Dev Kit Weekly: Thundercomm TurboX AI Kit

September 13, 2019 Brandon Lewis

This week we review the Thundercomm TurboX AI Kit, which is based on the Thundercomm TurboX module, which is based on the Qualcomm SDA845 heterogeneous SoC, which is based on... just kidding. That rabbit hole matters because the SDA845 SoC packs in a ton of processing performance for different kinds of AI workloads, including:

8 Kyro CPUs
An Adreno 630 GPU
A Hexagon 685 DSP
A dual 14-bit Qualcomm Spectra 280 image signal processor accompanied by HDR10, HLG, and HEVC hardware encoders/decoders

All of that compute delivers 450 GigaFlops of computing performance, and is supported by 8GB of low-power DDR4 RAM, 64 GB of universal flash storage, and a MicroSD card interface. For those struggling with moving their facial recognition, object detection, or speech processing applications to the edge, this abundance of compute power, high-bandwidth I/O, and memory can surely help.

But what really makes the TurboX board special for AI developers is the software support that comes with it. This starts with the Qualcomm AI Engine, a software package comprised of the Qualcomm Neural Processing SDK and the Android NN API that really fast track the development of facial recognition and object detection applications. The AI engine comes equipped with pre-optimized algorithms and sample source code to help get the prototyping process started.

Developers can train models in AI frameworks like TensorFlow, Caffe, or other development frameworks that are compatible with the ONNX interchange format.

As always, you can win this kit by entering the raffle here: https://opensysmedia.formstack.com/forms/dev_kit_weekly_kit_raffle

If you're interested in learning more about the Thundercomm TurboX AI Kit, visit https://www.thundercomm.com/app_en/product/1536844968290219?index=1&categoryId=category1&tabIndex=1

Questions for @techielew about the kit? Leave a comment.

Please like, subscribe, or follow us online.

See you next week...

Follow Brandon:

Twitter: https://twitter.com/techielew

LinkedIn: https://www.linkedin.com/in/techielew

Follow Embedded Computing Design:

Twitter: https://twitter.com/embedded_comp

LinkedIn: https://www.linkedin.com/groups/1802681/

Facebook: https://www.facebook.com/Embedded.Computing.Design/

Instagram: https://www.instagram.com/embedded_computing/

About the Author

Brandon Lewis, Editor-in-Chief of Embedded Computing Design, is responsible for guiding the property's content strategy, editorial direction, and engineering community engagement, which includes IoT Design, Automotive Embedded Systems, the Power Page, Industrial AI & Machine Learning, and other publications. As an experienced technical journalist, editor, and reporter with an aptitude for identifying key technologies, products, and market trends in the embedded technology sector, he enjoys covering topics that range from development kits and tools to cyber security and technology business models. Brandon received a BA in English Literature from Arizona State University, where he graduated cum laude. He can be reached by email at brandon.lewis@opensysmedia.com.
Follow on Twitter Follow on Linkedin Visit Website More Content by Brandon Lewis

Embedded Computing Design

Dev Kit Weekly: Thundercomm TurboX AI Kit

About the Author

Previous Article

Next Article

Dev Kit Weekly: Thundercomm TurboX AI Kit

About the Author

Previous Article

Next Article

We also recommend:

The new facility is enabling the company to scale up production of its (Hi-Rel) connectors to meet market requirements.

Companies looking to deliver value in the AIoT marketplace will be faced with extreme design requirements. To succeed, AIoT vendors must carefully consider their entire system design.

It is essential to ensure that all the blocks have a comparable number of erasures so that the life and reliability of the SSD are maximized.

Last year's 4 GB platform costs $99. Now, after some tweaks, the 2 GB version is just $59. And although it's in the price range of a Raspberry Pi, it offers the next level of oomph for AI newbies.

By integrating the wireless charging solution into its systems Stäubli WFT is reacting to the increasing customer demand for intelligent charging concepts.

Per the company, the MAX25430 decreased design size up to 40 percent and eliminates microcontrollers, metal enclosures, and heat sinks for 25 percent lower cost than competitive solutions.

VadaTech announced the release of the FMC238 and FMC239, which are a FPGA Mezzanine Cards per VITA 57.1 standard.

Power supplies produce it, and it must be addressed, but what are the sources and what are typical mitigation strategies?

Septentrio announced it has expanded its GPS/GNSS OEM portfolio with the AsteRx-m3 Pro receiver board.

Powered by the 11th Gen Intel® Core™ processors and based on the new COM-HPC standard with FuSa extensions, the CPU-18-02 enables Functional Safety applications at the Edge

From intense vibrations, mechanical shocks, wide temperature swings and so much more, designing for harsh environments requires extensive experience. But what could go wrong if you miss one of these..

It’s no secret that electronics systems are becoming more complex across all industries. It is less obvious how this complexity has infiltrated power supply design.

Powered by 11th Gen Intel® Core™ processors, and featuring the new COM-HPC standard, the CPU-180-01 enables AI, soft real time and advanced graphics at the Edge

The BlueNRG-LP radio SoC can now natively cover a much larger area in beacons, smart lighting, gaming, building automation, industrial, and tracking applications.

Together with the AP1302 Image Signal Processor (ISP), the AR0234CS delivers a comprehensive camera system that can be designed and developed for ideal time-to-market.

You can’t blame operators in critical industries like automation, manufacturing, and transportation for being careful in their transition to a new networking technology.

AS4C1G8D4 and AS4C512M16D4 High-Speed CMOS DDR4 SDRAMs

Renesas is the first I3C partner selected for ASPEED's AST2600 BMC Approved Vendor List (AVL), enabling an ideal migration path for customers shifting their DDR5 platforms and boards.

A combination of multi-radio and multi-protocol solutions accommodate two or more radios running different multiple protocols at the same or different frequency spectrum simultaneously.

For the new standard modules TQMxE40M, TQMxE40S, and TQMxE40C1/C2, TQ relies on the Intel Atom x6000E processor family of the 6th generation.