English(EN) Beyond Experience: Knowledge-Guided Evolution for NPU Kernel Generation

新AI方法使用知识库进行NPU内核生成

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

研究人员开发了ASCENDEVOLVE，一种新颖的NPU内核生成方法，该方法超越了仅依赖经验。这种新方法整合了一个大型外部知识库，该知识库源自平台文档和算子存储库，以指导内核搜索过程。通过索引和检索相关信息，ASCENDEVOLVE能够播种多样化的实现策略，辅助纠错，并优化候选内核。该系统在Ascend C算子的CANN-Bench基准测试中表现出显著的改进，性能优于Reflexion和OpenEvolve等现有方法。 AI

影响这种知识引导的方法可以通过实现更复杂的内核生成来提高AI加速器的性能和效率。

排序理由学术论文，详细介绍了一种新的NPU内核生成方法。[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 →

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; 学术论文，详细介绍了一种新的NPU内核生成方法。[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: paper, infra; 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: 2 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Xi Chen, Ming Shen, Haotian Yan, Ruoyu Sun, Tianjun Yao · 2026-10-21 04:00

超越体验：面向NPU内核生成的知识引导演化

arXiv:2610.27588v1 Announce Type: new Abstract: LLM agents have become capable kernel engineers on mainstream GPU stacks, but they struggle on emerging accelerators such as Ascend NPUs, whose programming model is barely represented in pretraining data. Recent NPU agents address t…

本文如何被排名

报道来源 [1]

超越体验：面向NPU内核生成的知识引导演化

相关实体

相关话题