Avoid Reinventing the Wheel on Industrial Designs

Software updates are easy to roll out, but hardware upgrades on custom designs often require a major investment of time and money. A modular approach can speed up this process. In this article, congatec’s Dan Demers explains how.

Make slow progress or speed ahead with buy-in?

By Dan Demers, Director of Sales and Marketing – Americas, congatec

We are used to receiving software updates on-the-fly today. So why not utilize converged embedded computing platforms to upgrade our hardware? This would enable us to take direct advantage of the rapid development cycles of the computing, vision and AI industries.

There are plenty of examples on how to upgrade the hardware during running series production. In the medical sector, for instance, where medical devices even require certification. But it appears that some system developers have not yet learned how to consistently build computing core upgrades into their product development.

This is because full custom designs are still quite common. The integration of expensive navigation systems by premium vehicle manufacturers is a bad example of this. Although pretty and expensive, they are often much slower than the driver’s considerably cheaper mobile phone. Before the computer technology that’s installed in the vehicle gets used by the customer, it is usually already obsolete.  Market acceptance for such monolithic solutions is therefore dwindling noticeably.

The problem of these manufacturers is anchored in the design principles of mass production, where every cent matters, but no attention is paid to the innovation cycle demanded by users. This has fatal consequences: If the computing part is entirely custom designed, an upgrade will in many cases require a redesign, where the ability to reuse blocks of the previous generation is limited. So all in all, we’re talking about a major investment to always deploy the latest computer technology in an application.

But there’s another way: To avoid having to reinvent the wheel every time, the Computer-on-Module concept was developed at the end of the 90s. Modular approaches had existed before then, but it is only since the Computer-on-Module concept emerged, that modules stopped being proprietary and became available as standardized components from numerous providers.

congatec offers SFF Computer-on-Modules for all leading standards: SMARC 2.0, Qseven, COM Express Mini and COM Express Compact modules.

Computer-on-Modules are available in different designs. For low-power CPUs such as Intel Atom, AMD G-Series or the ARM i.MX6 and i.MX8 platforms from NXP, the Qseven and SMARC Computer-on-Module standards are particularly suitable. For higher computing power and interface demands, COM Express is the best standard. COM Express Type 6 modules support fast CPUs, like the AMD V1000 or the latest Intel Core processors.

Type 7 was defined for edge server processors and 10 Gbit Ethernet support; however, in true server fashion, it no longer supports any video interfaces. The upcoming PICMG COM-HPC standard will support even faster interfaces. The specification is due to be published in 2019, with first products expected in 2020.

With Server-on-Modules a modular approach is even suitable for the development and constant update of high-performance microservers by just exchanging the modules. This significantly reduce the efforts and cost connected for upgrades.

All in all, Computer-on-Modules are an ideal and easy way to equip machines and devices with the latest processor technology. So anyone who wants to use converged system platforms as part of their closed-loop engineering, will find that Computer-on-Modules are a perfect platform for performance upgrades. However, this doesn’t mean that you shouldn’t implement a full custom design when it comes to mass production. But here too, getting the module supplier to implement a fusion of modules and carrier board works significantly better than the OEM developing everything from scratch.

congatec | www.congatec.com/us

 

Sponsored by: congatec

Linaro Launches Two 96Boards SOM Specifications

Linaro has launched two SOM specifications for 96Boards—a Compute Module spec and a Wireless spec. It has also released two board designs based on the Compute spec, along with a 96Boards SOM Carrier board compatible with those two boards.

Linaro, the Arm-backed open source collaborative engineering organization, has announced the publication of version 1.0 of 96Boards System-on-Module (SOM) specifications. 96Boards is Linaro’s initiative to build a single software and hardware community across low-cost development boards based on Arm technology. Along with the new specifications, the company has rolled out two board designs: the TB-96AI based on a Rockchip RK3399Pro processor, and the TB-96AIoT based on the newer Rockchip RK1808 processor.

We’ve [Linuxgizmos.com] covered a couple RK3399Pro-based boards just within that last four months, including Geniatech’s DB3399 Pro, Vamrs’ Toybrick RK3399Pro SBC and crowdfunded Khadas Edge-1S SBC from Shenzhen Wesion’s Khadas project. The newer Rockchip RK1808, announced in January at CES, is basically a “lite”, lower power version of the RK3399Pro with the same Network Processing Unti (NPU). See further down for more details on the RK1808.

