DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hyun, Bongjoon | ko |
dc.contributor.author | Kwon, Youngeun | ko |
dc.contributor.author | Choi, Yujeong | ko |
dc.contributor.author | Kim, John Dongjun | ko |
dc.contributor.author | Rhu, Minsoo | ko |
dc.date.accessioned | 2020-09-18T04:17:17Z | - |
dc.date.available | 2020-09-18T04:17:17Z | - |
dc.date.created | 2020-08-12 | - |
dc.date.created | 2020-08-12 | - |
dc.date.issued | 2020-03-20 | - |
dc.identifier.citation | The 25th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS-25), pp.1109 - 1124 | - |
dc.identifier.uri | http://hdl.handle.net/10203/276229 | - |
dc.description.abstract | To satisfy the compute and memory demands of deep neural networks (DNNs), neural processing units (NPUs) are widely being utilized for accelerating DNNs. Similar to how GPUs have evolved from a slave device into a mainstream processor architecture, it is likely that NPUs will become first-class citizens in this fast-evolving heterogeneous architecture space. This paper makes a case for enabling address translation in NPUs to decouple the virtual and physical memory address space. Through a careful data-driven application characterization study, we root-cause several limitations of prior GPU-centric address translation schemes and propose a memory management unit (MMU) that is tailored for NPUs. Compared to an oracular MMU design point, our proposal incurs only an average 0.06% performance overhead. | - |
dc.language | English | - |
dc.publisher | ACM | - |
dc.title | NeuMMU: Architectural Support for Efficient Address Translations in Neural Processing Units | - |
dc.type | Conference | - |
dc.identifier.wosid | 000541369300070 | - |
dc.identifier.scopusid | 2-s2.0-85082394185 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1109 | - |
dc.citation.endingpage | 1124 | - |
dc.citation.publicationname | The 25th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS-25) | - |
dc.identifier.conferencecountry | SZ | - |
dc.identifier.conferencelocation | Lausanne | - |
dc.identifier.doi | 10.1145/3373376.3378494 | - |
dc.contributor.localauthor | Kim, John Dongjun | - |
dc.contributor.localauthor | Rhu, Minsoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.