Papers by Souley Madougou
HAL (Le Centre pour la Communication Scientifique Directe), 2003
Le Centre pour la Communication Scientifique Directe - HAL - Diderot, 2005
2019 15th International Conference on eScience (eScience), 2019
Computing and Informatics, 2020
While political commitments for building exascale systems have been made, turning these systems i... more While political commitments for building exascale systems have been made, turning these systems into platforms for a wide range of exascale applications faces several technical, organisational and skills-related challenges. The key technical challenges are related to the availability of data. While the first exascale machines are likely to be built within a single site, the input data is in many cases impossible to store within a single site. Alongside handling of extreme-large amount of data, the exascale system has to process data from different sources, support accelerated computing, handle high volume of requests per day, minimize the size of data flows, and be extensible in terms of continuously increasing data as well as an increase in parallel requests being sent. These technical challenges are addressed by the general reference exascale architecture. It is divided into three main blocks: virtualization layer, distributed virtual file system, and manager of computing resources. Its main property is modularity which is achieved by containerization at two levels: 1) application containers-containerization of scientific workflows, 2) micro-infrastructure-containerization of extreme-large data serviceoriented infrastructure. The paper also presents an instantiation of the reference architecture-the architecture of the PROCESS project (PROviding Computing solutions for ExaScale ChallengeS) and discusses its relation to the reference exascale architecture. The PROCESS architecture has been used as an exascale platform within various exascale pilot applications. This paper also presents performance modelling of exascale platform with its validation 1 .
Next generation sequencing (NGS) produces large volumes of data. To keep the processing time with... more Next generation sequencing (NGS) produces large volumes of data. To keep the processing time within bounds, there is the need to optimize the bioinformatics analysis pipelines. We have been using scientific workflow technology for agile development of analysis pipelines and grid infrastructure to accelerate the processing. Although these methods were successfully applied to a diverse range
Computing and Informatics, 2020
Due to energy limitation and high operational costs, it is likely that exascale computing will no... more Due to energy limitation and high operational costs, it is likely that exascale computing will not be achieved by one or two datacentres but will require many more. A simple calculation, which aggregates the computation power of the 2017 Top500 supercomputers, can only reach 418 petaflops. Companies like Rescale, which claims 1.4 exaflops of peak computing power, describes its infrastructure as composed of 8 million servers spread across 30 datacentres. Any proposed solution to address exascale computing challenges has to take into consideration these facts and by design should aim to support the use of geographically distributed and likely independent datacentres. It should also consider, whenever possible, the co-allocation of the storage with the computation as it would take 3 years to transfer 1 exabyte on a dedicated 100 Gb Ethernet connection. This means we have to be smart about managing data more and more geographically dispersed and spread across different administrative domains. As the natural settings of the PROCESS project is to operate within the European Research Infrastructure and serve the European research communities facing exascale challenges, it is important that PROCESS architecture and solutions are well positioned within the European computing and data management landscape namely PRACE, EGI, and EUDAT. In this paper we propose a scalable and programmable data infrastructure that is easy to deploy and can be tuned to support various data-intensive scientific applications.
In this paper we discuss our efforts in “unlocking” the Long Term Archive (LTA) of the LOFAR radi... more In this paper we discuss our efforts in “unlocking” the Long Term Archive (LTA) of the LOFAR radio telescope using the software ecosystem developed in the PROCESS project. The LTA is a large (> 50 PB) archive that expands with about 7 PB per year by the ingestion of new observations. It consists of coarsely calibrated “visibilities”, i.e. correlations between signals from LOFAR stations. Converting these observations into sky maps (images), which are needed for astronomy research, can be challenging due to the data sizes of the observations and the complexity and compute requirements of the software involved. Using the PROCESS software environment and testbed, we enable a simple point-and-clickreduction of LOFAR observations into sky maps for users of this archive. This work was performed as part of the PROCESS project which aims to provide generalizable open source solutions for user friendly exascale data processing.
