Both sides previous revision
Previous revision
Next revision
|
Previous revision
Next revision
Both sides next revision
|
melange:papers:fall2019 [2019/10/09 12:03] jana |
melange:papers:fall2019 [2019/11/04 17:19] jana |
| |
| |
@misc{kwon2018understanding, | |
title={Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach}, | @article{DBLP:journals/corr/abs-1805-02566, |
author={Hyoukjun Kwon and Prasanth Chatarasi and Michael Pellauer and Angshuman Parashar and Vivek Sarkar and Tushar Krishna}, | author = {Hyoukjun Kwon and |
year={2018}, | Michael Pellauer and |
eprint={1805.02566}, | Tushar Krishna}, |
archivePrefix={arXiv}, | title = {Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach}, |
primaryClass={cs.DC} | journal = {CoRR}, |
| volume = {abs/1805.02566}, |
| year = {2018}, |
| url = {http://arxiv.org/abs/1805.02566}, |
| archivePrefix = {arXiv}, |
| eprint = {1805.02566}, |
| timestamp = {Mon, 13 Aug 2018 16:46:45 +0200}, |
| biburl = {https://dblp.org/rec/bib/journals/corr/abs-1805-02566}, |
| bibsource = {dblp computer science bibliography, https://dblp.org} |
} | } |
| |
| |
| |
address = {New York, NY, USA}, | address = {New York, NY, USA}, |
} | } |
| |
| @ARTICLE{7738524, author={Y. H. Chen and T. Krishna and J. S. Emer and V. Sze}, journal={IEEE Journal of Solid-State Circuits}, title={Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks}, year={2017}, volume={52}, number={1}, pages={127-138}, url = {http://ieeexplore.ieee.org/document/7738524/}, doi={10.1109/JSSC.2016.2616357}, ISSN={0018-9200}, month={Jan},} |
| |
| @article{Vasilache:2019:NAL:3366460.3355606, |
| author = {Vasilache, Nicolas and Zinenko, Oleksandr and Theodoridis, Theodoros and Goyal, Priya and Devito, Zachary and Moses, William S. and Verdoolaege, Sven and Adams, Andrew and Cohen, Albert}, |
| title = {The Next 700 Accelerated Layers: From Mathematical Expressions of Network Computation Graphs to Accelerated GPU Kernels, Automatically}, |
| journal = {ACM Trans. Archit. Code Optim.}, |
| issue_date = {October 2019}, |
| volume = {16}, |
| number = {4}, |
| month = oct, |
| year = {2019}, |
| issn = {1544-3566}, |
| pages = {38:1--38:26}, |
| articleno = {38}, |
| numpages = {26}, |
| url = {http://doi.acm.org/10.1145/3355606}, |
| doi = {10.1145/3355606}, |
| acmid = {3355606}, |
| publisher = {ACM}, |
| address = {New York, NY, USA}, |
| keywords = {Deep learning layers, GPU acceleration, polyhedral compilation}, |
| |