A Community for IT & Channel Technology Insiders

channelbytes tech talks
Google’s new reinforcement-learning AI optimizes chip placement

Written by Nick Dinsmoor

March 27, 2020

Google’s new reinforcement-learning AI optimizes chip placement

Traditionally, engineers have manually designed computer chip configurations that minimize the amount of wire used to increase efficiencies. Then, automation software simulates and verified performance which can take up to 30 hours for a single floor plan.

“In response to these challenges, Google researchers Anna Goldie and Azalia Mirhoseini took a new approach: reinforcement learning… After checking the designs with the electronic design automation software, the researchers found that many of the algorithm’s floor plans performed better than those designed by human engineers.”

Hopefully these algorithms will speed up design processes and lead to accelerated AI advancement.

3D TETRIS

~

Advanced Web Application Firewall (WAF)

Protection for today's new breed of cyber threats. Trusted by Chase Bank, JetBlue, Starbucks, & more.

Related Articles

How ESS Helps Push CAPEX into OPEX While Lowering TCO

How ESS Helps Push CAPEX into OPEX While Lowering TCO

Transforming CAPEX (capital expenses) into OPEX (operational expenses) is a great way to spread expenses out over time. To help our clients achieve this goal while reducing their TCO costs, Rahi Systems now offers our signature ELEVATE services as a subscription-based...

The Bird Rock Systems 2021 Guide to Cybersecurity Trends & Threats

The Bird Rock Systems 2021 Guide to Cybersecurity Trends & Threats

Many of us are looking forward to putting 2020 behind us. As we turn our attention to 2021, it’s critical that organizations in all verticals take time to prepare themselves for the challenges and potential cybersecurity attacks 2021 is likely to bring.  Familiar...

0 Comments

0 Comments

Submit a Comment

Your email address will not be published. Required fields are marked *

two × 4 =