A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is
In this work, we propose Bounded Staled Sync (BSSync), a hardware support for the bounded staleness consistency model, which accompanies simple logic layers in the memory hierarchy. ... BSSync overlaps the long latency atomic operation with the main computation, targeting iterative convergent machine learning workloads. ... Bounded Staleness Consistency Model BSSync supports the bounded staleness consistency model  to reduce the atomic operation overhead. ...doi:10.1109/pact.2015.42 dblp:conf/IEEEpact/LeeSK15 fatcat:ey5nkob5uvgq3imfydkz5ist44
We conclude that employing near-memory acceleration solutions for weather prediction modeling is promising as a means to achieve both high performance and high energy efficiency. ... To overcome these challenges, we propose and evaluate the use of near-memory acceleration using a reconfigurable fabric with high-bandwidth memory (HBM). ... Lee et al., “BSSync: Processing Near Memory for Machine Learning Work-  A. ...arXiv:2009.08241v1 fatcat:mj6kwwbhhne5xa7y2ilppi3ora