A GPGPU Transparent Virtualization Component for High Performance Computing Clouds

Giunta, Giulio; Montella, Raffaele; Agrillo, G.; Coviello, Giuseppe

doi:10.1007/978-3-642-15277-1_37

Cited by 161 publications

(117 citation statements)

References 7 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, GViM is designed to be used on VMs so that applications executed on them can access GPUs located in the real host; GViM does not support the access of GPUs in remote nodes. gVirtuS [24] supports CUDA 2.3 an again implements only a small portion of the runtime API. For example, in the case of the memory management module, it implements only 17 out of the 37 available functions.…”

Section: Related Workmentioning

confidence: 99%

Multi-tenant virtual GPUs for optimising performance of a financial risk application

Prades

Varghese

Reaño

et al. 2017

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

Graphics Processing Units (GPUs) are becoming popular accelerators in modern High-Performance Computing (HPC) clusters. Installing GPUs on each node of the cluster is not efficient resulting in high costs and power consumption as well as underutilisation of the accelerator. The research reported in this paper is motivated towards the use of few physical GPUs by providing cluster nodes access to remote GPUs on-demand for a financial risk application. We hypothesise that sharing GPUs between several nodes, referred to as multi-tenancy, reduces the execution time and energy consumed by an application. Two data transfer modes between the CPU and the GPUs, namely concurrent and sequential, are explored. The key result from the experiments is that multi-tenancy with few physical GPUs using sequential data transfers lowers the execution time and the energy consumed, thereby improving the overall performance of the application.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-tenant virtual GPUs for optimising performance of a financial risk application

Prades

Varghese

Reaño

et al. 2017

Journal of Parallel and Distributed Computing

View full text Add to dashboard Cite

show abstract

“…In addition, several remote GPU virtualization solutions exist for this framework, such as GridCuda [15], DS-CUDA [18], gVirtuS [4], vCUDA [25], GViM [5], and rCUDA [19]. Figure 1 depicts the architecture underlying most of these virtualization solutions, which follow a client-server distributed approach.…”

Section: Remote Gpu Virtualizationmentioning

confidence: 99%

Remote GPU Virtualization: Is It Useful?

Silla

Prades

Iserte

et al. 2016

2016 2nd IEEE International Workshop on High-Performance Interconnection Networks in the Exascale and Big-Data Era (HiPINEB)

View full text Add to dashboard Cite

Abstract-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 space requirements. Also, GPUs still require some amount of energy while idle and their utilization is usually low.In a similar way to virtual machines, using virtual GPUs may address the mentioned concerns. In this regard, remote GPU virtualization allows to share the GPUs present in the computing facility among the nodes of the cluster. This would increase overall GPU utilization, thus reducing the negative impact of the increased costs mentioned before. Reducing the amount of GPUs installed in the cluster could also be possible.In this paper we explore some of the benefits that remote GPU virtualization brings to clusters. For instance, this mechanism allows an application to use all the GPUs present in a cluster. Another benefit of this technique is that cluster throughput, measured as jobs completed per time unit, is doubled when this technique is used. Furthermore, in addition to increasing overall GPU utilization, total energy consumption is reduced up to 40%. This may be key in the context of exascale computing facilities, which present an important energy constraint.

show abstract

“…gVirtuS (GPU Virtualization Service) is our result in GPGPUs transparent virtualization targeting mainly the use of nVIDIA CUDA based accelerator boards through virtual machines instanced to accelerate scientific computations [45]. The basic virtualization idea is based on a split driver approach [37] in which a front-end is deployed on the virtual machine image and a back-end is hosted on the real machine.…”

Section: Gvirtus Architecture and Designmentioning

confidence: 99%

A GPU Accelerated High Performance Cloud Computing Infrastructure for Grid Computing Based Virtual Environmental Laboratory

Giunta¹,

Montella²,

Laccetti³

et al. 2011

Advances in Grid Computing

Self Cite

View full text Add to dashboard Cite

A GPGPU Transparent Virtualization Component for High Performance Computing Clouds

Cited by 161 publications

References 7 publications

Multi-tenant virtual GPUs for optimising performance of a financial risk application

Multi-tenant virtual GPUs for optimising performance of a financial risk application

Remote GPU Virtualization: Is It Useful?

A GPU Accelerated High Performance Cloud Computing Infrastructure for Grid Computing Based Virtual Environmental Laboratory

Contact Info

Product

Resources

About