CPU Clock Frequency Research Articles

Mask R-CNN aided fruit surface temperature monitoring algorithm with edge compute enabled internet of things system for automated apple heat stress management

Our prior study focused on development of internet of things (IoT) and edge-compute enabled crop physiology sensing system (CPSS) for apple sunburn monitoring. Edge compute algorithm on CPSS estimated sunburn susceptibility as fruit surface temperature (FST) through pixel-by-pixel multiplication of captured thermal infrared images with segmented fruits binary mask. The segmentation was performed using color-based K means clustering approach. This limited CPSS applicability to monitor sunburn of red colored cultivars only and when fruits develop color, typically late growing season. This is a key research gap as recent weather patterns have shown that sunburn can occur during early growing season when fruits are green to yellow. Therefore, aim of this study was to develop and field evaluate cultivar and color independent mask region-convolution neural network (R-CNN) aided fruit segmentation model and edge compute compatible FST estimation algorithm. Season long field data were collected in 2021 using eight CPSS nodes (three in cv. WA38 [Cosmic crisp] and five in cv. Honeycrisp). Collected data were used to develop and validate mask R-CNN based fruit segmentation model. Developed mask R-CNN based model was able to segment fruits of two apple cultivars and of varying colors with 91.4 % average precision. In orchard evaluations (2022 season), the resulting algorithm ported on CPSS was able to accurately segment (dice similarity coefficient = 0.89) and estimate apple FST with < 0.5 °C error compared to ground truth data. With compute time of about 37 s, data processing time was reduced by 22 % over previous algorithm. High ambient temperature (>35 °C) on a warmer day resulted in multiple throttling errors caused by excessive CPU temperature; however, the CPSS performance was uncompromised in FST estimation. Ambient air temperature did not affect RAM utilization and CPU clock frequency. Overall, developed FST algorithm can potentially be used as input to actuate water-based cooling system.

Design of automatic tobacco trash detection system based on quadratic fuzzy theory

Abstract Fuzzy sets and deep learning models have accurate recognition accuracy in automatic detection. To be able to accurately identify tobacco debris and improve the quality of cigarettes, this paper proposes the design of a tobacco debris detection system with a deep learning model and fuzzy quadratic theory. The collected data is stored to AL422B by quadratic fuzzy set timing conversion, the cached image data is read by the microcontroller, the image pixel points are output, and the external controller and internal registers are set to read the tobacco image. The integrated Thumb extended instruction set to obtain the CPU clock frequency makes the controller interrupt and ensures PWM output. Integrate the internal fixed oscillator and external integrated control circuit to debug the program interface circuit to prevent power on and off misoperation. The negative log-likelihood function is obtained by following the activation rules given by the visible layer and hidden layer activation functions. The RBM is trained by quadratic fuzzy set estimation to optimize the parameters; test sample sets appear overfitting, combined with DBN pre-training and fine-tuning, iterative output, and labeling target data to meet the preset requirements to achieve intelligent detection of tobacco debris. The result analysis shows that the deep learning model and the quadratic fuzzy set generalization ability and accuracy are high, the highest F-value in tobacco clutter detection reaches 100%, and the system is designed to detect tobacco clutter automatically with high accuracy and good detection of clutter.

Reliability Evaluation of LU Decomposition on GPU-Accelerated System-on-Chip Under Proton Irradiation

Graphic processing units (GPUs) have become a basic accelerator both in high-performance nodes and low-power system-on-chip (SoC). They provide massive data parallelism and very high performance per watt. However, their reliability in harsh environments is an important issue to take into account, especially for safety-critical applications. In this article, we evaluate the influence of the parallelization strategy on the reliability of lower–upper (LU) decomposition on a GPU-accelerated SoC under proton irradiation. Specifically, we compare a memory bound and a compute bound implementation of the decomposition on a K20A GPU embedded on a Tegra K1 (TK1) SoC. We leverage the GPU and CPU clock frequencies both to highlight the radiation sensitivity of the GPU where we are running the benchmark and also to apply both algorithms to solve problems with the same size when exposed to the same radiation dose. Results show that more intensive use of the resources of the GPU increases the cross section. We also observed that most of the radiation-induced errors hang the operating system and even the rebooting process. Finally, we present a preliminary study of the error propagation of the LU decomposition algorithms.

