Abstract | ||
---|---|---|
Datacenters consolidate diverse applications to improve utilization. However when multiple applications are co-located on such platforms, contention for shared resources like Networks-on-Chip (NoCs) can degrade the performance of latency-critical online services (high-priority applications). Recently proposed bufferless NoCs have the advantages of requiring less area and power, but they pose challenges in quality-of-service (QoS) support, which usually relies on buffer-based virtual channels (VCs). We propose QBLESS, a QoS-aware bufferless NoC scheme for datacenters. QBLESS consists of two components: a routing mechanism (QBLESS-R) that can substantially reduce flit deflection for high-priority applications, and a congestion-control mechanism (QBLESS-CC) that guarantees performance for high-priority applications and improves overall system throughput. We use trace-driven simulation to model a 64-core system, finding that when compared to BLESS, a previous state-of-the-art bufferless NoC design, QBLESS improves performance of high-priority applications by an average of 33.2%. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/IWQoS.2014.6914305 | IWQoS |
Keywords | Field | DocType |
networks-on-chip (nocs),network routing,computer centres,congestion control,quality of service,qbless-cc,networks-on-chip,qos,quality-of-service support,latency-critical online services,congestion-control mechanism,qos-aware bufferless noc scheme,routing mechanism,datacenters,network-on-chip,qos support,cloud computing,buffer-based virtual channels,qbless-r,routing,registers,network on chip,throughput | Qos aware,Computer science,Network routing,Computer network,Network on a chip,Quality of service,Communication channel,Real-time computing,Network congestion,Throughput,Distributed computing,Cloud computing | Conference |
Citations | PageRank | References |
0 | 0.34 | 17 |
Authors | ||
8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhicheng Yao | 1 | 4 | 1.13 |
Xiufeng Sui | 2 | 27 | 5.83 |
Tianni Xu | 3 | 4 | 1.08 |
Jiuyue Ma | 4 | 0 | 0.34 |
Fang Juan | 5 | 9 | 4.63 |
Sally A. Mckee | 6 | 1928 | 152.59 |
Binzhang Fu | 7 | 0 | 0.34 |
Yungang Bao | 8 | 361 | 31.11 |