Qualcomm: Choosing an IoT Application Processor

0

As the IoT world evolves, today’s use cases and vertical markets require processing to be performed at or near the edge of the device. At the same time, device architects designing their next cutting-edge devices are forced to balance a range of requirements, including new form factors, diverse operating environments, power efficiency, and deployment budgets. , while satisfying an economic nomenclature.

In some cases this means selecting a powerful IoT processor with advanced capabilities, while in other cases a simpler but more specialized processor does the trick.

As you begin to design your device, here are some key questions to consider:

  • What type of internet backhaul/backbone (e.g. 5G, Ethernet, etc.) does the device require?

  • What local connectivity is needed (eg cellular, Wi-Fi, Bluetooth, etc.)?

  • Is there a power source available to support the wiring? Or will the device have to rely on a battery?

  • Is hardware-accelerated AI processing required or will the device rely on cloud services for heavy inference processing?

  • What video resolution, frame rate, and codec capabilities are needed?

  • Which embedded operating system is required (eg Linux or Android)?

Answering these questions can help you select an appropriate application processor. And to support you, we offer a range of IoT application processors adapted to your needs.

Below are some of our IoT application processors based on our advanced mobile technology:

Qualcomm QCS610 and Qualcomm QCS410

The QCS610 is a high-level application processor and a sibling of the mid-level QCS410. Both are Linux-based systems designed to build solutions that require artificial intelligence at the edge. This includes cutting-edge applications such as Industrial IoT, Smart AI Enterprise Security, Home IP Cameras, Dash Cams, Body Cams, Smart Displays, and Video Conferencing.

Both application processors include our Qualcomm Hexagon DSP and Qualcomm Adreno 612 GPU, along with multiple connectivity options including Ethernet, Wi-Fi, and Bluetooth. The QCS610 has a more powerful Qualcomm Kryo processor than the QCS410. The QCS610 also supports higher camera and video resolutions (4K versus HD) than its mid-tier sibling, and can run multiple AI models simultaneously for inference.

Since both application processors are equipped with the Hexagon DSP, you can leverage Qualcomm’s Neural Processing SDK to convert your models to DLC format for running on Hexagon and our AI Model Efficiency Toolkit (AIMET) to optimize more models. You can also use the Hexagon SDK for bare-metal DSP development.

Several development kits and reference designs are available, including the eInfochips EIC-Q610-200 open development kit and Altek UPC610. See the Qualcomm Application Processor Selection Guide for additional kits and details.

For more inspiration on what you can build with the QCS610, read our remote kiosk project and check out some of our other projects on QDN. We also have several learning resources that provide additional development details.

Qualcomm QCS2290

The QCS2290 is a cost-effective entry-level SoC with LTE, Wi-Fi, and Bluetooth connectivity for industrial and retail IoT applications. Potential use cases suitable for the QCS2290 include asset tracking, industrial handhelds, and smart cameras.

The QCS2290 shares pin-to-pin compatibility with the more powerful QCS4290 application processor (described below), allowing you to take advantage of shared hardware designs across IoT devices.

If you want to use the QCS2290, check out the TurboX CM2290/C2290 Development Kit based on their CM2290/C2290 SoM.

Qualcomm QCS4290

Like the QCS2290, our mid-range QCS4290 offers LTE, Wi-Fi, and Bluetooth connectivity, but has more processing power thanks to its Kryo processor and Hexagon DSP. This means you can take advantage of tools like the Qualcomm Neural Processing SDK to convert your models to DLC format for running on Hexagon, and our AI Model Efficiency Toolkit (AIMET) to further optimize your models. You can also use the Hexagon SDK for bare metal Hexagon DSP development.

Potential use cases/verticals for the QCS4290 include industrial handhelds, security panels, cameras, logistics and warehousing.

The QCS4290 shares pin-to-pin compatibility with the QCS2290 (described above), allowing you to take advantage of shared hardware designs on IoT devices.

Qualcomm QCS8250

The QCS8250 is our premium Android application processor for enterprise and commercial IoT applications. It specializes in advanced artificial intelligence and video analytics, making it suitable for video collaboration, smart cameras, connected healthcare, smart retail digital signage, and event management. fleet. You can also use it to create AI hubs to offload the work of detection devices such as multiple camera streams – up to 24 in total.

Take advantage of the Qualcomm Neural Processing SDK to convert your models to our DLC format for running on Hexagon and our AI Model Efficiency Toolkit (AIMET) to further optimize your models. You can also use the Hexagon SDK for bare-metal DSP development.

If you are interested in the QCS8250, check out the eInfochips EIC-QCS8250-210 Development Kit or the Thundercomm Turbox C865 Development Kit. See the Qualcomm Application Processor Selection Guide for additional kits and details.

You can find information about these and other application processors, as well as support resources such as SDKs, learning resources, and more, on our Application Processor page on QDN.

Qualcomm QCS610, Qualcomm QCS410, Qualcomm Hexagon, Qualcomm Adreno, Qualcomm Neural Processing SDK, Qualcomm Kryo, Qualcomm QCS2290, Qualcomm QCS4290, and Qualcomm QCS8250 are products of Qualcomm Technologies, Inc. and/or its affiliates. AIMET is a product of Qualcomm Innovation Center, Inc.

Share.

Comments are closed.