mlsanityData to 7 Oct 2026

Scalable and Effective Arithmetic Tree Generation for Adder and Multiplier Designs

arXiv 2405.06758 ↗First posted 10 May 2024cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Across a wide range of hardware scenarios, the computational efficiency and physical size of the arithmetic units significantly influence the speed and footprint of the overall hardware system. Nevertheless, the effectiveness of prior arithmetic design techniques proves inadequate, as it does not sufficiently optimize speed and area, resulting in a reduced processing rate and larger module size. To boost the arithmetic performance, in this work, we focus on the two most common and fundamental arithmetic modules: adders and multipliers. We cast the design tasks as single-player tree generation games, leveraging reinforcement learning techniques to optimize their arithmetic tree structures. Such a tree generation formulation allows us to efficiently navigate the vast search space and discover superior arithmetic designs that improve computational efficiency and hardware size within just a few hours. For adders, our approach discovers designs of 128-bit adders that achieve Pareto optimality in theoretical metrics. Compared with the state-of-the-art PrefixRL, our method decreases computational delay and hardware size by up to 26% and 30%, respectively. For multipliers, when compared to RL-MUL, our approach increases speed and reduces size by as much as 49% and 45%. Moreover, the inherent flexibility and scalability of our method enable us to deploy our designs into cutting-edge technologies, as we show that they can be seamlessly integrated into 7nm technology. We believe our work will offer valuable insights into hardware design, further accelerating speed and reducing size through the refined search space and our tree generation methodologies. See our introduction video at https://bit.ly/ArithmeticTree. Codes are released at https://github.com/laiyao1/ArithmeticTree.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 29 of its 91 references that are in the map. First posted on arXiv 10 May 2024.

Builds on

29 of 91 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2015Continuous control with deep reinforcement learningcited by 3,279
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  6. 2015Fast R-CNNcited by 2,930
  7. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  8. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  9. 2021Monte Carlo Tree Search: A Review of Recent Modifications and Applicationscited by 158
  10. 2020GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learningcited by 89
  11. 2019DRiLLS: Deep Reinforcement Learning for Logic Synthesiscited by 47
  12. 2021On Joint Learning for Solving Placement and Routing in Chip Designcited by 44
17 more
  1. 2022MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learningcited by 43
  2. 2023Behavior Proximal Policy Optimizationcited by 43
  3. 2023ChiPFormer: Transferable Chip Placement via Offline Decision Transformercited by 42
  4. 2022DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learningcited by 40
  5. 2021Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Criticcited by 23
  6. 2023Macro Placement by Wire-Mask-Guided Black-Box Optimizationcited by 23
  7. 2022PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learningcited by 18
  8. 2021Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learningcited by 15
  9. 2021Unsupervised Domain Adaptation with Dynamics-Aware Rewards in Reinforcement Learningcited by 15
  10. 2022Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributionscited by 15
  11. 2023CEIL: Generalized Contextual Imitation Learningcited by 12
  12. 2022DeepTPI: Test Point Insertion with Deep Reinforcement Learningcited by 10
  13. 2022Efficient Exploration in Resource-Restricted Reinforcement Learningcited by 10
  14. 2018Cross-layer Optimization for High Speed Adders: A Pareto Driven Machine Learning Approachcited by 7
  15. 2023A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Designcited by 6
  16. 2024PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modelingcited by 5
  17. 2023Generalization in Visual Reinforcement Learning with the Reward Sequence Distributioncited by 4

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 5.

9 papers.

  1. 2024AnalogCoder: Analog Circuit Design via Training-Free Code Generationcited by 82
  2. 2024LLM-Enhanced Bayesian Optimization for Efficient Analog Layout Constraint Generationcited by 11
  3. 2024INSIGHT: Universal Neural Simulator for Analog Circuits Harnessing Autoregressive Transformerscited by 8
  4. 2024PrefixLLM: LLM-aided Prefix Circuit Designcited by 3
  5. 2025Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Designcited by 1
  6. 2025DOMAC: Differentiable Optimization for High-Speed Multipliers and Multiply-Accumulatorscited by 0
  7. 2025AC-Refiner: Efficient Arithmetic Circuit Optimization Using Conditional Diffusion Modelscited by 0
  8. 2025PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimizationcited by 0
  9. 2025PrefixGPT: Prefix Adder Optimization by a Generative Pre-trained Transformercited by 0