Metraipolis › archive › dc_ee4e08ace6eb

Structure-augmented LLMs for High-Level Synthesis Pragma Optimization — arXiv:2609.38601

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38601
License (as archived): CC0-1.0
Archived: 2026-10-07T13:15:20.121Z
SHA-256 of the archived text: c849f00136d2aa898a575c0736fae40486acb196c9c165b6889e7fc804c48b78
Stable URL of this page: https://metraipolis.com/documento/dc_ee4e08ace6eb

How to cite

Structure-augmented LLMs for High-Level Synthesis Pragma Optimization — arXiv:2609.38601 — arXiv (en), https://arxiv.org/abs/2609.38601 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ee4e08ace6eb (Metraipolis archive dc_ee4e08ace6eb, sha256 c849f00136d2aa898a575c0736fae40486acb196c9c165b6889e7fc804c48b78)

BibTeX

@misc{dcee4e08ace6eb,
  title = {Structure-augmented LLMs for High-Level Synthesis Pragma Optimization — arXiv:2609.38601},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38601},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ee4e08ace6eb; sha256 c849f00136d2aa898a575c0736fae40486acb196c9c165b6889e7fc804c48b78},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38601. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pragma insertion drives the quality of high-level synthesis (HLS) designs. Choosing the right directives demands expert knowledge and reasoning about loop nesting, data dependences, and memory layout. While existing large language models (LLMs) show promise in code generation, they lack explicit program-structure awareness, limiting their ability to suggest effective pragmas. We present PRISM, a novel structure-augmented LLM that closes this gap by adding compiler-grade structural reasoning to a pretrained, frozen code LLM. It combines three hierarchical program representations, Abstract Syntax Tree (AST), Control-Flow Graph (CFG), and Data-Flow Graph (DFG), injecting them into a specific transformer layer while keeping original code tokens in a separate stream. The cross-attention gate at the injection point allows falling back to the pretrained representation when its structural signal is unhelpful. On zero-shot evaluation in HLS-Eval, PRISM synthesizes 3.5\times as many kernels as Llama3-8B (26.9\% vs. 7.7\%), and on the kernels where it does succeed, it produces designs that are 2.31\times faster (geomean) than GPT-5-mini's. In the agentic flow, the PRISM codegen outperforms other baselines when optimizing complex code and drives the average normalized improvement across the HLS-Eval suite to 26.4\%.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AR).
Categorie arXiv: Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.38601 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:46:56.852Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).