https://www.nextplatform.com/2018/10/02/inferring-the-future-of-the-fpga-and-then-making-it/ In-depth coverage of high-end computing at large enterprises, supercomputing centers, hyperscale data centers, and public clouds. Thu, 03 Feb 2022 18:11:21 +0000 hourly 1 https://wordpress.org/?v=6.7.1 https://www.nextplatform.com/2018/10/02/inferring-the-future-of-the-fpga-and-then-making-it/#comment-105940 Mon, 08 Oct 2018 05:47:01 +0000 http://www.nextplatform.com/?p=38463#comment-105940 Interesting article. Just one thing you forgot to mention: inference done on user’s devices. Why do you need edge inference if you can do it on the device itself? You can do most of your training in the data center then deploy the model to the device where the final training and inference can be performed. The phone makers have been very busy in the last 12 months AI wise – just check the latest press releases.

]]> https://www.nextplatform.com/2018/10/02/inferring-the-future-of-the-fpga-and-then-making-it/#comment-105726 Wed, 03 Oct 2018 23:17:26 +0000 http://www.nextplatform.com/?p=38463#comment-105726 This is a very exciting time for the FPGA Developer; however, the problem with chips like these is the long, long software development time required and development tools that are difficult to use and little documentation.

]]>