{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T23:03:59Z","timestamp":1725663839570},"publisher-location":"Berlin, Heidelberg","reference-count":42,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540578406"},{"type":"electronic","value":"9783540483564"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1994]]},"DOI":"10.1007\/3-540-57840-4_26","type":"book-chapter","created":{"date-parts":[[2012,2,26]],"date-time":"2012-02-26T13:28:02Z","timestamp":1330262882000},"page":"87-104","source":"Crossref","is-referenced-by-count":4,"title":["Increasing memory bandwidth for vector computations"],"prefix":"10.1007","author":[{"given":"Sally A.","family":"McKee","sequence":"first","affiliation":[]},{"given":"Steven A.","family":"Moyer","sequence":"additional","affiliation":[]},{"given":"Wm. A.","family":"Wulf","sequence":"additional","affiliation":[]},{"given":"Charles","family":"Hitchcock","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2005,5,31]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Baer, J. L., Chen, T. F., \u201cAn Effective On-Chip Preloading Scheme To Reduce Data Access Penalty\u201d, Supercomputing 91, November 1991.","DOI":"10.1145\/125826.125932"},{"key":"6_CR2","unstructured":"Baron, R.L., and Higbie, L., Computer Architecture, Addison-Wesley, 1992."},{"key":"6_CR3","first-page":"12","volume":"20","author":"P. Budnik","year":"1971","unstructured":"Budnik, P., and Kuck, D., \u201cThe Organization and Use of Parallel Memories\u201d, IEEE Trans. Comput., 20, 12, 1971.","journal-title":"IEEE Trans. Comput."},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Callahan, D., et. al., \u201cSoftware Prefetching\u201d, Fourth International Conference on Architectural Support for Programming Languages and Systems, April 1991.","DOI":"10.1145\/106972.106979"},{"key":"6_CR5","unstructured":"Carr, S., Kennedy, K., \u201cBlocking Linear Algebra Codes for Memory Hierarchies\u201d, Proc. Fourth SIAM Conference on Parallel Processing for Scientific Computing, 1989."},{"key":"6_CR6","unstructured":"Davidson, Jack W., and Benitez, Manuel E., \u201cCode Generation for Streaming: An Access\/Execute Mechanism\u201d, Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, April 1991."},{"key":"6_CR7","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611971811","volume-title":"Linpack User's Guide","author":"Dongarra","year":"1979","unstructured":"Dongarra, et. al., \u201cLinpack User's Guide\u201c, SLAM, Philadelphia, 1979."},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Fu, J. W. C., and Patel, J. H., \u201cData Prefetching in Multiprocessor Vector Cache Memories\u201d, 18th International Symposium on Computer Architecture, May 1991.","DOI":"10.1145\/115952.115959"},{"key":"6_CR9","unstructured":"Golub, G., and Ortega, J.M., Scientific Computation: An Introduction with Parallel Computing, Academic Press, Inc., 1993."},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Goodman, J. R., et al, \u201cPIPE: A VLSI Decoupled Architecture\u201d, Twelfth International Symposium on Computer Architecture, June 1985.","DOI":"10.1145\/327070.327117"},{"issue":"9","key":"6_CR11","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1145\/62116.62137","volume":"23","author":"R. Gupta","year":"1988","unstructured":"Gupta, R., and Soffa, M., \u201cCompile-time Techniques for Efficient Utilization of Parallel Memories\u201d, SIGPLAN Not., 23, 9, 1988, pp. 235\u2013246.","journal-title":"SIGPLAN Not."},{"key":"6_CR12","first-page":"12","volume":"36","author":"D. T. Harper","year":"1987","unstructured":"Harper, D. T., Jump., J., \u201cVector Access Performance in Parallel Memories Using a Skewed Storage Scheme\u201d, IEEE Trans. Comput., 36, 12, 1987.","journal-title":"IEEE Trans. Comput."},{"key":"6_CR13","unstructured":"Harper, D. T., \u201cAddress Transformation to Increase Memory Performance\u201d, 1989 International Conference on Supercomputing."},{"key":"6_CR14","unstructured":"Hayes, J.P., Computer Architecture and Organization, McGraw-Hill, 1988."},{"key":"6_CR15","unstructured":"Hwang, K., and Briggs, F.A., Computer Architecture and Parallel Processing, McGraw-Hill, Inc., 1984."},{"key":"6_CR16","unstructured":"\u201cHigh-speed DRAMs\u201d, Special Report, IEEE Spectrum, vol. 29, no. 10, October 1992."},{"key":"6_CR17","unstructured":"i860 XP Microprocessor Data Book, Intel Corporation, 1991."},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Jouppi, N., \u201cImproving Direct-Mapped Cache Performance by the Addition of a Small Fully Associative Cache and Prefetch Buffers\u201d, 17th International Symposium on Computer Architecture, May 1990.","DOI":"10.1145\/325164.325162"},{"key":"6_CR19","unstructured":"Katz, R., and Hennessy, J., \u201cHigh Performance Microprocessor Architectures\u201d, University of California, Berkeley, Report No. UCB\/CSD 89\/529, August, 1989."