SMARC: The Smart Choice For Low-Power Embedded Computing

Thirty years after the mainstream adoption of the personal computer, the industry faces another paradigm shift in information technology. The innovations behind the IBM PC and similar machines not only revolutionized desktop computing, they also changed the world of embedded computing, which previously was restricted to the use of expensive minicomputers or custom digital logic with an often prohibitively high cost of non-recurrent engineering.

Related Articles

• Fundamentals Of Low-Power Design
• Understanding Low-Power IC Design Techniques
• Low-Power Analog Interface Circuit Design Techniques For SoCs

The embedded PC form factors have enabled systems integrators to implement a wide variety of systems, tackling many different applications. The most successful PC platforms were designed for power envelopes that run from tens of watts to more than a hundred. This puts some portable and low-energy applications out of reach. Using non-PC architectures can extend the benefits of off-the-shelf computing platforms even further.

The rise of architectures designed for mobile phones and tablets introduces a new paradigm. This shift promises to extend the reach of embedded computing into new markets, providing users with energy-efficient systems and intuitive user interfaces based on touchscreens and voice recognition. These interfaces promise to transform treatment in medical applications, provide more sophisticated control to industrial-equipment operators, and create the opportunity to access the Internet in remote and previously hard-to-reach locations.

ARM’s Role

Optimized for the mobile phone and tablet markets, the ARM architecture offers an effective alternative that extends the power envelope into low-energy applications that have previously found it difficult to adopt standard form factors and so had to absorb the high upfront costs of custom board and module design. At the same time, ARM offers scalability into upcoming high-performance computing and 64-bit platforms that will make it possible to build advanced, highly energy-efficient server platforms. ARM underpins this new, third generation of embedded computing.

There are strong historical contrasts between the Intel x86 and ARM market environments. Intel has been instrumental in defining not just the core microprocessor and instruction-set architecture, but also the architecture of peripherals. Companies that provide embedded-computing products based on the x86 architecture have been able to leverage that (chip level) expertise by providing either proprietary or open-standard products that employ a common I/O interface. Through the use of common connector pinouts, customers can select from a wide range of hardware- and software-compatible peripherals with which they can customize their end products.

COM Express, a successful embedded computing I/O standard, is a computer-on-module (COM) form factor that offers high integration to the degree that a complete, compact PC can be used in an end application as though it were a discrete IC component. The COM Express module itself typically comprises the core processor and memory together with the standard I/O of a PC, including USB ports, audio, graphics, and Ethernet networking. The PCI Express lanes and all other I/O signals that support custom I/O expansion are mapped to two high-density, low-profile connectors on the bottom side of the COM.

With COM Express, the emphasis is on high-speed I/O expansion. A pair of high-density connectors provides up to 32 PCI Express lanes or multiple storage, networking, and graphics channels. In addition to supplying a connector with a high degree of signal integrity and robustness, COM Express offers standardization, which is instrumental in building up a large portfolio of CPU modules and carrier boards from many different vendors. The road to a standard I/O pinout was assisted by the manner in which the PC form factor is itself built on a commonly accepted set of standard I/O functions.

The ARM environment is more complex and differentiated. In contrast to the PC environment, in which the core module comprises a processor and Northbridge and Southbridge devices, the focus in the ARM market is on system-on-chip (SoC) products, each usually optimized for a particular application. Historically, there has been far less focus on building standard I/O definitions. Each SoC would be used on a custom board design. ARM platforms also offer a wider range of I/O options, depending on their target market, with less emphasis on standard buses such as PCI Express.

The result has been the introduction of proprietary form factors and connector definitions that lock the customer into a vendor’s offerings and may not have support for more than a generation of silicon as they move to different SoCs. Some vendors claim the use of a standard form factor, sometimes piggybacking ARM support on an existing x86-focused specification, but with additional custom connectors to support I/O lines that cannot be supported by the primary connectors.

