EN FR
EN FR
ROMA - 2017
ROMA - 2017
Project-Team Roma
Personnel
Overall Objectives
Research Program
Application Domains
Highlights of the Year
New Software and Platforms
New Results
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Dissemination
Bibliography
Project-Team Roma
Personnel
Overall Objectives
Research Program
Application Domains
Highlights of the Year
New Software and Platforms
New Results
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Dissemination
Bibliography


previous Previous | up Home


Bibliography

Publications of the year

Doctoral Dissertations and Habilitation Theses

Articles in International Peer-Reviewed Journals

  • 5C. Alias, A. Plesco.

    Optimizing Affine Control with Semantic Factorizations, in: ACM Transactions on Architecture and Code Optimization (TACO) , December 2017, vol. 14, no 4, 27 p.

    https://hal.inria.fr/hal-01470873
  • 6P. Amestoy, A. Buttari, J.-Y. L'Excellent, T. Mary.

    On the Complexity of the Block Low-Rank Multifrontal Factorization, in: SIAM Journal on Scientific Computing, 2017, vol. 39, no 4, pp. A1710 - A1740. [ DOI : 10.1137/16M1077192 ]

    https://hal.inria.fr/hal-01672943
  • 7G. Aupy, A. Benoit, S. Dai, L. Pottier, P. Raghavan, Y. Robert, M. Shantharam.

    Co-scheduling Amdahl applications on cache-partitioned systems, in: International Journal of High Performance Computing Applications, June 2017. [ DOI : 10.1177/1094342017710806 ]

    https://hal.archives-ouvertes.fr/hal-01670137
  • 8G. Aupy, J. Herrmann.

    Periodicity in optimal hierarchical checkpointing schemes for adjoint computations, in: Optimization Methods & Software, 2017, vol. 32, no 3, pp. 594-624. [ DOI : 10.1080/10556788.2016.1230612 ]

    https://hal.inria.fr/hal-01654632
  • 9A. Benoit, L. Lefèvre, A.-C. Orgerie, I. Raïs.

    Reducing the energy consumption of large scale computing systems through combined shutdown policies with multiple constraints, in: International Journal of High Performance Computing Applications, January 2018, vol. 32, no 1, pp. 176-188. [ DOI : 10.1177/1094342017714530 ]

    https://hal.inria.fr/hal-01557025
  • 10A. Benoit, L. Pottier, Y. Robert.

    Resilient co-scheduling of malleable applications, in: International Journal of High Performance Computing Applications, May 2017. [ DOI : 10.1177/1094342017704979 ]

    https://hal.archives-ouvertes.fr/hal-01670153
  • 11G. Bosilca, A. Bouteiller, A. Guermouche, T. Hérault, Y. Robert, P. Sens, J. Dongarra.

    A Failure Detector for HPC Platforms, in: International Journal of High Performance Computing Applications, 2017.

    https://hal.inria.fr/hal-01531522
  • 12L.-C. Canon, P.-C. Héam, L. Philippe.

    Controlling the Correlation of Cost Matrices to Assess Scheduling Algorithm Performance on Heterogeneous Platforms, in: Concurrency and Computation: Practice and Experience, June 2017. [ DOI : 10.1002/cpe.4185 ]

    https://hal.inria.fr/hal-01664629
  • 13L.-C. Canon, L. Philippe.

    On the Heterogeneity Bias of Cost Matrices for Assessing Scheduling Algorithms, in: IEEE Transactions on Parallel and Distributed Systems, June 2017.

    https://hal.inria.fr/hal-01664636
  • 14S. Di, Y. Robert, F. Vivien, F. Cappello.

    Toward an Optimal Online Checkpoint Solution under a Two-Level HPC Checkpoint Model, in: IEEE Transactions on Parallel and Distributed Systems, January 2017, vol. 28, no 1, 16 p. [ DOI : 10.1109/TPDS.2016.2546248 ]

    https://hal.inria.fr/hal-01353871
  • 15M. Maalej, V. Paisante, F. Magno Quintao Pereira, L. Gonnord.

    Combining Range and Inequality Information for Pointer Disambiguation, in: Science of Computer Programming, 2017, Final published version of https://hal.inria.fr/hal-01429777v2.

    https://hal.archives-ouvertes.fr/hal-01625402
  • 16D. Shantsev, P. Jaysaval, S. de la Kethulle de Ryhove, P. R. Amestoy, A. Buttari, J.-Y. L'Excellent, T. Mary.

    Large-scale 3-D EM modelling with a Block Low-Rank multifrontal direct solver, in: Geophysical Journal International, June 2017, vol. 209, no 3, pp. 1558 - 1571. [ DOI : 10.1093/gji/ggx106 ]

    https://hal.inria.fr/hal-01672952

International Conferences with Proceedings

  • 17G. Aupy, A. Benoit, L. Pottier, P. Raghavan, Y. Robert, M. Shantharam.

    Co-scheduling algorithms for cache-partitioned systems, in: APDCM 2017 - 19th Workshop on Advances in Parallel and Distributed Computational Models, Orlando (FL), United States, Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2017 IEEE International, IEEE, May 2017, pp. 1-10. [ DOI : 10.1109/IPDPSW.2017.60 ]

    https://hal.inria.fr/hal-01654660
  • 18G. Aupy, C. Brasseur, L. Marchal.

    Dynamic Memory-Aware Task-Tree Scheduling, in: IPDPS 2017 - 31st IEEE International Parallel & Distributed Processing Symposium, Orlando, United States, proceedings of IPDPS 2017, May 2017, 10 p.

    https://hal.inria.fr/hal-01472062
  • 19G. Aupy, A. Gainaru, V. Le Fèvre.

    Periodic I/O scheduling for super-computers, in: PMBS 2017 - 8th International Workshop High Performance Computing Systems. Performance Modeling, Benchmarking and Simulation, Denver (CO), United States, November 2017, pp. 1-22.

    https://hal.inria.fr/hal-01654645
  • 20G. Aupy, Y. Robert, F. Vivien.

    Assuming failure independence: are we right to be wrong?, in: FTS 2017 - 3rd International Workshop on Fault-Tolerant Systems, Honolulu (HI), United States, September 2017, pp. 1-8.

    https://hal.inria.fr/hal-01654639
  • 21A. Benoit, L. Lefèvre, A.-C. Orgerie, I. Raïs.

    Shutdown Policies with Power Capping for Large Scale Computing Systems, in: Euro-Par: International European Conference on Parallel and Distributed Computing, Santiago de Compostela, Spain, F. F. Rivera, T. F. Pena, J. C. Cabaleiro (editors), Lecture Notes in Computer Science, springer, August 2017, vol. 10417, pp. 134 - 146. [ DOI : 10.1109/COMST.2016.2545109 ]

    https://hal.archives-ouvertes.fr/hal-01589555
  • 22L.-C. Canon, L. Marchal, F. Vivien.

    Low-Cost Approximation Algorithms for Scheduling Independent Tasks on Hybrid Platforms, in: Euro-Par 2017: 23rd International European Conference on Parallel and Distributed Computing, Santiago de Compostela, Spain, Springer, August 2017.

    https://hal.inria.fr/hal-01559898
  • 23M. Faverge, J. Langou, Y. Robert, J. Dongarra.

    Bidiagonalization and R-Bidiagonalization: Parallel Tiled Algorithms, Critical Paths and Distributed-Memory Implementation, in: IPDPS'17 - 31st IEEE International Parallel and Distributed Processing Symposium, Orlando, United States, May 2017.

    https://hal.inria.fr/hal-01484113
  • 24A. Graillat, M. Moy, P. Raymond, B. Dupont De Dinechin.

    Parallel Code Generation of Synchronous Programs for a Many-core Architecture, in: Design, Automation and Test in Europe, Dresden, Germany, March 2018.

    https://hal.inria.fr/hal-01667594
  • 25L. Han, L.-C. Canon, H. Casanova, Y. Robert, F. Vivien.

    Checkpointing Workflows for Fail-Stop Errors, in: IEEE Cluster 2017, Honolulu, United States, September 2017.

    https://hal.inria.fr/hal-01559967
  • 26J. Herrmann, J. Kho, B. Uçar, K. Kaya, U. V. Catalyurek.

