paper-with-me

Papers

MaxKernel: Agentic Kernel Generation for TPUs

2026-09-03 · Shangkun Wang, Nina Cai, Charles Hoong, Julian Walker, Gerson Kroiz, George Vanica, Deepak Patil, Andi Gavrilescu, Hassan Sipra, Sethu Sankaran arxiv

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-level expertise. Large Language Models (LLM) can be leveraged together with real-time compiler feedback to build agentic systems for kernel generation. In this work, we present MaxKernel, a multi-agent system that implements three distinct paradigms for TPU kernel development: (1) a Human-in-the-Loop (HITL) agent for collaborative, step-by-step design; (2) an Autonomous (Auto) agent that executes a fully automated, metric/trace-driven optimization loop; and (3) a Graph-Based Autonomous Search that scales the Auto agent for global exploration of the design space. All three paradigms leverage a shared pool of specialized sub-agents to handle planning, implementation, self-debugging, testing, and hardware profiling. We evaluate MaxKernel on JaxBench, a comprehensive suite of 50 diverse kernel tasks for TPUs, alongside complex, real-world workloads from state-of-the-art open-source models. We demonstrate that MaxKernel consistently generates highly optimized implementations, matching expert hand-tuned baselines and delivering significant performance across the benchmark. Our agent is open-sourced and available https://github.com/AI-Hypercomputer/accelerator-agents/tree/main/MaxKernel.

📄 PDF Abstract BibTeX arXiv:2609.04523

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation

2025-07-20 · Zhongzhen Wen, Yinghui Zhang, Zhong Li, Zhongxin Liu 외 arxiv

The automatic generation of deep learning (DL) kernels using large language models (LLMs) has emerged as a promising approach to reduce the manual effort and hardware-specific expertise required for writing high-performa…

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

2026-04-01 · Tara Saba, Zhiyang Chen, Jikai Jason Li, Anne Ouyang 외 arxiv

High-performance GPU kernels are critical to modern machine learning systems, yet developing them remains a manual, expert-driven process. Recent work has explored using LLMs to automate kernel generation, but generated …

Ragged Paged Attention: A High-Performance and Flexible LLM Inference Kernel for TPU

2026-04-16 · Jevin Jiang, Ying Chen, Blake A. Hechtman, Fenghui Zhang 외 arxiv

Large Language Model (LLM) deployment is increasingly shifting to cost-efficient accelerators like Google's Tensor Processing Units (TPUs), prioritizing both performance and total cost of ownership (TCO). However, existi…

Towards Automated Kernel Generation in the Era of LLMs

2026-01-22 · Yang Yu, Peiyu Zang, Chi Hsu Tsai, Haiming Wu 외 arxiv

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. Achieving near-optima…

KernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement Learning

2026-02-15 · Kris Shengjun Dong, Sahil Modi, Dima Nikiforov, Sana Damani 외 arxiv

Optimizing CUDA code across multiple generations of GPU architectures is challenging, as achieving peak performance requires an extensive exploration of an increasingly complex, hardware-specific optimization space. Trad…

Reinforcement Learning