Robust Computation Offloading and Resource Scheduling in Cloudlet-Based Mobile Cloud Computing

Mobile cloud computing (MCC) as an emerging computing paradigm enables mobile devices to offload their computation tasks to nearby resource-rich cloudlets so as to augment computation capability and reduce energy consumption of mobile devices. However, due to the mobility of mobile devices and the admission of cloudlets, the connection between mobile devices and cloudlets may be unstable, which will affect offloading decision, even cause offloading failure. To address such an issue, in this paper, we propose a robust computation offloading strategy with failure recovery (RoFFR) in an intermittently connected cloudlet system aiming to reduce energy consumption and shorten application completion time. We first provide an optimal cloudlet selection policy when multiple cloudlets are available near mobile devices. Furthermore, we formulate the RoFFR problem as two optimization problems, i.e., local execution cost minimization problem and offloading execution cost minimization problem while satisfying the task-dependency requirement and application completion deadline constraint. By solving both optimization problems, we present a distributed RoFFR algorithm for CPU clock frequency configuration in local execution and transmission power allocation and data rate control in cloudlet execution. Experimental results in a real testbed show that our distributed RoFFR algorithm outperforms several baseline policies and existing offloading schemes in terms of application completion cost and offloading data rate.

Latency-Aware Power Management in Software-Defined Radios

Cloud computing provides benefits in terms of equipment consolidation and power savings from higher utilization for virtualizable software. Cellular communication software faces challenges in cloud computing platforms. BSs create a specific load profile that differs from traditional cloud service loads. Cellular communication system implementations have real-time deadlines with fixed, periodic latency requirements. In this paper, we assess the suitability of an unmodified Ubuntu Linux OS running on a commodity server to operate latency-critical software using a 4G LTE BS software-defined radio implementation. Scaling of the CPU clock frequency is shown to be feasible without excessive impact on the platform’s ability to meet the 4 ms processing delay requirement imposed by the LTE standard. Measurements show the relationship between the processor’s operating frequency and the number of missed subframe processing deadlines to be nonlinear. The results obtained also indicate that a high computational capacity does not suffice to ensure satisfactory operation since fronthaul processing overhead can limit achievable performance. Use of offload-capable network interface cards is studied as a potential remedy.

Computation Offloading in a Mobile Edge Communication Network: A Joint Transmission Delay and Energy Consumption Dynamic Awareness Mechanism

Various problems arise in the maintenance of communication networks. For example, on-site maintenance personnel have insufficient work experience. Devices used for maintenance work have limited computing resources and battery life. Moreover, most maintenance systems still use the centralized single processing mode of traditional cloud computing, which increases the data center computing pressure and slows the data flow. To overcome these problems, we propose a communication network edge maintenance system based on smart wearable technology and introduce computation offloading technology for mobile edge computing (MEC). Before offloading, we propose a multimerged computing sorting segmentation (MCSS) algorithm to divide a part of the task to offload. When making an offloading decision, we access a suitable MEC service node for each user with the lowest transmission cost and establish a related model. We use an improved Kuhn-Munkras (KM) algorithm that considers fairness among users to solve this model. After that, we propose a dynamic energy-efficiency awareness strategy. When tasks are processed locally, we optimize the CPU clock frequency. When tasks are offloaded, we adaptively allocate the transmission power. Finally, we conduct a simulation experiment. The results demonstrate that the proposed scheme can reduce the transmission cost and improve the performance, thereby increasing the level of on-site maintenance work.

Energy-Efficient Dynamic Computation Offloading and Cooperative Task Scheduling in Mobile Cloud Computing

Mobile cloud computing (MCC) as an emerging and prospective computing paradigm, can significantly enhance computation capability and save energy for smart mobile devices (SMDs) by offloading computation-intensive tasks from resource-constrained SMDs onto resource-rich cloud. However, how to achieve energy-efficient computation offloading under hard constraint for application completion time remains a challenge. To address such a challenge, in this paper, we provide an energy-efficient dynamic offloading and resource scheduling (eDors) policy to reduce energy consumption and shorten application completion time. We first formulate the eDors problem into an energy-efficiency cost (EEC) minimization problem while satisfying task-dependency requirement and completion time deadline constraint. We then propose a distributed eDors algorithm consisting of three subalgorithms of computation offloading selection, clock frequency control, and transmission power allocation. Next, we show that computation offloading selection depends on not only the computing workload of a task, but also the maximum completion time of its immediate predecessors and the clock frequency and transmission power of the mobile device. Finally, we provide experimental results in a real testbed and demonstrate that the eDors algorithm can effectively reduce EEC by optimally adjusting CPU clock frequency of SMDs in local computing, and adapting the transmission power for wireless channel conditions in cloud computing.

