KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

原文：KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

作者：Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal Goyal, Rohit Singh Rathaur

来源：arXiv cs.AI（人工智能）

正文

Computer Science > Distributed, Parallel, and Cluster Computing

arXiv:2609.30059v1 (cs)

[Submitted on 24 Sep 2026]

Title:KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization

Authors:Aheli Poddar, Sanskar Prasad, Arindam Samanta, Subha Chakraborty, Vishal Goyal, Rohit Singh Rathaur

View a PDF of the paper titled KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization, by Aheli Poddar and 5 other authors

View PDF

HTML (experimental)

Abstract:Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted kernel optimizers can close this gap for standalone kernels, yet treat compiled models as black boxes, generally optimizing individual standalone kernels without respecting the compiler’s structural decisions or verifying the model end-to-end. We present KernelOPT, a multi-agent system that treats compiled models as structured artifacts. It preserves vendor library calls (cuBLAS, cuDNN) and exclusively targets generated Triton sub-kernels using five profiling-guided LLM agents. A four-gate verification cascade of static validation, multi-seed correctness, model-level float64-fallback verification, and performance gating filters candidates during optimization and verifies the re-stitched model end-to-end. If no candidate passes all four gates, the system preserves the compiler baseline. The system accepts PyTorch this http URL, standalone Triton kernels, and Helion kernels. Evaluated on 250 KernelBench problems, KernelOPT achieves geometric mean speedups over \texttt{this http URL} of 1.40$\times$ (Level 1: 51/100), 1.15$\times$ (Level 2: 31/100), and 1.07$\times$ (Level 3: 12/50) across all problems.

Subjects:

Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as:

arXiv:2609.30059 [cs.DC]

(or

arXiv:2609.30059v1 [cs.DC] for this version)

https://doi.org/10.48550/arXiv.2609.30059

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

分布式计算 · 人工智能 · 机器学习

由「前沿雷达」于 2026-09-25 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。