Abstract
The hydrodynamic approach to modeling astrophysics problems has several disadvantages in terms of the implementation of a parallel computing code. One of the main drawbacks is the low arithmetic intensity of the methods that implement the computational problem. This peculiarity produces the performance limitation associated with the performance limitations of the DRAM memory of high-performance computing systems. One of the solutions to this problem is data structuring based on the characteristics of processors and memory of a computer system on which supercomputer simulation is to be carried out. In this work, the authors use the specialized Intel SDLT library, which allows you to organize data in a special way that can help the compiler to vectorize a computational code for Intel server processors. The use of this library made it possible to speed up the computational code by fifty times, and for the first time bring the performance of some code functions to the performance limits of server processors on vector FMA instructions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kulikov, I.M., Chernykh, I.G., Snytnikov, A.V., Glinskiy, B.M., Tutukov, A.V.: AstroPhi: a code for complex simulation of dynamics of astrophysical objects using hybrid supercomputers. Comput. Phys. Commun. 186, 71–80 (2015). https://doi.org/10.1016/j.cpc.2014.09.004
Kulikov, I., Vorobyov, E.: Using the PPML approach for constructing a low-dissipation, operator-splitting scheme for numerical simulations of hydrodynamic flows. J. Comput. Phys. 317, 318–346 (2016). https://doi.org/10.1016/j.jcp.2016.04.057
Kulikov, I., et al.: A new parallel code based on a simple piecewise parabolic method for numerical modeling of colliding flows in relativistic hydrodynamics. Mathematics 10(11), 1865 (2022)
Kulikov, I.M., Chernykh, I.G., Glinskiy, B.M., Protasov, V.A.: An efficient optimization of HLL method for the second generation of Intel Xeon Phi processor. Lobachevskii J. Math. 39, 543–550 (2018). https://doi.org/10.1134/S1995080218040091
Kulikov, I., Chernykh, I., Tutukov, A.: A new hydrodynamic code with explicit vectorization instructions optimizations that is dedicated to the numerical simulation of astrophysical gas flow. I. numerical method, tests, and model problems. Astrophys. J. Suppl. Ser. 243, 1–15 (2019). https://doi.org/10.3847/1538-4365/ab2237
Kulikov, I.M., Chernykh, I.G., Tutukov, A.V.: A new parallel Intel Xeon Phi hydrodynamics code for massively parallel supercomputers. Lobachevskii J. Math. 39, 1207–1216 (2018). https://doi.org/10.1134/S1995080218090135
Kulikov, I., et al.: Using adaptive nested mesh code HydroBox3D for numerical simulation of type Ia supernovae: merger of carbon-oxygen white dwarf stars, collapse, and non-central explosion. In: Proceedings of the 2018 Ivannikov ISP RAS Open Conference ISPRAS (2018). https://doi.org/10.1109/ISPRAS.2018.00018
Popov, M., Ustyugov, S.: Piecewise parabolic method on local stencil for gasdynamic simulations. Comput. Math. Math. Phys. 47, 1970–1989 (2007). https://doi.org/10.1134/S0965542507120081
Popov, M., Ustyugov, S.: Piecewise parabolic method on a local stencil for ideal magnetohydrodynamics. Comput. Math. Math. Phys. 48, 477–499 (2008). https://doi.org/10.1134/S0965542508030111
Kulikov, I.: A new code for the numerical simulation of relativistic flows on supercomputers by means of a low-dissipation scheme. Comput. Phys. Commun. 257, 107532 (2020). https://doi.org/10.1016/j.cpc.2020.107532
Tutukov, A.V., Cherepashchuk, A.M.: Evolution of close binary stars: theory and observations. Phys.-Usp. 63, 209 (2020)
Mezcua, M.: Dwarf galaxies might not be the birth sites of supermassive black holes. Nat. Astron. 3, 6–7 (2019). https://doi.org/10.1038/s41550-018-0662-2
Miceli, M., et al.: Collisionless shock heating of heavy ions in SN 1987A. Nat. Astron. 3, 236–241 (2019). https://doi.org/10.1038/s41550-018-0677-8
Mitchell, N., Vorobyov, E., Hensler, G.: Collisionless stellar hydrodynamics as an efficient alternative to N-body methods. Mon. Not. R. Astron. Soc. 428, 2674–2687 (2013). https://doi.org/10.1093/mnras/sts228
Kulikov, I.: GPUPEGAS: a new GPU-accelerated hydrodynamic code for numerical simulations of interacting galaxies. Astrophys. J. Suppl. Ser. 214, 1–12 (2014). https://doi.org/10.1088/0067-0049/214/1/12
