Fast message assembly using compact address relations
Pages 47 - 56
Abstract
Message assembly and disassembly represent a significant fraction of total communication time in many parallel systems. We introduce a run-time approach for fast message assembly and disassembly. The approach is based on generating addresses by decoding a precomputed and compactly stored address relation that describes the mapping of addresses on the source node to addresses on the destination node. The main result is that relations induced by redistributions of regular block-cyclic distributed arrays can be encoded in an extremely compact form that facilitates high throughput message assembly and disassembly. We measure the throughput of decoding-based message assembly and disassembly on several systems and find performance on par with copy throughput.
References
[1]
AGRAWAL, G., SUSSMAN, A., AND SALZ, J. An integrated runtime and compile-time approach for parallelizing structured and block structured applications. IEEE Transaction on Parallel and Distributed Systems 6, 7 (July 1995), 747-754.
[2]
ALPERT, D., AND AVNON, D. Architecture of the Pentium processor. IEEE Micro 13, 3 (June 1993), 1-21.
[3]
BARREH, J., DHAWAN, S., HICKS, T., AND SHIPPY, D. The POWER2 processor, in Proceedings of COMPCON '94 (San Francisco, CA, March 1994), IEEE, pp. 389-398.
[4]
BECKER, M. C., ALLEN, M. S., MOORE, C. R., MUHICH, J. S., AND TUTFLE, D. P. The PowerPC 601 processor. IEEE Micro 13, 5 (October 1993), 54--68.
[5]
DINDA, P. A., AND O'HALLARON, D. R. High throughput message assembly using compact address relations. Tech. rep., Carnegie Mellon University, 1996. To Appear.
[6]
DINDA, P. A., AND O'HALLARON, D. R. The performance impact of address relation caching. In Proceedingsofthe Third International Workshop on Languages, Compilers and Runtime Systems for Scalable Computers (1996), B. K. Szymanski and B. Sinharoy, Eds., Kluwer Academic Publishers, pp. 213- 226.
[7]
DOBBERPUHL, D. I. A. A 200-MHz 64-bit dual-issue CMOS microprocessor. Digital Technical Journal4, 4 (1992), 35-50. ftp://ftp.digital.com/pub/Digital/info/DTJ/axp-cmos.txt.
[8]
DUTTON, T. A., EIREF, D., KURTH, H. R., REIS- ERT, J. J., AND STEWART, R.L. The design of the DEC 3000 AXP systems, two high performance workstations. Digital Technical Journal 4, 4 (1992), 66-81. ftp ://ftp.di gital.co m/pub/Digital/info/DTJ/axp-dec-3000.txt.
[9]
GUPTA, S., KAUSHIK, S., HUANG, C., AND SADAYAPPAN, P. On compiling array expressions for efficient execution on distributed-memory machines. Tech. Rep. OSU-CISRC-4/94- TR19, Computer and Information Science Research Center, Ohio State University, Apr. 1994.
[10]
HIGH PERFORMANCE FORTRAN FORUM. High Performance Fortran language specification, version 1.0. Tech. Rep. CRPC- TR92225, Center for Research on Parallel Computation, Rice University, May 1993.
[11]
HUFFMAN, D. A. A method for the construction of minimumredundancy codes. Proceedings of the IRE 40, 9 (September 1952), 1098-1101.
[12]
INTEL CORP. Paragon X/PS Product Overview, March 1991.
[13]
INTEL CORP. i860 Microprocessor Family Programmer's Reference Manual, 1992.
[14]
LELEWER, D. A., AND HIRSCHBERG, D. S. Data compression. Tech. Rep. 87-10, University of California- Irvine, 1987.
[15]
MCLELLAN, E. The Alpha AXP architecture and 21064 processor. IEEE Micro 13, 3 (June 1993), 36-47.
[16]
OEHLER, R., AND GROVES, R. IBM RISC system/6000 processor architecture. IBM Journal of Research and Development 34, 1 (Jan 1990), 23-36.
