DiVIT: Algorithm and architecture co-design of differential attention in vision transformer
Authors:
- Yangfan LiYLYangfan Li
- Yikun HuYHYikun Hu
- Fan WuFWFan Wu
- Kenli LiKLKenli Li
- 21 April 2022
- journal article
- research article
- Published by Elsevier in Journal of Systems Architecture
- Vol. 128
Abstract
No abstract availableKeywords
This publication has 9 references indexed in Scilit:
- FlinkCL: An OpenCL-Based In-Memory Computing Architecture on Heterogeneous CPU-GPU Clusters for Big DataIEEE Transactions on Computers, 2018
- GFlink: An In-Memory Computing Architecture on Heterogeneous CPU-GPU Clusters for Big DataIEEE Transactions on Parallel and Distributed Systems, 2018
- Bit-pragmatic deep neural network computing2017
- In-Datacenter Performance Analysis of a Tensor Processing Unit2017
- GPU-Accelerated Parallel Hierarchical Extreme Learning Machine on Flink for Big DataIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017
- Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural NetworksIEEE Journal of Solid-State Circuits, 2016
- Deep Residual Learning for Image Recognition2016
- Ramulator: A Fast and Extensible DRAM SimulatorIEEE Computer Architecture Letters, 2015
- DianNaoACM SIGARCH Computer Architecture News, 2014