Artificial Intelligence · 26.08.2026, 09:48 UTC
QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog Generation
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | arXiv cs.LG ↗ |
| Veröffentlicht | 26.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
arXiv:2602.00704v2 Announce Type: replace Abstract: The generation of Register-Transfer Level (RTL) code is a crucial yet labor-intensive step in digital hardware design, traditionally requiring engineers to manually translate complex specifications into thousands of lines of synthesizable Hardware Description Language (HDL) code. While Large Language Models (LLMs) have shown promise in automating this process, existing approaches--including fine-tuned domain-specific models and advanced agent-based systems--struggle to scale to industrial IP-level design tasks. We identify three key challenges: (1) handling long, highly detailed documents, where critical interface constraints become buried in unrelated submodule descriptions; (2) generating long RTL code, where both syntactic and semantic correctness degrade sharply with increasing output length; and (3) navigating the complex debugging cycles required for functional verification through simulation and waveform analysis. To overcome these challenges, we propose ChipV-RTL, a multi-agent framework that leverages information locality in modular hardware design. ChipV-RTL decomposes the long-document to long-code generation problem into a set of short-document, short-code tasks, enabling scalable generation and debugging. Specifically, ChipV-RTL integrates hierarchical document partitioning, task planning, localized code generation, interface-consistent merging, and AST-guided locality-aware debugging. Experiments on RealBench, an IP-level Verilog generation benchmark, demonstrate that ChipV-RTL substantially outperforms …
Maßnahmen
⬇ Als MarkdownVerwandte Beiträge
- info Bill Gates says we’ve passed AI’s danger thresholds. Now what?
- info IBM Releases Granite 4.2: Bringing Native Reasoning and Agentic RL to Open Enterprise Models
- info ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives
- info RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates