Clusters of multicore/GPU nodes connected with a fast network offer very high therotical peak performances, reaching tens of TeraFlops. Unfortunately, the efficient programing of such architectures remains challenging because of their complexity and the diversity of the existing programming models. The purpose of this thesis is to improve the programmability of dense scientific applications on hybrid architectures in three ways: reducing the execution times, processing larger data sets and reducing the programming effort. We propose DSTEP, a directive-based programming model expressing both data and computation distribution. A large set of distribution types are unified in a "dstep distribute" directive and the replication of some distribut...
As single processing unit performance has reached a technological limit, the power wall, the past de...
This thesis introduces a unified framework for various domain decomposition methods:those with overl...
The self-reconfiguration capabilities of modern FPGA architectures pave the way for dynamic applicat...
Clusters of multicore/GPU nodes connected with a fast network offer very high therotical peak perfor...
Heterogeneous architectures have been widely used in the domain of high performance computing. Howev...
Application specific instruction set processors (ASIP) are a well known compromise between the high ...
The development and maintenance of high-performance scientific computing software is a complex task....
This thesis intends to show how to efficiently exploit the parallelism present in applications in or...
We define and study a combinatorial optimization problem that models multi-path routing in a Network...
We define and study a combinatorial optimization problem that models multi-path routing in a Network...
The development and maintenance of high-performance scientific computing software is a complex task....
The development and maintenance of high-performance scientific computing software is a complex task....
The development and maintenance of high-performance scientific computing software is a complex task....
Supercomputing plays an important role in several innovative fields, speeding up prototyping or vali...
On many problems, it is hard to find an algorithm that solves all its instances with the shortest ex...
As single processing unit performance has reached a technological limit, the power wall, the past de...
This thesis introduces a unified framework for various domain decomposition methods:those with overl...
The self-reconfiguration capabilities of modern FPGA architectures pave the way for dynamic applicat...
Clusters of multicore/GPU nodes connected with a fast network offer very high therotical peak perfor...
Heterogeneous architectures have been widely used in the domain of high performance computing. Howev...
Application specific instruction set processors (ASIP) are a well known compromise between the high ...
The development and maintenance of high-performance scientific computing software is a complex task....
This thesis intends to show how to efficiently exploit the parallelism present in applications in or...
We define and study a combinatorial optimization problem that models multi-path routing in a Network...
We define and study a combinatorial optimization problem that models multi-path routing in a Network...
The development and maintenance of high-performance scientific computing software is a complex task....
The development and maintenance of high-performance scientific computing software is a complex task....
The development and maintenance of high-performance scientific computing software is a complex task....
Supercomputing plays an important role in several innovative fields, speeding up prototyping or vali...
On many problems, it is hard to find an algorithm that solves all its instances with the shortest ex...
As single processing unit performance has reached a technological limit, the power wall, the past de...
This thesis introduces a unified framework for various domain decomposition methods:those with overl...
The self-reconfiguration capabilities of modern FPGA architectures pave the way for dynamic applicat...