This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
melange:papers:spring2017 [2017/01/24 15:33] swetha |
melange:papers:spring2017 [2018/02/08 13:40] (current) prerana |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | @ARTICAL{123, | ||
+ | and P. Sadayappan}, | ||
+ | |||
+ | |||
+ | |||
+ | |||
+ | @INPROCEEDINGS{6043234, | ||
+ | author={A. Pedram and A. Gerstlauer and R. A. v. d. Geijn}, | ||
+ | booktitle={ASAP 2011 - 22nd IEEE International Conference on Application-specific Systems, Architectures and Processors}, | ||
+ | title={A high-performance, | ||
+ | year={2011}, | ||
+ | pages={35-42}, | ||
+ | keywords={floating point arithmetic; | ||
+ | doi={10.1109/ | ||
+ | ISSN={1063-6862}, | ||
+ | month={Sept}, | ||
+ | |||
+ | |||
+ | |||
+ | @inproceedings{Bandishti: | ||
+ | | ||
+ | title = {Tiling Stencil Computations to Maximize Parallelism}, | ||
+ | | ||
+ | | ||
+ | year = {2012}, | ||
+ | isbn = {978-1-4673-0804-5}, | ||
+ | | ||
+ | pages = {40: | ||
+ | | ||
+ | | ||
+ | url = {http:// | ||
+ | acmid = {2389051}, | ||
+ | | ||
+ | | ||
+ | | ||
+ | } | ||
+ | |||
+ | @ARTICLE{7582549, | ||
+ | author={U. Bondhugula and V. Bandishti and I. Pananilath}, | ||
+ | journal={IEEE Transactions on Parallel and Distributed Systems}, | ||
+ | title={Diamond Tiling: Tiling Techniques to Maximize Parallelism for Stencil Computations}, | ||
+ | year={2016}, | ||
+ | url={http:// | ||
+ | volume={PP}, | ||
+ | number={99}, | ||
+ | pages={1-1}, | ||
+ | keywords={Diamond; | ||
+ | doi={10.1109/ | ||
+ | ISSN={1045-9219}, | ||
+ | month={},} | ||
+ | |||
+ | @ARTICLE{7155440, | ||
+ | author={T. Nowatzki and J. Menon and C. H. Ho and K. Sankaralingam}, | ||
+ | journal={IEEE Micro}, | ||
+ | title={Architectural Simulators Considered Harmful}, | ||
+ | year={2015}, | ||
+ | url={http:// | ||
+ | volume={35}, | ||
+ | number={6}, | ||
+ | pages={4-12}, | ||
+ | keywords={computer architecture; | ||
+ | doi={10.1109/ | ||
+ | ISSN={0272-1732}, | ||
+ | month={Nov}, | ||
+ | |||
+ | @INPROCEEDINGS{7349585, | ||
+ | author={J. D. Garvey and T. S. Abdelrahman}, | ||
+ | booktitle={2015 44th International Conference on Parallel Processing}, | ||
+ | title={Automatic Performance Tuning of Stencil Computations on GPUs}, | ||
+ | year={2015}, | ||
+ | pages={300-309}, | ||
+ | keywords={graphics processing units; | ||
+ | doi={10.1109/ | ||
+ | ISSN={0190-3918}, | ||
+ | month={Sept}, | ||
+ | |||
+ | @article{DBLPSteve, | ||
+ | author | ||
+ | Cliff Woolley and | ||
+ | | ||
+ | | ||
+ | John Tran and | ||
+ | Bryan Catanzaro and | ||
+ | Evan Shelhamer}, | ||
+ | title = {cuDNN: Efficient Primitives for Deep Learning}, | ||
+ | journal | ||
+ | volume | ||
+ | year = {2014}, | ||
+ | url = {http:// | ||
+ | timestamp = {Sun, 02 Nov 2014 11:25:59 +0100}, | ||
+ | biburl | ||
+ | bibsource = {dblp computer science bibliography, | ||
+ | } | ||
+ | |||
@article{Bao: | @article{Bao: | ||
- | | + | |
title = {Static and Dynamic Frequency Scaling on Multicore CPUs}, | title = {Static and Dynamic Frequency Scaling on Multicore CPUs}, | ||
| | ||
Line 58: | Line 152: | ||
} | } | ||
- | |||
- | |||
- | @inproceedings{Kong: | ||
- | | ||
- | title = {When Polyhedral Transformations Meet SIMD Code Generation}, | ||
- | | ||
- | | ||
- | year = {2013}, | ||
- | isbn = {978-1-4503-2014-6}, | ||
- | | ||
- | pages = {127--138}, | ||
- | | ||
- | url = {http:// | ||
- | doi = {10.1145/ | ||
- | acmid = {2462187}, | ||
- | | ||
- | | ||
- | | ||
- | } | ||
@article{cummins2017synthesizing, | @article{cummins2017synthesizing, | ||
Line 83: | Line 158: | ||
| | ||
- | | + | |
+ | |||
+ | | ||
} | } | ||
+ | |||
@article{optimistic2017, | @article{optimistic2017, | ||
Line 125: | Line 203: | ||
[download] | [download] | ||
- | |||
- | @article{Putnam: | ||
- | | ||
- | title = {A Reconfigurable Fabric for Accelerating Large-scale Datacenter Services}, | ||
- | | ||
- | | ||
- | | ||
- | | ||
- | month = jun, | ||
- | year = {2014}, | ||
- | issn = {0163-5964}, | ||
- | pages = {13--24}, | ||
- | | ||
- | url = {http:// | ||
- | doi = {10.1145/ | ||
- | acmid = {2665678}, | ||
- | | ||
- | | ||
- | } | ||
@miscellaneous{accelerating-deep-convolutional-neural-networks-using-specialized-hardware, | @miscellaneous{accelerating-deep-convolutional-neural-networks-using-specialized-hardware, | ||
Line 250: | Line 309: | ||
biburl | biburl | ||
bibsource = {dblp computer science bibliography, | bibsource = {dblp computer science bibliography, | ||
+ | } | ||
+ | |||
+ | @inproceedings{FlowMap1994, | ||
+ | | ||
+ | title = {FlowMap: an optimal technology mapping algorithm for delay optimization in lookup-table based FPGA designs}, | ||
+ | | ||
+ | year = {1994}, | ||
+ | isbn = {1937-4151}, | ||
+ | pages = {1-12}, | ||
+ | url = {http:// | ||
+ | doi = {10.1109/ | ||
+ | | ||
+ | } | ||
+ | |||
+ | @article{MILROY20161589, | ||
+ | title = " | ||
+ | journal = " | ||
+ | volume = " | ||
+ | number = "", | ||
+ | pages = "1589 - 1600", | ||
+ | year = " | ||
+ | note = "", | ||
+ | issn = " | ||
+ | doi = " | ||
+ | url = " | ||
+ | author = " | ||
+ | keywords = " | ||
+ | keywords = "CESM Ensemble Consistency Test", | ||
+ | keywords = " | ||
+ | keywords = "code modification as source of variability", | ||
+ | keywords = " | ||
+ | keywords = " | ||
+ | keywords = " | ||
+ | keywords = "Fused Multiply-Add" | ||
} | } |