Differentiating Embedded Processors

By Ann Steffora Mutschler

The embedded processor world addresses a vast range of applications – from the datacenter to the biomedical device – all of which have critical power needs that vary with the use. Power concerns continue to dominate the embedded system whether it is avoid a noisy fan in a TV set-top box, allow video on a mobile phone or minimize pricey cooling costs in the datacenter.

The leading vendors in this space – ARM, MIPS and ARC (recently acquired by Virage Logic) – employ a variety of tactics and technologies to differentiate from trimming power by removing some features and making tradeoffs in the embedded software that run on them.

Putting power into the embedded perspective, Yankin Tanurhan, vice president and general manager for Processor and non-volatile memory Solutions at Virage, explained that in a system where there is a host doing most of the main processing, by adding small, deeply embedded processors it enables power to be saved on the big number cruncher. That allows smaller processors to listen to the analog signals, detect certain thresholds, and do whatever small level of signal processing needs to be done in a much smaller power budget that the ‘big gun’ would be using.

ARM looks at the embedded processing world in three segments, which its processor platform addresses in three ways, according to Travis Lanier, a product manager at ARM. ARM’s Cortex-A series is targeted at higher-end applications processing and is geared to running high-level operating systems such as Linux, Android and some flavors of Windows. The Cortex-M series is aimed at the microcontroller space for more deeply embedded applications that run RTOSs, with a focus on minimal gate count and extremely low energy. ARM’s Cortex-R series doesn’t have the ability to run the high-level OSes, but is instead focused on high performance and has a similar feature set.

In terms of differentiating, Lanier noted that it is important to look at it compared to what ARM offered historically and has built from that to refresh its product line.

On the technology front, ARM uses multiprocessing technology in its embedded processors. “We have some fairly small processors and generally when you think multiprocessing you think of the larger processors – you want to go faster, you want to do more operations per second. With the Cortex-A5, we’ve taken a different twist on that, and we have a fairly small, extremely power efficient processing,” he said.

Multiprocessing in the ARM Cortex-A5 allows up to four cores to be in a single configuration and run the processor doing four times the work, with each one of the processors having a fraction of what a higher performance processor would. So rather than running it at 2GHz, for example, there can be four processors running at 500MHz with each one taking a fraction of the energy of what a 2GHz processor would take.

“When you try to go faster it takes more and more energy, and when you try to get more done per clock cycle it takes more and more energy. We recently released the Cortex-A5 and this is pretty much our most power-efficient processor ever. Rather than just looking at absolute low power or absolute frequency, when we set out to design this one, we looked at a series of benchmarks and said, ‘What’s the maximum amount of work we can get done per unit of energy?’ Rather than saying, ‘We’re targeting 300mWs or we’re targeting 500MHz,’ we said, ‘Let’s just go for the maximum work we can get done per unit of energy,’” Lanier added.

MIPS’ technology, specifically its M14K and M14Kc cores, make use of a new code compression technology that maintains the native performance of the MIPS architecture. “Most of the applications that MIPS is used in and that comprise many of the embedded markets are very cost sensitive. You can look at cost from many different angles but your code has to be stored somewhere and the smaller you can make it, the less expensive the overall system is, and some systems are more sensitive to that than others,” said Mark Throndson, director of product marketing at MIPS.

For instance, MIPS decided to target the microcontroller space initially because microcontrollers in many cases are basically a self-contained piece of silicon containing on-chip memory and what you see is what you get. “So clearly packing in all of the code into on-chip flash is a very space-critical implementation. But even with portable products, the effect on power and limited built in flash tends to push code space as a higher priority,” he explained.

MIPS also employs coherent multicore technology that includes hardware multithreading in each of the cores in the system. 2 to 4 cores connected working as one unit to a symmetric multiprocessing operating system.

Software becomes big consideration
In terms of software, there are definite considerations – depending on the application – for the embedded processor. Lanier said this occurs many times with software such as device drivers. On the embedded level, if the software is running on the applications processor, for example, the device driver runs in the background and detects how much activity is on the processor and automatically shuts it down when necessary to conserve power. So when an application is running, it doesn’t interfere.

Then, in the deeply embedded space, such as a Bluetooth headset or biomedical application, the software must be written from scratch being very power aware as to what modes the processor is put into and how it is activated. You have to focus on getting every little scrap of power you can dig up from the processor

“The biggest challenge now is that everyone basically wants to have a mainframe computer inside their cell phone. So the question is how to keep adding more and more performance to these small devices where the battery life hasn’t increased. So you still have the same power budget that you had 10 years ago in the battery yet people are expecting more and more performance out of these devices. Part of that you get from Moore’s Law. But lately, as the process technologies have shrunk the voltages have slowed down as far as how much it has dropped. So a lot of the power gains you have from the process technology where the voltage would drop with each new process generation have kind of slowed down starting at 65nm. It’s a lot more incremental how much you reduce the voltage. There’s not as much power savings to be had from Moore’s Law, although the number of transistors increases,” he said.

The key thing about software in an embedded system that wants to operate at low power is that when you have a high-end processor like that, the trick is knowing when you are running out of things to do or ahead of schedule, said Darren Jones, MIPS’ engineering director.

“You want to think about if it is a camera, once you take a picture and you know you are done processing it, the whole thing can shut off,” Jones said. “So the trick is to get done processing as quickly as possible so the whole thing can shut down. Even though it is difficult for hardware to help this, the software can tell them how they are doing against their deadlines. And if they can know that, then they can use the hardware hooks we put in to bring the power down. Whenever you bring the power down, it is costing you something – lowering the MHz or frequency – so you get less performance out of it. You don’t want to do that in a real-time system like your antilock braking system. If it is extremely low power, something like a hearing aid or even an automotive application, then the trick is being super efficient with your code. MIPS processors and the MIPS architecture as a whole are very efficient. When you want to get work done, you get it done as efficiently as possible, get the work done as quickly as possible and then go to a lower power mode.”

Jones noted that low power used to be confined to portable electronic devices such as cell phones to conserve battery time. It now has moved to televisions, data centers and almost everything else imaginable.

“Companies are really starting to pay attention to power as a goal, not just performance,” he said. “So even in high performance applications they can’t just burn power.”