |
dc.contributor.author | Rhu, Minsoo | ko |
dc.date.accessioned | 2019-11-22T02:20:11Z | - |
dc.date.available | 2019-11-22T02:20:11Z | - |
dc.date.created | 2019-11-22 | - |
dc.date.created | 2019-11-22 | - |
dc.date.created | 2019-11-22 | - |
dc.date.created | 2019-11-22 | - |
dc.date.issued | 2019-10-15 | - |
dc.identifier.citation | The 52nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pp.740 - 753 | - |
dc.identifier.uri | http://hdl.handle.net/10203/268520 | - |
dc.description.abstract | Recent studies from several hyperscalars pinpoint to embedding layers as the most memory-intensive deep learning (DL) algorithm being deployed in today's datacenters. This paper addresses the memory capacity and bandwidth challenges of embedding layers and the associated tensor operations. We present our vertically integrated hardware/software co-design, which includes a custom DIMM module enhanced with near-memory processing cores tailored for DL tensor operations. These custom DIMMs are populated inside a GPU-centric system interconnect as a remote memory pool, allowing GPUs to utilize for scalable memory bandwidth and capacity expansion. A prototype implementation of our proposal on real DL systems shows an average 6.2-17.6× performance improvement on state-of-the-art DNN-based recommender systems. | - |
dc.language | English | - |
dc.publisher | IEEE/ACM | - |
dc.title | TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000519057400055 | - |
dc.identifier.scopusid | 2-s2.0-85074452476 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 740 | - |
dc.citation.endingpage | 753 | - |
dc.citation.publicationname | The 52nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Greater Columbus Convention Center, Columbus, OH | - |
dc.identifier.doi | 10.1145/3352460.3358284 | - |
dc.contributor.localauthor | Rhu, Minsoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.