Parallélisation d'opérateurs de TI : multi-cœurs, Cell ou GPU ?
نویسندگان
چکیده
منابع مشابه
Parallélisation d'opérateurs de TI : multi-curs, Cell ou GPU ?
This article deals with a performance analysis of eight current architectures : general purpose multi-core processors, graphic processing units and the Cell processor. The benched algorithm is the Harris operator. The main goal is to guide the user in chosing a parallel architecture and to assess how different transformations impact so as to get an architecture optimised implementation.
متن کاملAlgorithmes de reconnaissance NCTR et parallélisation sur GPU
In this paper, first, we present the problem of Non Cooperative Target Recognition (NCTR) as a supervised classification problem. After a presentation on the radar acquisition system of range profiles and the problem of recognition, followed by a statistical study of data, we use a classical classification method of K Nearest Neighbors (KNN) to do this classification. We explore and compare the...
متن کاملProposition De Stage Et / Ou De These »
Résumé: Recent progresses in the characterization of physical properties of viruses allows for the first time to investigate distinct virus cycle events at the single particle level [1]. Using an original combination of experimental approaches based on Atomic Force Microscopy (AFM) and statistical physics modelization, we propose to study the physical properties of Adeno-Associated Virus (AAV) ...
متن کاملAnalyse pire cas pour processeur multi-cœurs disposant de caches partagés
Hard real-time systems are subject to timing constraints and failure to respectthem can cause economic, ecological or human disasters. The validation processwhich guarantees the safety of such software, by ensuring the respect of theseconstraints in all situations including the worst case, is based on the knowledgeof the worst case execution time of each task. However, determini...
متن کاملÉtat de l’art des simulations multi-agents sur GPU
There are many tools for doing multi-agent based simulations (MABS) on CPU. However, computation time and resource increases so much with the number of entities that the CPU cannot support this inflation and an appealing solution is to use GPGPU. Inexpensive and powerful, this technology has one big issue : It’s programming difficulty which limits the accessibility and the reusability. In this ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Traitement du signal
سال: 2010
ISSN: 0765-0019
DOI: 10.3166/ts.27.161-187