[EN] About a decade ago, Graphics Processing Units (GPU) started to be used not only for graphics visualization, but also for accelerating scientific applications. However, its use for this aim presents several drawbacks such as increased costs and energy consumption, which combined with the low utilization rate of these accelerators have led to a growing interest in sharing remote GPUs concurrently among several nodes of a cluster. On the other hand, the current trend in many computing facilities is to use virtual machines in order to make a more efficient use of overall resources. Nevertheless, current software for creating virtual machine environments, such as Kernel Virtual Machine (KVM) or Xen, does not easily provide GPUs to applicati...
Directive-based programming models, such as OpenMP, OpenACC, and OmpSs, enable users to accelerate a...
Directive-based programming models, such as OpenMP, OpenACC, and OmpSs, enable users to accelerate a...
Abstract—Many current high-performance clusters include one or more GPUs per node in order to dramat...
International audienceThere is a trend towards using graphics processing units (GPUs) not only for g...
Graphics processing units (GPUs) are being adopted in many computing facilities given their extraord...
© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...
[EN] The use of Graphics Processing Units (GPUs) has become a very popular way to accelerate the exe...
2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all...
The hardware and software advances of Graphics Processing Units (GPUs) have favored the development ...
The hardware and software advances of Graphics Processing Units (GPUs) have favored the development ...
Graphics Processing Units (GPUs) are currently used in many computing facilities. However, GPUs pres...
Graphics Processing Units (GPUs) are currently used in many computing facilities. However, GPUs pres...
The final publication is available at Springer via http://dx.doi.org/ 10.1007/s11227-016-1754-3In t...
The final publication is available at Springer via http://dx.doi.org/ 10.1007/s11227-016-1754-3In t...
Ponencia presentada al 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (C...
Directive-based programming models, such as OpenMP, OpenACC, and OmpSs, enable users to accelerate a...
Directive-based programming models, such as OpenMP, OpenACC, and OmpSs, enable users to accelerate a...
Abstract—Many current high-performance clusters include one or more GPUs per node in order to dramat...
International audienceThere is a trend towards using graphics processing units (GPUs) not only for g...
Graphics processing units (GPUs) are being adopted in many computing facilities given their extraord...
© 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...
[EN] The use of Graphics Processing Units (GPUs) has become a very popular way to accelerate the exe...
2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all...
The hardware and software advances of Graphics Processing Units (GPUs) have favored the development ...
The hardware and software advances of Graphics Processing Units (GPUs) have favored the development ...
Graphics Processing Units (GPUs) are currently used in many computing facilities. However, GPUs pres...
Graphics Processing Units (GPUs) are currently used in many computing facilities. However, GPUs pres...
The final publication is available at Springer via http://dx.doi.org/ 10.1007/s11227-016-1754-3In t...
The final publication is available at Springer via http://dx.doi.org/ 10.1007/s11227-016-1754-3In t...
Ponencia presentada al 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (C...
Directive-based programming models, such as OpenMP, OpenACC, and OmpSs, enable users to accelerate a...
Directive-based programming models, such as OpenMP, OpenACC, and OmpSs, enable users to accelerate a...
Abstract—Many current high-performance clusters include one or more GPUs per node in order to dramat...