Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

Dynamically increasing the scope of code motions during the high-level synthesis of digital circuits

Dynamically increasing the scope of code motions during the high-level synthesis of digital circuits

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IEE Proceedings - Computers and Digital Techniques — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

The quality of high-level synthesis results for designs with complex and nested conditionals and loops can be improved significantly by employing speculative code motions. Two techniques are presented that add scheduling steps to the branch of a conditional construct with fewer scheduling steps. This ‘balances’ or equalises the number of scheduling steps in the conditional branches and increases the scope for application of speculative code motions. These branch balancing techniques have been applied ‘dynamically’ during scheduling. The authors have implemented algorithms for dynamic branch balancing techniques in a C-to-VHDL high-level synthesis framework called Spark. The utility of these techniques is demonstrated by experimental results on four designs derived from two moderately complex applications, namely, MPEG-1 and the GIMP image processing tool. These results show that the two branch balancing techniques can reduce the cycles on the longest path through the design by up to 38% and the number of states in the controller by up to 37%.

References

    1. 1)
      • Gupta, S., Dutt, N.D., Gupta, R.K., Nicolau, A.: `SPARK: a high-level synthesis framework for applying parallelizing compiler transformations', Int. Conf. on VLSI Design, New Delhi, India, 4–8 January 2003.
    2. 2)
      • Gupta, S., Dutt, N.D., Gupta, R.K., Nicolau, A.: `Dynamic Conditional branch balancing during the high-level synthesis of control-intensive designs', Presented at Design, Automation and Test Conference, 3--7 March 2003, Munich, Germany.
    3. 3)
      • Gupta, S., Reshadi, M., Savoiu, N., Dutt, N.D., Gupta, R.K., Nicolau, A.: `Dynamic common sub-expression elimination during scheduling in high-level synthesis', Presented at Int. Symp. on System Synthesis, Kyoto, Japan, 2–4 October 2002.
    4. 4)
      • P. Kolling , B. Al-Hashimi , K.M. Abott . Efficient scheduling of behavioural descriptions in high-level synthesis. IEEE Proceedings-Computers and Digital Techniques , 2 , 75 - 82
    5. 5)
      • M. Girkar , C.D. Polychronopoulos . Automatic extraction of functional parallelism from ordinary programs. IEEE Trans. Parallel Distrib. Syst. , 2 , 166 - 178
    6. 6)
      • Spark Synthesis Benchmarks FTP site. ftp://ftp.ics.uci.edu/pub/spark/benchmarks, accessed 10 January 2002.
    7. 7)
      • Gupta, S., Savoiu, N., Kim, S., Dutt, N.D., Gupta, R.K., Nicolau, A.: `Speculation techniques for high level synthesis of control intensive designs', Design Automation Conf., 18--22 June 2001, Las Vegas, NV.
    8. 8)
      • S.S. Muchnick . (1997) Advanced compiler design and implementation.
    9. 9)
      • I. Radivojevic , F. Brewer . A new symbolic technique for control-dependent scheduling. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. , 1 , 45 - 57
    10. 10)
      • J. Fisher . Trace scheduling: a technique for global microcode compaction. IEEE Trans. on Comput. , 478 - 490
    11. 11)
      • dos Santos, L.C.V., Jess, J.A.G.: `A reordering technique for efficient code motion', Design Automation Conf., New Orleans, LA, 21–25 June 1999.
    12. 12)
      • dos Santos, L.C.V.: `A method to control compensation code during global scheduling', Presented at Workshop on Circuits, Systems and Signal Processing, Mierlo, The Netherlands, 27–28 November 1997, p. .
    13. 13)
      • Chaiyakul, V., Gajski, D.D., Ramachandran, L.: `High-level transformations for minimizing syntactic variances', Design Automation Conf., 14--18 June 1993, Dallas, TX.
    14. 14)
      • M. Rim , Y. Fann , R. Jain . Global scheduling with code-motions for high-level synthesis applications. IEEE Trans. Very Large Scale Integr. (VLSI) Systems , 3 , 379 - 392
    15. 15)
      • Wakabayashi, K., Tanaka, H.: `Global scheduling independent of control dependencies based on condition vectors', Design Automation Conf., 8--12 June 1992, Anaheim, CA.
    16. 16)
      • GNU Image Manipulation Program. http://www.gimp.org, accessed 10 January 2002.
    17. 17)
      • Gupta, S.: ‘Coordinated Coarse-Grain and Fine-Grain Optimizations for High-level Synthesis’. PhD thesis, University of California, Irvine, 2003.
    18. 18)
      • Gupta, S., Savoiu, N., Dutt, N.D., Gupta, R.K., Nicolau, A.: `Conditional speculation and its effects on performance and area for high-level synthesis', Presented at Int. Symp. on System Synthesis, Montreal, Canada, 30 September 2001.
    19. 19)
      • D. Gajski , N. Dutt , A. Wu , S. Lin . (1992) High level synthesis: introduction to chip and system design.
    20. 20)
      • Lakshminarayana, G., Raghunathan, A., Jha, N.K.: `Incorporating speculative execution into scheduling of control-flow intensive behavioral descriptions', Design Automation Conf., 15-19 June 1998, San Francisco, CA.
http://iet.metastore.ingenta.com/content/journals/10.1049/ip-cdt_20030839
Loading

Related content

content/journals/10.1049/ip-cdt_20030839
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
This is a required field
Please enter a valid email address