This paper examines the future of deep neural networks, including sparse networks, low precision and ultra-low precision, and compares the performance of Intel® Arria® 10 and Intel Stratix® 10 FPGAs against NVIDIA graphics processing units (GPUs).
This white paper describes how Intel FPGAs leverage the OpenCL platform to meet the image processing and classification needs of today's image-centric world.
A detailed look at the architecture and performance of our Deep Learning Accelerator IP.
- Intel® FPGAs Power Microsoft* Project Brainwave AI
- Microsoft Turbocharges AI with Intel FPGAs. You Can, Too
- Real-Time AI: Microsoft Announces Preview of Project Brainwave
- Intel FPGAs Bring Power to Artificial Intelligence in Microsoft Azure
- Machine Learning on Intel FPGAs
- Microsoft’s Plans for FPGAs in Azure Should Worry Traditional Chipmakers
- FPGAs for Deep Learning-Based Vision Processing
- Myth Busted: General Purpose CPUs Can’t Tackle Deep Neural Network Training
- CERN openlab Explores New CPU/FPGA Processing Solutions
- Making Sense of When to Use FPGAs
- Can FPGAs Beat GPUs in Accelerating Next-Generation Deep Learning?
- FPGA-Based AI System Recognizes Faces at 1,000 Images per Second
OpenCL and the OpenCL logo are trademarks of Apple Inc. used by permission by Khronos.