Apple's neural engine and Nvidia's Tensor Cores are both designed to accelerate AI workloads, but they work in different ways and are optimized for different types of tasks.

Apple's neural engine is a dedicated block of hardware within the M series chips that is specifically designed to accelerate machine learning tasks on Apple devices. It uses Apple's own machine learning frameworks and libraries to perform tasks such as image recognition, natural language processing, and other AI-related tasks.

Nvidia's Tensor Cores, on the other hand, are specialized hardware units within Nvidia's GPUs that are designed to perform matrix operations, which are a fundamental building block of many AI and deep learning algorithms. Tensor Cores can accelerate these operations by performing many calculations in parallel, allowing for faster training and inference of AI models.

In summary, while both Apple's neural engine and Nvidia's Tensor Cores are designed to accelerate AI workloads, they work in different ways and are optimized for different types of tasks. Is there anything else you would like to know?

看上去基本上是一样的，估计是算力上的差别，软件层面上也有不同。

【 在 beaver 的大作中提到: 】
: 问个问题，苹果的芯片号称什么智能单元，那个处理器，跟黄仁勋的用于人工智能的芯片的主要区别是什么？
: 都说是智能智能的，是一回事么？
:
--
FROM 222.129.7.*