{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T15:48:28Z","timestamp":1764172108475,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1109\/hpec.2014.7040954","type":"proceedings-article","created":{"date-parts":[[2015,2,17]],"date-time":"2015-02-17T19:50:25Z","timestamp":1424202625000},"page":"1-6","source":"Crossref","is-referenced-by-count":12,"title":["HAMLeT: Hardware accelerated memory layout transform within 3D-stacked DRAM"],"prefix":"10.1109","author":[{"given":"Berkin","family":"Akin","sequence":"first","affiliation":[]},{"given":"James C.","family":"Hoe","sequence":"additional","affiliation":[]},{"given":"Franz","family":"Franchetti","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Multithreaded Transposition of Square Matrices with Common Code for Intel Xeon Processors and Intel Xeon Phi Coprocessors","year":"2013","author":"vladimirov","key":"19"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2012.40"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.50"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2003.1214317"},{"year":"0","author":"choi","key":"16"},{"year":"2008","key":"13"},{"key":"14","doi-asserted-by":"crossref","first-page":"801","DOI":"10.1109\/T-C.1972.223584","article-title":"a fast computer method for matrix transposing","volume":"c 21","author":"eklundh","year":"1972","journal-title":"IEEE Transactions on Computers"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1145\/1502793.1502799"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854332"},{"year":"0","key":"21"},{"key":"20","article-title":"Optimizing matrix transpose in cuda","author":"ruetsch","year":"2009","journal-title":"NVIDIA Technical Report"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828946"},{"key":"23","first-page":"53","article-title":"Hardware support for bulk data movement in server platforms","author":"zhao","year":"2005","journal-title":"Proc of IEEE Intl Conf on Computer Design (ICCD)"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"25","first-page":"131","article-title":"Dymaxion: Optimizing memory access patterns for heterogeneous systems","author":"che","year":"2011","journal-title":"Proc of Intl Conf for High Perf Comp Networking Storage and Analysis (SC)"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2014.6868669"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1145\/113445.113449"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1145\/233561.233564"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/VLSIT.2012.6242474"},{"key":"1","first-page":"128","article-title":"Memory access scheduling","author":"rixner","year":"2000","journal-title":"Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat No RS00201) ISCA"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2012.2235125"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.15"},{"key":"5","article-title":"Hybrid memory cube (HMC)","author":"pawlowski","year":"2011","journal-title":"HOTCHIPS"},{"key":"4","first-page":"219","article-title":"Micro-pages: Increasing dram efficiency with localityaware data placement","author":"sudan","year":"2010","journal-title":"Proc of Arch Sup for Prog Lang and OS Ser ASPLOS XV"},{"key":"9","first-page":"33","article-title":"CACTI-3DD: Architecture-level modeling for 3D diestacked DRAM main memory","author":"chen","year":"2012","journal-title":"Proceedings of the Design Automation and Test in Europe (DATE)"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/3DIC.2013.6702348"}],"event":{"name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","start":{"date-parts":[[2014,9,9]]},"location":"Waltham, MA, USA","end":{"date-parts":[[2014,9,11]]}},"container-title":["2014 IEEE High Performance Extreme Computing Conference (HPEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7027306\/7040940\/07040954.pdf?arnumber=7040954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T05:43:56Z","timestamp":1498196636000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7040954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/hpec.2014.7040954","relation":{},"subject":[],"published":{"date-parts":[[2014,9]]}}}