Performance Modeling based on Multidimensional Surface Learning for Performance Predictions of Parallel Applications in Non-Dedicated Environments

Modeling the performance behavior of parallel applications to predict the execution times of the applications for larger problem sizes and number of processors has been an active area of research for several years. The existing curve fitting strategies for performance modeling utilize data from experiments that are conducted under uniform loading conditions. Hence the accuracy of these models degrade when the load conditions on the machines and network change. In this paper, we analyze a curve fitting model that attempts to predict execution times for any load conditions that may exist on the systems during application execution. Based on the experiments conducted with the model for a parallel eigenvalue problem, we propose a multi-dimensional curve-fitting model based on rational polynomials for performance predictions of parallel applications in non-dedicated environments. We used the rational polynomial based model to predict execution times for 2 other parallel applications on systems with large load dynamics. In all the cases, the model gave good predictions of execution times with average percentage prediction errors of less than 20%

Performance modeling and architecture exploration of network processors

This paper proposes a Petri net model for a commercial network processor (Intel iXP architecture) which is a multithreaded multiprocessor architecture. We consider and model three different applications viz., IPv4 forwarding, network address translation, and IP security running on IXP 2400/2850. A salient feature of the Petri net model is its ability to model the application, architecture and their interaction in great detail. The model is validated using the Intel proprietary tool (SDK 3.51 for IXP architecture) over a range of configurations. We conduct a detailed performance evaluation, identify the bottleneck resource, and propose a few architectural extensions and evaluate them in detail.

Petri net based performance modeling for effective DVFS for multithreaded programs

Dynamic Voltage and Frequency Scaling (DVFS) is a very effective tool for designing trade-offs between energy and performance. In this paper, we use a formal Petri net based program performance model that directly captures both the application and system properties, to find energy efficient DVFS settings for CMP systems, that satisfy a given performance constraint, for SPMD multithreaded programs. Experimental evaluation shows that we achieve significant energy savings, while meeting the performance constraints.

Semi-gas kinetics model for performance modeling of flowing chemical oxygen-iodine lasers (COIL)

A semi-gas kinetics (SGK) model for performance analyses of flowing chemical oxygen-iodine laser (COIL) is presented. In this model, the oxygen-iodine reaction gas flow is treated as a continuous medium, and the effect of thermal motions of particles of different laser energy levels on the performances of the COIL is included and the velocity distribution function equations are solved by using the double-parameter perturbational method. For a premixed flow, effects of different chemical reaction systems, different gain saturation models and temperature, pressure, yield of excited oxygen, iodine concentration and frequency-shift on the performances of the COIL are computed, and the calculated output power agrees well with the experimental data. The results indicate that the power extraction of the SGK model considering 21 reactions is close to those when only the reversible pumping reaction is considered, while different gain saturation models and adjustable parameters greatly affect the output power, the optimal threshold gain range, and the length of power extraction.

Analysis of the structural characteristics of an intermediate rail vehicle and their effect on vehicle crash performance

In the current paper, the authors present an analysis of the structural characteristics of an intermediate rail vehicle and their effects on crash performance of the vehicle. Theirs is a simulation based analysis involving four stages. First, the crashworthiness of the vehicle is assessed by simulating an impact of the vehicle with a rigid wall. Second, the structural characteristics of the vehicle are analysed based on the structural behaviour during this impact and then the structure is modified. Third, the modified vehicle is tested again in the same impact scenario with a rigid wall. Finally, the modified vehicle is subjected to a modelled head-on impact which mirrors the real-life impact interface between two intermediate vehicles in a train impact. The emphasis of the current study is on the structural characteristics of the intermediate vehicle and the differences compared to an impact of a leading vehicle. The study shows that, similar to a leading vehicle, bending, or jackknifing is a main form of failure in this conventionally designed intermediate vehicle. It has also been found that the location of the door openings creates a major difference in the behaviour of an intermediate vehicle. It causes instability of the vehicle in the door area and leads to high stresses at the joint of the end beam with the solebar and shear stresses at the joint of the inner pillar with the cantrail. Apart from this, the shapes of the vehicle ends and impact interfaces are also different and have an effect on the crash performance of the vehicles. The simulation results allow the identification of the structural characteristics and show the effectiveness of relevant modifications. The conclusions have general relevance for the crashworthiness of rail vehicle design

