Abstract
We present a generic approach to transforming one-sided MPI communication in the context of adjoint code. The adjoint allows us to compute gradients of multivariate function implementations at a computational cost that is independent of the size of these gradients. In this paper, we apply the adjoint model to codes containing one-side MPI communication. The Partitioned Global Address Space notation is used to derive the corresponding adjoint code. Our adjoint solutions rely on certain workarounds due to limited adjoint support in the current MPI standard. To avoid these, we provide a wish list for future MPI standards that potentially lead to a more efficient adjoint communication.
This work was supported by the Fond National de la Recherche of Luxembourg under grant PHD-09-145.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bendsten, C., Stauning, O.: FADBAD, a Flexible C++ Package for Automatic Differentiation Using the Forward and Backward Methods. Technical report, IMM-REP-1996-17, Department of Mathematical Modelling, Technical University of Denmark, Lyngby, Denmark (1996)
Griewank, A., Juedes, D., Utke, J.: Algorithm 755: ADOL-C: A Package for the Automatic Differentiation of Algorithms written in C/C++. ACM Trans. Math. Softw. 22(2), 131–167 (1996)
Griewank, A., Walter, A.: Evaluating Derivatives. Principles and Techniques of Algorithmic Differentiation, 2nd edn. SIAM, Philadelphia (2008)
Gropp, W., Lusk, E., Thakur, R.: Using MPI-2: Advanced Features of the Message-Passing Interface. MIT Press, Cambridge (1999)
Hovland, P., Bischof, C.: Automatic Differentiation for Message-Passing Parallel Programs. In: IPPS 1998: Proceedings of the 12th International Parallel Processing Symposium. IEEE Computer Society, Washington, DC (1998)
Lotz, J., Leppkes, K., Naumann, U.: dco/c++ Derivative Code by Overloading in C++. Technical Report AIB-2011-06, RWTH Aachen (May 2012)
MPI Forum. MPI: A Message-Passing Interface Standard. Version 2.2 (September 4, 2009), http://www.mpi-forum.org (December 2009)
Naumann, U.: The Art of Differentiating Computer Programs. Society for Industrial and Applied Mathematics, Philadephia (2011)
Naumann, U., Hascoët, L., Hill, C., Hovland, P., Riehme, J., Utke, J.: A Framework for Proving Correctness of Adjoint Message-Passing Programs. In: Lastovetsky, A., Kechadi, T., Dongarra, J. (eds.) EuroPVM/MPI 2008. LNCS, vol. 5205, pp. 316–321. Springer, Heidelberg (2008)
Pascual, V., Hascoët, L.: TAPENADE for C. In: Advances in Automatic Differentiation. Lecture Notes in Computational Science and Engineering, vol. 64, pp. 199–209. Springer, Heidelberg (2008)
Schanen, M., Förster, M., Gendler, B., Naumann, U.: Compiler-based Differentiation of Numerical Simulation Codes. In: ICCGI 2011, The Sixth International Multi-Conference on Computing in the Global Information Technology, pp. 105–110. IARIA (2011)
Schanen, M., Förster, M., Naumann, U.: Second-Order Algorithmic Differentiation by Source Transformation of MPI Code. In: Keller, R., Gabriel, E., Resch, M., Dongarra, J. (eds.) EuroMPI 2010. LNCS, vol. 6305, pp. 257–264. Springer, Heidelberg (2010)
Schanen, M., Naumann, U., Hascoët, L., Utke, J.: Interpretative Adjoints for Numerical Simulation Codes using MPI. Procedia Computer Science 1(1), 1819–1827 (2010); ICCS 2010
Utke, J., Hascoët, L., Heimbach, P., Hill, C., Hovland, P., Naumann, U.: Toward Adjoinable MPI. In: Proceedings of the 23rd IEEE International Parallel & Distributed Processing Symposium. IEEE Computer Society, Washington, DC (2009)
Utke, J., Naumann, U., Fagan, M., Tallent, N., Strout, M., Heimbach, P., Hill, C., Wunsch, C.: OpenAD/F: A Modular, Open-Source Tool for Automatic Differentiation of Fortran Codes. ACM Transactions on Mathematical Software 34(4), 18:1–18:36 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schanen, M., Naumann, U. (2012). A Wish List for Efficient Adjoints of One-Sided MPI Communication. In: Träff, J.L., Benkner, S., Dongarra, J.J. (eds) Recent Advances in the Message Passing Interface. EuroMPI 2012. Lecture Notes in Computer Science, vol 7490. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33518-1_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-33518-1_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33517-4
Online ISBN: 978-3-642-33518-1
eBook Packages: Computer ScienceComputer Science (R0)