Leveraging Highly Approximated Multipliers in DNN Inference

December 21, 2024 Β· Declared Dead Β· πŸ› IEEE Access

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Georgios Zervakis, Fabio Frustaci, Ourania Spantidi, Iraklis Anagnostopoulos, Hussam Amrouch, JΓΆrg Henkel arXiv ID 2412.16757 Category cs.AR: Hardware Architecture Cross-listed cs.LG Citations 1 Venue IEEE Access Last Checked 3 months ago
Abstract
In this work, we present a control variate approximation technique that enables the exploitation of highly approximate multipliers in Deep Neural Network (DNN) accelerators. Our approach does not require retraining and significantly decreases the induced error due to approximate multiplications, improving the overall inference accuracy. As a result, our approach enables satisfying tight accuracy loss constraints while boosting the power savings. Our experimental evaluation, across six different DNNs and several approximate multipliers, demonstrates the versatility of our approach and shows that compared to the accurate design, our control variate approximation achieves the same performance, 45% power reduction, and less than 1% average accuracy loss. Compared to the corresponding approximate designs without using our technique, our approach improves the accuracy by 1.9x on average.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Hardware Architecture

Died the same way β€” πŸ‘» Ghosted