Duality cache for data parallel acceleration

Daichi Fujiki, Scott Mahlke, Reetuparna Das

研究成果: Conference contribution

36 被引用数 (Scopus)

抄録

Duality Cache is an in-cache computation architecture that enables general purpose data parallel applications to run on caches. This paper presents a holistic approach of building Duality Cache system stack with techniques of performing in-cache floating point arithmetic and transcendental functions, enabling a data-parallel execution model, designing a compiler that accepts existing CUDA programs, and providing flexibility in adopting for various workload characteristics. Exposure to massive parallelism that exists in the Duality Cache architecture improves performance of GPU benchmarks by 3.6× and OpenACC benchmarks by 4.0× over a server class GPU. Re-purposing existing caches provides 72.6× better performance for CPUs with only 3.5% of area cost. Duality Cache reduces energy by 5.8× over GPUs and 21× over CPUs.

本文言語English
ホスト出版物のタイトルISCA 2019 - Proceedings of the 2019 46th International Symposium on Computer Architecture
出版社Institute of Electrical and Electronics Engineers Inc.
ページ397-410
ページ数14
ISBN(電子版)9781450366694
DOI
出版ステータスPublished - 2019 6月 22
外部発表はい
イベント46th International Symposium on Computer Architecture, ISCA 2019 - Phoenix, United States
継続期間: 2019 6月 222019 6月 26

出版物シリーズ

名前Proceedings - International Symposium on Computer Architecture
ISSN(印刷版)1063-6897

Conference

Conference46th International Symposium on Computer Architecture, ISCA 2019
国/地域United States
CityPhoenix
Period19/6/2219/6/26

ASJC Scopus subject areas

  • ハードウェアとアーキテクチャ

フィンガープリント

「Duality cache for data parallel acceleration」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル