Agnostic Energy Consumption Models for Heterogeneous GPUs in Cloud Computing

Cloud Computing (CC) is a paradigm shift with the potential of transforming the information and communication technology (ICT) industry. ICT is an integral part of all businesses, and CC helps in lightening the burden of massive ICT investments. Thus, it is essential to understand the factors that influence CC adoption. The purpose of this study is to identify and rank critical factors for CC adoption in the Indian context. The research has adopted mixed methodology (qualitative and quantitative). Experts from 13 organizations (including 8 cloud service providers (CSPs) and 5 cloud service users (CSUs)) are interviewed. Content analysis is used to confirm existing factors and identify new factors in the Indian context. Qualitative analysis has identified four new factors, namely, ‘time to market’, ‘futuristic’, ‘resistance to change’ and ‘financial losses’ (arising from security and resource availability). The quantitative part of the research used analytic hierarchy process (AHP) and fuzzy analytic hierarchy process (FAHP) techniques to rank the factors. The analysis revealed ‘IT service cost’ and ‘time to market’ as the most critical factor through FAHP and AHP respectively. However, ‘organization size’ is reported the least critical for CC adoption through both the methods. The results also highlight divergence among the criticality of CC adoption factors using the two techniques. The study is very useful for CSPs and key decision-makers to understand the critical adoption factors and judiciously strategize for CC service promotions. It will also help users to wisely decide while making CC adoption decision.

Cloud computing (CC) represents a third-generation computing platform that offers numerous benefits, including faster data transactions, cost advantages, elasticity, flexibility, and pay-per-use models, among others. However, CC adoption in developing nations, such as Somalia, is impeded by various challenges. This study aims to investigate the factors influencing CC adoption in small to medium-sized enterprises (SMEs) in Somalia. Data was collected from 195 ICT officials and experts in the SME domain in Mogadishu, Somalia, and analyzed using structural equation modeling (SEM). The results revealed that cost savings, firm size, top management support, and regulatory support significantly influence CC adoption in SMEs. Conversely, security concerns and competitive pressure showed no significant relationship with CC adoption. This study contributes to the literature by examining the technology, organization, and environment (TOE) framework in the context of CC adoption and provides valuable insights to inform policymaking and promote CC adoption in developing nations. Nonetheless, the study's limitation lies in its narrow focus on Somalia, and the generalizability of the results to other developing nations may be limited.

Most Computational Fluid Dynamics (CFD) applications solve the Naiver-Stokes equations using various discretization methods like Finite Difference Method (FDM), Finite Element Method (FEM), Finite Volume Method (FVM), etc. The most compute-intensive process in CFD algorithms is the pressure Poisson solver. Solving the pressure Poisson equation requires the solution of a set of linear simultaneous equations. As the problem size/complexity increases, so does the effort and time invested in solving the equations. This study presents fast and robust iterative solvers and the acceleration of the same using the Graphics Processing Unit (GPU) architecture. Serial versions of the codes are implemented in the C language and the parallelization on GPU is achieved using Compute Unified Device Architecture (CUDA). For this study, a two-dimensional heat conduction problem is considered. FDM is used for discretization. Iterative solvers Conjugate Gradient and Multi Grid methods have been implemented in serial and parallel. The performance enhancement with single GPU and CPU system over a single CPU in terms of computing time is reported. It is seen that multigrid algorithms are superior in convergence and nearly 13 times speed-up has been obtained through GPU acceleration using CUDA, for a grid size of 2048 X 2048. The tests have been done on a cluster with Intel(R) Xeon(R) CPU E5-2670 CPU and NVIDIA K10 GPU.

Research on Cloud Computing (CC) adoption seems to be one of the less explored and examined topics in the Information Systems (IS) domains, particularly for Small and Medium-sized Enterprises (SMEs). Prior research on CC adoption does not appreciate the benefits of using Innovation Translation Approach. Instead, Essentialist Approach, a simplistic view of CC adoption which is based only on the technological characteristics of the innovation is prevalent. Thus, this study integrates the Technology-Organization-Environment framework as an IS adoption theory while Actor Network Theory as an Innovation Translation Approach in proposing the SMEs-CC adoption framework.

In recent years, container technology has been widely used in cloud computing, so the security monitoring technology for containers has also received widespread attention. To enhance the isolation of containers, cloud service providers usually run containers in different virtual machines. In this environment, in-container security tools can be detected or attacked by in-container attackers, and in-VM security tools face the risk of container escape attacks. This paper proposes a container-oriented virtual machine introspection technology to secure containers in cloud computing. It runs in cloud hypervisor and analyzes in-VM containers, so it is more secure and transparent. Even though there is container escaping to the operating system of VM, the security monitors are secure. Firstly, our approach automatically identifies the namespace and container processes in the virtual machine from outside by using virtual machine introspection technology. Secondly, security analysis is performed on processes belonging to different containers in the virtual machine, and our system can perform real-time abnormal response based on the analysis results. Finally, our system can monitor container escape behaviors from outside. Experimental results show that the approach proposed in this paper can automatically perform security analysis for different containers, and can monitor container escape behaviors with acceptable overhead.

The sustainability aspect must be implemented during all the phases of the decision-making phase regarding construction project execution to obtain the full advantages, shorn of conceding the project objective. Cloud computing (CC) has been an appreciated tool for successful and viable building processes in various nations over the past twenty years. CC and its drivers have certainly enhanced the successful and sustainable targets of quality, cost, and time. Conversely, CC adoption by the building industry in Egypt. Hence, the aim of this study is to build a decision support model to back drivers of CC adoption by analyzing the relationship concerning drivers of CC in building business in Egypt. The data was derived from various sources of the literature. A questionnaire survey for quantitative data generation followed this. The data was derived from 106 building practitioners in Egypt. Consequently, the study employed exploratory factor analysis (EFA) to authenticate the findings derived from the survey tool. The results categorized the drivers into three groups: Technology Drivers, Client Support Drivers, and Organization Drivers. Structural equation modeling using partial least squares (PLS-SEM) was then applied to test the relationships and rank their influence. Findings indicate that Technology is the most significant driver of CC adoption (β = 0.378, p < 0.001), followed closely by Client Support (β = 0.372, p < 0.001) and Organization (β = 0.360, p < 0.001). These findings can be used as a baseline or criteria for decision-making concerning improvements in the cost-effectiveness of CC and its proficiency to increase efficacy in the building sector. Therefore, this study adds to the understanding of contemporary construction management and engineering by extending the existing literature on CC adoption derivers and their effects on the building industry.

This paper presents the results of research investigating the impact of business model factors on cloud computing adoption. The introduced...

A direct simulation Monte Carlo (DSMC) method is implemented on graphical processing unit (GPU) architecture to simulate the deposition phenomena that occur on a glass panel during modern organic light emitting diodes (OLED) manufacturing processes with a huge number of simulated particles because a fully three-dimensional (3D) particle simulation is required to accurately predict deposition thickness and uniformity on the substrate in a low-pressure environment. To examine the accuracy and efficiency of the newly developed DSMC code running on GPU architecture, verification and validation tests were performed by solving several benchmarking problems. Under three conditions which have been applied in previous OLED deposition process test experiments, the new DSMC model successfully simulates the transport of organic material evaporated from the heated nozzle array and its deposition onto a glass panel inside a low-pressure chamber. The uniformity and normalized thickness between the DSMC and experimental results for the three test cases are then compared. The normalized thickness of the organic material deposited to the large glass panel calculated from the DSMC is found to have an error of less than 4%, and the uniformity values calculated from the absolute deposition thickness show good agreement with those obtained from experimental data in all test cases.

Modern computing paradigms, such as cloud computing, are increasingly adopting GPUs to boost their computing capabilities primarily due to the heterogeneous nature of AI/ML/deep learning workloads. However, the energy consumption of GPUs is a critical problem. Dynamic Voltage Frequency Scaling (DVFS) is a widely used technique to reduce the dynamic power of GPUs. Yet, configuring the optimal clock frequency for essential performance requirements is a non-trivial task due to the complex nonlinear relationship between the application’s runtime performance characteristics, energy, and execution time. It becomes more challenging when different applications behave distinctively with similar clock settings. Simple analytical solutions and standard GPU frequency scaling heuristics fail to capture these intricacies and scale the frequencies appropriately. In this regard, we propose a data-driven frequency scaling technique by predicting the power and execution time of a given application over different clock settings. We collect the data from application profiling and train the models to predict the outcome accurately. The proposed solution is generic and can be easily extended to different kinds of workloads and GPU architectures. Furthermore, using this frequency scaling by prediction models, we present a deadline-aware application scheduling algorithm to reduce energy consumption while simultaneously meeting their deadlines. We conduct real extensive experiments on NVIDIA GPUs using several benchmark applications. The experiment results have shown that our prediction models have high accuracy with the average RMSE values of 0.38 and 0.05 for energy and time prediction, respectively. Also, the scheduling algorithm consumes 15.07% less energy as compared to the baseline policies.

