{"ID":2878475,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.17826","arxiv_id":"2508.17826","title":"LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow","abstract":"Accurate and fast performance prediction for dataflow-based accelerators is vital for efficient hardware design and design space exploration, yet existing methods struggle to generalize across architectures, applications, and input-dependent control flows. We present LLMulator, a progressive numeric modeling framework leveraging the program semantic knowledge of pre-trained large language models (LLMs) for robust, hardware- and application-aware prediction. Our numeric model treats performance values as categorical token sequences, enabling range-agnostic estimates and confidence-aware predictions for unseen applications. To handle input-dependent control flows, we introduce a reinforcement learning-based dynamic calibration method, reducing cycle prediction error by 9.7% over static models and converging to 11.2% error after a few iterations. For cross-hardware generalization, we develop a progressive data augmentation strategy that generates diverse datasets covering multi-level dataflow structures, memory parameters, and loop mapping primitives, significantly boosting prediction accuracy across architectures and configurations.","short_abstract":"Accurate and fast performance prediction for dataflow-based accelerators is vital for efficient hardware design and design space exploration, yet existing methods struggle to generalize across architectures, applications, and input-dependent control flows. We present LLMulator, a progressive numeric modeling framework...","url_abs":"https://arxiv.org/abs/2508.17826","url_pdf":"https://arxiv.org/pdf/2508.17826v1","authors":"[\"Kaiyan Chang\",\"Wenlong Zhu\",\"Shengwen Liang\",\"Huawei Li\",\"Ying Wang\"]","published":"2025-08-25T09:26:20Z","proceeding":"cs.AR","tasks":"[\"cs.AR\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}