Frequency scaling and energy efficiency regarding the Gauss‐Jordan elimination scheme with application to the matrix‐sign‐function on OpenPOWER 8

SummaryThe Gauss‐Jordan Elimination scheme is an alternative to the LU decomposition for solving linear systems or computing the inverse of a matrix. We develop a multi‐GPU aware implementation of this algorithm on an OpenPOWER 8 system with application to the Matrix Sign Function. Thereby, we analyze the influence of the CPU clock frequency scaling on the overall energy consumption. The results show possible energy saving of 14.2% without a noteworthy increase of the runtime.

Dual-Side Optimization for Cost-Delay Tradeoff in Mobile Edge Computing

Mobile code offloading (MCO) is a technology that offloads computing tasks from mobile devices to remote servers managed by code offload service providers (CSPs). Nowadays, it is recommended that the remote servers be placed on the edge of the network to support modern applications, e.g., augmented reality, which demand stringent and ultralow latency or high bandwidth. To date, previous studies have independently addressed code offloading policy in mobile devices and pricing/server provisioning policies in the CSP; moreover, the system models for both user side and CSP side have not adequately reflected their practical aspects. This paper designs a practical model for the both sides and takes account of them in an integrated MCO framework simultaneously. By leveraging Lyapunov drift-plus-penalty technique, we propose code offloading, local CPU clock frequency, and network interface selection policies for mobile users, and propose MCO service pricing and server provisioning policies for the CSP in each of a competition scenario and a cooperation scenario. In the competition scenario, we propose a Com-UC algorithm for mobile users and a Com-PC algorithm for the CSP with the aim to minimize each cost for each queue stability constraint. In the cooperation scenario, we propose a Coo-JC algorithm with the aim to minimize their sum cost for both mobile users and CSP. Via trace-driven simulations, we demonstrate that Com-UC saves at most 71% of its cost and Com-PC attains 82% profit gain for the same delay compared to existing algorithms; moreover, the cooperation between mobile users and CSP additionally reduces costs and delays.

Energy Neutral Wireless Sensing for Server Farms Monitoring

Energy harvesting techniques are consolidating as effective solutions to power electronic devices with embedded wireless capability. We present an energy harvesting system capable to sustain sensing and wireless communication using thermoelectric generators as energy scavengers and server's CPU as heat source. We target data center safety monitoring, where human presence should be avoided, and the maintenance must be reduced the most. We selected ARM-based CPUs to tune and to demonstrate the proposed solution since market forecasts envision this architecture as the core of future data centers. Our main goal is to achieve a completely sustainable monitoring system powered with heat dissipation of microprocessor. To this end we present the performance characterization of different thermal-electric harvesters. We discuss the relationship between the temperature and the CPU load percentage and clock frequency. We introduce a model to simulate the power characteristic of the harvester and a prototype has been realized to demonstrate the feasibility of the proposed approach. The resulting system achieves a minimum 5 min sampling frequency of environmental parameters such as temperature, humidity, light, supply voltage, and carbon-monoxide/volatile organic compounds gases using a MOX sensor mounted on a commercial wireless node with a power budget in the microwatt range.

PMaC's green queue: a framework for selecting energy optimal DVFS configurations in large scale MPI applications

SummaryThis article presents Green Queue, a production quality tracing and analysis framework for implementing application aware dynamic voltage and frequency scaling (DVFS) for message passing interface applications in high performance computing. Green Queue makes use of both intertask and intratask DVFS techniques. The intertask technique targets applications where the workload is imbalanced by reducing CPU clock frequency and therefore power draw for ranks with lighter workloads. The intratask technique targets balanced workloads where all tasks are synchronously running the same code. The strategy identifies program phases and selects the energy‐optimal frequency for each by predicting power and measuring the performance responses of each phase to frequency changes. The success of these techniques is evaluated on 1024 cores on Gordon, a supercomputer at the San Diego Supercomputer Center built using Intel Xeon E5‐2670 (Sandybridge) processors. Green Queue achieves up to 21% and 32% energy savings for the intratask and intertask DVFS strategies, respectively. Copyright © 2013 John Wiley &amp; Sons, Ltd.

A Case Study of Truncated Electrostatics for Simulation of Polyelectrolyte Brushes on GPU Accelerators.

