Abstract:Neural Networks (NNs) have been widely adopted due to their outstanding efficacy and adaptability across computer vision and deep learning applications. The optimization of NNs is necessary to enable their deployment on energy constrained embedded devices, where the limited available energy poses a significant challenge for efficient inference. This paper presents a runtime reconfigurable multiplier architecture integrated into the RISC-V core, targeting energy efficient neural network inference and edge AI applications. The proposed multiplier supports adaptability for exact and approximate computation with multiple configurable accuracy levels via a dedicated mulscr, enabling fine-grained energy accuracy control within a standard processor pipeline. The proposed design achieves 44%-52% and 62%-68% power reduction in exact and approximate modes respectively, while maintaining the computational performance of 1.89 DMIPS/MHz. Evaluations on error-tolerant workloads including 2d convolution and matrix multiplication demonstrate up to 63% reduction in energy consumption, with the proposed design achieving 1.21 pJ/instruction for matrix multiplication, confirming its effectiveness for energy-constrained edge AI deployments.
| Comments: | Accepted in ISVLSI 2026 |
| Subjects: | Hardware Architecture (cs.AR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08785 [cs.AR] |
| (or arXiv:2605.08785v1 [cs.AR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08785 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pragun Jaswal [view email]
[v1]
Sat, 9 May 2026 08:14:09 UTC (4,403 KB)