14.4 A 21.5M-query-vectors/s 3.37nJ/vector reconfigurable k-nearest-neighbor accelerator with adaptive precision in 14nm tri-gate CMOS

@article{Kaul2016144A2,
  title={14.4 A 21.5M-query-vectors/s 3.37nJ/vector reconfigurable k-nearest-neighbor accelerator with adaptive precision in 14nm tri-gate CMOS},
  author={Himanshu Kaul and Mark Anders and Sanu K. Mathew and Gregory K. Chen and Sudhir Satpathy and Steven Hsu and Amit Agarwal and Ram Krishnamurthy},
  journal={2016 IEEE International Solid-State Circuits Conference (ISSCC)},
  year={2016},
  pages={260-261}
}
Energy-efficient k-nearest-neighbor (kNN) computations are key building blocks for computer vision, classification, and machine-learning workloads [1-3]. Determining distances to high-dimensional vectors within a large vector database results in high compute cost. Adaptive precision improves energy efficiency by eliminating a majority of vectors without costly full-precision computation, with as-needed precision refinement to guarantee kNN accuracy of closely matched vectors. A special-purpose… CONTINUE READING

From This Paper

Results and topics from this paper.

Key Quantitative Results

  • latency and 43pJ energy to find each subsequent nearest neighbor, iii) up to 5.2× higher throughput while maintaining full-precision kNN accuracy, iv) 16× search-space reduction for next-nearest neighbor, v) ultra-low voltage operation measured at 360mV, 1.1M vectors/s, 1.44mW, and vi) peak energy efficiency of 1.23nJ/vector at 390mV (near-threshold), 25°C.

Citations

Publications citing this paper.
SHOWING 1-9 OF 9 CITATIONS

Similar Papers

Loading similar papers…