{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T05:06:59Z","timestamp":1725772019568},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/ipdps.2017.116","type":"proceedings-article","created":{"date-parts":[[2017,7,3]],"date-time":"2017-07-03T16:41:58Z","timestamp":1499100118000},"page":"254-264","source":"Crossref","is-referenced-by-count":13,"title":["Accelerating Graph and Machine Learning Workloads Using a Shared Memory Multicore Architecture with Auxiliary Support for In-hardware Explicit Messaging"],"prefix":"10.1109","author":[{"given":"Halit","family":"Dogan","sequence":"first","affiliation":[]},{"given":"Farrukh","family":"Hijaz","sequence":"additional","affiliation":[]},{"given":"Masab","family":"Ahmad","sequence":"additional","affiliation":[]},{"given":"Brian","family":"Kahne","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Wilson","sequence":"additional","affiliation":[]},{"given":"Omer","family":"Khan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","article-title":"Imagenet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Computers and pattern recognition"},{"key":"ref32","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033589"},{"journal-title":"Squeezenet Alexnet-level accuracy with 50x fewer parameters and< 0 5 mb model size","year":"2016","author":"iandola","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/2.612254"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1736020.1736055"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2307874"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1145\/1508244.1508274","article-title":"Accelerating critical section execution with asymmetric multicore architectures","author":"suleman","year":"2009","journal-title":"Intl Conf on Architectural Support for Programming Languages and Operating Systems"},{"key":"ref14","article-title":"Haqu: Hardware-accelerated queueing for fine-grained threading on a chip multiprocessor","author":"tiwari","year":"2011","journal-title":"Proc Int Symp High Performance Comput Architecture"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967954"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2007.4378780"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2872362.2872414"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2254064.2254102"},{"journal-title":"Neural Networks and Deep Learning","year":"2015","author":"nielsen","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3837"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/NOCS.2012.31"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2556612"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541964"},{"article-title":"Mnist handwritten digit database","year":"1992","author":"lecun","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2015.11"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/165939.165970"},{"journal-title":"The Art of Multiprocessor Programming","year":"2008","author":"herlihy","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2009.10129177"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.1992.753322"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2007.375263"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1090\/qam\/253822"},{"journal-title":"Principles and Practices of Interconnection Networks","year":"2004","author":"dally","key":"ref22"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1145\/1854273.1854332","article-title":"ATAC: A 1000-core cache-coherent processor with on-chip optical network","author":"kurian","year":"2010","journal-title":"Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques (PACT)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2010.5416635"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228431"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2011.42"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1669112.1669172"}],"event":{"name":"2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","start":{"date-parts":[[2017,5,29]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2017,6,2]]}},"container-title":["2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7965806\/7967079\/07967115.pdf?arnumber=7967115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,30]],"date-time":"2022-07-30T06:59:59Z","timestamp":1659164399000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7967115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/ipdps.2017.116","relation":{},"subject":[],"published":{"date-parts":[[2017,5]]}}}