{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T06:55:21Z","timestamp":1747810521091},"publisher-location":"Berlin, Heidelberg","reference-count":34,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540775591"},{"type":"electronic","value":"9783540775607"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-77560-7_3","type":"book-chapter","created":{"date-parts":[[2008,1,17]],"date-time":"2008-01-17T01:13:02Z","timestamp":1200532382000},"page":"22-37","source":"Crossref","is-referenced-by-count":10,"title":["rMPI: Message Passing on Multicore Processors with On-Chip Interconnect"],"prefix":"10.1007","author":[{"given":"James","family":"Psota","sequence":"first","affiliation":[]},{"given":"Anant","family":"Agarwal","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"3_CR1","unstructured":"Intel pentium d, http:\/\/www.intel.com\/products\/processor\/pentium_d\/"},{"key":"3_CR2","unstructured":"Moore\u2019s law 40th anniversary, http:\/\/www.intel.com\/technology\/mooreslaw\/index.htm"},{"key":"3_CR3","unstructured":"The multicore association communications api, http:\/\/www.multicore-association.org\/workgroup\/ComAPI.html"},{"key":"3_CR4","unstructured":"Transputer reference manual. Prentice Hall International (UK) Ltd. Hertfordshire, UK (1998)"},{"key":"3_CR5","unstructured":"Borkar, S., Cohn, R., Cox, G., Gleason, S., Gross, T., Kung, H.T., Lam, M., Moore, B., Peterson, C., et al.: iwarp: An integrated solution to high-speed parallel computing. In: Proceedings of Supercomputing (1998)"},{"key":"3_CR6","unstructured":"Burns, G., Daoud, R., Vaigl, J.: LAM: An Open Cluster Environment for MPI. In: Proceedings of Supercomputing Symposium, pp. 379\u2013386 (1994)"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Espasa, et al.: Tarantula: A Vector Extension to the Alpha Architecture. In: ISCA, pp. 281\u2013292 (2002)","DOI":"10.1109\/ISCA.2002.1003586"},{"issue":"1","key":"3_CR8","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1147\/rd.461.0005","volume":"46","author":"J. T.","year":"2002","unstructured":"T.J., et al.: POWER4 system microarchitecture. IBM Journal of Research and Development\u00a046(1), 5\u201325 (2002)","journal-title":"IBM Journal of Research and Development"},{"key":"3_CR9","unstructured":"Forum, M.: A message passing interface standard. Technical report, University of Tennessee, Knoxville (1994)"},{"key":"3_CR10","unstructured":"Forum, M.P.I.: Mpi: A message-passing interface standard (1995), http:\/\/www.mpi-forum.org\/docs\/mpi-11-html\/mpi-report.html"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Gabriel, E., Fagg, G.E., Bosilca, G., Angskun, T., Dongarra, J.J., Squyres, J.M., Sahay, V., Kambadur, P., Barrett, B., Lumsdaine, A., Castain, R.H., Daniel, D.J., Graham, R.L., Woodall, T.S.: Open MPI: Goals, concept, and design of a next generation MPI implementation. In: Proceedings, 11th European PVM\/MPI Users\u2019 Group Meeting, Budapest, Hungary, pp. 97\u2013104 (September 2004)","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Gordon, M.I., Thies, W., Karczmarek, M., Lin, J., Meli, A.S., Lamb, A.A., Leger, C., Wong, J., Hoffmann, H., Maze, D., Amarasinghe, S.: A Stream Compiler for Communication-Exposed Architectures. In: Conference on Architectural Support for Programming Languages and Operating Systems, pp. 291\u2013303 (2002)","DOI":"10.1145\/605397.605428"},{"key":"3_CR13","unstructured":"Griffin, P.: CFlow. Master\u2019s thesis, Lab for Computer Science, MIT (2005)"},{"key":"3_CR14","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4789.001.0001","volume-title":"MPI: The Complete Reference","author":"W. Gropp","year":"1998","unstructured":"Gropp, W., Huss-Lederman, S., et al.: MPI: The Complete Reference, vol.\u00a02. The MIT Press, Cambridge (1998)"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Gropp, W.D., Lusk, E.: User\u2019s Guide for mpich, a Portable Implementation of MPI. In: ANL-96\/6. Mathematics and Computer Science Division, Argonne National Laboratory (1996)","DOI":"10.2172\/378911"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Hinrichs, S., Kosak, C., O\u2019Hallaron, D., Stricker, T., Take, R.: An architecture for optimal all-to-all personalized communication. In: Proceedings of Symposium on Parallelism in Algorithms and Architectures (1994)","DOI":"10.1145\/181014.181427"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Karamcheti, V., Chien, A.A.: Software overhead in messaging layers: Where does the time go? In: Proceedings of the Sixth International Conference on Architectural Support for