root / www / references.html @ 9
Historique | Voir | Annoter | Télécharger (11,61 ko)
| 1 | 1 | equemene | <HTML>
|
|---|---|---|---|
| 2 | 1 | equemene | <HEAD>
|
| 3 | 1 | equemene | <TITLE>HPL References</TITLE> |
| 4 | 1 | equemene | </HEAD>
|
| 5 | 1 | equemene | |
| 6 | 1 | equemene | <BODY
|
| 7 | 1 | equemene | BGCOLOR = "WHITE" |
| 8 | 1 | equemene | BACKGROUND = "WHITE" |
| 9 | 1 | equemene | TEXT = "#000000" |
| 10 | 1 | equemene | VLINK = "#000099" |
| 11 | 1 | equemene | ALINK = "#947153" |
| 12 | 1 | equemene | LINK = "#0000ff"> |
| 13 | 1 | equemene | |
| 14 | 1 | equemene | <H2>HPL References</H2> |
| 15 | 1 | equemene | |
| 16 | 1 | equemene | <STRONG>
|
| 17 | 1 | equemene | The list of references below contains some relevant published material |
| 18 | 1 | equemene | to this work. This list is provided for illustrative purposes, and |
| 19 | 1 | equemene | should be regarded as an initial starting point for the interested |
| 20 | 1 | equemene | reader. This list is by all means not meant to be exhaustive. |
| 21 | 1 | equemene | </STRONG><BR><BR> |
| 22 | 1 | equemene | |
| 23 | 1 | equemene | The references have been sorted in four categories and chronologically |
| 24 | 1 | equemene | listed within each category. The four categories are |
| 25 | 1 | equemene | <UL>
|
| 26 | 1 | equemene | <LI><A HREF="references.html#Linpack_Benchmark">Linpack Benchmark</A> |
| 27 | 1 | equemene | <LI><A HREF="references.html#parallel_LUfact">Parallel LU Factorization</A> |
| 28 | 1 | equemene | <LI><A HREF="references.html#recursiv_LUfact">Recursive LU Factorization</A> |
| 29 | 1 | equemene | <LI><A HREF="references.html#parallel_matmul">Parallel Matrix Multiply</A> |
| 30 | 1 | equemene | <LI><A HREF="references.html#parallel_trsolv">Parallel Triangular Solve</A> |
| 31 | 1 | equemene | </UL>
|
| 32 | 1 | equemene | <HR NOSHADE |
| 33 | 1 | equemene | |
| 34 | 1 | equemene | <H3<A ="Linpack_Benchmark">Linpack Benchmark</A></H3> |
| 35 | 1 | equemene | |
| 36 | 1 | equemene | <UL>
|
| 37 | 1 | equemene | |
| 38 | 1 | equemene | <! - 1979 ----------------------------------------------------------- !> |
| 39 | 1 | equemene | <LI><I>LINPACK Users Guide</I>, J. Dongarra, J. Bunch, C. Moler and |
| 40 | 1 | equemene | G. W. Stewart, SIAM, Philadelphia, PA, 1979. |
| 41 | 1 | equemene | |
| 42 | 1 | equemene | <! - 1989 ----------------------------------------------------------- !> |
| 43 | 1 | equemene | <LI><I>Performance of Various Computers Using Standard Linear Equations |
| 44 | 1 | equemene | Software</I>, J. Dongarra, Technical Report CS-89-85, University of
|
| 45 | 1 | equemene | Tennessee, 1989. (An updated version of this report can be found at |
| 46 | 1 | equemene | <A HREF="http://www.netlib.org/benchmark/performance.ps"> |
| 47 | 1 | equemene | http://www.netlib.org/benchmark/performance.ps</A>).
|
| 48 | 1 | equemene | |
| 49 | 1 | equemene | <! - 1991 ----------------------------------------------------------- !> |
| 50 | 1 | equemene | <LI><I>Towards Peak Parallel LINPACK Performance on 400</I>, |
| 51 | 1 | equemene | R. Bisseling and L. Loyens, Supercomputer, Vol. 45, pp. 20-27, 1991. |
| 52 | 1 | equemene | |
| 53 | 1 | equemene | <LI><I>Massively Parallel LINPACK Benchmark on the Intel Touchstone |
| 54 | 1 | equemene | DELTA and iPSC/860 Systems</I>, R. van de Geijn, 1991 Annual Users
|
| 55 | 1 | equemene | Conference Proceedings. Intel Supercomputer Users Group, Dallas, TX, |
| 56 | 1 | equemene | 1991. |
| 57 | 1 | equemene | |
| 58 | 1 | equemene | <LI><I>The LINPACK Benchmark on the AP 1000</I>, R. Brent, Frontiers, |
| 59 | 1 | equemene | 1992, pp. 128-135, McLean, VA, 1992. |
| 60 | 1 | equemene | |
| 61 | 1 | equemene | <! - 1993 ----------------------------------------------------------- !> |
| 62 | 1 | equemene | <LI><I>Implementation of BLAS Level 3 and LINPACK Benchmark on the |
| 63 | 1 | equemene | AP1000</I>, R. Brent and P. Strazdins, Fujitsu Scientific and Technical
|
| 64 | 1 | equemene | Journal, Vol. 5, No. 1, pp. 61-70, 1993. |
| 65 | 1 | equemene | |
| 66 | 1 | equemene | <! - 1994 ----------------------------------------------------------- !> |
| 67 | 1 | equemene | <LI><I>LU Factorization and the LINPACK Benchmark on the Intel |
| 68 | 1 | equemene | Paragon</I>, D. Womble, D. Greenberg, D. Wheat and S. Riesen, Sandia
|
| 69 | 1 | equemene | Technical Report, 1994. |
| 70 | 1 | equemene | |
| 71 | 1 | equemene | <! - 1995 ----------------------------------------------------------- !> |
| 72 | 1 | equemene | <LI><I>Massively Parallel Distributed Computing: Worlds First 281 |
| 73 | 1 | equemene | Gigaflop Supercomputer</I>, J. Bolen, A. Davis, B. Dazey, S. Gupta,
|
| 74 | 1 | equemene | G. Henry, D. Robboy, G. Schiffler, D. Scott, M. Stallcup, A. Taraghi, |
| 75 | 1 | equemene | S. Wheat from Intel SSD, L. Fisk, G. Istrail, C. Jong, R. Riesen, |
| 76 | 1 | equemene | L. Shuler, from Sandia National Laboratories, Proceedings of the Intel |
| 77 | 1 | equemene | Supercomputer Users Group 1995. |
| 78 | 1 | equemene | |
| 79 | 1 | equemene | <! - 1997 ----------------------------------------------------------- !> |
| 80 | 1 | equemene | <LI><I>High Performance Software on Intel Pentium Pro Processors or |
| 81 | 1 | equemene | Micro-Ops to TeraFLOPS</I>, B. Greer and G. Henry, Proceedings of the
|
| 82 | 1 | equemene | SuperComputing 1997 Conference, ACM SIGARCH - IEEE Computer Society |
| 83 | 1 | equemene | Press - ISBN: 0-89791-985-8, San Jose, CA, 1997. |
| 84 | 1 | equemene | |
| 85 | 1 | equemene | </UL>
|
| 86 | 1 | equemene | <! ------------------------------------------------------------------ !> |
| 87 | 1 | equemene | <HR NOSHADE |
| 88 | 1 | equemene | |
| 89 | 1 | equemene | <H3<A ="parallel_LUfact">Parallel LU Factorization</A></H3> |
| 90 | 1 | equemene | |
| 91 | 1 | equemene | <UL>
|
| 92 | 1 | equemene | |
| 93 | 1 | equemene | <! - 1986 ----------------------------------------------------------- !> |
