no code implementations • 13 Sep 2021 • Zachary Susskind, Bryce Arden, Lizy K. John, Patrick Stockton, Eugene B. John
We find that symbolic models have less potential parallelism than traditional neural models due to complex control flow and low-operational-intensity operations, such as scalar multiplication and tensor addition.
no code implementations • 24 Aug 2019 • Snehil Verma, Qinzhe Wu, Bagus Hanindhito, Gunjan Jha, Eugene B. John, Ramesh Radhakrishnan, Lizy K. John
We present a study on its characteristics and how the MLPerf benchmarks differ from some of the previous deep learning benchmarks like DAWNBench and DeepBench.