{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T22:49:47Z","timestamp":1725490187932},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540747413"},{"type":"electronic","value":"9783540747420"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007]]},"DOI":"10.1007\/978-3-540-74742-0_21","type":"book-chapter","created":{"date-parts":[[2007,8,21]],"date-time":"2007-08-21T07:03:30Z","timestamp":1187679810000},"page":"208-222","source":"Crossref","is-referenced-by-count":2,"title":["Comparing Direct-to-Cache Transfer Policies to TCP\/IP and M-VIA During Receive Operations in MPI Environments"],"prefix":"10.1007","author":[{"given":"Farshad","family":"Khunjush","sequence":"first","affiliation":[]},{"given":"Nikitas J.","family":"Dimopoulos","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Khunjush, F., Dimopoulos, N.J.: Lazy Direct-To-Cache Transfer during Receive Operations in a Message Passing Environment. In: Proceedings, the 3rd ACM International Conference on Computing Frontiers, CF 2006, pp. 331\u2013340 (2006)","DOI":"10.1145\/1128022.1128066"},{"key":"21_CR2","unstructured":"Khunjush, F., Dimopoulos, N.J.: Evaluation of Direct-To-Cache Transfer during Receive Operations in a Message Passing Environment. In: Proceedings, the Second International Workshop on Advanced Networking and Communications Hardware, ANCHOR2005, in conjunction with ISCA-32, pp. 22\u201329 (2005)"},{"issue":"1","key":"21_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1145\/1147349.1147358","volume":"34","author":"F. Khunjush","year":"2006","unstructured":"Khunjush, F., Dimopoulos, N.J.: Hiding Message Delivery and Reducing Memory Access Latency by providing Direct-to-Cache Transfer during Receive Operations in a Message Passing Environment. ACM SIGARCH Computer Architecture News\u00a034(1), 41\u201348 (2006)","journal-title":"ACM SIGARCH Computer Architecture News"},{"key":"21_CR4","unstructured":"Afsahi, A., Dimopoulos, N.J.: Architectural Extensions to Support Efficient Communication Using Message Prediction. In: Proceedings, HPCS2002, pp. 20\u201327 (2002)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Dubunicki, S., et al.: The Virtual Interface Architecture. IEEE Micro, 66\u201376 (March-April 1998)","DOI":"10.1109\/40.671404"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Engblom, J., et al.: Developing Embedded Networked Products using the Simics Full-System Simulator. In: Proceedings PIMRC 2005 (2005)","DOI":"10.1109\/PIMRC.2005.1651550"},{"key":"21_CR7","unstructured":"MPICH-A Portable Implementation of MPI: available at http:\/\/www-unix.mcs.anl.gov\/mpi\/mpich1\/"},{"key":"21_CR8","unstructured":"MVICH: MPI for Virtual Interface Architecture, http:\/\/www.nersc.gov\/research\/FTG\/mvich\/index.html"},{"key":"21_CR9","unstructured":"Bailey, D., et al.: The NAS Parallel Benchmarks 2.0: Report NAS-95-020. Nasa Ames Research Center (1995)"},{"key":"21_CR10","doi-asserted-by":"crossref","unstructured":"Worley, P., Foster, I.: Parallel Spectral Transform Shallow Water Model: A Runtime-tunable parallel benchmark code. In: Proceedings of the Scalable High Performance Computing Conference, pp. 207\u2013214 (1994)","DOI":"10.1109\/SHPCC.1994.296645"},{"issue":"2","key":"21_CR11","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1109\/2.982917","volume":"35","author":"T. Austin","year":"2002","unstructured":"Austin, T., et al.: SimpleScalar: an infrastructure for computer system modeling. IEEE Computer\u00a035(2), 59\u201367 (2002)","journal-title":"IEEE Computer"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Boden, N., et al.: Myrinet: A Gigabit-per-Second Local Area Network. IEEE Micro (1995)","DOI":"10.1109\/40.342015"},{"key":"21_CR13","unstructured":"InfiniBand Trade Association: InfiniBand Architecture Specification, http:\/\/www.infinibandta.org"},{"key":"21_CR14","unstructured":"Dubnicki, C., et al.: VMMC-2: Efficient Support for Reliable, Connection-Oriented Communication. In: Proceedings of the Hot Interconnect 1997 (1997)"},{"key":"21_CR15","unstructured":"Rodrigues, S., et al.: High-Performance Local Area Communication with Fast Sockets. In: USENIX 1997 (1997)"},{"key":"21_CR16","unstructured":"Basu, A., Welsh, M., Eicken, T.V.: Incorporating Memory Management into User-Level Network Interface. Hot Interconnects V (1997)"},{"issue":"10","key":"21_CR17","doi-asserted-by":"publisher","first-page":"1081","DOI":"10.1109\/71.963419","volume":"12","author":"M. Banikazemi","year":"2001","unstructured":"Banikazemi, M., et al.: MPI-LAPI: An Efficient Implementation of MPI for IBM RS\/6000 SP Systems. IEEE Trans. Parallel Distri. Systems\u00a012(10), 1081\u20131093 (2001)","journal-title":"IEEE Trans. Parallel Distri. Systems"},{"key":"21_CR18","unstructured":"Chu, H.: Zero-copy TCP in Solaris. In: Proceedings of the USENIX Annual Technical Conference, pp. 253\u2013263 (1996)"},{"key":"21_CR19","unstructured":"Alacritech, Inc.: Allacritech \/ SLIC technology overview, http:\/\/www.alacritech.com\/html\/tech_review.html"},{"key":"21_CR20","series-title":"Lecture Notes in Computer Science","volume-title":"Parallel Computing Technologies","author":"N.L. Binkert","year":"2005","unstructured":"Binkert, N.L., et al.: Performance Analysis of System Overheads in TCP\/IP Workloads. In: Malyshkin, V. (ed.) PaCT 2005. LNCS, vol.\u00a03606, Springer, Heidelberg (2005)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Huggahalli, R., Iyer, R., Tetrick, S.: Direct Cache Access for High Bandwidth Network I\/O. In: Proceedings, ISCA-32, pp. 50\u201359 (2005)","DOI":"10.1109\/ISCA.2005.23"},{"key":"21_CR22","unstructured":"Lauritzen, K., et al.: Intel I\/O acceleration technology improves network performance, reliability and efficiently. Technology@Intel magazine (2005), http:\/\/www.intel.com\/technology\/magazine\/communications\/Intel-IOAT-0305.pdf"},{"key":"21_CR23","unstructured":"RDMA Consortium: http:\/\/www.rdmaconsortium.org\/"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Acacio, M.E., et al.: Owner Prediction for Accelerating Cache-to-Cache Transfers in a cc-NUMA Architecture. In: Proceedings, SC 2002 (2002)","DOI":"10.1109\/SC.2002.10063"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Kim, J., Lilja, D.J.: Characterization of Communication Patterns in Message-Passing Parallel Scientific Application Programs. In: Proceedings of the Workshop on Communication, Architecture, and Applications for Network-based Parallel Computing, HPCA-4, pp. 202\u2013216 (1998)","DOI":"10.1007\/BFb0052218"},{"key":"21_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/10720115_12","volume-title":"Network-Based Parallel Computing - Communication, Architecture, and Applications","author":"A. Afsahi","year":"2000","unstructured":"Afsahi, A., Dimopoulos, N.J.: Efficient Communication Using Message Prediction for Cluster of Multiprocessors. In: Falsafi, B. (ed.) CANPC 2000. LNCS, vol.\u00a01797, pp. 162\u2013178. Springer, Heidelberg (2000)"},{"key":"21_CR27","unstructured":"M-VIA: Virtual Interface Architecture for Linux (2001), Was available at http:\/\/www.nserc.gov\/research\/FTG\/via\/"},{"key":"21_CR28","volume-title":"Computer Systems: A Programmer\u2019s Perspective","author":"R.E. Bryant","year":"2003","unstructured":"Bryant, R.E., O\u2019Hallaron, D.R.: Computer Systems: A Programmer\u2019s Perspective. Prentice-Hall, Englewood Cliffs (2003)"},{"key":"21_CR29","series-title":"Lecture Notes in Computer Science","volume-title":"Open Hypermedia Systems and Structural Computing","author":"F. Cappelo","year":"2000","unstructured":"Cappelo, F., Etiemble, D.: MPI versus MPI+OpenMP on the IBM SP for the NAS Benchmarks. In: Reich, S., Anderson, K.M. (eds.) Open Hypermedia Systems and Structural Computing. LNCS, vol.\u00a01903, Springer, Heidelberg (2000)"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Processing and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-74742-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,2]],"date-time":"2019-05-02T05:31:37Z","timestamp":1556775097000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-74742-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007]]},"ISBN":["9783540747413","9783540747420"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-74742-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2007]]}}}