Affiliation:
1. Lero, Trinity College Dublin, Ireland
Abstract
Logarithmic number systems (LNS) are used to represent real numbers in many applications using a constant base raised to a fixed-point exponent making its distribution exponential. This greatly simplifies hardware multiply, divide, and square root. LNS with base-2 is most common, but in this article, we show that for low-precision LNS the choice of base has a significant impact.
We make four main contributions. First, LNS is not closed under addition and subtraction, so the result is approximate. We show that choosing a suitable base can manipulate the distribution to reduce the average error. Second, we show that low-precision LNS addition and subtraction can be implemented efficiently in logic rather than commonly used ROM lookup tables, the complexity of which can be reduced by an appropriate choice of base. A similar effect is shown where the result of arithmetic has greater precision than the input. Third, where input data from external sources is not expected to be in LNS, we can reduce the conversion error by selecting a LNS base to match the expected distribution of the input. Thus, there is no one base that gives the global optimum, and base selection is a trade-off between different factors. Fourth, we show that circuits realized in LNS require lower area and power consumption for short word lengths.
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Information Systems,Software
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Multiple-base Logarithmic Quantization and Application in Reduced Precision AI Computations;2024 IEEE 31st Symposium on Computer Arithmetic (ARITH);2024-06-10
2. Designing an IEEE-Compliant FPU that Supports Configurable Precision for Soft Processors;ACM Transactions on Reconfigurable Technology and Systems;2024-04-30
3. LNS for DNN Architectures;Synthesis Lectures on Engineering, Science, and Technology;2023-09-02
4. Arithmetic for Deep Learning;Application-Specific Arithmetic;2023-08-23
5. Number Formats;Application-Specific Arithmetic;2023-08-23