Device Driver Research Articles

A Novel Isolation Approach for GaN-Based Power Integrated Devices.

This paper introduces a novel technology for the monolithic integration of GaN-based vertical and lateral devices. This approach is groundbreaking as it facilitates the drive of high-power GaN vertical switching devices through lateral GaN HEMTs with minimal losses and enhanced stability. A significant challenge in this technology is ensuring electrical isolation between the two types of devices. We propose a new isolation method designed to prevent any degradation of the lateral transistor's performance. Specifically, high voltage applied to the drain of the vertical GaN power FinFET can adversely affect the lateral GaN HEMT's performance, leading to a shift in the threshold voltage and potentially compromising device stability and driver performance. To address this issue, we introduce a highly doped n+ GaN layer positioned between the epitaxial layers of the two devices. This approach is validated using the TCAD-Sentaurus simulator, demonstrating that the n+ GaN layer effectively blocks the vertical electric field and prevents any depletion or enhancement of the 2D electron gas (2DEG) in the lateral GaN HEMT. To our knowledge, this represents the first publication of such an innovative isolation strategy between vertical and lateral GaN devices.

The Temperature Dependence of the Parameters of LED Light Source Control Devices Powered by Pulsed Voltage

Ambient temperature has a significant effect on the electrical and luminous parameters of light-emitting diodes (LEDs), which include forward and reverse current, forward voltage, and luminous flux. This paper gives insight into the influence of ambient temperature on the electrical and luminous parameters of LEDs powered by a rectangular pulsed voltage source versus those powered by a constant voltage source. The characteristics of LEDs in LED lighting devices were studied to determine their optimal operating conditions. To this end, rectangular pulse voltages with different pulse filling factors D were considered against the DC voltage source. Characteristics were obtained for the current stabilization mode and for the LED voltage stabilization mode. In both modes, the temperature dependence of the luminous flux, current, voltage, power consumption, and luminous efficiency of the LEDs was studied in the 20 °C to 60 °C range. The optimal LED operating conditions were determined, of which their luminous flux and luminous efficiency are least dependent on ambient temperature. When powered by a rectangular pulse voltage, the LED device drivers’ optimal pulse filling factor and operating frequency were determined.

UAV payload virtualization based on the unified driving and capability abstraction

As UAV and swarms applications continue to deepen and become increasingly widespread, UAV payloads have characteristics such as diverse types, heterogeneous forms, and complex interfaces. At the same time, it is required that the system can quickly access and efficiently manage payloads. In order to decouple the close relationship between the payloads and the system platforms, and expand the compatibility with heterogeneous payloads, a novel payload device virtualization method is proposed. Firstly, a layered driver model is proposed to decouple the device hardware and device driver, standardize the payload access process, and the driver model is implemented by using the software and hardware. Secondly, a payload abstraction based on "capability" is proposed to decouple load application and device. Finally, specific examples for the verification of the virtualization method are implemented. The present UAV payload virtualization method can not only achieve software and hardware decoupling, but also enhance the compatibility and scalability of system, improving the efficiency of unified payload management.

DEVELOPMENT OF SYSTEM SOFTWARE BASED ON THE CHATGPT CHAT-BOT

The article discusses the main aspects of system software development, namely writing program code for a simple device driver using the ChatGPT chat bot. The introduction outlines the main difficulties (hardware, software, complexity of debugging and testing, and security issues) that developers may encounter during driver development, as well as ways to possibly solve them: for example, by increasing the level of their theoretical knowledge or using modern tools, such as neural networks. The main part of the article reviews existing research in the field of system software development and testing. Existing software development tools are reviewed: such as development environments, tools for debugging, profiling, testing and static analysis of program code, as well as solutions in the field of version control and collaboration. A comparative table is provided showing the pros and cons of developing device drivers for Windows and Linux operating systems. The stages of the process of generating driver program code for a computer mouse using the ChatGPT chat bot are described. Conventionally, the article identifies five main stages: preparing training data, training, creating a query, generating and repeating stages in case of an unsatisfactory result. Examples of generated program code for a computer mouse driver for Windows and Linux operating systems are provided. In conclusion, conclusions are given regarding further prospects for using the ChatGPT chatbot in system software development tasks.

VISUAL DATA COMPUTER PROCESSING IN EDUCATIONAL DIY PROJECTS

The software tools for processing visual data in an educational chemical experiment, the experience of their usage, and a number of DIY (Do it yourself) projects developed on their basis were analyzed. Particular attention was paid to the role of self-made devices during the forced online education caused by COVID-19 and the full-scale war in Ukraine. The results of the development of the software tool ColorKit, which is being developed at the Department of Physics and Chemistry of H.S. Skovoroda Kharkiv National Pedagogical University are presented. The basic principles were covered, the interface was described, the main functions of the application and their areas of usage were given. The principle of operation of the modules: "Spectrophotometer", "Colorimeter", "Refractometer", "Polarimeter" was characterized. The features of the structure of optical computer devices for physico-chemical analysis developed by teachers, students of higher education and students, members of the Academy of Medical Sciences were considered, and the results of their testing were highlighted. The design of an absorption spectrophotometer based on a reflective diffraction grating made from a DVD disc was described; a new method of its calibration using a diamond green solution was proposed. The operating model was tested and it was established that the accuracy of the device was sufficient for demonstration and educational chemical experiments. The operating principle of the "Colorimeter" module of the ColorKit software tool was considered. It was shown that, unlike other software tools, it had built-in approximation tools, which significantly facilitated the processing of visual data; displaying the results of mathematical processing in a graphic form, which made the experiment visual. It should be noted that for the correct operation of the virtual spectrophotometer and colorimeter in real time, the correct setting of the video device driver is quite important. A number of optical schemes of refractometers developed on the basis of the ColorKit software tool were presented: with liquid and V-prisms; i.e. the device whose principle of action is based on changing the optical properties of the lens in contact with the solution. It was shown that the simultaneous display of the course of the rays and the results of mathematical processing provides a high level of visibility. The results of the approval of the LED DIE refractometer with a V-prism are outlined. Further prospects for the development of the ColorKit project are planned.

A Graphics Device Driver Implementation Compliant with OpenGL SC 2.0.1 Standard Specification

Various 3D graphics outputs are increasingly required in the field of safety-critical applications including military, avionics, aerospace, and medical applications. In this paper, we present a graphics device driver implementation of OpenGL SC (Open Graphics Library – Safety Critical) 2.0.1, a 3D graphics standard specification that reflects the needs of the safety-critical field. OpenGL SC 2.0.1 was newly announced in 2019, and only a few limited number of implementation cases have been reported so far. In this paper, to increase its own portability, we designed to only use some functions of DRM (direct rendering manager) in a general Linux environment, while various test results were confirmed targeting specific GPUs, in our case, Intel HD630 GPU. The implementation results can be used to implement 3D graphics terminals in the military and aviation fields.

A Multiagent Reinforcement Learning-Assisted Cache Cleaning Scheme for DM-SMR

To support non-sequential writes, Persistent Cache (PC) is constructed in DM-SMR drive. However, PC cleaning introduces drastic performance degradation and enlarges tail latencies. In this paper, we propose to utilize Reinforcement Learning (RL) to mitigate the long-tail latency of PC cleaning. Our scheme uses lightweight Q-learning method to monitor and learn the idle time of I/O workloads, based on which PC cleaning is intelligently guided, thus maximally exploit idle time between requests and hiding tail latency from normal requests. In addition, a multi-agent RL scheme with clustering algorithm is adopted to further mitigate the tail latencies and adapt to variable workloads. We emulate a DM-SMR drive inside a Linux device driver to implement our proposed scheme. According to the experimental results, our scheme can effectively reduce the tail latency by 59.45% at 99.9th percentile and the average latency by 48.75% compared with a typical SMR design.

