Google Expands TPU Lineup with 8tx and 8i Max to Challenge Nvidia
Google has announced the expansion of its Tensor Processing Unit (TPU) lineup by introducing two new models, the 8tx and 8i Max. These specialized AI chips are designed to accelerate product iterations and better meet specific industry demands. This expansion strengthens Google's position as a major custom AI silicon provider, offering cost-effective alternatives to Nvidia GPUs for major cloud and enterprise customers. It reflects the broader industry shift toward specialized hardware for complex artificial intelligence workloads. The TPU 8tx is optimized for confidential computing and data security by cooperating with AMD CPUs, while the TPU 8i Max integrates two TPU chips in a single package to support long-context window AI applications. Google is scaling its custom chip business with major clients like Apple, Meta, Oracle, and Anthropic adopting the technology.
## BACKGROUND
Google's Tensor Processing Unit (TPU) is a proprietary application-specific integrated circuit (ASIC) developed specifically for neural network machine learning and designed to handle massive AI workloads more efficiently than traditional general-purpose processors. Confidential computing is a cloud computing technology that isolates sensitive data in a hardware-based Trusted Execution Environment (TEE) during processing to protect it from unauthorized access.