Superlinear Performance in Real-Time Parallel Computation

Can a parallel computer with n processors solve a computational problem more than n times faster than a sequential computer? Can it solve it more than n times better? New computational paradigms offer an affirmative answer to the above questions through concrete examples in which the improvement in speed or quality is superlinear in the number of processors used by the parallel computer. Furthermore, the improvement is consistent and provable. All examples are characterized by the presence of one or several real-time input streams. In one of the examples, an exponential improvement in speed is achieved despite the fact that the processors of the parallel computer are significantly slower than their sequential counterpart. In another example, the improvement in quality is unbounded. A metaphor from everyday life motivates each computational paradigm in which a superlinear improvement in performance is exhibited.

[1]  Selim G. Akl,et al.  Real-Time Computation: A Formal Definition And Its Applications , 2003 .

[2]  John A. Stankovic,et al.  On real-time transactions , 1988, SGMD.

[3]  Selim G. Akl,et al.  Parallel real-time computation: sometimes quantity means quality , 2000, Proceedings International Symposium on Parallel Architectures, Algorithms and Networks. I-SPAN 2000.

[4]  Fabrizio Luccio,et al.  Three non Conventional Paradigms of Parallel Computation , 1992, Heinz Nixdorf Symposium.

[5]  Azer Bestavros,et al.  Real-Time Database and Information , 1997 .

[6]  D. Parkinson.  Parallel efficiency can be greater than unity , 1986, Parallel Comput..

[7]  Selim G. Akl,et al.  Real-time minimum vertex cover for two-terminal series-parallel graphs , 2006, Int. J. High Perform. Comput. Netw..

[8]  Selim G. Akl,et al.  The Characterization of Data-Accumulating Algorithms , 2000, Theory of Computing Systems.

[9]  Selim G. Akl.  Parallel computation: models and methods , 1997 .

[10]  Selim G. Akl,et al.  A Case Study in Real-Time Parallel Computation: Correcting Algorithms , 2001, J. Parallel Distributed Comput..

[11]  Richard S. Barr,et al.  Parallel Simplex for Large Pure Network Problems: Computational Testing and Sources of Speedup , 1994, Oper. Res..

[12]  Christos H. Papadimitriou,et al.  Elements of the Theory of Computation , 1997, SIGA.

[13]  John L. Gustafson,et al.  Reevaluating Amdahl's law , 1988, CACM.

[14]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[15]  Edward F. Gehringer,et al.  Superlinear Speedup Through Randomized Algorithms , 1985, International Conference on Parallel Processing.

[16]  R. Janßen.  A note on superlinear speedup , 1987, Parallel Comput..

[17]  M. Thorin.  Real-time Transaction Processing , 1992 .

[18]  DAVID P. HELMBOLD,et al.  Modeling Speedup (n) Greater than n , 1990, IEEE Trans. Parallel Distributed Syst..

[19]  Selim G. Akl,et al.  Paradigms Admitting Superunitary Behaviour in Parallel Computation , 1997, Parallel Algorithms Appl..

[20]  Selim G. Akl,et al.  The characterization of data-accumulating algorithms , 1999, Proceedings 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing. IPPS/SPDP 1999.

[21]  Fabrizio Luccio,et al.  The p-shovelers problem-computing with time-varying data , 1992, [1992] Proceedings of the Fourth IEEE Symposium on Parallel and Distributed Processing.

[22]  Azer Bestavros,et al.  Real-Time Database and Information Systems - Research Advances, Papers from the Second International Workshop on Real-Time Databases, RTDB'97, September 18-19, 1997, Burlington, Vermont, USA , 1997, RTDB.

[23]  Harold W. Lawson.  Parallel processing in industrial real-time applications , 1992 .

[24]  Sartaj Sahni,et al.  Anomalies in Parallel Branch-and-Bound Algorithms , 1984 .

[25]  Fabrizio Luccio,et al.  Computing with Time-Varying Data: Sequential Complexity and Parallel Speed-Up , 1998, Theory of Computing Systems.

[26]  Fabrizio Luccio,et al.  The p-shovelers problem: (computing with time-varying data) , 1992, SIGA.

[27]  Selim G. Akl,et al.  Parallel Real-Time Optimization: Beyond Speedup , 1999, Parallel Process. Lett..