2 papers
cs.AR2026
Google's Training Supercomputers from TPU v2 to Ironwood: Architectural Stability, Scale, Resilience, Power Efficiency, and Sustainability Across Five Generations
Norman P. Jouppi, Sridhar Lakshmanamurthy, Cliff Young +1
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 s…
cs.AR2026
Challenges and Research Directions for Large Language Model Inference Hardware
Xiaoyu Ma, David Patterson
Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerb…