Research Article
BibTex RIS Cite

GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ

Year 2022, Volume: 27 Issue: 1, 251 - 270, 30.04.2022
https://doi.org/10.17482/uumfd.911736

Abstract

Astronomi, çok büyük boyutlu veriler ile çalışmak zorunda olan bir alandır. Bu büyük boyutlu verilerin işlenmesi ve bu verilerden bilgi çıkarımı işlemi çok uzun zaman aldığı için bu verileri modelleyen bilgisayar yazılımlarının performansı çok önemlidir. Bu çalışmada, Atacama Büyük Milimetre/Milimetre-altı Dizisi (Atacama Large Millimeter/Submillimeter Array- ALMA) isimli teleskop setinden gelen astronomik verileri modellemek için geliştirilen XCLASS (extended CASA Line Analysis Software Suite-genişletilmiş CASA Çizgi Analiz Yazılım Bölümü) adlı yazılımın çok yoğun hesaplamaların yapıldığı myXCLASS adlı bölümü, Grafik İşlemci Birimi (Graphics Processing Unit- GPU) programlama tekniği kullanılarak hızlandırılmıştır. GPU programlama ortamı olarak Birleşik Hesap Cihazı Mimarisi (Compute Unified Device Architecture- CUDA) kullanılmıştır. Uygulama, Tesla K20m isimli iki adet ekran kartı üzerinde test edilmiş, CPU- GPU çalışma süresi bakımından performans karşılaştırılması yapılmış ve ayrıntılı sonuçlar sunulmuştur. Elde edilen sonuçlar ile GPU programlama tekniği kullanılarak ALMA gibi gelişmiş gözlem araçlarından elde edilen çok büyük boyutlu astronomik verilerin modellenmesinde kullanılan yazılımlarda yüksek performans kazanımı sağlanacağı gösterilmiştir.

