A Stream Based Memory Access Control System of an On-Chip Clustered Processor for Multi-task Application

HU Kai; XIE Jing; MAO Zhi-gang

Chinese

您当前的位置：

首页 >

文章列表页 >

A Stream Based Memory Access Control System of an On-Chip Clustered Processor for Multi-task Application

更新时间：2026-09-04

- A Stream Based Memory Access Control System of an On-Chip Clustered Processor for Multi-task Application
- Vol. 31, Issue 6, Pages: 40-43(2014)
- 作者机构：
  
  上海交通大学微电子学院,上海,200240
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2014
- 稿件说明：
移动端阅览
胡凯, 谢憬, 毛志刚. 面向多任务的片上簇处理器流访存控制系统设计[J]. 微电子学与计算机, 2014, 31(6): 40-43.

HU Kai, XIE Jing, MAO Zhi-gang. A Stream Based Memory Access Control System of an On-Chip Clustered Processor for Multi-task Application[J]. 2014, 31(6): 40-43.
胡凯, 谢憬, 毛志刚. 面向多任务的片上簇处理器流访存控制系统设计[J]. 微电子学与计算机, 2014, 31(6): 40-43. DOI：

HU Kai, XIE Jing, MAO Zhi-gang. A Stream Based Memory Access Control System of an On-Chip Clustered Processor for Multi-task Application[J]. 2014, 31(6): 40-43. DOI：

摘要

为了解决分簇流处理器在进行多任务处理时访存系统效率不高的问题，提出了一种新的流访存系统.针对多任务处理情况下，各簇间工作的差异性与独立性，设计了新的流访存机制，包括流访存系统结构、访存流控制、簇间流顺序调度和流信息配置等.实验结果表明，改进后的多簇流处理器能够工作在并行与多任务两种模式下，同时在并行处理性能基本不变的情况下，获得平均20%的多任务处理性能提升.

Abstract

In order to solve the low efficiency of the memory access system in a clustered stream processor while doing multi-task processing

a new stream memory access system is proposed. Considering the diversity and independency between each cluster under multi-task condition

a new stream memory access mechanism is designed

including system architecture

stream control

stream schedule

and stream information configuration. Result shows that after modification

the processor can work in both parallel and multi-task mode

remain almost the same parallel performance

and achieve an average improvement of 20% in multi-task mode.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on assembly action recognition based on MSS-YOLO-MPHands fusion architecture

Aerial vehicle detection algorithm based on multi-scale fusion and small-object enhancement

Lightweight countermeasures against Spectre attacks on the branch prediction unit

Monte carlo analysis of V-layout trench SiC neutron detector

A review of large model development: technological evolution from BERT to Deepseek

Related Author

No data

Related Institution

No data

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