CAMeleon: Reconfigurable B(T)CAM in Computational RAM
CAMeleon: Reconfigurable B(T)CAM in Computational RAM
复制标题
DOI：
10.1145/3453688.3461507
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Z. Chowdhury;Salonik Resch;Husrev Cilasun;Zhengyang Zhao;Masoud Zabihi;Sachin S. Sapatnekar;Jianping Wang;Ulya R. Karpuzcu
中科院分区：
文献类型：
--
作者：
Z. Chowdhury;Salonik Resch;Husrev Cilasun;Zhengyang Zhao;Masoud Zabihi;Sachin S. Sapatnekar;Jianping Wang;Ulya R. Karpuzcu
嵌入式/边缘计算伴随着非常严格的硬件资源(面积)预算和对极高能效的需求。这促使重新调整用途，即按需重新配置硬件资源，其中重新配置本身的开销在面积和能源效率方面受到非常紧张的预算的影响。在可穿戴设备和物联网等资源受限环境中运行的许多应用程序都将CAM(内容可寻址存储器)作为关键的计算构建块。在本文中，我们介绍了Cameleon--一种新型的节能计算基板，它可以无缝地重新配置，除了逻辑和存储功能外，还可以执行CAM操作。Cameleon具有与基于SRAM和新兴存储器技术(如STT-MTJ、ReRAM和PCM)的传统CAM设计类似的延迟水平，但是，由于其可重新配置，它可以更高效地执行CAM操作，消耗更少的面积，并可以支持传统的逻辑和存储功能，而不是CAM操作。
Embedded/edge computing comes with a very stringent hardware resource (area) budget and a need for extreme energy efficiency. This motivates repurposing, i.e., reconfiguring hardware resources on demand, where the overhead of reconfiguration itself is subject to the very same tight budgets in area and energy efficiency. Numerous applications running on resource constrained environments such as wearable devices and Internet-of-Things incorporate CAM (Content Addressable Memory) as a key computational building block. In this paper we present CAMeleon -- a novel energy-efficient compute substrate which can seamlessly be reconfigured to perform CAM operations in addition to logic and memory functions. CAMeleon has a similar level of latency to conventional CAM designs based on SRAM and emerging memory technologies (such as STT-MTJ, ReRAM and PCM), however, performs CAM operations more energy-efficiently, consumes less area, and can support traditional logic and memory functions beyond CAM operations on demand thanks to its reconfigurability.