{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:31:17Z","timestamp":1743150677392,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755905"},{"type":"electronic","value":"9789819755912"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-5591-2_11","type":"book-chapter","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T18:02:42Z","timestamp":1723572162000},"page":"124-136","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimization of NUMA Aware DNN Computing System"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5409-8670","authenticated-orcid":false,"given":"Xiaoxiang","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2890-260X","authenticated-orcid":false,"given":"Pan","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5853-0993","authenticated-orcid":false,"given":"Jun","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9499-5940","authenticated-orcid":false,"given":"Leilei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4741-517X","authenticated-orcid":false,"given":"Yan","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8509-3167","authenticated-orcid":false,"given":"Zhe","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Matthias, D., et al.: Affinity-based thread and data mapping in shared memory systems.\u00a0ACM Comput. Surv.\u00a049(4), 1\u201338 (2016)","DOI":"10.1145\/3006385"},{"key":"11_CR2","unstructured":"numactl(8)-Linux man page. https:\/\/linux.die.net\/man\/8\/numactl. Accessed 3 March 2024"},{"issue":"9","key":"11_CR3","first-page":"16","volume":"40","author":"HJ Li","year":"2017","unstructured":"Li, H.J., et al.: A memory allocation policy for the balance of access latency among multiple memory nodes in NUMA architecture. Chin. J. Comput. 40(9), 16 (2017)","journal-title":"Chin. J. Comput."},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"John, B., et al.: Extending OpenMP for NUMA machines.\u00a0In: SC\u201900: Proceedings of the 2000 ACM\/IEEE Conference on Supercomputing, p. 48. IEEE, Dallas, TX, USA (2000)","DOI":"10.1109\/SC.2000.10019"},{"key":"11_CR5","unstructured":"AutoNUMA: The Other Approach to NUMAScheduling. http:\/\/lwn.net\/Articles\/488709. Accessed 8 May 2024"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Cruz, Eduardo, H.M., et al.: An efficient algorithm for communication-based task mapping.\u00a0In: 2015 23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, pp. 207\u2013214. IEEE, Turku,\u00a0FINLAND (2015)","DOI":"10.1109\/PDP.2015.25"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Cruz, Eduardo, H.M., et al.: Dynamic thread mapping of shared memory applications by exploiting cache coherence protocols.\u00a0J. Parallel Distrib. Comput.\u00a074(3), 2215\u20132228 (2014)","DOI":"10.1016\/j.jpdc.2013.11.006"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, Y., Zhang, X.: CMLB: a communication-aware and memory load balance mapping optimization for modern NUMA systems. In: 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor. Cloud & Big Data Systems & Application (HPCC\/DSS\/SmartCity\/DependSys), pp. 579\u2013586. IEEE, Haikou, Hainan, China (2021)","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys53884.2021.00099"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Fran\u00e7ois, B., et al.: ForestGOMP: an efficient OpenMP environment for NUMA architectures.\u00a0Int. J. Parallel Program.\u00a038(5\u20136), 418\u2013439 (2010)","DOI":"10.1007\/s10766-010-0136-3"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Mohammad, D., et al.: Traffic management: a holistic approach to memory placement on NUMA systems.\u00a0ACM SIGPLAN Not.\u00a048(4), 381\u2013394 (2013)","DOI":"10.1145\/2499368.2451157"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Li, D., et al.: Optimizing massively parallel winograd convolution on arm processor.\u00a0In: Proceedings of the 50th International Conference on Parallel Processing, pp. 1\u201312. ACM, ELECTR NETWORK (2021)","DOI":"10.1145\/3472456.3472496"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: Numa-aware fft-based convolution on armv8 many-core CPUS. In:\u00a02021 IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA\/BDCloud\/SocialCom\/SustainCom), pp. 1019-1026. IEEE, New York (2021)","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00142"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, J., et al.: Full-stack optimizing transformer inference on ARM many-core CPU.\u00a0IEEE Trans. Parallel Distrib. Syst. 34(7), 2221\u20132235\u00a0(2023)","DOI":"10.1109\/TPDS.2023.3280805"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Tallada, M.G.: Coarse grain parallelization of deep neural networks. In:\u00a0Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. pp. 1\u201312. ACM, Barcelona,\u00a0SPAIN (2016)","DOI":"10.1145\/2851141.2851158"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Roy, P., et al.: Numa-caffe: numa-aware deep learning neural networks.\u00a0ACM Trans. Architect. Code Optim.\u00a015(2), 1\u201326 (2018)","DOI":"10.1145\/3199605"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Qin, L., et al: Training deep nets with progressive batch normalization on multi-GPUs.\u00a0Int. J. Parallel Program.\u00a047(3), 373\u2013387 (2019)","DOI":"10.1007\/s10766-018-0615-5"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Yin, L., et al.: Parax: boosting deep learning for big data analytics on many-core CPUS.\u00a0Proc. VLDB Endow.\u00a014(6), 864\u2013877 (2021)","DOI":"10.14778\/3447689.3447692"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: ParaX: bandwidth-efficient instance assignment for DL on multi-NUMA many-core CPUs.\u00a0IEEE Trans. Comput.\u00a071(11), 3032\u20133046 (2022)","DOI":"10.1109\/TC.2022.3145164"},{"key":"11_CR19","unstructured":"Linux Manpages Online. https:\/\/man.cx\/mbind. Accessed 8 April 2024"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5591-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T17:43:00Z","timestamp":1732642980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5591-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755905","9789819755912"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5591-2_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"14 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}