|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| R. Raghavan, J.P. Hayes, "Reducing Interference Among Vector Accesses in Interleaved Memories," IEEE Transactions on Computers, vol. 42, no. 4, pp. 471-483, April, 1993. | |||
| BibTex | x | ||
| @article{ 10.1109/12.214693, author = {R. Raghavan and J.P. Hayes}, title = {Reducing Interference Among Vector Accesses in Interleaved Memories}, journal ={IEEE Transactions on Computers}, volume = {42}, number = {4}, issn = {0018-9340}, year = {1993}, pages = {471-483}, doi = {http://doi.ieeecomputersociety.org/10.1109/12.214693}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - JOUR JO - IEEE Transactions on Computers TI - Reducing Interference Among Vector Accesses in Interleaved Memories IS - 4 SN - 0018-9340 SP471 EP483 EPD - 471-483 A1 - R. Raghavan, A1 - J.P. Hayes, PY - 1993 KW - interference reduction; memory interference; vector accesses; interleaved memories; concurrent data requests; vector superconductors; memory bandwidth; system performance; vector data; vector data placement; computer architecture; vector processor systems. VL - 42 JA - IEEE Transactions on Computers ER - | |||
Memory interference occurs when two or more concurrent data requests are addressed to the same main memory bank. In vector superconductors, this problem is serious due to the periodic interaction among vectors accesses, and can significantly reduce memory bandwidth and overall system performance. Two techniques can be used to reduce the effects of memory interference. First, vector data can be placed in the main memory such that, when accessed concurrently, the vectors do not interfere with one another. Second, buffers can be used at the memory banks to hold conflicting requests and to allow vector streams to continue to access other banks. Conditions for arbitrary numbers of vector streams to access an interleaved memory system without conflict are derived. It is shown that when three or more vector streams must be accessed concurrently, vector data placement to avoid conflicts becomes increasingly difficult, and that bank buffers can be effective under these conditions in increasing the effective memory bandwidth.
[1] F. A. Briggs and E. S. Davidson, "Organization of semiconductor memories for parallel processors,"IEEE Trans. Comput., vol. C-26, pp. 162-169, Feb. 1977.
[2] P. Budnik and D. J. Kuck, "The organization and use of parallel memories,"IEEE Trans. Comput., vol. C-20, pp. 1566-1569, Dec. 1971.
[3] G. J. Burnett and E. G. Coffman, "A study of interleaved memory systems," inProc. AFIPS Spring Joint Conf., vol. 33, 1970, pp. 467-474.
[4] D. Y. Changet al., "On the effective bandwidth of parallel memories,"IEEE Trans. Comput., vol. C-26, pp. 480-490, May 1977.
[5] T. Cheung and J. E. Smith, "A simulation study of the CRAY X-MP memory system,"IEEE Trans. Computers, vol. C-35, pp. 613-622, July 1986.
[6] E. G. Coffman, G. J. Burnett, and R.A. Snowdon, "On the performance of interleaved memories with multiple-word bandwidth,"IEEE Trans. Commun., vol. C-20, pp. 1570-1573, Dec. 1971.
[7] J. Dongarra, "Performance of various computers using standard linear equations software in a Fortran environment," inMultiprocessors and Array Processors, W. J. Karplus, Ed. San Diego, CA: Simulation Councils Inc., Jan. 1987, pp. 15-33.
[8] G. H. Hardy and E. M. Wright,An Introduction to the Theory of Numbers, fifth ed. New York: Oxford University Press, 1979.
[9] W. Oed and O. Lange, "On the effective bandwidth of interleaved memories in vector processing systems,"IEEE Trans. Comput., vol. C-34, no. 10, pp. 949-957, Oct. 1985.
[10] R. Raghavan, J. P. Hayes, and W. R. Martin, "Logic simulation on vector processors," inDig. 1988 Int. Conf. Comput.-Aided Design, Nov. 1988, pp. 268-271.
[11] R. Raghavan and J. P. Hayes, "On randomly interleaved memories," inProc. Supercomputing '90 Conf.(New York), Nov. 1990.
[12] R. Raghavan, "Memory architectures for vector processing," Ph.D. dissertation, Univ. Michigan, 1991.
[13] B. R. Rauet al., "The Cydra 5 departmental supercomputer: Design philosophies. decisions, and trade-offs,"IEEE Comput. Mag., vol. 22, pp. 12-35, Jan. 1989.
[14] B. R. Rau, M. S. Schlansker, and D. W. L. Yen, "The Cydra 5 stride-insensitive memory system," inProc. 1989 Int. Conf. Parallel Processing, Aug.1989, pp. 242-246.
[15] C. V. Ravi, "On the bandwith and interface in interleaved memory systems,"IEEE Trans. Comput., Vol. C-21, pp. 899-901, Aug. 1972.
[16] P. Tang and R.H Mendez, "Memory conflicts and machine performance," inProc. Supercomput.'89, Nov. 1989, pp. 826-831.
[17] D. T. Harper III and J. R. Jump, "Vector access performance in parallel memories using a skewed storage scheme,"IEEE Trans. Comput., vol. C-36, no. 12, pp. 1440-1449, 1987.