First of two parts: ARM Fellow Rob Aitken digs into a technique that can increase power savings by 4X to 6X at established nodes.
ARM fellow Rob Aitken talks about what is NTC, why it has taken so long to catch on, and the enormous energy savings possible using this technique at established process nodes.
How pervasive will this new wireless technology actually become, and what problems still need to be solved?
Goal is to improve quality while reducing time to revenue, but it’s not always so clear-cut.
Next-gen lithography technology resurfaces for a variety of tasks.
So far there are no tools and no clear methodology to eliminating bugs. That would require understanding what an AI bug actually is.
This more than Moore technology is still ramping up, and problems need to be solved, but it could lead to some fundamental changes.
As advanced-node chips are added into cars, and usage models shift inside of data centers, new questions surface about reliability.
Is the industry heading toward another hardware/software divide in machine learning? Both sides have different objectives.
Cost of porting tools and IP will limit choices at partial nodes and create confusion at others.
Are optimizations really a zero sum gain? Where to gamble and when to play it safe.
This more than Moore technology is still ramping up, and problems need to be solved, but it could lead to some fundamental changes.
Why new approaches are needed to tie together training and inferencing.
The race is on to simulate thermal and electromagnetic effects.
Heat is becoming a bigger problem for chips developed at new process nodes and for automotive and industrial applications.
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
[…] ARM Fellow Rob Aitken said energy savings are significant using the same exact processors differently. Moreover, it’s most effective at established process geometries where there are no finFETs. But it isn’t a simple process. (For a deeper understanding of this subject, click here). […]