Intel and FPGA provider Altera recently announced a collaboration to develop a flexible, real-time sensor-bridge reference solution for a range of edge and physical AI industries, including healthcare, aerospace and defense, and robotics applications.
By combining Intel compute, connectivity and software with Altera FPGAs, the companies hope to help OEMs address the growing complexity of connecting, processing and acting on real-world data across increasingly sensor-rich edge environments.
Edge and physical AI systems can require data from different sensors and interfaces to be brought together while meeting requirements for timing, performance, power and cost. Some applications also require very high bandwidth or flexible form factors in which input/output (I/O) is located away from the compute board. Sensor data must then be streamed rapidly into memory for the host Intel processor to use across edge, robotics and other workloads.
Intel and Altera plan to address these challenges through modular reference solutions that combine Altera programmable hardware with a consistent Intel compute and software foundation. The goal is to give OEMs greater flexibility as applications, sensors and workloads evolve, while helping them move more efficiently from prototype to deployment.
“Physical AI systems have to sense, decide and act in real time, and the physical world demands accuracy, reliability and safety. Altera FPGAs provide the sensor connectivity, data processing and deterministic control that machines need to respond to the physical world, and they stay programmable as sensors and AI models evolve. Combining that with Intel’s compute and software is intended to give OEMs a flexible foundation to tailor systems to their needs,” said Farhad Shafai, head of business solutions and marketing at Altera.
Intel and Altera plan to apply the collaboration across multiple markets where real-time processing and programmable computing matter most. The companies intend to make resulting reference solutions accessible to developers through Intel’s Open Edge Platform SDK and an Altera SDK.
- Healthcare: A reference solution targeting the stringent latency and real-time requirements of advanced healthcare equipment is currently under development.
- Aerospace and defense: New reference solutions will support next-generation mission systems, focusing on size, weight and power requirements for converged AI and signal-processing workloads.
- Robotics: The companies are addressing the increasingly complex sensing, timing and real-time processing requirements of intelligent machines.
