Sparse Tensor Core: Algorithm and Hardware Co-Design for Vector-wise Sparse Neural Networks on Modern GPUs
Year: 2019
Type: conference-paper
Abstract: Deep neural networks have become the compelling solution for the applications such as image classification, object detection, speech recognition, and machine translation. However, the great success comes at the cost of excessive computation due to the over-provisioned parameter space. To improve the computation efficiency of neural networks, many pruning techniques have been proposed to reduce the amount of multiply-accumulate (MAC) operations, which results in high sparsity in the networks.
Authors: Maohua Zhu, Tao Zhang, Zhenyu Gu, Yuan Xie
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Funder: National Science Foundation
Awards: II-New: RICARDO: Research Infrastructure for Circuit and Architecture Design with Emerging Technologies, SPX: Collaborative Research: Ula! - An Integrated Deep Neural Network (DNN) Acceleration Framework with Enhanced Unsupervised Learning Capability, SHF:Small: Tensor-Based Algorithm and Hardware Co-Optimization for Neural Network Architecture
OpenAlex ID: W2980186997
