This paper is concerned with an overview of the salient features of combining the hitherto online and digit-serial arithmetic techniques for the design, development, and hardware implementation of algorithms for high-speed arithmetic operations. The online technique processes digital signals as generated and consumed by current practical analog-to-digital and digital-to-analog converters. The digit-serial technique permits a trade-off between speed and area in a corresponding hardware implementation. As online operations require redundant representations, carries do not propagate through long paths, thereby reducing the d e l a y in hardware implementation. Moreovel; the most significant digits of the result of an online operation can be fed as the inputs to other online operations after a small number of bit-serial clock cycles called latency. The area of online operations was a concern in the past, but one can now circumvent this problem by employing the digit-serial technique.signal processor to a digital-to-analog (D/A) converter. At a given time instant, one, several, or all of the digits of a word can be transmitted, i.e. in a bit-serial, digit-serial, or bit-parallel fashion, respectively. Of course, the bit-serial and bit-parallel fashions are subsumed by the digit-serial arithmetic technique. However, the digit-serial arithmetic technique itself can be derived from the bit-serial arithmetic technique. In addition, a bit-serial data stream can be processed, (a) the least-significant-digit (LSD) first, which is the case in the conventional arithmetic technique, or (b) the least-significant-digit (MSD) first, which is the case in the online arithmetic technique. The digit-serial and online arithmetic techniques are described in the following subsections.
This paper presents three alternative implementations of a high-performance low-power inner product processor. Several previously published algorithms are examined and modifications that d u c e the avemge activity and computational time are proposed. In addition, various hardware implementations and their evaluation of power and performance are provided.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.