    Acyclic Partitioning of Large Directed Acyclic Graphs, in: CCGRID 2017 - 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, Madrid, Spain, May 2017, pp. 371-380. [ DOI : 10.1109/CCGRID.2017.101 ]

    https://hal.inria.fr/hal-01672010
  • 27M. Maalej, V. Paisante, R. Pedro, L. Gonnord, F. Pereira.

    Pointer Disambiguation via Strict Inequalities, in: Code Generation and Optimisation, Austin, United States, February 2017, pp. 134-147.

    https://hal.archives-ouvertes.fr/hal-01387031
  • 28L. Marchal, S. Mccauley, B. Simon, F. Vivien.

    Minimizing I/Os in Out-of-Core Task Tree Scheduling, in: 19th Workshop on Advances in Parallel and Distributed Computational Models, Orlando, United States, May 2017.

    https://hal.inria.fr/hal-01491969

Conferences without Proceedings

  • 29Y. Caniou, E. Caron, A. Kong Win Chang, Y. Robert.

    Budget-aware scheduling algorithms for scientific workflows on IaaS Cloud platforms, in: WORKS 2017 - 12th Workshop Workflows in Support of Large-Scale Science, Denver, United States, November 2017, 1 p.

    https://hal.archives-ouvertes.fr/hal-01678736
  • 30A. Kong Win Chang.

    Ordonnancement multi-objectifs de workflows dans le cloud : un modèle plus réaliste avec tâches de durée stochastique, in: Compas 2017 - Conférence d’informatique en Parallélisme, Architecture et Système, Sophia Antipolis, France, June 2017, pp. 1-7.

    https://hal.archives-ouvertes.fr/hal-01679699

Internal Reports

  • 31E. Agullo, A. Buttari, M. Byckling, A. Guermouche, I. Masliah.

    Achieving high-performance with a sparse direct solver on Intel KNL, Inria Bordeaux Sud-Ouest ; CNRS-IRIT ; Intel corporation ; Université Bordeaux, February 2017, no RR-9035, 15 p.

    https://hal.inria.fr/hal-01473475
  • 32C. Alias.

    Improving Communication Patterns in Polyhedral Process Networks, Inria Grenoble - Rhône-Alpes, December 2017, no RR-9131, pp. 1-13.

    https://hal.inria.fr/hal-01665155
  • 33P. R. Amestoy, A. Buttari, J.-Y. L'Excellent, T. Mary.

    Performance and Scalability of the Block Low-Rank Multifrontal Factorization on Multicore Architectures, INPT-IRIT ; CNRS-IRIT ; Inria-LIP ; UPS-IRIT, April 2017.

    https://hal.archives-ouvertes.fr/hal-01505070
  • 34P. Amestoy, J.-Y. L'Excellent, G. Moreau.

    On Exploiting Sparsity of Multiple Right-Hand Sides in Sparse Direct Solvers, ENS de Lyon ; Inria Grenoble - Rhone-Alpes, December 2017, no RR-9122, pp. 1-28.

    https://hal.inria.fr/hal-01649244
  • 35G. Aupy, L. Bautista Gomez, Y. Robert, F. Vivien.

    Revisiting temporal failure independence in large scale systems, Inria, December 2017, no RR-9134.

    https://hal.inria.fr/hal-01672404
  • 36G. Aupy, A. Benoit, S. Dai, L. Pottier, P. Raghavan, Y. Robert, M. Shantharam.

    Co-scheduling Amdahl applications on cache-partitioned systems, Inria, February 2017, no RR-9021, 33 p.

    https://hal.inria.fr/hal-01461157
  • 37G. Aupy, A. Gainaru, V. Le Fèvre.

    Periodic I/O scheduling for super-computers, Inria Bordeaux Sud-Ouest, February 2017, no RR-9037.

    https://hal.inria.fr/hal-01474553
  • 38G. Aupy, Y. Robert, F. Vivien.

    Assuming failure independence: are we right to be wrong?, Inria, July 2017, no RR-9078.

    https://hal.inria.fr/hal-01556292
  • 39O. Beaumont, T. Lambert, L. Marchal, B. Thomas.

    Matching-Based Assignement Strategies for Improving Data Locality of Map Tasks in MapReduce, Inria - Research Centre Grenoble – Rhône-Alpes ; Inria Bordeaux Sud-Ouest, February 2017, no RR-8968.

    https://hal.inria.fr/hal-01386539
  • 40A. Benoit, A. Cavelan, F. Cappello, P. Raghavan, Y. Robert, H. Sun.

