Nvidia’s Next-Gen Blackwell Platform Set to Launch on Google Cloud in Early 2025

expects Google to be one of its key customers for the new Blackwell platform. Liquid cooling is becoming increasingly popular in data centers as it allows for more efficient cooling of high-performance hardware, enabling better performance and longevity of the components.

In addition to Nvidia’s offerings, Google Cloud is introducing its own AI accelerators, including the GA110, a GPU optimized for machine learning training workloads. This GPU is designed to provide high performance and efficiency for training deep learning models, helping customers accelerate their AI projects on Google Cloud Platform.

Google is also introducing the GA100, a new GPU designed for inferencing workloads. This GPU is optimized for running pre-trained AI models and performing real-time predictions, making it ideal for applications such as image recognition, natural language processing, and recommendation systems.

Overall, these new instance types and accelerators demonstrate Google Cloud’s commitment to providing cutting-edge technology for AI and HPC workloads, giving customers the tools they need to drive innovation and solve complex problems in their industries.