How embedded FPGAs fit AI applications
June 18, 2018 // By Alok Sanghavi, Achronix Semiconductor Corp.
Artificial intelligence, and machine learning in particular, is reshaping the way the world works, opening up countless opportunities in industry and commerce, but the optimum hardware architecture to support neural network evolution, diversity, training and inferencing is not determined. Alok Sanghavi surveys the landscape and makes the case for embedded FPGAs.
Applications span diverse markets such as autonomous driving, medical diagnostics, home appliances, industrial automation, adaptive websites, financial analytics and network infrastructure.
These applications, especially when implemented on the edge, demand high performance and, low latency to respond successfully to real-time changes in conditions. They also require low power consumption, rendering energy-intensive cloud-based solutions unusable. A further requirement is for these embedded systems to always be on and ready to respond even in the absence of a network connection to the cloud. This combination of factors calls for a change in the way that hardware is designed.
Related Semiconductor IP
- eFPGA
- Radiation-Hardened eFPGA
- eFPGA IP as a synthesizable RTL core
- eFPGA IP and FPGA Software Built on GLOBALFOUNDRIES 22FDX
- eFPGA IP and FPGA Software Built on Samsung Foundry 28nm FDSOI
Related White Papers
- Enabling error resilience throughout the embedded system
- Developing FPGA applications for Edition 2 of the IEC 61508 Safety Standard
- Introduction to OpenVG for embedded 2D graphics applications
- Real-Time Trace: A Better Way to Debug Embedded Applications
Latest White Papers
- New Realities Demand a New Approach to System Verification and Validation
- How silicon and circuit optimizations help FPGAs offer lower size, power and cost in video bridging applications
- Sustainable Hardware Specialization
- PCIe IP With Enhanced Security For The Automotive Market
- Top 5 Reasons why CPU is the Best Processor for AI Inference