1 @article{ch19:matrix-collection,
2 author = {Duff, I. S. and Grimes, R. G. and Lewis, J. G.},
3 title = {Sparse matrix test problems},
4 journal = {ACM Trans. Math. Softw.},
5 issue_date = {March 1989},
13 address = {New York, NY, USA},
16 @Conference{ch19:spmv-iccs,
17 author = {Dang, H.-V. and Schmidt, B.},
18 title = {The Sliced {COO} format for Sparse Matrix-Vector Multiplication on {CUDA}-enabled {GPUs}},
21 booktitle = {International Conference on Computational Science ICCS, Procedia Vol. 9}
24 @article{ch19:spmv-ccpe,
25 author = {B. Schmidt and
28 title = {{Iterative Sparse Matrix-Vector Multiplication for accelerating
29 the Block Wiedemann Algorithm over GF(2) on Multi-graphics
30 Processing Unit Systems}},
31 journal = {Concurrency and Computation: Practice and Experience},
40 note = {http://www.csm.ornl.gov/~kohl/MatView/},
41 title = {Mat{V}iew: Scalable Sparse Matrix Viewer},
45 @inproceedings{ch19:nvidia-spmv,
46 author = {Bell, N. and Garland, M.},
47 title = {Implementing sparse matrix-vector multiplication on throughput-oriented processors},
48 booktitle = {SC '09: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis},
50 isbn = {978-1-60558-744-8},
52 location = {Portland, Oregon},
53 doi = {http://doi.acm.org/10.1145/1654059.1654078},
55 address = {New York, NY, USA},
58 @article{ch19:bellpack,
59 author = {Choi, J. W. and Singh, A. and Vuduc, R. W.},
60 title = {Model-driven autotuning of sparse matrix-vector multiply on {GPUs}},
61 journal = {ACM SIGPLAN Notices - PPoPP '10},
71 address = {New York, NY, USA},
72 keywords = {gpu, performance modeling, sparse matrix-vector multiplication},
75 @inproceedings{ch19:europar,
76 author = {Bertil Schmidt and
79 title = { Iterative Sparse Matrix-Vector Multiplication for Integer
80 Factorization on {GPUs} },
81 booktitle = {Euro-Par (2)},
84 ee = {http://dx.doi.org/10.1007/978-3-642-23397-5_41},
85 crossref = {DBLP:conf/europar/2011-2},
86 bibsource = {DBLP, http://dblp.uni-trier.de}
89 @proceedings{ch19:DBLP:conf/europar/2011-2,
90 editor = {Emmanuel Jeannot and
93 title = {Euro-Par 2011 Parallel Processing - 17th International Conference,
94 Euro-Par 2011, Bordeaux, France, August 29 - September 2,
95 2011, Proceedings, Part II},
96 booktitle = {Euro-Par (2)},
97 publisher = {Springer},
98 series = {Lecture Notes in Computer Science},
101 isbn = {978-3-642-23396-8},
102 ee = {http://dx.doi.org/10.1007/978-3-642-23397-5},
103 bibsource = {DBLP, http://dblp.uni-trier.de}
106 @article{ch19:Thome:subqad,
107 author = {Thom\'{e}, E.},
108 title = { Subquadratic Computation of Vector Generating Polynomials and Improvement of the Block {W}iedemann Algorithm },
109 journal = {J. Symb. Comput.},
117 url = {http://portal.acm.org/citation.cfm?id=612306.612319},
118 doi = {10.1006/jsco.2002.0533},
120 publisher = {Academic Press, Inc.},
121 address = {Duluth, MN, USA},
125 author = {Peter L. Montgomery},
126 title = {A Survey of Modern Integer Factorization Algorithms},
127 journal = {CWI Quarterly},
134 author = {Wiedemann, D H},
135 title = {Solving sparse linear equations over finite fields},
136 journal = {IEEE Trans. Inf. Theor.},
144 url = {http://dl.acm.org/citation.cfm?id=13738.13744},
145 doi = {10.1109/TIT.1986.1057137},
147 publisher = {IEEE Press},
148 address = {Piscataway, NJ, USA},
151 @inproceedings{ch19:wie-guass,
152 author = {LaMacchia, Brian A. and Odlyzko, Andrew M.},
153 title = {Solving Large Sparse Linear Systems over Finite Fields},
154 booktitle = {Proceedings of the 10th Annual International Cryptology Conference on Advances in Cryptology},
