{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:37:31Z","timestamp":1742981851677,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030495558"},{"type":"electronic","value":"9783030495565"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-49556-5_10","type":"book-chapter","created":{"date-parts":[[2020,6,8]],"date-time":"2020-06-08T23:05:06Z","timestamp":1591657506000},"page":"101-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["PSL: Exploiting Parallelism, Sparsity and Locality to Accelerate Matrix Factorization on x86 Platforms"],"prefix":"10.1007","author":[{"given":"Weixin","family":"Deng","sequence":"first","affiliation":[]},{"given":"Pengyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,9]]},"reference":[{"key":"10_CR1","unstructured":"Advanced vector extensions. https:\/\/en.wikipedia.org\/wiki\/Advanced_Vector_Extensions"},{"key":"10_CR2","unstructured":"Intel guide for developing multithreaded applications. https:\/\/software.intel.com\/sites\/default\/files\/m\/d\/4\/1\/d\/8\/GDMA_2.pdf"},{"key":"10_CR3","unstructured":"Intel math kernel library. https:\/\/software.intel.com\/en-us\/mkl"},{"key":"10_CR4","unstructured":"Movielens. https:\/\/grouplens.org\/datasets\/movielens\/"},{"key":"10_CR5","unstructured":"Openmp. https:\/\/en.wikipedia.org\/wiki\/OpenMP"},{"issue":"2","key":"10_CR6","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1162\/neco\\_a_01157","volume":"31","author":"AMS Ang","year":"2019","unstructured":"Ang, A.M.S., Gillis, N.: Accelerating nonnegative matrix factorization algorithms using extrapolation. Neural Comput. 31(2), 417\u2013439 (2019). https:\/\/doi.org\/10.1162\/neco_a_01157","journal-title":"Neural Comput."},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Balaji, V., Lucia, B.: Combining data duplication and graph reordering to accelerate parallel graph processing. In: Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2019, pp. 133\u2013144. ACM, New York (2019). https:\/\/doi.org\/10.1145\/3307681.3326609","DOI":"10.1145\/3307681.3326609"},{"key":"10_CR8","doi-asserted-by":"publisher","unstructured":"Chen, J., Fang, J., Liu, W., Tang, T., Chen, X., Yang, C.: Efficient and portable als matrix factorization for recommender systems. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 409\u2013418, May 2017. https:\/\/doi.org\/10.1109\/IPDPSW.2017.91","DOI":"10.1109\/IPDPSW.2017.91"},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"Chen, S., Fang, J., Chen, D., Xu, C., Wang, Z.: Adaptive optimization of sparse matrix-vector multiplication on emerging many-core architectures. In: 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 649\u2013658, June 2018. https:\/\/doi.org\/10.1109\/HPCC\/SmartCity\/DSS.2018.00116","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00116"},{"issue":"3","key":"10_CR10","doi-asserted-by":"publisher","first-page":"26:1","DOI":"10.1145\/3134442","volume":"44","author":"A Elafrou","year":"2018","unstructured":"Elafrou, A., Karakasis, V., Gkountouvas, T., Kourtis, K., Goumas, G., Koziris, N.: Sparsex: a library for high-performance sparse matrix-vector multiplication on multicore platforms. ACM Trans. Math. Softw. 44(3), 26:1\u201326:32 (2018). https:\/\/doi.org\/10.1145\/3134442","journal-title":"ACM Trans. Math. Softw."},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Eyerman, S., Heirman, W., Bois, K.D., Fryman, J.B., Hur, I.: Many-core graph workload analysis. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018 pp. 22:1\u201322:11. IEEE Press, Piscataway (2018). https:\/\/doi.org\/10.1109\/SC.2018.00025","DOI":"10.1109\/SC.2018.00025"},{"key":"10_CR12","unstructured":"Fog, A.: Optimizing software in C++. https:\/\/www.agner.org\/optimize\/optimizing_cpp.pdf"},{"key":"10_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-32813-9_1","volume-title":"Benchmarking, Measuring, and Optimizing","author":"W Gao","year":"2019","unstructured":"Gao, W., et al.: AIBench: towards scalable and comprehensive datacenter AI benchmarking. In: Zheng, C., Zhan, J. (eds.) Bench 2018. LNCS, vol. 11459, pp. 3\u20139. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32813-9_1"},{"key":"10_CR14","unstructured":"Gao, W., et al.: Aibench: An industry standard internet service ai benchmark suite. arXiv preprint arXiv:1908.08998 (2019)"},{"issue":"4","key":"10_CR15","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1162\/NECO\\_a\\_00256","volume":"24","author":"N Gillis","year":"2012","unstructured":"Gillis, N., Glineur, F.: Accelerated multiplicative updates and hierarchical ALS algorithms for nonnegative matrix factorization. Neural Comput. 24(4), 1085\u20131105 (2012). https:\/\/doi.org\/10.1162\/NECO_a_00256","journal-title":"Neural Comput."},{"key":"10_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/978-3-030-32813-9_3","volume-title":"Benchmarking, Measuring, and Optimizing","author":"T Hao","year":"2019","unstructured":"Hao, T., et al.: Edge AIBench: towards comprehensive end-to-end edge computing benchmarking. In: Zheng, C., Zhan, J. (eds.) Bench 2018. LNCS, vol. 11459, pp. 23\u201330. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32813-9_3"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Hao, T., Zheng, Z.: The implementation and optimization of matrix decomposition based collaborative filtering task on x86 platform. In: Gao, W., Zhan, J., Fox, G., Lu, X., Stanzione, D. (eds.) Bench 2019. LNCS, vol. 12093, pp. 110\u2013115. Springer, Cham (2019)","DOI":"10.1007\/978-3-030-49556-5_11"},{"key":"10_CR18","unstructured":"Hollowell, C., Caramarcu, C., Strecker-Kellogg, W., Wong, T., Zaytsev, A.: The effect of NUMA tunings on CPU performance. https:\/\/indico.cern.ch\/event\/304944\/contributions\/1672535\/attachments\/578723\/796898\/numa.pdf"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Hou, P., Yu, J., Miao, Y., Tai, Y., Wu, Y., Zhao, C.: RVTensor: a light-weight neural network inference framework based on the RISC-V architecture. In: Gao, W., Zhan, J., Fox, G., Lu, X., Stanzione, D. (eds.) Bench 2019. LNCS, vol. 12093, pp. 85\u201390. Springer, Cham (2019)","DOI":"10.1007\/978-3-030-49556-5_8"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, Z., et al.: HPC AI500: a benchmarksuite for HPC AI systems. In: 2018 Bench Council International Symposium on Benchmarking, Measuring and Optimizing, Bench 2018 (2018)","DOI":"10.1007\/978-3-030-32813-9_2"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Li, G., Wang, X., Ma, X., Liu, L., Feng, X.: XDN: towards efficient inference of residual neural networks on Cambricon chips. In: Gao, W., Zhan, J., Fox, G., Lu, X., Stanzione, D. (eds.) Bench 2019. LNCS, vol. 12093, pp. 51\u201356. Springer, Cham (2019)","DOI":"10.1007\/978-3-030-49556-5_4"},{"key":"10_CR22","doi-asserted-by":"publisher","unstructured":"Li, S., Hoefler, T., Snir, M.: NUMA-aware shared-memory collective communication for MPI. In: Proceedings of the 22nd International Symposium on High-performance Parallel and Distributed Computing, HPDC 2013, pp. 85\u201396. ACM, New York (2013). https:\/\/doi.org\/10.1145\/2493123.2462903","DOI":"10.1145\/2493123.2462903"},{"key":"10_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-030-32813-9_4","volume-title":"Benchmarking, Measuring, and Optimizing","author":"C Luo","year":"2019","unstructured":"Luo, C., et al.: AIoT bench: towards comprehensive benchmarking mobile and embedded device intelligence. In: Zheng, C., Zhan, J. (eds.) Bench 2018. LNCS, vol. 11459, pp. 31\u201335. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32813-9_4"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Mukkara, A., Beckmann, N., Abeydeera, M., Ma, X., Sanchez, D.: Exploiting locality in graph analytics through hardware-accelerated traversal scheduling. In: Proceedings of the 51st Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO-51, pp. 1\u201314. IEEE Press, Piscataway (2018). https:\/\/doi.org\/10.1109\/MICRO.2018.00010","DOI":"10.1109\/MICRO.2018.00010"},{"key":"10_CR25","unstructured":"van der Pas, R.: How to befriend NUMA. https:\/\/www.openmp.org\/wp-content\/uploads\/SC18-BoothTalks-vanderPas.pdf"},{"key":"10_CR26","doi-asserted-by":"publisher","unstructured":"Wang, P., Zhang, L., Li, C., Guo, M.: Excavating the potential of GPU for accelerating graph traversal. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 221\u2013230, May 2019. https:\/\/doi.org\/10.1109\/IPDPS.2019.00032","DOI":"10.1109\/IPDPS.2019.00032"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Xiong, X., Wen, X., Huang, C.: Improving RGB-D face recognition via transfer learning from a pretrained 2D network. In: Gao, W., Zhan, J., Fox, G., Lu, X., Stanzione, D. (eds.) Bench 2019. LNCS, vol. 12093, pp. 141\u2013148. Springer, Cham (2019)","DOI":"10.1007\/978-3-030-49556-5_14"},{"key":"10_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/978-3-540-68880-8_32","volume-title":"Algorithmic Aspects in Information and Management","author":"Y Zhou","year":"2008","unstructured":"Zhou, Y., Wilkinson, D., Schreiber, R., Pan, R.: Large-scale parallel collaborative filtering for the netflix prize. In: Fleischer, R., Xu, J. (eds.) AAIM 2008. LNCS, vol. 5034, pp. 337\u2013348. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-68880-8_32"}],"container-title":["Lecture Notes in Computer Science","Benchmarking, Measuring, and Optimizing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-49556-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,19]],"date-time":"2021-03-19T09:23:20Z","timestamp":1616145800000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-49556-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030495558","9783030495565"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-49556-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"9 June 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denver, CO","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.benchcouncil.org\/bench19\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"79","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"11","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}