{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T10:06:38Z","timestamp":1767693998214,"version":"3.48.0"},"reference-count":29,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":5,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Computers &amp; Digital Techniques"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>The posit number system represents a significant advancement aimed at replacing the current IEEE floating\u2010point standard in a seamless manner. With its notable dynamic range and gradually tapering precision, a smaller posit can closely match the performance of a larger floating\u2010point number in representing decimal values. Multiplication is a fundamental arithmetic operation that is essential in a wide range of applications, particularly in fields such as image processing, signal processing, neural networks (NNs), and machine learning. Given the considerable power consumption, area requirements, and latency associated with multiplication, it is imperative to explore optimization strategies in these areas. This article provides a comprehensive review of both exact and inexact (approximate) posit multiplier designs. It includes a detailed comparative evaluation of their error rates and circuit characteristics, aimed at fostering a deeper understanding of the distinctive features of various designs. This study examines Booth\u2010based posit multipliers and logarithmic posit multipliers, categorizing Booth multipliers into exact and inexact types. The posit multipliers are implemented and synthesized using the Cadence RTL Compiler in Verilog HDL, while error characterization is conducted using the soft posit library in Python. In this article, power, area, and delay are compared in relation to the mean relative error distance (MRED). The comparative results indicate that the logarithmic\u2010based posit multiplier is hardware\u2010efficient but has low accuracy. In contrast, the Booth posit multiplier offers superior accuracy, despite having higher performance metrics. Notably, the logarithmic multiplier, referred to as posit logarithmic\u2010approximate multiplier (PLAM), provides a substantial decrease in power, area, and delay by at least 92%, 82%, and 78%, respectively, compared to all the Booth multipliers. The approximation error of PLAM is analyzed, including metrics such as MRED, to assess performance relative to exact posit multipliers. The posit logarithmic multiplier was validated using various NN architectures, including LeNet\u20105, VGG11, and ResNet\u201018. The results indicate that posit logarithmic multiplier achieves inference accuracy comparable to traditional floating\u2010point multipliers while also enhancing hardware efficiency.<\/jats:p>","DOI":"10.1049\/cdt2\/7515558","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T10:01:57Z","timestamp":1767693717000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Posit Multiplication: A Comprehensive Review of Booth and Logarithmic Mantissa Methods"],"prefix":"10.1049","volume":"2026","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0987-3190","authenticated-orcid":false,"given":"Thalla Narasimha","family":"Swetha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4328-6953","authenticated-orcid":false,"given":"Uppugunduru Anil","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0333-9387","authenticated-orcid":false,"given":"Syed Ershad","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"e_1_2_11_1_2","volume-title":"Lecture Notes on the Status of IEEE","author":"Kahan W.","year":"1996"},{"key":"e_1_2_11_2_2","doi-asserted-by":"crossref","unstructured":"HaripriyaR. S. PuliK. AnnapalliS. R. R. andPudiV. Design of Energy Efficient and Low Delay Posit Multiplier 2023 36th International Conference on VLSI Design and 2023 22nd International Conference on Embedded Systems (VLSID) 2023 Hyderabad India Institute of Electrical and Electronics Engineers (IEEE) 1\u20136 https:\/\/doi.org\/10.1109\/VLSID57277.2023.00042.","DOI":"10.1109\/VLSID57277.2023.00042"},{"key":"e_1_2_11_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3347295"},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3109127"},{"key":"e_1_2_11_5_2","first-page":"71","article-title":"Beating Floating Point at its Own Game: Posit Arithmetic","volume":"4","author":"Gustafson J. L.","year":"2017","journal-title":"Supercomputing Frontiers and Innovations"},{"key":"e_1_2_11_6_2","doi-asserted-by":"crossref","unstructured":"MurilloR. Del BarrioA. A. andBotellaG. A Suite of Division Algorithms for Posit Arithmetic 2023 IEEE. 34th International Conference on Application-Specific Systems Architectures and Processors (ASAP) 2023 IEEE 41\u201344 