References

  • 1. Abe Y., Sasak H., Peres M., Inoue K., Murakami K., Kato S., (2012), Power and Performance Analysis of GPU-Accelerated Systems, HotPower.
  • 2. Arimilli R. K., Siegel D. W. (2002) Symetric Multiprocessing (SMP) System with Fully-Interconnected Heterogenous Microprocessors, International Business Machines Corpotation.
  • 3. Astronomical Image Processing System (2011), Erişim Adresi: http://www.aips.nrao.edu/index.shtml. (Erişim tarihi: 22.12.2019).
  • 4. Atamaca Large Millimeter/Submillimeter Array (2012), Erişim Adresi: http://www.almaobservatory.org/en/home/. (Erişim Tarihi: 25.12.2018).
  • 5. Awan M. G. ve Saeed F., (2017), n Out-of-Core GPU based dimensionality reduction algorithm for Big Mass Spectrometry Data and its application in bottom-up Proteomics, 550-555, doi:10.1145/3107411.3107466.
  • 6. Barsdell B. R., Barnes D. G. ve Fluke C. J. (2011) Fitting Galaxies on GPUs, Astronomical Data Analysis Software and Systems Conference, Massachusetts-USA, 451- 454.
  • 7. Cárcamo M., Román P.E., Casassus S., Moral V. ve Rannou F.R. (2018) Multi-GPU Maximum Entropy Image Synthesis for Radio Astronomy, Astronomy and Computing, 22, 16–27, doi:10.1016/j.ascom.2017.11.003.
  • 8. Combined Array for Research in Millimeter-wave Astronomy (2012), Erişim Adresi: https://www.mmarray.org/. (Erişim Tarihi: 22.12.2017).
  • 9. Common Astronomy Software Applications (2016), Erişim Adresi: https://casa.nrao.edu/. (Erişim Tarihi: 24.03.2018).
  • 10. Continuum and Line Analysis Single-dish Software (2010), Erişim Adresi: https://www.iram.fr/IRAMFR/GILDAS/doc/html/class-html/class.html. (Erişim Tarihi: 21.06.2019).
  • 11. Diaz, J., Muñoz-Caro, C. ve Niño, A. (2012) A Survey of Parallel Programming Models and Tools in the Multi and Many-Core Era, IEEE Transactions on Parallel and Distributed Systems, 8-23, 1369-1386, doi: 10.1109/TPDS.2011.308.
  • 12. eXtended CASA Line Analysis Software Suite (2016), Erişim Adresi: https://xclass.astro.uni-koeln.de/. (Erişim Tarihi: 14.03.2018).
  • 13. George B. R., Lightman A. P. (1979) Radiative Processes in Astrophysics, Haruard-Smithsonian Center for Astrophysics, Germany.
  • 14. Grenoble Image and Line Data Analysis Software. (2010), Erişim Adresi: https://www.iram.fr/IRAMFR/GILDAS/doc/pdf/gildas-intro.pdf. (Erişim Tarihi: 22.06.2019).
  • 15. Hall C. A., Meyer W. W. (2004) Optimal Error Bounds for Cubic Spline Interpolation, Journal of Approximation Theory, 2-16, 105–122, doi: 10.1016/0021-9045(76)90040-X.
  • 16. Image Reduction and Analysis Facility (2014), Erişim Adresi: http://ast.noao.edu/data/software. (Erişim Tarihi: 21.12.2019).
  • 17. Jang H., Park A. ve Jung K., (2008) Neural Network Implementation Using CUDA and OpenMP, Digital Image Computing: Techniques and Applications, Canberra, ACT, 155-161, doi: 10.1109/DICTA.2008.82.
  • 18. Mei Y., Wang F., Wang W., Chen L., Liu Y., Deng H., Dai W., Liu C. ve Yan Y. (2017) GPU-Based High-performance Imaging for Mingantu Spectral RadioHeliograph, Instrumentation and Methods for Astrophysics, 130, 983, doi: 10.1088/1538-3873/aa9608.
  • 19. NVIDIA and PGI Compiler. CUDA Fortran (2007), Erişim Adresi: https://developer.nvidia.com/cuda-fortran. (Erişim Tarihi: 08.04.2018).
  • 20. NVIDIA and PGI Compiler. Introduction to PGI CUDA Fortran (2008), Erişim Adresi: http://www.pgroup.com/lit/articles/insider/v1n3a2.htm. (Erişim Tarihi: 10.04.2018).
  • 21. NVIDIA Corporation (2017) PGI Compilers and Tools. CUDA Fortran Programming Guide and Reference.
  • 22. NVIDIA CUDA C Programming Guide (2010), Erişim Adresi: https://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Programming_Guide.pdf. (Erişim Tarihi: 20.03.2018).
  • 23. Plateau-de-bure (2010), Erişim Adresi: http://www.iram-institute.org/EN/plateau-de-bure.php/. (Erişim Tarihi: 22.12.2018).
  • 24. Ruetsch G., Fatica M. (2013) CUDA Fortran for Scientists and Engineers, NVIDIA Corporation, Santa Clara, USA.
  • 25. Sánchez-Monge Á. (2018) XCLASS: Automatic Line Fitting of ALMA Data Introduction and Tutorial, I. Physikalisches Institution Universität zu Köln.
  • 26. Submillimeter Array (2005), Erişim Adresi: http://sma1.sma.hawaii.edu/. (Erişim tarihi: 24.12.2018).
  • 27. Very Large Array, (2008), Erişim Adresi: http://www.vla.nrao.edu/. (Erişim Tarihi: 24.12.2018).
  • 28. Westerlund S. ve Harris C. (2015) Performance analysis of GPU-accelerated filter-based source finding for HI spectral line image data, Experimental Astronomy, 1-39, 95–117, doi: 10.1007/s10686-015-9445-2.

Implementing Accelerated Spectrum Analysis on XCLASS Software by Using GPU Programming Technique

Year 2022, Volume: 27 Issue: 1, 251 - 270, 30.04.2022
https://doi.org/10.17482/uumfd.911736

Abstract

Astronomy is a field that has to deal with massive amount of data. The performance of software modeling this data is very important because it takes a very long time to process and extract information from these massive amount of the data. In this study, myXCLASS which is very compute-intensive parts of extended CASA Line Analysis Software Suite (XCLASS) which is developed to model astronomical data taken from Atacama Large Millimeter/Submillimeter Array (ALMA) devices is accelerated using the Graphics Processing Unit (GPU) programming technique. Compute Unified Device Architecture (CUDA) is used as a GPU programming environment. The application is tested using two Tesla K20m GPU cards, CPU- GPU versions of the software are compared in terms of the time and obtained experimental results are presented in detail. The obtained experimental results show that high performance gain can be achieved in software used for modeling very large astronomical data obtained from advanced observation tools such as ALMA using GPU programming technique.

