Author:
Dirk Akemann, head of technical marketing at Segger
Date
03/21/2025
PDF
Click image to enlarge
Figure 1: Difference between an RTOS using cycle-resolution timing (bottom) and a conventional RTOS (top). The CPU stays in energy-saving mode significantly longer and is woken up less often by interrupts (red), resulting in more computing power and less energy consumption
When developing embedded systems, selecting the appropriate real-time operating system (RTOS) is essential to ensuring efficient and reliable operation. When comparing the available RTOS scheduling options, cycle-resolution timing stands out because of its unique approach.
This article takes a closer look at the differences between super-loop architectures, traditional real-time operating systems, and an RTOS, SEGGER’s embOS-Ultra, that uses cycle-resolution timing. It details this distinct approach and compares it to other approaches when it comes to developing applications for embedded systems.
Differences between a super-loop architecture, a standard RTOS, and an RTOS using cycle-resolution timing
To better understand cycle-resolution timing, it is essential to compare it with super-loop architectures and standard real-time operating systems.
Super-loop architecture
A super-loop architecture, also known as “bare-metal programming,” does not use a real-time operating system. In this architecture, the system continuously checks the operating states without using a scheduling mechanism. This constant checking adds unnecessary processing load and consumes device power. Moreover, the lack of scheduling restricts the system's effectiveness in managing tasks.
Approach of standard real-time operating systems
In contrast to the super-loop approach, a standard real-time operating system takes care of tasks and resource management. It also uses periodic system tick interrupts generated by a hardware timer as both the time base for the RTOS and for scheduling. While this improves task management compared to a super-loop architecture, it still requires periodic checks to identify pending tasks. In most applications, the system tick interrupt occurs every millisecond and continues to occur even when the system is idle or no other task is scheduled. It, therefore, wastes computing time when no time-based action is required for multiple consecutive system ticks.
For an RTOS that does not use cycle-resolution timing, a SysTick event with no pending task causes an “empty” interrupt. The existence of "empty" tasksor interrupts has several implications for the application. Firstly, they unnecessarily burden the processor, leading to increased usage and higher energy consumption. Additionally, these interruptions can be disruptive, especially in the context of signal processing. For instance, when a signal is being generated and an interrupt interferes withthe process, it introduces a time delay of approximately 5 µs. This isdue to task switching time, depending on the real-time operating system, and the microcontrolleror processor used. This delay primarily restricts the bandwidth at which the system can generate signals.
The problem is that interrupts do not always cause disruptions, making it difficult to attribute signal instabilities solely to them. This complexity poses challenges during debugging, particularly when using the step-by-step execution mode (single-step mode) where such interrupts often go unnoticed.
In a traditional RTOS that uses periodic system tick interrupts as both the time base and for scheduling, all timeouts, delays, and periodic timers need to be specified in system ticks instead of an amount of time. This means that they are always aligned with the periodic system tick interrupt, severely limiting the resolution for scheduling events.
When tasks need to be executed at times that do not align with the System Tick, traditional RTOSs can only do this by either waiting or utilizing extra resources–if they are available at all. Waiting imposes unnecessary strain on the system. Allocating additional resources, such as another timer interrupt, could potentially introduce additional side effects or computational load.
Cycle-resolution timing explained
An RTOS using cycle-resolution timing however, is active when a change necessitates the operation of the RTOS. The system precisely determines when to awaken to fulfill its tasks and allocate resources to pending assignments. There's no need to continually poll for events, consistently or intermittently, via the SystemTick. Instead, it leverages the cycles of an ongoing hardware counter that runs continuously, serving as the fundamental time base for the RTOS.
With the option of CRT, the RTOS has flexible system tick interrupts available to precisely schedule any future task without further side effects. Thus, they can be specified in system-independent, high-resolution units such as milliseconds, microseconds, or even hardware counter cycles instead of system ticks.
Click image to enlarge
This new cycle-resolution timing approach makes it possible to schedule task switches precisely, thusenabling the shifting of tasks into the real-time operating system that would traditionally be programmed outside of it. This applies to tasks shorter than the system tick as well as tasks that do not need to be scheduled exactly at multiples of the system tick.
The ability to program such cases facilitates portability, particularly when replacing a microcontroller, while also reducing energy consumption.In addition, it eliminates the need to check for pending tasks and accurately determines the optimal execution time for each task. Developers can now use RTOS API calls where dedicated hardware timers were required before. This makes firmware much easier to maintain and port and improves application performance.
Enhanced efficiency and reliability for various device applications
A real-time operating system using cycle-resolution timing is particularly well-suited for a range of devices with specific requirements. Battery-powered or rechargeable devices, for example, benefit greatly from the efficiency and power-saving features offered by this type RTOS. Minimizing unnecessary tasks and optimizing scheduling, effectively reduces the system’s energy demand and extends battery life.
In the field of signal processing devices, their specialized design enables efficient management of signal processing tasks. For instance, they excel in devices that generate signals using protocols such as JTAG/SWD, typically through debug probes. Additionally, they demonstrate exceptional performance in scenarios where proprietary protocols lack dedicated peripheral drivers, such as Ethernet or USB controllers. When it comes to motor control applications, the RTOS ensures precise timing and synchronization of critical tasks involved in controlling moving components such as fans or drill drives.
Reliability and safe operation are especially critical when developing applications for medical devices. The stringent requirements commonly associated with medical devices align well with the capabilities of real-time operating systems such as SEGGER’s embOS-Ultra. Their capacity to optimize power usage and reliably handle signal processing tasks make these RTOSs a perfect choice for medical applications that demand high efficiency, accuracy, and real-time performance.
