Computing with Near Data

Xulong Tang, Mahmut Taylan Kandemir, Hui Zhao, Myoungsoo Jung, Mustafa Karakoy

Research output: Contribution to journalArticlepeer-review

Abstract

The cost of moving data between compute elements and storage elements plays a signiicant role in shaping the overall performance of applications.We present a compiler-driven approach to reducing data movement costs. Our approach, referred to as Computing with Near Data (CND), is built upon a concept called 'recomputation', in which a costly data access is replaced by a few less costly data accesses plus some extra computation, if the cumulative cost of the latter is less than that of the costly data access. Experimental result reveals that i) the average recomputability across our benchmarks is 51.1%, ii) our compiler-driven strategy is able to exploit 79.3% of the recomputation opportunities presented by our workloads, and iii) our enhancements increase the value of the recomputability metric signiicantly.

Original languageEnglish
Pages (from-to)27-28
Number of pages2
JournalPerformance Evaluation Review
Volume47
Issue number1
DOIs
Publication statusPublished - 2019 Dec 17

Bibliographical note

Funding Information:
We thank Evgenia Smirni for shepherding our paper. We also thank the anonymous reviewers for their constructive feedback. Myoungsoo Jung is in part supported by NRF 2016R1C1B2015312, DOE DEAC02-05CH11231, IITP-2018-2017-0-01015, NRF 2015M3C4A7065645, Yonsei Future Research Grant (2017-22-0105) and Samsung grant (2018). This research is supported in part by NSF grants #1526750, #1763681, #1439057, #1439021, #1629129, #1409095, #1626251, #1629915, and a grant from Intel.

Publisher Copyright:
© 2019 Copyright is held by the owner/author(s).

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Computing with Near Data'. Together they form a unique fingerprint.

Cite this