Evolution of Google’s TPUv4i
Source:
Norman P. Jouppi, Doe Hyun Yoon, Matthew Ashcraft, Mark Gottscho, Thomas B. Jablin, George Kurian, James Laudon, Sheng Li, Peter Ma, Xiaoyu Ma, Nishant Patil, Sushma Prasad, Clifford Young, Zongwei Zhou (Google); David Patterson (Google / Berkeley)
Find technical paper here.
2021 ACM/IEEE 48th Annual International Symposium on Computer Architecture (ISCA)
Abstract–”Google deployed several TPU generations since 2015, teaching us lessons that changed our views: semiconductor technology advances unequally; compiler compatibility trumps binary compatibility, especially for VLIW domain-specific architectures (DSA); target total cost of ownership vs initial cost; support multi-tenancy; deep neural networks (DNN) grow 1.5X annually; DNN advances evolve workloads; some inference tasks require floating point; inference DSAs need air-cooling; apps limit latency, not batch size; and backwards ML compatibility helps deploy DNNs quickly. These lessons molded TPUv4i, an inference DSA deployed since 2020.”
Leave a Reply