Generating synchronous timed descriptions of digital receivers from dynamic data flow system level configuration

Peter Zepter, Thorsten Grötker
{"title":"Generating synchronous timed descriptions of digital receivers from dynamic data flow system level configuration","authors":"Peter Zepter, Thorsten Grötker","doi":"10.1109/EDTC.1994.326923","DOIUrl":null,"url":null,"abstract":"The system and architecture design of digital receivers for high to medium throughput communication links and similar signal processing hardware has special characteristics. The algorithm development on the system level is performed using a data flow driven simulation tool. To shorten the turn-around time in the joint optimization of algorithm and architecture we developed the concept of a tool and library support for a smooth direct transition from the untimed system level dynamic data flow specification and simulation to a synchronous timed ASIC implementation using a hardware description language. Multiple and dynamic data rates can be converted. To reuse design knowledge a library of several generic implementations is provided, which should allow to cover various trade-offs for the particular functions. The timing interface of the library allows for introduction of timing and implementation-dependent information in terms of data rates, iteration intervals (i.e. the number of clock cycles between two data items), port related latencies and control conditions (for models with dynamic rates). The system incorporates algorithms for checking whether the system is consistent and deadlock-free as well as the computation of the arrival times for the data items on the edges. The main task in the implementation of the dynamic data flow is the automatic creation of the gated clock or control signal system to enable the correct setting of algorithmic states in the system. Furthermore algorithms for detecting the registers representing the algorithmic states (which are different from pipeline registers when dealing with dynamic subgraphs) and deciding on the feasibility of the implementation have been developed.<<ETX>>","PeriodicalId":244297,"journal":{"name":"Proceedings of European Design and Test Conference EDAC-ETC-EUROASIC","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1994-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of European Design and Test Conference EDAC-ETC-EUROASIC","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EDTC.1994.326923","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9

Abstract

The system and architecture design of digital receivers for high to medium throughput communication links and similar signal processing hardware has special characteristics. The algorithm development on the system level is performed using a data flow driven simulation tool. To shorten the turn-around time in the joint optimization of algorithm and architecture we developed the concept of a tool and library support for a smooth direct transition from the untimed system level dynamic data flow specification and simulation to a synchronous timed ASIC implementation using a hardware description language. Multiple and dynamic data rates can be converted. To reuse design knowledge a library of several generic implementations is provided, which should allow to cover various trade-offs for the particular functions. The timing interface of the library allows for introduction of timing and implementation-dependent information in terms of data rates, iteration intervals (i.e. the number of clock cycles between two data items), port related latencies and control conditions (for models with dynamic rates). The system incorporates algorithms for checking whether the system is consistent and deadlock-free as well as the computation of the arrival times for the data items on the edges. The main task in the implementation of the dynamic data flow is the automatic creation of the gated clock or control signal system to enable the correct setting of algorithmic states in the system. Furthermore algorithms for detecting the registers representing the algorithmic states (which are different from pipeline registers when dealing with dynamic subgraphs) and deciding on the feasibility of the implementation have been developed.<>
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
从动态数据流系统级配置生成数字接收机的同步定时描述
用于中高吞吐量通信链路和类似信号处理硬件的数字接收机系统和体系结构设计具有特殊的特点。系统级的算法开发使用数据流驱动的仿真工具进行。为了缩短算法和架构联合优化的周转时间,我们开发了一个工具和库的概念,支持从非定时系统级动态数据流规范和模拟到使用硬件描述语言的同步定时ASIC实现的平滑直接过渡。多重和动态数据速率可以转换。为了重用设计知识,提供了几个通用实现的库,它应该允许覆盖特定功能的各种权衡。该库的定时接口允许在数据速率、迭代间隔(即两个数据项之间的时钟周期数)、端口相关延迟和控制条件(对于具有动态速率的模型)方面引入定时和实现相关信息。该系统包含用于检查系统是否一致和无死锁以及边缘上数据项到达时间的计算的算法。实现动态数据流的主要任务是自动创建门控时钟或控制信号系统,使系统中的算法状态能够正确设置。此外,还开发了用于检测表示算法状态的寄存器(与处理动态子图时的管道寄存器不同)和决定实现可行性的算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Application of simple genetic algorithms to sequential circuit test generation Efficient implementations of self-checking multiply and divide arrays A reduced-swing data transmission scheme for resistive bus lines in VLSIs Genesis: a behavioral synthesis system for hierarchical testability Nondeterministic finite-state machines and sequential don't cares
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1