Guest Editorial: Special Section on Parallel and Distributed Computing Techniques for Non-Von Neumann Technologies

作     者：Pakin, Scott Teuscher, Christof Schuman, Catherine 

作者机构：Los Alamos Natl Lab Comp Computat & Stat Sci Div Los Alamos NM 87545 USA Portland State Univ Dept Elect & Comp Engn Portland OR 97207 USA Oak Ridge Natl Lab Comp Sci & Math Div Oak Ridge TN 37831 USA 

出 版 物：《IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS》 (IEEE并行与分布系统汇刊)

年 卷 期：2022年第33卷第2期

页      面：249-250页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：U.S. Department of Energy  USDOE 

主　　题：Special issues and sections Computer architecture Neuromorphic engineering Computational modeling Distributed computing Memory Deep learning Hardware 

摘      要：The title of this special section, Parallel and Distributed Computing Techniques for Non-Von Neumann Technologies, is a bit misleading. Technically, parallel and distributed computers already diverge from the basic architecture that John von Neumann proposed in 1945, although they are still based on processors that execute a sequence of instructions, each of which performs a simple action such as computing an arithmetic result, reading or writing memory, or branching to a new location in the instruction sequence. But what would a computer that is not based on this model of execution look like? The technologies discussed in the following articles are more exotic, more innovative, and more intriguing than what you are likely to encounter in a typical collection of peerreviewed computer-science articles. We hope that these articles will help you view computing in a new light and give you a sense of what the future of computing may look like. Silent-PIM: Realizing the Processing-in-Memory Computing with Standard Memory Requests, by Kim et al. [A1], presents a new approach to performing computation within the computer’s memory system.