Problem
Research questions and friction points this paper is trying to address.
hardware evolution
RTL versioning
legacy design
specification-driven
semantic change
Spec-Driven Hardware Evolution via Executable Contract Refinement and Proof-Guided RTL Update
🤖 AI Summary
This work addresses the challenge that existing LLM-driven hardware generation methods struggle to support the semantic evolution of trusted legacy RTL designs. The authors propose an executable-contract-centered framework for hardware evolution, which translates new functional requirements into formally scrutinized contracts and realizes controlled, verifiable iterations from behavioral specifications to RTL modifications through a four-phase Specify-Plan-Implement-Validate workflow. Key technical innovations include executable-contract-guided evolution, mutation-based semantic probing, cross-version semantic differential analysis, and proof-driven RTL repair and verification. Evaluated on a TPU datapath module undergoing data format evolution, the approach successfully achieves functional convergence from legacy RTL to the updated version while ensuring correctness through contract-driven verification.
📝 Abstract
Hardware development is inherently evolutionary: major revisions typically begin by changing intended behavior and then updating a previously validated implementation, rather than regenerating RTL from scratch. Yet most recent LLM-based hardware research still frames the task primarily as prompt-to-RTL generation, offering limited support for semantic version evolution of trusted legacy designs. We present spec-driven hardware evolution, a contract-centered formulation for RTL version iteration. Instead of treating a new feature request as a direct prompt for RTL generation, we refine it into a reviewed executable contract for the next version. This contract specifies what must hold at the externally visible transactional level through a behavior-level reference together with explicit observation and checking semantics, while leaving how the change is realized in RTL to the evolution process. Based on this formulation, we organize hardware evolution into four stages: Specify, Plan, Implement, and Validate. After contract approval, the remaining stages proceed automatically: Plan derives cross-version semantic deltas and localizes affected RTL regions, aided by mutation-based semantic probing; Implement and Validate then perform legacy-aware RTL update under proof-guided checking and iterative repair. We evaluate the framework on a controlled version-evolution case study of a representative TPU datapath block under data-format changes. The results support the feasibility of contract-driven hardware evolution and demonstrate that the proposed backend workflow can effectively drive validated legacy RTL toward next-version functional convergence under a reviewed executable contract. An anonymous artifact for reproducibility is available at https://anonymous.4open.science/r/SDHE-3A6C.
Innovation
Methods, ideas, or system contributions that make the work stand out.
spec-driven hardware evolution
executable contract
proof-guided RTL update
semantic versioning
legacy-aware RTL modification
🔎 Similar Papers
No similar papers found.
