Dominique Houzet
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Dominique Houzet has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Nathalie Guyader
GIPSA-Lab
3 shared publications - Anis Ur Rahman
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan
2 shared publications - Denis Pellerin
GIPSA-Lab
2 shared publications - Vincent Fristot
GIPSALAB, Grenoble Alpes University, 11 Rue des Mathématiques, 38400 Saint-Martin-d'Hères, France
2 shared publications Abdelkrim Hamzaoui
Cadi Ayyad University
1 shared publication- Anne-Claire Legrand
Université de Lyon F-42023 Saint-Etienne France
1 shared publication
Latest Publications
- 17 June 2022
- Published by Springer Nature
- p. 3-18
3D Dense & Scaled Reconstruction Pipeline with Smartphone Acquisition
- 17 June 2022
- Published by Springer Nature
- p. 3-18
3D Dense & Scaled Reconstruction Pipeline with Smartphone Acquisition
- 1 October 2020
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 17 (5) , 1567-1583
Efficient adaptive load balancing approach for compressive background subtraction algorithm on heterogeneous CPU-GPU platforms
- 1 October 2020
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 17 (5) , 1567-1583
Efficient adaptive load balancing approach for compressive background subtraction algorithm on heterogeneous CPU-GPU platforms
- Open Access
- 31 July 2020
- Published by International Union of Crystallography (IUCr) in Journal of Synchrotron Radiation
- Vol. 27 (5) , 1297-1306
RDMA data transfer and GPU acceleration methods for high-throughput online processing of serial crystallography images
The continual evolution of photon sources and high-performance detectors drives cutting-edge experiments that can produce very high throughput data streams and generate large data volumes that are challenging to manage and store. In these cases, efficient data transfer and processing architectures that allow online image correction, data reduction or compression become fundamental. This work investigates different technical options and methods for data placement from the detector head to the processing computing infrastructure, taking into account the particularities of modern modular high-performance detectors. In order to compare realistic figures, the future ESRF beamline dedicated to macromolecular X-ray crystallography, EBSL8, is taken as an example, which will use a PSI JUNGFRAU 4M detector generating up to 16 GB of data per second, operating continuously during several minutes. Although such an experiment seems possible at the target speed with the 100 Gb s−1 network cards that are currently available, the simulations generated highlight some potential bottlenecks when using a traditional software stack. An evaluation of solutions is presented that implements remote direct memory access (RDMA) over converged ethernet techniques. A synchronization mechanism is proposed between a RDMA network interface card (RNIC) and a graphics processing unit (GPU) accelerator in charge of the online data processing. The placement of the detector images onto the GPU is made to overlap with the computation carried out, potentially hiding the transfer latencies. As a proof of concept, a detector simulator and a backend GPU receiver with a rejection and compression algorithm suitable for a synchrotron serial crystallography (SSX) experiment are developed. It is concluded that the available transfer throughput from the RNIC to the GPU accelerator is at present the major bottleneck in online processing for SSX experiments.
- 31 July 2020
- Published by International Union of Crystallography (IUCr) in Journal of Synchrotron Radiation
- Vol. 27 (5) , 1297-1306
Open AccessRDMA data transfer and GPU acceleration methods for high-throughput online processing of serial crystallography images
The continual evolution of photon sources and high-performance detectors drives cutting-edge experiments that can produce very high throughput data streams and generate large data volumes that are challenging to manage and store. In these cases, efficient data transfer and processing architectures that allow online image correction, data reduction or compression become fundamental. This work investigates different technical options and methods for data placement from the detector head to the processing computing infrastructure, taking into account the particularities of modern modular high-performance detectors. In order to compare realistic figures, the future ESRF beamline dedicated to macromolecular X-ray crystallography, EBSL8, is taken as an example, which will use a PSI JUNGFRAU 4M detector generating up to 16 GB of data per second, operating continuously during several minutes. Although such an experiment seems possible at the target speed with the 100 Gb s−1 network cards that are currently available, the simulations generated highlight some potential bottlenecks when using a traditional software stack. An evaluation of solutions is presented that implements remote direct memory access (RDMA) over converged ethernet techniques. A synchronization mechanism is proposed between a RDMA network interface card (RNIC) and a graphics processing unit (GPU) accelerator in charge of the online data processing. The placement of the detector images onto the GPU is made to overlap with the computation carried out, potentially hiding the transfer latencies. As a proof of concept, a detector simulator and a backend GPU receiver with a rejection and compression algorithm suitable for a synchrotron serial crystallography (SSX) experiment are developed. It is concluded that the available transfer throughput from the RNIC to the GPU accelerator is at present the major bottleneck in online processing for SSX experiments.
