353 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Hewlett Packard Enterprise (Ireland)IE11 papers
- Hewlett-Packard (United States)US10 papers
- Nanyang Technological UniversitySG6 papers
- Forschungszentrum JülichDE5 papers
- Stanford UniversityUS5 papers
- Georgia Institute of TechnologyUS4 papers
- RWTH Aachen UniversityDE4 papers
- The University of Texas at AustinUS4 papers
- University of California, BerkeleyUS4 papers
- Aalto UniversityFI3 papers
- Carnegie Mellon UniversityUS3 papers
- Centre National de la Recherche ScientifiqueFR3 papers
7 papers · 1 filter
On Hardware-Aware Design and Optimization of Edge Intelligence
Shuo Huai, Hao Kong, Xiangzhong Luo +5
Edge intelligence systems, the intersection of edge computing and artificial intelligence (AI), are pushing the frontier of AI applications. However, the complexity of deep learnin…
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
Hao Kong, Di Liu, Xiangzhong Luo +5
In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks…
EvoLP: Self-Evolving Latency Predictor for Model Compression in Real-Time Edge Systems
Shuo Huai, Hao Kong, Shiqing Li +5
Edge devices are increasingly utilized for deploying deep learning applications on embedded systems. The real-time nature of many applications and the limited resources of edge dev…
Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems
Shuo Huai, Di Liu, Hao Kong +5
Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. Howe…
Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization
Shuo Huai, Di Liu, Hao Kong +4
Deep learning applications have been widely adopted on edge devices, to mitigate the privacy and latency issues of accessing cloud servers. Deciding the number of neurons during th…
In-Network Collective Operations: Game Changer or Challenge for AI Workloads?
Torsten Hoefler, Mikhail Khalilov, Josiah Clark +9
This paper summarizes the opportunities of in-network collective operations (INC) for accelerated collective operations in AI workloads. We provide sufficient detail to make this i…
Multi-Partner Project: Multi-GPU Performance Portability Analysis for CFD Simulations at Scale
Panagiotis-Eleftherios Eleftherakis, George Anagnostopoulos, Anastassis Kapetanakis +10
As heterogeneous supercomputing architectures leveraging GPUs become increasingly central to high-performance computing (HPC), it is crucial for computational fluid dynamics (CFD)…