用大模型直接预测GPU内核性能，无需运行代码即可预估关键指标。
Omniwise: Predicting GPU Kernels Performance with LLMs
- 基于大模型的自监督微调框架，直接从内核代码预测性能。
- 在AMD MI250和MI300X上90%预测误差小于10%。
- 支持开发工具链集成，适合性能优化开发者使用。
近年来，深度神经网络（DNN）的快速发展彻底改变了人工智能，使模型具备前所未有的理解、生成和处理复杂数据的能力。这些强大架构已广泛应用于各类下游任务，解决了人类难以完成的问题。本文提出Omniwise，首个端到端、自监督微调的大型语言模型（LLM）用于GPU内核性能预测——这是性能分析中的全新应用。Omniwise具有模型无关性与轻量化特点，即使使用仅30亿参数的小模型也能取得优异效果。它可直接从内核代码预测内存带宽、缓存命中率、每秒浮点运算量（GFLOPs）和算术强度等关键性能指标，无需实际执行代码或依赖分析工具。在AMD MI250和MI300X架构上，该方法超过90%的预测结果相对误差小于10%。此外，我们还构建了在线推理服务和Visual Studio Code插件，实现大模型性能预测与开发者工作流的无缝集成。
原文摘要 · Abstract (English)
In recent years, the rapid advancement of deep neural networks (DNNs) has revolutionized artificial intelligence, enabling models with unprecedented capabilities in understanding, generating, and processing complex data. These powerful architectures have transformed a wide range of downstream applications, tackling tasks beyond human reach. In this paper, we introduce Omniwise, the first end-to-end, self-supervised fine-tuning pipeline that applies large language models (LLMs) to GPU kernel performance prediction--a novel use case in performance profiling. Omniwise is model-agnostic and lightweight, achieving strong results even with a small 3B-parameter model. It can predict key performance metrics, including memory bandwidth, cache hit rates, GFLOPs, and arithmetic intensity, directly from kernel code without the need for code execution or profiling tools. Our approach achieves over 90% of predictions within 10% relative error on GPU kernels executed on AMD MI250 and MI300X architectures. In addition to the pipeline, we develop an online inference server and a Visual Studio Code plugin that seamlessly integrate LLM-based performance prediction into developers' workflows.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。