Permalink
Switch branches/tags
Nothing to show
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
executable file 291 lines (253 sloc) 10.4 KB
% ##################### CORE PAPER #####################
@inproceedings{dongarra2016performance,
title={Performance, Design, and Autotuning of Batched GEMM for GPUs},
author={Abdelfattah, Ahmad and Haidar, Azzam and Tomov, Stanimire and Dongarra, Jack},
booktitle={High Performance Computing: 31st International Conference, ISC High Performance 2016, Frankfurt, Germany, June 19-23, 2016, Proceedings},
volume={9697},
pages={21},
year={2016},
organization={Springer}
} ---------------------------------
% ##################### OTHER BATCHED GEMM PAPERS #####################
@inproceedings{masliah2016high,
title={High-performance matrix-matrix multiplications of very small matrices},
author={Masliah, Ian and Abdelfattah, Ahmad and Haidar, A and Tomov, S and Baboulin, Marc and Falcou, J and Dongarra, Jack},
booktitle={European Conference on Parallel Processing},
pages={659--671},
year={2016},
organization={Springer}
} ---------------------------------
@article{abdelfattah2016high,
title={High-Performance Tensor Contractions for GPUs},
author={Abdelfattah, Ahmad and Baboulin, Marc and Dobrev, Veselin and Dongarra, Jack and Earl, Christopher and Falcou, Joel and Haidar, Azzam and Karlin, Ian and Kolev, Tzanio and Masliah, Ian and others},
journal={Procedia Computer Science},
volume={80},
pages={108--118},
year={2016},
publisher={Elsevier}
}
@article{jhurani2015gemm,
title={A GEMM interface and implementation on NVIDIA GPUs for multiple small matrices},
author={Jhurani, Chetan and Mullowney, Paul},
journal={Journal of Parallel and Distributed Computing},
volume={75},
pages={133--140},
year={2015},
publisher={Elsevier}
} ---------------------------------
@incollection{lopez2014batch,
title={Batch matrix exponentiation},
author={Lopez, M Graham and Horton, Mitchel D},
booktitle={Numerical Computations with GPUs},
pages={45--67},
year={2014},
publisher={Springer}
} ---------------------------------
@techreport {dong2016batchfact,
title = {MAGMA Batched: A Batched BLAS Approach for Small Matrix Factorizations and Applications on GPUs},
journal = {ICL Tech Report},
year = {2016},
month = {08/2016},
keywords = {Batched, Bi-diagonalization, gpu, Hydrodynamic},
author = {Tingxing Dong and Azzam Haidar and Piotr Luszczek and Stanimire Tomov and Ahmad Abdelfattah and Jack Dongarra}
} ---------------------------------
@article{shi2016tensor,
title={Tensor Contractions with Extended BLAS Kernels on CPU and GPU},
author={Shi, Yang and Niranjan, UN and Anandkumar, Animashree and Cecka, Cris},
journal={arXiv preprint arXiv:1606.05696},
year={2016}
}
@misc{nvidia2013basic,
title={Basic Linear Algebra Subroutines (cuBLAS) library},
author={NVIDIA, CUDA},
year={2013}
} ---------------------------------
@article{haidar2015batched,
title={Batched matrix computations on hardware accelerators based on GPUs},
author={Haidar, Azzam and Dong, Tingxing and Luszczek, Piotr and Tomov, Stanimire and Dongarra, Jack},
journal={International Journal of High Performance Computing Applications},
volume={29},
pages={2},
year={2015}
} ---------------------------------
@conference {abdelfattah2015batchcholesky,
title = {Performance Tuning and Optimization Techniques of Fixed and Variable Size Batched Cholesky Factorization on GPUs},
booktitle = {International Conference on Computational Science (ICCS{\textquoteright}16)},
year = {2015.9},
month = {06-2016},
address = {San Diego, CA},
author = {Ahmad Abdelfattah and Azzam Haidar and Stanimire Tomov and Jack Dongarra}
} ---------------------------------
@conference {abdelfattah2016variablebatch,
title = {On the Development of Variable Size Batched Computation for Heterogeneous Parallel Architectures},
booktitle = {The 17th IEEE International Workshop on Parallel and Distributed Scientific and Engineering Computing (PDSEC 2016), IPDPS 2016},
year = {2016},
month = {05-2016},
publisher = {IEEE},
organization = {IEEE},
address = {Chicago, IL},
author = {Ahmad Abdelfattah and Azzam Haidar and Stanimire Tomov and Jack Dongarra}
}
@conference {dong2014factor,
title = {LU Factorization of Small Matrices: Accelerating Batched DGETRF on the GPU},
booktitle = {16th IEEE International Conference on High Performance Computing and Communications (HPCC)},
author={Dong, Tingxing and Haidar, Azzam and Luszczek, Piotr and Harris, James Austin and Tomov, Stanimire and Dongarra, Jack},
year = {2014},
month = {08-2014},
publisher = {IEEE},
organization = {IEEE},
address = {Paris, France}
} ---------------------------------
@conference {dong2014chols,
title = {A Fast Batched Cholesky Factorization on a GPU},
booktitle = {International Conference on Parallel Processing (ICPP-2014)},
year = {2014},
month = {09-2014},
address = {Minneapolis, MN},
author = {Tingxing Dong and Azzam Haidar and Stanimire Tomov and Jack Dongarra}
} ---------------------------------
@inproceedings{polok2012fast,
title={Fast linear algebra on GPU},
author={Polok, Lukas and Smrz, Pavel},
booktitle={High Performance Computing and Communication \& 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), 2012 IEEE 14th International Conference on},