Numerous issues have disrupted the trend for increasing computational performance with faster CPU clock frequencies. In order to exploit the potential performance of new computers, it is becoming increasingly desirable to re-evaluate computational physics methods and models with an eye toward approaches that allow for increased concurrency and data locality. The evaluation of long-range Coulombic interactions is a common bottleneck for molecular dynamics simulations. Enhanced truncation approaches have been proposed as an alternative method and are particularly well-suited for many-core architectures and GPUs due to the inherent fine-grain parallelism that can be exploited. In this paper, we compare efficient truncation-based approximations to evaluation of electrostatic forces with the more traditional particle-particle particle-mesh (P(3)M) method for the molecular dynamics simulation of polyelectrolyte brush layers. We show that with the use of GPU accelerators, large parallel simulations using P(3)M can be greater than 3 times faster due to a reduction in the mesh-size required. Alternatively, using a truncation-based scheme can improve performance even further. This approach can be up to 3.9 times faster than GPU-accelerated P(3)M for many polymer systems and results in accurate calculation of shear velocities and disjoining pressures for brush layers. For configurations with highly nonuniform charge distributions, however, we find that it is more efficient to use P(3)M; for these systems, computationally efficient parametrizations of the truncation-based approach do not produce accurate counterion density profiles or brush morphologies.

Experimental Performance Evaluation of POBICOS Middleware for Wireless Sensor Networks

The advances in the theory of wireless sensor networks have been remarkable during the past decades, but there is a lack of extensive experimental evaluations. In this paper we present performance-evaluation methods and results for POBICOS (platform for opportunistic behaviour in incompletely specified, heterogeneous object communities), which is an advanced middleware for wireless sensor networks (WSNs). The measurements concern energy consumption, duty cycle, and OS task profiling as well as communication characteristics such as round trip time (RTT) and throughput. In addition, a bandwidth analysis during a long-term experiment of fully functional POBICOS network and application is studied. Based on the evaluation results, power mode and data cache improvements are presented as well as CPU clock frequency optimizations.

Modular Software Performance Monitoring

CPU clock frequency is not likely to be increased significantly in the coming years, and data analysis speed can be improved by using more processors or buying new machines, only if one is willing to change the programming paradigm to a parallel one. Therefore, performance monitoring procedures and tools are needed to help programmers to optimize existing software running on current and future hardware. Low level information from hardware performance counters is vital to spot specific performance problems slowing program execution. HEP software is often huge and complex, and existing tools are unable to give results with the required granularity. We will report on the approach we have chosen to solve this problem that involves decomposing the application into parts and monitoring each one of them separately. Both counting and sampling methods are used to allow an analysis with the required custom granularity: from global level, up to the function level. A set of tools (based on perfmon2 - a software interface to hardware counters) for CMSSW, Gaudi and Geant4 has been developed and deployed. We will show how this type of analysis has been proven useful in spotting specific performance problems and effective in helping with code optimization.

A combined approach for QoS-guaranteed and low-power video decoding

This paper proposes a power management technique for video playback in mobile multimedia devices, which combines low-power video decoding and QoS-guaranteed algorithms: ILI (Interval-based Linear Interpolation) and QLB (QoS-guaranteed and Low-power Buffering). First, the proposed ILI algorithm precisely estimates the decoding time of video frames through interval-based linear interpolation. Second, the QLB algorithm has two modes of operation, and dynamically switches between the modes based on feedback of decoding statistics of recent frames. The combinations ILI and QLB algorithms allow the CPU voltage and clock frequency to be adjusted to the optimal setting. Our extensive experiments show that the proposed approach can achieve about 4.8%-13.7% more power savings compared with existing methods.

임베디드 응용프로그램의 동작 특성을 이용한 에너지 인식 스케쥴링 기법

효율적인 전력관리는 모바일 휴대용 제품 시장에서 중요한 경쟁력 중의 하나이다. 본 논문은 전력을 미리 예측하는 방법으로 실행중인 응용프로그램의 sleep 상태를 이용하는 Energy-Aware Scheduling policy(EASY)를 제안한다. 기존 대기 모드에서 전력소모를 줄이는 방법과의 차이점은 응용프로그램들이 얼마나 오랫동안 스케쥴러에서 sleep 상태에 있었는지를 검사하여 각 응용프로그램들의 동작 상태를 결정한다. EASY 기법은 측정된 sleep 시간을 기준으로 현재의 작업량에 맞는 적정한 CPU 클럭 주파수를 정하고, 다음 작업량의 적정한 CPU 클럭 주파수를 예측함으로서 동작 상태에서 전력 소모를 줄일 수 있다. 실험 결과 기존의 대기모드를 이용한 전력관리 기법과 비교하여 평균적으로 10-30%의 전력소모를 줄임으로써 제안된 기법의 우수성을 입증한다. Efficient power management plays a crucial role to strengthen competitiveness in the market of portable mobile commodities. This paper presents a proactive power management technique, called by Energy-Aware Scheduling policY (EASY), to exploit the sleep time information of running applications. Different from previous power management approaches focusing on power conservation in standby mode, the proposed scheme characterizes each application program's operational characteristic in active mode by observing how long the task stays in sleep state of CPU scheduler. Based on the measured sleep time, the proposed EASY speculates an adequate CPU clock frequency according to the current CPU workload and scales the frequency directly to the predicted one. Experimental results show that the proposed scheme reduces the power consumption by 10-30% on average compared to traditional DPM approach, with a minimal impact on the performance overhead.

