mlsanityData to 14 Oct 2026

FAMES: Fast Approximate Multiplier Substitution for Mixed-Precision Quantized DNNs--Down to 2 Bits!

arXiv 2411.18055 ↗First posted 27 Nov 2024cs.LG cs.ETcited by 0

Not on the map. Why?

Abstract (arXiv)

A widely-used technique in designing energy-efficient deep neural network (DNN) accelerators is quantization. Recent progress in this direction has reduced the bitwidths used in DNN down to 2. Meanwhile, many prior works apply approximate multipliers (AppMuls) in designing DNN accelerators to lower their energy consumption. Unfortunately, these works still assume a bitwidth much larger than 2, which falls far behind the state-of-the-art in quantization area and even challenges the meaningfulness of applying AppMuls in DNN accelerators, since a high-bitwidth AppMul consumes much more energy than a low-bitwidth exact multiplier! Thus, an important problem to study is: Can approximate multipliers be effectively applied to quantized DNN models with very low bitwidths? In this work, we give an affirmative answer to this question and present a systematic solution that achieves the answer: FAMES, a fast approximate multiplier substitution method for mixed-precision DNNs. Our experiments demonstrate an average 28.67% energy reduction on state-of-the-art mixed-precision quantized models with bitwidths as low as 2 bits and accuracy losses kept under 1%. Additionally, our approach is up to 300x faster than previous genetic algorithm-based methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 25 references that are in the map. First posted on arXiv 27 Nov 2024.

Builds on

15 of 25 references.

References · 15

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  2. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 479
  3. 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
  4. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  5. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 424
  6. 2019HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precisioncited by 402
  7. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
  8. 2017Comparative Study of CNN and RNN for Natural Language Processingcited by 82
  9. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 61
  10. 2019ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retrainingcited by 28
  11. 2020TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPUcited by 17
  12. 2021BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratchcited by 11
3 more
  1. 2022AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorchcited by 11
  2. 2020Architecture Disentanglement for Deep Neural Networkscited by 10
  3. 2022ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inferencecited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025MAx-DNN: Multi-Level Arithmetic Approximation for Energy-Efficient DNN Hardware Accelerators
  2. 2024Exploring Quantization and Mapping Synergy in Hardware-Aware Deep Neural Network Accelerators
  3. 2023PQA: Exploring the Potential of Product Quantization in DNN Hardware Acceleration
  4. 2022QAPPA: Quantization-Aware Power, Performance, and Area Modeling of DNN Accelerators
  5. 2023Ultra-low Precision Multiplication-free Training for Deep Neural Networks
  6. 2022QADAM: Quantization-Aware DNN Accelerator Modeling for Pareto-Optimality
  7. 2022QUIDAM: A Framework for Quantization-Aware DNN Accelerator and Model Co-Exploration
  8. 2022Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization