Abstract | ||
---|---|---|
GPGPU can boost the performance significantly for many compute intensive tasks. However, in datacenter scenarios, not all the applications need GPGPU. Thus, it is not necessary to equip GPGPU in each node considering its high price and infrequent usage demands. By leveraging high bandwidth of emerging interconnect like 100Gb Ethernet, PCI Express or RapidIO etc., it is reasonable to figure out a mechanism to allow nodes to share the remote GPGPUs. In this work, we proposed V-OpenCL, which supports transparently using of remote GPGPU in data center. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2464996.2467289 | I4CS |
Keywords | Field | DocType |
remote gpgpu,datacenter scenario,intensive task,data center,pci express,remote gpgpus,infrequent usage demand,high price,high bandwidth,datacenter,virtualization | Virtualization,Computer science,Parallel computing,Real-time computing,RapidIO,Ethernet,General-purpose computing on graphics processing units,PCI Express,Interconnection,Data center,Operating system,High bandwidth | Conference |
Citations | PageRank | References |
1 | 0.40 | 0 |
Authors | ||
3 |