English

From LLM to Silicon: RL-Driven ASIC Architecture Exploration for On-Device AI Inference

Hardware Architecture 2026-04-10 v1 Machine Learning

Abstract

We present an RL-driven compiler that jointly optimizes ASIC architecture, memory hierarchy, and workload partitioning for AI inference across 3nm to 28nm. The design space is formulated as a single Markov Decision Process with mixed discrete-continuous actions and a unified Power-Performance-Area (PPA) objective. Soft Actor-Critic (SAC) with Mixture-of-Experts gating explores the joint space of mesh topology, per-core microarchitecture, and operator placement. We validate on two workloads, Llama 3.1 8B FP16 (high-performance mode, 29809 tokens per second at 3nm) and SmolVLM (low-power mode, less than 13 mW at all nodes, 10 MHz). Across 7 process nodes, the RL automatically adapts mesh sizes and per-tile configurations, including heterogeneous FETCH, VLEN, and memory allocation without node-specific manual retuning.

Keywords

Cite

@article{arxiv.2604.07526,
  title  = {From LLM to Silicon: RL-Driven ASIC Architecture Exploration for On-Device AI Inference},
  author = {Ravindra Ganti and Steve Xu},
  journal= {arXiv preprint arXiv:2604.07526},
  year   = {2026}
}

Comments

25 pages, 12 figures, 21 tables

R2 v1 2026-07-01T12:00:00.615Z