Multiprocessor Systems Research Articles

SpecMap: An efficient spectral partitioning based static application mapping algorithm for 2D mesh NoCs

SummaryNetwork‐on‐chip (NoC) is adopted as a flexible and effective communication backbone by multiprocessor systems with core counts ranging from a few to hundreds. The performance of NoC based systems greatly rely on the communication between cores when two dependent tasks of an application are mapped to these cores. Hence, application mapping becomes a critical issue in NoC‐based systems as it affects the overall performance of the system. Application mapping aims to reduce the communication among the cores by carefully mapping the highly communicating tasks. Most of the existing static mapping approaches consider only single‐task platforms. In this article, we propose an efficient multi‐task static mapping algorithm called , for regular 2D NoC systems. consists of three stages namely, (i) graph partitioning, (ii) topology clustering, and (iii) mapping. In the graph partitioning stage, accurately identifies and groups the highly communicating tasks based on spectral graph partitioning. Then, the clustering and mapping stages allocate the most communicating tasks in the same or adjacent multi‐tasking cores. It also eliminates the interference between multiple applications by mapping them into different clusters of the NoC network. Simulations of have been conducted on different synthetic and real‐life applications using Gem5 simulator. The simulation results show considerable improvements for SpecMap in terms of communication cost, average network latency, energy consumption, throughput, and execution time as compared to the state‐of‐the‐art algorithms.

Implementation of Real-Time Space Target Detection and Tracking Algorithm for Space-Based Surveillance

Space-based target surveillance is important for aerospace safety. However, with the increasing complexity of the space environment, the stellar target and strong noise interference pose difficulties for space target detection. Simultaneously, it is hard to balance real-time processing with computational performance for the onboard processing platform owing to resource limitations. The heterogeneous multi-core architecture has corresponding processing capabilities, providing a hardware implementation platform with real-time and computational performance for space-based applications. This paper first developed a multi-stage joint detection and tracking model (MJDTM) for space targets in optical image sequences. This model combined an improved local contrast method and the Kalman filter to detect and track the potential targets and use differences in movement status to suppress the stellar targets. Then, a heterogeneous multi-core processing system based on a field-programmable gate array (FPGA) and digital signal processor (DSP) was established as the space-based image processing system. Finally, MJDTM was optimized and implemented on the above image processing system. The experiments conducted with simulated and actual image sequences examine the accuracy and efficiency of the MJDTM, which has a 95% detection probability while the false alarm rate is 10−4. According to the experimental results, the algorithm hardware implementation can detect targets in an image with 1024 × 1024 pixels in just 22.064 ms, which satisfies the real-time requirements of space-based surveillance.

The Diagnosability of the Generalized Cartesian Product of Networks

Motivated by two typical ways to construct multiprocessor systems, matching composition networks and cycle composition networks, we generalize the definition of the Cartesian product of networks and consider the classical diagnosability of the generalized Cartesian product of networks (GCPNs). In this paper, we determine the accurate value of the classical diagnosability of the generalized Cartesian product of networks (GCPNs) under the PMC model and the MM* model.

Detecting gene breakpoints in noisy genome sequences using position-annotated colored de-Bruijn graphs

BackgroundIdentifying the locations of gene breakpoints between species of different taxonomic groups can provide useful insights into the underlying evolutionary processes. Given the exact locations of their genes, the breakpoints can be computed without much effort. However, often, existing gene annotations are erroneous, or only nucleotide sequences are available. Especially in mitochondrial genomes, high variations in gene orders are usually accompanied by a high degree of sequence inconsistencies. This makes accurately locating breakpoints in mitogenomic nucleotide sequences a challenging task.ResultsThis contribution presents a novel method for detecting gene breakpoints in the nucleotide sequences of complete mitochondrial genomes, taking into account possible high substitution rates. The method is implemented in the software package DeBBI. DeBBI allows to analyze transposition- and inversion-based breakpoints independently and uses a parallel program design, allowing to make use of modern multi-processor systems. Extensive tests on synthetic data sets, covering a broad range of sequence dissimilarities and different numbers of introduced breakpoints, demonstrate DeBBI ’s ability to produce accurate results. Case studies using species of various taxonomic groups further show DeBBI ’s applicability to real-life data. While (some) multiple sequence alignment tools can also be used for the task at hand, we demonstrate that especially gene breaks between short, poorly conserved tRNA genes can be detected more frequently with the proposed approach.ConclusionThe proposed method constructs a position-annotated de-Bruijn graph of the input sequences. Using a heuristic algorithm, this graph is searched for particular structures, called bulges, which may be associated with the breakpoint locations. Despite the large size of these structures, the algorithm only requires a small number of graph traversal steps.