- 20 September 2015
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 28 (3) , 750-767
A domain‐specific high‐level programming model
Summary: Nowadays, computing hardware continues to move toward more parallelism and more heterogeneity, to obtain more computing power. From personal computers to supercomputers, we can find several levels of parallelism expressed by the interconnections of multi‐core and many‐core accelerators. On the other hand, computing software needs to adapt to this trend, and programmers can use parallel programming models (PPM) to fulfil this difficult task. There are different PPMs available that are based on tasks, directives, or low‐level languages or library. These offer higher or lower abstraction levels from the architecture by handling their own syntax. However, to offer an efficient PPM with a greater (additional) high‐level abstraction level while saving on performance, one idea is to restrict this to a specific domain and to adapt it to a family of applications. In the present study, we propose a high‐level PPM specific to digital signal‐processing applications. It is based on data‐flow graph models of computation, and a dynamic run‐time model of execution (StarPU). We show how the user can easily express this digital signal‐processing application and can take advantage of task, data, and graph parallelism in the implementation, to enhance the performances of targeted heterogeneous clusters composed of CPUs and different accelerators (e.g., GPU and Xeon Phi). Copyright © 2015 John Wiley & Sons, Ltd.
- 20 September 2015
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 28 (3) , 750-767
A domain‐specific high‐level programming model
Summary: Nowadays, computing hardware continues to move toward more parallelism and more heterogeneity, to obtain more computing power. From personal computers to supercomputers, we can find several levels of parallelism expressed by the interconnections of multi‐core and many‐core accelerators. On the other hand, computing software needs to adapt to this trend, and programmers can use parallel programming models (PPM) to fulfil this difficult task. There are different PPMs available that are based on tasks, directives, or low‐level languages or library. These offer higher or lower abstraction levels from the architecture by handling their own syntax. However, to offer an efficient PPM with a greater (additional) high‐level abstraction level while saving on performance, one idea is to restrict this to a specific domain and to adapt it to a family of applications. In the present study, we propose a high‐level PPM specific to digital signal‐processing applications. It is based on data‐flow graph models of computation, and a dynamic run‐time model of execution (StarPU). We show how the user can easily express this digital signal‐processing application and can take advantage of task, data, and graph parallelism in the implementation, to enhance the performances of targeted heterogeneous clusters composed of CPUs and different accelerators (e.g., GPU and Xeon Phi). Copyright © 2015 John Wiley & Sons, Ltd.
- 24 March 2015
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 10 (3) , 423-429
Contribution of color in saliency model for videos
- 24 March 2015
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 10 (3) , 423-429
Contribution of color in saliency model for videos
- 10 October 2012
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 9 (1) , 217-232
Efficient implementation of data flow graphs on multi-gpu clusters
- 10 October 2012
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 9 (1) , 217-232
Efficient implementation of data flow graphs on multi-gpu clusters
- 1 June 2012
- Published by Springer Nature in Cognitive Computation
- Vol. 5 (1) , 63-75
Improving Visual Saliency by Adding ‘Face Feature Map’ and ‘Center Bias’
- 1 June 2012
- Published by Springer Nature in Cognitive Computation
- Vol. 5 (1) , 63-75
Improving Visual Saliency by Adding ‘Face Feature Map’ and ‘Center Bias’
- 27 June 2010
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 6 (1) , 3-14
Parallel implementation of a spatio-temporal visual saliency model
- 27 June 2010
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 6 (1) , 3-14
Parallel implementation of a spatio-temporal visual saliency model
- Open Access
Evaluation and Design Space Exploration of a Time-Division Multiplexed NoC on FPGA for Image Analysis Applications
The aim of this paper is to present an adaptable Fat Tree NoC architecture for Field Programmable Gate Array (FPGA) designed for image analysis applications. Traditional NoCs (Network on Chip) are not optimal for dataflow applications with large amount of data. On the opposite, point to point communications are designed from the algorithm requirements but they are expensives in terms of resource and wire. We propose a dedicated communication architecture for image analysis algorithms. This communication mechanism is a generic NoC infrastructure dedicated to dataflow image processing applications, mixing circuit-switching and packet-switching communications. The complete architecture integrates two dedicated communication architectures and reusable IP blocks. Communications are based on the NoC concept to support the high bandwidth required for a large number and type of data.
Open AccessEvaluation and Design Space Exploration of a Time-Division Multiplexed NoC on FPGA for Image Analysis Applications
The aim of this paper is to present an adaptable Fat Tree NoC architecture for Field Programmable Gate Array (FPGA) designed for image analysis applications. Traditional NoCs (Network on Chip) are not optimal for dataflow applications with large amount of data. On the opposite, point to point communications are designed from the algorithm requirements but they are expensives in terms of resource and wire. We propose a dedicated communication architecture for image analysis algorithms. This communication mechanism is a generic NoC infrastructure dedicated to dataflow image processing applications, mixing circuit-switching and packet-switching communications. The complete architecture integrates two dedicated communication architectures and reusable IP blocks. Communications are based on the NoC concept to support the high bandwidth required for a large number and type of data.