Scholarly research works on the adoption of Cloud Computing (CC) have recently emerged with the technology’s importance for organizations at a fast pace. Despite the numerous advantages of CC adoption for financial institutions (FI) in terms of storage cost mitigation, computation higher increase, and information access higher access rates from any place, Banking’s CC adoption executives and practitioners are badly seeking to obtain trustworthy recipes of how to utilize CC adoption frameworks to transform banks operations to cloud. In this vein and based on a systematic literature review (SLR) method, we conducted a review of 370 empirical studies from 2011 to 2021, downsized the studies to 27 directly relevant papers to reveal 14 frameworks, methods, models, or strategies of CC adoption in Banking sectors in 14 countries, and compared the findings across studies in terms of the utilized frameworks, methods, models, or strategies.

Scholarly research works on the adoption of Cloud Computing (CC) have recently emerged with the technology’s importance for organizations at a fast pace. Despite the numerous advantages of CC adoption for financial institutions (FI) in terms of storage cost mitigation, computation higher increase, and information access higher access rates from any place, Banking’s CC adoption executives and practitioners are badly seeking to obtain trustworthy recipes of how to utilize CC adoption frameworks to transform banks operations to cloud. In this vein and based on a systematic literature review (SLR) method, we conducted a review of 370 empirical studies from 2011 to 2021, downsized the studies to 27 directly relevant papers to reveal 14 frameworks, methods, models, or strategies of CC adoption in Banking sectors in 14 countries, and compared the findings across studies in terms of the utilized frameworks, methods, models, or strategies.

Nowadays graphics processing units (GPUs) have become popular parallel computing platforms known as General-Purpose GPU (GPGPU) computing. GPUs thereby are chosen by some security researchers as cryptographic accelerators to secure massive volumes of transactions. However, their security issues are ignored in spite of their popularity and performance. There are some possible information leakages faced with malicious attacks or even in the normal GPU computing. Our objective is to secure the confidentiality of cryptographic keys in GPU computing environments and provide easy-to-use programming with few constraints. In this paper, we propose a prototype in Linux, a system of GPGPU computing solution empowered by GPU virtualization technology, which keeps encrypted keys in guest machine to protect secret keys from leakage even in the event of full system compromise. With the API interception and redirection of CUDA, applications in Virtual Machines (VMs) can access the GPU device in a transparent way. Besides, we use virtio, a dedicated virtual I/O device, to transfer data between virtual and host machines in high performance. In our current study, we evaluate our prototype with the GPU implementation of ECC. We show that it can protect private keys of GPU cryptographic computation and it also incurs low performance penalty compared with the native environment, therefore demonstrating the prototype is secure and requires reasonable overhead.

As the size of data increases and computation becomes complicated in fog computing environments, the need for highperformance computation is increasing. One of the most popular ways to improve the performance of a virtual machine (VM) is to allocate a graphic processing unit (GPU) to the VM for supporting general purpose computing on graphic processing unit (GPGPU) operations. The direct pass-through, often used for GPUs in VMs, is popular in the cloud because VMs can use the full functionality of the GPU and experience virtually no performance degradation owing to virtualization. Direct pass-through is very useful for improving the performance of VMs. However, since the GPU usage time is not considered in the VM scheduler that operates based on the central processing unit (CPU) usage time of the VM, the VM performing the GPGPU operation degrades the performance of other VMs. In this paper, we analyze the effect of the VM performing the GPGPU operation (GPGPU-intensive VM) on other VMs through experiments. Then, we propose a method to mitigate the performance degradation of other VMs by dynamically allocating the resource usage time of the VM and preventing the priority preemption of the GPGPU-intensive VM.

Security Strategy for Virtual Machine Allocation in Cloud Computing

Cloud Computing is known as a provider of dynamic services. It utilizes a very large, scalable and virtualized resource over the Internet. So many industries have joined this bandwagon nowadays. One of the major research issues is to maintain good Quality of Service (QoS) of a Cloud Service Provider (CSP). The QoS encompasses different parameters, like, smart job allocation strategy, efficient load balancing, response time optimization, reduction in wastage of bandwidth, accountability of the overall system, etc. The efficient allocation strategy of the independent computational jobs among different Virtual Machines (VM) in a Datacenter (DC) is a distinguishable challenge in the Cloud Computing domain and finding out an optimal job allocation strategy guided by a good scheduling heuristic for such an environment is an NP-complete problem. So different heuristic approaches may be used for better result. The related works with other NP- complete problems have shown that solutions guided by heuristic approaches can often be improved by applying local scheduling procedure for allocating independent jobs in the virtual machines (VM) inside a Datacenter (DC), which, when combined with fast construction heuristics, can find out the shorter schedules on benchmark problems than the other solution methodologies found in different literatures, and in significant less time. This paper highlights a smart job allocation strategy for a CSP by applying Round-Robin (RR) scheduling policy.