Joint optimization of mission abort and system structure considering dynamic tasks

Mission abort has recently attracted considerable attention to enhance the safety of critical systems during the primary mission (PM). Most of the existing research focuses on mission abort policies for systems performing a deterministic PM, i.e., operating for a fixed mission duration or completing a specified amount of work. However, in practice, systems are commonly required to perform dynamic tasks. This paper first makes advancements by jointly optimizing condition-based mission abort policies and system structure for the l-out-of-n: G warm standby system, where the dynamic arrival of tasks with a random amount of work is considered. In such systems, some components are initially in active mode, and the remaining warm standby components provide fault tolerance. Two types of mission success criteria are considered and corresponding mission abort policies are proposed based on different decision criteria. Mission reliability (MR) and system survivability (SS) are derived using recursive methods, considering the random switching of the active, idle, and warm standby modes under dynamic arrival of tasks. Mission abort policies and system structure are jointly optimized to balance MR and SS with the objective of minimizing the expected total cost. An example of a multiprocessor system is presented to illustrate the proposed model.

A fault-tolerant resource locking protocol for multiprocessor real-time systems

This paper presents the first fault-tolerant resource locking protocol for multiprocessor real-time systems. Resource locking protocols control access to shared resources in real-time systems. Most of the previous studies in resource locking protocols have focused on decreasing blocking time and resource conflicts. The use of such protocols in multiprocessor safety-critical real-time systems necessitates fault tolerance in the design of these systems. However, in research focused on multiprocessor real-time systems, fault tolerance has received low attention in resource allocation studies. In addition, many solutions proposed to improve the reliability in real-time scheduling ignored resource models in their task model. This paper proposes a novel fault-tolerant resource locking protocol, called FTPIA-NPCS, which considers transient faults in shared resources. FTPIA-NPCS proposes a checkpointing-based fault-tolerant mechanism to recover from errors caused by transient faults. In this mechanism, a checkpoint is taken from the tasks, before each resource allocation. In addition to providing fault tolerance, FTPIA-NPCS solves the problem of priority inversion in NPCS protocol for periodic tasks with hard deadlines. The simulation results demonstrate that FTPIA-NPCS tolerates at least one transient fault in resources for each execution of the periodic tasks with 15% blocking time overhead in comparison to its non-fault-tolerant configuration, called PIA-NPCS. Furthermore, the blocking time of higher-priority tasks is minimized in comparison to PIA-NPCS. An analytical evaluation of the protocol supports the simulation results.

Hyper‐heuristic method for processor allocation in parallel tasks scheduling

SummaryScheduling the tasks of parallel scientific applications is very important for efficient utilization of resources and reducing the overall execution time (makespan). Parallel applications typically include both data parallelism and task parallelism. It is known that the scheduling problem on multiprocessor systems problem is NP‐Hard even for applications involving pure task parallelism. The problem becomes more difficult when data parallelism is also taken into consideration. These problems usually considered in two steps, processor allocation and task scheduling, and various algorithms have been proposed. In this study, we introduce a genetic algorithm based hyper‐heuristic approach for the processor allocation problem. Experimental results indicate that the algorithm provides better performance compared to various greedy algorithms.

Three Processor Allocation Approaches towards EDF Scheduling for Performance Asymmetric Multiprocessors

With the rapid development of high-performance computing and parallel computing technology, by virtue of its cost-effectiveness, strong scalability, and easy programming, the multiprocessor system has gradually become the mainstream computing platform. Meanwhile, a growing number of researchers pay attention to the performance of multiprocessor systems, especially the task scheduling problem, which has an important impact on the system performance. Most of the current research works on task scheduling algorithms are based on the homogeneous computing environment. On the contrary, research works focusing on more complex performance asymmetric multiprocessor environments still remain rare. In this paper, we compare the effects of three earliest deadline first algorithms under different processor allocation strategies on performance asymmetric multiprocessors. We propose an efficient schedulability analysis for an allocation strategy that assigns high-priority tasks to the slowest idle processor. Experimental results show that the strategy of allocating processors with optimum speeds for high-priority tasks can schedule more task sets than the other two allocation strategies. The strategy that prioritizes the slowest processors for high-priority tasks has the smallest number of task migrations, and the strategy has the highest effective processor utilization.