    Coping with silent and fail-stop errors at scale by combining replication and checkpointing, University of Basel ; Ecole Normale Supérieure de Lyon - ENS LYON ; Vanderbilt University ; University of Tennessee Knoxville, USA ; Argonne National Laboratory, October 2017, no RR-9106.

    https://hal.inria.fr/hal-01616514
  • 41A. Benoit, A. Cavelan, F. Cappello, P. Raghavan, Y. Robert, H. Sun.

    Identifying the right replication level to detect and correct silent errors at scale, Inria Grenoble Rhône-Alpes, Université de Grenoble, March 2017, no RR-9047.

    https://hal.inria.fr/hal-01494678
  • 42A. Benoit, A. Cavelan, V. Le Fèvre, Y. Robert.

    Optimal checkpointing period with replicated execution on heterogeneous platforms, Inria, April 2017, no RR-9055.

    https://hal.inria.fr/hal-01504936
  • 43G. Bosilca, A. Bouteiller, A. Guermouche, T. Hérault, Y. Robert, P. Sens, J. Dongarra.

    A Failure Detector for HPC Platforms, Inria, February 2017, no RR-9024.

    https://hal.inria.fr/hal-01453086
  • 44Y. Caniou, E. Caron, A. Kong Win Chang, Y. Robert.

    Budget-aware scheduling algorithms for scientific workflows on IaaS cloud platforms, Inria, August 2017, no RR-9088, 27 p.

    https://hal.inria.fr/hal-01574491
  • 45Y. Caniou, E. Caron, A. Kong Win Chang, Y. Robert.

    Budget-aware scheduling algorithms for scientific workflows with stochastic task weights on IaaS Cloud platforms, Inria, November 2017, no RR-9128, pp. 1-28.

    https://hal.inria.fr/hal-01651149
  • 46F. Dufossé, K. Kaya, I. Panagiotas, B. Uçar.

    Further notes on Birkhoff-von Neumann decomposition of doubly stochastic matrices, Inria - Research Centre Grenoble – Rhône-Alpes, September 2017, no RR-9095.

    https://hal.inria.fr/hal-01586245
  • 47A. A. Fang, A. A. Cavelan, Y. Robert, A. A. Chien.

    Resilience for Stencil Computations with Latent Errors, Inria, March 2017, no RR-9042.

    https://hal.inria.fr/hal-01488409
  • 48R. Fontaine, L. Morel, L. Gonnord.

    Combining dataflow programming and polyhedral optimization, a case study, Inria Rhône-Alpes ; CITI - CITI Centre of Innovation in Telecommunications and Integration of services ; LIP - ENS Lyon, July 2017, no RT-0490, 40 p.

    https://hal.archives-ouvertes.fr/hal-01572439
  • 49L. Gonnord, S.-M. Bagoly, L. Morel.

    Static Analysis via Horn Encoding from synchronous Dataflow Programs, Université Lyon 1 Claude Bernard, LIP & INSA, CITI , October 2017, no RT-0492, 25 p.

    https://hal.inria.fr/hal-01614637
  • 50C. Gou, A. Benoit, L. Marchal.

    Memory-aware tree partitioning on homogeneous platforms, Inria Grenoble Rhône-Alpes, November 2017, no RR-9115, pp. 1-25.

    https://hal.inria.fr/hal-01644352
  • 51L. Han, L.-C. Canon, H. Casanova, Y. Robert, F. Vivien.

    Checkpointing Workflows for Fail-Stop Errors, Inria, November 2017, no RR-9068, 33 p.

    https://hal.inria.fr/hal-01525378
  • 52T. Hérault, Y. Robert, A. Bouteiller, D. Arnold, K. B. Ferreira, G. Bosilca, J. Dongarra.

    Optimal Cooperative Checkpointing for Shared High-Performance Computing Platforms, Inria, October 2017, no RR-9109, pp. 1-20.

    https://hal.inria.fr/hal-01621295
  • 53O. Kaya, Y. Robert, B. Uçar.

    Computing Dense Tensor Decompositions with Optimal Dimension Trees, Inria, July 2017, no RR-9080.

    https://hal.inria.fr/hal-01562399
  • 54L. Marchal, L.-C. Canon, F. Vivien.

