Details
Presenter(s)
![Mohammed Salman Ahmed Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/14282.jpg?h=2c4e73f8&itok=rAHAaoKD)
Display Name
Mohammed Salman Ahmed
- Affiliation
-
AffiliationInternational Institute of Information Technology, Hyderabad
- Country
Abstract
Approximate Computing has paved way for elaborate savings in design area and latency of modern system architectures, by a deliberate yet tolerable loss of functional accuracy. This paper thus proposes a design of an approximate multiplier based on the efficient Toom-Cook algorithm. Inherent integer divisions in the algorithm has restricted its feasibility in hardware, unless without suitable approximation. On an average, the proposed multiplier achieves 53%, 18% and 57% improvements in area, delay and power only with less than 1% mean error. Also, the efficacy of the multiplier is tested well in the epoch extraction system for speech processing.