Min-You Wu

Performance-effective and low-complexity task scheduling for heterogeneous computing

Efficient application scheduling is critical for achieving high performance in heterogeneous computing environments. The application scheduling problem has been shown to be NP-complete in general cases as well as in several restricted cases. Because of its key importance, this problem has been extensively studied and various algorithms have been proposed in the literature which are mainly for systems with homogeneous processors. Although there are a few algorithms in the literature for heterogeneous processors, they usually require significantly high scheduling costs and they may not deliver good quality schedules with lower costs. In this paper, we present two novel scheduling algorithms for a bounded number of heterogeneous processors with an objective to simultaneously meet high performance and fast scheduling time, which are called the Heterogeneous Earliest-Finish-Time (HEFT) algorithm and the Critical-Path-on-a-Processor (CPOP) algorithm. The HEFT algorithm selects the task with the highest upward rank value at each step and assigns the selected task to the processor, which minimizes its earliest finish time with an insertion-based approach. On the other hand, the CPOP algorithm uses the summation of upward and downward rank values for prioritizing tasks. Another difference is in the processor selection phase, which schedules the critical tasks onto the processor that minimizes the total execution time of the critical tasks. In order to provide a robust and unbiased comparison with the related work, a parametric graph generator was designed to generate weighted directed acyclic graphs with various characteristics. The comparison study, based on both randomly generated graphs and the graphs of some real applications, shows that our scheduling algorithms significantly surpass previous approaches in terms of both quality and cost of schedules, which are mainly presented with schedule length ratio, speedup, frequency of best results, and average scheduling time metrics.

Task scheduling algorithms for heterogeneous processors

Scheduling computation tasks on processors is the key issue for high-performance computing. Although a large number of scheduling heuristics have been presented in the literature, most of them target only homogeneous resources. The existing algorithms for heterogeneous domains are not generally efficient because of their high complexity and/or the quality of the results. We present two low-complexity efficient heuristics, the Heterogeneous Earliest-Finish-Time (HEFT) algorithm and the Critical-Path-on-a-Processor (CPOP) algorithm for scheduling directed acyclic weighted task graphs (DAGs) on a bounded number of heterogeneous processors. We compared the performances of these algorithms against three previously proposed heuristics. The comparison study showed that our algorithms outperform previous approaches in terms of performance (schedule length ratio and speedup) and cost (time-complexity).

CDC : Compressive Data Collection for Wireless Sensor Networks

Data collection is a crucial operation in wireless sensor networks. The design of data collection schemes is challenging due to the limited energy supply and the hot spot problem. Leveraging empirical observations that sensory data possess strong spatiotemporal compressibility, this paper proposes a novel compressive data collection scheme for wireless sensor networks. We adopt a power-law decaying data model verified by real data sets and then propose a random projection-based estimation algorithm for this data model. Our scheme requires fewer compressed measurements, thus greatly reduces the energy consumption. It allows simple routing strategy without much computation and control overheads, which leads to strong robustness in practical applications. Analytically, we prove that it achieves the optimal estimation error bound. Evaluations on real data sets (from the GreenOrbs, IntelLab and NBDC-CTD projects) show that compared with existing approaches, this new scheme prolongs the network lifetime by 1.5X to 2X for estimation error 5-20 percent.

Segmented min-min: a static mapping algorithm for meta-tasks on heterogeneous computing systems

The min-min algorithm is a simple algorithm. It runs fast and delivers good performance. However, the min-min algorithm schedules small tasks first, resulting in some load imbalance. We present an algorithm which improves the min-min algorithm by scheduling large tasks first. The new algorithm, segmented min-min, balances the load well and demonstrates even better performance in both makespan and running time.

Performance Evaluation of SUVnet With Real-Time Traffic Data

In this paper, we present the characteristics of a vehicular ad hoc network (VANET), which is the Shanghai urban vehicular network (SUVnet). We construct a mobility model using the GPS data collected from more than 4000 taxis in Shanghai. The model is both realistic and large scale. Based on this model, network topology and connectivity of SUVnet are studied. Because of the sparse distribution and dynamic topology of SUVnet, simply utilizing the conventional mobile ad hoc network routing protocols in SUVnet may not achieve a satisfactory performance. Therefore, we apply the delay-tolerant network model to SUVnet and evaluate the epidemic routing protocols. We propose a new protocol, which is the distance aware epidemic routing (DAER), to improve the bundle delivery ratio. Results show that DAER performs well for a VANET. This paper provides a basis in studying a realistic urban VANET.

Protocols and architectures for channel assignment in wireless mesh networks

The use of multiple channels can substantially improve the performance of wireless mesh networks. Considering that the IEEE PHY specification permits the simultaneous operation of three non-overlapping channels in the 2.4GHz band and 12 non-overlapping channels in the 5GHz band, a major challenge in wireless mesh networks is how to efficiently assign these available channels in order to optimize the network performance. We survey and classify the current techniques proposed to solve this problem in both single-radio and multi-radio wireless mesh networks. This paper also discusses the issues in the design of multi-channel protocols and architectures.

Performance Evaluation of Vehicle-Based Mobile Sensor Networks for Traffic Monitoring

Vehicle-based sensors can be used for traffic monitoring. These sensors are usually set with long sampling intervals to save communication costs and to avoid network congestion. In this paper, we are interested in understanding the traffic-monitoring performance that we can expect from such vehicle-based mobile sensor networks, despite the incomplete information provided. This is a fundamental problem to be addressed. A performance evaluation has been carried out in Shanghai, China, by utilizing the vehicle-based sensors installed in about 4000 taxies. Two types of traffic status-estimation algorithms, i.e., the link-based and the vehicle-based, are introduced and analyzed. The results show that estimations of the traffic status based on these imperfect data are reasonably accurate. Therefore, the feasibility of such an application is demonstrated.

On the Capacity of Multi-Channel Wireless Networks Using Directional Antennas

The capacity of wireless ad hoc networks is affected by two key factors: the interference among concurrent transmissions and the number of simultaneous transmissions on a single interface. Recent studies found that using multiple channels can separate concurrent transmissions and greatly improve network throughput. However, those studies only consider that wireless nodes are equipped with only omnidirectional antennas, which cause high collisions. On the other hand, some researchers found that directional antennas bring more benefits such as reduced interference and increased spatial reuse compared with omnidirectional antennas. But, they only focused on a single-channel network which only allows finite concurrent transmissions. Thus, combining the two technologies of multiple channels and directional antennas together potentially brings more benefits. In this paper, we propose a multi-channel network architecture (called MC-MDA) that equips each wireless node with multiple directional antennas. We derive the capacity bounds of MC-MDA networks under arbitrary and random placements. We will show that deploying directional antennas to multi-channel networks can greatly improve the network capacity due to increased network connectivity and reduced interference. We have also found that even a multi-channel network with a single directional antenna only at each node can give a significant improvement on the throughput capacity. Besides, using multiple channels mitigates interference caused by directional antennas. MC-MDA networks integrate benefits from multi-channel and directional antennas and thus have significant performance improvement.

Compiling Fortran 90D/HPF for distributed memory MIMD computers

Distributed memory multiprocessors are increasingly being used to provide high performance for advanced calculations with scientific applications. Distributed memory machines offer significant advantages over their shared memory counterparts in terms of cost and scalability, though it is widely accepted that they are difficult to program given the current status of software technology. Currently, distributed memory machines are programmed using a node language and a message passing library. This process is tedious and error prone because the user must perform the task of data distribution and communication for non-local data access. This thesis describes an advanced compiler that can generate efficient parallel programs when the source programming language naturally represents an applications parallelism. Fortran 90D/HPF described in this thesis is such a language. Using Fortran 90D/HPF, parallelism is represented with parallel constructs, such as array operations, where statements, forall statements, and intrinsic functions. The language provides directives for data distribution. Fortran 90D/HPF gives the programmer powerful tools to express a problem with natural data parallelism. To validate this hypothesis, a prototype of Fortran 90D/HPF was implemented. The compiler is organized around several major units: language parsing, partitioning data and computation, detecting communication and generating code. The compiler recognizes the presence of communication patterns in the computations in order to generate appropriate communication calls. Specifically, this involves a number of tests on the relationships among subscripts of various arrays in a statement. The compiler includes a specially designed algorithm to detect communications and to generate appropriate collective communication calls to execute array assignments and forall statements. The Fortran 90D/HPF compiler performs several types of communication and computation optimizations to improve the performance of the generated code. Empirical measurements show that the performance of the output of the Fortran 90D/HPF compiler is comparable to that of corresponding hand-written codes on several systems. We hope that this thesis assists in the widespread adoption of parallel computing technology and leads to a more attractive and powerful software development environment to support application parallelism that many users need.

Data loss and reconstruction in sensor networks

Reconstructing the environment in cyber space by sensory data is a fundamental operation for understanding the physical world in depth. A lot of basic scientific work (e.g., nature discovery, organic evolution) heavily relies on the accuracy of environment reconstruction. However, data loss in wireless sensor networks is common and has its special patterns due to noise, collision, unreliable link, and unexpected damage, which greatly reduces the accuracy of reconstruction. Existing interpolation methods do not consider these patterns and thus fail to provide a satisfactory accuracy when missing data become large. To address this problem, this paper proposes a novel approach based on compressive sensing to reconstruct the massive missing data. Firstly, we analyze the real sensory data from Intel Indoor, GreenOrbs, and Ocean Sense projects. They all exhibit the features of spatial correlation, temporal stability and low-rank structure. Motivated by these observations, we then develop an environmental space time improved compressive sensing (ESTICS) algorithm to optimize the missing data estimation. Finally, the extensive experiments with real-world sensory data shows that the proposed approach significantly outperforms existing solutions in terms of reconstruction accuracy. Typically, ESTICS can successfully reconstruct the environment with less than 20% error in face of 90% missing data.