AXIS Takyon: a much-needed solution to communication in embedded HPC applications

September 30, 2019

In the eHPC (embedded high performance computing) market, developers are focused on domain-specific application development (e.g. radar processing, signal intelligence, autonomous driving). These domain-specific problems require substantial algorithm expertise (math, physics, etc.) not related to communication.

The resulting applications may be compute-intensive such that in order to achieve real-time, the algorithm must be distributed across multiple compute elements (e.g. CPUs, GPUs, FPGAs, ASICs) that make up a heterogeneous system. They must also integrate high throughput I/O devices like video, lidar, and radar sensors as well as high speed storage. Distributing the processing and integrating I/O currently requires multiple nontrivial communication interfaces (e.g. sockets, verbs, shared memory, semaphores, conditional variables).

Overall, eHPC developers are immersed in the algorithm development (the primary focus), but when it comes time to distributing the application, point-to-point communication is typically a secondary focus.

 

Previous Article
Overcoming the Outdoor Design Challenges of Complex AIoT Systems
Overcoming the Outdoor Design Challenges of Complex AIoT Systems

Companies looking to deliver value in the AIoT marketplace will be faced with extreme design requirements.

Next White Paper
Artificial Intelligence in Software Defined SIGINT Systems
Artificial Intelligence in Software Defined SIGINT Systems

Learn about artificial intelligence (AI) and deep learning (DL) in signals intelligence (SIGINT) systems an...