Lightning Talk: Model, Framework and Integration for In-Storage Computing with Computational SSDs

被引：0

作者：

Wang, Tianyu ^{[1
]}

Xue, Jin ^{[1
]}

Du, Zelin ^{[1
]}

Wang, Zhiqi ^{[1
]}

Cui, Yaotian ^{[1
]}

Shao, Zili ^{[1
]}

机构：

[1] Chinese Univ Hong Kong, Dept Comp Sci & Engn, Hong Kong, Peoples R China

来源：

2023 60TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC | 2023年

关键词：

In-Storage Computing; Computational SSD; Flash Translation Layer; Multi-core SSD Firmware;

D O I：

10.1109/DAC56929.2023.10247955

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In-storage computing with computational SSDs is emerging as one effective solution for I/O bottlenecks in big data applications such as AI learning model training. Specifically, with in-SSD computing, computation can be pushed down to SSDs and the volume of the output data that will be transferred back to the host can be greatly reduced. However, there are several fundamental issues for applications to fully exploit in-SSD computing with simple and efficient function offloading. In this paper, we present three challenges for in-SSD computing, namely, data model, programming framework, and storage/computing integration, and discuss possible research directions.

引用

页数：2