Add to ORKGWe describe the principles of a novel framework for performance-aware composition of sequential and explicitly parallelsoftware components with implementation variants. Context-aware composition dynamically selects, for each a performance-aware component, the expected best implementationvariant, processor allocation and schedule for the actualproblem size and processors available. The selection functionsare pre-computed statically using machine learningbased on profiling data.Self-organizing Architectures: Design,Composition, Optimizatio
This paper describes the ParaPhrase project, a new 3-year targeted research project funded under EU ...
This paper describes a dynamic framework for mapping the threads of parallel applications to the com...
Abstract: The computational and compositional features are very important while constructing paralle...
Abstract. We describe the principles of a novel framework for performance-aware composition of seque...
Abstract—User-level components of applications can be made performance-aware by annotating them with...
Development of efficient and correct parallel programs is a complex task. These parallel codes have...
Sometimes components are conservatively implemented as thread-safe, while during the actual executio...
In recent years parallel computing has become ubiquitous. Lead by the spread of commodity multicore ...
Distributing the workload of computationally intensive software components across a set of homogeneo...
International audienceAs Grid architectures provide execution environments that are distributed, par...
This paper presents self-organizing feature maps as an efficient tool generating solutions of the ma...
This paper introduces a resource allocation framework specifically tailored for addressing the probl...
There is an increasing need for a framework that supports research on portable high-performance para...
Nowadays, a significant part of computing systems and real-world applications demand parallelism to ...
While parallel programming is needed to solve large-scale scientific applications, it is more diffic...
This paper describes the ParaPhrase project, a new 3-year targeted research project funded under EU ...
This paper describes a dynamic framework for mapping the threads of parallel applications to the com...
Abstract: The computational and compositional features are very important while constructing paralle...
Abstract. We describe the principles of a novel framework for performance-aware composition of seque...
Abstract—User-level components of applications can be made performance-aware by annotating them with...
Development of efficient and correct parallel programs is a complex task. These parallel codes have...
Sometimes components are conservatively implemented as thread-safe, while during the actual executio...
In recent years parallel computing has become ubiquitous. Lead by the spread of commodity multicore ...
Distributing the workload of computationally intensive software components across a set of homogeneo...
International audienceAs Grid architectures provide execution environments that are distributed, par...
This paper presents self-organizing feature maps as an efficient tool generating solutions of the ma...
This paper introduces a resource allocation framework specifically tailored for addressing the probl...
There is an increasing need for a framework that supports research on portable high-performance para...
Nowadays, a significant part of computing systems and real-world applications demand parallelism to ...
While parallel programming is needed to solve large-scale scientific applications, it is more diffic...
This paper describes the ParaPhrase project, a new 3-year targeted research project funded under EU ...
This paper describes a dynamic framework for mapping the threads of parallel applications to the com...
Abstract: The computational and compositional features are very important while constructing paralle...