The launch of the new 96Boards specifications provides developers with a SOM solution that is compatible across SoCs. According to Linaro, SOM solutions today use a variety of different connector solutions including SO-DIMM connectors used in DRAM and Mini Module Plus (MMP) connectors for certain specialist boards. Up until now, there has been no solution offering flexible IO and a robust mounting mechanism, nor a standard form factor, says Linaro. The goal of new 96Boards SOM specifications is to enable plug and play compatibility between a whole range of different SOM solutions.

Two 96Boards SOM specifications have been launched: The Compute Module Specification and the Wireless Specification. Both specifications encourage the development of reliable and cost-effective embedded platforms for building end-products. The specifications have been proposed, created and reviewed by the current 96Boards Steering Committee Members.

The Compute Module Specification defines a SOM with generic module-to-carrier board interface, independent of the specific SoC choice on the module. The Compute module addresses the application requirements of segments including industrial automation, smart devices, gateway systems, automotive, medical, robotics and retail POS systems. Two form factors are defined as SOM-CA and SOM-CB with a maximum of four 100 pin Connectors. The X1 connector is mandatory on all SOMs. The defined interfaces are shown in the table below.


Compute Module Spec — Defined Interfaces
(click image to enlarge)
The Wireless specification designs a SOM for interchangeable wireless module applications, supporting standard and/or proprietary wireless standards such as 802.15.4, BLE, WiFi, LoRa, NB-IoT, LTE-M etc. The specification is designed to enable evolution that will support multiple products and future wireless standards. The two form factors are defined as SOM-WA/SOM-WB with the pinouts to the specification shown in the table below.


Wireless Spec Pinouts
(click image to enlarge)
TB-96AI

The TB-96AI can be combined with the backplane to form a complete industry application motherboard, and be applied to various embedded artificial intelligence fields. The TB-96AI’s RK3399Pro processor has an Arm dual-core Cortex-A72+quad-core Cortex-A53 architecture. The processor has frequencies is up to 1.8 GHz and integrates a Mali-T860 MP4 quad-core graphics processor. The chip’s integrated NPU supports 8Bit/16Bit operation. With computing power of 3.0 Tops, the NPU can meet various AI application needs such as vision, audio and so on.

 
TB-96AI, front and back
(click images to enlarge)
The TB-96AI supports DP1.2, HDMI 2.0, MIPI-DSI, eDP multiple display output interfaces, dual-screen co-display/dual-screen heterodyne, 4K VP9, 4K 10bits H265/H264 and 1080P multi-format (VC-1, MPEG-1/2/4, VP8) video decoding, 1080P (H.264, VP8 format) video coding. The board is compatible with multiple AI frameworks, the design supports TensorFlow Lite/Android NN API, AI software tools support import, mapping and optimization of Caffe / TensorFlow models, allowing developers to easily use AI technology.

TB-96AIoT

The TB-96AIoT meanwhile is equipped with the RK1808 AIoT chip. According to Linaro, the TB-96AIoT also provides rich interfaces and strong scalability. Aside from this, little other detail on the TB-96AIoT is provided in the announcement.

The Rockchip RK1808 processor used on the TB-96AIoT features a dual-core Cortex-A35 CPU architecture, NPU computing performance up to 3.0 Tops, VPU supporting 1080P video codec, microphone array with hardware VAD function, and camera video signal input with built-in ISP. The RK1808 boasts lower power consumption thanks in part to being built on an 22nm FD-SOI process. This shrinks power consumption by about 30%, compared with mainstream 28nm processes under the same performance, according to Rockchip. The device features DDR-free operation of the always-on device with built-in 2MB system-level SRAM. A hardware VAD function provides low-power monitoring and far-field wake-up, features all suited to IoT applications.

Both the TB-96AI and TB-96AIoT SOM designs are available for purchase from Beiqicloud.com—sign in required. A story by cnx-software points out that Vamrs is also involved because of the “ToyBrick” reference on the boards’ silkscreen.

96Boards SOM Carrier Board

The 96Boards SOM Carrier Board is compatible with both the TB-96AI and TB-96AIoT. It is designed to suit different markets and demonstrates how easy it is to support multiple different SOMs.


96Boards SOM carrier board
(click image to enlarge)
There wasn’t much detailed on the carrier board spelled-out in the announcement, although this detail graphic was provided:


96Boards SOM carrier board detail
(click image to enlarge)
 Further information

More information on the new SOM specifications can be found on the announcement page. You can learn more about Linaro’s engineering work on the Linaro and 96Boards websites. Beiqicloud is 96Boards Compute SOM Lead partner. For more information about SOM boards and Carrier board visit Beiqicloud’s products page.

This article originally appeared on LinuxGizmos.com on April 2.

Linaro | www.linaro.org