新的研究表明，在 GPU 性能方面，自动生成的代码开始超越手工编写的 CUDA 内核。这种转变归因于大规模优化复杂 CUDA 内核的难度。这一发展预示着未来 AI 生成的代码可能成为最大化硬件效率的标准。 AI
影响 AI 生成的代码在优化 GPU 性能方面显示出潜力，可能带来更高效的硬件利用率。
排序理由 该集群讨论了一篇研究论文及其关于 GPU 代码生成的发现。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
GPUs are leaving performance on the table. Closing the gap between theoretical peak and real-world throughput is nearly impossible when hand-tuning CUDA kernels at scale. So why are hand-written CUDA kernels losing to auto-generated ones? Mohamed Abdelfattah at Makora has a
GPUs are leaving performance on the table. Closing the gap between theoretical peak and real-world throughput is nearly impossible when hand-tuning CUDA kernels at scale. So why are hand-written CUDA kernels losing to auto-generated ones? Mohamed Abdelfattah at Makora has a