Technological limitations faced by the semi-conductor manufacturers in the early 2000's restricted the increase in performance of the sequential computation units. Nowadays, the trend is to increase the number of processor cores per socket and to progressively use the GPU cards for highly parallel computations. Complexity of the recent architectures makes it difficult to statically predict the performance of a program. We describe a reliable and accurate parallel loop nests execution time prediction method on GPUs based on three stages: static code generation, offline profiling, and online prediction. In addition, we present two techniques to fully exploit the computing resources at disposal on a system. The first technique consists in join...
GPUs have become popular due to their high computational power. Data scientists rely on GPUs to proc...
In the field of high performance computing, the architectures evolve continuously. In order to incre...
The GPU-based heterogeneous architectures (e.g., Tianhe-1A, Nebulae), composing multi-core CPU and G...
Technological limitations faced by the semi-conductor manufacturers in the early 2000's restricted t...
Technological limitations faced by the semi-conductor manufacturers in the early 2000's restricted t...
Les verrous technologiques rencontrés par les fabricants de semi-conducteurs au début des années deu...
International audienceWe contribute a method to jointly use CPU and GPU in order to execute a balanc...
International audienceIt is often hard to predict the performance of a statically generated code. Ha...
Current Graphics Processing Units (GPUs) are high-performance, low-cost parallel processors. This ma...
In this thesis work, we have mainly worked on two topics of GPU performance analysis. First, we hav...
Recent advances in GPUs (graphics processing units) lead to mas-sively parallel hardware that is eas...
Graphics processor units (GPUs) today can be used for computations that go beyond graphics and such...
Abstract. Using Graphics Processing Units (GPUs) to solve general purpose problems has received sign...
GPUs have become popular due to their high computational power. Data scientists rely on GPUs to proc...
Since the beginning of the 2000s, the raw performance of processors stopped its exponential increase...
GPUs have become popular due to their high computational power. Data scientists rely on GPUs to proc...
In the field of high performance computing, the architectures evolve continuously. In order to incre...
The GPU-based heterogeneous architectures (e.g., Tianhe-1A, Nebulae), composing multi-core CPU and G...
Technological limitations faced by the semi-conductor manufacturers in the early 2000's restricted t...
Technological limitations faced by the semi-conductor manufacturers in the early 2000's restricted t...
Les verrous technologiques rencontrés par les fabricants de semi-conducteurs au début des années deu...
International audienceWe contribute a method to jointly use CPU and GPU in order to execute a balanc...
International audienceIt is often hard to predict the performance of a statically generated code. Ha...
Current Graphics Processing Units (GPUs) are high-performance, low-cost parallel processors. This ma...
In this thesis work, we have mainly worked on two topics of GPU performance analysis. First, we hav...
Recent advances in GPUs (graphics processing units) lead to mas-sively parallel hardware that is eas...
Graphics processor units (GPUs) today can be used for computations that go beyond graphics and such...
Abstract. Using Graphics Processing Units (GPUs) to solve general purpose problems has received sign...
GPUs have become popular due to their high computational power. Data scientists rely on GPUs to proc...
Since the beginning of the 2000s, the raw performance of processors stopped its exponential increase...
GPUs have become popular due to their high computational power. Data scientists rely on GPUs to proc...
In the field of high performance computing, the architectures evolve continuously. In order to incre...
The GPU-based heterogeneous architectures (e.g., Tianhe-1A, Nebulae), composing multi-core CPU and G...