{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T15:55:40Z","timestamp":1742399740911,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540377832"},{"type":"electronic","value":"9783540377849"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11823285_14","type":"book-chapter","created":{"date-parts":[[2006,9,5]],"date-time":"2006-09-05T18:04:04Z","timestamp":1157479444000},"page":"134-144","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Optimization of Dense Matrix Multiplication on IBM Cyclops-64: Challenges and Experiences"],"prefix":"10.1007","author":[{"given":"Ziang","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"del Cuvillo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weirong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"14_CR1","unstructured":"Denneau, M., Warren, Jr., H.S.: 64-bit Cyclops principles of operation part I. Technical report, IBM Watson Research Center, Yorktown Heights, NY (2005)"},{"key":"14_CR2","unstructured":"Denneau, M., Warren, Jr., H.S.: 64-bit Cyclops principles of operation part II: Memory organization, the A-switch, and SPRs. Technical report, IBM Watson Research Center, Yorktown Heights, NY (2005)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Almagor, L., Cooper, K.D., Al, E.: Finding effective compilation sequences. In: LCTES 2004, Wahsington, DC, USA (2004)","DOI":"10.1145\/997163.997196"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Wolf, M.E., Maydan, D.E., Chen, D.K.: Combining loop transformations considering caches and scheduling. In: Proceedings of the 29th Annual International Symposium on Microarchitecture, Paris, IEEE-CS TC-MICRO and ACM SIGMICRO, pp. 274\u2013286 (1996)","DOI":"10.1109\/MICRO.1996.566468"},{"key":"14_CR5","unstructured":"del Cuvillo, J., Zhu, W., Hu, Z., Gao, G.R.: Fast: A functionally accurate simulation toolset for the cyclops-64 cellular architecture. In: Workshop on Modeling, Benchmarking and Simulation (MoBS 2005) of ISCA 2005, Madison, Wisconsin (2005)"},{"key":"14_CR6","volume-title":"Optimizing Compilers for Modern Architectures: A Dependence-based Approach","author":"R. Allen","year":"2001","unstructured":"Allen, R., Kennedy, K.: Optimizing Compilers for Modern Architectures: A Dependence-based Approach. Morgan Kaufmann, San Francisco (2001)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Wolf, M.E., Lam, M.S.: A data locality optimizing algorithm. In: Proceedings of the ACM SIGPLAN 1991 Conference on Programming Language Design and Implementation, Toronto, Ontario, pp. 30\u201344 (1991), SIGPLAN Notices 26(6) (June 1991)","DOI":"10.1145\/113446.113449"},{"issue":"5","key":"14_CR8","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1145\/381792.195557","volume":"28","author":"S. Carr","year":"1994","unstructured":"Carr, S., McKinley, K.S., Tseng, C.W.: Compiler optimizations for improving data locality. In: Proceedings of the Sixth International Conference on Architectural Support for Programming Languages and Operating Systems, San Jose, California, pp. 252\u2013262. ACM SIGARCH, SIGOPS, SIGPLAN, and the IEEE Computer Society (1994), Computer Architecture News (October 22, 1994) Operating Systems Review 28(5) (December 1994), SIGPLAN Notices 29(11) (November 1994)","journal-title":"Operating Systems Review"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Anderson, J.M., Lam, M.S.: Global optimizations for parallelism and locality on scalable parallel machines. In: Proceedings of the ACM SIGPLAN 1993 Conference on Programming Language Design and Implementation, Albuquerque, New Mexico, pp. 112\u2013125 (1993), SIGPLAN Notices 28(6) (June 1993)","DOI":"10.1145\/173262.155101"},{"key":"14_CR10","volume-title":"High Performance Compilers for Parallel Computing","author":"M.J. Wolfe","year":"1995","unstructured":"Wolfe, M.J.: High Performance Compilers for Parallel Computing. Addison-Wesley Longman Publishing, Boston (1995)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Lim, A.W., Lam, M.S.: Maximizing parallelism and minimizing synchronization with affine transforms. In: Conference Record of POPL 1997: The 24th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, Paris, pp. 201\u2013214 (1997)","DOI":"10.1145\/263699.263719"},{"key":"14_CR12","unstructured":"Wolfe, M.: Iteration space tiling for memory hierarchies (SIAM) Parallel Processing for Scientific Computing, pp. 36\u2013361 (1987)"},{"key":"14_CR13","unstructured":"Andonov, R., Bourzoufi, H., Rajopadhye, S.: Two-dimensional orthogonal tiling: from theory to pratice. In: HiPC 1996, Trivandrum, India (1996)"},{"key":"14_CR14","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-4337-4","volume-title":"Loop Tiling for Parallelism","author":"J. Xue","year":"2000","unstructured":"Xue, J.: Loop Tiling for Parallelism. Kluwer Academic Publishers, Dordrecht (2000)"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Calder, B., Krintz, C., John, S., Austin, T.: Cache-conscious data placement. In: Proceedings of the Eighth International Conference on Architectural Support for Programming Languages and Operating Systems, San Jose, California, pp. 139\u2013149. ACM SIGARCH, SIGOPS, SIGPLAN, and the IEEE Computer Society (1998), Computer Architecture News (October 26, 1998), Operating Systems Review 32(5) (December 1998), SIGPLAN Notices 33(11) (November 1998)","DOI":"10.1145\/291006.291036"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Ding, C., Kennedy, K.: Improving cache performance in dynamic applications through data and computation reorganization at run time. In: [22], May 1999. SIGPLAN Notices 34(5), 229\u2013241 (1999)","DOI":"10.1145\/301631.301670"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Kennedy, K., Kremer, U.: Automatic data layout for distributed memory machines. ACM Transactions on Programming Languages and Systems\u00a020(4) (1998)","DOI":"10.1145\/291891.291901"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Chilimbi, T.M., Davidson, B., Larus, J.R.: Cache-conscious structure definition. In: [22], May 1999. SIGPLAN Notices 34(5), 13\u201324 (1999)","DOI":"10.1145\/301631.301635"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Gloy, N., Smith, M.D.: Procedure placement using temporal-ordering information. ACM Transactions on Programming Languages and Systems\u00a021(5) (1999)","DOI":"10.1145\/330249.330254"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Ding, C., Kennedy, K.: Improving effective bandwidth through compiler enhancement of global cache reuse. Parallel and Distributed Computing\u00a064(1) (2004)","DOI":"10.1016\/j.jpdc.2003.09.005"},{"key":"14_CR21","unstructured":"Ding, C., Orlovich, M.: The potential of computation regrouping for improving locality. In: SuperComputing 2004, Pittsburgh, PA (2004)"},{"key":"14_CR22","unstructured":"Proceedings of the ACM SIGPLAN 1999 Conference on Programming Language Design and Implementation. In: Proceedings of the ACM SIGPLAN 1999 Conference on Programming Language Design and Implementation, Atlanta, Georgia (1999), SIGPLAN Notices 34(5) (May 1999)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2006 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11823285_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T19:26:01Z","timestamp":1736537161000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11823285_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540377832","9783540377849"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/11823285_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}