Electric personal mobility device driver behaviors, their antecedents and consequences: A narrative review

Introduction: Electric personal mobility devices (ePMDs), as well as crashes involving ePMDs, have been on the rise all over the world. The objectives of this study were: (a) to summarize the literature based on a narrow definition of ePMD (excluding e-bikes) and (b) to sort out the results to fit into a psychological and behavioral framework. The available literature was sorted into three main categories: the behaviors of ePMD drivers, their antecedents, and their consequences. Method. A narrative review of the literature was carried out in 101 documents published between January 2018 and July 2021. Results. Regarding behavioral antecedents, regulations vary from country to country. ePMDs were found to be used primarily by males under 40 years of age. We found no studies on driving skills or learning, driver education or training, or on the effect of health messages on attitudes and behavior. Regarding the main behaviors themselves, the drivers’ reasons for focusing on ePMDs were our main focus (use for short distances and mainly for commuting, shopping, and leisure). Few of the studies we reviewed explored the interactions between ePMD drivers and other road users in natural or simulated environments, and the influence of road infrastructure on behavior has rarely been studied. Regarding health consequences, reported ePMD crashes resulted in serious head and limb injuries, especially head and leg fractures. The lack of personal protective equipment (e.g., a helmet) increased the severity of crashes. The conclusion highlights gaps in the literature from a psychological and behavioral point of view.

Real-Time USB Networking and Device I/O

Multicore PC-class embedded systems present an opportunity to consolidate separate microcontrollers as software-defined functions. For instance, an automotive system with more than 100 electronic control units (ECUs) could be replaced with one or, at most, several multicore PCs running software tasks for chassis, body, powertrain, infotainment, and advanced driver assistance system (ADAS) services. However, a key challenge is how to handle real-time device input and output (I/O) and host-level networking as part of sensor data processing and control. A traditional microcontroller would commonly feature one or more Controller Area Network (CAN) buses for real-time I/O. CAN buses are usually absent in PCs, which instead feature higher bandwidth Universal Serial Bus (USB) interfaces. This article shows how to achieve real-time device I/O and host-to-host communication over USB, using suitably written device drivers and a time-aware POSIX-like “tuned pipe” abstraction. This allows developers to establish task pipelines spanning one or more hosts, with end-to-end latency and throughput guarantees for sensor data processing, control, and actuation.

Overcoming the IOTLB wall for multi-100-Gbps Linux-based networking.

This article explores opportunities to mitigate the performance impact of IOMMU on high-speed network traffic, as used in the Linux kernel. We first characterize IOTLB behavior and its effects on recent Intel Xeon Scalable & AMD EPYC processors at 200 Gbps, by analyzing the impact of different factors contributing to IOTLB misses and causing throughput drop (up to 20% compared to the no-IOMMU case in our experiments). Secondly, we discuss and analyze possible mitigations, including proposals and evaluation of a practical hugepage-aware memory allocator for the network device drivers to employ hugepage IOTLB entries in the Linux kernel. Our evaluation shows that using hugepage-backed buffers can completely recover the throughput drop introduced by IOMMU. Moreover, we formulate a set of guidelines that enable network developers to tune their systems to avoid the "IOTLB wall", i.e., the point where excessive IOTLB misses cause throughput drop. Our takeaways signify the importance of having a call to arms to rethink Linux-based I/O management at higher data rates.

Preview the Products on Display at Display Week 2023

Preview the Products on Display at Display Week 2023

HyperIO: A Hypervisor-Based Framework for Secure IO

Malware often attempts to steal input and output through human interface devices to obtain confidential information. We propose to use a thin hypervisor, called “HyperIO”, to realize a secure path between input and output devices using a partial implementation of device drivers. We apply our approach using two security systems built on HyperIO: FireSafe and ClipCrypt. FireSafe is a web browser extension which allows a remote web server to display and receive sensitive user information securely. ClipCrypt enables the user to securely enter and view their confidential information in commodity Windows applications.

