1 @Inproceedings{PF_PDSEC2011,
2 author ={P. Fortin and R. Habel and F.~J\'ez\'equel and J.-L. Lamotte and N.S. Scott},
3 title = {Deployment on GPUs of an application in computational atomic physics},
4 booktitle = {{12th IEEE International Workshop on Parallel and Distributed Scientific
5 and Engineering Computing (PDSEC) in conjunction with the 25th International Parallel and Distributed Processing Symposium (IPDPS)}},
8 @Comment address= {{Anchorage, Alaska, USA}},
13 author={P.G. Burke and C.J. Noble and M.P. Scott},
14 title={{R-matrix theory of electron scattering at intermediate energies}},
15 journal={Proceedings of the Royal Society of London A},
20 % %Proc. Roy. Soc. A }
23 author ={N.S. Scott and M.P. Scott and P.G. Burke and T. Stitt and V. Faro-Maza and C. Denis and A. Maniopoulou},
24 title ={{2DRMP: A~suite of two-dimensional R-matrix propagation codes}},
25 journal ={Computer Physics Communications},
30 %note={ISSN: {0010-4655}, doi:10.1016/j.cpc.2009.07.017}
33 author ={ V.M. Burke and C.J. Noble and V. Faro-Maza and A. Maniopoulou and N.S. Scott},
34 title ={ {FARM\_2DRMP: a version of FARM for use with 2DRMP}},
35 journal ={Computer Physics Communications},
40 % note={ISSN: {0010-4655}, doi:10.1016/j.cpc.2009.07.017}
42 @INPROCEEDINGS{VECPAR,
43 author = {T. Stitt and
47 title = {{2-D R-Matrix Propagation: A Large Scale Electron Scattering
48 Simulation Dominated by the Multiplication of Dynamically
50 booktitle = {Proc. of VECPAR'02},
56 % ee = {http://link.springer.de/link/service/series/0558/bibs/2565/25650354.htm}
59 % crossref = {DBLP:conf/vecpar/2002},
60 % bibsource = {DBLP, http://dblp.uni-trier.de}
64 title= {{CPC}: {C}omputer {P}hysics {C}ommunications},
65 howpublished = {Queen's University, Belfast},
66 note = {\url{http://cpc.cs.qub.ac.uk/}},
73 title={{NVIDIA} {CUDA} {T}oolkit 4.1, {CUBLAS} {L}ibrary},
78 @Comment howpublished = {available at: \url{http://docs.nvidia.com/cuda/cublas}},
84 title={{NVIDIA} {CUDA} {C} {P}rogramming {G}uide, version 4.1},
89 @Comment howpublished = {available at: \url{http://docs.nvidia.com/cuda/cuda-c-programming-guide}},
93 @Misc{CUDA_ProgGuide_3.2,
94 title={{NVIDIA} {CUDA} {C} {P}rogramming {G}uide},
96 howpublished = {version 3.2, available at: \url{www.nvidia.com/object/cuda_get.html}}
101 title={{CUDA C/C++ Streams and Concurrency, NVIDIA}},
111 title= { Goto\uppercase{BLAS}},
112 howpublished = { \url{http://www.tacc.utexas.edu/tacc-projects/gotoblas2}}
116 title={{MAGMA (Matrix Algebra on GPU and Multicore Architectures)}},
117 howpublished={Available at: \url{http://icl.cs.utk.edu/magma}},
121 @Misc{MAGMA_0.2_UserGuide,
122 title={{MAGMA (Matrix Algebra on GPU and Multicore Architectures) version 0.2 Users' Guide}},
123 author={S. Tomov and R. Nath and P. Du and J. Dongarra},
124 howpublished={available at: \url{http://icl.cs.utk.edu/magma}}
128 @INPROCEEDINGS{NTD10a,
129 author = {R. Nath and S. Tomov and J. Dongarra},
130 title = {{Accelerating GPU Kernels for Dense Linear Algebra}},
131 booktitle={Proc. of VECPAR'10},
138 author = {Nath, R. and Tomov, S. and Dongarra, J.},
139 title = {{An Improved Magma Gemm For Fermi Graphics Processing Units}},
140 journal = {International Journal of High Performance Computing Applications},
146 @Comment issue_date = {November 2010},
147 @Comment publisher = {Sage Publications, Inc.},
148 @Comment address = {Thousand Oaks, CA, USA},
149 @Comment keywords = {CUDA matrix mutiply, Fermi, GPU BLAS, dense linear algebra, hybrid computing},
150 @Comment numpages = {5},
151 @Comment url = {http://dx.doi.org/10.1177/1094342010385729},
152 @Comment doi = {10.1177/1094342010385729},
153 @Comment acmid = {1889710},
154 @Comment issn = {1094-3420},
155 @Comment month = nov,
159 title= {{CUDA CUBLAS Library 3.1}},
160 howpublished = { \url{http://developer.download.nvidia.com/compute/cuda/3_1/toolkit/docs/CUBLAS_Library_3.1.pdf} }
164 title= {{CUDA CUBLAS Library 3.2}},
165 howpublished = { \url{http://developer.download.nvidia.com/compute/cuda/3_2_prod/toolkit/docs/CUBLAS_Library.pdf} }