Abstract
In general, the majority of instructions bound for processing and executions consist of straight and branched constructs. A straight instruction set does not rely or depend on processes to reach complete execution. Unlike branched (or conditional) instructions, constructs require outcomes of other processes in order to peak its process executions. Previous works intended to first transform all branched instructions types to straight instructions types due to the structure and architecture of underlying compiler and processing elements known as predication process. While instruction-level parallelism (ILP) architecture ensures that many more parallel processes are executed by overlapping of these processes. This paper presents a comparative analysis of predicted and ILP techniques for processes executions of branched instructions constructs. The paper recommends ILP as the best way to deal with branched instructions in concurrent processes/executions because it supports multiple issues, execution speedups, improves memory utilization, and optimization of complier/processing elements based on selected parameters.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hennessy, J., Patterson, D.A.: Computer Architecture, 4th edn, pp. 2–104. Morgan Kaufmann Publishers Elsevier, San Francisco (2007)
Smith, J.E., Weiss, J.: PowerPC 601 and Alpha 21064: A tale of two RISCs. J. Comput. IEEE Press 27(6), 46–58 (1994)
Jack, W.D., Sanjay, J.: Improving instruction-level parallelism by loop unrolling and dynamic memory disambiguation. Unpublished M.Sc. thesis of Department of Computer Science, Thornton Hall, University of Virginia, Charlottesville, pp. 1−8 (1995)
Pepijn, W.: Simdization transformation strategies - polyhedral transformations and cost estimation. Unpublished M.Sc thesis, Department of Computer/Electrical Engineering, Delft University of Technology, Netherlands, pp. 1−77 (2012)
Vijay, S.P., Sarita, A.: Code transformations to improve memory parallelism. In: 32nd Annual ACM/IEEE International Symposium on Microarchitecture, pp. 147 − 155. IEEE Computer Society, Haifa (1999)
Pozzi, L.: Compilation techniques for exploiting instruction level parallelism, a survey. Department of Electrical and Information, University of Milan, Italy Technical Report 20133, pp. 1−31 (2010)
Parthasarathy, K.A.: Performance measures of superscalar processor. Int. J. Eng. Technol. IJET Publications, UK 1(3), 164–168 (2011)
Kaeli, D., Rosano, R.A.: Exposing instruction level parallelism in presence of loops. J. Comput. Syst. 8(1), 74–85 (2004)
Marcos, R.D.A., David, R.K.: Runtime predictability of loops. In: 4th Annual IEEE International Workshop on Workload Characterization, I.C., Ed., Texas, pp. 91−98 (2001)
Misra, S., Alfa, A.A., Adewale, O.S., Akogbe, A.M., Olaniyi, M.O.: A two-way loop algorithm for exploiting instruction-level parallelism in memory system. In: Beniamino, M., Sanjay, M., Ana, M., Rocha, A.C. (eds.) ICCSA 2014, LNCS, vol. 8583, pp. 255–264. Springer, Heidelbreg (2014)
Cantrell, C.D.: Computer system performance measurement. Lecture CE/EE 4304, The University of Texas, Dallas (2012). http://www.utdallas.edu/~cantrell/ee4304/perf.pdf
Flynn, M.J.: Computer Architecture: Pipelined and Parallel Processor Design, 1st edn, pp. 34–55. Jones and Bartlett Publishers, New York (1995)
Olukotun, K., Nayfeh, B.A., Hammond, L., Wilson, K., Chang, K.: The case for a single-chip multiprocessor. Conf. ACM SIGPLAN Not. Stanf. 31(9), 2–11 (1996)
Acknowledgements
We acknowledge the support and sponsorship provided by Covenant University through the Centre for Research, Innovation and Discovery (CUCRID).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Misra, S., Alfa, A.A., Ajagbe, K.D., Odusami, M., Abayomi-Alli, O. (2019). A Comparative Analysis of Techniques for Executing Branched Instructions. In: Shukla, R.K., Agrawal, J., Sharma, S., Singh Tomer, G. (eds) Data, Engineering and Applications. Springer, Singapore. https://doi.org/10.1007/978-981-13-6351-1_20
Download citation
DOI: https://doi.org/10.1007/978-981-13-6351-1_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-6350-4
Online ISBN: 978-981-13-6351-1
eBook Packages: Computer ScienceComputer Science (R0)