動機付けを考慮したLinuxデバイスドライバプログラミング教材の改良

動機付けを考慮したLinuxデバイスドライバプログラミング教材の改良

베이스보드 매니지먼트 컨트롤러를 위한 부팅 과정 프로파일링 도구

Baseboard Management Controller(BMC) supports server monitoring, maintenance, and control functions using various communication interfaces. However, if an unexpected problem occurs during the device driver initialization process, the BMC may not operate normally. Therefore, a boot process profiling tool that accurately analyzes the device driver initialization process and provides a function to check the analysis result is essential. Existing boot process profiling tools do not specifically provide the device driver initialization process and results required for BMC boot process analysis, forcing developers to use a combination of tools to analyze the boot process in detail. In this paper, we propose an integrated profiling tool for BMC's booting process. The proposed tool provides device driver initialization process analysis, CPU and memory usage analysis, and kernel version management functions. Users can easily analyze the booting process using the proposed tool, and the analysis result can be used to shorten the booting time. Also, the proposed tool is implemented in Linux-based BMC, and it is shown that the proposed tool is more efficient than the existing profiling tool.

On-Chip Dynamic Gate-Voltage Waveform Sampling in a 200-V GaN-on-SOI Power IC

The continual improvement of GaN-on-Si processes motivates the integration of more complex circuits alongside GaN power devices. Additional transistors can be leveraged to provide control, logic, and protection; however, low-voltage GaN devices consume more power and area than similar CMOS counterparts. This article investigates the feasibility of a monolithic gate-monitoring circuit integrated with a GaN power device and gate driver. The monitoring circuit captures 16 samples within 50 ns during the gate rising transient and stores them in on-chip capacitors. The stored voltages are asynchronously read off-chip through integrated source-follower buffers and a digitally controlled multiplexer. The proposed design incorporates approximately 330 e-HEMT transistors and was fabricated in a 200-V GaN-on-SOI process. A detailed characterization was performed to calibrate the dynamic on-chip gate voltage from the sampled values that are read off-chip, paving the way for future active control based on this feedback. Experimental results and the postcalibration estimate of the on-chip gate voltage highlight that off-chip measurements are poor and pessimistic estimators for the on-chip dynamic excursions. The on-chip gate-voltage waveform was estimated using the sampling circuit while switching the power device at 80 V, 1.5 A, demonstrating more accurate measurements of on-chip signals. This circuit stands as a proof-of-concept for the viability of integrating relatively complex circuits in GaN power ICs to perform critical monitoring and sensing tasks.

A Survey of Storage Systems in the RDMA Era

Remote Direct Memory Access (RDMA) based network devices are increasingly being deployed in modern data centers. RDMA brings significant performance improvements over traditional network devices such as Ethernet due to its unique features: <i>protocol offloading</i> and <i>memory semantics</i> . In particular, it can achieve microsecond level latency, which is about 2 <inline-formula><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 3 orders of magnitude improvement. With such improvement in hardware, the software stack, including device drivers and programming libraries, is becoming a new performance bottleneck. Developers need to use new programming libraries to take full advantage of the performance of the underlying hardware. Storage systems are very important in modern data centers. This article surveys the current efforts to use RDMA for optimizing storage systems. We first present five classes of RDMA-based storage systems, including key-value stores, file systems, distributed memory systems, database systems, and systems using smart NICs, to demonstrate different design choices. Then, we examine the core modules of storage systems from different perspectives: communication mode, concurrency control, fault tolerance, caching, and resource management. Finally, we provide some design guidelines for new RDMA-based storage systems, as well as a discussion of opportunities and challenges.

