English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The High Performance Computing (HPC) field is witnessing a widespreadadoption of Graphics Processing Units (GPUs) as co-processors for conventionalhomogeneous clusters. The adoption of prevalent Single- Program Multiple-Data(SPMD) programming paradigm for GPU-based parallel processing brings in thechallenge of resource underutilization, with the asymmetricalprocessor/co-processor distribution. In other words, under SPMD, balancedCPU/GPU distribution is required to ensure full resource utilization. In thispaper, we propose a GPU resource virtualization approach to allow underutilizedmicroprocessors to effi- ciently share the GPUs. We propose an efficient GPUsharing scenario achieved through GPU virtualization and analyze theperformance potentials through execution models. We further present theimplementation details of the virtualization infrastructure, followed by theexperimental analyses. The results demonstrate considerable performance gainswith GPU virtualization. Furthermore, the proposed solution enables fullutilization of asymmetrical resources, through efficient GPU sharing amongmicroprocessors, while incurring low overhead due to the added virtualizationlayer.

Efficient Resource Sharing Through GPU Virtualization on Accelerated High Performance Computing Systems