Ironwood TPU

Ironwood TPU is the TPU generation discussed in E228｜谷歌TPU能撼动英伟达吗？前TPU工程师首次揭秘. Henry describes Ironwood V7 as having meaningfully improved peak FLOPS and memory bandwidth, and says it is aimed especially at large-scale inference needs such as lower latency, higher throughput, and enough memory bandwidth for LLM decode.

In the source, Ironwood matters less as a standalone chip benchmark than as evidence of Google shifting TPU design toward the inference-heavy economics of deployed Gemini and cloud workloads. Its value still depends on XLA, TPU Pod design, Advanced Packaging, supply ramp, and integration into Google Cloud.

Connections

• TPU, Google, Gemini, and Google Cloud — platform context.
• Memory Wall, High Bandwidth Memory, and AI Inference Cost Structure — inference bottleneck and cost context.
• AI Chip Specialization and ASIC Workload Prediction Risk — specialization and model-churn tradeoff.