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.
- Intel Shipping 10nm NUCs to Major Retailers - December 3, 2018
- Haiku: Reviving the Dreams of BeOS - December 3, 2018
- The AWS ARM Chip That Wasn’t - November 28, 2018
- AWS re:Intervention | Gestalt IT Rundown: November 28, 2018 - November 28, 2018
- Germany Considering SOHO Router Security Rules - November 27, 2018
- Build the Droids You’re Looking For with AWS RoboMaker - November 26, 2018
- Intel’s Neural Compute Stick 2 - November 16, 2018
- Radeon Returns to the Data Center - November 16, 2018
- Raspberry Pi 3 A+: Quad-Core SoC for $25 - November 15, 2018
- Drobo + Nexsan = StorCentric - November 13, 2018