Clumsy Flow Control for High-Throughput Bufferless On-Chip Networks

@article{Kim2013ClumsyFC,
  title={Clumsy Flow Control for High-Throughput Bufferless On-Chip Networks},
  author={Hanjoon Kim and Yonggon Kim and John Kim},
  journal={IEEE Computer Architecture Letters},
  year={2013},
  volume={12},
  pages={47-50}
}
Bufferless on-chip networks are an alternative type of on-chip network organization that can improve the cost-efficiency of an on-chip network by removing router input buffers. However, bufferless on-chip network performance degrades at high load because of the increased network contention and large number of deflected packets. The energy benefit of bufferless network is also reduced because of the increased deflection. In this work, we propose a novel flow control for bufferless on-chip… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • By using a clumsy flow control (CFC), instead of the per-hop flow control that is commonly used in buffered on-chip networks, we are able to reduce the amount of deflection by up to 92% on high-throughput workloads.
  • As a result, on average, CFC can approximately match the performance of a baseline buffered router while reducing the energy consumption by approximately 39%.
  • Our results show that CFC results in 92% reduction in the amount of deflection that occurs in the network, thus, providing a 39% reduction in energy on average, with minimal loss in overall performance.

Citations

Publications citing this paper.
SHOWING 1-10 OF 21 CITATIONS

Towards High-Performance Bufferless NoCs with SCEPTER

  • IEEE Computer Architecture Letters
  • 2016
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Design and Evaluation of Hierarchical Rings with Deflection Routing

  • 2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing
  • 2014
VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Pipelined chipper based noc for performance enhancement

  • 2017 International Conference on Networks & Advances in Computational Technologies (NetACT)
  • 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 13 REFERENCES

CHIPPER: A low-complexity bufferless deflection router

  • 2011 IEEE 17th International Symposium on High Performance Computer Architecture
  • 2011
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Throughput-Effective On-Chip Networks for Manycore Accelerators

  • 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture
  • 2010
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Analyzing CUDA workloads using a detailed GPU simulator

  • 2009 IEEE International Symposium on Performance Analysis of Systems and Software
  • 2009
VIEW 1 EXCERPT

Rodinia: A benchmark suite for heterogeneous computing

  • 2009 IEEE International Symposium on Workload Characterization (IISWC)
  • 2009
VIEW 1 EXCERPT

SCARAB: A single cycle adaptive routing and bufferless network

  • 2009 42nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)
  • 2009
VIEW 3 EXCERPTS

Similar Papers

Loading similar papers…