CPPL: A Circuit Prompt Programming Language

TL;DR

CPPL introduces a compiler-mediated framework that enhances LLM-assisted hardware design by transforming it into a statically checkable frontend problem, improving correctness and optimization.

Contribution

It presents CPPL, a new hardware design framework combining a Python DSL and JSON IR to make LLM-generated hardware descriptions more reliable and compiler-friendly.

Findings

CPPL improves functional correctness over direct Verilog generation.

CIRCT optimization reduces post-synthesis AIG node counts.

The framework makes hardware design more analyzable and optimizable.

Abstract

Large language models (LLMs) have shown promise in register-transfer level (RTL) design automation, but direct RTL generation remains difficult to validate, optimize, and integrate with compiler-based hardware design flows. Hardware compiler infrastructures such as CIRCT provide typed intermediate representations, legality checks, and optimization passes, yet current LLMs struggle to emit raw compiler IR because of MLIR syntax, SSA discipline, dialect-specific operations, and strict width constraints. This paper presents CPPL, a compiler-mediated design framework that turns LLM-assisted hardware generation into a statically checkable frontend problem rather than an unconstrained RTL text-generation task. CPPL combines a Python frontend DSL for declaring module interfaces and hierarchy with CPPL IR, a JSON-based circuit IR designed to expose compiler-visible structure while remaining accessible to LLMs. The compiler infers operation widths from declared module ports, validates generated IR, checks hierarchy and port bindings, and deterministically lowers the result to CIRCT for synthesizable Verilog generation. On the RTLLM benchmark, CPPL improves functional correctness over direct Verilog and direct CIRCT IR generation, while CIRCT optimization reduces post-synthesis AIG node counts. These results show that a compiler-mediated interface can make LLM-assisted hardware design more reliable, analyzable, and amenable to backend optimization. CPPL is available at https://github.com/SawyDust1228/CPPL.