The Experts below are selected from a list of 801561 Experts worldwide ranked by ideXlab platform
Christian Pérez - One of the best experts on this subject based on the ideXlab platform.
-
A reconfigurable Component Model for HPC
2015 18th International ACM SIGSOFT Symposium on Component-Based Software Engineering (CBSE), 2015Co-Authors: Vincent Lanore, Christian PérezAbstract:High-performance applications whose structure changes dynamically during execution are extremely complex to develop, maintain and adapt to new hardware. Such applications would greatly benefit from easy reuse and separation of concerns which are typical advantages of Component Models. Unfortunately, no existing Component Model is both HPC-ready (in terms of scalability and overhead) and able to easily handle dynamic reconfiguration. We aim at addressing performance, scalability and programmability by separating locking and synchronization concerns from reconfiguration code. To this end, we propose directMOD, a Component Model which provides on one hand a flexible mechanism to lock subassemblies with a very small overhead and high scalability, and on the other hand a set of well-defined mechanisms to easily plug various independently-written reconfiguration Components to lockable subassemblies. We evaluate both the Model itself and a C++/MPI implementation called directL2C.
-
CBSE - A Reconfigurable Component Model for HPC
Proceedings of the 18th International ACM SIGSOFT Symposium on Component-Based Software Engineering, 2015Co-Authors: Vincent Lanore, Christian PérezAbstract:High-performance applications whose structure changes dynamically during execution are extremely complex to develop, maintain and adapt to new hardware. Such applications would greatly benefit from easy reuse and separation of concerns which are typical advantages of Component Models. Unfortunately, no existing Component Model is both HPC-ready (in terms of scalability and overhead) and able to easily handle dynamic reconfiguration. We aim at addressing performance, scalability and programmability by separating locking and synchronization concerns from reconfiguration code. To this end, we propose directMOD, a Component Model which provides on one hand a flexible mechanism to lock subassemblies with a very small overhead and high scalability, and on the other hand a set of well-defined mechanisms to easily plug various independently-written reconfiguration Components to lockable subassemblies. We evaluate both the Model itself and a C++/MPI implementation called directL2C.
-
A Low Level Component Model Enabling Performance Portability of HPC Applications
2012Co-Authors: Julien Bigot, Christian Pérez, Zhengxiong Hou, Vincent PichonAbstract:Scientific applications are increasingly getting complex, e.g. to improve their accuracy by taking into account more phenomena. Meanwhile, computing infrastructures are continuing their fast evolution. Thus, software engineering is becoming a major issue to achieve easiness of development, portability, maintenance, while achieving high performance. Software Component Model is a promising approach, which enables to manipulate the software architecture of an application. However, existing Models do not provide enough support for performance portability. This paper proposes a low level Component Model (L2 C) that supports directly native connectors for typical scenarios of high performance computing, such as MPI, shared memory and method invocation. We walk through a typical example of stencil compu tation, i.e. 2-D Jacobi computation with domain decomposition. The experimental results show that L2 C can achieve the same p erformance as native implementations, while gaining benefits such as performance portability on the basis of the software com ponent Model.
-
A Low Level Component Model enabling Resource Specialization of HPC Applications
2012Co-Authors: Julien Bigot, Christian Pérez, Vincent PichonAbstract:Scientific applications are still getting more complex, e.g. to improve their accuracy by taking into account more phenomena. Moreover, computing infrastructures are continuing their fast evolution. Therefore, software engineering is becoming a major issue to achieve easiness of development, portability, simple maintenance, while achieving high performance. Software Component Model is a promising approach, which enables to manipulate the software architecture of an application. However, existing Models do not capture enough resource specificities. This paper proposes a low level Component Model (L2C) that supports directly native connectors such as MPI, shared memory and method invocation. L2C is intended to be used as a back end by a ''compiler'' (such as HLCM) to generate an application assembly specific to a given machine. This paper shows on a typical domain decomposition use case that \llc can achieve the same performance as native implementations, while gaining benefits such as enabling resource specialization capabilities.
-
A software Component Model with spatial and temporal compositions for Grid infrastructures
2008Co-Authors: Hinde Lilia Bouziane, Christian Pérez, Thierry PriolAbstract:Grids are very complex and volatile infrastructures that exhibit parallel and distributed characteristics. To harness their complexity as well as the increasing intricacy of scientific applications, modern software engineering practices are needed. As of today, two major programming Models dominate: software Component Models that are mainly based on a spatial composition and service oriented Models with their associated workflow languages promoting a temporal composition. This paper tends to unify these two forms of composition into a coherent spatio-temporal software Component Model while keeping their benefits. To attest the validity of the proposed approach, we describe how the Grid Component Model, as defined by the CoreGRID Network of Excellence, and the Askalon-AGWL workflow language have been adapted.