A New Fractal Topologies Based on Hypercube Interconnection Network

A parallel processing system's most crucial part is a network interconnection that links its processors. The hypercube topology has exciting features, making it an excellent option for parallel processing applications. This paper presents two innovative configurations of interconnection networks based on fractal Sierpinski and a hypercube. These are the Sierpinski Triangle Topology (STT) and Sierpinski Carpet Topology (SCT). Compared to a hypercube, the Sierpinski Triangle topology (STT) noticed a significant decrease in the number of nodes and links as large networks grew. Hence, it considers a great way to reduce costs because it uses fewer nodes and links. The average distance is also shorter, which is better. Despite it has a smaller bisection width and a more degree than a hypercube by one. The Sierpinski Carpet Topology (SCT) has the advantage of having a higher bisection width than a hypercube. That is preferable because it places a lower restriction on the difficulty of parallel algorithms. In contrast, the drawback of this topology is that it has a diameter and average distance more than a hypercube.

Multiprocessor task scheduling using multi-objective hybrid genetic Algorithm in Fog–cloud computing

Multiprocessor task scheduling is an operation of processing more than two tasks simultaneously in the system. The Fog–cloud multiprocessor computing structures are the categories of exchanged collateral structures with great demand from its initiation. Like other networking systems, the existing fog–cloud system based on multiprocessor systems faces some challenges. Due to the availability of excess clients and various services, scheduling and energy consumption issues are challenging. The existing problems must be resolved with proper planning to reduce makespan and energy consumption. To obtain this, an optimal scheduling approach is required. The proposed approach presents a novel methodology called Hybrid Genetic Algorithm and Energy Conscious Scheduling for better scheduling tasks over the processors. Here Genetic Algorithm and Energy conscious scheduling model are integrated. When only a Genetic Algorithm is chosen for the task scheduling approach, it becomes computationally expensive. Energy consumption becomes a huge challenge as it does not cope with complexity, making it extremely difficult to schedule appropriate tasks. When choosing the proposed hybrid Genetic algorithm, these issues can be overcome by considering optimal solutions with minimized makespan and consumed energy. A Genetic Algorithm is used to generate three primary chromosomes using priority approaches. The allocated resources are optimized through the Energy Conscious Scheduling model, and the proposed method is implemented using MATLAB. The existing methods, including genetic algorithm, particle swarm optimization, gravitational search algorithm, ant colony optimization and round robin models, are compared with the proposed method, proven comparatively better than existing models.

The partial diagnosability of interconnection networks under the Hybrid PMC model

System level diagnosis is a primary method to identify the faulty elements in a multiprocessor system. Different from the traditional system level fault diagnosis models, the new fault diagnosis model, hybrid PMC model (short for HPMC model), is suitable to the circumstances that the processor and link faults occur simultaneously. Under the HPMC model, the q-edge restricted diagnosability of a system H, denoted by tqe(H), is the maximum number p such that H can correctly identify all the faulty elements containing p faulty processors and at most q faulty links. Similarly, the p-vertex restricted edge-diagnosability of a system H, denoted by spv(H), is the maximum number q such that H can correctly identify all the faulty elements containing q faulty links and at most p faulty processors. These two diagnosability are collectively referred to as partial diagnosability. We investigate and determine the q-edge restricted diagnosability of a system H under the HPMC model for q≥η(H), where η(H)=max⁡{|N(u)∩N(v)||uv∈E(H)}. In addition, we investigate the relationship between tqe(H) and spv(H) under the HPMC model, and show that under some conditions, spv(H)=q if tqe(H)=p. Applying our results, the two kinds of partial diagnosability of k-ary n-cubes, bijective connection networks and undirected Kautz graphs are established.

Fault tolerability analysis of folded crossed cubes based on g-component and g-good neighbor fault pattern

As data center networks and network-on-chip are developing rapidly, many graph invariants have been proposed to measure the reliability and fault tolerance of the network so that the multiprocessor systems can be ensured to operate efficiently and smoothly. The g-component connectivity of a graph G, denoted by cκg(G), is the minimum size of vertex cut such that G has at least g components. The g-good neighbor connectivity of a graph G, represented by κg(G), is the minimum size of vertex cut such that each vertex has at least g fault-free neighbors. Motivated by the conditional connectivities above, the g-component diagnosability (ctg(G)) and g-good neighbor diagnosability (tg(G)) of graph G have been suggested to evaluate the fault diagnostic capability of multiprocessor systems successively. In this paper, we determine the (g+1)-component connectivity of folded crossed cubes FCQn, i.e., cκg+1(FCQn)=ng−g22+g2+1 for 1≤g≤⌊n2⌋, and (g+1)-component diagnosability of FCQn under the PMC model and MM⁎ model, i.e., ctg+1(FCQn)=ng+n−g22−g2+1. Moreover, we establish the g-good neighbor connectivity of FCQn, i.e., κg(FCQn)=(n+1−g)2g for 0≤g≤n−5, and g-good neighbor diagnosability of FCQn under the PMC model and MM⁎ model, i.e., tg(FCQn)=(n+2−g)2g−1.

