AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units

arXiv:2601.07160v2 Announce Type: replace Abstract: To meet the ever-increasing demand for computational efficiency, Neural Processing Units (NPUs) have become critical in modern AI infrastructure. However, unlocking their full potential requires developing high-performance compute kernels using vendor-specific Domain-Specific Languages (DSLs), a task that demands deep hardware expertise and is labor-intensive. While Large Language Models (LLMs) have shown promise in general code generation, the