DecoRTL: A Run-time Decoding Framework for RTL Code Generation with LLMs

TL;DR

DecoRTL introduces a run-time decoding strategy for RTL code generation with LLMs, improving correctness and validity by being syntax-aware and contrastive, without additional training.

Contribution

The paper proposes DecoRTL, a novel inference-time decoding method that enhances RTL code generation by integrating syntax-aware temperature adaptation and self-consistency sampling.

Findings

Significant improvements in syntactic validity and correctness.

Enhanced output diversity with minimal performance overhead.

Effective across multiple open-source LLMs on the VerilogEval benchmark.

Abstract

As one of their many applications, large language models (LLMs) have recently shown promise in automating register transfer level (RTL) code generation. However, conventional LLM decoding strategies, originally designed for natural language, often fail to meet the structural and semantic demands of RTL, leading to hallucinated, repetitive, or invalid code outputs. In this paper, we first investigate the root causes of these decoding failures through an empirical analysis of token-level entropy during RTL generation. Our findings reveal that LLMs exhibit low confidence in regions of structural ambiguity or semantic complexity, showing that standard decoding strategies fail to differentiate between regions requiring determinism (syntax-critical regions) and those that benefit from creative exploratory variability (design-critical regions). Then, to overcome this, we introduce DecoRTL, a novel run-time decoding strategy, that is both syntax-aware and contrastive for RTL code generation. DecoRTL integrates two complementary components: (i) self-consistency sampling, which generates multiple candidates and re-ranks them based on token-level agreement to promote correctness while maintaining diversity; and (ii) syntax-aware temperature adaptation, which classifies tokens by their syntactical and functional roles and adjusts the sampling temperature accordingly, enforcing low temperature for syntax-critical tokens and higher temperature for exploratory ones. Our approach operates entirely at inference time without requiring any additional model fine-tuning. Through evaluations on multiple open-source LLMs using the VerilogEval benchmark, we demonstrate significant improvements in syntactic validity, functional correctness, and output diversity, while the execution overhead (performance overhead) is imperceptible.