SMARC Steps In

Supported by a number of embedded computing module vendors, the Smart Mobility ARChitecture (SMARC) provides an open-standard definition for ARM-based embedded computing solutions, optimized for low power, cost efficiency, and high performance. SMARC also supports systems that need more compact solutions than are offered by the PC-oriented form factors.

As the ARM SoCs do not need the support chips of a PC platform and draw less power, the amount of board space that needs to be reserved for power converters and power supply lines is greatly reduced. This allows the use of a smaller form factor, facilitating use of SMARC-based modules in low-power portable equipment. SMARC CPU modules are expected to have an actual power intake between 2 W to 6 W, allowing for passive cooling and further reducing subsequent design effort and overall cost. The standard permits up to 9-W continuous power draw for more demanding scenarios.

Based on the proven connector as it is employed by Mobile PCI Express Modules (MXMs), SMARC defines two sizes of module: a full-size module that measures 82 mm by 80 mm, and a short module for more compact systems that measures 82 mm by 50 mm. The edge connector supports 314 electrical contacts. For systems designed for harsh environments, shock- and vibration-proof versions of the connector are readily available. The temperature range of the connector extends from −55°C to 85°C. Competing systems such as Q7, which also lacks the ecosystem advantages of SMARC due to the proprietary extensions used by its restricted group of supporters, are not specified over this temperature range.

The connection system employed by SMARC offers a number of benefits over competing systems beyond its adoption of multiple vendors, which promises to form the basis of a successful commercial ecosystem. The MXM connector guarantees a high degree of signal integrity, required by high-frequency serial interfaces that are commonly supported by ARM SoCs. For example, on 2.5-GHz signals as employed by PCI Express Gen 2, the insertion loss of the connector is just 0.5 dB. In comparison, the insertion loss encountered on the connection scheme used by previous generation MXM connectors is significantly higher at 3 dB.

A further advantage of SMARC over other small module formats is its support for a wider input voltage range, reducing the need to use additional dc-dc converters on the core module and overall power dissipation. A SMARC module can support input voltages from 3 V to 5.25 V. Originally designed to support PC-class hardware, the many other formats are restricted to a nominal 5-V input.

The SMARC module is designed to support a combined height above the carrier of less than 7 mm. The PC heritage of most computer-on-modules has led to the assumption that all COM boards will be used with a heatspreader, which adds to the overall height of the package. The typical combined height of the processor board and heatspreader alone is greater than the height of a package that includes both the SMARC COM and carrier board. Many ARM SoCs do not require a dedicated heatspreader because of their lower overall power consumption. The SMARC format allows for this, making it more suitable for use in systems where space is at a premium, such as tablet computers.

To take advantage of the greater I/O diversity of the core ARM-based SoCs, SMARC uses a different mix of connection options to those offered by COM Express or Q7. In contrast to the PCI Express focus of COM Express, SMARC provides options for different types of video and graphics output, serial buses such as I²C, I²S, both client and host forms of USB, serial and parallel camera interfaces, and support for standard flash-memory card formats such as SD and eMMC. Coming SMARC modules will also be enabled to support fieldbuses such as EtherCat, ProfiBus, and Sercos.

SMARC’s Support

Using SMARC, systems integrators can take full advantage of the user-interface options available to mobile device OEMs, options that are not usually found in x86-based embedded-computing systems. For example, SMARC does not just support a direct parallel display bus for low-cost connection to a wide variety of thin-film transistor LCDs, but also supports a display interface compatible with the MIPI specification. This provides access to the smaller, low-cost display modules employed in smart phones or tablets as they find their way into the embedded market.

Because of its I/O flexibility and focus on ARM solutions, SMARC provides the support needed to build scalable solutions. Integrators can choose from a wide variety of processing options, from low-power single-core devices such as the Cortex A8 processor provided by ADLINK’s LEC-3517 to dual- and quad-core processor platforms (see the figure).