[17]
SAINI, A. An overview of the Intel Pentium processor. In COMPCON Spring 1993 Digest of Papers (San Francisco, CA, 1993), pp. 60-62.
[18]
SALTZ, J., PETITON, S., BERRYMAN, H., AND RIFKIN, A. Performance effects of irregular communication patterns on massively parallel multiprocessors. Journal of Parallel and Distributed Computing 13 ( 1991 ), 202-212.
[19]
SNIR, M. Scalable Parallel Computing- The IBM 9076 Scalable POWERParallel-1. In ACM Symposium on Parallel Algorithms and Architectures (June 1993), ACM, p. 42.
[20]
STEENKISTE, P., ZILL, B., KUNG, H., SCHLICK, S., HUGHES, J., KOWALSKI, B., AND MULLANEY, J. A host interface architecture for high-speed networks. In Proceedings of the 4th IFIP Conference on High Performance Networks (Liege, Belgium, December 1992), IFIP, Elsevier, pp. A3 1-16.
[21]
STEENKISTE, P. A. A systematic approach to host interface design for high-speed networks. Computer 27, 3 (March 1994), 47-57.
[22]
STICHNOTH, J. Efficient compilation of array statements for private memory multicomputers. Tech. Rep. CMU-CS-93- 109, School of Computer Science, Carnegie Mellon University, Feb. 1993.
[23]
STICHNOTH, J., O'HALLARON, D., AND GROSS, T. Generating communication for array statements: Design, implementation, and evaluation. Journal of Parallel and Distributed Computing 21, 1 (Apr. 1994), 150-159.
[24]
STICHNOTH, J., AND T., G. A communication backend for parallel language compilers. Proc. Fifth Workshop on Compilers for Parallel Languages, Malaga, Spain (Tech Report UMA-DAC-95/09), pages 65-77, 1995.
[25]
STRICKER, T., AND GROSS, T. Optimizing memory system performance for communication in parallel computers. In Proc. 22nd Intl. Syrup. on Computer Architecture (Portofino, Italy, June 1995), ACM/IEEE, pp. 308-319.
[26]
WELCH, J. A technique for high performance data compression. IEEE Computer 17, 6 (June 1984), 8-19.
[27]
WHITE, S. W. Power2: Architecture and performance. In Proceedings of COMPCON '94 (San Francisco, CA, March 1994), IEEE, pp. 384-388.
[28]
Zlv, J., AND LEMPEL, A. A universal algorithm for sequential data compression. IEEE Transactions on Information Theory 23, 3 (May 1977), 337-343.
Index Terms
- Fast message assembly using compact address relations
Recommendations
Fast message assembly using compact address relations
SIGMETRICS '96: Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systemsMessage assembly and disassembly represent a significant fraction of total communication time in many parallel systems. We introduce a run-time approach for fast message assembly and disassembly. The approach is based on generating addresses by decoding ...
Side-effect analysis with fast escape filter
SOAP '12: Proceedings of the ACM SIGPLAN International Workshop on State of the Art in Java Program analysisSide-effect analysis is a fundamental static analysis used to determine the memory locations modified or used by each program entity. For the programs with pointers, the analysis can be very imprecise. To improve the precision of side-effect analysis, ...
Assembly reconciliation
Motivation: Many genomes are sequenced by a collaboration of several centers, and then each center produces an assembly using their own assembly software. The collaborators then pick the draft assembly that they judge to be the best and the ...
Comments
Information & Contributors
Information
Published In
May 1996
273 pages
May 1996279 pages
Copyright © 1996 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]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 15 May 1996
Published in SIGMETRICS Volume 24, Issue 1
Check for updates
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 275Total Downloads
- Downloads (Last 12 months)73
- Downloads (Last 6 weeks)15
Reflects downloads up to 10 Oct 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