Google Inc.

Erik Karl Norden

Norman Paul Jouppi

Martin Guy Dixon

Parthasarathy Ranganathan

Quoc V Le

Sridhar Lakshmanamurthy

Sheng Li

Liqun Cheng

Daniel Stodolsky

Aspects of the disclosure are directed to a heterogeneous machine learning accelerator system with compute and memory nodes connected by high speed chip-to-chip interconnects. While existing remote/disaggregated memory may require memory expansion via remote processing units, aspects of the disclosure add memory nodes into machine learning accelerator clusters via the chip-to-chip interconnects without needing assistance from remote processing units to achieve higher performance, simpler software stack, and/or lower cost. The memory nodes may support prefetch and intelligent compression to enable the use of low cost memory without performance degradation.

Heterogeneous ML accelerator cluster with flexible system resource balance

Growing community of inventors

San Jose, CA, United States of America

Erik Karl Norden