How Shifting Focus from Register to Data Functionality Can Enhance Register and Bus Management

Abstract

Bus and register management is one of the crucial aspects of application-specific integrated circuit-, system-on-chip-, or field-programmable gate array-based designs. The problems related to it are well known, and multiple tools or approaches are already trying to solve or mitigate them. However, all available solutions share the same register-centric paradigm. A user defines registers and then manually lays out the data into the registers. Such an approach has its limitations. A description does not contain information on data spanning multiple registers or data forming a broader context, for example, procedure arguments. It also does not contain information on the purpose of the data. As a result, the generated access code is low-level and usually needs an extra wrapper, which leaves room for potential human mistakes. For instance, it is the user’s responsibility to guarantee proper access order to registers or to provide an atomic change of data wider than a single register width. This article proposes a new approach, the functionality-centric approach. In the functionality-centric approach, the user defines the data with the type of their functionality. The registers and bus hierarchy are later implicitly inferred. By defining the functionality of the data placed in the registers, it is possible to generate more access code, increase code robustness, improve system design readability, and shorten the implementation process.

Keywords

• HW/SW codesign
• field-programmable gate array
• system-on-chip
• bus interface
• register addressing
• register synthesis