https:\/\/doi.org\/10.1109\/ASAP57973.2023.00020.","DOI":"10.1109\/ASAP57973.2023.00020"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2920936"},{"key":"e_1_2_11_8_2","doi-asserted-by":"crossref","unstructured":"ZurasD. CowlishawM. andAikenA. et al.IEEE Standard for Floating-Point Arithmetic\u2014Redline IEEE Std 2008 754 1\u201382 https:\/\/doi.org\/10.1109\/IEEESTD.2008.5976968.","DOI":"10.1109\/IEEESTD.2008.5976968"},{"key":"e_1_2_11_9_2","doi-asserted-by":"crossref","unstructured":"CarmichaelZ. LangroudiH. F. KhazanovC. LillieJ. GustafsonJ. L. andKudithipudiD. Performance-Efficiency Trade-Off of Low-Precision Numerical Formats in Deep Neural Networks Proceedings of the Conference on Next Generation Arithmetic 2019 1\u20139.","DOI":"10.1145\/3316279.3316282"},{"key":"e_1_2_11_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2020.102762"},{"key":"e_1_2_11_11_2","first-page":"82318","volume-title":"IEEE Access","author":"Romanov A. Y.","year":"2021"},{"key":"e_1_2_11_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3377890"},{"key":"e_1_2_11_13_2","doi-asserted-by":"crossref","unstructured":"NorrisC. J.andKimS. An Approximate and Iterative Posit Multiplier Architecture for FPGAs Proceedings of IEEE International Symposium on Circuits and Systems (ISCAS) 2021 IEEE 1\u20135.","DOI":"10.1109\/ISCAS51556.2021.9401158"},{"key":"e_1_2_11_14_2","volume-title":"Posit: A Potential Replacement for IEEE","author":"Gustafson J. L.","year":"2017"},{"key":"e_1_2_11_15_2","doi-asserted-by":"crossref","unstructured":"UguenY. ForgetL. andde DinechinF. Evaluating the Posit Number System Hardware Cost Proceedings of the 29th International Conference on Field Programmable Logic and Applications (FPL) 2019 IEEE 106\u2013113.","DOI":"10.1109\/FPL.2019.00026"},{"key":"e_1_2_11_16_2","doi-asserted-by":"crossref","unstructured":"PodobasA.andMatsuokaS. Hardware Implementation of POSITs and Their Application in FPGAs Proceedings of IPDPSW 2018 IEEE 138\u2013145.","DOI":"10.1109\/IPDPSW.2018.00029"},{"key":"e_1_2_11_17_2","unstructured":"GustafsonJ. Posit Arithmetic: A Mathematica Notebook Describing the Posit Number System 2017."},{"key":"e_1_2_11_18_2","unstructured":"Posit Working Group Posit Standard Documentation Release 3.2-Draft 2018 Accessed September 24 2020https:\/\/posithub.org\/docs\/posit_standard.pdf."},{"key":"e_1_2_11_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2980531"},{"key":"e_1_2_11_20_2","volume-title":"Computer Architecture: A Quantitative Approach","author":"Hennessy J. L.","year":"2007"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.1962.5219391"},{"key":"e_1_2_11_22_2","doi-asserted-by":"crossref","unstructured":"JonnalagaddaA. K. UppugunduruS. VeeramachaneniS. andAhmedS. E. Design of Energy-Efficient Posit Multiplier Proceedings of the Great Lakes Symposium on VLSI 2023 1\u20136.","DOI":"10.1145\/3583781.3590227"},{"key":"e_1_2_11_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2022.3231642"},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3369695"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/qjmam\/4.2.236"},{"key":"e_1_2_11_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.micpro.2010.07.001"},{"key":"e_1_2_11_27_2","first-page":"2503","article-title":"Variable-Precision Approximate Floating-Point Multiplier for Efficient Deep Learning Computation","volume":"69","author":"Zhang H.","year":"2022","journal-title":"IEEE Transactions on Circuits and Systems II: Express Briefs"},{"key":"e_1_2_11_28_2","doi-asserted-by":"crossref","unstructured":"YinP. WangC. LiuW. andLombardiF. Design and Performance Evaluation of Approximate Floating-Point Multipliers 2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI) 2016 IEEE 296\u2013301 https:\/\/doi.org\/10.1109\/ISVLSI.2016.15 2-s2.0-84988966522.","DOI":"10.1109\/ISVLSI.2016.15"},{"key":"e_1_2_11_29_2","unstructured":"MicikeviciusP. NarangS. andAlbenJ. et al.Mixed Precision Training 2017 arXiv: 1710.03740."}],"container-title":["IET Computers &amp; Digital Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cdt2\/7515558","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T10:02:01Z","timestamp":1767693721000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cdt2\/7515558"}},"subtitle":[],"editor":[{"given":"Sudarshan","family":"Srinivasan","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":29,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/cdt2\/7515558"],"URL":"https:\/\/doi.org\/10.1049\/cdt2\/7515558","archive":["Portico"],"relation":{},"ISSN":["1751-8601","1751-861X"],"issn-type":[{"value":"1751-8601","type":"print"},{"value":"1751-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-03-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"7515558"}}