Both sides previous revision
Previous revision
Next revision
|
Previous revision
|
melange:papers:spring2017 [2017/02/03 14:29] swetha |
melange:papers:spring2017 [2018/02/08 13:40] prerana |
@article{DBLP, | @ARTICAL{123, author={Sanket Tavarageri, Albert Hartono, Muthu Baskaran, Louis-Noel Pouchet,J. Ramanujam |
| and P. Sadayappan}, title={Parametric Tiling of Affine Loop Nests}, year={2010}, doi = {http://web.cse.ohio-state.edu/~pouchet.2/doc/cpc-article.10.pdf} ,} |
| |
| |
| |
| |
| @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, low-power linear algebra core}, |
| year={2011}, |
| pages={35-42}, |
| keywords={floating point arithmetic;matrix multiplication;GFLOPS-W;application-specific custom hardware;floating point operations per second;linear algebra core;matrix computations;matrix-matrix multiplication;power consumption reduction;technology scaling;Bandwidth;Computer architecture;Hardware;Kernel;Linear algebra;Program processors;Registers}, |
| doi={10.1109/ASAP.2011.6043234}, |
| ISSN={1063-6862}, |
| month={Sept},} |
| |
| |
| |
| @inproceedings{Bandishti:2012:TSC:2388996.2389051, |
| author = {Bandishti, Vinayaka and Pananilath, Irshad and Bondhugula, Uday}, |
| title = {Tiling Stencil Computations to Maximize Parallelism}, |
| booktitle = {Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis}, |
| series = {SC '12}, |
| year = {2012}, |
| isbn = {978-1-4673-0804-5}, |
| location = {Salt Lake City, Utah}, |
| pages = {40:1--40:11}, |
| articleno = {40}, |
| numpages = {11}, |
| url = {http://dl.acm.org/citation.cfm?id=2388996.2389051}, |
| acmid = {2389051}, |
| publisher = {IEEE Computer Society Press}, |
| address = {Los Alamitos, CA, USA}, |
| keywords = {compilers, program transformation}, |
| } |
| |
| @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://ieeexplore.ieee.org/document/7582549/}, |
| volume={PP}, |
| number={99}, |
| pages={1-1}, |
| keywords={Diamond;Face;Indexes;Optimization;Parallel processing;Shape;Silicon;Compilers;locality;loop tiling;parallelism;program transformation;stencils}, |
| doi={10.1109/TPDS.2016.2615094}, |
| 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://ieeexplore.ieee.org/document/7155440/}, |
| volume={35}, |
| number={6}, |
| pages={4-12}, |
| keywords={computer architecture;digital simulation;architectural layers;architectural simulators;black boxes;evaluation standard recalibration;quantitative simulators;Analytical models;Benchmark testing;Computer architecture;Market research;Mathematical model;Simulation;architecture;benchmarks;evaluation standards;footprint;modeling;simulators;validation}, |
| doi={10.1109/MM.2015.74}, |
| 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;learning (artificial intelligence);parallel processing;storage management;Nvidia GTX Titan GPU;OpenCL stencil kernel;automatic performance tuning;graphics processing unit;machine learning;optimization;random sampling;stencil computation;Graphics processing units;Instruction sets;Kernel;Merging;Optimization;Parallel processing;Yttrium;GPGPU;auto-tuning;machine learning;stencil}, |
| doi={10.1109/ICPP.2015.39}, |
| ISSN={0190-3918}, |
| month={Sept},} |
| |
| @article{DBLPSteve, |
author = {Sharan Chetlur and | author = {Sharan Chetlur and |
Cliff Woolley and | Cliff Woolley and |
| |
@article{Bao:2016:SDF:3012405.3011017, | @article{Bao:2016:SDF:3012405.3011017, |
author = {Bao, Wenlei and Hong, Changwan and Chunduri, Sudheer and Krishnamoorthy, Sriram and Pouchet, Louis-No\"{e}l and Rastello, Fabrice and Sadayappan, P.}, | author = {Bao, Wenlei and Hong, Changwan and Chunduri, Sudheer and Krishnamoorthy, Sriram and Pouchet, Louis-Noel and Rastello, Fabrice and Sadayappan, P.}, |
title = {Static and Dynamic Frequency Scaling on Multicore CPUs}, | title = {Static and Dynamic Frequency Scaling on Multicore CPUs}, |
journal = {ACM Trans. Archit. Code Optim.}, | journal = {ACM Trans. Archit. Code Optim.}, |
author={Cummins, Chris and Petoumenos, Pavlos and Wang, Zheng and Leather, Hugh}, | author={Cummins, Chris and Petoumenos, Pavlos and Wang, Zheng and Leather, Hugh}, |
| |
year={2017} | year={2017}, |
| |
| url={http://homepages.inf.ed.ac.uk/hleather/publications/2017-benchsynth-cgo.pdf} |
| |
} | } |
| |
@article{optimistic2017, | @article{optimistic2017, |
| |
publisher = { IEEE} | publisher = { IEEE} |
} | } |
| |
| @article{MILROY20161589, |
| title = "Towards Characterizing the Variability of Statistically Consistent Community Earth System Model Simulations", |
| journal = "Procedia Computer Science", |
| volume = "80", |
| number = "", |
| pages = "1589 - 1600", |
| year = "2016", |
| note = "", |
| issn = "1877-0509", |
| doi = "http://dx.doi.org/10.1016/j.procs.2016.05.489", |
| url = "http://www.sciencedirect.com/science/article/pii/S1877050916309759", |
| author = "Daniel J. Milroy and Allison H. Baker and Dorit M. Hammerling and John M. Dennis and Sheri A. Mickelson and Elizabeth R. Jessup", |
| keywords = "Community Earth System Model", |
| keywords = "CESM Ensemble Consistency Test", |
| keywords = "statistical consistency", |
| keywords = "code modification as source of variability", |
| keywords = "compiler as source of variability", |
| keywords = "Community Atmosphere Model", |
| keywords = "non-bit-for-bit", |
| keywords = "Fused Multiply-Add" |
| } |