Programming Languages and Operating Systems, San Jose, California, pp. 51\u201360 (1994)","DOI":"10.1145\/195473.195499"},{"key":"3_CR18","unstructured":"Kozyrakis, C.E., Patterson, D.: A new direction for computer architecture research. Journal of the ACM (1997)"},{"key":"3_CR19","unstructured":"Kubiatowicz, J.: Integrated Shared-Memory and Message-Passing Communication in the Alewife Multiprocessor. PhD thesis, MIT (1998)"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Lee, W., Barua, R., Frank, M., Srikrishna, D., Babb, J., Sarkar, V., Amarasinghe, S.: Space-Time Scheduling of Instruction-Level Parallelism on a Raw Machine. In: Proceedings of the Eighth ACM Conference on Architectural Support for Programming Languages and Operating Systems, San Jose, CA, pp. 46\u201357 (October 1998)","DOI":"10.1145\/291069.291018"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Mai, K., Paaske, T., Jayasena, N., Ho, R., Dally, W., Horowitz, M.: Smart memories: A modular reconfigurable architecture. In: Proceedings of the 27th International Symposium on Computer Architecture, pp. 161\u2013170 (2000)","DOI":"10.21236\/ADA419598"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Mai, et al.: Smart Memories: A Modular Reconfigurable Architecture. In: ISCA (2000)","DOI":"10.21236\/ADA419598"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Nagarajan, R., Sankaralingam, K., Burger, D., Keckler, S.W.: A design space evaluation of grid processor architectures. In: International Symposium on Microarchitecture (MICRO) (2001)","DOI":"10.1109\/MICRO.2001.991104"},{"key":"3_CR24","volume-title":"Parallel Programming with MPI","author":"P.S. Pacheco","year":"1997","unstructured":"Pacheco, P.S.: Parallel Programming with MPI. Morgan Kaufmann Publishers, San Francisco (1997)"},{"key":"3_CR25","unstructured":"Psota, J.: rMPI: An MPI-Compliant Message Passing Library for Tiled Architectures. Master\u2019s thesis, Lab for Computer Science, MIT (2005), http:\/\/cag.lcs.mit.edu\/jim\/publications\/ms.pdf"},{"key":"3_CR26","volume-title":"Parallel Programming in C with MPI and OpenMP","author":"M.J. Quinn","year":"2004","unstructured":"Quinn, M.J.: Parallel Programming in C with MPI and OpenMP. McGraw Hill, New York (2004)"},{"key":"3_CR27","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4789.001.0001","volume-title":"MPI: The Complete Reference","author":"W. Gropp","year":"1998","unstructured":"Gropp, W., Huss-Lederman, S., et al.: MPI: The Complete Reference. The MIT Press, Cambridge (1998)"},{"key":"3_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1007\/978-3-540-39924-7_52","volume-title":"EuroPVM\/MPI 2003","author":"J.M. Squyres","year":"2003","unstructured":"Squyres, J.M., Lumsdaine, A.: A Component Architecture for LAM\/MPI. In: Dongarra, J.J., Laforenza, D., Orlando, S. (eds.) EuroPVM\/MPI 2003. LNCS, vol.\u00a02840, pp. 379\u2013387. Springer, Heidelberg (2003)"},{"key":"3_CR29","unstructured":"Swanson, S., Michelson, K., Schwerin, A., Oskin, M.: Wavescalar. In: In the 36th Annual International Symposium on Microarchitecture (MICRO-36) (2003)"},{"key":"3_CR30","unstructured":"Taylor, M.B.: The Raw Processor Specification, ftp:\/\/ftp.cag.lcs.mit.edu\/pub\/raw\/documents\/RawSpec99.pdf"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Taylor, et al.: The Raw Microprocessor: A Computational Fabric for Software Circuits and General-Purpose Programs. IEEE Micro, 25\u201335 ( March 2002)","DOI":"10.1109\/MM.2002.997877"},{"key":"3_CR32","unstructured":"Taylor, et al.: Scalar Operand Networks: On-Chip Interconnect for ILP in Partitioned Architectures. In: HPCA (2003)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Taylor, et al.: Evaluation of the Raw Microprocessor: An Exposed-Wire-Delay Architecture for ILP and Streams. In: ISCA (2004)","DOI":"10.1145\/1028176.1006733"},{"key":"3_CR34","unstructured":"William Gropp, A.S., Lusk. E.: A high-performance, portable implementation of the mpi message passing interface standard, http:\/\/www-unix.mcs.anl.gov\/mpi\/mpich\/papers\/mpicharticle\/paper.html"}],"container-title":["Lecture Notes in Computer Science","High Performance Embedded Architectures and Compilers"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-77560-7_3.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T06:44:29Z","timestamp":1619505869000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77560-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540775591","9783540775607"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77560-7_3","relation":{},"subject":[]}}