Cortex-M4F micros with DSP can be energy efficient
In an age of stripped-down processors there are good reasons to consider a microcontroller equipped with DSP functions even for low power designs, writes Andreas Koller
The microcontroller market is abuzz with talk about low energy consumption.
Many designers are looking for microcontrollers (MCUs) that will function, sometimes for a period of years, on the energy stored in a battery, or that is available from an energy harvesting system.
This is a trend which has culminated in the recent launch of ARM’s ‘Flycatcher’ M0+ product, a stripped-down, ultra-low power processor core intended for just these applications.
Against this backdrop, it might seem strange to offer an MCU based on the ARM Cortex-M4F processor core that offers not less performance but more, including floating point DSP instructions.
So, why would anyone choose a low-energy MCU equipped with DSP functions?
The first reason is that – perhaps counterintuitively – such a processor may in fact prove to be more energy efficient than a less competent device. The availability of floating point and single-cycle multiply-accumulate instructions often allows the designer to reduce execution time, or reduce the clock frequency to accomplish the same workload. Put simply, expending 10% more power for 20% less time represents an energy saving overall.
This effect is, of course, accentuated in devices with well designed sleep modes that deliver very low power. The bigger the difference between active and sleep mode power consumption, the greater will be the benefit of a rapid return to a low-energy state.
Such considerations also come into play in the field of smart sensing. As MCU prices have dipped below the dollar mark, it has become increasingly possible to put intelligence into everyday objects. A DSP-equipped MCU provides a special type of intelligence that can be used for signal conditioning purposes.
By siting such processors at the location where each signal is captured, designers can choose lower cost sensor types, increasing the range of applications that can cost-effectively be addressed.
Ultrasonic water metering is one example of such a use case, that in addition to signal processing also requires outstanding sleep mode performance – meters require a battery life of years.
In such an application an MCU can be configured with the CPU in sleep mode and its peripherals set up as a kind of analogue state machine that wakes the Cortex-M4 only when water is flowing. The availability of DSP instructions allows the designer to build sophisticated filtering functions that come into action when there is water flow to measure, and eliminate the need for expensive ultrasonic transducers.
Some applications simply need the processing horsepower of a DSP.
For example, I know of one firm which is working on a security device that senses glass breakages using acoustic analysis. Breaking glass is accompanied by a distinctive series of sounds and vibrations that culminates in a resonance at the characteristic natural frequency of the glass – in this case around 13kHz.
The MCU is used to perform fast Fourier transforms on the output from a wide-band sound transducer, and hence to determine whether a breakage has taken place. The transducer may be sited close to the window and used to detect sounds, or attached directly to the glass to work in ‘seismic’ mode.
Because the system needs to run for a period of years from a single battery, it must be designed so that the MCU wakes up and starts processing only when a possible candidate acoustic event has occurred. The chip’s fast wake up capabilities facilitate this, and its DSP capabilities minimise wake time, while allowing the designer to choose a detection algorithm that is robust against false alarms.
Portable medical equipment provides another typical example of such an application. Instruments like battery-powered ECGs have been favorite talking points: but the fact is that as of today, for a really accurate read-out of cardiac health, the patient needs to visit a hospital or health clinic. The processing power of current portable instruments is restricted by the power and energy budget imposed by battery-based operation: as a result designers compromise by reducing sampling rate. DSP-equipped low-energy processors present a practical solution to this problem.
Applications like these demonstrate that low-energy operation is not always about paring processing power to the bone. Tomorrow’s energy efficient products require MCUs with the right balance of processing capabilities, low active power consumption, well-designed sleep modes and tailored, autonomous peripherals.
Andreas Koller is v-p sales and marketing at Energy Micro