| 94 | 1 | equemene | <LI><I>Communication Complexity of the Gaussian Elimination Algorithm |
| 95 | 1 | equemene | on Multiprocessors</I>, Y. Saad, Linear Algebra and Its Applications,
|
| 96 | 1 | equemene | Vol. 77, pp. 315-340, 1986. |
| 97 | 1 | equemene | |
| 98 | 1 | equemene | <! - 1988 ----------------------------------------------------------- !> |
| 99 | 1 | equemene | <LI><I>LU Factorization Algorithms on Distributed-Memory Multiprocessor |
| 100 | 1 | equemene | Architectures</I>, G. Geist and C. Romine, SIAM Journal on Scientific
|
| 101 | 1 | equemene | and Statistical Computing, Vol. 9, pp. 639-649, 1988. |
| 102 | 1 | equemene | |
| 103 | 1 | equemene | <! - 1989 ----------------------------------------------------------- !> |
| 104 | 1 | equemene | <LI><I>Parallel LU Decomposition on a Transputer Network</I>, |
| 105 | 1 | equemene | R. Bisseling and J. van der Vorst, Lecture Notes in Computer Sciences, |
| 106 | 1 | equemene | Springer-Verlag, Eds. G. van Zee and J. van der Vorst, Vol. 384, |
| 107 | 1 | equemene | pp. 61-77, 1989. |
| 108 | 1 | equemene | |
| 109 | 1 | equemene | <! - 1990 ----------------------------------------------------------- !> |
| 110 | 1 | equemene | <LI><I>The Distributed Solution of Linear Systems Using the Torus-Wrap |
| 111 | 1 | equemene | Data Mapping</I>, C. Ashcraft, ECA-TR-147, Boeing Computer Services,
|
| 112 | 1 | equemene | Seattle, WA, 1990. |
| 113 | 1 | equemene | |
| 114 | 1 | equemene | <LI><I>Experiments with Multicomputer LU-Decomposition</I>, E. van de |
| 115 | 1 | equemene | Velde, Concurrency: Practice and Experience, Vol. 2, pp. 1-26, 1990. |
| 116 | 1 | equemene | |
| 117 | 1 | equemene | <! - 1991 ----------------------------------------------------------- !> |
| 118 | 1 | equemene | <LI><I>A Taxonomy of Distributed Dense LU Factorization Methods</I>, |
| 119 | 1 | equemene | C. Ashcraft, ECA-TR-161, Boeing Computer Services, Seattle, WA, 1991. |
| 120 | 1 | equemene | |
| 121 | 1 | equemene | <! - 1994 ----------------------------------------------------------- !> |
| 122 | 1 | equemene | <LI><I>The Torus-Wrap Mapping for Dense Matrix Calculations on Massively |
| 123 | 1 | equemene | Parallel Computers</I>, B. Hendrickson and D. Womble, SIAM Journal on
|
| 124 | 1 | equemene | Scientific and Statistical Computing, Vol. 15, pp. 1201-1226, 1994. |
| 125 | 1 | equemene | |
| 126 | 1 | equemene | <LI><I>Scalability Issues in the Design of a Library for Dense Linear |
| 127 | 1 | equemene | Algebra</I>, J. Dongarra, R. van de Geijn and D. Walker, Journal of
|
| 128 | 1 | equemene | Parallel and Distributed Computing, Vol. 22, No. 3, pp. 523-537, 1994. |
| 129 | 1 | equemene | |
| 130 | 1 | equemene | <! - 1995 ----------------------------------------------------------- !> |
| 131 | 1 | equemene | <LI><I>Matrix Factorization using Distributed Panels on the Fujitsu |
| 132 | 1 | equemene | AP1000</I>, P. Strazdins, Proceedings of the IEEE First International
|
| 133 | 1 | equemene | Conference on Algorithms And Architectures for Parallel Processing |
| 134 | 1 | equemene | ICA3PP-95, Brisbane, 1995. |
| 135 | 1 | equemene | |
