Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs

v1v2 (latest)

Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs

28 February 2018

ArXiv (abs)PDF HTML

Papers citing "Escoin: Efficient Sparse Convolutional Neural Network Inference on GPUs"

16 / 16 papers shown

Title
FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel ExtractionNeural Information Processing Systems (NeurIPS), 2024 Feijie Wu Xingchen Wang Yaqing Wang Tianci Liu Lu Su Jing Gao FedML 262 18 0 28 Jul 2024
STen: Productive and Efficient Sparsity in PyTorch Andrei Ivanov Nikoli Dryden Tal Ben-Nun Saleh Ashkboos Torsten Hoefler 193 6 0 15 Apr 2023
FSCNN: A Fast Sparse Convolution Neural Network Inference System Bo Ji Tianyi Chen 128 3 0 17 Dec 2022
Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reductionJournal of Computer Science (JCS), 2021 Marcin Pietroñ Dominik Zurek 150 17 0 28 Dec 2021
On the Compression of Natural Language Models S. Damadi 87 0 0 13 Dec 2021
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging Edouard Yvinec Arnaud Dapogny Matthieu Cord Kévin Bailly 211 24 0 30 Sep 2021
Only Train Once: A One-Shot Neural Network Training And Pruning FrameworkNeural Information Processing Systems (NeurIPS), 2021 Tianyi Chen Bo Ji Tianyu Ding Biyi Fang Guanyi Wang Zhihui Zhu Luming Liang Yixin Shi Sheng Yi Xiao Tu 216 125 0 15 Jul 2021
High Performance Convolution Using Sparsity and Patterns for Inference in Deep Convolutional Neural Networks Hossam Amer Ahmed H. Salamah A. Sajedi En-Hui Yang 154 6 0 16 Apr 2021
SparseDNN: Fast Sparse Deep Learning Inference on CPUs Ziheng Wang MQ 285 21 0 20 Jan 2021
When deep learning models on GPU can be accelerated by taking advantage of unstructured sparsity Marcin Pietroñ Dominik Zurek BDL 119 1 0 12 Nov 2020
SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning InferenceInternational Conference on Parallel Architectures and Compilation Techniques (PACT), 2020 Ziheng Wang 138 80 0 26 Aug 2020
Self-Supervised GAN Compression Chong Yu Jeff Pool 218 9 0 03 Jul 2020
TIRAMISU: A Polyhedral Compiler for Dense and Sparse Deep Learning Riyadh Baghdadi Abdelkader Nadir Debbagh K. Abdous Fatima-Zohra Benhamida Alex Renda Jonathan Frankle Michael Carbin Saman P. Amarasinghe 135 22 0 07 May 2020
Accelerating convolutional neural network by exploiting sparsity on GPUsACM Transactions on Architecture and Code Optimization (TACO) (TACO), 2019 Weizhi Xu Yintai Sun Shengyu Fan Hui Yu Xin Fu 299 8 0 22 Sep 2019
Accelerated CNN Training Through Gradient Approximation Ziheng Wang Sree Harsha Nelaturu 648 5 0 15 Aug 2019
Low-Memory Neural Network Training: A Technical Report N. Sohoni Christopher R. Aberger Megan Leszczynski Jian Zhang Christopher Ré 213 110 0 24 Apr 2019