Tom R Tyler - One of the best experts on this subject based on the ideXlab platform.
-
a four Component Model of procedural justice defining the meaning of a fair process
Personality and Social Psychology Bulletin, 2003Co-Authors: Steven L Blader, Tom R TylerAbstract:Two studies test the prediction of the four-Component Model of procedural justice that people evaluate the fairness of group procedures using four distinct types of judgment. The Model hypothesizes that people are influenced by two aspects of the formal procedures of the group: those aspects that relate to decision making and those that relate to the quality of treatment that group members are entitled to receive under the rules. In addition, people are hypothesized to be separately influenced by two aspects of the authorities with whom they personally deal: the quality of decision making by those authorities and the quality of the treatment that they receive from them. The results of two studies support the hypothesis of the four-Component Model by finding that all four of the procedural judgments identified by the Model contribute to overall evaluations of the fairness of group procedures.
-
what constitutes fairness in work settings a four Component Model of procedural justice
Human Resource Management Review, 2003Co-Authors: Steven L Blader, Tom R TylerAbstract:Abstract Despite a recent surge in research on procedural justice in organizational contexts, little work has systematically investigated how employees define procedural justice. In other words, relatively little has been done to establish a clear awareness of what employees consider when making their procedural justice evaluations. This lack of attention to construct definition is problematic, since it prevents an understanding of what underlies employees' fairness evaluations and leaves several issues regarding the definition and conceptualization of procedural justice unresolved. To address these issues, this article describes the four-Component Model of procedural justice [Blader, S. L., & Tyler, T. R. (in press). A four Component Model of procedural justice: Defining the meaning of a “fair” process. Personality and Social Psychology Bulletin; Tyler, T. R., & Blader, S. L. (2000). Cooperation in groups: procedural justice, social identity and behavioral engagement. Philadelphia, PA: Psychology Press.], which posits four Components that are believed to underlie overall procedural justice evaluations. The Model differentiates between both justice type (decision making, quality of treatment) and justice source (formal, informal) in developing these Components. Research supporting the four-Component conceptualization is discussed and the utility of this approach for procedural justice research is reviewed.
Steven L Blader - One of the best experts on this subject based on the ideXlab platform.
-
a four Component Model of procedural justice defining the meaning of a fair process
Personality and Social Psychology Bulletin, 2003Co-Authors: Steven L Blader, Tom R TylerAbstract:Two studies test the prediction of the four-Component Model of procedural justice that people evaluate the fairness of group procedures using four distinct types of judgment. The Model hypothesizes that people are influenced by two aspects of the formal procedures of the group: those aspects that relate to decision making and those that relate to the quality of treatment that group members are entitled to receive under the rules. In addition, people are hypothesized to be separately influenced by two aspects of the authorities with whom they personally deal: the quality of decision making by those authorities and the quality of the treatment that they receive from them. The results of two studies support the hypothesis of the four-Component Model by finding that all four of the procedural judgments identified by the Model contribute to overall evaluations of the fairness of group procedures.
-
what constitutes fairness in work settings a four Component Model of procedural justice
Human Resource Management Review, 2003Co-Authors: Steven L Blader, Tom R TylerAbstract:Abstract Despite a recent surge in research on procedural justice in organizational contexts, little work has systematically investigated how employees define procedural justice. In other words, relatively little has been done to establish a clear awareness of what employees consider when making their procedural justice evaluations. This lack of attention to construct definition is problematic, since it prevents an understanding of what underlies employees' fairness evaluations and leaves several issues regarding the definition and conceptualization of procedural justice unresolved. To address these issues, this article describes the four-Component Model of procedural justice [Blader, S. L., & Tyler, T. R. (in press). A four Component Model of procedural justice: Defining the meaning of a “fair” process. Personality and Social Psychology Bulletin; Tyler, T. R., & Blader, S. L. (2000). Cooperation in groups: procedural justice, social identity and behavioral engagement. Philadelphia, PA: Psychology Press.], which posits four Components that are believed to underlie overall procedural justice evaluations. The Model differentiates between both justice type (decision making, quality of treatment) and justice source (formal, informal) in developing these Components. Research supporting the four-Component conceptualization is discussed and the utility of this approach for procedural justice research is reviewed.
