activity
20182026
most citedAccelerating Bandwidth-Bound Deep Learning Inference with Main-Memory Accelerators

9 citations · 20 across the 13 of their papers we have counts for

collaborators
Showing 2018Show all

1 paper · 1 filter

cs.LG2018

Mini-batch Serialization: CNN Training with Inter-layer Data Reuse

Sangkug Lym, Armand Behroozi, Wei Wen +3

Training convolutional neural networks (CNNs) requires intense computations and high memory bandwidth. We find that bandwidth today is over-provisioned because most memory accesses…