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},
54 address={Porto, Portugal}
58 % ee = {http://link.springer.de/link/service/series/0558/bibs/2565/25650354.htm}
61 % crossref = {DBLP:conf/vecpar/2002},
62 % bibsource = {DBLP, http://dblp.uni-trier.de}
66 title= {{CPC}: {C}omputer {P}hysics {C}ommunications},
67 howpublished = {Queen's University, Belfast},
68 note = {\url{http://cpc.cs.qub.ac.uk/}},
75 title={{\it {NVIDIA} {CUDA} {T}oolkit} 4.1, {CUBLAS} {L}ibrary},
80 @Comment howpublished = {available at: \url{http://docs.nvidia.com/cuda/cublas}},
86 title={{\it {NVIDIA} {CUDA} {C} {P}rogramming {G}uide}, version 4.1},
91 @Comment howpublished = {available at: \url{http://docs.nvidia.com/cuda/cuda-c-programming-guide}},
95 @Misc{CUDA_ProgGuide_3.2,
96 title={{NVIDIA} {CUDA} {C} {P}rogramming {G}uide},
98 howpublished = {version 3.2, available at: \url{www.nvidia.com/object/cuda_get.html}}
103 title={{\it {CUDA C/C++ Streams and Concurrency}, NVIDIA}},
113 title= { Goto\uppercase{BLAS}},
114 howpublished = { \url{http://www.tacc.utexas.edu/tacc-projects/gotoblas2}}
118 title={{MAGMA (Matrix Algebra on GPU and Multicore Architectures)}},
119 howpublished={Available at \url{http://icl.cs.utk.edu/magma}},
123 @Misc{MAGMA_0.2_UserGuide,
124 title={{MAGMA (Matrix Algebra on GPU and Multicore Architectures) version 0.2 Users' Guide}},
125 author={S. Tomov and R. Nath and P. Du and J. Dongarra},
126 howpublished={available at: \url{http://icl.cs.utk.edu/magma}}
129 @INPROCEEDINGS{NTD10a,
130 author = {R. Nath and S. Tomov and J. Dongarra},
131 title = {{Accelerating GPU kernels for dense linear algebra}},
132 booktitle={{Proc. of VECPAR'10}},
133 address={{Berkeley, CA (USA)}},
142 author = {Nath, R. and Tomov, S. and Dongarra, J.},
143 title = {{An improved MAGMA GEMM for Fermi graphics processing units}},
144 journal = {International Journal of High Performance Computing Applications},
150 @Comment issue_date = {November 2010},
151 @Comment publisher = {Sage Publications, Inc.},
152 @Comment address = {Thousand Oaks, CA, USA},
153 @Comment keywords = {CUDA matrix mutiply, Fermi, GPU BLAS, dense linear algebra, hybrid computing},
154 @Comment numpages = {5},
155 @Comment url = {http://dx.doi.org/10.1177/1094342010385729},
156 @Comment doi = {10.1177/1094342010385729},
157 @Comment acmid = {1889710},
158 @Comment issn = {1094-3420},
159 @Comment month = nov,
163 title= {{CUDA CUBLAS Library 3.1}},
164 howpublished = { \url{http://developer.download.nvidia.com/compute/cuda/3_1/toolkit/docs/CUBLAS_Library_3.1.pdf} }
168 title= {{CUDA CUBLAS Library 3.2}},
169 howpublished = { \url{http://developer.download.nvidia.com/compute/cuda/3_2_prod/toolkit/docs/CUBLAS_Library.pdf} }