# DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings

arXiv: https://arxiv.org/abs/2604.09240 · HTML: https://mlsanity.com/paper/2604.09240/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [PowerGear: Early-Stage Power Estimation in FPGA HLS via Heterogeneous Edge-Centric GNNs](https://mlsanity.com/paper/2201.10114/) (2022)
- [Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis](https://mlsanity.com/paper/2406.09606/) (2024)
- [Adapting Decoder-Based Language Models for Diverse Encoder Downstream Tasks](https://mlsanity.com/paper/2503.02656/) (2025)
- [HL-Pow: A Learning-Based Power Modeling Framework for High-Level Synthesis](https://mlsanity.com/paper/2009.00871/) (2020)
- [Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis](https://mlsanity.com/paper/2410.19225/) (2024)
- [DB4HLS: A Database of High-Level Synthesis Design Space Explorations](https://mlsanity.com/paper/2101.00587/) (2021)
- [Hierarchical Source-to-Post-Route QoR Prediction in High-Level Synthesis with GNNs](https://mlsanity.com/paper/2401.08696/) (2024)
- [wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation](https://mlsanity.com/paper/2511.05615/) (2025)
- [Predicting Post-Route Quality of Results Estimates for HLS Designs using Machine Learning](https://mlsanity.com/paper/2205.12397/) (2022)
- [ForgeHLS: A Large-Scale, Open-Source Dataset for High-Level Synthesis](https://mlsanity.com/paper/2507.03255/) (2025)

## Abstract (arXiv)

High-Level Synthesis (HLS) compiles C/C++ into RTL, but exploring pragma-driven optimization choices remains expensive because each design point requires time-consuming synthesis. We propose DiffHLS, a differential learning framework for HLS Quality-of-Result (QoR) prediction that learns from kernel--design pairs: a kernel baseline and a pragma-inserted design variant. DiffHLS~encodes kernel and design intermediate-representation graphs with dedicated graph neural network (GNN) branches, and augments the delta pathway with code embeddings from a pretrained code large language model (LLM). Instead of regressing absolute targets directly, we jointly predict the kernel baseline and the design-induced delta, and compose them to obtain the design prediction. On PolyBench, DiffHLS~attains lower average MAPE than GNN baselines under four GNN backbones, and LLM code embeddings consistently improve over a GNN-only ablation. We further validate scalability on the ForgeHLS dataset.