A Multi-Format Floating-Point Multiplier for Power-Efficient Operations

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

626 Downloads (Pure)

Abstract

In this work, we present a radix-16 multi-format multiplier to multiply 64-bit unsigned integer operands, doubleprecision and single-precision operands. The multiplier is sectioned in two lanes such that two single-precision multiplications can be computed in parallel. Radix-16 is chosen for the reduced number of partial products and the resulting power savings. The experimental results show that high power efficiency is obtained by issuing two single-precision multiplications per cycle. Moreover, by converting the double-precision numbers which fit to single-precision, further energy can be saved
Original languageEnglish
Title of host publicationProceedings of the 30th IEEE International System-on-Chip Conference
PublisherIEEE
Publication date2017
Pages351-356
ISBN (Print)9781538640333
DOIs
Publication statusPublished - 2017
Event2017 30th IEEE International System-on-Chip Conference - Hotel Novotel München City, München, Germany
Duration: 5 Sept 20178 Sept 2017
Conference number: 30
https://ieeexplore.ieee.org/xpl/conhome/8170502/proceeding

Conference

Conference2017 30th IEEE International System-on-Chip Conference
Number30
LocationHotel Novotel München City
Country/TerritoryGermany
CityMünchen
Period05/09/201708/09/2017
Internet address

Fingerprint

Dive into the research topics of 'A Multi-Format Floating-Point Multiplier for Power-Efficient Operations'. Together they form a unique fingerprint.

Cite this