George Tucker - One of the best experts on this subject based on the ideXlab platform.
-
two variance Component Model improves genetic prediction in family datasets
American Journal of Human Genetics, 2015Co-Authors: George Tucker, Iona M Macleod, Ben J Hayes, M E Goddard, Bonnie Berger, Alkes L PriceAbstract:Genetic prediction based on either identity by state (IBS) sharing or pedigree information has been investigated extensively with best linear unbiased prediction (BLUP) methods. Such methods were pioneered in plant and animal-breeding literature and have since been applied to predict human traits, with the aim of eventual clinical utility. However, methods to combine IBS sharing and pedigree information for genetic prediction in humans have not been explored. We introduce a two-variance-Component Model for genetic prediction: one Component for IBS sharing and one for approximate pedigree structure, both estimated with genetic markers. In simulations using real genotypes from the Candidate-gene Association Resource (CARe) and Framingham Heart Study (FHS) family cohorts, we demonstrate that the two-variance-Component Model achieves gains in prediction r 2 over standard BLUP at current sample sizes, and we project, based on simulations, that these gains will continue to hold at larger sample sizes. Accordingly, in analyses of four quantitative phenotypes from CARe and two quantitative phenotypes from FHS, the two-variance-Component Model significantly improves prediction r 2 in each case, with up to a 20% relative improvement. We also find that standard mixed-Model association tests can produce inflated test statistics in datasets with related individuals, whereas the two-variance-Component Model corrects for inflation.
-
two variance Component Model improves genetic prediction in family data sets
bioRxiv, 2015Co-Authors: George Tucker, Iona M Macleod, Ben J Hayes, M E Goddard, Bonnie Berger, Alkes L PriceAbstract:Genetic prediction based on either identity by state (IBS) sharing or pedigree information has been investigated extensively using Best Linear Unbiased Prediction (BLUP) methods. Such methods were pioneered in the plant and animal breeding literature and have since been applied to predict human traits with the aim of eventual clinical utility. However, methods to combine IBS sharing and pedigree information for genetic prediction in humans have not been explored. We introduce a two variance Component Model for genetic prediction: one Component for IBS sharing and one for approximate pedigree structure, both estimated using genetic markers. In simulations using real genotypes from CARe and FHS family cohorts, we demonstrate that the two variance Component Model achieves gains in prediction r2 over standard BLUP at current sample sizes, and we project based on simulations that these gains will continue to hold at larger sample sizes. Accordingly, in analyses of four quantitative phenotypes from CARe and two quantitative phenotypes from FHS, the two variance Component Model significantly improves prediction r2 in each case, with up to a 20% relative improvement. We also find that standard mixed Model association tests can produce inflated test statistics in data sets with related individuals, whereas the two variance Component Model corrects for inflation.
Lu Yan - One of the best experts on this subject based on the ideXlab platform.
-
The Research of Timing-Constraint Component Model on the Basis of Reflection Technology
Computer Science, 2006Co-Authors: Lu YanAbstract:The reflection-based real-time Component Model mainly researches on timing-constraint Component Model or horizontal reuse in real-time application software. Starting from traditional Component Model and using reflection technology,a new Component Model——reflective real-time Component Model is brought forward while developing real-time software system. The Model is composed of reflective real-time semantic and grammatical Model. Besides the necessary functional requirement features of specification Components, it can effectively identify the time-constraint feature of Components, which makes it different from the traditional functional Components and therefore a better choice for the software system developer. Also, integrated with reflection technology, it can make dynamic update according to changed customer requirement to protect the constructing and developing of real-time application system more safely. This enhances the flexibility of Component design and results in better products. Reflective real-time Component Model is a theoretical Component Model as well as a project Model.
-
PCCM: Performance-Constraint Component Model
Computer Science, 2004Co-Authors: Lu YanAbstract:Component Model is the basis of Component reuse. The paper is to synthesize 3C and REBOOT Component Models to put forward a Performance-Constraint Component Model-PCCM to implement Component reuses with performance constraints. Firstly analyze research of Component Models and reuse status briefly to educe reuse requirement with performance constraints in special domains- Then a Component Model with performance constraints is proposed . description is specified. After that key technology route of implementation and excellence of the Model are analyzed. Finally further research direction is given.