arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1108.3970cs.AR
收藏

使用投影空间格的VLSI应用中折叠流水线结构的设计方法

A Design Methodology for Folded, Pipelined Architectures in VLSI Applications using Projective Space Lattices

Hrishikesh Sharma, Sachin Patkar

摘要:

半并行或折叠式VLSI架构在设计时需要节省硬件资源时使用。大多数最近的基于投影几何(PG)的平衡二分图的应用也属于这一类。在本文中,我们提供了一个高层次的,自顶向下的设计方法来设计最佳的半并行架构的应用程序,其数据流图(DFG)是基于PG二分图。这样的应用已经在例如差错控制编码和矩阵计算中被发现。与许多其他折叠方案不同,物理元件之间的连接拓扑在该方法中不会改变。另一个优点是易于实施。为了减少吞吐量的损失,由于折叠,我们还采用了多层流水线策略的设计方法。该设计方法已通过在C++中实现一个合成工具进行了验证,这也得到了验证。该工具是公开的。此外,在合成工具设计之前,手动构建完整的解码器原型,以验证本文中开发的所有算法,并进行各个细化步骤。在此基础上设计了一种高性能的LDPC译码器,并获得了专利。

英文摘要:

Semi-parallel, or folded, VLSI architectures are used whenever hardware resources need to be saved at design time. Most recent applications that are based on Projective Geometry (PG) based balanced bipartite graph also fall in this category. In this paper, we provide a high-level, top-down design methodology to design optimal semi-parallel architectures for applications, whose Data Flow Graph (DFG) is based on PG bipartite graph. Such applications have been found e.g. in error-control coding and matrix computations. Unlike many other folding schemes, the topology of connections between physical elements does not change in this methodology. Another advantage is the ease of implementation. To lessen the throughput loss due to folding, we also incorporate a multi-tier pipelining strategy in the design methodology. The design methodology has been verified by implementing a synthesis tool in C++, which has been verified as well. The tool is publicly available. Further, a complete decoder was manually protototyped before the synthesis tool design, to verify all the algorithms evolved in this paper, towards various steps of refinement. Another specific high-performance design of an LDPC decoder based on this methodology was worked out in past, and has been patented as well.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