mlsanityData to 14 Oct 2026

DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning

arXiv 2512.11342 ↗First posted 12 Dec 2025cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

High-Level Synthesis (HLS) tools are widely adopted in FPGA-based domain-specific accelerator design. However, existing tools rely on fixed optimization strategies inherited from software compilations, limiting their effectiveness. Tailoring optimization strategies to specific designs requires deep semantic understanding, accurate hardware metric estimation, and advanced search algorithms -- capabilities that current approaches lack. We propose DAPO, a design structure-aware pass ordering framework that extracts program semantics from control and data flow graphs, employs contrastive learning to generate rich embeddings, and leverages an analytical model for accurate hardware metric estimation. These components jointly guide a reinforcement learning agent to discover design-specific optimization strategies. Evaluations on classic HLS designs demonstrate that our end-to-end flow delivers a 2.36 speedup over Vitis HLS on average.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 30 references that are in the map. First posted on arXiv 12 Dec 2025.

Builds on

12 of 30 references.

References · 12

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  5. 2020Principal Neighbourhood Aggregation for Graph Netscited by 478
  6. 2021IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learningcited by 26
  7. 2020AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learningcited by 24
  8. 2020RLlib Flow: Distributed Reinforcement Learning is a Dataflow Problemcited by 16
  9. 2023Learning Compiler Pass Orders using Coreset and Normalized Value Predictioncited by 11
  10. 2022Democratizing Domain-Specific Computingcited by 6
  11. 2024Hierarchical Source-to-Post-Route QoR Prediction in High-Level Synthesis with GNNscited by 5
  12. 2022POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation
  2. 2024Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
  3. 2026HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning
  4. 2024Optimizing High-Level Synthesis Designs with Retrieval-Augmented Large Language Models
  5. 2025LLM-DSE: Searching Accelerator Parameters with LLM Agents
  6. 2026HiFuzz: Hierarchical Reinforcement Learning for Semantic-Aware and Adaptive CPU Fuzzing
  7. 2025ChipSeek: Optimizing Verilog Generation via EDA-Integrated Reinforcement Learning
  8. 2025Automated Design Optimization via Strategic Search with Large Language Models