AgentDSE: Reasoning-Augmented Architectural Design Space Exploration
AgentDSE is a simulator-in-the-loop methodology that uses a large language model to automate architectural design space exploration.
AgentDSE introduces a novel simulator-in-the-loop methodology that uses a large language model to automate architectural design space exploration, unlike prior work that treats the simulator as a black-box oracle.
Before reading this…
Applications
- →Deep neural network accelerator mapping
- →Hardware/software co-design
- →CPU cache-hierarchy optimization
To understand this paper, make sure you know these concepts first:
- Large language modelsfind papers →
- Simulator-in-the-loop methodologiesfind papers →
Abstract
More Like ThisTraditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods. This inefficiency arises because conventional methods treat the simulator as a black-box oracle. In contrast, human architects effectively guide exploration by reasoning through physical constraints, performance bottlenecks, data reuse, and workload structures. To bridge this gap, we introduce AgentDSE, a simulator-in-the-loop methodology driven by a general-purpose large language model (LLM) coding agent. AgentDSE automates this architectural-reasoning loop without requiring model fine-tuning, precomputed design databases, or domain-specific optimizer code. Across deep neural network (DNN) accelerator mapping, hardware/software co-design, and CPU cache-hierarchy optimization, AgentDSE achieves competitive or better design quality with up to two orders of magnitude fewer evaluations. AgentDSE also produces inspectable traces that surface architectural hypotheses, performance cliffs, implicit priors, and simulator artifacts, making every search decision traceable rather than buried in optimizer state.