MLPerf Inference Benchmark

@article{Reddi2020MLPerfIB,
  title={MLPerf Inference Benchmark},
  author={V. Reddi and Christine Cheng and D. Kanter and P. Mattson and Guenther Schmuelling and Carole-Jean Wu and B. Anderson and Maximilien Breughe and Mark Charlebois and W. Chou and R. Chukka and Cody A. Coleman and S. Davis and P. Deng and Greg Diamos and J. Duke and D. Fick and J. Gardner and Itay Hubara and S. Idgunji and T. Jablin and Jeff Jiao and T. John and Pankaj Kanwar and D. Lee and Jeffery Liao and Anton Lokhmotov and F. Massa and P. Meng and P. Micikevicius and C. Osborne and Gennady Pekhimenko and A. Rajan and Dilip Sequeira and Ashish Sirasao and Fei Sun and Hanlin Tang and M. Thomson and F. Wei and E. Wu and Lingjie Xu and K. Yamada and B. Yu and George Yuan and Aaron Zhong and P. Zhang and Y. Zhou},
  journal={2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA)},
  year={2020},
  pages={446-459}
}
  • V. Reddi, Christine Cheng, +44 authors Y. Zhou
  • Published 2020
  • Computer Science, Mathematics
  • 2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture (ISCA)
  • Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and five orders of magnitude in performance; they range from embedded devices to data-center solutions. Fueling the hardware are a dozen or more software frameworks and… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 27 CITATIONS, ESTIMATED 100% COVERAGE

    Missing the Forest for the Trees: End-to-End AI Application Performance in Edge Data Centers

    VIEW 3 EXCERPTS
    CITES BACKGROUND

    SMAUG: End-to-End Full-Stack Simulation Infrastructure for Deep Learning Workloads

    VIEW 1 EXCERPT
    CITES METHODS

    DeepRecSys: A System for Optimizing End-To-End At-Scale Neural Recommendation Inference

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Benchmarking TinyML Systems: Challenges and Direction

    VIEW 1 EXCERPT
    CITES BACKGROUND

    AIBench: Scenario-distilling AI Benchmarking

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2019
    2020

    CITATION STATISTICS

    • 2 Highly Influenced Citations

    • Averaged 14 Citations per year from 2019 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 79 REFERENCES

    MLPerf Training Benchmark

    VIEW 4 EXCERPTS

    Benchmarking and Analyzing Deep Neural Network Training

    Fathom: reference workloads for modern deep learning methods

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    EIE: Efficient Inference Engine on Compressed Deep Neural Network

    TensorFlow: A system for large-scale machine learning

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    AI Benchmark: All About Deep Learning on Smartphones in 2019

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL