Processing in Memory: Opportunities and Challenges

Speaker:  Mohamed Zahran – New York, NY, United States
Topic(s):  Applied Computing

Abstract

One of the main factors that negatively affects performance and power consumption of a computer system is communication. That is, moving data from one point to another, especially among cores or from storage to memory hierarchy to cores. This problem is due to the fact that we move the data to the computation. How about the other way around: moving the computation to the data? This is called near-data processing (NDP) or processing-in-memory (PIM). In this talk, we will discuss the enabling technology for this new design, the opportunities NDP/PIM offers, and the challenges we need to deal with in order to get the best performance per watt. 

About this Lecture

Number of Slides:  40
Duration:  60 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.