    Low-Cost Approximation Algorithms for Scheduling Independent Tasks on Hybrid Platforms, Inria - Research Centre Grenoble – Rhône-Alpes, June 2017, no RR-9029.

    https://hal.inria.fr/hal-01475884
  • 55L. Marchal, S. Mccauley, B. Simon, F. Vivien.

    Minimizing I/Os in Out-of-Core Task Tree Scheduling, Inria, February 2017, no RR-9025.

    https://hal.inria.fr/hal-01462213
  • 56L. Marchal, H. Nagy, B. Simon, F. Vivien.

    Parallel scheduling of DAGs under memory constraints, LIP - ENS Lyon, 2017, no RR-9108.

    https://hal.inria.fr/hal-01620255
References in notes
  • 57Blue Waters Newsletter, dec 2012.
  • 58Blue Waters Resources, 2013.

    https://bluewaters.ncsa.illinois.edu/data
  • 59The BOINC project, 2013.

    http://boinc.berkeley.edu/
  • 60Final report of the Department of Energy Fault Management Workshop, December 2012.

    https://science.energy.gov/~/media/ascr/pdf/program-documents/docs/FaultManagement-wrkshpRpt-v4-final.pdf
  • 61System Resilience at Extreme Scale: white paper, 2008, DARPA.

    http://institute.lanl.gov/resilience/docs/IBM%20Mootaz%20White%20Paper%20System%20Resilience.pdf
  • 62IEEE 1666 Standard: SystemC Language Reference Manual, Open SystemC Initiative, 2011.

    http://www.accellera.org/
  • 63OSCI TLM-2.0 Language Reference Manual, Open SystemC Initiative (OSCI), June 2008.

    http://www.accellera.org/downloads/standards
  • 64Top500 List - November, 2011.

    http://www.top500.org/list/2011/11/
  • 65Top500 List - November, 2012.

    http://www.top500.org/list/2012/11/
  • 66The Green500 List - November, 2015.

    https://www.top500.org/green500/lists/2015/11/
  • 67C. Alias, A. Plesco.

    Data-aware Process Networks, Inria - Research Centre Grenoble – Rhône-Alpes, June 2015, no RR-8735, 32 p.

    https://hal.inria.fr/hal-01158726
  • 68I. Assayad, A. Girault, H. Kalla.

    Tradeoff exploration between reliability power consumption and execution time, in: Proceedings of SAFECOMP, the Conf. on Computer Safety, Reliability and Security, Washington, DC, USA, 2011.
  • 69H. Aydin, Q. Yang.

    Energy-aware partitioning for multiprocessor real-time systems, in: IPDPS'03, the IEEE Int. Parallel and Distributed Processing Symposium, 2003, pp. 113–121.
  • 70N. Bansal, T. Kimbrel, K. Pruhs.

    Speed Scaling to Manage Energy and Temperature, in: Journal of the ACM, 2007, vol. 54, no 1, pp. 1 – 39.

    http://doi.acm.org/10.1145/1206035.1206038
  • 71A. Benoit, L. Marchal, J.-F. Pineau, Y. Robert, F. Vivien.

    Scheduling concurrent bag-of-tasks applications on heterogeneous platforms, in: IEEE Transactions on Computers, 2010, vol. 59, no 2, pp. 202-217.
  • 72S. Blackford, J. Choi, A. Cleary, E. D'Azevedo, J. Demmel, I. Dhillon, J. Dongarra, S. Hammarling, G. Henry, A. Petitet, K. Stanley, D. Walker, R. C. Whaley.

    ScaLAPACK Users' Guide, SIAM, 1997.
  • 73S. Blackford, J. Dongarra.

    Installation Guide for LAPACK, LAPACK Working Note, June 1999, no 41, originally released March 1992.
  • 74A. Buttari, J. Langou, J. Kurzak, J. Dongarra.

    Parallel tiled QR factorization for multicore architectures, in: Concurrency: Practice and Experience, 2008, vol. 20, no 13, pp. 1573-1590.
  • 75J.-J. Chen, T.-W. Kuo.

