Optimizing latency and throughput of application workflows on clusters

Scheduling, in many application domains, involves optimization of multiple performance metrics. For example, application workflows with real-time constraints have strict throughput requirements and also desire a low latency or response time. In this paper, we present a novel algorithm for the scheduling of workflows that act on a stream of input data. Our algorithm focuses on the two performance metrics, latency and throughput, and minimizes the latency of workflows while satisfying strict throughput requirements. We also describe steps to use the above approach to solve the problem of meeting latency requirements while maximizing throughput. We leverage pipelined, task and data parallelism in a coordinated manner to meet these objectives and investigate the benefit of task duplication in alleviating communication overheads in the pipelined schedule for different workflow characteristics. The proposed algorithm is designed for a realistic bounded multi-port communication model, where each processor can simultaneously communicate with at most k distinct processors. Experimental evaluation using synthetic benchmarks as well as those derived from real applications shows that our algorithm consistently produces lower latency schedules that meet throughput requirements, even when previously proposed schemes fail.     

An Integrated Approach to Locality-Conscious Processor Allocation and Scheduling of Mixed-Parallel Applications

Complex parallel applications can often be modeled as directed acyclic graphs of coarse-grained application tasks with dependences. These applications exhibit both task and data parallelism, and combining these two (also called mixed parallelism) has been shown to be an effective model for their execution. In this paper, we present an algorithm to compute the appropriate mix of task and data parallelism required to minimize the parallel completion time (makespan) of these applications. In other words, our algorithm determines the set of tasks that should be run concurrently and the number of processors to be allocated to each task. The processor allocation and scheduling decisions are made in an integrated manner and are based on several factors such as the structure of the task graph, the runtime estimates and scalability characteristics of the tasks, and the intertask data communication volumes. A locality-conscious scheduling strategy is used to improve intertask data reuse. Evaluation through simulations and actual executions of task graphs derived from real applications and synthetic graphs shows that our algorithm consistently generates schedules with a lower makespan as compared to Critical Path Reduction (CPR) and Critical Path and Allocation (CPA), two previously proposed scheduling algorithms. Our algorithm also produces schedules that have a lower makespan than pure task- and data-parallel schedules. For task graphs with known optimal schedules or lower bounds on the makespan, our algorithm generates schedules that are closer to the optima than other scheduling approaches.     

An analytic hierarchy process and two-sided matching based decision support system for military personnel assignment

Assignment of military personnel to positions is very demanding, primarily a manual process performed by detailers. Detailers try to satisfy needs and preferences of commands and personnel. In this paper, an analytic hierarchy process (AHP) and two sided matching based Decision Support System is proposed to assist detailers. The DSS is programmed to generate positions’ preferences from position requirement profiles and personnel competence profiles by using analytic hierarchy process and matches personnel to positions by using two-sided matching. The use of the proposed DSS is demonstrated with an example. Also, the effects of preference list length on two-sided matching are examined.     

Electrical and photovoltaic properties of an organic-inorganic heterojunction based on a BODIPY dye

An organic-inorganic heterojunction based on a BODIPY dyes has been produced by forming dye thin film on n-Si. The electrical parameters of the structure have been investigated by current-voltage (I-V) and capacitance-voltage (C-V) measurements. The ideality factor, the barrier height and the series resistance values of the diode have been calculated as 2.43, 0.84 eV, and about 1.3 kΩ, respectively. The diode behaves as a non-ideal diode because of the series resistance and interface layer. The barrier height value obtained from I-V measurement has been compared with one from C-V measurement. Moreover, it has been seen that the diode is highly sensitive to the light and the reverse bias current increases about 1 × 10⁴ times at −1 V under 100 mW/cm² and AM1.5 illumination condition. The short photocurrent density (J_sc) and the open circuit voltage (V_oc), the fill factor (FF) and power conversion efficiency (η) have been determined as 3.78 mA/cm², 327 mV, 0.28 and 0.48 %, respectively.     

Effect of an organic compound (Methyl Red) interfacial layer on the calculation of characteristic parameters of an Al/Methyl Red/p-Si sandwich Schottky barrier diode

An Al/Methyl Red/p-Si sandwich Schottky barrier diode (SBD) has been fabricated by adding a solution of the organic compound Methyl Red in chloroform onto a p-Si substrate, and then evaporating the solvent. Current-voltage (I-V) measurements of the Al/Methyl Red/p-Si sandwich SBD have been carried out at room temperature and in the dark. The Al/Methyl Red/p-Si sandwich SBD demonstrated rectifying behavior. Barrier height (BH) and ideality factor values of 0.855 eV and 1.19, respectively, for this device have been determined from the forward-bias I-V characteristics. The Al/Methyl Red/p-Si sandwich SBD showed non-ideal I-V behavior with the value of ideality factor greater than unity. The energy distribution of the interface state density determined from I-V characteristics increases exponentially with bias from 3.68 × 10¹² cm^− 2 eV^− 1 at (0.81 − E_v) eV to 9.99 × 10¹³ cm^− 2 eV^− 1 at (0.69 − E_v) eV.     

Discrete-time point processes in urban traffic queue estimation

This research was motivated by the belief that it is possible to develop improved algorithms for the computer control of urban traffic. Previous research suggested that the computer software, and especially the filtering and prediction algorithms, is the limiting factor in computerized traffic control. Since the modern approach to filtering and prediction begins with the development of models for the generation of the data and since these models are also useful in the control problem, this paper deals with the modeling of traffic queues and filtering and prediction. It is shown that the data received from vehicle detectors is a discrete-time point process. The formation and dispersion of queues at a traffic signal is then modeled by a discrete-time time-varying Markov chain which is related to the observation point process. Three such models of increasing complexity are given. Recent results in the theory of point-process filtering and prediction are then used to derive the nonlinear minimum error variance filters/predictors corresponding to these models. It is then shown that these optimal estimators are computationally feasible in a micro-processor. All three algorithms were tested against the UTCS-1 traffic simulator and, in one case, against an algorithm in current use called ASCOT. Some results of these tests are shown. They indicate good performance in every case and better performance than ASCOT in the comparable case.     

Large-scale biomedical image analysis in grid environments

This paper presents the application of a component-based Grid middleware system for processing extremely large images obtained from digital microscopy devices. We have developed parallel, out-of-core techniques for different classes of data processing operations employed on images from confocal microscopy scanners. These techniques are combined into a data preprocessing and analysis pipeline using the component-based middleware system. The experimental results show that: 1) our implementation achieves good performance and can handle very large datasets on high-performance Grid nodes, consisting of computation and/or storage clusters and 2) it can take advantage of Grid nodes connected over high-bandwidth wide-area networks by combining task and data parallelism.     

False aneurysms in carotid arteries of cattle and water buffalo during shechita and halal slaughter

It has previously been shown that the cattle brain is supplied with blood via a basi-occipital plexus, in addition to branches from the carotid and basilar arteries. In addition it has been shown during conventional stunning and slaughter that the carotid arteries in cattle can develop false aneurysms at their severed ends and this can curtail exsanguination. This investigation examined whether false aneurysms can occur during religious slaughter, and during bleeding following electrical stunning that simultaneously induced a cardiac arrest. The prevalence of large (>3 cm outer diameter) false aneurysms in cattle carotid arteries was 10% for both shechita and halal slaughter. The prevalence of animals with bilateral false aneurysms (at least 2 cm in one artery and at least 3 cm diameter in the opposite artery) was 7% and 8% for shechita and halal slaughter, respectively. No false aneurysms occurred during bleeding in cattle that were electrically stunned and simultaneously developed a cardiac arrest. The combination of false aneurysms and collateral routes to the brain present a risk of sustained consciousness during religious slaughter in cattle.