155 series = {CRYPTO '90},
157 isbn = {3-540-54508-5},
160 url = {http://dl.acm.org/citation.cfm?id=646755.705355},
162 publisher = {Springer-Verlag},
163 address = {London, UK, UK},
167 author = {Quinn, Michael},
169 howpublished = {Hardcover},
172 posted-at = {2010-04-02 13:14:26},
174 publisher = {McGraw-Hill Science/Engineering/Math},
175 title = {{Parallel Programming in C with MPI and OpenMP}},
179 @INPROCEEDINGS{ch19:mpi:col,
180 author = {Rajeev Thakur},
181 title = {Improving the performance of collective operations in MPICH},
182 booktitle = {Recent Advances in Parallel Virtual Machine and Message Passing Interface. Number 2840 in LNCS, Springer Verlag (2003) 257–267 10th European PVM/MPI User’s Group Meeting},
185 publisher = {Springer Verlag}
188 @INPROCEEDINGS{ch19:reduce_tree,
189 author = {Pitch Patarasuk and Xin Yuan},
190 title = {Bandwidth Efficient Allreduce Operation on Tree Topologies},
191 booktitle = {IEEE IPDPS Workshop on High-Level Parallel Programming Models and Supportive Environments},
195 @InProceedings{ch19:aoki,
196 author = {Aoki, K. and Shimoyama, T. and Ueda, H.},
197 title = {Experiments on the Linear Algebra Step in the Number Field Sieve},
198 booktitle = {Proceedings of the Security 2nd International Conference on Advances in Information and Computer Security},
201 isbn = {3-540-75650-7, 978-3-540-75650-7},
202 location = {Nara, Japan},
205 _url = {http://portal.acm.org/citation.cfm?id=1778902.1778909},
207 publisher = {Springer-Verlag},
208 address = {Berlin, Heidelberg},
209 keywords = {block Lanczos, ethernet, integer factoring, number field sieve, parallel computation},
212 @InProceedings{ch19:kilobit,
213 author = {K. Aoki and J. Franke and T. Kleinjung and A. K. Lenstra and D. A. Osvik},
214 title = {A Kilobit Special Number Field Sieve Factorization.},
215 address ={Kuching, Malaysia},
216 booktitle = {ASIACRYPT},
220 @techreport{ch19:nvidia,
221 author = {N. Bell and M. Garland},
222 title = {Efficient Sparse Matrix-Vector Multiplication on {CUDA}},
225 institution = {NVIDIA Corporation},
226 type = {NVIDIA Technical Report},
227 number = {NVR-2008-004},
230 @TechReport{ch19:rsa170,
231 author = {Dominik Bonenberger and Martin Krone},
232 title = {{Factorization of RSA-170}},
233 institution = {Ostfalia University of Applied Sciences},
235 url = {http://public.rz.fh-wolfenbuettel.de/~kronema/pdf/rsa170.pdf},
238 @article{ch19:exactspmv,
239 author = {B. Boyer and
242 title = {Exact Sparse Matrix-Vector Multiplication on GPU's and Multicore
245 volume = {abs/1004.3719},
247 ee = {http://arxiv.org/abs/1004.3719},
248 bibsource = {DBLP, http://dblp.uni-trier.de}
252 author = {D. Coppersmith},
253 title = {Solving Homogeneous Linear Equations Over {GF(2)} via Block {W}iedemann Algorithm},
254 journal = {Mathematics of Computation},
257 doi = {10.2307/2153413},
261 @InProceedings{ch19:hwang,
262 author = {W. Hwang and
264 title = {{Load Balanced Block Lanczos Algorithm over GF(2) for Factorization
266 booktitle = {High Performance Computing, HiPC},
267 address = {Bangalore, India},
270 ee = {http://dx.doi.org/10.1007/11945918_38},
271 bibsource = {DBLP, http://dblp.uni-trier.de}
274 @InProceedings{ch19:rsa768,
275 author = {{T. Kleinjung et al.}},
276 title = {Factorization of a 768-bit {RSA} modulus},
277 booktitle = {International Crytology Conference},
279 adress= {Melaka, Malaysia},
281 doi = {10.1007/978-3-642-14623-7_18},
285 @article{ch19:hetero768,
286 author = {{T. Kleinjung et al.}},