Intermittent Fault Diagnosis of Split-Star Networks and its Applications

With the rapid increase of the number of processors in multiprocessor systems and the fast expansion of interconnection networks, the reliability of interconnection network is facing severe challenges, where the fast recognition of fault processors is crucial. In practice, most of the processor failures are intermittent faults. In this article, we first determine the intermittent fault diagnosability <inline-formula><tex-math notation="LaTeX">$t_{I}^{PMC}(S_{n}^{2})$</tex-math></inline-formula> of <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula> -dimensional split-star network <inline-formula><tex-math notation="LaTeX">$S_{n}^{2}$</tex-math></inline-formula> under the PMC model. In addition, we propose a fast intermittent fault probabilistic diagnosis algorithm FIFPDPMC to identify the nodes with intermittent fault in the <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula> -dimensional split-star network <inline-formula><tex-math notation="LaTeX">$S_{n}^{2}$</tex-math></inline-formula> under the PMC model, and we calculated the time complexity of the algorithm FIFPDPMC. Then we implement the algorithm FIFPDPMC in the IoT-based wireless sensor network (IoTWSN) and a randomly generated network (RGN) under different number of nodes with intermittent fault, and we evaluate the performance and efficiency of the algorithm FIFPDPMC in terms of accuracy, precision, recall (TPR), F1, G-mean, FPR, TNR and FNR. Experimental results show that, as the number of stages of executing the algorithm FIFPDPMC increases, the number of nodes with intermittent fault being diagnosed by the algorithm FIFPDPMC increases, which implies that the algorithm FIFPDPMC has good performance and efficiency in both IoTWSN and RGN.

Simulation-based fault-tolerant multiprocessors system

System reliability is an important issue in designing modern multiprocessor systems. This paper proposes a fault-tolerant, scalable, multiprocessor system architecture that adopts a pipeline scheme. To verify the performance of the proposed system, the SimEvent/Stateflow tool of the MATLAB program was used to simulate the system. The proposed system uses twelve processors (P), connected in a linear array, to build a ten-stage system with two backup processors (BP). However, the system can be expanded by adding more processors to increase pipeline stages and performance, and more backup processors to increase system reliability. The system can automatically reorganize itself in the event of a failure of one or two processors and execution continues without interruption. Each processor communicates with its neighboring processors through input/output (I/O) ports which are used as bypass links between the processors. In the event of a processor failure, the function of the faulty processor is assigned to the next processor that is free from faults. The fast Fourier transform (FFT) algorithm is implemented on the simulated circuit to evaluate the performance of the proposed system. The results showed that the system can continue to execute even if one or two processors fail without a noticeable decrease in performance.

The Tiny-Tasks Granularity Trade-Off: Balancing Overhead Versus Performance in Parallel Systems

Models of parallel processing systems typically assume that one has <inline-formula><tex-math notation="LaTeX">$l$</tex-math></inline-formula> workers and jobs are split into an equal number of <inline-formula><tex-math notation="LaTeX">$k=l$</tex-math></inline-formula> tasks. Splitting jobs into <inline-formula><tex-math notation="LaTeX">$k &gt; l$</tex-math></inline-formula> smaller tasks, i.e. using “tiny tasks”, can yield performance and stability improvements because it reduces the variance in the amount of work assigned to each worker, but as <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula> increases, the overhead involved in scheduling and managing the tasks begins to overtake the performance benefit. We perform extensive experiments on the effects of task granularity on an Apache Spark cluster, and based on these, develop a four-parameter model for task and job overhead that, in simulation, produces sojourn time distributions that match those of the real system. We also present analytical results which illustrate how using tiny tasks improves the stability region of split-merge systems, and analytical bounds on the sojourn and waiting time distributions of both split-merge and single-queue fork-join systems with tiny tasks. Finally we combine the overhead model with the analytical models to produce an analytical approximation to the sojourn and waiting time distributions of systems with tiny tasks which include overhead. We also perform analogous tiny-tasks experiments on a hybrid multi-processor shared memory system based on MPI and OpenMP which has no load-balancing between nodes. Though no longer strict analytical bounds, our analytical approximations with overhead match both the Spark and MPI/OpenMP experimental results very well.