},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Klaiber, A., et. al., \u201cAn Architecture for Software-Controlled Data Prefetching\u201d, 18th International Symposium on Computer Architecture, May 1991.","DOI":"10.1145\/115952.115958"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Lam, Monica, et. al., \u201cThe Cache Performance and Optimizations of Blocked Algorithms\u201d, Fourth International Conference on Architectural Support for Programming Languages and Systems, April 1991.","DOI":"10.1145\/106972.106981"},{"key":"6_CR22","first-page":"3","volume":"5","author":"Lawson","year":"1979","unstructured":"Lawson, et. al., \u201cBasic Linear Algebra Subprograms for Fortran Usage\u201d, ACM Trans. Math. Soft., 5, 3, 1979.","journal-title":"ACM Trans. Math. Soft."},{"key":"6_CR23","unstructured":"Lee, K., \u201cAchieving High Performance On the i860 Microprocessor Using Naspack Subroutines\u201d, NAS Systems Division, NASA Ames Research Center, July 1990."},{"key":"6_CR24","unstructured":"Lee, K., \u201cOn the Floating Point Performance of the i860 Microprocessor\u201d, RNR-90-019, NAS Systems Division, NASA Ames Research Center, October 1990."},{"key":"6_CR25","unstructured":"Maccabe, A.B., Computer Systems: Architecture, Organization, and Programming, Richard D. Irwin, Inc., 1993."},{"key":"6_CR26","unstructured":"Mano, M.M., Computer System Architecture, 2nd ed., Prentice-Hall, Inc., 1982"},{"key":"6_CR27","unstructured":"McMahon, F.H., \u201cThe Livermore Fortran Kernels: A Computer Test of the Numerical Performance Range\u201d, Lawrence Livermore National Laboratory, UCRL-53745, December 1986."},{"key":"6_CR28","unstructured":"McKee, S.A, \u201cHardware Support for Access Ordering: Performance of Some Design Options\u201d, University of Virginia, Department of Computer Science, Technical Report CS-93-08, July 1993."},{"key":"6_CR29","unstructured":"Meadows, L., Nakamoto, S., and Schuster, V., \u201cA Vectorizing, Software Pipelining Compiler for LIW and Superscalar Architectures\u201d, RISC'92, February 1992."},{"key":"6_CR30","unstructured":"Moyer, S.A., \u201cPerformance of the iPSC\/860 Node Architecture,\u201d University of Virginia, IPC-TR-91-007, 1991."},{"key":"6_CR31","unstructured":"Moyer, S., \u201cAccess Ordering and Effective Memory Bandwidth\u201d, Ph.D. Dissertation, Department of Computer Science, University of Virginia, Technical Report CS-93-18, April 1993."},{"key":"6_CR32","unstructured":"Quinnell, R., \u201cHigh-speed DRAMs\u201d, EDN, May 23, 1991."},{"key":"6_CR33","unstructured":"\u201cArchitectural Overview\u201d, Rambus Inc., Mountain View, CA, 1992."},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Rau, B. R., \u201cPseudo-Randomly Interleaved Memory\u201d, 18th International Symposium on Computer Architecture, May 1991.","DOI":"10.1145\/115952.115961"},{"key":"6_CR35","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1145\/141868.141869","volume":"20","author":"S. Ivan","year":"1992","unstructured":"Sklenar, Ivan, \u201cPrefetch Unit for Vector Operation on Scalar Computers\u201d, Computer Architecture News, 20, 4, September 1992.","journal-title":"Computer Architecture News"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Smith, J. E., et al, \u201cThe ZS-1 Central Processor\u201d, The Second International Conference on Architectural Support for Programming Languages and Systems, Oct. 1987","DOI":"10.1145\/36206.36203"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Sohi, G. and Manoj, F., \u201cHigh Bandwidth Memory Systems for Superscalar Processors\u201d, Fourth International Conference on Architectural Support for Programming Languages and Systems, April 1991.","DOI":"10.1145\/106972.106980"},{"key":"6_CR38","unstructured":"Tomek, I., The Foundations of Computer Architecture and Organization, Computer Science Press, 1990."},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Valero, M., et. al., \u201cIncreasing the Number of Strides for Conflict-Free Vector Access\u201d, 19th International Symposium on Computer Architecture, May 1992.","DOI":"10.1145\/139669.140400"},{"key":"6_CR40","unstructured":"Wallach, S., \u201cThe CONVEX C-1 64-bit Supercomputer\u201d, Compcon Spring 85, February 1985."},{"key":"6_CR41","volume-title":"Optimizing Supercompilers for Supercomputers","author":"M. Wolfe","year":"1989","unstructured":"Wolfe, M., \u201cOptimizing Supercompilers for Supercomputers\u201d, MIT Press, Cambridge, MA, 1989."},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Wulf, W. A., \u201cEvaluation of the WM Architecture\u201d, 19th Annual International Symposium on Computer Architecture, vol 20, no. 2, May 19\u201321, 1992.","DOI":"10.1145\/146628.140402"}],"container-title":["Lecture Notes in Computer Science","Programming Languages and System Architectures"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-57840-4_26.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T18:35:48Z","timestamp":1687286148000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-57840-4_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1994]]},"ISBN":["9783540578406","9783540483564"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/3-540-57840-4_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1994]]}}}