David Bernstein
Abstract
Chaining is the ability to pipeline two or more vector instructions on Cray-1 like machines. We show how to optimally use this feature to compute (vector) expression trees, in the context of automatic code-generation. We present a linear-time scheduling algorithm for finding an optimal order of evaluation for a machine with a bounded number of registers.
- A Arya, S., "An optimal instructionscheduling model for a class of vector processors", IEEE Transactions on Cornputers, Vol. C-34, No. 11, (November 1985), 981-995.Google Scholar
- AJ Aho, A.V., and Johnson, S.C., "Optimal code generation for expression trees", Journal of the A CM 23, 3 (July 1976), 488-501. Google ScholarDigital Library
- AJU Aho, A.V., Johnson, S.C., and Ullman, J.D. "Code generation for expressions with common subexpressions", Journal of the ACM 24, 1 (January 1977), 146-160. Google ScholarDigital Library
- BJPR Bernstein, D., Jaffe, J.M., Pinter, R.Y., and Rodeh, M., "Optimal scheduling of arithmetic operations in parallel with memory access", TR 88.136, IBM-Israel Scientific Center (May 1985). A preliminary version has appeared in the Proceedings of the Twelfth A CM Symposium on Principles of Programming Languages, (January 1985), 325-333. Google ScholarDigital Library
- BJR Bernstein, D., Jaffe, J.M., and Rodeh, M., "Scheduling arithmetic and load operations in parallel with no spilling", in preparation.Google Scholar
- BS Bruno, J.L., and Sethi, R., "Code generation for a one-register machine", Journal of the ACM 23, 3 (July 1976), 502-510. Google ScholarDigital Library
- C Cray-I Hardware Reference Manual, Cray Research inc., Cray-I Comput. Syst. Publ. 2240004 (May 1979).Google Scholar
- HB Hwang, K., and Briggs, F.A., Computer architecture and parallel processing, McGraw-Hill, New York, 1984. Google ScholarDigital Library
- R Russell, R.M., "The Cray-I computer system", Communication of the A CM 21, 1 (January 1978), 63-72. Google ScholarDigital Library
- SU Sethi, R., and Ullman, J.D., "The generation of optimal code for arithmetic expressions", Journal of the A CM 17, 4 (October 1970), 715-728. Google ScholarDigital Library
Index Terms
- Optimal chaining in expression trees
Recommendations
Optimal Chaining in Expression Trees
Chaining is the ability to pipeline two or more vector instructions on Cray-1 like machines. The authors show how to optimally use this feature to compute (vector) expression trees in the context of automatic code generation. They present a linear time ...
Optimal chaining in expression trees
SIGPLAN '86: Proceedings of the 1986 SIGPLAN symposium on Compiler constructionChaining is the ability to pipeline two or more vector instructions on Cray-1 like machines. We show how to optimally use this feature to compute (vector) expression trees, in the context of automatic code-generation. We present a linear-time scheduling ...
Optimal and approximate bottleneck Steiner trees
Given a set of terminals in the plane, a bottleneck Steiner tree is a tree interconnecting the terminals, in which the length of the longest edge is minimized. The bottleneck Steiner tree problem, or special cases thereof, has applications in facility ...
Comments