Some design aspects for VLIW architectures exploiting fine-grained parallelism

  • Wolfgang Karl
Paper Sessions Architectures: Fine Grain Parallelism
Part of the Lecture Notes in Computer Science book series (LNCS, volume 694)


Very Long Instruction Word Architectures (VLIW architectures) can exploit the fine-grained (instruction level) parallelism typically found in sequential-natured program code. A parallelizing compiler is used to restructure the program code. Sophisticated global compaction techniques have emerged that can effectively extract fine-grained parallelism from ordinary sequential natured program code.

In this paper we propose an effective mechanism for multiway branches and introduce a generalized conditional execution model for VLIW architectures. For the evaluation of VLIW architectures and their parallelizing compilers we use a simulation environment. This simulation environment comprises a parallelizing compiler and a highly configurable simulator for VLIW architectures. With this simulation environment the architectural enhancements proposed in this paper can be evaluated. Our studies are directed in finding high performance combinations of VLIW architectures and parallelizing compilers.


Condition Code Register File Control Flow Graph Core Transformation Instruction Word 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abnous, A., Potasman, R., Bagherzadeh, N., Nicolau, A.: A Percolation Based VLIW Architecture. Proceedings of the 1991 International Conference on Parallel Processing (1991) I-144–I-148. CRC PressGoogle Scholar
  2. 2.
    Aho, A. V., Sethi, R., Ullman, J. D.: Compilers — Priciples, Techniques and Tools. Addison Wesley Publishing Company, Reading Massachusetts (1986)Google Scholar
  3. 3.
    Aiken, A.: Compaction-Based Parallelization. PhD thesis, Department of Computer Science, Cornell University, Ithaca, New York 14853–7501 (1988)Google Scholar
  4. 4.
    Benitez, M. E., Davidson, J. W.: A Portable Global Optimizer and Linker. Proceedings of the SIGPLAN '88 Symposium on Programming Language Design and Implementation, SIGPLAN Notices, (1988) 329–338, Atlanta, GeorgiaGoogle Scholar
  5. 5.
    Benitez, M. E., Davidson, J. W.: Code Generation for Streaming: an Access/Execute Mechanism. ASPLOS-IV Proceedings, Fourth International Conference on Architectural Support for Programming Languages and Operating Systems (1991) 132–141, Santa Clara, CaliforniaGoogle Scholar
  6. 6.
    Böckle, G., Trosch, S.: A Simulator for VLIW Architectures. SFB-Bericht 342/16/90 A, Institut für Informatik, Technische Universität München, (1990)Google Scholar
  7. 7.
    Breternitz, M.: Architectural Synthesis of High Performance Application-Specific Processors. PhD thesis, Carnegie Mellon University (1991)Google Scholar
  8. 8.
    Callahan, D.: The Program Summary Graph and Flow-sensitive Interprocedural Data Flow Analysis. Proceedings of the SIGPLAN '88 Conference on Programming Language Design and Implementation, SIGPLAN Notices, (1988) 47–56, Atlanta, GeorgiaGoogle Scholar
  9. 9.
    Colwell, R. P., Nix, R. P., O'Donnell, J. J., Papworth, D. B., Rodman, P. K.: A VLIW Architecture for a Trace Scheduling Compiler. IEEE Transactions on Computers, C-37(8), (1988) 967–979CrossRefGoogle Scholar
  10. 10.
    Ebcioğlu, K.: Some Design Ideas for a VLIW Architecture for Sequential Natured Software. Proceedings of IFIP WG 10.3 Working Conference on Parallel Processing, (1988) 3–21, Pisa, Elsevier Science Publishers B. V.Google Scholar
  11. 11.
    Ebcioğlu, K., Nakatani, T.: A New Compilation Technique for Parallelizing Loops with Unpredictable Branches on a VLIW-Architecture. Proceedings 2nd Workshop on Compilers and Languages for Parallelism, University of Illinois, (1989)Google Scholar
  12. 12.
    Ebcioğlu, K., Nicolau, A.: A Global Ressource Constrained Parallelization Technique. International Conference on Supercomuting, (1989) Crete, GreeceGoogle Scholar
  13. 13.
    Fisher, J.: Trace-Scheduling: A Technique for Global Microcode Compaction. IEEE Transactions on Computers, C-30(7) (1981) 478–490Google Scholar
  14. 14.
    Fisher, J.: Very Long Instruction Word Architectures and the ELI-512. Proceedings of the 10th Symposium on Computer Architecture (1983) 140–150Google Scholar
  15. 15.
    Gasperoni, F.: Compilation Techniques for VLIW-Architectures. Research Report RC 14915, IBM Research Devision, T. J. Watson Research Center, Yorktown Heights, (1989) New YorkGoogle Scholar
  16. 16.
    Hsu, P. Y. T., Davidson, E. S.: Highly Concurrent Scalar Processing. Proceedings of the 13th Annual Symposium on Computer Architecture, (1986)Google Scholar
  17. 17.
    Johnson, M.: Superscalar Microprocessor Design. Prentice Hall, (1991) Englewood Cliffs, New Jersey 07632Google Scholar
  18. 18.
    Jouppi, N. P., Wall, D. W.: Available Instruction Level Parallelism for Superscalar and Superpipelined Machines. ASPLOS-III Proceedings, Third International Conference on Architectural Support for Programming Languages and Operating Systems, (1989) 272–282, Boston, MassachusettsGoogle Scholar
  19. 19.
    Kane, G.: Mips RISC Architecture. Prentice Hall, (1987) Englewood Cliffs, NY 07632Google Scholar
  20. 20.
    Karl, W. Architektureigenschaften und Parallelisierungsmethoden für Rechner mit Funktionspipelining. Dissertation, Institut für Informatik, Technische Universität, München, (1992) (to appear in B. I. Wissenschaftsverlag, Mannheim)Google Scholar
  21. 21.
    Labrousse, J., Slavenburg, G. A.: A 50 MHz Microprocessor with a Very Long Instruction Word. IEEE International Solid-State Circuit Conference (1990)Google Scholar
  22. 22.
    Nicolau, A.: Percolation Scheduling: A Parallel Compilation Technique. Technical Report TM 85-678, Department of Computer Science, Cornell University, (1985) Ithaca, New York 14853Google Scholar
  23. 23.
    Slavenburg, G. A., Huang, A. S., Lee, Y. C.: The LIFE Family of High Performance Single Chip VLIWs. HOT CHIPS Symposium (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Wolfgang Karl
    • 1
  1. 1.Institut für InformatikTechnische Universität MünchenMünchen 2

Personalised recommendations