PulseAugur
中
实时 04:27:07
English(EN) CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning

AI系统CUDA-L2在矩阵乘法方面超越NVIDIA的cuBLAS

研究人员开发了CUDA-L2系统,该系统利用大型语言模型和强化学习自动优化矩阵乘法CUDA核函数。该系统通过探索人类优化难以企及的巨大配置空间,显著优于包括NVIDIA的cuBLAS和cuBLASLt库在内的现有基线。CUDA-L2在离线和模拟实时推理场景中均实现了显著的加速,展示了AI驱动的自动化在性能关键型计算任务中的潜力。 AI

影响 展示了AI在高度优化的计算核函数中显著提升性能的能力,可能影响科学计算和AI基础设施。

排序理由 该集群描述了一篇详细介绍使用AI技术优化计算核函数的新颖系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

AI系统CUDA-L2在矩阵乘法方面超越NVIDIA的cuBLAS

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群描述了一篇详细介绍使用AI技术优化计算核函数的新颖系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra, paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
78 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Songqiao Su, Xiaoya Li, Albert Wang, Guoyin Wang, Jiwei Li, Chris Shum ·

    CUDA-L2:通过强化学习超越 cuBLAS 的矩阵乘法性能

    arXiv:2512.02551v3 Announce Type: replace-cross Abstract: In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels. Using CUDA execu…