Software-Hardware Codesign for Machine Learning Workloads, a Workshop at MLSyS 2020SEI Speaking Workshop
Mar 4, 2020 · Austin, TX
Bridging the Gap Between Software and Hardware
Machine learning development workflows today involve the siloed design and optimization of task-specific software for a limited number of fixed hardware options. As a result, hardware and software are seen as individual components where the impact of either SW or HW on each other cannot be optimized or assessed jointly. This abstraction leads to computationally inefficient machine learning workloads.