Sketch and taxonomies of current performance modeling landscape for GPGPU.A thorough description ... more Sketch and taxonomies of current performance modeling landscape for GPGPU.A thorough description of 10 different approaches to GPU performance modeling.Empirical evaluation of models' performance using three kernels and four GPUs.Discussion of the strengths and weaknesses of the studied model classes. GPUs are gaining fast adoption as high-performance computing architectures, mainly because of their impressive peak performance. Yet most applications only achieve small fractions of this performance. While both programmers and architects have clear opinions about the causes of this performance gap, finding and quantifying the real problems remains a topic for performance modeling tools. In this paper, we sketch the landscape of modern GPUs' performance limiters and optimization opportunities, and dive into details on modeling attempts for GPU-based systems. We highlight the specific features of the relevant contributions in this field, along with the optimization and design sp...
Performance analysis and modeling of applications running on GPUs is still a challenge for most d... more Performance analysis and modeling of applications running on GPUs is still a challenge for most designers and developers. State-of-the-art solutions are dominated by two classic approaches: statistical models that require a lot of training and profiling on existing hardware, and analytical models that require in-depth knowledge of the hardware platform and significant calibration. Both these classes separate the application from the hardware and attempt a high-level combination of the two models for performance prediction. In this work, we propose an orthogonal approach, based on high-level simulation. Specifically, we use Colored Petri Nets (CPN) to model both the hardware and the application. Using this model, the execution of the application is a simulation of the CPN model using warps as tokens. Our prototype implementation of this modeling approach demonstrates promising results on a few case studies on two different GPU architectures: both reasonably accurate predictions and d...
Large experiments on distributed infrastructures become increasingly complex to manage, in partic... more Large experiments on distributed infrastructures become increasingly complex to manage, in particular to trace all computations that gave origin to a piece of data or an event such as an error. The work presented in this paper describes the design and implementation of an architecture to support experiment provenance and its deployment in the concrete case of a particular e-infrastructure for biosciences. The proposed solution consists of: (a) a data provenance repository to capture scientific experiments and their execution path, (b) a software tool (crawler) that gathers, classifies, links, and stores the information collected from various sources, and (c) a set of user interfaces through which the end-user can access the provenance data, interpret the results, and trace the sources of failure. The approach is based on an OPM-compliant API, PLIER, that is flexible to support future extensions and facilitates interoperability among heterogeneous application systems.
La visualisation scientifique joue un role fondamental dans l'interpretation des donnees scie... more La visualisation scientifique joue un role fondamental dans l'interpretation des donnees scientifiques et techniques. Avec l'explosion de la taille des donnees consecutivement a l'evolution des instruments de mesure et d'acquisition de donnees, le stockage, la transmission et la visualisation de ces donnees sont devenus des problemes difficiles. Diverses solutions allant des techniques d'optimisation graphique ou de stockage aux algorithmes complexes de multiresolution en passant par les techniques de rendu parallele sont proposees. Pour etre efficaces, certaines applications doivent combiner toutes ces solutions. C'est typiquement le cas de celles de realite virtuelle. En effet, dans ce domaine, les algorithmes de rendu doivent s'adapter aux contraintes fortes et simultanees d'interaction temps-reel et d'immersion pour offrir un realisme convaincant a l'utilisateur. Dans cette these, nous proposons une methode parallele de gestion interactive...
2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2016
Proceedings of the ACM International Conference on Computing Frontiers - CF '16, 2016
2014 IEEE Intl Conf on High Performance Computing and Communications, 2014 IEEE 6th Intl Symp on Cyberspace Safety and Security, 2014 IEEE 11th Intl Conf on Embedded Software and Syst (HPCC,CSS,ICESS), 2014
Studies in Health Technology and Informatics, 2012
2011 IEEE Seventh International Conference on eScience, 2011
Lecture Notes in Computer Science, 2014
Uploads
Papers by Souley Madougou