The recent growth in the number of precessing units in today's multicore processor architectures enables multiple threads to execute simultanesiouly achieving better performances by exploiting thread level parallelism. With the architectural complexity of these new state of the art designs, comes a need to better understand the interactions between the operating system layers, the applications and the underlying hardware platforms. The ability to characterise and to quantify those interactions can be useful in the processes of performance evaluation and analysis, compiler optimisations and operating system job scheduling allowing to achieve better performance stability, reproducibility and predictability. We consider in our study performanc...
International audienceThis report presents a study of techniques used to speedup a scientific simula...
Through the past several decades, based on the Moore's law, the semiconductor industry was doubling ...
Mapping applications onto heterogeneous platforms is a difficult challenge, even for simple applicat...
Since several years, classical multiprocessor systems have evolved to multicores, which tightly inte...
The recent growth in the number of precessing units in today's multicore processor architectures ena...
Performance analysis is the task of monitor the behavior of a program execution. The main goal is to...
With the increase in the integration of functions, modern embedded systems have become very smart an...
International audienceIn [8], we demonstrated that contrary to sequential applications, parallel Ope...
In this thesis, we address the problem of schedulers for multi-core architectures from several persp...
The significant increase of the hardware complexity that occurred in the last few years led the high...
Increasing processors' clock frequency has traditionally been one of the largest drivers of performa...
Hardware performance monitoring counters have recently received a lot of attention. They have been u...
Rinnakkaisohjelmointi on tullut moniydin- ja moniprosessorijärjestelmien suosion myötä pinnalle. Rin...
Next generation high performance computers will massively use virtualization as a way to share hardw...
NUMA nodes are potentially powerful but taking benefit of their capabilities is challenging due to t...
International audienceThis report presents a study of techniques used to speedup a scientific simula...
Through the past several decades, based on the Moore's law, the semiconductor industry was doubling ...
Mapping applications onto heterogeneous platforms is a difficult challenge, even for simple applicat...
Since several years, classical multiprocessor systems have evolved to multicores, which tightly inte...
The recent growth in the number of precessing units in today's multicore processor architectures ena...
Performance analysis is the task of monitor the behavior of a program execution. The main goal is to...
With the increase in the integration of functions, modern embedded systems have become very smart an...
International audienceIn [8], we demonstrated that contrary to sequential applications, parallel Ope...
In this thesis, we address the problem of schedulers for multi-core architectures from several persp...
The significant increase of the hardware complexity that occurred in the last few years led the high...
Increasing processors' clock frequency has traditionally been one of the largest drivers of performa...
Hardware performance monitoring counters have recently received a lot of attention. They have been u...
Rinnakkaisohjelmointi on tullut moniydin- ja moniprosessorijärjestelmien suosion myötä pinnalle. Rin...
Next generation high performance computers will massively use virtualization as a way to share hardw...
NUMA nodes are potentially powerful but taking benefit of their capabilities is challenging due to t...
International audienceThis report presents a study of techniques used to speedup a scientific simula...
Through the past several decades, based on the Moore's law, the semiconductor industry was doubling ...
Mapping applications onto heterogeneous platforms is a difficult challenge, even for simple applicat...