Local and remote GPUs perform similar with EDR 100G InfiniBand

C Reaño, F Silla, G Shainer, S Schultz - … of the Industrial Track of the …, 2015 - dl.acm.org
The use of graphics processing units (GPUs) to accelerate some portions of applications is
widespread nowadays. To avoid the usual inconveniences associated with these …

DRMaestro: orchestrating disaggregated resources on virtualized data-centers

M Amaral, J Polo, D Carrera, N Gonzalez… - Journal of cloud …, 2021 - Springer
Modern applications demand resources at an unprecedented level. In this sense, data-
centers are required to scale efficiently to cope with such demand. Resource disaggregation …

Remote gpu virtualization: Is it useful?

F Silla, J Prades, S Iserte… - 2016 2nd IEEE …, 2016 - ieeexplore.ieee.org
Graphics Processing Units (GPUs) are currently used in many computing facilities. However,
GPUs present several side effects, such as increased acquisition costs as well as larger …

MultiCL: Enabling automatic scheduling for task-parallel workloads in OpenCL

AM Aji, AJ Peña, P Balaji, W Feng - Parallel Computing, 2016 - Elsevier
The OpenCL specification tightly binds a command queue to a specific device. For best
performance, the user has to find the ideal queue-device mapping at command queue …

On the benefits of the remote GPU virtualization mechanism: The rCUDA case

F Silla, S Iserte, C Reaño… - … and Computation: Practice …, 2017 - Wiley Online Library
Graphics processing units (GPUs) are being adopted in many computing facilities given their
extraordinary computing power, which makes it possible to accelerate many general …

Increasing the performance of data centers by combining remote GPU virtualization with Slurm

S Iserte, J Prades, C Reaño… - 2016 16th IEEE/ACM …, 2016 - ieeexplore.ieee.org
The use of Graphics Processing Units (GPUs) presents several side effects, such as
increased acquisition costs as well as larger space requirements. Furthermore, GPUs …

Automatic command queue scheduling for task-parallel workloads in opencl

AM Aji, AJ Pena, P Balaji… - 2015 IEEE International …, 2015 - ieeexplore.ieee.org
OpenCL is a portable interface that can be used to program cluster nodes with
heterogeneous compute devices. The OpenCL specification tightly binds its workflow …

Affect-expressive movement generation with factored conditional restricted boltzmann machines

O Alemi, W Li, P Pasquier - 2015 International Conference on …, 2015 - ieeexplore.ieee.org
The expressivity of virtual, animated agents plays an important role in their believability.
While the planning and goal-oriented aspects of agent movements have been addressed in …

Improving the management efficiency of GPU workloads in data centers through GPU virtualization

S Iserte, J Prades, C Reaño… - … and Computation: Practice …, 2021 - Wiley Online Library
Graphics processing units (GPUs) are currently used in data centers to reduce the execution
time of compute‐intensive applications. However, the use of GPUs presents several side …

Reducing the performance gap of remote GPU virtualization with InfiniBand Connect-IB

C Reaño, F Silla - 2016 IEEE symposium on computers and …, 2016 - ieeexplore.ieee.org
GPU accelerators may provide great performance improvements in the context of parallel
applications. However, their use in HPC clusters may also present some disadvantages …