| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Pllana, Sabri, et al.
(author)
-
A Novel Approach for Hybrid Performance Modelingand Prediction of Large-Scale Computing Systems
- 2009
-
In: International Journal of Grid and Utility Computing (IJGUC). - : InderScience Publishers. - 1741-8488. ; 1:4, s. 316-327
-
Journal article (peer-reviewed)abstract
- We present a novel approach for hybrid performance modelling and prediction of large-scale parallel and distributed computing systems, which combines Mathematical Modelling (MathMod) and Discrete-Event Simulation (DES). We use MathMod to develop parameterised performance models for components of the system. Thereafter, we use DES to describe the structure of system and the interaction among its components. As a result we obtain a high-level performance model, which combines the evaluation speed of mathematical models with the structure awareness and fidelity of the simulation model. We evaluate empirically our approach with a real-world material science program that comprises more than 15,000 lines of code.
|
|
| 6. |
- Pllana, Sabri, et al.
(author)
-
Agent-supported Programming of Multi-core Computing Systems
- 2010
-
In: Complex Intelligent Systems and Their Applications. - New York, NY : Springer. - 9781441916358 ; , s. 207-224
-
Book chapter (peer-reviewed)abstract
- In this chapter we argue that an intelligent program development environment that proactively supports the user helps a mainstream programmer to overcome the difficulties of programming multicore computing systems. We propose a programming environment based on intelligent software agents that enables users to work at a high level of abstraction while automating low-level implementation activities. The programming environment supports program composition in a model-driven development fashion using parallel building blocks and proactively assists the user during major phases of program development and performance tuning. We highlight the potential benefits of using such a programming environment with usage scenarios. An experiment with a parallel building block on a Sun UltraSPARC T2 Plus processor shows how the system may assist the programmer in achieving performance improvements.
|
|
| 7. |
- Pllana, Sabri, et al.
(author)
-
Automatic Performance Model Transformation from a Human-intuitive to a Machine-efficient Form
- 2009
-
In: Scalable computing. - : SCPE. - 1895-1767. ; 10:1, s. 35-47
-
Journal article (peer-reviewed)abstract
- We address the issue of the development of performance models for programs that may be executed on large-scale computing systems. The commonly used approaches apply non-standard notations for model specification and often require that the software engineer has a thorough understanding of the underlying performance modeling technique. We propose to bridge the gap between the performance modeling and software engineering by incorporating UML. In our approach we aim to permit the graphical specification of performance model in a human-intuitive fashion on one hand, but on the other hand we aim for a machine-efficient model evaluation. The user specifies graphically the performance model using UML. Thereafter, the transformation of the performance model from the human-usable UML representation to the machine-efficient C++ representation is done automatically. We describe our methodology and illustrate it with the automatic transformation of a sample performance model. Furthermore, we demonstrate the usefulness of our approach by modeling and simulating a real-world material science program.
|
|
| 8. |
- Pllana, Sabri, et al.
(author)
-
Automatic Performance Model Transformation from UML to C+
- 2008
-
In: Proceedings of the International Conference on Parallel Processing Workshops. - : IEEE Computer Society. - 9780769533759 ; , s. 228-235
-
Conference paper (peer-reviewed)abstract
- We address the issue of the development of performance models for programs that may be executed on large-scale computing systems. The commonly used approaches apply non-standard notations for model specification and often require that the software engineer has a thorough understanding of the underlying performance modeling technique. We propose to bridge the gap between the performance modeling and software engineering by incorporating UML. In our approach we aim to permit the graphical specification of performance model in a human-intuitive fashion on one hand, but on the other hand we aim for a machine-efficient model evaluation. The user specifies graphically the performance model using UML. Thereafter, the transformation of the performance model from the human-usable UML representation to the machine-efficient C++ representation is done automatically. We describe our methodology and illustrate it with the automatic transformation of a sample performance model.
|
|
| 9. |
- Pllana, Sabri, et al.
(author)
-
Hybrid Performance Modeling and Prediction of Large-Scale Computing Systems
- 2008
-
In: International Conference on Complex, Intelligent and Software Intensive Systems, 2008. - : IEEE Computer Society. - 9780769531090 ; , s. 132-138
-
Conference paper (peer-reviewed)abstract
- Performance is a key feature of large-scale computing systems. However, the achieved performance when a certain program is executed is significantly lower than the maximal theoretical performance of the large-scale computing system. The model-based performance evaluation may be used to support the performance-oriented program development for large-scale computing systems. In this paper we present a hybrid approach for performance modeling and prediction of parallel and distributed computing systems, which combines mathematical modeling and discrete-event simulation. We use mathematical modeling to develop parameterized performance models for components of the system. Thereafter, we use discrete-event simulation to describe the structure of system and the interaction among its components. As a result, we obtain a high-level performance model, which combines the evaluation speed of mathematical models with the structure awareness and fidelity of the simulation model. We evaluate empirically our approach with a real-world material science program that comprises more than 15,000 lines of code.
|
|
| 10. |
|
|
