CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language
Source
Qi Fan, An Zou, Yehan Ma
Author
Qi Fan, An Zou, Yehan Ma
Date
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Text2CUDA is a harder loop than transpilation: the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → must implement and validate the kernel. The paper names the validation weakness, reliance on predefined test inputs, that any kernel-generation agent inherits.
articleRealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI FrameworksJinjun Huang, Zhongzhen Wen, Tongtong Xu, Meng Yan, Xin Xia, Zhongxin Liu
articleHarness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven SystemsPaul Barbaste, Tristan Darrigol, Germain Vu, Tom Wiltberger
articleHarness Engineering for Predictable Agentic Systems: An Empirical Study of Deterministic Execution ConstraintsSaransh Dhage