Flexible Communication Avoiding Matrix Multiplication on FPGA with High-Level Synthesis-Reference-Cited by-同舟云学术

Flexible Communication Avoiding Matrix Multiplication on FPGA with High-Level Synthesis

Published:2020-02-23 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays
language:
Short-container-title:

Author:

de Fine Licht Johannes¹,Kwasniewski Grzegorz¹,Hoefler Torsten¹

Affiliation:

1. ETH Zurich, Zurich, Switzerland

Funder

Horizon 2020

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3373087.3375296

Reference35 articles.

1. Hitting the memory wall

2. M. Scquizzato and F. Silvestri "Communication lower bounds for distributedmemory computations " arXiv preprint arXiv:1307.1805 2013. M. Scquizzato and F. Silvestri "Communication lower bounds for distributedmemory computations " arXiv preprint arXiv:1307.1805 2013.

Cited by 35 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. CHARM 2.0: Composing Heterogeneous Accelerators for Deep Learning on Versal ACAP Architecture;ACM Transactions on Reconfigurable Technology and Systems;2024-08-05

2. EA4RCA: Efficient AIE accelerator design framework for regular Communication-Avoiding Algorithm;ACM Transactions on Architecture and Code Optimization;2024-07-15

3. FPGA Framework Improvements for HPC Applications;2023 International Conference on Field Programmable Technology (ICFPT);2023-12-12

4. Algorithm/Hardware Co-Optimization for Sparsity-Aware SpMM Acceleration of GNNs;IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems;2023-12

5. Co-design Hardware and Algorithm for Vector Search;Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis;2023-11-11