activity
20182022
most citedReducing Activation Recomputation in Large Transformer Models

55 citations · 60 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG202255 cited

Reducing Activation Recomputation in Large Transformer Models

Vijay Korthikanti, Jared Casper, Sangkug Lym +4

Training large transformer models is one of the most important computational challenges of modern AI. In this paper, we show how to significantly accelerate training of large trans…

cs.LG20205 cited

FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training

Sangkug Lym, Mattan Erez

Modern deep learning models have high memory and computation cost. To make them fast and memory-cost efficient, structured model pruning is commonly used. We find that pruning a mo…

cs.AR2019

Near Data Acceleration with Concurrent Host Access

Benjamin Y. Cho, Yongkee Kwon, Sangkug Lym +1

Near-data accelerators (NDAs) that are integrated with main memory have the potential for significant power and performance benefits. Fully realizing these benefits requires the la…

cs.DC2019

DeLTA: GPU Performance Model for Deep Learning Applications with In-depth Memory System Traffic Analysis

Sangkug Lym, Donghyuk Lee, Mike O'Connor +2

Training convolutional neural networks (CNNs) requires intense compute throughput and high memory bandwidth. Especially, convolution layers account for the majority of the executio…

cs.LG2019

PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration

Sangkug Lym, Esha Choukse, Siavash Zangeneh +3

State-of-the-art convolutional neural networks (CNNs) used in vision applications have large models with numerous weights. Training these models is very compute- and memory-resourc…

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…