Fault tolerance of composite graph based on disc-ring and folded hypercube

Multiprocessor systems commonly take interconnection network (simply graph) as the underlying topological structure. The performance of multiprocessor systems is greatly influenced by their network topologies. The connectivity is a classical metric to evaluate the fault tolerance of multiprocessor systems. In this work, we propose a composite graph based on disc-ring and folded hypercube, DFQ(m,d,n) (simply, DFQn). Compared with the compound graph DQcube (DQn), DFQn shows better performance in terms of many metrics such as diameter, connectivity and layout cost. In detail, we first show that the connectivity, edge-connectivity and tightly super connectivity are n+2 uniformly. Furthermore, we show that h-extra connectivity of DFQn is κh(DFQn)=(h+1)(n+2)−2h−(h2).

The Cyclic Diagnosability Of Hypercubes Under The PMC Model And The MM* Model

Abstract Motivated by a multitude of practical applications, many distinct vulnerability parameters of multiprocessor systems have been explored. Traditional connectivity and diagnosability are undoubtedly the most well investigated of these metrics, but often fail to capture the most subtle differences of a multiprocessor system. Subsequently, it is necessary to take into account the minimum degree of components, the size of components or the number of components. However, the structure of the components is ignored in these circumstances. In this work, we propose a novel diagnostic strategy based on cyclic connectivity, namely the cyclic diagnosability. The cyclic diagnosability, denoted by $ct(G)$, is the maximum size of the faulty vertex set $F$ of $G$ such that the self-diagnosable system $G$ can identify all the vertices in $F$ under the condition that at least two connected components of $G-F$ contain a cycle. Furthermore, we investigate the cyclic diagnosability of hypercube $Q_{n}$ under the PMC model and the MM* model, and show that $ct(Q_{n})=5n-10$ for $n\geq 7$.

Reliability Evaluation Of Multiprocessor System Based On The Balanced Complete Multipartite Graphs

Abstract Reliability evaluation of multiprocessor systems is of significant importance in the design and maintenance of multiprocessor systems. Based on edge-connectivity, more refined quantitative indicators for the reliability of multiprocessor systems have been introduced. The extra edge-connectivity and the component edge-connectivity, as two important parameters to evaluate the robustness of multiprocessor systems, are explored extensively. In this paper, we determine the $h$-extra edge-connectivity and the $(g+1)$-component edge-connectivity of the balanced complete $t$-partite graph $K_{r}^{t}$ for $t, r\geq 2$, where $1\leq h \leq \lfloor tr/2 \rfloor$ and $2\leq g \leq tr-1$.

Online fault tolerant energy-aware algorithm for CubeSats

Energy and reliability constraints play an important role in performances of embedded multiprocessor systems. This paper proposes an online fault tolerant energy-aware scheduling algorithm called OneOffEnergy. It is designed for energy-constrained applications, such as CubeSats, with aim to make these small satellites more robust and to reduce energy consumption. We propose to take advantage of multiprocessor architecture and put together all CubeSat processors on one board. This multiprocessor system makes use of our devised algorithm, which schedules all tasks aboard a CubeSat, detects faults and takes appropriate measures in order to deliver correct results subject to limited energy resources.OneOffEnergy operates in two processor modes (Run and Standby) to save energy and considers three system modes (normal, safe and critical) related to the task priorities depending on the current energy stored in the battery. In order to show the wide algorithm usability, OneOffEnergy was not only evaluated for CubeSats but also in the context of another energy-constrained application.It is shown that the implementation of OneOffEnergy aboard a CubeSat reduces energy consumption. The results demonstrate that putting processors in Standby mode brings energy savings and OneOffEnergy exhibits better performances in terms of the system operation under energy constraints when compared to simpler algorithms. Finally, it was found that OneOffEnergy also performs well in a harsh environment.

Efficient approximation algorithms for scheduling moldable tasks

Moldable tasks allow schedulers to determine the number of processors assigned to each task, thus enabling efficient use of large-scale parallel processing systems. We consider the problem of scheduling independent moldable tasks on processors and propose a new perspective of the existing speedup models: as the number p of processors assigned to a task increases, the speedup is linear if p is small and becomes sublinear after p exceeds a threshold. Based on this, we propose an efficient approximation algorithm to minimize the makespan. As a by-product, we also propose an approximation algorithm to maximize the sum of values of tasks completed by a deadline; this scheduling objective is considered for moldable tasks for the first time while similar works have been done for other types of parallel tasks.