I’m not going to lie, when I saw the headline to this article, I thought it was going to talk about AMD starting to become a force in the ML/AI workload market. Instead it makes the much more cogent case that FPGAs and ASIC will supplement the industry’s need for GPUs to AI processing. Those with high volume and specialized workloads will be faster to supplant GPUs with more specialized silicon. But the general parallel processing capabilities of GPUs should keep them in use for AI workloads in the foreseeable future. It will be interesting to see what the lower cost efficiencies of FPGAs and ASICs will enable in this emerging field.
Kurt Marko comments:
Note that the entire market for AI acceleration hardware is expanding, so these new forms are so much displacing GPUs, at least initially, but supplementing them.
- AI All The Things | Gestalt IT Rundown: February 13, 2019 - February 13, 2019
- Gestalt News for the Week of February 11, 2019 - February 11, 2019
- Intel’s Swan Song | Gestalt IT Rundown: February 6, 2019 - February 6, 2019
- You Need Sensors for Analytics – The On-Premise IT Roundtable - February 5, 2019
- Gestalt News for the Week of February 4, 2019 - February 4, 2019
- Necessary NAS Nomenclature - February 1, 2019
- A Shortage in Common Sense: The Myth of the Talent Gap - January 31, 2019
- Olympic Hacking in Japan | Gestalt IT Rundown: January 30, 2019 - January 30, 2019
- Kubernetes: Theory and Practice - January 30, 2019
- Compute Module 3+ on sale now from $25 - January 29, 2019