Challenges and Opportunities: From Near-memory Computing to In-memory Computing (invited)

Challenges and Opportunities: From Near-memory Computing to In-memory Computing (invited). KhoramS, S., ZhaS, Y., ZhangS, J., & Li, J. In Proceedings of the 2017 ACM on International Symposium on Physical Design, of ISPD '17, pages 43–46, New York, NY, USA, Mar, 2017. ACM.

Paper doi abstract bibtex

The confluence of the recent advances in technology and the ever-growing demand for large-scale data analytics created a renewed interest in a decades-old concept, processing-in-memory (PIM). PIM, in general, may cover a very wide spectrum of compute capabilities embedded in close proximity to or even inside the memory array. In this paper, we present an initial taxonomy for dividing PIM into two broad categories: 1) Near-memory processing and 2) In-memory processing. This paper highlights some interesting work in each category and provides insights into the challenges and possible future directions.

@inproceedings{Khoram2017ISPD,
 author = {Khoram<sup>S</sup>, Soroosh and Zha<sup>S</sup>, Yue and Zhang<sup>S</sup>, Jialiang and Li, Jing},
 title = {Challenges and Opportunities: From Near-memory Computing to In-memory Computing (<strong>invited</strong>)},
 booktitle = {Proceedings of the 2017 ACM on International Symposium on Physical Design},
 series = {<strong>ISPD</strong> '17},
 year = {2017},
 month = {Mar},
 date={2017-03-19},
 isbn = {978-1-4503-4696-2},
 location = {Portland, Oregon, USA},
 pages = {43--46},
 numpages = {4},
 url = {http://doi.acm.org/10.1145/3036669.3038242},
 doi = {10.1145/3036669.3038242},
 acmid = {3038242},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {conference, 3d integration, in-memory processing, near-memory processing, nonvolatile memory},
 abstract={The confluence of the recent advances in technology and the ever-growing demand for large-scale data analytics created a renewed interest in a decades-old concept, processing-in-memory (PIM). PIM, in general, may cover a very wide spectrum of compute capabilities embedded in close proximity to or even inside the memory array. In this paper, we present an initial taxonomy for dividing PIM into two broad categories: 1) Near-memory processing and 2) In-memory processing. This paper highlights some interesting work in each category and provides insights into the challenges and possible future directions.},
% note = {(Acceptance Rate*: <u>35\%</u>)}
}

Downloads: 0