Alternatives to the IEEE standard floating-point representation

GAFENCO, Victor; BALAN, Gabriel; MOISEI, Daniel

Home
→
Colecția instituțională
→
Conferințe
→
Conferinţa tehnico-ştiinţifică a studenţilor, masteranzilor şi doctoranzilor
→
2025
→
Secţia Calculatoare, Informatică şi Microelectronică
→
Subsecţia Inginerie Software și Securitate
→
View Item

dc.contributor.advisor	COJUHARI, Elena
dc.contributor.author	GAFENCO, Victor
dc.contributor.author	BALAN, Gabriel
dc.contributor.author	MOISEI, Daniel
dc.date.accessioned	2026-01-13T17:15:11Z
dc.date.available	2026-01-13T17:15:11Z
dc.date.issued	2026
dc.identifier.citation	GAFENCO, Victor; Gabriel BALAN and Daniel MOISEI. Alternatives to the IEEE standard floating-point representation. In: Conferenţa Tehnico-Ştiinţifică a Colaboratorilor, Doctoranzilor şi Studenţilor = The Technical Scientific Conference of Undergraduate, Master and PhD Students, 14-16 Mai 2025. Universitatea Tehnică a Moldovei. Chişinău: Tehnica-UTM, 2026, vol. 1, pp. 465-470. ISBN 978-9975-64-612-3, ISBN 978-9975-64-613-0 (PDF).	en_US
dc.identifier.isbn	978-9975-64-612-3
dc.identifier.isbn	978-9975-64-613-0
dc.identifier.uri	https://repository.utm.md/handle/5014/34319
dc.description.abstract	The IEEE-754 floating-point standard is widely used, but alternatives like Posit, Logarithmic Number System (LNS), and Fixed-Point offer advantages in accuracy, efficiency, and range. Posit improves precision and reduces power and area consumption but faces challenges with numerical cancellations. LNS simplifies multiplication and division but complicates addition and subtraction. Fixed-point enhances efficiency in embedded systems but limits range and precision. Benchmarks on AxBench, OpenBLAS, and neural networks highlight trade-offs in performance. As computing demands evolve, these alternatives present promising solutions for deep learning, scientific computing, and low-power systems.	en_US
dc.language.iso	en	en_US
dc.publisher	Universitatea Tehnică a Moldovei	en_US
dc.relation.ispartofseries	Conferinţa tehnico-ştiinţifică a studenţilor, masteranzilor şi doctoranzilor = The Technical Scientific Conference of Undergraduate, Master and PhD Students: 14-16 mai 2025;
dc.rights	Attribution-NonCommercial-NoDerivs 3.0 United States	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/us/	*
dc.subject	computational accuracy	en_US
dc.subject	energy-efficient computing	en_US
dc.subject	high-performance arithmetic	en_US
dc.subject	numerical precision	en_US
dc.subject	unconventional number systems	en_US
dc.title	Alternatives to the IEEE standard floating-point representation	en_US
dc.type	Article	en_US