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。

In a move that shouldn't be that surprising, NVIDIA has announced that its popular CUDA platform is being ported to x86. The obvious angle here is that this will give NVIDIA a weapon against OpenCL ...

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 CUDA C++ 即可高效编写 Kernel，引发社区热议。尽管仍处早期，Tile 思维的抽象优势、社区探索迁移工具及实践尝试表明，cuTile 有 ...

快科技12月7日消息，日前NVIDIA正式推出了CUDA 13.1，官方将其定位为“自2006年CUDA平台诞生以来最大、最全面的升级”。 此次更新的核心亮点，是引入了革命性的CUDA Tile编程模型，标志着GPU编程范式迈入一个新的、更高抽象的阶段。 传统的GPU编程基于SIMT (单指令多 ...

In this Programming Throwdown podcast, Mark Harris from Nvidia describes CUDA programming for GPUs. “CUDA is a parallel computing platform and programming model invented by NVIDIA. It enables dramatic ...

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 ...

NVIDIA has announced that it is porting its popular GPU programming architecture to x86. Once the port is complete, developers will be able to choose from two different architectures—OpenCL and ...

Nvidia has released a public beta of CUDA 1.1, an update to the company's C-compiler and SDK for developing multi-core and parallel processing applications on GPUs, specifically Nvidia's 8-series GPUs ...

在 AI 领域，英伟达开发的 CUDA 是驱动大语言模型（LLM）训练和推理的核心计算引擎。 不过，CUDA 驱动的 LLM 推理面临着手动优化成本高、端到端延迟高等不足，需要进一步优化或者寻找更高效的替代方案。 近日，CMU 助理教授贾志豪（Zhihao Jia）团队创新玩法 ...

I just finished reading the new book by David Kirk and Wen-mei Hwu called Programming Massively Parallel Processors. The generic title notwithstanding, readers should not come to this book expecting ...