Energy optimal speed control of a producer--consumer device pair

We propose a modular approach for minimizing the total energy consumed by a pair of generic communicating devices (producer--consumer scenario) by jointly controlling their speed profiles. Each device (like a CPU, or disk drive) is assumed to have a controllable variable called its speed (e.g., a CPU's clock frequency, a disk drive's spindle motor speed) that affects its power consumption and performance (e.g., throughput, data transfer rate). The device and task models we analyzed were inspired by applications like CD recording (hard drive to CD drive data transfer) and data processing (disk drive to CPU data transfer). The proposed solution can be used for any pair of devices with convex (for continuous speed sets) or W-convex (a discrete version of a convex function for discrete speed sets) power--speed relationships. For discrete speed sets, the method operates directly on the power--speed values and does not require an analytical relationship between power and speed. The key to solving the two-device optimization problem was the observation that it could be split into two single device parametric optimization problems, where the parameters correspond to the common task that both the devices must execute. The following divide-and-conquer approach is proposed: [divide] the optimal speed policy and energy consumption of each device is derived as an analytical function of its task parameters; [conquer] the optimal values of these parameters are found by minimizing the sum of the parameterized energy functions and plugged back into the parameterized speed profiles. The main advantage of this approach is that each device can be characterized independently and this allows system designers to mix and match manufacturer-supplied device energy curves to evaluate and optimize different application scenarios. We demonstrate our approach using three device characterization examples (for a CD drive, hard drive, and a CPU) and two application scenarios (CD recording, MD5 checksum computation).

Power‐aware optimization of CPU and frequency allocation based on fairness of QoS

AbstractIn embedded real‐time systems, it is important to reduce energy consumption in order to achieve efficient energy utilization. Many investigations have focused on Quality of Service (QoS) control, which adapts the resource consumption of task execution by adapting the QoS of the tasks. In our past work, fairness of QoS has been focused on in the QoS adaptation control methods we have proposed. In this paper, a CPU clock cycle and frequency allocation problem, whose objectives are to minimize the energy consumption for task execution and to maximize the QoS while guaranteeing fairness of QoS, is formulated as a multiobjective optimization problem. We also propose to obtain a Pareto‐optimal solution of the problem by using the weighted‐sum optimization method. © 2007 Wiley Periodicals, Inc. Syst Comp Jpn, 38(12): 37–45, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.20819

Measurement of performance impact of SSL on IP data transmissions

Secure socket layer (SSL) provides networking security at session layer of the ISO/OSI reference model. The paper deals with the problem of developing a measurement instrument for evaluating the performance of a communication system based on SSL 3.0 implemented by the SSLeay library. The developed measurement instrument is able to evaluate the maximum throughput obtainable in such a communication system and allows users to carry out an experimental investigation on the throughput variations when the encryption algorithms used for confidentiality are changed. Moreover, for the various ciphers analyzed, the performance improvement gained by increasing the CPU clock frequency has been estimated.

Copycat hand — robot hand imitating human motions at high speed and with high accuracy

We developed a method enabling them to search similar images at high speed with high accuracy and in uniform processing time, even in the case of using a large-scale database, by clustering databases with uniform numbers of data through self-organizing including self-multiplication and self-extinction, and by collating the input image with the data in the database by means of low-order amounts of characteristics of images, while narrowing the search space in accordance with the past history. By estimating the continuous hand finger shape image string by using the method, we succeeded in realizing processing with an estimation error of the joint angle within several degrees, at a processing time of 150–160 f.p.s, and in an operating time without dispersion, in the case of using a PC having a CPU clock frequency of 2.8 GHz and a memory capacity of 1GB. As the image information and the joint angle information are paired in the database, the robot hand, called the 'Copycat hand', was able to reproduce the same motions as those of the hand and fingers of a human being, without any delay in time, by outputting the results of estimation at the robot hand.