References

  • 1. Abe Y., Sasak H., Peres M., Inoue K., Murakami K., Kato S., (2012), Power and Performance Analysis of GPU-Accelerated Systems, HotPower.
  • 2. Arimilli R. K., Siegel D. W. (2002) Symetric Multiprocessing (SMP) System with Fully-Interconnected Heterogenous Microprocessors, International Business Machines Corpotation.
  • 3. Astronomical Image Processing System (2011), Erişim Adresi: http://www.aips.nrao.edu/index.shtml. (Erişim tarihi: 22.12.2019).
  • 4. Atamaca Large Millimeter/Submillimeter Array (2012), Erişim Adresi: http://www.almaobservatory.org/en/home/. (Erişim Tarihi: 25.12.2018).
  • 5. Awan M. G. ve Saeed F., (2017), n Out-of-Core GPU based dimensionality reduction algorithm for Big Mass Spectrometry Data and its application in bottom-up Proteomics, 550-555, doi:10.1145/3107411.3107466.
  • 6. Barsdell B. R., Barnes D. G. ve Fluke C. J. (2011) Fitting Galaxies on GPUs, Astronomical Data Analysis Software and Systems Conference, Massachusetts-USA, 451- 454.
  • 7. Cárcamo M., Román P.E., Casassus S., Moral V. ve Rannou F.R. (2018) Multi-GPU Maximum Entropy Image Synthesis for Radio Astronomy, Astronomy and Computing, 22, 16–27, doi:10.1016/j.ascom.2017.11.003.
  • 8. Combined Array for Research in Millimeter-wave Astronomy (2012), Erişim Adresi: https://www.mmarray.org/. (Erişim Tarihi: 22.12.2017).
  • 9. Common Astronomy Software Applications (2016), Erişim Adresi: https://casa.nrao.edu/. (Erişim Tarihi: 24.03.2018).
  • 10. Continuum and Line Analysis Single-dish Software (2010), Erişim Adresi: https://www.iram.fr/IRAMFR/GILDAS/doc/html/class-html/class.html. (Erişim Tarihi: 21.06.2019).
  • 11. Diaz, J., Muñoz-Caro, C. ve Niño, A. (2012) A Survey of Parallel Programming Models and Tools in the Multi and Many-Core Era, IEEE Transactions on Parallel and Distributed Systems, 8-23, 1369-1386, doi: 10.1109/TPDS.2011.308.
  • 12. eXtended CASA Line Analysis Software Suite (2016), Erişim Adresi: https://xclass.astro.uni-koeln.de/. (Erişim Tarihi: 14.03.2018).
  • 13. George B. R., Lightman A. P. (1979) Radiative Processes in Astrophysics, Haruard-Smithsonian Center for Astrophysics, Germany.
  • 14. Grenoble Image and Line Data Analysis Software. (2010), Erişim Adresi: https://www.iram.fr/IRAMFR/GILDAS/doc/pdf/gildas-intro.pdf. (Erişim Tarihi: 22.06.2019).
  • 15. Hall C. A., Meyer W. W. (2004) Optimal Error Bounds for Cubic Spline Interpolation, Journal of Approximation Theory, 2-16, 105–122, doi: 10.1016/0021-9045(76)90040-X.
  • 16. Image Reduction and Analysis Facility (2014), Erişim Adresi: http://ast.noao.edu/data/software. (Erişim Tarihi: 21.12.2019).
  • 17. Jang H., Park A. ve Jung K., (2008) Neural Network Implementation Using CUDA and OpenMP, Digital Image Computing: Techniques and Applications, Canberra, ACT, 155-161, doi: 10.1109/DICTA.2008.82.
  • 18. Mei Y., Wang F., Wang W., Chen L., Liu Y., Deng H., Dai W., Liu C. ve Yan Y. (2017) GPU-Based High-performance Imaging for Mingantu Spectral RadioHeliograph, Instrumentation and Methods for Astrophysics, 130, 983, doi: 10.1088/1538-3873/aa9608.
  • 19. NVIDIA and PGI Compiler. CUDA Fortran (2007), Erişim Adresi: https://developer.nvidia.com/cuda-fortran. (Erişim Tarihi: 08.04.2018).
  • 20. NVIDIA and PGI Compiler. Introduction to PGI CUDA Fortran (2008), Erişim Adresi: http://www.pgroup.com/lit/articles/insider/v1n3a2.htm. (Erişim Tarihi: 10.04.2018).
  • 21. NVIDIA Corporation (2017) PGI Compilers and Tools. CUDA Fortran Programming Guide and Reference.
  • 22. NVIDIA CUDA C Programming Guide (2010), Erişim Adresi: https://developer.download.nvidia.com/compute/DevZone/docs/html/C/doc/CUDA_C_Programming_Guide.pdf. (Erişim Tarihi: 20.03.2018).
  • 23. Plateau-de-bure (2010), Erişim Adresi: http://www.iram-institute.org/EN/plateau-de-bure.php/. (Erişim Tarihi: 22.12.2018).
  • 24. Ruetsch G., Fatica M. (2013) CUDA Fortran for Scientists and Engineers, NVIDIA Corporation, Santa Clara, USA.
  • 25. Sánchez-Monge Á. (2018) XCLASS: Automatic Line Fitting of ALMA Data Introduction and Tutorial, I. Physikalisches Institution Universität zu Köln.
  • 26. Submillimeter Array (2005), Erişim Adresi: http://sma1.sma.hawaii.edu/. (Erişim tarihi: 24.12.2018).
  • 27. Very Large Array, (2008), Erişim Adresi: http://www.vla.nrao.edu/. (Erişim Tarihi: 24.12.2018).
  • 28. Westerlund S. ve Harris C. (2015) Performance analysis of GPU-accelerated filter-based source finding for HI spectral line image data, Experimental Astronomy, 1-39, 95–117, doi: 10.1007/s10686-015-9445-2.
There are 28 citations in total.

