Performance and accuracy of hardware-oriented native-, emulated- and mixed-precision solvers in FEM simulations

International Journal of Parallel, Emergent and Distributed Systems

Volumn 22, Issue 4, 2007, Pages 221-256

  Göddeke, Dominik ^a   Strzodka, Robert ^b   Turek, Stefan ^a  

^a TU DORTMUND UNIVERSITY   (Germany)

^b STANFORD UNIVERSITY   (United States)

Author keywords

Emulated precision; FEM; Graphics hardware; Large sparse linear equation systems; Mixed precision iterative refinement; Reconfigurable hardware

Indexed keywords

COMPUTER GRAPHICS; FIELD PROGRAMMABLE GATE ARRAYS (FPGA); FINITE ELEMENT METHOD; ITERATIVE METHODS; LINEAR EQUATIONS; PROBLEM SOLVING; VECTORS;

CONJUGATE GRADIENT (CG); EMULATED PRECISION; GRAPHICS HARDWARE; LARGE SPARSE LINEAR EQUATION SYSTEMS; MIXED PRECISION ITERATIVE REFINEMENT; RECONFIGURABLE HARDWARE;

LINEAR SYSTEMS;

EID: 33947588604     PISSN: 17445760     EISSN: 17445779     Source Type: Journal    
DOI: 10.1080/17445760601122076     Document Type: Review

References (64)

1. Wilkes, M., 2000, The memory gap (keynote). Solving the Memory Wall Problem Workshop, http://www.ece.neu.edu/conf/wall2k/wilkes1.pdf.
2. Ho, C.H., Leong, P., Luk, W., Wilton, S. and Lopez-Buedo, S., 2006, Virtual embedded blocks: a methodology for evaluating embedded elements in FPGAs. IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'06).
3. Dekker, T.J., 1971, A floating-point technique for extending the available precision, Numerische Mathematik, 18, 224-242.
4. Knuth, D.E., 1997, The Art of Computer Programming, Volume 2 (3rd ed.): Seminumerical Algorithms (Boston, MA: Addison-Wesley Longman Publishing Co., Inc.).
5. Moøller, O., 1965, Quasi double-precision in floating point addition. BIT, 5(1), 37-50.
6. Hida, Y., Li, X.S. and Bailey, D.H., 2001, Algorithms for quad-double precision floating point arithmetic. In: N. Burgess and L. Ciminiera (Eds.) Proceedings of the 15th Symposium on Computer Arithmetic, pp. 155-162.
7. Li, X.S., Demmel, J.W., Bailey, D.H., Henry, G., Hida, Y., Iskandar, J., Kahan, W., Kang, S.Y., Kapur, A., Martin, M.C., Thompson, B.J., Tung, T. and Yoo, D.J., 2002, Design, implementation and testing of extended and mixed precision BLAS, ACM Transactions on Mathematical Software, 28(2), 152-205.
8. Priest, D.M., 1991, Algorithms for arbitrary precision floating point arithmetic. 10th IEEE Symposium on Computer Arithmetic, pp. 132-143.
9. Shewchuk, J.R., 1997, Adaptive precision floating-point arithmetic and fast robust geometric predicates, Discrete & Computational Geometry, October 18(3), 305-363.
10. Bailey, D.H., Hida, Y., Jeyabalan, K., Li, X.S. and Thompson, B., 2006, High-precision software directory, http://crd.lbl.gov/~dhbailey/mpdist/
11. Free Software Foundation, Inc., GNU Multiple Precision Arithmetic Library, 4.2.1 edition, 2006. http://www.swox.com/gmp.
12. Wilkinson, J.H., 1963, Rounding Errors in Algebraic Processes (New York, NY: Dover Publications, Incorporated).
13. Martin, R.S., Peters, G. and Wilkinson, J.H., 1966, Handbook series linear algebra: iterative refinement of the solution of a positive definite system of equations, Numerische Mathematik, 8, 203-216.
14. Bowdler, H.J., Martin, R.S., Peters, G. and Wilkinson, J.H., 1966, Handbook series linear algebra: solution of real and complex systems of linear equations, Numerische Mathematik, 8, 217-234.
15. Demmel, J., Hida, Y., Kahan, W., Li, X.S., Mukherjeek, S. and Riedy, E.J., 2006, Error bounds from extra precise iterative refinement, ACM Transactions on Mathematical Software, June 32(2), 325-351.
16. Zielke, G. and Drygalla, V., 2003, Genaue Lösung linearer Gleichungssysteme, GAMM-Mitteilungen, 2(1), 7-107.
17. Turner, K. and Walker, H.F., 1992, Efficient high accuracy solutions with GMRES(m), SIAM Journal on Scientific and Statistical Computing archive, 13(3), 815-825.
18. Geddes, K.O. and Zheng, W.W., 2003, Exploiting fast hardware floating point in high precision computation. ISSAC'03: Proceedings of the 2003 International Symposium on Symbolic and Algebraic Computation (New York, NY: ACM Press), pp. 111-118.
19. Langou, J., Langou, J., Luszczek, P., Kurzak, J., Buttari, A. and Dongarra, J.J., 2006, Exploiting the performance of 32 bit floating point arithmetic in obtaining 64 bit accuracy (revisiting iterative refinement for linear systems). Proceedings of the ACM/IEEE SuperComputing 2006 (SC'06), to appear.
20. Stewart, G.W., 1973, Introduction to Matrix Computations (San Diego: Academic Press).
21. Higham, N.J., 2002, Accuracy and Stability of Numerical Algorithms, 2nd ed. (Philadelphia, PA: Society for Industrial and Applied Mathematics).
22. Hartenstein, R., 2001, A decade of reconfigurable computing: a visionary retrospective, Design, Automation and Test in Europe-DATE, March 2001.
23. Hartenstein, R., 2003, Data-stream-based computing: models and architectural resources. International Conference on Microelectronics, Devices and Materials (MIDEM 2003), Ocotober.
24. Sankaralingam, K., Nagarajan, R., Liu, H., Kim, C., Huh, J., Burger, D., Keckler, S.W. and Moore, C.R., 2003, Exploiting ILP, TLP, and DLP with the polymorphous TRIPS architecture. ISCA 2003, pp. 422-433.
25. Quo, Z., Najjar, W., Vahid, F. and Vissers, K., 2004, A quantitative analysis of the speedup factors of FPGAs over processors. ACM/IEEE International Symposium on Field-Programmable Gate Arrays.
26. Taylor, M.B., Kim, J.S., Miller, J., Wentzlaff, D., Ghodrat, F., Greenwald, B., Hoffman, H., Johnson, P., Lee, J., Lee, W., Ma, A., Saraf, A., Seneski, M., Shnidman, N., Strumpen, V., Frank, M., Amarasinghe, S.P. and Agarwal, A., 2002, The raw microprocessor: a computational fabric for software circuits and general purpose programs, IEEE Micro, 22(2), 25-35.
27. Suh, J., Kim, E., Crago, S.P., Srinivasan, L. and French, M.C., 2003, A performance analysis of PIM, stream processing, and tiled processing on memory-intensive signal processing kernels. In: D. DeGroot (Ed.) Proceedings of the 30th Annual International Symposium on Computer Architecture (ISCA-03), Volume 31 of Computer Architecture News June (New York, NY: ACM Press), pp. 410-421.
28. Strzodka, R., 2004, Hardware Efficient PDE Solvers in Quantized Image Processing. PhD thesis, University of Duisburg-Essen.
29. Fatahalian, K., Knight, T.J., Houston, M., Erez, M., Horn, D.R., Leem, L., Park, J.Y., Ren, M., Aiken, A., Dally, W.J. and Hanrahan, P., 2006, Sequoia: programming the memory hierarchy. Proceedings of the ACM/IEEE SuperComputing 2006 (SC'06), to appear.
30. Clearspeed, CSX600. www.clearspeed.com/downloads/CSX600Processor.pdf, 2006.
31. IBM Sony, Toshiba. Cell BE. http://www.ibm.com/developerworks/power/cell.
32. Mercury. Cell BE. http://www.mc.com/cell/.
33. Williams, S., Shalf, J., Oliker, L., Kamil, S., Husbands, P. and Yelick, K., 2006, The potential of the cell processor for scientific computing. CF '06: Proceedings of the 3rd Conference on Computing Frontiers (New York, NY: ACM Press), pp. 9-20.
34. AGEIA. PhysX. http://www.ageia.com/products/physx.html.
