Slides available here!

Speaker:

Qiong Cai, HP Labs, USA

Title:

Converging memory and storage for Big Data Applications

Abstract:

Non-Volatile Memory (NVM) technologies, such as memristor, are getting more mature to replacement or augment DRAM in large scale computing systems. NVM also provides high capacity and long data retention time so that it can be used as a replacement for the traditional storage tier. In this talk, we will describe several architecture options to converge memory and storage systems. We will also discuss opportunities and challenges when we have a flat, converged memory and storage system. Finally we will present how HP Labs is approaching this problem in The Machine project.

Bio:

Qiong Cai is a senior researcher in HP Labs, working on the architecture for The Machine project. In the past, he was the technical lead on NVM-based memory systems in Intel Labs Barcelona. He has also participated different research and product projects related to compiler optimizer, power-efficient multi-core architectures and programmable accelerators in the past 10 years.



* If you wish to modify any information or update your photo, please contact the web chairmpsoc2014@imag.fr