Model-based Systems Engineering plays a pivotal role in the design of Software-Intensive and Cybe... more Model-based Systems Engineering plays a pivotal role in the design of Software-Intensive and Cyber-Physical Systems by enabling early virtual integration of the different parts of the system. Often multiple formalisms are combined to express the behaviour of these complex engineered systems. Co-simulation in general and the Functional Mock-up Interface specifically, is a technique to simulate multiple heterogeneous models in concert. However, usage and performance of the overall co-simulation does not only depend on the accuracy of the distinct heterogeneous models. It also depends on the co-simulation master: the orchestration mechanism for this simultaneous simulation. In this paper we report on a technique to increase the performance of co-simulation. We explicitly model a co-simulation setup, using language engineering techniques. An explicit model of the co-simulation allows to automatically generate an optimised orchestration algorithm compliant to the Functional Mock-up Inter...
With the advent of Software-Intensive and Cyber-Physical Systems, hybrid formalisms can be used t... more With the advent of Software-Intensive and Cyber-Physical Systems, hybrid formalisms can be used to intuitively model the interactions of different models in different formalisms. Hybrid formalisms combine discrete (time/event) model constructs with continuous-time model constructs. These hybrid formalisms usually require a dedicated simulator. In this work we explicitly model the interfaces involved in the semantic adaptation of different formalisms and implement the execution using the Functional Mock-up Interface standard for co-simulation. The interfaces and co-simulation units are automatically generated using transformations. On the one hand, this allows tool builders to reuse the existing simulation tools without the need to create a new simulation kernel for the hybrid formalism. On the other hand, our approach supports the generation of different bus architectures to address different constraints, such as the use of hardware in the loop, the API of the legacy simulator, bus ...
9th International Conference on Electronics, Circuits and Systems, 2002
... The PMOS of this inverter determines the rise time and the NMOS determines the fall time. The... more ... The PMOS of this inverter determines the rise time and the NMOS determines the fall time. The most significant bits drive the gates of many transistors in parallel, and interconnecting all the gates of these transistors requires long interconnections. ...
ABSTRACT The split diffuse maxima around the \{110\} and \{100\} positions in the diffraction pat... more ABSTRACT The split diffuse maxima around the \{110\} and \{100\} positions in the diffraction pattern of short-range-ordered Cu1-xPdx alloys (x=0.10...0.60) are attributed to small atomic clusters, being part of the underlying fcc lattice. By analyzing the reciprocal space geometry, our cluster method identifies two prominent cluster types: the tetrahedron of nearest neighbors and a linear three-points cluster along the directions. Since both cluster types contain different information on the same nearest-neighbor correlations, local anisotropy has to be assumed. It is shown that the three interatomic pair interactions within these basic clusters are sufficient to generate the spot splitting in the diffraction pattern. A ground-state analysis with these interactions reproduces the results of the anisotropic next-nearest-neighbor Ising model.
2013 Eighth International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 2013
ABSTRACT In the development of advanced data acquisition, testing or telecommunication equipment,... more ABSTRACT In the development of advanced data acquisition, testing or telecommunication equipment, one often relies on modular off-the-shelf processor boards and I/O-boards that are being composed to a single distributed system. To support such architectures, the microTCA (micro Telecommunication Computing Architecture) offers standardized racks and standardized back panel communication protocols connecting the different boards. During the design of such distributed systems, the performance characteristics of the end-to-end communication between different boards in the system are often not sufficiently known. In this paper, we present a setup allowing for benchmarking the performance of the full PCIe-communication path between two microTCA FPGA-boards. The experimental setup is discussed, and it is shown that benchmarking figures for throughput, delay and delay variation of the PCIe end-to-end path can be retrieved.
ABSTRACT Cu-Pd alloys containing 10, 20, 30, 40, and 50 at. % Pd and quenched from a temperature ... more ABSTRACT Cu-Pd alloys containing 10, 20, 30, 40, and 50 at. % Pd and quenched from a temperature just above the ordering temperature Tc are investigated by electron diffraction and high-resolution electron microscopy (HREM). The results show diffuse electron diffraction intensities at {100} and {110} positions for the alloy with 10 at. % Pd, but with a characteristic twofold and fourfold splitting for the alloys with more than 10 at. % Pd. High-resolution images show the formation of microdomains best developed between 20 and 30 at. % Pd. A real-space characterization has been performed by applying videographic real-structure simulations revealing that the splitting of the diffuse maxima depends on the average distance between microdomains of Cu3Au-type in antiphase with each other. By applying image processing routines on the HREM images, correlation vectors are identified which correspond to correlations between microdomains.
ABSTRACT The drive towards standardization in the automotive sector puts a lot of pressure on sof... more ABSTRACT The drive towards standardization in the automotive sector puts a lot of pressure on software suppliers to comply with standards such as OSEK and AUTOSAR. However, many of these suppliers have a vested interest in proprietary software and are seeking ways to migrate their existing code base to comply with these standards. This paper reports on a feasibility study to migrate an automotive off-highway application to the OSEK-OS using a wrapper around the proprietary real-time operating system (RTOS). Besides investigating whether this is feasible, we also assess the performance impact in terms of computation time and memory consumption, as this is critically important for real-time systems. Finally some pitfalls are given when porting a given application to OSEK-compliant RTOS. As such, we evaluate the typical trade-offs one has to make when adopting an incremental migration strategy towards a standard compliant interface.
2011 37th EUROMICRO Conference on Software Engineering and Advanced Applications, 2011
ABSTRACT AUTOSAR, the Automotive Open System Architecture, is growing to an accepted industrial s... more ABSTRACT AUTOSAR, the Automotive Open System Architecture, is growing to an accepted industrial standard for the development of automotive embedded software. The AUTOSAR design method describes a software development process starting at the architectural design up to the deployment of the developed software on embedded controllers. Since most companies already have their own system development process, the introduction of AUTOSAR will have a direct impact on these processes. In this paper we will demonstrate the integration of AUTOSAR in a system development process that is similar to an industrial development process. This process is validated by means of an ABS case study. It is shown that introducing AUTOSAR has a relative small impact on the existing system development process.
ABSTRACT In embedded systems development, software engineers increasingly rely on modelling and s... more ABSTRACT In embedded systems development, software engineers increasingly rely on modelling and simulation to produce optimal design solutions. A bottleneck in the Modelling and Simulation Based Design (MSBD) process is model calibration. Setting up experiments to estimate parameter values such that the model accurately reflects real-world system structure and behaviour is technically complex and labour intensive. Parameters to be estimated are for example effective processor speed, memory consumption and network throughput of the hardware platform on which software is deployed. In this paper we show how Multi-Paradigm Modelling (MPM) allows for the synthesis of a model calibration infrastructure. This includes the synthesis, from a model, of a simulator for the "environment" in which a system-to-be built will operate. To demonstrate the feasibility of our approach, we calibrate the model of an automotive power window controller running on the AUTOSAR-platform.
Model-based Systems Engineering plays a pivotal role in the design of Software-Intensive and Cybe... more Model-based Systems Engineering plays a pivotal role in the design of Software-Intensive and Cyber-Physical Systems by enabling early virtual integration of the different parts of the system. Often multiple formalisms are combined to express the behaviour of these complex engineered systems. Co-simulation in general and the Functional Mock-up Interface specifically, is a technique to simulate multiple heterogeneous models in concert. However, usage and performance of the overall co-simulation does not only depend on the accuracy of the distinct heterogeneous models. It also depends on the co-simulation master: the orchestration mechanism for this simultaneous simulation. In this paper we report on a technique to increase the performance of co-simulation. We explicitly model a co-simulation setup, using language engineering techniques. An explicit model of the co-simulation allows to automatically generate an optimised orchestration algorithm compliant to the Functional Mock-up Inter...
With the advent of Software-Intensive and Cyber-Physical Systems, hybrid formalisms can be used t... more With the advent of Software-Intensive and Cyber-Physical Systems, hybrid formalisms can be used to intuitively model the interactions of different models in different formalisms. Hybrid formalisms combine discrete (time/event) model constructs with continuous-time model constructs. These hybrid formalisms usually require a dedicated simulator. In this work we explicitly model the interfaces involved in the semantic adaptation of different formalisms and implement the execution using the Functional Mock-up Interface standard for co-simulation. The interfaces and co-simulation units are automatically generated using transformations. On the one hand, this allows tool builders to reuse the existing simulation tools without the need to create a new simulation kernel for the hybrid formalism. On the other hand, our approach supports the generation of different bus architectures to address different constraints, such as the use of hardware in the loop, the API of the legacy simulator, bus ...
9th International Conference on Electronics, Circuits and Systems, 2002
... The PMOS of this inverter determines the rise time and the NMOS determines the fall time. The... more ... The PMOS of this inverter determines the rise time and the NMOS determines the fall time. The most significant bits drive the gates of many transistors in parallel, and interconnecting all the gates of these transistors requires long interconnections. ...
ABSTRACT The split diffuse maxima around the \{110\} and \{100\} positions in the diffraction pat... more ABSTRACT The split diffuse maxima around the \{110\} and \{100\} positions in the diffraction pattern of short-range-ordered Cu1-xPdx alloys (x=0.10...0.60) are attributed to small atomic clusters, being part of the underlying fcc lattice. By analyzing the reciprocal space geometry, our cluster method identifies two prominent cluster types: the tetrahedron of nearest neighbors and a linear three-points cluster along the directions. Since both cluster types contain different information on the same nearest-neighbor correlations, local anisotropy has to be assumed. It is shown that the three interatomic pair interactions within these basic clusters are sufficient to generate the spot splitting in the diffraction pattern. A ground-state analysis with these interactions reproduces the results of the anisotropic next-nearest-neighbor Ising model.
2013 Eighth International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 2013
ABSTRACT In the development of advanced data acquisition, testing or telecommunication equipment,... more ABSTRACT In the development of advanced data acquisition, testing or telecommunication equipment, one often relies on modular off-the-shelf processor boards and I/O-boards that are being composed to a single distributed system. To support such architectures, the microTCA (micro Telecommunication Computing Architecture) offers standardized racks and standardized back panel communication protocols connecting the different boards. During the design of such distributed systems, the performance characteristics of the end-to-end communication between different boards in the system are often not sufficiently known. In this paper, we present a setup allowing for benchmarking the performance of the full PCIe-communication path between two microTCA FPGA-boards. The experimental setup is discussed, and it is shown that benchmarking figures for throughput, delay and delay variation of the PCIe end-to-end path can be retrieved.
ABSTRACT Cu-Pd alloys containing 10, 20, 30, 40, and 50 at. % Pd and quenched from a temperature ... more ABSTRACT Cu-Pd alloys containing 10, 20, 30, 40, and 50 at. % Pd and quenched from a temperature just above the ordering temperature Tc are investigated by electron diffraction and high-resolution electron microscopy (HREM). The results show diffuse electron diffraction intensities at {100} and {110} positions for the alloy with 10 at. % Pd, but with a characteristic twofold and fourfold splitting for the alloys with more than 10 at. % Pd. High-resolution images show the formation of microdomains best developed between 20 and 30 at. % Pd. A real-space characterization has been performed by applying videographic real-structure simulations revealing that the splitting of the diffuse maxima depends on the average distance between microdomains of Cu3Au-type in antiphase with each other. By applying image processing routines on the HREM images, correlation vectors are identified which correspond to correlations between microdomains.
ABSTRACT The drive towards standardization in the automotive sector puts a lot of pressure on sof... more ABSTRACT The drive towards standardization in the automotive sector puts a lot of pressure on software suppliers to comply with standards such as OSEK and AUTOSAR. However, many of these suppliers have a vested interest in proprietary software and are seeking ways to migrate their existing code base to comply with these standards. This paper reports on a feasibility study to migrate an automotive off-highway application to the OSEK-OS using a wrapper around the proprietary real-time operating system (RTOS). Besides investigating whether this is feasible, we also assess the performance impact in terms of computation time and memory consumption, as this is critically important for real-time systems. Finally some pitfalls are given when porting a given application to OSEK-compliant RTOS. As such, we evaluate the typical trade-offs one has to make when adopting an incremental migration strategy towards a standard compliant interface.
2011 37th EUROMICRO Conference on Software Engineering and Advanced Applications, 2011
ABSTRACT AUTOSAR, the Automotive Open System Architecture, is growing to an accepted industrial s... more ABSTRACT AUTOSAR, the Automotive Open System Architecture, is growing to an accepted industrial standard for the development of automotive embedded software. The AUTOSAR design method describes a software development process starting at the architectural design up to the deployment of the developed software on embedded controllers. Since most companies already have their own system development process, the introduction of AUTOSAR will have a direct impact on these processes. In this paper we will demonstrate the integration of AUTOSAR in a system development process that is similar to an industrial development process. This process is validated by means of an ABS case study. It is shown that introducing AUTOSAR has a relative small impact on the existing system development process.
ABSTRACT In embedded systems development, software engineers increasingly rely on modelling and s... more ABSTRACT In embedded systems development, software engineers increasingly rely on modelling and simulation to produce optimal design solutions. A bottleneck in the Modelling and Simulation Based Design (MSBD) process is model calibration. Setting up experiments to estimate parameter values such that the model accurately reflects real-world system structure and behaviour is technically complex and labour intensive. Parameters to be estimated are for example effective processor speed, memory consumption and network throughput of the hardware platform on which software is deployed. In this paper we show how Multi-Paradigm Modelling (MPM) allows for the synthesis of a model calibration infrastructure. This includes the synthesis, from a model, of a simulator for the "environment" in which a system-to-be built will operate. To demonstrate the feasibility of our approach, we calibrate the model of an automotive power window controller running on the AUTOSAR-platform.
Uploads
Papers by Paul Meulenaere