This paper (to appear in the July/August 2026 issue of IEEE Micro magazine) summarizes five generations of Google s TPUs, from TPU v2 to Ironwood, highlighting their evolution as scalable, resilient, power-efficient, sustainable supercomputers for AI training. It details the TPU s stable architecture, which has surprisingly easily accommodated the rapidly changing deep neural network workloads, such as the rise of Transformers. Key advancements over eight years include 10x increase in HBM capacity and bandwidth per node, a 100x increase in peak node performance, and a 3600x increase in supercomputer performance. The paper also discusses the role of optical circuit switches, built-in self test, and hardware replay in enhancing resilience and how TPU's environmental impact is reduced with substantial improvements in performance per Watt and in carbon emissions per floating point operation. It concludes by identifying six features that may well characterize successful training accelerators of this decade.

翻译：本文（将发表于2026年7月/8月期《IEEE Micro》杂志）总结了谷歌TPU从v2到Ironwood的五代演进，重点阐述了这些超级计算机作为可扩展、高弹性、高能效、可持续的人工智能训练系统的发展历程。文章详述了TPU稳定的架构设计——该架构出人意料地轻松适应了快速变革的深度神经网络工作负载，如Transformer的兴起。八年来关键技术指标取得突破：每节点HBM容量与带宽提升10倍，峰值节点性能提升100倍，超级计算机性能提升3600倍。本文还讨论了光路交换机、内置自检及硬件回放在增强弹性方面的作用，并指出TPU通过每瓦性能及每浮点运算碳排放量的显著改善来降低环境影响。最后，文章归纳了可能定义本十年成功训练加速器的六大特征。