287 HAL_ID = {inria-00535765},
288 _URL = {http://hal.inria.fr/inria-00535765/en/},
289 title = { A Heterogeneous Computing Environment to Solve the 768-bit {RSA} Challenge},
290 publisher = {{S}pringer-{V}erlag },
291 journal = {Cluster Computing },
298 @inproceedings{ch19:grid,
299 HAL_ID = {inria-00502899},
300 _URL = {http://hal.inria.fr/inria-00502899/en/},
301 title = { Using a Grid Platform for Slving Large Sparse Linear Systems over {GF}(2)},
302 author = {{K}leinjung, {T}. and {N}ussbaum, {L}. and {T}hom{\'e}, {E}.},
303 language = {{A}nglais},
304 affiliation = {{L}aboratory for {C}ryptologic {A}lgorithms - {LACAL} - {\'E}cole {P}olytechnique {F}{\'e}d{\'e}rale de {L}ausanne - {ALGORILLE} - {INRIA} {L}orraine - {LORIA} - {INRIA} - {CNRS} : {UMR}7503 - {U}niversit{\'e} {H}enri {P}oincar{\'e} - {N}ancy {I} - {U}niversit{\'e} {N}ancy {II} - {I}nstitut {N}ational {P}olytechnique de {L}orraine - {CARAMEL} - {INRIA} {N}ancy - {G}rand {E}st / {LORIA} - {INRIA} - {CNRS} : {UMR}7503 - {U}niversit{\'e} {H}enri {P}oincar{\'e} - {N}ancy {I} - {U}niversit{\'e} {N}ancy {II} - {I}nstitut {N}ational {P}olytechnique de {L}orraine },
305 booktitle = {11th {ACM}/{IEEE} {I}nternational {C}onference on {G}rid {C}omputing ({G}rid 2010) },
306 address = {{B}russels {B}elgique },
307 audience = {internationale },
312 @inproceedings{ch19:sle,
313 author = {A. Monakov and
316 title = {Automatically Tuning Sparse Matrix-Vector Multiplication
317 for {GPU} Architectures},
318 booktitle = {International conference on High-Performance
319 Embedded Architectures and Compilers,HiPEAC},
320 address= {Pisa, Italy},
323 ee = {http://dx.doi.org/10.1007/978-3-642-11515-8_10},
324 bibsource = {DBLP, http://dblp.uni-trier.de}
327 @inproceedings{ch19:bl,
328 author = {Peter L. Montgomery},
329 title = {{A Block Lanczos Algorithm for Finding Dependencies Over GF(2)}},
330 booktitle = {Theory and Application of Cryptographic Techniques},
337 author = {Nickolls, John and Buck, Ian and Garland, Michael and Skadron, Kevin},
338 title = {{Scalable Parallel Programming with CUDA}},
340 issue_date = {March/April 2008},
348 _url = {http://doi.acm.org/10.1145/1365490.1365500},
349 doi = {http://doi.acm.org/10.1145/1365490.1365500},
352 address = {New York, NY, USA},
356 author = {Nickolls, John and Dally, William J.},
357 title = {{The GPU Computing Era}},
358 journal = {IEEE Micro},
367 publisher = {IEEE Computer Society Press},
368 address = {Los Alamitos, CA, USA},
369 keywords = {GPU computing, CUDA, scalable parallel computing, heterogeneous CPU\&\#x002B, GPU coprocessing, Tesla GPU architecture, Fermi GPU architecture, NVIDIA.},
372 @misc{ch19:cuda-guide,
374 url = {http://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Programming_Guide.pdf},
375 title = {{CUDA C Programming Guide}},
379 @misc{ch19:p-reduction,
380 author = {Mark Harris},
381 url = {http://developer.download.nvidia.com/compute/cuda/1_1/Website/projects/reduction/doc/reduction.pdf},
382 title = {{Optimizing parallel reduction in CUDA}},
386 @misc{ch19:rsa190-factored,
387 url = {http://www.mersenneforum.org/showthread.php?t=14177},
388 title = {{RSA190 factored}},
393 author = {{P. Gaudry et al.}},
394 title = {{CADO-NFS}},
395 note = {http://cado-nfs.gforge.inria.fr/},
400 author = "N. Bell and M. Garland",
401 title = {CUSP: Generic Parallel Algorithms for Sparse Matrix and Graph Computations},
403 note = "http://cusplibrary.github.io/",
408 author = {Jason Papadopoulos},
410 url = {http://sourceforge.net/projects/msieve/},