Pabst, C., et al.: Disruption of the Orion molecular core 1 by wind from the massive star \(\theta ^1\) Orionis C. Nature 565, 618–621 (2019). https://doi.org/10.1038/s41586-018-0844-1
Forbes, J., Krumholz, M., Goldbaum, N., Dekel, A.: Suppression of star formation in dwarf galaxies by photoelectric grain heating feedback. Nature 535, 523–525 (2016). https://doi.org/10.1038/nature18292
Willcox, D., Townsley, D., Calder, A., Denissenkov, P., Herwig, F.: Type Ia supernova explosions from hybrid carbon-oxygen-neon white dwarf progenitors. Astrophys. J. 832, 13 (2016). https://doi.org/10.3847/0004-637X/832/1/13
Spillane, T., et al.: \(^{12}\)C + \(^{12}\)C fusion reactions near the Gamow energy. Phys. Rev. Lett. 98, 122501 (2007)
Jiang, J.A., et al.: A hybrid type Ia supernova with an early flash triggered by helium-shell detonation. Nature 550, 80–83 (2017). https://doi.org/10.1038/nature23908
Terreran, G., et al.: Hydrogen-rich supernovae beyond the neutrino-driven core-collapse paradigm. Nat. Astron. 1, 713–720 (2017). https://doi.org/10.1038/s41550-017-0228-8
Mendygral, P.J., et al.: WOMBAT: a scalable and high-performance astrophysical magnetohydrodynamics code. Astrophys. J. Suppl. Ser. 228, 23 (2017). https://doi.org/10.3847/1538-4365/aa5b9c
Schneider, E., Robertson, B.: Cholla: a new massively parallel hydrodynamics code for astrophysical simulation. Astrophys. J. Suppl. Ser. 217, 24 (2015). https://doi.org/10.1088/0067-0049/217/2/24
Schneider, E., Robertson, B.: Introducing CGOLS: the cholla galactic outflow simulation suite. Astrophys. J. 860, 135 (2018). https://doi.org/10.3847/1538-4357/aac329
Schneider, E., Robertson, B., Thompson, T.: Production of cool gas in thermally driven outflows. Astrophys. J. 862, 56 (2018). https://doi.org/10.3847/1538-4357/aacce1
Collela, P.: Multidimensional upwind methods for hyperbolic conservation laws. J. Comput. Phys. 87, 171–200 (1990). https://doi.org/10.1016/0021-9991(90)90233-Q
Gardiner, T., Stone, J.: An unsplit Godunov method for ideal MHD via constrained transport in three dimensions. J. Comput. Phys. 227, 4123–4141 (2008). https://doi.org/10.1016/j.jcp.2004.11.016
Zhang, U., Schive, H., Chiueh, T.: Magnetohydrodynamics with GAMER. Astrophys. J. Suppl. Ser. 236, 50 (2018). https://doi.org/10.3847/1538-4365/aac49e
Benitez-Llambay, P., Masset, F.: FARGO3D: a new GPU-oriented MHD code. Astrophys. J. Suppl. Ser. 223, 11 (2016). https://doi.org/10.3847/0067-0049/223/1/11
Griffiths, M., Fedun, V., Erdelyi, R.: A fast MHD code for gravitationally stratified media using graphical processing units: SMAUG. J. Astrophys. Astron. 36, 197–223 (2015). https://doi.org/10.1007/s12036-015-9328-y
Pandolfi, M., D’Ambrosio, D.: Numerical instabilities in upwind methods: analysis and cures for the “carbuncle” phenomenon. J. Comput. Phys. 166, 271–301 (2000). https://doi.org/10.1006/jcph.2000.6652
Chauvat, Y., Moschetta, J.-M., Gressier, J.: Shock wave numerical structure and the carbuncle phenomenon. Int. J. Numer. Methods Fluids 47, 903–909 (2005). https://doi.org/10.1002/fld.916
Liou, M.S.: Mass flux schemes and connection to shock instability. J. Comput. Phys. 160, 623–648 (2000). https://doi.org/10.1006/jcph.2000.6478
Xu, K., Li, Z.: Dissipative mechanism in Godunov-type schemes. Int. J. Numer. Methods Fluids 37, 1–22 (2001). https://doi.org/10.1002/fld.160
Kim, S.-S., Kim, C., Rho, O.-H., Hong, S.K.: Cures for the shock instability: development of a shock-stable Roe scheme. J. Comput. Phys. 185, 342–374 (2003). https://doi.org/10.1016/S0021-9991(02)00037-2
Dumbser, M., Morschetta, J.-M., Gressier, J.: A matrix stability analysis of the carbuncle phenomenon. J. Comput. Phys. 197, 647–670 (2004). https://doi.org/10.1016/j.jcp.2003.12.013
Davis, S.F.: A rotationally biased upwind difference scheme for the Euler equations. J. Comput. Phys. 56, 65–92 (1984). https://doi.org/10.1016/0021-9991(84)90084-6
Levy, D.W., Powell, K.G., Van Leer, B.: Use of a rotated Riemann solver for the two-dimensional Euler equations. J. Comput. Phys. 106, 201–214 (1993). https://doi.org/10.1016/S0021-9991(83)71103-4
Ren, Y.-X.: A robust shock-capturing scheme based on rotated Riemann solvers. Comput. Fluids 32, 1379–1403 (2003). https://doi.org/10.1016/S0045-7930(02)00114-7
Nishikawa, H., Kitamura, K.: Very simple, carbuncle-free, boundary-layer-resolving, rotated-hybrid Riemann solvers. J. Comput. Phys. 227, 2560–2581 (2008). https://doi.org/10.1016/j.jcp.2007.11.003
