arXiv AI October 28, 2026 By Yihan Wang, Peiyu Liu, Runyu Chen, Wei Xu

Less is more: learning what to profile for GPU kernel optimization

The paper introduces AutoProfiler, a feedback-driven framework that learns a deterministic profiling tree for GPU kernel optimization. By iteratively refining the tree with REWRITE and SPLIT operations guided by an LLM and empirical evaluation, it selects the most useful profiling metrics for each kernel rather than relying on a fixed set. Experiments on KernelBench demonstrate that this adaptive profiling approach outperforms static configurations under limited profiling budgets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

Hugging Face Trending Papers

6d ago

Less is more: learning what to profile for GPU kernel optimization

Large language models have recently shown strong potential for automatically optimizing GPU kernels, yet their effectiveness depends critically on the hardware information available to the kernel opti...

llms

arXiv Machine Learning

Sep 4

KernelFoundry: Hardware-aware evolutionary GPU kernel optimization

KernelFoundry is a hardware‑aware evolutionary framework that optimizes GPU kernels by combining MAP‑Elites quality‑diversity search, meta‑prompt evolution, and template‑based parameter tuning. It generates SYCL and CUDA kernels, outperforming baseline methods with an average 2.3× speedup on KernelBench. The system is distributed, supports remote hardware access, and offers a flexible user interface for diverse real‑world kernel generation tasks.

By Nina Wiedemann, Quentin Leboutet, Michael Paulitsch, Diana Wofk, Benjamin Ummenhofer

llms benchmarks

arXiv Machine Learning

Jun 26

Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization

arXiv:2606. 26453v1 Announce Type: new Abstract: We present KernelPro, a closed-loop multi-agent system that automatically generates, profiles, and iteratively optimizes GPU kernel code by integrating large language model (LLM) code generation with hardware profiler feedback and pluggable bottleneck detection tools.

By Jiading Gai, Shuai Zhang, Kaj Bostrom, Jin Huang, Vihang Patil, Haoyang Fang, Bernie Wang, Huzefa Rangwala, George Karypis

llms agents efficiency benchmarks

arXiv Machine Learning

Aug 4

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts

arXiv:2605. 30359v2 Announce Type: replace-cross Abstract: Generating high-performance GPU kernels remains challenging due to the need for both correctness and hardware-aware optimization.

By Zixuan Huang, Da Chen, Kecheng Huang, Lihao Yin, Xing Li, Huiling Zhen, Mingxuan Yuan, Zili Shao

llms rag

arXiv Machine Learning

Jun 9

Towards Automated Kernel Generation in the Era of LLMs

arXiv:2601. 15727v3 Announce Type: replace Abstract: The performance of modern AI systems is fundamentally constrained by the quality of their underlying GPU kernels, which translate high-level algorithmic semantics into low-level hardware operations.

By Yang Yu, Peiyu Zang, Chi Hsu Tsai, Haiming Wu, Yixin Shen, Jialing Zhang, Haoyu Wang, Zhiyou Xiao, Jingze Shi, Yuyu Luo, Wentao Zhang, Chunlei Men, Guang Liu, Yonghua Lin

llms agents benchmarks

arXiv AI

Jul 21

Harness Engineering for LLM-Driven GPU Kernel Generation

arXiv:2607. 17979v1 Announce Type: cross Abstract: Large language models (LLMs) can assist GPU kernel generation, but their practical effectiveness depends on whether generated code can be reliably constrained, validated, profiled, and selected.

By Yue Shui, Chenyu Ma, Hangfei Xu, Shengzhao Wen, Yanpeng Wang

llms agents

One email a morning, machine-written

Related stories

Less is more: learning what to profile for GPU kernel optimization

KernelFoundry: Hardware-aware evolutionary GPU kernel optimization

Optimizing CUDA like a Human: Micro-Profiling Tools as Expert Surrogates for LLM-Based GPU Kernel Optimization

Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts

Towards Automated Kernel Generation in the Era of LLMs

Harness Engineering for LLM-Driven GPU Kernel Generation