Performance Comparisons of Timing Techniques in a Non-Real-Time Environment

Author(s):  
Frederick M. Proctor ◽  
Justin R. Hibbits

General-purpose computers are increasingly being used for serious control applications, due to their prevalence, low cost and high performance. Real-time operating systems are available for PCs that overcome the nondeterminism inherent in desktop operating systems. Depending on the timing requirements, however, many users can get by with a non-real-time operating system. This paper discusses timing techniques applicable to non-real-time operating systems, using Linux as an example, and compares them with the performance that can be obtained with true real-time OSes.

Author(s):  
Massimo Violante ◽  
Gianpaolo Macario ◽  
Salvatore Campagna

Automotive infotainment applications are examples of embedded systems in which a heterogeneous software stack is used, which most likely comprises a real-time operating system, an automotive-grade Linux, and possibly Android. Thanks to the availability of modern systems-on-a-chip providing multicore computing platforms, architects have the possibility of integrating the entire software stack in a single chip. Embedded virtualization appears an interesting technology to achieve this goal, while providing the different operating systems the capability of exchanging data as well as optimizing resource usage. Although very well known in server-class systems, virtualization is rather new to the embedded domain; in order to leverage its benefits, it is therefore mandatory to understand its peculiarities and shortcomings. In this chapter, the authors illustrate the virtualization technologies with particular emphasis on hypervisors and Linux Containers. Moreover, they illustrate how those technologies can cooperate to fulfill the requirements on automotive infotainment applications. Finally, the authors report some experimental evidence of the performance overheads introduced when using embedded virtualization.


2010 ◽  
Vol 47 (2) ◽  
pp. 120-131 ◽  
Author(s):  
Janez Puhan ◽  
Árpád Bűrmen ◽  
Tadej Tuma ◽  
Iztok Fajfar

The paper discusses whether (and how) to teach assembly coding as opposed to (or in conjunction with) higher programming languages as part of a modern electrical engineering curriculum. We describe the example of a very simple cooperative embedded real-time operating system, first programmed in C and then in assembler. A few lines of C language code are compared with the slightly longer assembly code equivalent, and the advantages and drawbacks are discussed. The example affords students a much deeper understanding of computer architecture and operating systems. The course is linked to other courses in the curriculum, which all use the same hardware and software platform; this lowers prices, reduces overheads and encourages students to reuse parts of a written code in subsequent courses. A student learns that badly written and poorly documented code is very difficult to reuse.


2011 ◽  
Vol 383-390 ◽  
pp. 6964-6968
Author(s):  
Hui Li ◽  
Hao Zhang ◽  
Dao Gang Peng ◽  
Jia Wei Wang

This paper uses ARM7 processor LPC2290, embedded data acquisition chip AD7715 and real-time operating system μC/OS-II as a basis to design an ARM-based embedded data acquisition system. This system achieves RS-232/RS-485 communication, Ethernet communication, keyboard and LCD display embedded control applications. It has a small size hardware, low power consumption, plenty functions and highly extended features. The reliability of embedded real-time operating system μC/OS-II has been certified. It makes the system more stable, and makes maintenance and upgrade program more convenient.


Author(s):  
Tri Cong Phung

Controlling accurately the position and velocity of robots in a given time is an important requirement in the industry. The open-source real-time operating systems not only have more advantages than the normal operating systems in both economy and flexibility but also meet the needs. This paper concentrates on building algorithms for controlling the robot trajectory in time using a modern real-time operating system called Linux-Xenomai. Firstly, the paper analyzes several advantages of the real-time operating system Linux-Xenomai comparing general operating systems and other real-time operating systems. Secondly, a real-time controller of a 5 degree-of-freedom (DOF) robot is built based on the real-time operating system Linux-Xenomai. After that, the paper proposes algorithms to test the ability of working in time of the robot. Finally, the real experiments are done to verify the proposed algorithms.


Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5853
Author(s):  
Jesús Morales ◽  
Jorge L. Martínez ◽  
Alfonso J. García-Cerezo

This paper proposes a low-cost sensor system composed of four GNSS-RTK receivers to obtain accurate position and posture estimations for a vehicle in real-time. The four antennas of the receivers are placed so that every three-antennas combination is optimal to get the most precise 3D coordinates with respect to a global reference system. The redundancy provided by the fourth receiver allows to improve estimations even more and to maintain accuracy when one of the receivers fails. A mini computer with the Robotic Operating System is responsible for merging all the available measurements reliably. Successful experiments have been carried out with a ground rover on irregular terrain. Angular estimates similar to those of a high-performance IMU have been achieved in dynamic tests.


Author(s):  
Amit K. Shukla ◽  
Rachit Sharma ◽  
Pranab K. Muhuri

A real-time operating system (RTOS) is an integral part of a real-time embedded system (RTES). Most of the RTESs work on dynamic environments, and hence, the computational cost of tasks cannot be calculated in advance. Thus, RTOSs play a significant role in the smooth operations of the RTES through efficient task scheduling schemes and resource managements. This article investigates the existing design challenges and scope of the modern RTOSs. A wide variety of latest RTOSs are discussed and elaborated in detail. A comparative study with their prospects has been explained so that interested readers can use the article as a readily available starting point for their further studies on this topic.


2016 ◽  
Vol 10 (1) ◽  
pp. 13-22
Author(s):  
Ionel Zagan ◽  
Vasile Gheorghita Gaitan

Abstract The predictable CPU architectures that run hard real-time tasks must be executed with isolation in order to provide a timing-analyzable execution for real-time systems. The major problems for real-time operating systems are determined by an excessive jitter, introduced mainly through task switching. This can alter deadline requirements, and, consequently, the predictability of hard real-time tasks. New requirements also arise for a real-time operating system used in mixed-criticality systems, when the executions of hard real-time applications require timing predictability. The present article discusses several solutions to improve the performance of CPU architectures and eventually overcome the Operating Systems overhead inconveniences. This paper focuses on the innovative CPU implementation named nMPRA-MT, designed for small real-time applications. This implementation uses the replication and remapping techniques for the program counter, general purpose registers and pipeline registers, enabling multiple threads to share a single pipeline assembly line. In order to increase predictability, the proposed architecture partially removes the hazard situation at the expense of larger execution latency per one instruction.


2014 ◽  
Vol 7 (1) ◽  
pp. 16-29
Author(s):  
Taqwa Flayyih Hasan

Scheduling is a key concept in computer multitasking and multiprocessing operating system design, and in real-time operating system design. CPU scheduling is the basis of multiprogramming operating systems by switching the CPU among process; the operating system can make the computer more productive, scheduling algorithms are widely used in communications networks and in operating systems to allocate resources to competing tasks. In this paper, visual interfaces for CPU scheduling algorithms were designed by using Visual Basic6 language. They may use to learn users about this algorithms and how they work


2014 ◽  
Vol 8 (1) ◽  
pp. 38-61
Author(s):  
Prashanta Kumar Patra ◽  
Padma Lochan Pradhan

This article provide maximum preventive control, high performance and fault tolerance at an optimal resources, cost, time with high availability and quality of services to be invested into dynamic security mechanisms deciding on the measure component of real time operating system resources (Shell, File, Memory, Processor, Kernel, Encryption key, I/O devices). The authors have to define, design, develop and deploy our valuable idea to be optimizing the technology, resource, cost and maximize the throughput, productivity of business all together at anytime and anywhere in around the globe by applying this integrated dynamic model. This dynamic model interfacing, integrating, communicating, synchroning, preventing and optimize step by step through real time algebraic method over a RTOS on distributed super scalar environment (MIMD). This proposed dynamic algebraic model would be preventing the data and services on RTOS from uncertainty, unorder, unsetup, unsafe and external hackers. Mean while this model would be identifying vulnerabilities and threats on operating system resources to achieving the highest business objectives by utilizing the efficient and reliable resources management. The authors have to optimized the system attacks and down time by verification and validation of this method on complex heterogonous infrastructure.


Sign in / Sign up

Export Citation Format

Share Document