A methodology for fast scheduling of partitioned systolic algorithms

Resource provisioning in scalable cloud using bio-inspired artificial neural network model

Environmental issues and the need to reduce energy consumption for lowering operating costs have pushed power efficiency to become one of the major issues of current research in the field of wireless networks. This paper addresses a number of multiple input multiple output (MIMO) precoding and scheduling techniques across the PHY and MAC layers that can operate under a reduced link budget and collectively improve the transmit power efficiency of a base station, while maintaining the same levels of service. Different MIMO transmission and precoding schemes proposed for LTE, achieving varying degrees of multiuser diversity in both the time, frequency as well as the space domain, are examined. Several fairness-aware resource allocation algorithms are applied to the considered MIMO schemes and a detailed analysis of the tradeoffs between power efficiency and quality of service is presented. This paper explicitly examines the performance of a system serving real-time, VoIP traffic under different traffic loading conditions and transmit power levels. It is demonstrated that by use of efficient scheduling and resource allocation techniques significant savings in terms of consumed energy can be achieved, without compromising QoS.

Heterogeneous computing platforms with multicore central processing units (CPUs) and graphics processing units (GPUs) are of increasing interest to designers of embedded signal processing systems since they offer the potential for significant performance boost while maintaining the flexibility of software-based design flows. Developing optimized implementations for CPU-GPU platforms is challenging due to complex, inter-related design issues, including task scheduling, interprocessor communication, memory management, and modeling and exploitation of different forms of parallelism. In this paper, we present an automated, dataflow based, design framework called DIF-GPU for application mapping and software synthesis on heterogeneous CPU-GPU platforms. DIF-GPU is based on novel extensions to the dataflow interchange format (DIF) package, which is a software environment for developing and experimenting with dataflow-based design methods and synthesis techniques for embedded signal processing systems. DIF-GPU exploits multiple forms of parallelism by deeply incorporating efficient vectorization and scheduling techniques for synchronous dataflow specifications, and incorporating techniques for streamlining interprocessor communication. DIF-GPU also provides software synthesis capabilities to help accelerate the process of moving from high-level application models to optimized implementations.

Dataflow programming has proven to be popular for representing applications in rapid prototyping tools for digital signal processing (DSP), however, existing dataflow design tools are limited in their ability to effectively handle dynamic application behavior. We develop efficient quasi-static scheduling techniques for a broad class of dynamically-reconfigurable dataflow specifications. We use a CD to DAT sample rate conversion system and a speech compression application to illustrate the efficacy of our scheduling techniques in real life DSP systems.

Cloud computing is an innovative technology that mainly relies on sharing of computing resources, data as well as information over the internet. Cloud computing has been evolved from technological growth in Grid systems, Virtualization and Web2.0. Efficient Load Balancing (LB) and scheduling techniques are required for optimal utilization of computing resources and to reduce turnaround time. Load Balancing balances the load among nodes by shifting load from over-utilized node to under-utilized node. This paper presents an extensive review of different meta-heuristic techniques that are applicable in grid and cloud systems to generate optimal load balancing solution.

Cloud computing is becoming very common in recent years and is growing rapidly due to its attractive benefits and features such as resource pooling, accessibility, availability, scalability, reliability, cost saving, security, flexibility, on-demand services, pay-per-use services, use from anywhere, quality of service, resilience, etc. With this rapid growth of cloud computing, there may exist too many users that require services or need to execute their tasks simultaneously by resources provided by service providers. To get these services with the best performance, and minimum cost, response time, makespan, effective use of resources, etc. an intelligent and efficient task scheduling technique is required and considered as one of the main and essential issues in the cloud computing environment. It is necessary for allocating tasks to the proper cloud resources and optimizing the overall system performance. To this end, researchers put huge efforts to develop several classes of scheduling algorithms to be suitable for the various computing environments and to satisfy the needs of the various types of individuals and organizations. This research article provides a classification of proposed scheduling strategies and developed algorithms in cloud computing environment along with the evaluation of their performance. A comparison of the performance of these algorithms with existing ones is also given. Additionally, the future research work in the reviewed articles (if available) is also pointed out. This research work includes a review of 88 task scheduling algorithms in cloud computing environment distributed over the seven scheduling classes suggested in this study. Each article deals with a novel scheduling technique and the performance improvement it introduces compared with previously existing task scheduling algorithms. Keywords: Cloud computing, Task scheduling, Load balancing, Makespan, Energy-aware, Turnaround time, Response time, Cost of task, QoS, Multi-objective. DOI: 10.7176/IKM/12-5-03 Publication date: September 30 th 2022

The design of optimal planar systolic arrays for matrix multiplication

The concept oft Cloud computing has significantly changed the field of parallel and distributed computing systems today. Cloud computing enables a wide range of users to access distributed, scalable, virtualized hardware and/or software infrastructure over the Internet. Load balancing is a methodology to distribute workload across multiple computers, or other resources over the network links to achieve optimal resource utilization, maximize throughput, minimum response time, and avoid overload. With recent advent of technology, resource control or load balancing in cloud computing is main challenging issue. A few existing scheduling algorithms can maintain load balancing and provide better strategies through efficient job scheduling and resource allocation techniques as well. In order to gain maximum profits with optimized load balancing algorithms, it is necessary to utilize resources efficiently. This paper presents a review of a few load balancing algorithms or technique in cloud computing. The objective of this paper is to identify qualitative components for simulation in cloud environment and then based on these components, execution analysis of load balancing algorithms are also presented.

The essence of efficient scheduling and data transmission techniques lies in providing the Web-applications with advanced data processing capabilities. In this paper we have efficiently combined the push and the pull scheduling to develop a new, practical, dynamic, hybrid scheduling strategy for heterogenous, asymmetric environments. The proposed algorithm dynamically computes the probabilities and the optimal cutoff-point to separate the push and the pull data sets. The data items are also assumed to be of variable lengths. While the push strategy uses the flat, round-robin scheduling, the pull items are determined by stretch-optimal (max-request min-service time) scheduling policy. In order to make the scheduling more practical, we have considered the impact of the impatience of the clients waiting to get the service of a particular data item. The effects of this impatience can lead to departure of specific client(s) from the system. Our proposed hybrid scheduling strategy takes care of these effects to capture a real portrayal of the system dynamics. These scenarios are modelled by suitable birth and death process to analyze the overall expected delay of the system. Subsequently, simulation results corroborate the average system performance and points out significant improvement over existing hybrid systems in terms of average waiting time spent by a client.

Delay and Disruption Tolerant Networks (DTNs) have been proposed for challenging environments where the instability or lack of end-to-end paths is the rule rather than the exception. In this context, the principle of store-carry-and forward is used to sustain data sessions under intermittent connectivity, and data replication to increase the probability of on-time delivery. However, these techniques create the need for efficient scheduling and buffer management techniques, as the data load is generally larger than the amount of the available resources (i.e. bandwidth per communication opportunity, and buffer storage). A number of recent schemes have been proposed to make forwarding decisions that improve or even optimize the usage of these resources, in one way or another. Nevertheless, the majority of these schemes consider application sessions (and thus data messages) of equal importance. Furthermore, the few proposals that consider different traffic classes, do so in a somewhat "ad-hoc" manner, failing to provide real QoS guarantees. To this end, in this paper we formulate the problem of maximizing the network performance, in a limited resource network, subject to constraints corresponding to distinct QoS requirements (e.g., delivery probability) for each application class. Based on this formulation, we propose a distributed algorithm which: (i) guarantees that the individual QoS constraints are satisfied, when this is feasible given the amount of available resources, and (ii) allocates any remaining resources optimally, so as to maximize the desired performance metric. Simulation results, based on synthetic and realistic mobility scenarios, support our theoretical claims and further show that our policy outperforms other existing QoS prioritization schemes.

The ever-increasing popularity of Web services, growing demand for wireless multimedia and introduction of new, feature-enhanced, hand-held devices has already given birth to a new set of data-centric applications. Providing such applications with enhanced data processing capability calls for an efficient scheduling and transmission technique. The goal of most scheduling strategy lies in reducing the average waiting time. However, in most practical systems the variation of waiting time often results in client's impatience, thus provoking the clients to send repeated requests for the particular data item(s). In this paper we have developed a new hybrid scheduling framework for heterogeneous, asymmetric environments, by exploring the advantages of broadcasting very popular (push) data and dissemination of less popular (pull) data. The data access probabilities and the cut-off point used to segregate push and pull sets are dynamically computed. Packet fair scheduling (PFS) and stretch-optimal scheduling principle is deployed to obtain the push and pull schedule respectively. The framework explicitly takes care of the repeated requests originating from the impatient clients and minimizes the overall expected access time by obtaining an optimal cut-off point. Extensive performance analysis and simulation experiments are performed to show the efficiency of the system in reducing the overall expected access time (delay).

The rapid growth of web services has already given birth to a set of data dissemination applications. Efficient scheduling techniques are necessary to endow such applications with advanced data processing capability. In this paper, we have developed a new hybrid scheduling scheme by effectively combining broadcasting of very popular (push) data and dissemination of less popular (pull) data to develop a new, ideal hybrid scheduling scheme. Our algorithm assumes no prior knowledge of the data access probability, i.e. which items are being pushed or pulled. Instead, data access probabilities and the cut-off-point to segregate the push and the pull sets are computed dynamically. The data items are assumed to be of variable lengths. The clients send their requests to the server, which ignores the requests for the push items but queues those for the pull items. An ideal behavior of the clients is assumed: a client, after making a request, patiently waits without taking any action. Every client is assumed to have a priority. The priority of a data item is determined by adding the priorities of all the clients requesting that item. At every instant, the item to be broadcast is selected with the help of a pure-push scheduling. On the other hand, the item to be pulled is the one stored in the pull-queue, having the optimal stretch value (max-request min-service time). When more than one data item has the same stretch value, the influence of the priorities of different clients on data dissemination is considered. A suitable modelling technique using the birth-and-death process is developed to analyze the performance of the system. Simulation results corroborate the average system performance and exhibit significant improvement over a pure push and existing hybrid systems in terms of average waiting time spent by a client.

Cloud computing is a revolutionary cloud or Internet-based computing that provides services to customers with their on-demand requirements. The service providers who use cloud computing can provide their services to the users simultaneously. Also, cloud computing helps the users to use it like pay-as-you-go service over the internet providing them with uncertainty, dynamism, and elasticity-based services. It is being widely used by many clients in the fields of education, government services, telecommunication, and financial services. Due to the rapid growth of demand for cloud computing services and the heterogeneous nature of the resources for cloud computing, resource scheduling has become a major issue. In recent times, it can be observed that the increase of cloud services is to increase the workload in the cloud environment. The algorithms used for scheduling also need to optimize the main performance indicating parameters such as makespan time, response time, cost, reliability, energy consumption, availability, and resource utilization. Many state-of-the-art scheduling algorithms are proposed in the past to fulfill these requirements. These algorithms are based on heuristic, metaheuristic, and hybrid techniques. In this paper, systematic reviews of these scheduling techniques including the proposed scheduling techniques are provided with their classification.

Consideration is given to the problem of mapping systolic array algorithms into efficient algorithms for a fixed-size hypercube architecture. The authors describe in detail several optimal implementations of algorithms given for one-way one- and two-dimensional systolic arrays. Since interprocessor communication is many times slower than local computation in parallel computers built to date, the problem of efficient communication is specifically addressed for these mappings. In order to validate the technique experimentally, five systolic algorithms were mapped in various ways onto a 64-node NCUBE/7 MIMD hypercube machine. The algorithms are for the following problems: the shuffle scheduling problem, finite impulse response filtering, linear context-free language recognition, matrix multiplication, and computing the Boolean transitive closure. Experimental evidence indicates that good performance is obtained for the mappings. >

Petri Nets for Real Time Control Algorithms Decomposition