Intel offers a portfolio of solutions to meet a variety of needs for AI development and deployment. For custom hardware implementations, the Deep Learning Accelerator IP (contact your local sales representative for more information) offers exceptional performance of AI workloads with the flexibility to implement a variety of topologies without recompiling. The following tools help you get started.
The Intel Arria 10 FPGA development kit delivers a complete design environment that includes all hardware and software you need to start taking advantage of the performance and capabilities available in Arria 10 GX FPGAs for your design needs.
The Deep Learning Inference Accelerator IP fully integrates hardware and software, providing an easy, out of the box solution to implement deep learning workloads on a PCIe add-in card form factor.
For more partner board options that support the OpenCL™ platform, please refer to Design Solutions Network.
For experienced Intel® FPGA users, the OpenCL™ platform, HDL, and RTL design flows enable complete control and customization of workloads for a portfolio of Intel FPGAs including low-power Intel Cyclone® devices, mid-range Arria devices, and high-performance Intel Stratix® devices.