research
∙
05/10/2022
Reducing Activation Recomputation in Large Transformer Models
Training large transformer models is one of the most important computati...
share
research
∙
04/27/2020
FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training
Modern deep learning models have high memory and computation cost. To ma...
research
∙
08/18/2019
CHoNDA: Near Data Acceleration with Concurrent Host Access
Near-data accelerators (NDAs) that are integrated with main memory have ...
research
∙
04/02/2019
DeLTA: GPU Performance Model for Deep Learning Applications with In-depth Memory System Traffic Analysis
Training convolutional neural networks (CNNs) requires intense compute t...
research
∙
01/26/2019
PruneTrain: Gradual Structured Pruning from Scratch for Faster Neural Network Training
Model pruning is a popular mechanism to make a network more efficient fo...
research
∙
09/30/2018