| 136 | 1 | equemene | <! - 1996 ----------------------------------------------------------- !> |
| 137 | 1 | equemene | <LI><I>The Design and Implementation of the ScaLAPACK LU, QR, and |
| 138 | 1 | equemene | Cholesky Factorization Routines</I>, J. Choi, J. Dongarra, S. Ostrouchov,
|
| 139 | 1 | equemene | A. Petitet, D. Walker and R. C. Whaley, Scientific Programming, Vol. 5, |
| 140 | 1 | equemene | pp. 173-184, 1996. |
| 141 | 1 | equemene | |
| 142 | 1 | equemene | </UL>
|
| 143 | 1 | equemene | <! ------------------------------------------------------------------ !> |
| 144 | 1 | equemene | <HR NOSHADE |
| 145 | 1 | equemene | |
| 146 | 1 | equemene | <H3<A ="recursiv_LUfact">Recursive LU Factorization</A></H3> |
| 147 | 1 | equemene | |
| 148 | 1 | equemene | <UL>
|
| 149 | 1 | equemene | |
| 150 | 1 | equemene | <! - 1997 ----------------------------------------------------------- !> |
| 151 | 1 | equemene | <LI><I>Locality of Reference in LU Decomposition with partial |
| 152 | 1 | equemene | pivoting</I>, S. Toledo, SIAM Journal on Matrix. Anal. Appl., Vol. 18,
|
| 153 | 1 | equemene | No. 4, 1997. |
| 154 | 1 | equemene | |
| 155 | 1 | equemene | <LI><I>Recursion Leads to Automatic Variable Blocking for Dense |
| 156 | 1 | equemene | Linear-Algebra Algorithms</I>, F. Gustavson, IBM Journal of Research
|
| 157 | 1 | equemene | and Development, Vol. 41, No. 6, pp. 737-755, 1997 |
| 158 | 1 | equemene | |
| 159 | 1 | equemene | </UL>
|
| 160 | 1 | equemene | <! ------------------------------------------------------------------ !> |
| 161 | 1 | equemene | <HR NOSHADE |
| 162 | 1 | equemene | |
| 163 | 1 | equemene | <H3<A ="parallel_matmul">Parallel Matrix Multiply</A></H3> |
| 164 | 1 | equemene | |
| 165 | 1 | equemene | <UL>
|
| 166 | 1 | equemene | |
| 167 | 1 | equemene | <! - 1990 ----------------------------------------------------------- !> |
| 168 | 1 | equemene | <LI><I>Matrix Algorithms on a Hypercube I: Matrix Multiplication</I>, |
| 169 | 1 | equemene | G. Fox, S. Otto and A. Hey, Parallel Computing, Vol. 3, pp. 17-31, 1987. |
| 170 | 1 | equemene | |
| 171 | 1 | equemene | <! - 1990 ----------------------------------------------------------- !> |
| 172 | 1 | equemene | <LI><I>Basic Matrix Subprograms for Distributed-Memory Systems</I>, |
| 173 | 1 | equemene | A. Elster, Proceedings of the Fifth Distributed-Memory Computing |
| 174 | 1 | equemene | Conference, Eds. D. Walker and Q. Stout, IEEE Press, pp. 311-316, 1990. |
| 175 | 1 | equemene | |
| 176 | 1 | equemene | <! - 1991 ----------------------------------------------------------- !> |
| 177 | 1 | equemene | <LI><I>The Parallelization of Level 2 and 3 BLAS Operations on |
| 178 | 1 | equemene | Distributed-Memory Machines</I>, M. Aboelaze, N. Chrisochoides
|
| 179 | 1 | equemene | and E. Houstis, CSD-TR-91-007, Purdue University, West Lafayette, |
| 180 | 1 | equemene | IN, 1991. |
| 181 | 1 | equemene | |
| 182 | 1 | equemene | <! - 1992 ----------------------------------------------------------- !> |
| 183 | 1 | equemene | <LI><I>The Multicomputer Toolbox Approach to Concurrent BLAS and LACS</I>, |
