Tutoring LLM into a Better CUDA Optimizer
Not on the map. Why?
Abstract (arXiv)
Recent leaps in large language models (LLMs) caused a revolution in programming tools (like GitHub Copilot) that can help with code generation, debugging, and even performance optimization. In this paper, we focus on the capabilities of the most recent reasoning models to generate optimized CUDA code for predefined, well-known tasks. Our objective is to determine which types of code optimizations and parallel patterns the LLMs can perform by themselves and whether they can be improved by tutoring (providing more detailed hints and guidelines in the prompt). The generated solutions were evaluated both automatically (for correctness and speedup) and manually (code reviews) to provide a more detailed perspective. We also tried an interactive approach where the LLM can fix its previous mistakes within a session. The results indicate that LLMs are quite skilled coders; however, they require tutoring to reach optimized solutions provided by parallel computing experts.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 3 of its 6 references that are in the map. First posted on arXiv 19 Oct 2025.
Builds on
3 of 6 references.
References · 3
- 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
- 2024A Survey on Large Language Models for Code Generationcited by 646
- 2024Can Large Language Models Write Parallel Code?cited by 36
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
- 2026CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language
- 2025Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation
- 2024Performance-Aligned LLMs for Generating Fast Code
- 2025REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving
- 2025Holistic Evaluation of State-of-the-Art LLMs for Code Generation
- 2025Data-efficient LLM Fine-tuning for Code Generation
- 2026Exploring the Role of LLMs in HPC Programming: A Survey