AI Chips Are Taking Over: Seven Specialized Processors from Tech Giants

We're at the dawn of a new era in computing, marked by the rise of cutting-edge technologies that promise to significantly enhance AI's abilities. Recently, conversations have surged around a novel computing concept called the Language Processing Unit (LPU), noted for its exceptional performance with large language models. Our latest free weekly newsletter explored its origins and functionality, providing insights into this industry breakthrough.

Additionally, we've observed a pivotal shift in the computing landscape, with expectations that every major cloud platform will soon start producing its own AI chips. This move signifies a departure from the traditional reliance on NVIDIA GPUs for generative AI projects. Here's a brief overview of the market updates:

• Google is at the forefront of improving its Tensor Processing Unit (TPU) technology for Google Cloud.

• OpenAI is investigating the potential of designing proprietary AI chips.

• Microsoft announced two custom-designed chips: the Microsoft Azure Maia AI Accelerator for large language model training and inferencing and the Microsoft Azure Cobalt CPU for general-purpose compute workloads on the Microsoft Cloud.

• Amazon has rolled out its Inferentia AI chip and the second-generation machine learning (ML) accelerator, AWS Trainium.

• Apple has been developing its series of custom chips and unveiled M3, M3 Pro, and M3 Max processors, which could be extended to specialized AI tasks.

• Meta plans to deploy a new version of a custom chip aimed at supporting its artificial intelligence (AI) push, according to Reuters.

• Huawei is reportedly prioritizing AI and slowing the production of its premium Mate 60 phones as the demand for their AI chips has soared.

What are the other trends we see on the market? Read the full article to learn about it:

We post helpful lists and bite-sized explanations daily on our X (Twitter). Let’s connect!