# Implementation of a block based neural branch predictor

Cadenas, O., Megson, G.M. and Jones, D.J. 2005. Implementation of a block based neural branch predictor. in: 8th Euromicro Conference on Digital System Design: proceedings IEEE . pp. 235-238

- Book chapter

Cadenas, O., Megson, G.M. and Jones, D.J. 2005. Implementation of a block based neural branch predictor. in: 8th Euromicro Conference on Digital System Design: proceedings IEEE . pp. 235-238

Chapter title | Implementation of a block based neural branch predictor |
---|---|

Authors | Cadenas, O., Megson, G.M. and Jones, D.J. |

Abstract | This paper contributes to a dynamic branch predictor algorithm based on a perceptron in two directions: Firstly, a new block form of computation is introduced that reduces theoretically by half the combinational critical path for computing a prediction. Secondly, implementation in FPGA hardware is fully developed for quantitative comparison purposes. FPGA circuits for a one-cycle block predictor produces 1.7 faster clock rates than a direct implementation of the original perceptron predictor. This faster clock allows to realize predictions with longer history lengths for the same hardware budget. |

Keywords | Combinational circuits, field programmable gate arrays, perceptrons, FPGA hardware, block based neural branch predictor, dynamic branch predictor algorithm, perceptron predictor |

Book title | 8th Euromicro Conference on Digital System Design: proceedings |

Page range | 235-238 |

Year | 2005 |

Publisher | IEEE |

Publication dates | |

Published | 2005 |

ISBN | 0769524338 |

Digital Object Identifier (DOI) | https://doi.org/10.1109/DSD.2005.49 |

Preconditioning 2D Integer Data for Fast Convex Hull Computations

Cadenas, J.O., Megson, G.M. and Luengo Hendriks, C.L. 2016. Preconditioning 2D Integer Data for Fast Convex Hull Computations. *PLoS ONE.* 11 (3) e0149860. https://doi.org/10.1371/journal.pone.0149860

An Empirical Evaluation of Preconditioning Data for Accelerating Convex Hull Computations

Cadenas, J.O. and Megson, G.M. 2015. *An Empirical Evaluation of Preconditioning Data for Accelerating Convex Hull Computations.* arXiv.

Median Filter Architecture by Accumulative Parallel Counters

Cadenas, J.O., Megson, G.M. and Sherratt, R.S. 2015. Median Filter Architecture by Accumulative Parallel Counters. *IEEE Transactions on Circuits and Systems II: Express Briefs.* 62 (7), pp. 661-665. https://doi.org/10.1109/TCSII.2015.2415655

DTAGS user manual

Megson, G.M. and Comish, D. Forthcoming. *DTAGS user manual.* Internal research group report.

Acceleration and visualization of Dynamic Network Optimization

Ye, Y., Megson, G.M. and Cadenas, J.O. 2014. Acceleration and visualization of Dynamic Network Optimization. in: 2014 International Conference on Computing, Networking and Communications (ICNC), February 3-6, 2014 in Honolulu, USA. IEEE . pp. 726-730

Rapid preconditioning of data for accelerating convex hull computations

Megson, G.M. and Cadenas, J.O. 2014. Rapid preconditioning of data for accelerating convex hull computations. *Electronics Letters.* 50 (4), pp. 270-272. https://doi.org/10.1049/el.2013.3507

A parallel quantum histogram architecture

Megson, G.M., Cadenas, O., Sherratt, R.S., Huerta, P. and Kao, W.C. 2013. A parallel quantum histogram architecture. *IEEE Transactions on Circuits and Systems II: Express Briefs.* 60 (7), pp. 437-441. https://doi.org/10.1109/TCSII.2013.2258263

C-slow retimed parallel histogram architectures for consumer imaging devices

Cadenas, O., Sherratt, R.S., Huerta, P., Wen-Chung, K. and Megson, G.M. 2013. C-slow retimed parallel histogram architectures for consumer imaging devices. *IEEE Transactions on Consumer Electronics.* 59 (2), pp. 291-295. https://doi.org/10.1109/TCE.2013.6531108

Parallel pipelined histogram architecture via C-slow retiming

Cadenas, J.O., Sherratt, R.S., Huerta, P., Kao, W.C. and Megson, G.M. 2013. Parallel pipelined histogram architecture via C-slow retiming. in: 2013 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, 11-14 Jan. 2013 IEEE . pp. 230-231

Asynchronous distributed parallelization of mobile network optimization algorithms

Ye, Y., Megson, G.M. and Cadenas, J.O. 2013. Asynchronous distributed parallelization of mobile network optimization algorithms. in: 2013 3rd International Conference on Wireless Communications, Vehicular Technology, Information Theory and Aerospace & Electronic Systems (VITAE), Atlantic City, NJ , 24-27 June 2013 IEEE . pp. 1-6

Distributed parallelization of greedy Mobile Network Optimization algorithms

Ye, Y., Cadenas, J.O. and Megson, G.M. 2013. Distributed parallelization of greedy Mobile Network Optimization algorithms. in: 21st International Conference on Software, Telecommunications and Computer Networks (SoftCOM), Primosten, 18-20 Sept. 2013 IEEE . pp. 1-5

Bit-index sort: A fast non-comparison integer sorting algorithm for permutations

Curi-Quintal, L.F., Cadenas, J.O. and Megson, G.M. 2013. Bit-index sort: A fast non-comparison integer sorting algorithm for permutations. in: 2013 International Conference on Technological Advances in Electrical, Electronics and Computer Engineering (TAEECE), Konya, 9-11 May 2013 IEEE . pp. 83-87

Application of presuppositions in motivating change

Megson, G.M. 2013. Application of presuppositions in motivating change. in: Forman, D. and McMahon, G. (ed.) Creating a coaching culture for managers in your organisation London Taylor & Francis.

Quantum linguistic patterning, Volume 2

Megson, G.M. 2012. *Quantum linguistic patterning, Volume 2.* Xlibris Corporation.

Fast median calculation method

Cadenas, O., Megson, G.M., Sherratt, R.S. and Huerta, P. 2012. Fast median calculation method. *Electronics Letters.* 48 (10), pp. 558-560. https://doi.org/10.1049/el.2012.0343

Quantum linguistic patterning, Volume 1

Megson, G.M. 2011. *Quantum linguistic patterning, Volume 1.* Xlibris Corporation.

KTP Final Report, Parallel Algorithms for Radio Air Interfaces

Megson, G.M. 2010. *KTP Final Report, Parallel Algorithms for Radio Air Interfaces.*

Distributed acceleration of mobile radio network optimisation algorithms

Ye, Y. and Megson, G.M. 2010. Distributed acceleration of mobile radio network optimisation algorithms. in: Proceedings of the 9th conference on Wireless telecommunications symposium IEEE . pp. 124-131

Parallelisation of the decision based network optimisation algorithms

Ye, Y. and Megson, G.M. 2009. Parallelisation of the decision based network optimisation algorithms. *International Conference on Parallel and Distibuted Processing Techniques and Applications.* pp. 118-124

Acceleration of radio network optimisation algorithms

Ye, Y. and Megson, G.M. 2009. Acceleration of radio network optimisation algorithms. *2nd International Multi-Conference on Engineering and Technological Innovation.* pp. 104-109

Poker playing with learning classifier systems

Reid, D. and Megson, G.M. 2009. Poker playing with learning classifier systems. in: Arabnia, H.R., Fuente, D.D.L. and Olivas, J.A. (ed.) Proceedings of the 2009 International Conference on Artificial Intelligence, ICAI 2009, July 13-16, 2009, Las Vegas Nevada, USA CSREA Press. pp. 297-303

Largest connected component of a star graph with faulty vertices

Yang, X., Megson, G.M., Tang, Y.Y. and Xing, Y. 2008. Largest connected component of a star graph with faulty vertices. *International Journal of Computer Mathematics.* 85 (12), pp. 1771-1778. https://doi.org/10.1080/00207160701619200

Generalized matching networks and their properties

Yang, X., Megson, G.M., Liao, X. and Cao, J. 2007. Generalized matching networks and their properties. *International Journal of Parallel, Emergent and Distributed Systems.* 22 (3), pp. 185-193. https://doi.org/10.1080/17445760601139039

Global exponential periodicity of a class of bidirectional associative memory networks with finite distributed delays

Yang, X., Li, C., Liao, X., Evans, D.J. and Megson, G.M. 2006. Global exponential periodicity of a class of bidirectional associative memory networks with finite distributed delays. *Applied Mathematics and Computation.* 171 (1), pp. 108-121. https://doi.org/10.1016/j.amc.2005.01.029

An oblivious shortest-path routing algorithm for fully connected cubic networks

Yang, X., Megson, G.M. and Evans, D.J. 2006. An oblivious shortest-path routing algorithm for fully connected cubic networks. *Journal of Parallel and Distributed Computing.* 66 (10), pp. 1294-1303. https://doi.org/10.1016/j.jpdc.2006.03.008

A lower bound on the size of k-neighborhood in generalized cubes

Yang, X., Megson, G.M., Cao, J. and Luo, J. 2006. A lower bound on the size of k-neighborhood in generalized cubes. *Applied Mathematics and Computation.* 179 (1), pp. 47-54. https://doi.org/10.1016/j.amc.2005.11.080

On two rational difference equations

Yang, X., Evans, D.J. and Megson, G.M. 2006. On two rational difference equations. *Applied Mathematics and Computation.* 176 (2), pp. 422-430. https://doi.org/10.1016/j.amc.2005.09.031

Pancyclicity of Möbius cubes with faulty nodes

Yang, X., Megson, G.M. and Evans, D.J. 2006. Pancyclicity of Möbius cubes with faulty nodes. *Microprocessors and Microsystems.* 30 (3), pp. 165-172. https://doi.org/10.1016/j.micpro.2005.11.001

A novel radix-3/9 algorithm for type-III generalized discrete Hartley transform

Yang, X., Megson, G.M., Xing, Y. and Evans, D.J. 2006. A novel radix-3/9 algorithm for type-III generalized discrete Hartley transform. *Journal of Circuits, Systems, and Computers.* 15 (2), pp. 301-312. https://doi.org/10.1142/S0218126606003064

Minimum neighborhood in a generalized cube

Yang, X., Cao, J., Megson, G.M. and Luo, J. 2006. Minimum neighborhood in a generalized cube. *Information Processing Letters.* 97 (3), pp. 88-93. https://doi.org/10.1016/j.ipl.2005.10.003

On the system of rational difference equations

Zhang, Y., Yang, X., Megson, G.M. and Evans, D.J. 2006. On the system of rational difference equations. *Applied Mathematics and Computation.* 176 (2), pp. 403-408. https://doi.org/10.1016/j.amc.2005.09.039

Two-pass hexagonal algorithm for distributed video processing

Wu, Y. and Megson, G.M. 2006. Two-pass hexagonal algorithm for distributed video processing. *Signal Processing for Wireless Communication (SPWC).* London 30 - 31 May 2006

Parallel linear hashtable motion estimation algorithm for parallel video processing

Wu, Y. and Megson, G.M. 2006. Parallel linear hashtable motion estimation algorithm for parallel video processing. in: International Symposium on Parallel Computing in Electrical Engineering: proceedings: 13-17 September 2006, Bialystok, Poland IEEE . pp. 357-362

Parallel linear hashtable motion estimation algorithm

Wu, Y. and Megson, G.M. 2006. Parallel linear hashtable motion estimation algorithm. in: Proceedings of the 2006 16th IEEE Signal Processing Society Workshop on Machine Learning for Signal Processing, Arlington, VA , 6-8 Sept 2006 IEEE . pp. 277-282

Verification and FPGA circuits of a block-2 fast path-based predictor

Cadenas, O. and Megson, G.M. 2006. Verification and FPGA circuits of a block-2 fast path-based predictor. in: International Conference on Field Programmable Logic and Applications, Madrid, Spain, 28-30 Aug. 2006. FPL '06. IEEE . pp. 213-218

FPGA organisation of a block-2 fast path-based predictor

Cadenas, O. and Megson, G.M. 2006. FPGA organisation of a block-2 fast path-based predictor. *FPL06: 16th International Conference on Field Programmable Logic and Applications.* Meliá Madrid Princesa, Madrid, Spain 28-30 August 2006 pp. 213-218

On the maximal connected component of a hypercube with faulty vertices III

Yang, X., Evans, D.J. and Megson, G.M. 2006. On the maximal connected component of a hypercube with faulty vertices III. *International Journal of Computer Mathematics.* 83 (1), pp. 27-37. https://doi.org/10.1080/00207160500113173

On a non-autonomous difference equation

Yang, X., Evans, D.J. and Megson, G.M. 2005. On a non-autonomous difference equation. *Applied Mathematics and Computation.* 168 (1), pp. 380-388. https://doi.org/10.1016/j.amc.2004.09.004

Maximum induced subgraph of a recursive circulant

Yang, X., Evans, D.J. and Megson, G.M. 2005. Maximum induced subgraph of a recursive circulant. *Information Processing Letters.* 95 (1), pp. 293-298. https://doi.org/10.1016/j.ipl.2005.03.004

A comparison-based diagnosis algorithm tailored for crossed cube multiprocessor systems

Yang, X., Megson, G.M. and Evans, D.J. 2005. A comparison-based diagnosis algorithm tailored for crossed cube multiprocessor systems. *Microprocessors and Microsystems.* 29 (4), pp. 169-175. https://doi.org/10.1016/j.micpro.2004.08.002

The locally twisted cubes

Yang, X., Evans, D.J. and Megson, G.M. 2005. The locally twisted cubes. *International Journal of Computer Mathematics.* 82 (4), pp. 401-413. https://doi.org/10.1080/0020716042000301752

Diameter of parallelogramic honeycomb torus

Yang, X., Megson, G.M., Tang, Y. and Evans, D.J. 2005. Diameter of parallelogramic honeycomb torus. *Computers & Mathematics with Applications.* 50 (8-9), pp. 1477-1486. https://doi.org/10.1016/j.camwa.2005.01.029

On the path-connectivity, vertex-pancyclicity, and edge-pancyclicity of crossed cubes

Yang, X. and Megson, G.M. 2005. On the path-connectivity, vertex-pancyclicity, and edge-pancyclicity of crossed cubes. *Neural, Parallel & Scientific Computations.* 13, pp. 107-118.

Linear hashtable method predicted hexagonal search algorithm with spatial related criterion

Wu, Y., Megson, G.M., Nie, Z. and Alavi, F.N. 2005. Linear hashtable method predicted hexagonal search algorithm with spatial related criterion. in: Kalviainen, H., Parkkinen, J. and Kaarna, A. (ed.) Image Analysis: 14th Scandinavian Conference, SCIA 2005, Joensuu, Finland, June 19-22, 2005: proceedings Berlin Springer.

Two-pass hexagonal algorithm with parallel implementation for video coding

Wu, Y. and Megson, G.M. 2005. Two-pass hexagonal algorithm with parallel implementation for video coding. in: EUROCON 2005: the International Conference on "Computer as a Tool": Belgrade, Serbia and Montenegro, November 21-24 2005 IEEE .

Two-pass hexagonal algorithm with improved hashtable structure for motion estimation

Wu, Y. and Megson, G.M. 2005. Two-pass hexagonal algorithm with improved hashtable structure for motion estimation. in: AVSS 2005 IEEE international conference on advanced video and signal based surveillance: September 15-16, 2005, Como, Italy IEEE . pp. 564-569

Two-pass hexagonal algorithm with improved hashtable structure for motion estimation

Wu, Y. and Megson, G.M. 2005. Two-pass hexagonal algorithm with improved hashtable structure for motion estimation. in: IEEE Conference on Advanced Video and Signal Based Surveillance, 2005. AVSS 2005 IEEE . pp. 564-569

Paralleled two-pass hexagonal algorithm for motion estimation

Wu, Y. and Megson, G.M. 2005. Paralleled two-pass hexagonal algorithm for motion estimation. in: Eighth International Conference on High Performance Computing in Asia Pacific Region: proceedings: 30 November-3 December, Beijing, China Los Alamitos, USA IEEE . pp. 451-456

Linear predicted two-pass hexagonal search algorithm for motion estimation

Wu, Y. and Megson, G.M. 2005. Linear predicted two-pass hexagonal search algorithm for motion estimation. *AC2005: 4th Chapter Conference on Applied Cybernetics 2005.* City University, London 7-8 September 2005

Linear predicted two-pass hexagonal algorithm with parallel implementation for motion estimation

Wu, Y. and Megson, G.M. 2005. Linear predicted two-pass hexagonal algorithm with parallel implementation for motion estimation. in: Proceedings of the Fifth IEEE International Symposium on Signal Processing and Information Technology, Athens, Greece, 18-21 December 2005. ISSPIT 2005 IEEE . pp. 191-196

Linear predicted hexagonal search algorithm with moments

Wu, Y. and Megson, G.M. 2005. Linear predicted hexagonal search algorithm with moments. in: Huang, D.S., Zhang, X.P. and Huang, G.B. (ed.) Advances in Intelligent Computing: International Conference on Intelligent Computing, ICIC 2005, Hefei, China, August 23-26, 2005, proceedings, Part I Berlin Springer.

Linear hashtable method and predicted hexagonal search algorithm with moments invariant

Wu, Y. and Megson, G.M. 2005. Linear hashtable method and predicted hexagonal search algorithm with moments invariant. *VVG05: the 2nd International Conference on Video, Vision and Graphics.* Heriot Watt University, Edinburgh 7-8 July 2005 pp. 195-202

Linear algorithm and hexagonal search based two-pass algorithm for motion estimation

Wu, Y. and Megson, G.M. 2005. Linear algorithm and hexagonal search based two-pass algorithm for motion estimation. in: Gagalowicz, A. and Philips, W. (ed.) Computer Analysis of Images and Patterns: 11th International Conference, CAIP 2005, Versailles, France, September 5-8, 2005: proceedings Berlin Springer.

Enhanced linear hashtable method predicted hexagonal search algorithm with moments

Wu, Y. and Megson, G.M. 2005. Enhanced linear hashtable method predicted hexagonal search algorithm with moments. in: Villanueva, J.J. (ed.) Proceedings of the fifth IASTED international conference on visualization, imaging, and image processing : September 7-9, 2005, Benidorm, Spain Acta Press. pp. 174-179

A new organization for a perceptron-based branch predictor and its FPGA implementation

Cadenas, O., Megson, G.M. and Jones, D.J. 2005. A new organization for a perceptron-based branch predictor and its FPGA implementation. in: Smailagic, A. and Ranganathan, N. (ed.) IEEE Computer Society annual symposium on VLSI: new frontiers in VLSI design Los Alamitos, USA IEEE . pp. 305-306

FPGA organization for the fast path-based neural branch predictor

Cadenas, O., Megson, G.M. and Jones, D.J. 2005. FPGA organization for the fast path-based neural branch predictor. in: 2005 IEEE International Conference on Field-Programmable Technology, National University of Singapore, Singapore, 11-14 Dec 2008: proceedings. IEEE . pp. 251-257

Global asymptotic stability in a rational recursive sequence

Yang, X., Lai, H., Evans, D.J. and Megson, G.M. 2004. Global asymptotic stability in a rational recursive sequence. *Applied Mathematics and Computation.* 158 (3), pp. 703-716. https://doi.org/10.1016/j.amc.2003.10.010

Global attractivity in a recursive sequence

Yang, X., Chen, B., Megson, G.M. and Evans, D.J. 2004. Global attractivity in a recursive sequence. *Applied Mathematics and Computation.* 158 (3), pp. 667-682. https://doi.org/10.1016/j.amc.2003.10.007

A clocking technique for FPGA pipelined designs

Cadenas, O. and Megson, G.M. 2004. A clocking technique for FPGA pipelined designs. *Journal of Systems Architecture.* 51 (11), pp. 687-696. https://doi.org/10.1016/j.sysarc.2004.04.001

Generalized honeycomb torus is Hamiltonian

Yang, X., Evans, D.J., Lai, H. and Megson, G.M. 2004. Generalized honeycomb torus is Hamiltonian. *Information Processing Letters.* 92 (1), pp. 31-37. https://doi.org/10.1016/j.ipl.2004.05.017

On the maximal connected component of hypercube with faulty vertices (II)

Yang, X., Evans, D.J. and Megson, G.M. 2004. On the maximal connected component of hypercube with faulty vertices (II). *International Journal of Computer Mathematics.* 81 (10), pp. 1175-1185. https://doi.org/10.1080/0020716041233127208

A solution to the three disjoint path problem on honeycomb tori

Yang, X., Megson, G.M., Zhang, S. and Liu, X. 2004. A solution to the three disjoint path problem on honeycomb tori. *Parallel Processing Letters.* 14 (3-4), pp. 411-422. https://doi.org/10.1142/S0129626404001994

A solution to the three disjoint path problem on honeycomb meshes

Yang, X., Megson, G.M., Zhang, S. and Liu, X. 2004. A solution to the three disjoint path problem on honeycomb meshes. *Parallel Processing Letters.* 14 (3-4), pp. 399-410. https://doi.org/10.1142/S0129626404001982

Fault tolerance of Möbius cubes under two forbidden fault set models

Yang, X. and Megson, G.M. 2004. Fault tolerance of Möbius cubes under two forbidden fault set models. *International Journal of Computer Mathematics.* 81 (8), pp. 909-916. https://doi.org/10.1080/00207160410001712332

On the maximal connected component of hypercube with faulty vertices

Yang, X., Evans, D.J., Chen, B., Megson, G.M. and Lai, H. 2004. On the maximal connected component of hypercube with faulty vertices. *International Journal of Computer Mathematics.* 81 (5), pp. 515-525. https://doi.org/10.1080/00207160410001661726

On the double-vertex-cycle-connectivity of crossed cubes

Yang, X. and Megson, G.M. 2004. On the double-vertex-cycle-connectivity of crossed cubes. *International Journal of Parallel, Emergent and Distributed Systems.* 19 (1), pp. 11-17. https://doi.org/10.1080/1063719042000208836

Tools for regularizing array designs

Manjunathaiah, M. and Megson, G.M. 2004. Tools for regularizing array designs. *International Journal of Parallel, Emergent and Distributed Systems.* 19 (1), pp. 51-75. https://doi.org/10.1080/17445760601139039

A solution to the three disjoint path problem on honeycomb meshes

Yang, X., Megson, G.M., Zhang, S. and Liu, X. 2004. A solution to the three disjoint path problem on honeycomb meshes. *Parallel Processing Letters.* 14 (3-4), pp. 399-410. https://doi.org/10.1142/S0129626404001982

A solution to the three disjoint path problem on honeycomb tori

Yang, X., Megson, G.M., Zhang, S. and Liu, X. 2004. A solution to the three disjoint path problem on honeycomb tori. *Parallel Processing Letters.* 14 (3-4), pp. 411-422. https://doi.org/10.1142/S0129626404001994

Locally twisted cubes are 4-pancyclic

Yang, X., Megson, G.M. and Evans, D.J. 2004. Locally twisted cubes are 4-pancyclic. *Applied Mathematics Letters.* 17 (8), pp. 919-925. https://doi.org/10.1016/j.aml.2003.10.009

Fractal quantization

Cadenas, O. and Megson, G.M. 2004. Fractal quantization. in: 2004 IEEE International Symposium on Consumer Electronics: proceedings: September 1-3 2004 Piscataway, N.J. IEEE . pp. 461-464

A FPGA pipelined backward adaptive scalar quantizer

Cadenas, O. and Megson, G.M. 2004. A FPGA pipelined backward adaptive scalar quantizer. in: Proceedings of the Second IASTED International Conference on Circuits, Signals, and Systems, Clearwater Beach, FL, USA, November 28 - December 1, 2004 IASTED/ACTA Press. pp. 410-415

Investigation into low power of a 2D inverse discrete cosine transform (IDCT) in FPGAs

Cadenas, O., Brandt, M.A., Megson, G.M. and Goswami, N. 2004. Investigation into low power of a 2D inverse discrete cosine transform (IDCT) in FPGAs. in: 2004 IEEE International Symposium on Consumer Electronics: proceedings: September 1-3 2004 Piscataway, N.J. IEEE . pp. 465-469

Designing fuzzy approximaters with genetic algorithms

Brudaru, O., Buzatu, O. and Megson, G.M. 2003. Designing fuzzy approximaters with genetic algorithms. in: Craus, M., Galia, D. and Valachi, A. (ed.) New Trends in Computer Science and Engineering, Anniversary Volume Romania Department of Computer Engineering, Faculty of Automatic Control and Computer Engineering, Technical University Gheorghe Asachi of Iasi. pp. 79-101

A system-level fault diagnosis algorithm based on preprocessing and parallel Hopfield neural network

Yang, X., Zhao, L., Megson, G.M. and Evans, D.J. 2003. A system-level fault diagnosis algorithm based on preprocessing and parallel Hopfield neural network. *4th IEEE Workshop on RTL and High Level Testing.* Xi'an Hotel, Xi'an, China 20 - 21 Nov 2003 pp. 189-196

A fast diagnosis algorithm for crossed cube connected multicomputer systems under the Maeng-Malek model

Yang, X., Megson, G.M. and Evans, D.J. 2003. A fast diagnosis algorithm for crossed cube connected multicomputer systems under the Maeng-Malek model. *4th IEEE workshop on WRT and high level testing.* Xi'an, China pp. 197-204

A sufficient condition for pessimistically t/t diagnosable systems with application to cube-connected systems

Yang, X. and Megson, G.M. 2003. A sufficient condition for pessimistically t/t diagnosable systems with application to cube-connected systems. *4th IEEE workshop on WRT and high level testing.* Xi'an, China pp. 205-210

A linear algebra processor using Monte Carlo methods

Plaks, T.P., Megson, G.M., Cadenas, O. and Alexandrov, V.N. 2003. A linear algebra processor using Monte Carlo methods. *2003 MAPLD International Conference.* Ronald Reagan Building and International Trade Center, Washington D.C. 09 - 13 Dec 2003

FPGA circuits for a Monte-Carlo based matrix inversion architecture

Cadenas, O., Megson, G.M. and Plaks, T.P. 2003. FPGA circuits for a Monte-Carlo based matrix inversion architecture. in: Proceedings of the International Conference on Engineering of Reconfigurable Systems and Algorithms, June 23 - 26, 2003, Las Vegas, Nevada, USA CSREA Press. pp. 201-217

An average-case classifier algorithm and FPGA implementation

Cadenas, O. and Megson, G.M. 2003. An average-case classifier algorithm and FPGA implementation. in: Rashid, M.H. (ed.) Circuits, signals, and systems: proceedings of the IASTED international conference on circuits, signals, and systems. May 19-21 2003, Cancun, Mexico. Acta Press. pp. 285-289

Pullpipelining: a technique for systolic pipelined circuits

Cadenas, O. and Megson, G.M. 2003. Pullpipelining: a technique for systolic pipelined circuits. in: 3rd IEEE International workshop on system-on-chip for real-time applications IEEE . pp. 205-210

Power performance with gated clocks of a pipelined Cordic core

Cadenas, O. and Megson, G.M. 2003. Power performance with gated clocks of a pipelined Cordic core. in: 5th International Conference on ASIC: proceedings. IEEE .

Compositional technique for synthesising multi-phase regular arrays

Manjunathaiah, M. and Megson, G.M. 2002. Compositional technique for synthesising multi-phase regular arrays. in: IEEE international conference on application-specific systems, architectures and processors: proceedings IEEE . pp. 7-16

A clocking technique with power savings in virtex-based pipelined designs

Cadenas, O. and Megson, G.M. 2002. A clocking technique with power savings in virtex-based pipelined designs. in: Glesner, M., Zipf, P. and Renovell, M. (ed.) Field-Programmable Logic and Applications: Reconfigurable Computing Is Going Mainstream: 12th International Conference, FPL 2002 Montpellier, France, September 2–4, 2002: proceedings Berlin Springer.

Improving mW/MHz ratio in FPGAs pipelined designs

Cadenas, O. and Megson, G.M. 2002. Improving mW/MHz ratio in FPGAs pipelined designs. in: Edwards, M. (ed.) Euromicro symposium on digital system design: architectures, methods and tools: proccedings. IEEE . pp. 276-282

Guest editors forward: Engineering of reconfigurable hardware/software objects

Plaks, T.P. and Megson, G.M. 2001. Guest editors forward: Engineering of reconfigurable hardware/software objects. *Journal of Supercomputing.* 19 (1), pp. 5-6. https://doi.org/10.1023/A:1011195109315

Patent GB0111627.6: Image compression and transmission - for Salgen Systems Ltd

Alavi, F.N. and Megson, G.M. 2001. *Patent GB0111627.6: Image compression and transmission - for Salgen Systems Ltd.*

An evolutionary approach to static task graph scheduling with task duplication for minimised interprocessor traffic

Sandnes, F.E. and Megson, G.M. 2001. An evolutionary approach to static task graph scheduling with task duplication for minimised interprocessor traffic. in: Lin, Y.C. and Shen, H. (ed.) The second international conference on parallel and distributed computing, applications and technologies (PDCAT 2001): proceedings, July 9-11, 2001, Tamkang University, Taipei, Taiwan Department of Electrical Engineering, Tamkang University. pp. 101-108

Uniformization of affine dependence programs for parallel embedded system design

Manjunathaiah, M., Megson, G.M., Rajopadhye, S.V. and Risset, T. 2001. Uniformization of affine dependence programs for parallel embedded system design. in: International Conference on Parallel Processing IEEE . pp. 205-213

A n-bit reconfigurable scalar quantiser

Cadenas, O. and Megson, G.M. 2001. A n-bit reconfigurable scalar quantiser. in: Brebner, G. and Woods, R. (ed.) Field-Programmable Logic and Applications: 11th International Conference, FPL 2001 Belfast, Northern Ireland, UK, August 27-29, 2001: proceedings Berlin Springer.

Pipelining considerations for an FPGA case

Cadenas, O. and Megson, G.M. 2001. Pipelining considerations for an FPGA case. in: Euromicro symposium on digital systems design: architectures, methods and tools IEEE . pp. 276-283

Final Report, EPSRC Grant, REFLEX

Megson, G.M. 2001. *Final Report, EPSRC Grant, REFLEX.* EPSRC.

A family of efficient regular arrays for band and sparse matrix inversion using Monte Carlo methods

Plaks, T.P., Megson, G.M. and Aleksandrov, V.N. 2000. A family of efficient regular arrays for band and sparse matrix inversion using Monte Carlo methods. *16th IMACS World Congress on Scientific Computation, Applied Modelling and Simulation.* Lausanne, Switzerland 21-25 August 2000

Quantitative evaluation of three reconfiguration strategies on FPGAs: a case study

Cadenas, O., Megson, G.M. and Plaks, T.P. 2000. Quantitative evaluation of three reconfiguration strategies on FPGAs: a case study. in: The fourth international conference/exhibition on high performance computing in the Asia-Pacific region IEEE .

Accelerating JPEG compression with a dynamically reconfigurable FPGA systolic array

Cadenas, O., Megson, G.M. and Plaks, T.P. 2000. Accelerating JPEG compression with a dynamically reconfigurable FPGA systolic array. *International Conference on Parallel and Distibuted Processing Techniques and Applications, vol VI.* Las Vegas, USA 26 - 29 June 2000 pp. 3023-3026

Final Report, EPSRC Grant GR/L35089/01: systolic and regular array composition environment (SARACEN)

Megson, G.M. 2000. *Final Report, EPSRC Grant GR/L35089/01: systolic and regular array composition environment (SARACEN).* EPSRC.

Fault-tolerant ring embedding in a honeycomb torus with node failures

Megson, G.M., Liu, X. and Yang, X. 1999. Fault-tolerant ring embedding in a honeycomb torus with node failures. *Parallel Processing Letters.* 9 (4), pp. 551-561. https://doi.org/10.1142/S0129626499000517

Honeycomb tori are Hamiltonian

Megson, G.M., Yang, X. and Liu, X. 1999. Honeycomb tori are Hamiltonian. *Information Processing Letters.* 72 (3-4), pp. 99-103. https://doi.org/10.1016/S0020-0190(99)00141-6

Experiences using reconfigurable FPGAs in implementing Monte-Carlo methods

Plaks, T.P., Cadenas, O. and Megson, G.M. 1999. Experiences using reconfigurable FPGAs in implementing Monte-Carlo methods. in: Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications, PDPTA 1999, June 28 - Junlly 1, 1999, Las Vegas, Nevada, USA CSREA Press. pp. 1131-1137

Parallel algorithms for knapsack type problems

Aleksandrov, V.N. and Megson, G.M. 1999. *Parallel algorithms for knapsack type problems.* World Scientific Publishing.

Systolic arrays for the Haar transform

Megson, G.M. 1998. Systolic arrays for the Haar transform. *Computers and Digital techniques, IEE Proceedings E.* 145 (6), pp. 403-410.

Neural network analysis of hue spectra from natural images

Robertson, C. and Megson, G.M. 1998. Neural network analysis of hue spectra from natural images. in: Smith, G.D., Steele, N.C. and Albrecht, R.F. (ed.) Artificial neural nets and genetic algorithms: proceedings of the international conference in Norwich, U.K., 1997 Springer.

Static multiprocessor task graph scheduling in the genetic paradigm: a comparison of genotype representations, research report no. 98-25

Rebreyend, P., Sandnes, F.E. and Megson, G.M. 1998. *Static multiprocessor task graph scheduling in the genetic paradigm: a comparison of genotype representations, research report no. 98-25.* Lyon, France Ecole Normale Superieure de Lyon, Laboratoire de Informatique du Parallelisme.

Creation of reconfigurable hardware objects in PVM environments

Megson, G.M., Fish, R.S. and Clarke, D.N.J. 1998. Creation of reconfigurable hardware objects in PVM environments. in: Alexandrov, V.N. and Dongarra, J. (ed.) Recent advances in parallel virtual machine and message passing interface: 5th European PVM/MPI Users' Group Meeting Liverpool, UK, September 7–9, 1998: proceedings Berlin Springer.

Synthesis of a systolic array genetic algorithm

Megson, G.M. and Bland, I.M. 1998. Synthesis of a systolic array genetic algorithm. in: Proceedings of the first merged International Parallel Processing Symposium & Symposium on Parallel and Distributed Processing, March 30-April 3, 1998, Orlando, Florida Los Alamitos, USA IEEE . pp. 316-320

The systolic array genetic algorithm, an example of systolic arrays as a reconfigurable design methodology

Bland, I.M. and Megson, G.M. 1998. The systolic array genetic algorithm, an example of systolic arrays as a reconfigurable design methodology. in: Pocek, K.L. and Arnold, J.M. (ed.) IEEE symposium on FPGAs for custom computing machines, 1998 IEEE . pp. 260-261

Systolic array library for hardware genetic algorithms

Bland, I.M. and Megson, G.M. 1998. Systolic array library for hardware genetic algorithms. *MPCS 98.* Colorado Springs 6th-9th April 1998

Scalar quantisation using a fast systolic array

Megson, G.M. and Diemoz, E. 1997. Scalar quantisation using a fast systolic array. *Electronics Letters.* 33 (17), pp. 1435-1437.

Efficient operator pipelining in a bit serial genetic algorithm engine

Bland, I.M. and Megson, G.M. 1997. Efficient operator pipelining in a bit serial genetic algorithm engine. *Electronics Letters.* 33 (12), pp. 1026-1028. https://doi.org/10.1049/el:19901316

Generic systolic array for genetic algorithms

Megson, G.M. and Bland, I.M. 1997. Generic systolic array for genetic algorithms. *Computers and Digital techniques, IEE Proceedings E.* 144 (2), pp. 107-119.

Improved static multiprocessor scheduling using cyclic task graphs: a genetic approach

Sandnes, F.E. and Megson, G.M. 1997. Improved static multiprocessor scheduling using cyclic task graphs: a genetic approach. *2nd Workshop on Randomized Parallel Computing - IPPS97.* Geneva, Switzerland 1 April 1997

Improved static multiprocessor scheduling using cyclic task graphs: a genetic approach

Sandnes, F.E. and Megson, G.M. 1997. Improved static multiprocessor scheduling using cyclic task graphs: a genetic approach. in: D'Hollander, E.H., Joubert, G.R., Peters, F.J. and Trottenburg, U. (ed.) Parallel Computing: Fundamentals, Applications and New Directions, Proceedings of the Conference ParCo'97, 19-22 September 1997, Bonn, Germany Elsevier.

Automatic parallelization for a class of regular computations

Megson, G.M. and Chen, X. 1997. *Automatic parallelization for a class of regular computations.* World Scientific Publishing.

Mapping a generic systolic array for genetic algorithms onto FPGAs: theory and practice

Megson, G.M. and Bland, I.M. 1997. Mapping a generic systolic array for genetic algorithms onto FPGAs: theory and practice. in: D'Hollander, E.H., Joubert, G.R., Peters, F.J. and Trottenburg, U. (ed.) Parallel Computing: Fundamentals, Applications and New Directions, Proceedings of the Conference ParCo'97, 19-22 September 1997, Bonn, Germany Elsevier.

Implementing a generic systolic array for genetic algorithms

Bland, I.M. and Megson, G.M. 1997. Implementing a generic systolic array for genetic algorithms. *First Online Workshop on Soft Computing, (WSC1).* Nagoya, Japan 19 - 31 Aug 1996 pp. 268-274

Systolic random number generation for genetic algorithms

Bland, I.M. and Megson, G.M. 1996. Systolic random number generation for genetic algorithms. *Electronics Letters.* 32 (12), pp. 1069-1070.

A hybrid genetic algorithm applied to automatic parallel controller code generation

Sandnes, F.E. and Megson, G.M. 1996. A hybrid genetic algorithm applied to automatic parallel controller code generation. in: Proceedings of the Eighth Euromicro Workshop on Real-Time Systems, 1996 IEEE . pp. 70-75

Genetic algorithms applied to automatic parallel controller code generation

Megson, G.M. and Sandnes, F.E. 1996. Genetic algorithms applied to automatic parallel controller code generation. *International Symposium on SOFT computing: SOCO 96.* University of Reading 26 - 28 Mar 1996

Automatic synthesis of parallel algorithms

Megson, G.M., Rapanotti, L. and Chen, X. 1996. Automatic synthesis of parallel algorithms. in: Ferreira, A. and Pardalos, P. (ed.) Solving Combinatorial Optimization Problems in Parallel: Berlin Springer.

Exploiting reconfigurability through high level synthesis

Megson, G.M. 1996. Exploiting reconfigurability through high level synthesis. in: IEE Colloquium on Hardware-Software Cosynthesis for Reconfigurable Systems (Digest No: 1996/036) London Institute of Electrical Engineers. pp. 5/1-5/4

Systolic algorithms in numerical analysis

Brudaru, O., Megson, G.M. and Galea, D. 1996. *Systolic algorithms in numerical analysis.* Bucharest Editura Academiei Romane.

Solving systems of linear algebraic equations by Monte Carlo method on regular arrays

Aleksandrov, V.N. and Megson, G.M. 1996. Solving systems of linear algebraic equations by Monte Carlo method on regular arrays. in: Vollmar, R., Jossifov, V. and Erhard, W. (ed.) Parcella '96: proceedings of the 7th international workshop on parallel processing by cellular automata and arrays held in Berlin, September 16-20 1996 Akademie Verlag.

Final Report, EPSRC Grant GR/H 46725: recurrence for-loop extensions (reflex)

Gurd, J.R. and Megson, G.M. 1996. *Final Report, EPSRC Grant GR/H 46725: recurrence for-loop extensions (reflex).* EPSRC.

A general methodology of partitioning and mapping for given regular arrays

Chen, X. and Megson, G.M. 1995. A general methodology of partitioning and mapping for given regular arrays. *IEEE Transactions on Parallel and Distributed Systems.* 6 (10), pp. 1100-1107. https://doi.org/10.1109/71.473518

Uniformization techniques for reducible integral recurrence equations

Rapanotti, L. and Megson, G.M. 1995. Uniformization techniques for reducible integral recurrence equations. in: Moonen, M.S. and Catthoor, F. (ed.) Algorithms and parallel VLSI architectures III: proceedings of the international workshop, algorithms and parallel VLSI Architectures III, Leuven, Belgium, August 29-31, 1994 Elsevier. pp. 283-294

Regularising transformations for integral dependencies

Megson, G.M. and Rapanotti, L. 1995. Regularising transformations for integral dependencies. in: Ferreira, A. and Rolim, J. (ed.) Parallel algorithms for irregular problems: state of the art Springer. pp. 297-322

Determining n-D convex hulls using parallel facial lattice exploration

Megson, G.M. and Eyoh, E.O. 1995. Determining n-D convex hulls using parallel facial lattice exploration. *ParCo'95: Fifth International Conference on Parallel Computing.* Ghent, Belgium 19 - 22 Sep 1995

A synthesis method of LSGP partitioning for given-shape regular arrays

Megson, G.M. and Chen, X. 1995. A synthesis method of LSGP partitioning for given-shape regular arrays. in: Proceedings of the 9th International Parallel Processing Symposium, April 25-28, 1995, Santa Barbara, California Los Alamitos, USA IEEE . pp. 234-238

Software tools for algorithmic engineering

Megson, G.M. 1994. Software tools for algorithmic engineering. *Innovation.* 25, p. 15.

Systolic state estimators for discrete-time controllers

Megson, G.M. 1994. Systolic state estimators for discrete-time controllers. *Electronics Letters.* 30 (11), pp. 914-915.

Systolic algorithm design environments (SADEs)

Megson, G.M. and Comish, D. 1994. Systolic algorithm design environments (SADEs). in: Megson, G.M. (ed.) Transformational approaches to systolic design London Chapman & Hall. pp. 205-239

Automatic derivation of systolic algorithms for Kalman filtering

Megson, G.M. and Comish, D. 1994. Automatic derivation of systolic algorithms for Kalman filtering. in: McWhirter, J.G. (ed.) Mathematics in signal processing III: based on the proceedings of the third conference organized by the Institute of Mathematics and Its Applications on mathematics in signal processing, held at the University of Warwick in December 1992 Clarendon Press.

Partitioning and mapping for lower dimensional given arrays

Megson, G.M. and Chen, X. 1994. Partitioning and mapping for lower dimensional given arrays. in: Second Euromicro Workshop on Parallel and Distributed Processing, University of Malaga, Spain, January 26-28, 1994: proceedings Los Alamitos, USA IEEE . pp. 149-155

Fixed sized systolic arrays for matrix inversion using a Monte Carlo method

Megson, G.M., Aleksandrov, V.N. and Dimov, I.T. 1994. Fixed sized systolic arrays for matrix inversion using a Monte Carlo method. in: Dimov, I.T., Sendov, B.L. and Vassilevski, P.S. (ed.) Advances in numerical methods and applications: proceedings of the 3rd international conference World Scientific Publishing. pp. 255-265

Systolic matrix inversion using a Monte Carlo method

Megson, G.M., Aleksandrov, V.N. and Dimov, I.T. 1994. Systolic matrix inversion using a Monte Carlo method. *International Journal of Parallel, Emergent and Distributed Systems.* 3 (3 & 4), pp. 311-330. https://doi.org/10.1080/10637199408962545

Systolic matrix inversion by Monte Carlo method

Megson, G.M., Aleksandrov, V.N. and Dimov, I.T. 1994. Systolic matrix inversion by Monte Carlo method. in: Ames, W.F. (ed.) Proceedings of the 14th IMACS World Congress on Computation and Applied Mathematics [also] IMACS '94, July 11-15, 1994, Georgia Institute of Technology, Atlanta, Georgia, USA Georgia Institute of Technology. pp. 1371-1373

Towards a formal model of algorithmic engineering

Megson, G.M. 1994. Towards a formal model of algorithmic engineering. in: Dimov, I.T. and Tonev, O. (ed.) Advances in parallel algorithms IOS Press. pp. 184-193

Final Report, SERC Grant GR/F 80494: design of multi-layer systolic algorithms

Megson, G.M. 1994. *Final Report, SERC Grant GR/F 80494: design of multi-layer systolic algorithms.* Science and Engineering Research Council.

CAD tools for the automatic synthesis of parallel algorithms in control

Megson, G.M. 1994. CAD tools for the automatic synthesis of parallel algorithms in control. in: International Conference on Control '94: 21-24 March 1994: venue, University of Warwick, Coventry, UK London Institution of Electrical Engineers.

Implementation and evaluation of parallel n-D convex hull algorithms

Eyoh, E.O. and Megson, G.M. 1994. Implementation and evaluation of parallel n-D convex hull algorithms. in: Joubert, G.R., Trystram, D., Peters, F.J. and Evans, D.J. (ed.) Parallel computing: trends and applications: proceedings of the international conference ParCo93, Grenoble, France 7-10 September, 1993 Amsterdam ; London Elsevier.

A space-time modeler for systlic algorithms

Diemoz, E. and Megson, G.M. 1994. A space-time modeler for systlic algorithms. *Advances in Engineering Software.* 20 (1), pp. 29-41. https://doi.org/10.1016/0965-9978(94)90028-0

Systolic designs for evaluating linear combinations of Chebyshev polynomials

Brudaru, O. and Megson, G.M. 1994. Systolic designs for evaluating linear combinations of Chebyshev polynomials. in: Halatsis, C., Maritsas, D., Philokyprou, G. and Theodoridis, S. (ed.) PARLE'94 Parallel Architectures and Languages Europe: 6th International PARLE Conference Athens, Greece, July 4–8, 1994: proceedings Berlin Springer.

Systolic arrays for accelerating iteration processes

Brudaru, O. and Megson, G.M. 1994. Systolic arrays for accelerating iteration processes. in: Jesshope, C.R., Jossifov, V. and Wilhelmi, W. (ed.) Parcella '94: proceedings of the 6th international workshop on parallel processing by cellular automata and arrays held in Potsdam, September 21-23 1994 Berlin Akademie Verlag.

Mapping knapsack type problems on 2D regular arrays: two case studies

Aleksandrov, V.N., Megson, G.M. and Fidanova, S. 1994. Mapping knapsack type problems on 2D regular arrays: two case studies. in: Jesshope, C.R., Jossifov, V. and Wilhelmi, W. (ed.) Parcella '94: proceedings of the 6th international workshop on parallel processing by cellular automata and arrays held in Potsdam, September 21-23 1994 Berlin Akademie Verlag.

Systolic partitioning algorithms

Megson, G.M. 1993. Systolic partitioning algorithms. *Information Processing Letters.* 46 (1), pp. 13-18. https://doi.org/10.1016/0020-0190(93)90189-G

Efficient systolic Broyden algorithm

Megson, G.M. 1993. Efficient systolic Broyden algorithm. *Electronics Letters.* 29 (1), p. 93. https://doi.org/10.1049/el:19930061

The givens-batcher reduction algorithm and matrix triangularisation

Megson, G.M. 1993. The givens-batcher reduction algorithm and matrix triangularisation. *International Journal of Computer Mathematics.* 47 (3&4), pp. 199-208. https://doi.org/10.1080/00207169308804177

The derivation of uniform recurrence equations using the knapsack problem

Megson, G.M. 1993. The derivation of uniform recurrence equations using the knapsack problem. *International Journal of Parallel, Emergent and Distributed Systems.* 1 (2), pp. 127-140. https://doi.org/10.1080/10637199308915436

Multi-layer systolic algorithms

Megson, G.M. 1993. Multi-layer systolic algorithms. *DTI/SERC JFIT Technical Conference.* Keele 23 - 24 Mar 1993

Mapping a class of run-time dependencies onto regular arrays

Megson, G.M. 1993. Mapping a class of run-time dependencies onto regular arrays. in: Proceedings of Seventh International Parallel Processing Symposium Los Alamitos, USA IEEE . pp. 97-104

Pre-processing stage in solving ODEs with extrapolation methods

Brudaru, O. and Megson, G.M. 1993. Pre-processing stage in solving ODEs with extrapolation methods. *Studia Universitatis Babes-Bolyai, Thematica.* XXXVII (3), pp. 31-57.

A fast Faddeev array

Megson, G.M. 1992. A fast Faddeev array. *IEEE Transactions on Computers.* 41 (12), pp. 1594-1600. https://doi.org/10.1109/12.214668

Keeping a finger on the pulse

Megson, G.M. 1992. Keeping a finger on the pulse. *Parallelogram International: international journal of high performance computing.*

Systolic designs for Aitken's root finding method

Megson, G.M., Brudaru, O. and Comish, D. 1992. Systolic designs for Aitken's root finding method. *Parallel Computing.* 18 (4), pp. 415-429. https://doi.org/10.1016/0167-8191(92)90137-V

More on systolic line drawing

Megson, G.M. and Evans, D.J. 1992. More on systolic line drawing. *Parallel Computing.* 18 (2), pp. 355-358. https://doi.org/10.1016/0167-8191(92)90103-E

VLSI systolic arrays for table based algorithms

Megson, G.M. and Evans, D.J. 1992. VLSI systolic arrays for table based algorithms. in: Evans, D.J. (ed.) Advances in parallel computing: a research annual JAI Press.

An introduction to systolic algorithm design

Megson, G.M. 1992. *An introduction to systolic algorithm design.* Oxford Clarendon.

Practical steps towards algorithmic engineering

Megson, G.M. 1992. Practical steps towards algorithmic engineering. in: IEE Colloquium on applications of parallel and distributed processing in automation and control on Friday, 13 November 1992 Institution of Electrical Engineers.

Experimenting with DTAGS: an interactive synthesis package

Megson, G.M. 1992. Experimenting with DTAGS: an interactive synthesis package. in: Colloquium on Generic Parallelisation of Algorithms for Control and Simulation Institution of Electrical Engineers.

Two-dimensional systolic array for the column-by-column QD algorithm

Brudaru, O. and Megson, G.M. 1991. Two-dimensional systolic array for the column-by-column QD algorithm. *Computers and Digital techniques, IEE Proceedings E.* 138 (6), pp. 401-406.

A systolic simplex algorithm

Evans, D.J. and Megson, G.M. 1991. A systolic simplex algorithm. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 417-445

Compact systolic arrays for incomplete matrix factorisation methods

Evans, D.J. and Megson, G.M. 1991. Compact systolic arrays for incomplete matrix factorisation methods. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 321-373

Matrix inversion by systolic rank annihilation

Evans, D.J. and Megson, G.M. 1991. Matrix inversion by systolic rank annihilation. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 159-197

Systolic arrays for group explicit methods for solving first order hyperbolic equations

Megson, G.M. and Evans, D.J. 1991. Systolic arrays for group explicit methods for solving first order hyperbolic equations. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 215-231

Construction of extrapolation tables by systolic arrays for solving ordinary differential equations

Evans, D.J. and Megson, G.M. 1991. Construction of extrapolation tables by systolic arrays for solving ordinary differential equations. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 199-213

Romberg integration using systolic arrays

Evans, D.J. and Megson, G.M. 1991. Romberg integration using systolic arrays. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 183-197

On systolic arrays for complex matrix problems

Megson, G.M. and Evans, D.J. 1991. On systolic arrays for complex matrix problems. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 153-165

Algorithmic fault tolerance for matrix operations on triangular arrays

Megson, G.M. and Evans, D.J. 1991. Algorithmic fault tolerance for matrix operations on triangular arrays. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 139-151

Triangular systolic arrays for matrix product and factorisation

Megson, G.M. and Evans, D.J. 1991. Triangular systolic arrays for matrix product and factorisation. in: Evans, D.J. (ed.) Systolic Algorithms Philadelphia, USA Gordon and Breach Science Publishers. pp. 115-137

Systolic algorithm design environments

Megson, G.M. and Comish, D. 1991. Systolic algorithm design environments. in: Second International Specialist Seminar on the Design and Application of Parallel Digital Processors, 15-19 April, 1991, venue The Gulbenkian Foundation, Lisbon, Portugal London Institution of Electrical Engineers. pp. 100-104

A systolic Broyden algorithm

Megson, G.M. 1991. A systolic Broyden algorithm. in: Second International Specialist Seminar on the Design and Application of Parallel Digital Processors, 15-19 April, 1991, venue The Gulbenkian Foundation, Lisbon, Portugal London Institution of Electrical Engineers. pp. 127-131

Unifying structures for parallel algorithms in control

Megson, G.M. 1991. Unifying structures for parallel algorithms in control. *First European Control Conference.* Grenoble Alpes Congrès Centre, Grenoble, France 02 - 05 Jul 1991

Systolic rank updating and the solution of non-linear equations

Megson, G.M. 1991. Systolic rank updating and the solution of non-linear equations. in: Fifth International Parallel Processing Symposium: proceedings IEEE . pp. 344-351

Systolic algorithms for B-spline patch generation

Megson, G.M. 1991. Systolic algorithms for B-spline patch generation. *Journal of Parallel and Distributed Computing.* 11 (3), pp. 231-238. https://doi.org/10.1016/0743-7315(91)90047-D

Fast multi-layer systolic arrays for Kalman filtering

Megson, G.M. 1991. Fast multi-layer systolic arrays for Kalman filtering. in: Deprettere, F. and Van der Veen, A.J. (ed.) Algorithms and parallel VLSI architectures. Volume B, Proceedings Elsevier.

Book review: Vector models for data-parallel computing

Megson, G.M. 1991. Book review: Vector models for data-parallel computing. *Journal of Computer Systems Science & Engineering.*

Book review: Parallel computing 89

Megson, G.M. 1991. Book review: Parallel computing 89. *Journal of Computer Systems Science & Engineering.*

Book review: Computing with Parallel Architectures – T. Node, ISBN 0792312252, Kluwer Academic Publishers Groups

Megson, G.M. 1991. Book review: Computing with Parallel Architectures – T. Node, ISBN 0792312252, Kluwer Academic Publishers Groups. *Computer Journal.* 34 (6), p. 573. https://doi.org/10.1093/comjnl/34.6.573-b

Automatic systolic algorithm design II: a practical approach

Megson, G.M. 1991. Automatic systolic algorithm design II: a practical approach. *ICL Parallel Computing.* University of Newcastle upon Tyne pp. 19-36

Automatic systolic algorithm design I: basic synthesis techniques

Megson, G.M. 1991. Automatic systolic algorithm design I: basic synthesis techniques. *ICL Parallel Computing.* University of Newcastle upon Tyne

A systolic simplex algorithm

Evans, D.J. and Megson, G.M. 1991. A systolic simplex algorithm. *International Journal of Computer Mathematics.* 38 (1&2), pp. 1-30. https://doi.org/10.1080/00207169108803954

An orthogonal systolic design for the assignment problem

Megson, G.M. and Evans, D.J. 1990. An orthogonal systolic design for the assignment problem. *Parallel Computing.* 16 (2-3), pp. 253-267. https://doi.org/10.1016/0167-8191(90)90062-E

Systolic arrays for group explicit methods for solving first order hyperbolic equations

Megson, G.M. and Evans, D.J. 1990. Systolic arrays for group explicit methods for solving first order hyperbolic equations. *Parallel Computing.* 16 (2-3), pp. 191-205. https://doi.org/10.1016/0167-8191(90)90058-H

Efficient systolic string matching

Megson, G.M. 1990. Efficient systolic string matching. *Electronics Letters.* 26 (24), pp. 2040-2042. https://doi.org/10.1049/el:19901316

Improved matrix triangularisation using a double pipeline systolic array

Megson, G.M. and Gaston, F.M.F. 1990. Improved matrix triangularisation using a double pipeline systolic array. *Information Processing Letters.* 36 (2), pp. 103-109. https://doi.org/10.1016/0020-0190(90)90105-7

Sorting without exchanges on a bit-serial systolic array

Megson, G.M. 1990. Sorting without exchanges on a bit-serial systolic array. *Circuits, Devices and Systems, IEE Proceedings G.* 137 (5), pp. 345-352.

Transputer implementation of systolic arrays for model reduction

Megson, G.M. 1990. Transputer implementation of systolic arrays for model reduction. *Computers and Digital techniques, IEE Proceedings E.* 137 (5), pp. 343-352.

The systolic control ring instruction processor (SCRIP)

Megson, G.M. and Evans, D.J. 1990. The systolic control ring instruction processor (SCRIP). *Integration: the VLSI Journal.* 9 (3), pp. 287-302. https://doi.org/10.1016/0167-9260(90)90021-R

Transputer arrays and computer-aided control system design

Megson, G.M. 1990. Transputer arrays and computer-aided control system design. *Control Theory and Applications, IEE Proceedings D.* 137 (4), pp. 197-210.

Complex eigenproblem solution by a parallel norm-reducing Jacobi method

Megson, G.M. 1990. Complex eigenproblem solution by a parallel norm-reducing Jacobi method. *Journal of Computer Systems Science and Engineering.* 5 (3), pp. 159-168.

A systolic helix for matrix triangularisation with partial pivoting

Megson, G.M. 1990. A systolic helix for matrix triangularisation with partial pivoting. *Parallel Computing.* 14 (2), pp. 199-206. https://doi.org/10.1016/0167-8191(90)90107-K

The Givens Batcher Reduction (GBR) algorithm

Megson, G.M. 1990. The Givens Batcher Reduction (GBR) algorithm. *International Workshop on Algorithms and Parallel VLSI Architectures.* Pont-a-Mousson, France 10 - 16 Jun 1990

Ray tracing using the SCRIP machine

Popovic, R. and Megson, G.M. 1990. Ray tracing using the SCRIP machine. in: Evans, D.J., Joubert, G.R. and Peters, F.J. (ed.) Parallel computing 89: proceedings of the international conference, Leiden, 29 August-1 September 1989 Elsevier. pp. 387-396

A systolic array solution for the assignment problem

Megson, G.M. and Evans, D.J. 1990. A systolic array solution for the assignment problem. *The Computer Journal.* 33 (6), pp. 562-569. https://doi.org/10.1093/comjnl/33.6.562

An efficient double pipe systolic array for matrix product

Megson, G.M. and Evans, D.J. 1990. An efficient double pipe systolic array for matrix product. *The Computer Journal.* 33 (3), pp. 261-265. https://doi.org/10.1093/comjnl/33.3.261

On the suitability of higher block matrix forms for systolic LU decomposition

Megson, G.M. and Evans, D.J. 1990. On the suitability of higher block matrix forms for systolic LU decomposition. *Journal of New Generation Computer Systems.* 3 (2), pp. 143-158.

A systolic topelitz linear solver

Evans, D.J. and Megson, G.M. 1990. A systolic topelitz linear solver. in: McWhirter, J.G. (ed.) Mathematics in signal processing II: based on the proceedings of a conference organized by the Institute of Mathematics and its Applications on mathematics in signal processing held at the University of Warwick in December 1988 Clarendon Press.

Rank annihilation on a ring of processors

Megson, G.M. 1990. Rank annihilation on a ring of processors. *Parallel Computing.* 13 (1), pp. 85-94. https://doi.org/10.1016/0167-8191(90)90121-O

Fast triangularization of a symmetric tridiagonal matrix

Evans, D.J. and Megson, G.M. 1989. Fast triangularization of a symmetric tridiagonal matrix. *Journal of Parallel and Distributed Computing.* 6 (3), pp. 663-678. https://doi.org/10.1016/0743-7315(89)90012-9

Algorithmic fault tolerance for matrix operations on triangular arrays

Megson, G.M. and Evans, D.J. 1989. Algorithmic fault tolerance for matrix operations on triangular arrays. *Parallel Computing.* 10 (2), pp. 207-219. https://doi.org/10.1016/0167-8191(89)90018-5

Systolic preconditioning algorithms for the iterative solution of sparse linear systems

Megson, G.M. and Evans, D.J. 1989. Systolic preconditioning algorithms for the iterative solution of sparse linear systems. *Journal of New Generation Computer Systems.* 2, pp. 111-128.

On systolic arrays for complex matrix problems

Megson, G.M. and Evans, D.J. 1989. On systolic arrays for complex matrix problems. *International Journal of Computer Mathematics.* 30 (1&2), pp. 103-116. https://doi.org/10.1080/00207168908803772

A systolic matrix norm generator

Evans, D.J. and Megson, G.M. 1989. A systolic matrix norm generator. in: Jesshope, C.R. (ed.) Major advances in parallel processing: seminar: papers and summaries Temple University. pp. 320-327

Systolic preconditioning algorithms for the jacobi iterative solution of sparse linear systems

Evans, D.J. and Megson, G.M. 1989. Systolic preconditioning algorithms for the jacobi iterative solution of sparse linear systems. in: Wolf, G., Legendi, T. and Schendel, U. (ed.) Parcella '88: 4th International workshop on parallel processing by cellular automata and arrays: Berlin, GDR, October 17–21, 1988: proceedings Berlin Springer.

Parallel and systolic algorithms for robot control

Evans, D.J. and Megson, G.M. 1989. Parallel and systolic algorithms for robot control. *IMA Conference of Robotics: Applied Mathematics and Computational Apsects.* Loughborough 12-14 July 1989

Hopscotch schemes for the solution of parabolic equations on area efficient systolic arrays

Evans, D.J. and Megson, G.M. 1989. Hopscotch schemes for the solution of parabolic equations on area efficient systolic arrays. in: McCanny, J., McWhirter, J.G. and Swartzlander, E. (ed.) Systolic array processors: 3rd International conference on systolic arrays: papers New York ; London Prentice Hall. pp. 62-72

Matrix power generation using an optical reduced-bandwidth systolic array

Megson, G.M. and Evans, D.J. 1988. Matrix power generation using an optical reduced-bandwidth systolic array. *Optoelectronics, IEE Proceedings J.* 135 (6), pp. 435-442. https://doi.org/10.1049/ip-j:19880075

Final report short-term transputer loan TR1/083

Megson, G.M. and O'Young, S.D. 1988. *Final report short-term transputer loan TR1/083.* Science and Engineering Research Council.

The unification of systolic differencing algorithms

Megson, G.M. and Evans, D.J. 1988. The unification of systolic differencing algorithms. *The Computer Journal.* 31 (1), pp. 83-91. https://doi.org/10.1093/comjnl/31.1.83

Triangular systolic arrays for matrix product and factorisation

Megson, G.M. and Evans, D.J. 1988. Triangular systolic arrays for matrix product and factorisation. *International Journal of Computer Mathematics.* 25 (3&4), pp. 321-343. https://doi.org/10.1080/00207168808803676

Short notes: improved matrix product computation using double-pipeline systolic arrays

Megson, G.M. and Evans, D.J. 1988. Short notes: improved matrix product computation using double-pipeline systolic arrays. *The Computer Journal.* 31 (6), pp. 567-569. https://doi.org/10.1093/comjnl/31.6.567

Improved matrix product computation using double-pipeline systolic arrays

Megson, G.M. and Evans, D.J. 1988. Improved matrix product computation using double-pipeline systolic arrays. *The Computer Journal.* 31 (6), pp. 567-569. https://doi.org/10.1093/comjnl/31.6.567

Compact systolic arrays for incomplete matrix factorisation methods

Megson, G.M. and Evans, D.J. 1988. Compact systolic arrays for incomplete matrix factorisation methods. *International Journal of Computer Mathematics.* 25 (3&4), pp. 235-286. https://doi.org/10.1080/00207168808803673

Transputer implementation of systolic arrays for model reduction

Megson, G.M. 1988. Transputer implementation of systolic arrays for model reduction. in: IEE Colloquium on Recent Advances in Parallel Processing for Control London Institution of Electrical Engineers. pp. 5/1-5/10

Implementing SVD computation for feedback control systems on transputer arrays

Megson, G.M. 1988. Implementing SVD computation for feedback control systems on transputer arrays. *CONPAR 88.* UMIST, Manchester 12 - 16 Sep 1988

Hardware accelerators for STABLE-H

Megson, G.M. 1988. Hardware accelerators for STABLE-H. in: International Conference on Control 88, 13-15 April 1988 London Institution of Electrical Engineers. pp. 104-109

The alternating group explict (AGE) systolic array for the solution of large linear systems

Evans, D.J. and Megson, G.M. 1988. The alternating group explict (AGE) systolic array for the solution of large linear systems. *IFIP Workshop on Parallel Processing.* Pisa, Italy 25-27 April 1988 pp. 241-260

Systolic arrays for group explicit methods for solving parabolic partial differential equations

Evans, D.J. and Megson, G.M. 1988. Systolic arrays for group explicit methods for solving parabolic partial differential equations. in: Bromley, K., Kung, S.Y. and Swartzlander, E. (ed.) Proceedings of the International Conference on Systolic Arrays, San Diego, California, 25-27 May 1988 Washington, D.C. The Computer Society. pp. 315-329

Systolic array for the quotient difference algorithm

Evans, D.J. and Megson, G.M. 1988. Systolic array for the quotient difference algorithm. *Computers and Digital techniques, IEE Proceedings E.* 135 (1), pp. 60-66.

Construction of extrapolation tables by systolic arrays for solving ordinary differential equations

Evans, D.J. and Megson, G.M. 1987. Construction of extrapolation tables by systolic arrays for solving ordinary differential equations. *Parallel Computing.* 4 (1), pp. 33-48. https://doi.org/10.1016/0167-8191(87)90061-5

Novel algorithms for the soft-systolic paradigm

Megson, G.M. 1987. *Novel algorithms for the soft-systolic paradigm.* PhD thesis Loughborough University of Technology Department of Computer Studies

The solution of parabolic differential equations by systolic marching techniques

Evans, D.J. and Megson, G.M. 1987. The solution of parabolic differential equations by systolic marching techniques. in: Vichnevetsky, R. and Stepleman, R.S. (ed.) Advances in computer methods for partial differential equations-VI: proceedings of the sixth IMACS International Symposium on Computer Methods for Partial Differential Equations, held at Lehigh University, Bethlehem, Pennsylvania, U.S.A., June 23-25, 1987 Liége, Belgium International Association for Mathematics and Computers in Simulation. pp. 44-52

Matrix inversion by systolic rank annihilation

Evans, D.J. and Megson, G.M. 1987. Matrix inversion by systolic rank annihilation. *International Journal of Computer Mathematics.* 21 (3), pp. 319-357. https://doi.org/10.1080/00207168708803574

Romberg integration using systolic arrays

Evans, D.J. and Megson, G.M. 1986. Romberg integration using systolic arrays. *Parallel Computing.* 3 (4), pp. 289-304. https://doi.org/10.1016/0167-8191(86)90012-8

Soft-systolic pipelined matrix algorithms

Megson, G.M. and Evans, D.J. 1986. Soft-systolic pipelined matrix algorithms. in: Feilmeier, M., Joubert, G.R. and Schendel, U. (ed.) Parallel computing 85: proceedings of the Second International Conference on Parallel Computing, held at the Freie Universität Berlin, 23-25, September 1985 Elsevier. pp. 171-180

LISA: a parallel processing architecture

Megson, G.M. and Evans, D.J. 1986. LISA: a parallel processing architecture. in: Händler, W., Haupt, D., Jeltsch, R., Juling, W. and Lange, O. (ed.) CONPAR 86: Conference on Algorithms and Hardware for Parallel Processing Aachen, September 17–19, 1986: proceedings Berlin ; New York Springer.

**Permalink - **https://westminsterresearch.westminster.ac.uk/item/92v7w/implementation-of-a-block-based-neural-branch-predictor