| 184 | 1 | equemene | R. Falgout, A. Skjellum, S. Smith and C. Still, Proceedings of the |
| 185 | 1 | equemene | Scalable High Performance Computing Conference SHPCC-92, IEEE Computer |
| 186 | 1 | equemene | Society Press, 1992. |
| 187 | 1 | equemene | |
| 188 | 1 | equemene | <! - 1994 ----------------------------------------------------------- !> |
| 189 | 1 | equemene | <LI><I>A High Performance Matrix Multiplication Algorithm on a |
| 190 | 1 | equemene | Distributed-Memory Parallel Computer, Using Overlapped Communication</I>,
|
| 191 | 1 | equemene | R. Agarwal, F. Gustavson and M. Zubair, IBM Journal or Research and |
| 192 | 1 | equemene | Development, Vol. 38, No. 6, pp. 673-681, 1994. |
| 193 | 1 | equemene | |
| 194 | 1 | equemene | <LI><I>PUMMA: Parallel Universal Matrix Multiplication Algorithms on |
| 195 | 1 | equemene | Distributed-Memory Concurrent Computers</I>, J. Choi, J. Dongarra and
|
| 196 | 1 | equemene | D. Walker, Concurrency: Practice and Experience, Vol. 6, No. 7, |
| 197 | 1 | equemene | pp. 543-570, 1994. |
| 198 | 1 | equemene | |
| 199 | 1 | equemene | <LI><I>Matrix Multiplication on the Intel Touchstone DELTA</I>, |
| 200 | 1 | equemene | S. Huss-Lederman, E. Jacobson, A. Tsao and G. Zhang, Concurrency: |
| 201 | 1 | equemene | Practice and Experience, Vol. 6, No. 7, pp. 571-594, 1994. |
| 202 | 1 | equemene | |
| 203 | 1 | equemene | <! - 1995 ----------------------------------------------------------- !> |
| 204 | 1 | equemene | <LI><I>A Three-Dimensional Approach to Parallel Matrix Multiplication</I>, |
| 205 | 1 | equemene | R. Agarwal, S. Balle, F. Gustavson, M. Joshi and P. Palkar, IBM Journal |
| 206 | 1 | equemene | or Research and Development, Vol. 39, No. 5, pp. 575-582, 1995. |
| 207 | 1 | equemene | |
| 208 | 1 | equemene | <! - 1995 ----------------------------------------------------------- !> |
| 209 | 1 | equemene | <LI><I>A High Performance Parallel Strassen Implementation</I>, |
| 210 | 1 | equemene | B. Grayson and R. van de Geijn, Parallel Processing Letters, Vol. 6, |
| 211 | 1 | equemene | No. 1, pp. 3-12, 1996. |
| 212 | 1 | equemene | |
| 213 | 1 | equemene | <! - 1997 ----------------------------------------------------------- !> |
| 214 | 1 | equemene | <LI><I>Parallel Implementation of BLAS: General Techniques for Level |
| 215 | 1 | equemene | 3 BLAS</I>, A. Chtchelkanova, J. Gunnels, G. Morrow, J. Overfelt and
|
| 216 | 1 | equemene | R. van de Geijn, Concurrency: Practice and Experience, Vol. 9, No. 9, |
| 217 | 1 | equemene | pp. 837-857, 1997. |
| 218 | 1 | equemene | |
| 219 | 1 | equemene | <LI><I>A Poly-Algorithm for Parallel Dense Matrix Multiplication on |
| 220 | 1 | equemene | Two-Dimensional Process Grid Topologies</I>, J. Li, R. Falgout and
|
| 221 | 1 | equemene | A. Skjellum, Concurrency: Practice and Experience, Vol. 9, No. 5, |
| 222 | 1 | equemene | pp. 345-389, 1997. |
| 223 | 1 | equemene | |
| 224 | 1 | equemene | <LI><I>SUMMA: Scalable Universal Matrix Multiplication Algorithm</I>, |
| 225 | 1 | equemene | R. van de Geijn and J. Watts, Concurrency: Practice and Experience, |
