Using PCI Pass-Through for GPU Virtualization with CUDA

Abstract : Nowadays, NVIDIA’s CUDA is a general purpose scalable parallel programming model for writing highly parallel applications. It provides several key abstractions – a hierarchy of thread blocks, shared memory, and barrier synchronization. This model has proven quite successful at programming multithreaded many core GPUs and scales transparently to hundreds of cores: scientists throughout industry and academia are already using CUDA to achieve dramatic speedups on production and research codes. GPU-base clusters are likely to play an important role in future cloud data centers, because some compute-intensive applications may require both CPUs and GPUs. The goal of this paper is to develop a VM execution mechanism that could run these applications inside VMs and allow them to effectively leverage GPUs in such a way that different VMs can share GPUs without interfering with one another.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-01551356
Contributor : Hal Ifip <>
Submitted on : Friday, June 30, 2017 - 10:36:06 AM
Last modification on : Friday, December 1, 2017 - 1:09:57 AM
Long-term archiving on : Monday, January 22, 2018 - 7:33:16 PM

File

978-3-642-35606-3_53_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Chao-Tung Yang, Hsien-Yi Wang, Yu-Tso Liu. Using PCI Pass-Through for GPU Virtualization with CUDA. 9th International Conference on Network and Parallel Computing (NPC), Sep 2012, Gwangju, South Korea. pp.445-452, ⟨10.1007/978-3-642-35606-3_53⟩. ⟨hal-01551356⟩

Share

Metrics

Record views

175

Files downloads

691