机器之心报道机器之心编辑部几个小时前，NVIDIA CUDA Toolkit 13.1 正式发布，英伟达官方表示：「这是 20 年来最大的一次更新。」这个自 2006 年 CUDA 平台诞生以来规模最大、最全面的更新包括：NVIDIA CUDA Tile 的发布，这是英伟达基于 tile 的编程模型，可用于抽象化专用硬件，包括张量核心。Runtime API exposure of ...

作者：紫晗编辑：李宝珠转载请联系本公众号获得授权，并标明来源2025 年 12 月，在 CUDA 发布近二十年后，NVIDIA 推出新的 GPU 编程入口「cuTile」，通过 Tile-based 编程模型重构 GPU 内核，使开发者无需深入 ...

NVIDIA’s CUDA is a general purpose parallel computing platform and programming model that accelerates deep learning and other compute-intensive apps by taking advantage of the parallel processing ...

TL;DR: NVIDIA CUDA 13.1 introduces the largest update in two decades, featuring CUDA Tile programming to simplify AI development on Blackwell GPUs. By abstracting tensor core operations and automating ...

Nvidia has updated its CUDA software platform, adding a programming model designed to simplify GPU management. Added in what the chip giant claims is its “biggest evolution” since its debut back in ...

This isn’t a review, but given the popularity of my last CUDA book review, I thought I’d mention that Addison-Wesley has published a new book called CUDA by Example: An Introduction to General-Purpose ...

Programmers have been interested in leveraging the highly parallel processing power of video cards to speed up applications that are not graphic in nature for a long time. Here, I explain how to do ...

A hands-on introduction to parallel programming and optimizations for 1000+ core GPU processors, their architecture, the CUDA programming model, and performance analysis. Students implement various ...

Graphics processing units (GPUs) are traditionally designed to handle graphics computational tasks, such as image and video processing and rendering, 2D and 3D graphics, vectoring, and more.

Support for unified memory across CPUs and GPUs in accelerated computing systems is the final piece of a programming puzzle that we have been assembling for about ten years now. Unified memory has a ...