Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization

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.

Demystifying the MLPerf Benchmark Suite

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.

BIG-bench Machine Learning Scheduling