Multi-cluster computing interconnection network performance modeling and analysis

The overall performance of a distributed system is often depends on the effectiveness of its interconnection network. Thus, the study of the communication networks for distributed systems is very important, which is the focus of this paper. In particular, we address the problem of fat-tree based interconnection networks performance modeling for multi-user heterogeneous multi-cluster computing systems. To this end, we present an analytical model and validate the model through comprehensive simulation. The results of the simulation demonstrated that the proposed model exhibits a good degree of accuracy for various system organizations and under different working conditions.

Analytical performance modeling of the enterprise grid computing

This paper addresses the problem of performance modeling of large-scale heterogeneous distributed systems with emphases on enterprise grid computing systems. To this end, we present an analytical model that can be employed to explore the effectiveness of different design approaches so that one can have an intelligent choice during design and evaluation a cost-effective large-scale heterogeneous distributed computing system. The model is validated through comprehensive simulation.

Performance modeling and analysis of heterogeneous meta-computing systems interconnection networks

The overall performance of a distributed system often depends on the effectiveness of its interconnection network. Thus, the study of the communication networks for distributed systems is very important, which is the focus of this paper. In particular, we address the problem of interconnection networks performance modeling for heterogeneous meta-computing systems. We consider the meta-computing system as a typical multi-cluster system. Since the heterogeneity is becoming common in such systems, we take into account network as well as cluster size heterogeneity to propose the model. To this end, we present an analytical network model and validate the model through comprehensive simulation. The results of the simulation demonstrated that the proposed model exhibits a good degree of accuracy for various system organizations and under different working conditions.

Multi-cluster computing interconnection network performance modeling and analysis

The overall performance of a distributed system often depends on the effectiveness of its interconnection network. Thus, the study of the communication networks for distributed systems–which is the focus of this paper–is very important. In particular, we address the problem of fat-tree based interconnection networks performance modeling for multi-user heterogeneous multi-cluster computing systems. To this end, we present an analytical model and validate the model through comprehensive simulation. The results of the simulation demonstrate that the proposed model exhibits a good degree of accuracy for various system organizations and under different working conditions. On the basis of the validated model, we propose an adaptive assignment function based on the existing heterogeneity of the system to minimize multi-user environment overhead.

Managerial share ownership and operating performance : do independent and executive directors have different incentives?

We investigate the relationship between managerial share ownership (MSO) and earnings as a measure of operating performance in Australia. To mitigate potential earnings management, we also use discretionary accrual adjusted earnings as an alternative measure of performance. We document a negative relation between MSO and performance followed by a positive relation. We suggest that these unique results are an artefact of certain Australian institutional features and imply that the ownership–performance relation is context-specific, with the wider corporate governance systems influencing the theorised incentive effects. We also posit that executive directors and independent directors have different ownership–performance incentives. Our results are consistent with this proposition and suggest that independent directors may be immune to the theorised incentive alignment or entrenchment effects associated with share ownership.

Performance Modeling Of Reconfigurable Distributed Systems Based On The Opensparc Fpga Board And The Sirc Communication Framewor

This thesis explores system performance for reconfigurable distributed systems and provides an analytical model for determining throughput of theoretical systems based on the OpenSPARC FPGA Board and the SIRC Communication Framework. This model was developed by studying a small set of variables that together determine a system¿s throughput. The importance of this model is in assisting system designers to make decisions as to whether or not to commit to designing a reconfigurable distributed system based on the estimated performance and hardware costs. Because custom hardware design and distributed system design are both time consuming and costly, it is important for designers to make decisions regarding system feasibility early in the development cycle. Based on experimental data the model presented in this paper shows a close fit with less than 10% experimental error on average. The model is limited to a certain range of problems, but it can still be used given those limitations and also provides a foundation for further development of modeling reconfigurable distributed systems.