PRIM: Hybrid Array-Compressor Multipliers with Carry Disregard and OR-based Approximation
This paper introduces an efficient new 4:1 compressor that uses carry disregard and OR-based approximation, leading to the development of 13 approximate unsigned multipliers. The proposed multipliers, 8-bit array-comPressor oR-based carry dIsregard Multipliers (PRIM8s) demonstrate significant improvements in area, power, delay, and Power-Delay-Product (PDP) by an average of 29%, 31%, 25%, and 47%, compared to the exact multiplier. In the approximate multiplier literature, with our hardware, we establish new Pareto fronts for most criteria. The effectiveness of the proposed multipliers for noise reduction is demonstrated in an image-processing application using a low-pass Gaussian filter. On average, PRIM8s reduce power consumption and improve speed by 32.36% and 19.01% compared to the exact multiplier, while also enhancing image quality, as indicated by a 0.14% increase in Structural Similarity Index Measure (SSIM).
Authors
- Nima Amirafshar (ORCID: https://orcid.org/0009-0000-4361-8095)
- Hadi Shahriar Shahhoseini (ORCID: https://orcid.org/0000-0002-6042-0993)
- Gulafshan Gulafshan
- Nima TaheriNejad (ORCID: https://orcid.org/0000-0002-1295-0332)
Institutions
- Heidelberg University (DE)
- Iran University of Science and Technology (IR)
Publication Details
- Published
- 2025-05-25
- DOI
- https://doi.org/10.1109/iscas56072.2025.11044007
- Primary Topic
- Parallel Computing and Optimization Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00