BiN: a buffer-in-NUCA scheme for accelerator-rich CMPs

@inproceedings{Cong2012BiNAB,
  title={BiN: a buffer-in-NUCA scheme for accelerator-rich CMPs},
  author={Jason Cong and Mohammad Ali Ghodrat and Michael Gill and Chunyue Liu and Glenn Reinman},
  booktitle={ISLPED '12},
  year={2012}
}
As the number of on-chip accelerators grows rapidly to improve power-efficiency, the buffer size required by accelerators drastically increases. Existing solutions allow the accelerators to share a common pool of buffers or/and allocate buffers in cache. In this paper we propose a Buffer-in-NUCA (BiN) scheme with the following contributions: (1) a dynamic interval-based global buffer allocation method to assign shared buffer spaces to accelerators that can best utilize the additional buffer… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 19 CITATIONS

On-chip interconnection network for accelerator-rich architectures

  • 2015 52nd ACM/EDAC/IEEE Design Automation Conference (DAC)
  • 2015
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS

Accelerator-rich CMPs: From concept to real hardware

  • 2013 IEEE 31st International Conference on Computer Design (ICCD)
  • 2013
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS

Improving scalability of chip-multiprocessors with many HW ACCelerators

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Alleviating Scalability Limitation of Accelerator-Based Platforms

  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-3 OF 3 REFERENCES

Simics: A Full System Simulation Platform

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Buffer-Integrated-Cache: A cost-effective SRAM architecture for handheld and embedded platforms

  • 2011 48th ACM/EDAC/IEEE Design Automation Conference (DAC)
  • 2011
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL