Saved in:
Bibliographic Details
Main Authors: Collini, Luca, Hennessee, Andrew, Karri, Ramesh, Garg, Siddharth
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.12721
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912324054417408
author Collini, Luca
Hennessee, Andrew
Karri, Ramesh
Garg, Siddharth
author_facet Collini, Luca
Hennessee, Andrew
Karri, Ramesh
Garg, Siddharth
contents Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, and identifies optimal design points via feedback from HLs tools and access to integer-linear programming (ILP) solvers. Experiments compare reasoning models against conventional LLMs on benchmarks using success rate, efficiency, and design quality (area/latency) metrics, and provide the first-ever glimpse into the CoTs produced by a powerful open-source reasoning model like DeepSeek-R1.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
Collini, Luca
Hennessee, Andrew
Karri, Ramesh
Garg, Siddharth
Artificial Intelligence
Recent Large Language Models (LLMs) such as OpenAI o3-mini and DeepSeek-R1 use enhanced reasoning through Chain-of-Thought (CoT). Their potential in hardware design, which relies on expert-driven iterative optimization, remains unexplored. This paper investigates whether reasoning LLMs can address challenges in High-Level Synthesis (HLS) design space exploration and optimization. During HLS, engineers manually define pragmas/directives to balance performance and resource constraints. We propose an LLM-based optimization agentic framework that automatically restructures code, inserts pragmas, and identifies optimal design points via feedback from HLs tools and access to integer-linear programming (ILP) solvers. Experiments compare reasoning models against conventional LLMs on benchmarks using success rate, efficiency, and design quality (area/latency) metrics, and provide the first-ever glimpse into the CoTs produced by a powerful open-source reasoning model like DeepSeek-R1.
title Can Reasoning Models Reason about Hardware? An Agentic HLS Perspective
topic Artificial Intelligence
url https://arxiv.org/abs/2503.12721