| 226 | 1 | equemene | Vol. 9, No. 4, pp. 255-274, 1997. |
| 227 | 1 | equemene | |
| 228 | 1 | equemene | </UL>
|
| 229 | 1 | equemene | <! ------------------------------------------------------------------ !> |
| 230 | 1 | equemene | <HR NOSHADE |
| 231 | 1 | equemene | |
| 232 | 1 | equemene | <H3<A ="parallel_trsolv">Parallel Triangular Solve</A></H3> |
| 233 | 1 | equemene | |
| 234 | 1 | equemene | <UL>
|
| 235 | 1 | equemene | |
| 236 | 1 | equemene | <! - 1988 ----------------------------------------------------------- !> |
| 237 | 1 | equemene | <LI><I>Parallel Solution Triangular Systems on Distributed-Memory |
| 238 | 1 | equemene | Multiprocessors</I>, M. Heath and C. Romine, SIAM Journal on Scientific
|
| 239 | 1 | equemene | and Statistical Computing, Vol. 9, pp. 558-588, 1988. |
| 240 | 1 | equemene | |
| 241 | 1 | equemene | <LI><I>A Parallel Triangular Solver for a Distributed-Memory |
| 242 | 1 | equemene | Multiprocessor</I>, G. Li and T. Coleman, SIAM Journal on Scientific
|
| 243 | 1 | equemene | and Statistical Computing, Vol. 9, No. 3, pp. 485-502, 1988. |
| 244 | 1 | equemene | |
| 245 | 1 | equemene | <! - 1989 ----------------------------------------------------------- !> |
| 246 | 1 | equemene | <LI><I>A New Method for Solving Triangular Systems on Distributed-Memory |
| 247 | 1 | equemene | Message-Passing Multiprocessor</I>, G. Li and T. Coleman, SIAM Journal
|
| 248 | 1 | equemene | on Scientific and Statistical Computing, Vol. 10, No. 2, pp. 382-396, |
| 249 | 1 | equemene | 1989. |
| 250 | 1 | equemene | |
| 251 | 1 | equemene | <! - 1991 ----------------------------------------------------------- !> |
| 252 | 1 | equemene | <LI><I>Parallel Triangular System Solving on a Mesh Network of |
| 253 | 1 | equemene | Transputers</I>, R. Bisseling and J. van der Vorst, SIAM Journal
|
| 254 | 1 | equemene | on Scientific and Statistical Computing, Vol. 12, pp. 787-799, 1991. |
| 255 | 1 | equemene | |
| 256 | 1 | equemene | </UL>
|
| 257 | 1 | equemene | <! ------------------------------------------------------------------ !> |
| 258 | 1 | equemene | |
| 259 | 1 | equemene | <HR NOSHADE |
| 260 | 1 | equemene | <CENTER |
| 261 | 1 | equemene | <A = "index.html"> [Home]</A> |
| 262 | 1 | equemene | <A HREF = "copyright.html"> [Copyright and Licensing Terms]</A> |
| 263 | 1 | equemene | <A HREF = "algorithm.html"> [Algorithm]</A> |
| 264 | 1 | equemene | <A HREF = "scalability.html"> [Scalability]</A> |
| 265 | 1 | equemene | <A HREF = "results.html"> [Performance Results]</A> |
| 266 | 1 | equemene | <A HREF = "documentation.html"> [Documentation]</A> |
| 267 | 1 | equemene | <A HREF = "software.html"> [Software]</A> |
| 268 | 1 | equemene | <A HREF = "faqs.html"> [FAQs]</A> |
| 269 | 1 | equemene | <A HREF = "tuning.html"> [Tuning]</A> |
| 270 | 1 | equemene | <A HREF = "errata.html"> [Errata-Bugs]</A> |
| 271 | 1 | equemene | <A HREF = "references.html"> [References]</A> |
| 272 | 1 | equemene | <A HREF = "links.html"> [Related Links]</A><BR> |
| 273 | 1 | equemene | </CENTER>
|
| 274 | 1 | equemene | <HR NOSHADE |
| 275 | 1 | equemene | </BODY |
| 276 | 1 | equemene | </HTML |