35. Göddeke, D. and Strzodka, R., 2006, Scientific computing on graphics hardware, tutorial at the 6th International Conference on Computational Science (ICCS 2006).
36. Owens, J.D., Luebke, D., Govindaraju, N., Harris, M.J., Krüger, J., Lefohn, A.E. and Purcell, T., 2005, A survey of general-purpose computation on graphics hardware. Eurographics 2005, State of the Art Reports, pp. 21-51.
37. GPGPU. General-purpose computation using graphics hardware, http://www.gpgpu.org.
38. Strzodka, R., Doggett, M. and Kolb, A., 2005, Scientific computation for simulations on programmable graphics hardware, Simulation Modelling Practice and Theory, Special Issue: Programmable Graphics Hardware, 13(8), 667-680.
39. Hillesland, K. and Lastra, A., 2004, GPU floating-point paranoia. Proceedings of GP2.
40. Daumas, M., Da Graça, G. and Detour, D., 2006, Caractéristiques arithmétiques des processeurs graphiques. Symposium en Architecture de Machines.
41. Da Graça, G. and Defour, D., 2006, Implementation of float-float operators on graphics hardware. 7th Conference on Real Numbers and Computers, RNC7, pp. 23-32.
42. Hitz, M.A. and Payne, B.R., 2006, Implementation of residue number systems on GPUs. ACM SIGGRAPH Conference Abstracts and Applications.
43. Thall, A., 2006, Extended-precision floating-point numbers for GPU computation. ACM SIGGRAPH Conference Abstracts and Applications.
44. Dale, K., Sheaffer, J.W., Kumar, V.V., Luebke, D.P., Humphreys, G. and Skadron, K., 2006, Applications of small-scale reconfigurability to graphics processors. Proceedings of the International Workshop on Applied Reconfigurable Computing (ARC2006) (Berlin: Springer).
45. Belanovic, P. and Leeser, M., 2002, A library of parameterized floating-point modules and their use. FPL'02: Proceedings of the Reconfigurable Computing Is Going Mainstream, 12th International Conference on Field-Programmable Logic and Applications (London: Springer-Verlag), pp. 657-666.
46. Fang, F., Chen, T. and Rutenbar, R., 2002, Lightweight floating-point arithmetic: case study of inverse discrete cosine transform, EURASIP Journal on Signal Processing, Special Issue on Applied Implementation of DSP and Communication Systems, 879-892.
47. Gaffar, A.A., Mencer, O., Luk, W. and Cheung, P.Y.K., 2004, Unifying bit-width optimisation for fixed-point and floating-point designs. 12th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM04), pp. 79-88.
48. Liang, J., Tessier, R. and Mencer, O., 2003, Floating point unit generation and evaluation for FPGAs. FCCM'03: Proceedings of the 11th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (Washington, DC: IEEE Computer Society), p. 185.
49. Dido, J., Geraudie, N., Loiseau, L., Payeur, O., Savaria, Y. and Poirier, D., 2002, A flexible floating-point format for optimizing data-paths and operators in FPGA based DSPs. FPGA'02: Proceedings of the 2002 ACM/SIGDA 10th International Symposium, on Field Programmable Gate Arrays (New York, NY: ACM Press), pp. 50-55.
50. Govindu, G., Zhuo, L., Choi, S. and Prasanna, V., 2004, Analysis of high-performance floating-point arithmetic on FPGAs. 18th International Parallel and Distributed Processing Symposium (IPDPS04), Workshop 3, p. 149b.
51. Matousek, R., Tichy, M., Phol, Z., Kadlec, J., Softley, C. and Coleman, N., 2002, Logarithmic number systems and floating-point arithmetics on FPGA. 12th International Conference on Field Programmable Logic and Applications (London: Springer-Verlag), pp. 627-636.
52. Haselman, M., Beauchamp, M., Wood, A., Hauck, S., Underwood, K. and Hemmert, K.S., 2005, A comparison of floating point and logarithmic number systems on FPGAs. 13th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'05), pp. 181-190.
53. Bondalapati, K. and Prasanna, V.K., 2002, Reconfigurable computing systems, Proceedings of the IEEE.
54. Compton, K. and Hauck, S., 2002, Reconfigurable computing: a survey of systems and software, ACM Computing Surveys, 34(2), 171-210.
55. Turek, S., 1999, Efficient Solvers for Incompressible Flow Problems: An Algorithmic and Computational Approach (Berlin: Springer).
56. Grajewski, M., Köster, M., Kilian, S. and Turek, S., 2005, Numerical analysis and practical aspects of a robust and efficient grid deformation method in the finite element context, Ergebnisberichte des Instituts für Angewandte Mathematik, Nr. 294, FB Mathematik, Universität Dortmund.
57. Industrial Light & Magic, OpenEXR, implementation of the half data type.
58. Strzodka, R. and Göddeke, D., 2006, Pipelined mixed precision algorithms on FPGAs for fast and accurate PDE solvers from low precision components. IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM 2006).
59. Göddeke, D., Strzodka, R. and Turek, S., 2005, Accelerating double precision FEM simulations with GPUs. In: F. Hülsemann, M. Kowarschik and U. Rüde (Eds.) 18th Symposium Simulations Technique volume Frontiers in Simulation, ASIM 2005 (Erlangen: SCS Publishing House e.V.), pp. 139-144.
60. Göddeke, D., Becker, Ch. and Turek, S., 2006, Integrating GPUs as fast co-processors into the parallel FE package FEAST. In: M. Becker and H. Szczerbicka (Eds.) Proceedings of the 19th Symposium on Simulation Technique, pp. 277-282.
61. Altieri, M., Becker, Ch. and Turek, S., 1999, On the realistic performance of linear algebra components in iterative solvers. In: H.-J. Bungartz, F. Durst and Chr. Zenger (Eds.) High Performance Scientific and Engineering Computing: Proceedings of the International FORTWIHR Conference on HPSEC, volume 8 of Lecture Notes in Computational Science and Engineering (Berlin: Springer), pp. 3-12.
62. Kilian, S., 2001, Ein verallgemeinertes Gebietszerlegungs-/ Mehrgitterkonzept auf Parallelrechnern. PhD thesis, Universität Dortmund.
63. Becker, Ch., Kilian, S. and Turek, S., 2002, Hardware-oriented numerics and concepts for PDE software. FUTURE 1095 (Amsterdam; International Conference on Computational Science ICCS2002 Elsevier), pp. 1-23.
64. Strzodka, R. and Göddeke, D., 2006, Mixed precision methods for convergent iterative schemes. Proceedings of the Workshop on Edge Computing Using New Commodity Architectures.