Perepelkina, A., Levchenko, V.D.: Functionally arranged data for algorithms with space-time Wavefront. In: Sokolinsky, L., Zymbler, M. (eds.) PCT 2021. CCIS, vol. 1437, pp. 134–148. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-81691-9_10
Araudo A., Bosch-Ramon V., Romero G.: Gamma rays from cloud penetration at the base of AGN jets. Astron. Astrophys. 522 (2010)
Begelman, M., Blandford, R., Rees, M.: Theory of extragalactic radio sources. Rev. Mod. Phys. 56, 255–351 (1984)
Laing, R.: The sidedness of jets and depolarization in powerful extragalactic radio sources. Nature 331, 149–151 (1988)
Shakura, N., Sunyaev, R.: Black holes in binary systems. Observational appearance. Astron. Astrophys. 24, 337–355 (1973)
Bisnovatyi-Kogan, G., Blinnikov, S.: A hot corona around a black-hole accretion disk as a model for CYG X-1. Sov. Astron. Lett. 2, 191–193 (1976)
Artemova, Y., Bisnovatyi-Kogan, G., Igumenshchev, I., Novikov, I.: Black hole advective accretion disks with optical depth transition. Astroph. J. 637, 968–977 (2006)
Narayan, R., Yi, I.: Advection-dominated accretion: a self-similar solution. Astroph. J. Let. 428, L13–L16 (1994)
Glushak, A.P.: Microquasar jets in the supernova remnant G11.2-0.3. Astron. Rep. 58, 6–15 (2014)
Barkov, M.V., Bisnovatyi-Kogan, G.S.: Interaction of a cosmological gamma-ray burst with a dense molecular cloud and the formation of jets. Astron. Rep. 49, 24–35 (2005)
Istomin, Ya.N., Komberg, B.V.: Gamma-ray bursts as a result of the interaction of a shock from a supernova and a neutron-star companion. Astron. Reps. 46, 908–917 (2002)
Artyukh, V.S.: Phenomenological model for the evolution of radio galaxies such as Cygnus A. Astron. Rep. 59, 520–524 (2015)
Artyukh, V.S.: Effect of aberration on the estimated parameters of relativistic radio jets. Astron. Rep. 62, 436–439 (2018)
Butuzova, M.S.: Search for differences in the velocities and directions of the kiloparsec-scale jets of quasars with and without X-ray emission. Astron. Rep. 60, 313–321 (2016)
Butuzova, M.S.: The blazar OJ 287 jet from parsec to kiloparsec scales. Astron. Rep. 65, 635–644 (2021)
Sotomayor, P., Romero, G.: Nonthermal radiation from the central region of super-accreting active galactic nuclei. Astron. Astrophys. 664(A178) (2022)
Kulikov, I., Chernykh, I., Tutukov, A.: A new hydrodynamic model for numerical simulation of interacting galaxies on Intel Xeon Phi supercomputers. J. Phys: Conf. Ser. 719, 012006 (2016)
Glinsky, B., et al.: The co-design of astrophysical code for massively parallel supercomputers. In: Carretero, J., et al. (eds.) ICA3PP 2016. LNCS, vol. 10049, pp. 342–353. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49956-7_27
Akimova, E.N., Misilov, V.E., Kulikov, I.M., Chernykh, I.G.: OMPEGAS: optimized relativistic code for multicore architecture. Mathematics 10, 2546 (2022). https://doi.org/10.3390/math10142546
relax Intel Corporation. SIMD Data Layout Templates. https://www.intel.com/content/www/us/en/develop/documentation/oneapi-dpcpp-cpp-compiler-dev-guide-and-reference/top/compiler-reference/libraries/introduction-to-the-simd-data-layout-templates.html
Intel Corporation. Intel Advisor User Guide. https://www.intel.com/content/www/us/en/develop/documentation/advisor-user-guide/top.html
NERSC. Introduction to the Roofline model. https://www.nersc.gov/assets/Uploads/Tutorial-ISC2019-Intro-v2.pdf
Acknowledgements
Computations were performed on the NKS-1P supercomputer at the Siberian Supercomputer Center, Institute of Computational Mathematics and Mathematical Geophysics SB RAS, Novosibirsk, Russia. This work was supported by the Russian Science Foundation (project 23-11-00014) https://rscf.ru/project/23-11-00014/.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chernykh, I., Misilov, V., Akimova, E., Kulikov, I. (2023). The Effect of Data Structuring on the Parallel Efficiency of the HydroBox3D Relativistic Code. In: Voevodin, V., Sobolev, S., Yakobovskiy, M., Shagaliev, R. (eds) Supercomputing. RuSCDays 2023. Lecture Notes in Computer Science, vol 14388. Springer, Cham. https://doi.org/10.1007/978-3-031-49432-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-49432-1_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49431-4
Online ISBN: 978-3-031-49432-1
eBook Packages: Computer ScienceComputer Science (R0)