research
∙
11/16/2021
Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks
Despite the recent success of Graph Neural Networks (GNNs), training GNN...
share
research
∙
09/16/2021
Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs
Machine/deep-learning (ML/DL) based techniques are emerging as a driving...
research
∙
04/11/2021
GraphGuess: Approximate Graph Processing System with Adaptive Correction
Graph-based data structures have drawn great attention in recent years. ...
research
∙
08/28/2020
Fifer: Tackling Underutilization in the Serverless Era
Datacenters are witnessing a rapid surge in the adoption of serverless f...
research
∙
04/30/2018
Holistic Management of the GPGPU Memory Hierarchy to Manage Warp-level Latency Tolerance
In a modern GPU architecture, all threads within a warp execute the same...
research
∙
05/12/2017
Sprinkler: Maximizing Resource Utilization in Many-Chip Solid State Disks
Resource utilization is one of the emerging problems in many-chip SSDs. ...
research
∙
04/17/2017