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.
- You’re Wrong About Data Protection Policy – The On-Premise IT Roundtable - May 14, 2019
- Gestalt News for the Week of May 13, 2019 - May 13, 2019
- The Perpetual Plugin Problem | Gestalt IT Rundown: May 8, 2019 - May 8, 2019
- Gestalt News for the Week of May 6 ,2019 - May 6, 2019
- Azure and VMware Team Up | Gestalt IT Rundown: May 1, 2019 - May 1, 2019
- Bringing Yourself to Work – The On-Premise IT Roundtable - April 30, 2019
- Gestalt News for the Week of April 29, 2019 - April 29, 2019
- Docker Partners With Arm | Gestalt IT Rundown: April 24, 2019 - April 24, 2019
- Gestalt News for the Week of April 22, 2019 - April 22, 2019
- Patent Peace in Our Time | Gestalt IT Rundown: April 17, 2019 - April 17, 2019