Details

Primary Language Turkish
Subjects Software Engineering, Software Testing, Verification and Validation
Journal Section Research Articles
Authors

Yasemin Poyraz Koçak 0000-0002-1502-7260

Selçuk Sevgen 0000-0003-1443-1779

Publication Date April 30, 2022
Submission Date April 8, 2021
Acceptance Date February 13, 2022
Published in Issue Year 2022 Volume: 27 Issue: 1

Cite

APA Poyraz Koçak, Y., & Sevgen, S. (2022). GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 27(1), 251-270. https://doi.org/10.17482/uumfd.911736
AMA Poyraz Koçak Y, Sevgen S. GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ. UUJFE. April 2022;27(1):251-270. doi:10.17482/uumfd.911736
Chicago Poyraz Koçak, Yasemin, and Selçuk Sevgen. “GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ”. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi 27, no. 1 (April 2022): 251-70. https://doi.org/10.17482/uumfd.911736.
EndNote Poyraz Koçak Y, Sevgen S (April 1, 2022) GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi 27 1 251–270.
IEEE Y. Poyraz Koçak and S. Sevgen, “GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ”, UUJFE, vol. 27, no. 1, pp. 251–270, 2022, doi: 10.17482/uumfd.911736.
ISNAD Poyraz Koçak, Yasemin - Sevgen, Selçuk. “GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ”. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi 27/1 (April 2022), 251-270. https://doi.org/10.17482/uumfd.911736.
JAMA Poyraz Koçak Y, Sevgen S. GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ. UUJFE. 2022;27:251–270.
MLA Poyraz Koçak, Yasemin and Selçuk Sevgen. “GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ”. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, vol. 27, no. 1, 2022, pp. 251-70, doi:10.17482/uumfd.911736.
Vancouver Poyraz Koçak Y, Sevgen S. GPU PROGRAMLAMA TEKNİĞİ KULLANILARAK HIZLANDIRILMIŞ XCLASS YAZILIMI İLE SPEKTRUM ANALİZİNİN GERÇEKLEŞTİRİLMESİ. UUJFE. 2022;27(1):251-70.

Announcements:

30.03.2021-Beginning with our April 2021 (26/1) issue, in accordance with the new criteria of TR-Dizin, the Declaration of Conflict of Interest and the Declaration of Author Contribution forms fulfilled and signed by all authors are required as well as the Copyright form during the initial submission of the manuscript. Furthermore two new sections, i.e. ‘Conflict of Interest’ and ‘Author Contribution’, should be added to the manuscript. Links of those forms that should be submitted with the initial manuscript can be found in our 'Author Guidelines' and 'Submission Procedure' pages. The manuscript template is also updated. For articles reviewed and accepted for publication in our 2021 and ongoing issues and for articles currently under review process, those forms should also be fulfilled, signed and uploaded to the system by authors.