Blaize Delivers Programmable AI at the Edge

August 17, 2020 Rich Nass

AI is probably the most talked about subject in the embedded space these days. Hardly a meeting goes by without AI being brought up, either as the main subject of conversation or something peripherally related. That was certainly the case with the virtual press conference I attended last week for Blaize, a fairly new entrant to the space.

Blaize introduced the company’s first AI computing hardware and software solutions aimed specifically at the Edge of the IoT, dubbed the Pathfinder and Xplorer platforms and the AI Software Suite. According to the company, the hardware-software combination will enable Edge-based AI products across a wide range of edge use cases and industries. That would include industrial, smart cities, sensor fusion, last-mile delivery, and retail.

The company feels that it is filling the void created by products that are either not compute intensive enough, too expensive, or too complex. It claims to “migrate AI computing out of the data center to the Edge,” as well as the industry’s first option for code-free AI development at the Edge.

The new products are built upon Blaize’s Graph Streaming Processor (GSP) architecture. The Blaize GSP is a 100% programmable processor that features multi-threading and streaming. With 16 GSP cores and 16TOPS of AI inference performance within a 7W power envelope, GSP can deliver superior system-level efficiency versus GPU/CPUs for edge AI applications as well as less memory bandwidth and lower latency.

In terms of a specific product, the P1600 embedded systems-on-module (SOM) is designed such that no host processor is needed. It simply plugs into a PCIe slot. Beyond that, the X1600E small form factor accelerator platform is aimed at small and power-constrained environments such as convenience stores or industrial sites. It can accelerate AI applications in industrial PCs or as a rack of cards in a small 1U server. The X1600P is a standard PCIe-based accelerator in a half-height, half-width form factor.

The Blaize AI software suite is built on open standards. Comprised of the Picasso software development kit (SDK), and AI Studio, a completely code-free visual interface, the software suite offers tools for both traditional developers and non-coder domain experts. In addition, both tools sets utilize Blaize Netdeploy, which uses edge-aware algorithms to maximize accuracy and performance.

Samples of both product lines are available now with full production expected starting in the fourth quarter. The Xplorer X1600E sells for $299 in large volumes. The Pathfinder P1600 SOM is available in an industrial grade for $399, while the Xplorer X1600P costs $999.

About the Author

Rich Nass

Richard Nass is the Executive Vice-President of OpenSystems Media. His key responsibilities include setting the direction for all aspects of OpenSystems Media’s Embedded and IoT product portfolios, including web sites, e-newsletters, print and digital magazines, and various other digital and print activities. He was instrumental in developing the company's on-line educational portal, Embedded University. Previously, Nass was the Brand Director for UBM’s award-winning Design News property. Prior to that, he led the content team for UBM Canon’s Medical Devices Group, as well all custom properties and events in the U.S., Europe, and Asia. Nass has been in the engineering OEM industry for more than 25 years. In prior stints, he led the Content Team at EE Times, handling the Embedded and Custom groups and the TechOnline DesignLine network of design engineering web sites. Nass holds a BSEE degree from the New Jersey Institute of Technology.

Follow on Twitter Follow on Linkedin Visit Website More Content by Rich Nass
Previous Article
AAEON and Aotu.ai Announce the Release of a Smart Vision AI Developers Kit on an Intel AI Platform for IoT
AAEON and Aotu.ai Announce the Release of a Smart Vision AI Developers Kit on an Intel AI Platform for IoT

AAEON and Aotu.ai announce the release of the UPX-Edge BrainFrame Dev Kit, putting the BrainFrame software ...

Next Article
Blending DSP and ML Features in a Low-power, General-Purpose Processor: How far can we go?

Arm has been working on technologies that boost the signal processing and machine learning capabilities in ...