CeMux: Maximizing the Accuracy of Stochastic Mux Adders and an Application to Filter Design

CeMux: Maximizing the Accuracy of Stochastic Mux Adders and an Application to Filter Design
复制标题

CeMux:最大化随机复用加法器的精度及其在滤波器设计中的应用

DOI:
10.1145/3491213
复制
发表时间:
2022
影响因子:
1.4
通讯作者:
Hayes, John P.
Hayes, John P.
中科院分区:
计算机科学4区
文献类型:
--
作者:
Baker, Timothy J.;Hayes, John P.

文献摘要

参考文献

被引文献

相似文献

随机计算(SC)是一种低成本计算范式,在数字滤波器设计、图像处理和神经网络中具有广阔的应用前景。这些应用程序的基础是加权加法运算,该运算通常由多路复用器 (mux) 树实现。基于多路复用器的加法器面积非常小,但当被加数数量很大时,通常需要长比特流才能达到实际精度阈值。在这项工作中,我们首先确定了多路复用器加法器错误的主要贡献者。然后,我们通过分析和实验证明,精确采样和完全相关这两种新技术可以瞄准并减轻这些误差源。在硬件中实现这些技术导致了 CeMux(相关增强型多路复用器)的设计,这是一种随机多路复用加法器,与传统的加权加法器相比,它的精确度明显提高,并且占用的面积也少得多。我们将 CeMux 与其他 SC 和混合设计进行比较,以进行采用大型数字滤波器的心电图滤波案例研究。一项主要结果是,即使对于大输入量,CeMux 也是准确的。与其他设计相比,CeMux 的精度更高,延迟时间减少了 4 倍到 16 倍。此外,CeMux 使用的面积比现有设计减少了约 35%,并且我们证明可以用少量的精度换取面积进一步减少 50%。最后,我们将 CeMux 与传统的二进制设计进行比较,结果表明,CeMux 可以实现 50% 至 73% 的面积减少,功耗和延迟与传统设计相似,但误差水平略高。
Stochastic computing (SC) is a low-cost computational paradigm that has promising applications in digital filter design, image processing, and neural networks. Fundamental to these applications is the weighted addition operation, which is most often implemented by a multiplexer (mux) tree. Mux-based adders have very low area but typically require long bitstreams to reach practical accuracy thresholds when the number of summands is large. In this work, we first identify the main contributors to mux adder error. We then demonstrate with analysis and experiment that two new techniques, precise sampling and full correlation, can target and mitigate these error sources. Implementing these techniques in hardware leads to the design of CeMux (Correlation-enhanced Multiplexer), a stochastic mux adder that is significantly more accurate and uses much less area than traditional weighted adders. We compare CeMux to other SC and hybrid designs for an electrocardiogram filtering case study that employs a large digital filter. One major result is that CeMux is shown to be accurate even for large input sizes. CeMux's higher accuracy leads to a latency reduction of 4× to 16× over other designs. Furthermore, CeMux uses about 35% less area than existing designs, and we demonstrate that a small amount of accuracy can be traded for a further 50% reduction in area. Finally, we compare CeMux to a conventional binary design and we show that CeMux can achieve a 50% to 73% area reduction for similar power and latency as the conventional design but at a slightly higher level of error.
DOI: 10.23919/date.2019.8714937
发表时间: 2019
期刊: 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE)
影响因子: --
作者:
S. R. Faraji;M. Hassan Najafi;Bingzhe Li;David J. Lilja;K. Bazargan
通讯作者: K. Bazargan
随机计算在助听器滤波器组设计中的优势
DOI: --
发表时间: 2021
期刊: 2021 IEEE Biomedical Circuits and Systems Conference (BioCAS
影响因子: --
作者:
Baker, Timothy J.;Sun, Yiqiu;Hayes, John P.
通讯作者: Hayes, John P.
矩阵运算的随机逻辑实现
DOI: 10.1109/dsd.2014.75
发表时间: 2014
期刊: 2014 17th Euromicro Conference on Digital System Design
影响因子: --
作者:
Pai;J. Hayes
通讯作者: J. Hayes
多级随机计算中的能量和精度
DOI: --
发表时间: 2014
期刊: IEEE International New Circuits and Systems Conference
影响因子: --
作者:
Bert Moons;M. Verhelst
通讯作者: M. Verhelst
使用随机电路进行快速准确的计算
DOI: 10.7873/date2014.089
发表时间: 2014
期刊: 2014 Design, Automation & Test in Europe Conference & Exhibition (DATE)
影响因子: --
作者:
Armin Alaghi;J. Hayes
通讯作者: J. Hayes