Scale By the Bay Scale By the Bay

Thursday, October 28, 2021

- PDT
Panel: The Hardware vs Software
Anna Goldie
Anna Goldie
Google Brain / Stanford, Staff Research Scientist
Bryan Cantrill
Bryan Cantrill
Oxide Computer, co-founder and CTO
Vitaly Gordon
Vitaly Gordon
Faros AI, Co-founder and CEO
David Kanter
David Kanter
MLCommons™, Founder and the Executive Director
Alexander O'Connor
Alexander O'Connor
Autodesk, Senior Manager, Data Science & Machine Learning

This panel brings together builders of hardware and software that drive the post-cloud and AI landscape of tomorrow.  How will the hardware changes affect software development?  What drives what?  Join us for a famous debate format that is an SBTB tradition!

- PDT
Chip Floorplanning with Deep Reinforcement Learning
Anna Goldie
Anna Goldie
Google Brain / Stanford, Staff Research Scientist

In this talk, I will describe a reinforcement learning (RL) method for chip floorplanning, the engineering problem of designing the physical layout of a computer chip. Chip floorplanning ordinarily requires weeks or months of effort by physical design engineers to produce manufacturable layouts. Our method generates floorplans in under six hours that are superior or comparable to humans in all key metrics, including power consumption, performance, and chip area. To achieve this, we pose chip floorplanning as a reinforcement learning problem, and develop a novel edge-based graph convolutional neural network architecture capable of learning rich and transferrable representations of the chip. Our method was used in the design of the next generation of Google’s artificial intelligence (AI) accelerators (TPU).