{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T19:47:13Z","timestamp":1725652033424},"reference-count":16,"publisher":"IEEE Comput. Soc","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/clustr.2002.1137747","type":"proceedings-article","created":{"date-parts":[[2003,6,26]],"date-time":"2003-06-26T01:03:42Z","timestamp":1056589422000},"page":"195-203","source":"Crossref","is-referenced-by-count":0,"title":["Mixed mode matrix multiplication"],"prefix":"10.1109","author":[{"family":"Meng-Shiou Wu","sequence":"first","affiliation":[]},{"given":"S.","family":"Aluru","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Introduction to Parallel Computing Design and Analysis of Parallel Algorithms","year":"1994","author":"kumar","key":"ref10"},{"key":"ref11","first-page":"370","article-title":"The influence of caches on the performance of sorting","author":"lamarca","year":"1997","journal-title":"Proceedings of the 8th ACM-SIAM Symposium on Discrete Algorithms"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263591"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0871-6","author":"sagan","year":"1994","journal-title":"Space-Filling Curves"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF02165411"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SC.1998.10045"},{"key":"ref16","article-title":"Automatically tuned linear algebra software","author":"whaley","year":"1997","journal-title":"Technical Report UT-CS-97-366"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305231"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/5992.947105"},{"journal-title":"Software Optimization for High Performance Computing Creating Faster Applications","year":"2000","author":"crawford","key":"ref6"},{"key":"ref5","first-page":"222","article-title":"Recursive array layouts and fast parallel matrix multiplication","author":"chatterjee","year":"1999","journal-title":"ACM Symposium on Parallel Algorithms and Architectures"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1145\/263764.263789","article-title":"Auto-blocking matrix-multiplication or tracking blas3 performance from source code","author":"frens","year":"1997","journal-title":"Proceedings of the Sixth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"},{"journal-title":"High Performance Computing","year":"1998","author":"dowd","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1996.508049"},{"year":"0","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814600"}],"event":{"name":"2002 IEEE International Conference on Cluster Computing","acronym":"CLUSTR-02","location":"Chicago, IL, USA"},"container-title":["Proceedings. IEEE International Conference on Cluster Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8231\/25385\/01137747.pdf?arnumber=1137747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T15:30:51Z","timestamp":1682523051000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1137747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/clustr.2002.1137747","relation":{},"subject":[]}}