Custom code optimisation of selected numeric calculations in virtual machines for JIT compilers

• Autorzy: Żupnik M. , Miernik K. , Onderka Z.

Warianty tytułu

PL

Niestandardowe techniki optymalizacji wybranych zagadnień numerycznych dla komponentowych maszyn wirtualnych

• Języki publikacji: EN

Abstrakty

EN

The optimisation of calculations in selected virtual machines is described and non-conventional performance optimisation techniques for selected numerical expressions are proposed. The first presents mantissa expression transformation, while the second presents degrees to radians conversion. Considerations are illustrated by code and tests carried out in Java, MS.NET and Mono environments.

PL

W artykule przedstawiono dwie niestandardowe metody optymalizacji kodu dla obliczeń numerycznych w środowisku komponentowym maszyn wirtualnych. Obie techniki pozwalają na przyśpieszenie operacji matematycznych - pierwsza obliczenia mantysy liczby rzeczywistej, druga konwersji stopniowej miary kąta na łukową. Do rozważań dołączono kody źródłowe oraz testy przeprowadzone w środo-wiskach Java, MS.NET oraz Mono.

Słowa kluczowe

EN

component platform; JIT; compilers; optimisation

PL

platforma komponentowa; JIT; kompilatory; optymalizacja

• Wydawca: Wydawnictwo Politechniki Śląskiej
• Czasopismo: Studia Informatica
• Rocznik: 2016
• Tom: Vol. 37, nr 1
• Strony: 55--70
• Opis fizyczny: Bibliogr. 23 poz.

Twórcy

autor

Żupnik M.

autor

Miernik K.

• AGH University of Science and Technology, Department of Geoinformatics and Applied Computer Science, al. A. Mickiewicza 30, 30-059 Cracow, Poland

autor

Onderka Z.

• AGH University of Science and Technology, Department of Geoinformatics and Applied Computer Science, al. A. Mickiewicza 30, 30-059 Cracow, Poland

Bibliografia

• Aho A.V., Sethi R., Ullman J.D.: Compilers: Principles, Techniques, and Tools. Addison Wesley Publishing Company, 2006.
• Artigas P.V., Gupta M., Midkiff S.P., Moreira J.E.: High Performance Numerical Computing in Java: Language and Compiler Issues. Languages and Compilers for Parallel Computing, Lecture Notes in Computer Science, Vol. 1863, 2000, p. 1÷17.
• Eaddy M., Feiner S.: Multi-Language Edit-and-Continue for the Masses. Columbia University Department of Computer Science Tech Report CUCS-01505, 2005.
• Gay D.M.: Using expression graphs in optimization algorithms. Abstract in Mixed Integer Nonlinear Optimization: Algorithmic Advances and Applications Workshop, 2008.
• Hoste K., Georges A., Eeckhout L.: Automated just-in-time compiler tuning. Code Generation and Optimization. Proceedings of the 8th annual IEEE/ACM international symposium on Code generation and optimization, Toronto 2010, p. 62÷72.
• Kalibera T., Tuma P.: Precise Regression Benchmarking with Random E?ects: Improving Mono Benchmark Results. Formal Methods and Stochastic Models for Performance Evaluation, LNCS, Vol. 4054, Springer, 2006, p. 63÷77.
• Kniotek M.: Lazy evaluation method in the component environments. Advances in Computer Science Research, Vol. 10, 2013, p. 53÷65.
• Kowal A., Piorkowski A., Danek T., Pieta A.: Analysis of selected component technologies efficiency for parallel and distributed seismic wave field modeling. Innovations and Advances in Computer Sciences and Engineering, Springer, 2010, p. 359÷362.
• Piorkowski A., Pieta A., Kowal A., Danek T.: The Performance of Geothermal Field Modeling in Distributed Component Environment. Innovations in Computing Sciences and Software Engineering, Springer, 2010, p. 279÷283.
• Microsoft Corp.: Microsoft Developer Network, http://msdn.microsoft.com.
• Oracle Corp.: Java SE 6 Documentation, http://download.oracle.com/javase/6/docs/.
• Oleszko K: The Efficiency of the Code Parallelization in Multi Core Environment on the Basis of Image Processing in 3D Space. New Trends in Networking, Computing,
• E-learning, Systems Sciences, and Engineering, Springer, 2015, p. 361÷364.
• Piorkowski A., Zupnik M.: Loop optimization in managed code environments with expressions evaluated only once. TASK Quarterly – Scientific Bulletin of Academic Computer Centre in Gdansk, Vol. 14, No. 4, Gdańsk 2010, p. 397÷404.
• Smith M.R.: Code Optimization Techniques for DSP Applications. 9th IEEE DSP Workshop, Hunt, Texas 2000.
• Kumar R.V., Narayanan B.L., Govindarajan R.: Dynamic Path Profile Aided Recompilation in a JAVA Just-In-Time Compiler. Proc. of the 9th Intl. Conf. on High Performance Computing (HiPC-02), Bangalore 2002.
• Xamarin: Mono Project, http://mono-project.com.
• Eckel B.: Thinking in Java. Prentice Hall Ptr, 2006.
• Lidin S.: Expert .NET 2.0 IL Assembler. Apress, 2006.
• Oracle: Enterprise Java Beans, http://www.oracle.com/technetwork/java/javaee/ejb/ index.html.
• Pivotal Software Inc.: Spring Framework, http://projects.spring.io/spring-framework/.
• Pico Container, http://picocontainer.com/.
• Google: Guice, https://github.com/google/guice/.
• Miernik K., Bogacz A., Kozubal A., Danek T., Wojdyła M.: Efficiency of Pareto joint inversion of 2D geophysical data using global optimization methods. General Assembly 2016, European Geosciences Union, Vienna, Austria 2016.

Uwagi

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.