pages={439--444},
year={2012},
organization={IEEE}
} ---------------------------------
@inproceedings{kabir2015design,
title={On the Design, Development, and Analysis of Optimized Matrix-Vector Multiplication Routines for Coprocessors},
author={Kabir, Khairul and Haidar, Azzam and Tomov, Stanimire and Dongarra, Jack},
booktitle={International Conference on High Performance Computing},
pages={58--73},
year={2015},
organization={Springer}
} ---------------------------------
% ##################### OTHER GEMM PAPERS #####################
@inproceedings{agullo2009numerical,
title={Numerical linear algebra on emerging architectures: The PLASMA and MAGMA projects},
author={Agullo, Emmanuel and Demmel, Jim and Dongarra, Jack and Hadri, Bilel and Kurzak, Jakub and Langou, Julien and Ltaief, Hatem and Luszczek, Piotr and Tomov, Stanimire},
booktitle={Journal of Physics: Conference Series},
volume={180},
number={1},
pages={012037},
year={2009},
organization={IOP Publishing}
}
@article{dongarra2016parallel,
title={Parallel Programming Models for Dense Linear Algebra on Heterogeneous Systems},
author={Dongarra, Jack and Abalenkovs, M and Abdelfattah, A and Gates, M and Haidar, A and Kurzak, J and Luszczek, P and Tomov, S and Yamazaki, I and YarKhan, A},
journal={Supercomputing frontiers and innovations},
volume={2},
number={4},
pages={67--86},
year={2016}
}
@article{nath2010improved,
title={An improved MAGMA GEMM for Fermi graphics processing units},
author={Nath, Rajib and Tomov, Stanimire and Dongarra, Jack},
journal={International Journal of High Performance Computing Applications},
volume={24},
number={4},
pages={511--515},
year={2010},
publisher={SAGE Publications}
}
% ##################### BOOTSTRAP AND HC PAPERS #####################
@Article{white1980hc,
author={White, Halbert},
title={{A Heteroskedasticity-Consistent Covariance Matrix Estimator and a Direct Test for Heteroskedasticity}},
journal={Econometrica},
year=1980,
volume={48},
number={4},
pages={817-38},
month={May},
keywords={},
doi={},
abstract={No abstract is available for this item.},
url={https://ideas.repec.org/a/ecm/emetrp/v48y1980i4p817-38.html}
} ---------------------------------
@article{cameron2010robust,
title={Robust inference with clustered data},
author={Cameron, A Colin and Miller, Douglas L and others},
journal={Handbook of empirical economics and finance},
pages={1--28},
year={2010},
publisher={CRC Press Boca Raton, LA, USA}
} ---------------------------------
@article{moulton1990illustration,
title={An Illustration of a Pitfall in Estimating the Effects of Aggregate Variables on Micro Units},
author={Moulton, Brent R},
journal={The Review of Economics and Statistics},
volume={72},
number={2},
pages={334--338},
year={1990}
} ---------------------------------
@article{froot1989consistent,
title={Consistent covariance matrix estimation with cross-sectional dependence and heteroskedasticity in financial data},
author={Froot, Kenneth A},
journal={Journal of Financial and Quantitative Analysis},
volume={24},
number={03},
pages={333--355},
year={1989},
publisher={Cambridge Univ Press}
} ---------------------------------
@article{cameron2008bootstrap,
title={Bootstrap-based improvements for inference with clustered errors},
author={Cameron, A Colin and Gelbach, Jonah B and Miller, Douglas L},
journal={The Review of Economics and Statistics},
volume={90},
number={3},
pages={414--427},
year={2008},
publisher={MIT Press}
} ---------------------------------
@article{rogers1994regression,
title={Regression standard errors in clustered samples},
author={Rogers, William},
journal={Stata technical bulletin},
volume={3},
number={13},
year={1994},
publisher={StataCorp LP}
} ---------------------------------
@article{zeileis2004sandwitch,
title = {Econometric Computing with HC and HAC Covariance Matrix Estimators},
author = {Zeileis, Achim},
journal = {Journal of Statistical Software},
year = {2004},
volume = {11},
number = {10},
pages = {1--17},
url = {http://www.jstatsoft.org/v11/i10/},
} ---------------------------------
% ##################### OTHER IMPLEMENTATION PAPERS #####################
@Misc{roodman2015boottest,
author={David Roodman},
title={{BOOTTEST: Stata module to provide fast execution of the wild bootstrap with null imposed}},
year=2015,
month=Dec,
howpublished={Statistical Software Components, Boston College Department of Economics},
keywords={wild bootstrap; Cameron; Gelbach; Miller; score bootstrap; Rao LM test; multi-way clustering},
doi={},
url={https://ideas.repec.org/c/boc/bocode/s458121.html},
} ---------------------------------
@article{lopez2016gpu,
title={GPU Parallel Implementation of Numerical Distribution Functions for Seasonal Unit Root Tests},
author={L{\'o}pez-de-Lacalle, Javier},
year={2016}
} ---------------------------------
@article{guo2012econgpu,
author = { Guangbao Guo },
title = {Parallel Statistical Computing for Statistical Inference},
journal = {Journal of Statistical Theory and Practice},
volume = {6},
number = {3},
pages = {536-565},
year = {2012},
doi = {10.1080/15598608.2012.695705},
URL = {http://dx.doi.org/10.1080/15598608.2012.695705}
} ---------------------------------
% NEED R BOOT LIBRARY