24373

Efficient Nearest-Neighbor Data Sharing in GPUs

Negin Nematollahi, Mohammad Sadrosadati, Hajar Falahati, Marzieh Barkhordar, Mario Paulo Drumond, Hamid Sarbazi-Azad, Babak Falsafi
Department of Computer Engineering, Sharif University of Technology, Iran
ACM Transactions on Architecture and Code Optimization, Vol. 18, No.6, 2020

@article{10.1145/3429981,

   author={Nematollahi, Negin and Sadrosadati, Mohammad and Falahati, Hajar and Barkhordar, Marzieh and Drumond, Mario Paulo and Sarbazi-Azad, Hamid and Falsafi, Babak},

   title={Efficient Nearest-Neighbor Data Sharing in GPUs},

   year={2021},

   issue_date={January 2021},

   publisher={Association for Computing Machinery},

   address={New York, NY, USA},

   volume={18},

   number={1},

   issn={1544-3566},

   url={https://doi.org/10.1145/3429981},

   doi={10.1145/3429981}

}

Download Download (PDF)   View View   Source Source   

1509

views

Stencil codes (a.k.a. nearest-neighbor computations) are widely used in image processing, machine learning, and scientific applications. Stencil codes incur nearest-neighbor data exchange because the value of each point in the structured grid is calculated as a function of its value and the values of a subset of its nearest-neighbor points. When running on Graphics Processing Unit (GPUs), stencil codes exhibit a high degree of data sharing between nearest-neighbor threads. Sharing is typically implemented through shared memories, shuffle instructions, and on-chip caches and often incurs performance overheads due to the redundancy in memory accesses. In this article, we propose Neighbor Data (NeDa), a direct nearest-neighbor data sharing mechanism that uses two registers embedded in each streaming processor (SP) that can be accessed by nearest-neighbor SP cores. The registers are compiler-allocated and serve as a data exchange mechanism to eliminate nearest-neighbor shared accesses. NeDa is embedded carefully with local wires between SP cores so as to minimize the impact on density. We place and route NeDa in an open-source GPU and show a small area overhead of 1.3%. The cycle-accurate simulation indicates an average performance improvement of 21.8% and power reduction of up to 18.3% for stencil codes in General-Purpose Graphics Processing Unit (GPGPU) standard benchmark suites. We show that NeDa’s performance is within 13.2% of an ideal GPU with no overhead for nearest-neighbor data exchange.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: