A massively parallel optimizer for expression evaluation
Pages 97 - 106
Abstract
A number of “tricks” are known that trade multiplications for additions. The term “tricks” reflects the way these methods seem not to proceed from any general theory, but instead jump into existence as recipes that work. The Strassen method for 2 by 2 matrix product with 7 multiplications is a well-known example, as is the method for finding a complex number product in 3 multiplications. We have created a practical computer program for finding such tricks automatically, where massive parallelism makes the combinatorially explosive search tolerable for small problems. One result of this program is a method for computing cross products of 3-vectors using only 5 multiplications.
References
[1]
AIfred V. Aho, John E. Hopcroft, and Jeffrey D. Ullman. The Design and Analysis of Computer Algohihms. Addison-Wesley 1974.
[2]
D. Baily et.al., The NAS Parallel Benchmarks, Report RNR-91-002, NASA Ames Research Center, Jan 1991.
[3]
John L. Gustafson and Srinivas Aluru, Massively parallel searching for better algorithms, Tech. Rep. IS-5088 UC-32, Ames Laboratory, Iowa State University, Dec. 92.
[4]
J.E. Hopcroft, L.R. Kerr, On minimizing the number of multiplications necessary for matrix multiplication, SIAM J. Applied Math. 20:1 (1971) 30-36.
[5]
D.E. Knuth, The Art of Computer Programming, Vol. 2: seminumerical Algorithms, 2nd ed. Addison-Wesley, Reading, MA, 1981.
[6]
Lydia Kronsjo, Algorithms: Their Complexity and Efficiency, 2nd ed. John Wiley & Sons, 1987.
[7]
David W. Krumme and David H. Ackley, A practical method for code generation based on exhaustical search, Proc. ACM SIGPLAN'82 Symposium on Compiler Construction (1982) 185-196.
[8]
J.D. Laderman, A non-commutative algorithm for multiplying 3 ~ 3 matrices using 23 multiplications, Bull Am. Math. Soc., 82 (1976) 126-128.
[9]
Henry Masslin, Superoptimizer- A look at the smallest program, ASPLOS II (1987) 122-126.
[10]
V. Pan, Strassen algorithm is not optimal. Trilinear technique of aggregating, uniting and cancling for constructing fast algorithms for matrix multiplication, Proc. 19th Annual Symposium on the Foundations of Computer Science, Ann Arbor, MI, (1978) 166-176.
[11]
V. Pan, How can we speed up matrix multiplication?, SIAM Rev., 26,3 (1984) 393-415.
[12]
W.H. Press, B.P. Flannery, S.A. Teukolsky, W.T. Vetterling, Numerical Recipes in C The Art of Scientific Computing, Cambridge University Press, 1990.
[13]
V.N. Rao, V. Kumar. Superlinear speedup in ordered depth-first search, Proceedings of 6th Distributed Memory Computing Conference(DMCC6) (1991).
[14]
V. Strassen, Gaussian elimination is not optimal, Numer, Math., 13 (1969)354-356.
[15]
S. Winograd, On multiplication of 2 ~ 2 matrices, Linear Alg. Appl., 4 (1971) 381-388.
Index Terms
- A massively parallel optimizer for expression evaluation
Recommendations
Efficient, Massively Parallel Eigenvalue Computation
In numerical simulations of disordered electronic sys tems, one of the most common approaches is to diag onalize random Hamiltonian matrices and to study the eigenvalues and eigenfunctions of a single electron in the presence of a random potential. We ...
Evaluation of massively parallel linear sparse solvers on unstructured finite element meshes
The performance of massively parallel direct and iterative methods for solving large sparse systems of linear equations arising in finite element method on unstructured (free) meshes in solid mechanics is evaluated on a latest high performance computing ...
Performance evaluation of a new parallel preconditioner
IPPS '95: Proceedings of the 9th International Symposium on Parallel ProcessingThe linear systems associated with large, sparse, symmetric, positive definite matrices are often solved iteratively using the preconditioned conjugate gradient method. We have developed a new class of preconditioners, support tree preconditioners, that ...
Comments
Information & Contributors
Information
Published In
Copyright © 1993 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 01 August 1993
Check for updates
Qualifiers
- Article
Conference
ICS93
Sponsor:
Acceptance Rates
Overall Acceptance Rate 629 of 2,180 submissions, 29%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 249Total Downloads
- Downloads (Last 12 months)20
- Downloads (Last 6 weeks)5
Reflects downloads up to 27 Jul 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in