← Back to KHAO

Google · Intel · Blackwell · Agentic AI · Nvidia · India ·

Google commits to multiyear Intel CPU deployments, will partner with chipmaker on custom IPU development

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

◌ Single Source

Switch Pyramid.

Intel has announced a multiyear collaboration with Google that will see the hyperscaler commit to using multiple generations of Intel CPUs in its data centers.

Key facts

Summary

The partners will all co-develop custom ASIC (application-specific integrated circuit)-based IPUs (infrastructure processing units) for “scaling… heterogeneous AI systems.” Google and Intel first announced they were collaborating on the development of an IPU in October 2021, naming the initial hardware offering ‘Mount Evans.’ The IPU helps hyperscalers offload infrastructure tasks from CPUs to IPUs, freeing up server CPU cycles for revenue-generating tasks. The agreement will also see Google deploy Intel’s Xeon 6 CPUs for training and inferencing workloads, and commit to using “multiple” future generations of the hardware across its Google Cloud Platform (GCP). In May of that same year, the chipmaker unveiled three new additions to its Xeon 6 family of processors, equipped with P-cores (Performance-cores).

Read full article at Datacenter Dynamics →

#Google #Intel #Blackwell #Agentic AI #Nvidia #India