OKdo, OStream team on edge AI supercomputers
Board distributor OKdo has licensed streaming software that runs AI video and audio processing at the edge of the network on a range of hardware in a significant shift to its business.
OKdo has licensed OStream’s PipeRunner technology that automatically delegates edge AI operations to the most optimised hardware available across a cluster of single board computers (SBCs). The deal, announced at CES 2023, allows the AI operations to run on nueral processors (NPUs), video on video processors and computer vision tasks on CPUs.
PipeRunner modules are based on Nvidia’s Orin GPUs and RockChip’s neural processors, computer vision specific CPUs and video encoders/decoders connected by a high speed backplane to create a supercomputer built out of SBCs.
The system is deployed on the Edge and pulls media streams from already deployed cameras in the environment.
Historically, integrators are forced to choose between vertically scaled servers that offer static amounts of AI and CPU but no dedicated video processing. Now a modular, clustered approach allows for scaling from a pilot project with 3 TOPs to a production system of 800 TOPs all in one hardware unit.
OKdo touts that the horizontal model of building AI supercomputers out of SBCs is far more cost effective than the more limited and expensive vertical model.
- Researcher builds supercomputer with Raspberry Pi boards
- OKdo distributes Google’s machine learning SBC family
As a result of the deal OKdo now describes itself as the Single Board Computer and Internet of Things arm of RS Group as the Piperunner deal adds a secondary track to OKdo’s SBC roadmap.
OKdo’s primary track of SBCs focuses on CPU bound applications with their Rock boards and modules, while Okdo PipeRunner will offer a separate track of boards with hardware acceleration from NPU, VPU and CPU coupled with the software to make it run smoothly at any level of expertise.
The cluster software will come as standard on OKdo boards in this track offering a powerful layer that allows developers to deliver value faster.
“While the demand for AI applications at the Edge is at an all-time high, the SBC boards and software stacks offered today create too much work for integrators. We want to enable highly scalable AI applications without developers losing sleep over whether it will perform,” said Richard Curtin, CTO of Okdo.
OKdo sees PipeRunner as being useful for makers and industrial integrators alike. It has been deployed with customers including a Fortune 100 company, several international integrators and bundled by a leading camera company. PipeRunner is designed to stream video and audio from cameras, execute AI models against the media and enrich the resulting metadata into the Object MP4 format. The extended format allows customers to take real-time action at the Edge and build a data lake of searchable media.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