Design A Mini Operating System Using Open Source System

Abstract: COSMOS (C# Open Source Managed Operating System) Paper provides a framework and tool-chain to develop an OS purely in managed code (C# and VB .NET). Cosmos supports integration with Visual Studio, and therefore is much easier to use. However, the framework is not rich, and therefore, there is still a lot of work to be done on OS developer side (E.g., it does not support mouse, file system etc.) In this paper, a microkernel based OS is developed using COSMOS framework for x86 based computer systems. This paper demonstrates device driver (PS/2) pointing device and GUI System. Since Cosmos does not provide support file system, mouse, keyboard, we have designed appropriate drivers for screen, mouse and keyboard. We have developed Event handlers and drivers for each device.In this part, we have developed drivers for Hard Disk and RAM to detect them in order to achieve partial fulfilment. From the development of general purpose computers, software industry has also evolved. However, there is not much improvement in OS development, as compared with other fields of software world: while other fields are enjoying power of garbage collection, OS developers are still doing their job in classic languages like C, C++ and assembly. Although there has been some research work regarding this, none of them was successful. This project is an attempt to develop a mini OS in pure managed code, particularly C# and .NET Framework 4.0.

Intelligent Fingerprint-Based Localization Scheme Using CSI Images for Internet of Things

Fingerprint-based indoor localization methods have become an important technology because of their wide availability, low hardware costs, and the rapidly growing demand for location-based services. However, it is low precision of positioning and time-consuming for retraining the model when the fingerprint database has changed with new input samples. In this paper, we propose a novel intelligence localization scheme utilizing incremental learning without retraining models based on channel state information (CSI), namely ILCL. CSI phase data are extracted through a modified device driver, and we convert them into CSI images, which are the input to a convolutional neural network for training the weights in the offline stage. The estimated location is obtained by a probabilistic method based on a broad learning system (BLS) that can continue to train rapidly on new input data in the online stage. The ILCL architecture can be characterized as “deep” and “broad” and can further extract features. Experimental results confirm the superiority of ILCL compared with five existing algorithms in two real-world indoor environments with a total area is over 200 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">${m}^{2}$</tex-math></inline-formula> .

SMT-based verification of program changes through summary repair

This article provides an innovative approach for verification by model checking of programs that undergo continuous changes. To tackle the problem of repeating the entire model checking for each new version of the program, our approach verifies programs incrementally. It reuses computational history of the previous program version, namely function summaries. In particular, the summaries are over-approximations of the bounded program behaviors. Whenever reusing of summaries is not possible straight away, our algorithm repairs the summaries to maximize the chance of reusability of them for subsequent runs. We base our approach on satisfiability modulo theories (SMT) to take full advantage of lightweight modeling approach and at the same time the ability to provide concise function summarization. Our approach leverages pre-computed function summaries in SMT to localize the checks of changed functions. Furthermore, to exploit the trade-off between precision and performance, our approach relies on the use of an SMT solver, not only for underlying reasoning, but also for program modeling and the adjustment of its precision. On the benchmark suite of primarily Linux device drivers versions, we demonstrate that our algorithm achieves an order of magnitude speedup compared to prior approaches.

Customization of GPRS, and Wi-Fi device drivers for PXA270 of Linux OS based barcode scanner

To access any device, it is necessary to have an access point. A device driver is an entry point to access a device. This project is aimed to customize the Wi-Fi and general packet radio service (GPRS) device drivers in Linux OS for PXA270 (Intel Xscale ARM processor). Customizing a device driver is a special way of designing software that can be more easily ported from one architecture to another without rewriting it from scratch. The paper is discussing about the customisation of Wi-Fi and GPRS device driver in Linux OS for PXA270 (Intel Xscale ARM processor). To develop a device driver, it is necessary to understand the processor architecture and Linux kernel internals and other design constraints. Since dynamically loaded driver module is attached to the existing kernel, and any error in the driver will crash the entire system. Resource allocation and implementation for a device is one of the main concerns for device driver developers. The device resources are input/output, memory, IRQs and ports. The required toolchain to build the cross-complier for the Intel Xscale ARM processor was built on Linux platform. The customised device drivers of Wi-Fi, and GPRS was customised, and the customised images are made to port for PXA270 processor architecture on EMX-270 board. With all the supporting parameters the kernel images with drivers are build and ported efficiently. Also, a successful verification and testing had been performed for their functionalities.