English

AdAM: Adaptive Fault-Tolerant Approximate Multiplier for Edge DNN Accelerators

Artificial Intelligence 2024-03-06 v1 Hardware Architecture Machine Learning
Authors: Mahdi Taheri , Natalia Cherezova , Samira Nazari , Ahsan Rafiq , Ali Azarpeyvand , Tara Ghasempouri , Masoud Daneshtalab , Jaan Raik , Maksim Jenihhin
View on arXiv ↗ PDF ↗

Abstract

In this paper, we propose an architecture of a novel adaptive fault-tolerant approximate multiplier tailored for ASIC-based DNN accelerators.

Keywords

adaptive fault-tolerant approximate multiplier DNN accelerator ASIC edge computing

Cite

@article{arxiv.2403.02936,
  title  = {AdAM: Adaptive Fault-Tolerant Approximate Multiplier for Edge DNN Accelerators},
  author = {Mahdi Taheri and Natalia Cherezova and Samira Nazari and Ahsan Rafiq and Ali Azarpeyvand and Tara Ghasempouri and Masoud Daneshtalab and Jaan Raik and Maksim Jenihhin},
  journal= {arXiv preprint arXiv:2403.02936},
  year   = {2024}
}

Related papers

View all related →
Hardware Architecture · Computer Science
Positive/Negative Approximate Multipliers for DNN Accelerators
Ourania Spantidi, Georgios Zervakis, Iraklis Anagnostopoulos, Hussam Amrouch +1
2022-03-17
Machine Learning · Computer Science
AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorch
Dimitrios Danopoulos, Georgios Zervakis, Kostas Siozios, Dimitrios Soudris +1
2022-10-13
Machine Learning · Computer Science
Special Session: Approximation and Fault Resiliency of DNN Accelerators
Mohammad Hasan Ahmadilivani, Mario Barbareschi, Salvatore Barone, Alberto Bosio +8
2023-06-09
Optimization and Control · Mathematics
An Adaptive Proximal ADMM for Nonconvex Linearly Constrained Composite Programs
Leandro Farias Maia, David H. Gutman, Renato D. C. Monteiro, Gilson N. Silva
2026-05-04
Hardware Architecture · Computer Science
Using Libraries of Approximate Circuits in Design of Hardware Accelerators of Deep Neural Networks
Vojtech Mrazek, Lukas Sekanina, Zdenek Vasicek
2020-07-06
Hardware Architecture · Computer Science
A Reconfigurable Multiplier Architecture for Error-Resilient Applications in RISC-V Core
Pragun Jaswal, L. Hemanth Krishna, B. Srinivasu
2026-05-12
Hardware Architecture · Computer Science
SIMDive: Approximate SIMD Soft Multiplier-Divider for FPGAs with Tunable Accuracy
Zahra Ebrahimi, Salim Ullah, Akash Kumar
2020-11-03
Hardware Architecture · Computer Science
Low Power Approximate Multiplier Architecture for Deep Neural Networks
Pragun Jaswal, L. Hemanth Krishna, B. Srinivasu
2025-09-03
Cryptography and Security · Computer Science
ApproxABFT: Approximate Algorithm-Based Fault Tolerance for Neural Network Processing
Xinghua Xue, Cheng Liu, Feng Min, Tao Luo +1
2025-04-22
Machine Learning · Computer Science
Exploring Fault-Energy Trade-offs in Approximate DNN Hardware Accelerators
Ayesha Siddique, Kanad Basu, Khaza Anuarul Hoque
2021-01-11
Optimization and Control · Mathematics
An Accelerated Linearized Alternating Direction Method of Multipliers
Yuyuan Ouyang, Yunmei Chen, Guanghui Lan, Eduardo Pasiliao
2014-02-13
Hardware Architecture · Computer Science
Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization
Yao Lu, Jide Zhang, Su Zheng, Zhen Li +1
2022-11-17
Hardware Architecture · Computer Science
Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey
Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris, Jörg Henkel
2022-03-18
Hardware Architecture · Computer Science
ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference
Jing Gong, Hassaan Saadat, Hasindu Gamaarachchi, Haris Javaid +2
2022-09-26
Machine Learning · Computer Science
Fast ADMM Algorithm for Distributed Optimization with Adaptive Penalty
Changkyu Song, Sejong Yoon, Vladimir Pavlovic
2016-04-05
Hardware Architecture · Computer Science
Approximate Signed Multiplier with Sign-Focused Compressor for Edge Detection Applications
L. Hemanth Krishna, Srinivasu Bodapati, Sreehari Veeramachaneni, BhaskaraRao Jammu +1
2025-10-28
Optimization and Control · Mathematics
Sensitivity Assisted Alternating Directions Method of Multipliers for Distributed Optimization and Statistical Learning
Dinesh Krishnamoorthy, Vyacheslav Kungurtsev
2022-03-04
Hardware Architecture · Computer Science
HADES: Hardware/Algorithm Co-design in DNN accelerators using Energy-efficient Approximate Alphabet Set Multipliers
Arani Roy, Kaushik Roy
2023-10-24
Distributed, Parallel, and Cluster Computing · Computer Science
TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPU
Filip Vaverka, Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina
2020-07-03
Hardware Architecture · Computer Science
On the Approximation of Accuracy-configurable Sequential Multipliers via Segmented Carry Chains
Jorge Echavarria, Stefan Wildermann, Oliver Keszocze, Faramarz Khosravi +2
2021-05-26
Machine Learning · Computer Science
Adaptive Consensus ADMM for Distributed Optimization
Zheng Xu, Gavin Taylor, Hao Li, Mario Figueiredo +2
2017-06-21
Neural and Evolutionary Computing · Computer Science
ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining
Vojtech Mrazek, Zdenek Vasicek, Lukas Sekanina, Muhammad Abdullah Hanif +1
2020-01-31
Machine Learning · Computer Science
Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers
Mohammad Javad Askarizadeh, Ebrahim Farahmand, Jorge Castro-Godinez, Ali Mahani +2
2024-04-19
Signal Processing · Electrical Eng. & Systems
Machine Learning-Based Self-Compensating Approximate Computing
Mahmoud Masadeh, Osman Hasan, Sofiene Tahar
2020-01-14
Machine Learning · Computer Science
Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
Geng Yuan, Zhiheng Liao, Xiaolong Ma, Yuxuan Cai +10
2021-06-22