    Multiprocessor energy-efficient scheduling for real-time tasks, in: ICPP'05, the Int. Conference on Parallel Processing, 2005, pp. 13–20.
  • 76S. Donfack, L. Grigori, W. Gropp, L. V. Kale.

    Hybrid Static/dynamic Scheduling for Already Optimized Dense Matrix Factorization, in: Parallel Distributed Processing Symposium (IPDPS), 2012 IEEE 26th International, 2012, pp. 496-507.

    http://dx.doi.org/10.1109/IPDPS.2012.53
  • 77J. Dongarra, J.-F. Pineau, Y. Robert, Z. Shi, F. Vivien.

    Revisiting Matrix Product on Master-Worker Platforms, in: International Journal of Foundations of Computer Science, 2008, vol. 19, no 6, pp. 1317-1336.
  • 78J. Dongarra, J.-F. Pineau, Y. Robert, F. Vivien.

    Matrix Product on Heterogeneous Master-Worker Platforms, in: 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, Salt Lake City, Utah, February 2008, pp. 53–62.
  • 79I. S. Duff, J. K. Reid.

    The multifrontal solution of indefinite sparse symmetric linear systems, in: "ACM Transactions on Mathematical Software", 1983, vol. 9, pp. 302-325.
  • 80I. S. Duff, J. K. Reid.

    The multifrontal solution of unsymmetric sets of linear systems, in: SIAM Journal on Scientific and Statistical Computing, 1984, vol. 5, pp. 633-641.
  • 81P. Feautrier, C. Lengauer.

    The Polyhedron Model, in: Encyclopedia of Parallel Programming, 2011.
  • 82A. Graillat, M. Moy, P. Raymond, B. Dupont De Dinechin.

    Parallel Code Generation of Synchronous Programs for a Many-core Architecture, in: Design, Automation and Test in Europe, Dresden, Germany, March 2018.

    https://hal.inria.fr/hal-01667594
  • 83L. Grigori, J. W. Demmel, H. Xiang.

    Communication avoiding Gaussian elimination, in: Proceedings of the 2008 ACM/IEEE conference on Supercomputing, Piscataway, NJ, USA, SC '08, IEEE Press, 2008, 29:1 p.

    http://dl.acm.org/citation.cfm?id=1413370.1413400
  • 84B. Hadri, H. Ltaief, E. Agullo, J. Dongarra.

    Tile QR Factorization with Parallel Panel Processing for Multicore Architectures, in: IPDPS'10, the 24st IEEE Int. Parallel and Distributed Processing Symposium, 2010.
  • 85J. W. H. Liu.

    The multifrontal method for sparse matrix solution: Theory and Practice, in: SIAM Review, 1992, vol. 34, pp. 82–109.
  • 86R. Melhem, D. Mossé, E. Elnozahy.

    The Interplay of Power Management and Fault Recovery in Real-Time Systems, in: IEEE Transactions on Computers, 2004, vol. 53, no 2, pp. 217-231.
  • 87A. J. Oliner, R. K. Sahoo, J. E. Moreira, M. Gupta, A. Sivasubramaniam.

    Fault-aware job scheduling for bluegene/l systems, in: IPDPS'04, the IEEE Int. Parallel and Distributed Processing Symposium, 2004, pp. 64–73.
  • 88G. Quintana-Ortí, E. Quintana-Ortí, R. A. van de Geijn, F. G. V. Zee, E. Chan.

    Programming Matrix Algorithms-by-Blocks for Thread-Level Parallelism, in: ACM Transactions on Mathematical Software, 2009, vol. 36, no 3.
  • 89Y. Robert, F. Vivien.

    Algorithmic Issues in Grid Computing, in: Algorithms and Theory of Computation Handbook, Chapman and Hall/CRC Press, 2009.
  • 90G. Zheng, X. Ni, L. V. Kale.

    A scalable double in-memory checkpoint and restart scheme towards exascale, in: Dependable Systems and Networks Workshops (DSN-W), 2012.

    http://dx.doi.org/10.1109/DSNW.2012.6264677
  • 91D. Zhu, R. Melhem, D. Mossé.

    The effects of energy management on reliability in real-time embedded systems, in: Proc. of IEEE/ACM Int. Conf. on Computer-Aided Design (ICCAD), 2004, pp. 35–40.


previous Previous | up Home