{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:03:15Z","timestamp":1763190195840,"version":"3.45.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032104656","type":"print"},{"value":"9783032104663","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-10466-3_37","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T06:59:40Z","timestamp":1763189980000},"page":"448-460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Reducing Load-Balancing Cost for\u00a0Multithreading Applications on\u00a0Asymmetric NUMA Machine"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6963-883X","authenticated-orcid":false,"given":"Yuhang","family":"Fang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3685-0901","authenticated-orcid":false,"given":"Pu","family":"Pang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5832-0347","authenticated-orcid":false,"given":"Quan","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6099-614X","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0034-2302","authenticated-orcid":false,"given":"Minyi","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"key":"37_CR1","unstructured":"Apache http server. http:\/\/httpd.apache.org\/"},{"key":"37_CR2","unstructured":"hackbench. https:\/\/github.com\/linux-test-project\/ltp\/blob\/master\/testcases\/kernel\/sched\/cfs-scheduler\/hackbench.c"},{"key":"37_CR3","unstructured":"Mysql. https:\/\/www.mysql.com\/"},{"key":"37_CR4","unstructured":"New AMD-based Dav4 and Eav4 azure VMs are available in additional regions (2020). https:\/\/azure.microsoft.com\/en-us\/updates\/new-amdbased-dav4-and-eav4-azure-vms-are-available-in-additional-regions\/"},{"key":"37_CR5","unstructured":"Amazon EC2 M7a instances are now available in additional regions. https:\/\/aws.amazon.com\/about-aws\/whats-new\/2024\/03\/amazon-ec2-m7a-instances-additional-regions\/ (2024)"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Antoniadis, K., Guerraoui, R., Trigonakis, V.: Thread-placement learning. In: ICDCS (2020)","DOI":"10.1109\/ICDCS47774.2020.00050"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Bailey, D.H., et\u00a0al.: The NAS parallel benchmarks\u2014summary and preliminary results. In: SC (1991)","DOI":"10.1145\/125826.125925"},{"key":"37_CR8","doi-asserted-by":"crossref","unstructured":"Bhatele, A., Kale, L.V.: Application-specific topology-aware mapping for three dimensional topologies. In: IPDPS. IEEE (2008)","DOI":"10.1109\/IPDPS.2008.4536348"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Bienia, C., Kumar, S., Singh, J.P., Li, K.: The parsec benchmark suite: characterization and architectural implications. In: PACT (2008)","DOI":"10.1145\/1454115.1454128"},{"key":"37_CR10","unstructured":"Blagodurov, S., Fedorova, A.: User-level scheduling on NUMA multicore systems under Linux. In: Linux Symposium (2011)"},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Booth, J.D., Lane, P.: A NUMA-aware version of an adaptive self-scheduling loop scheduler. ACM TACO (2024)","DOI":"10.1145\/3680549"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Chatzopoulos, G., Guerraoui, R., Harris, T., Trigonakis, V.: Abstracting multi-core topologies with MCTOP. In: EuroSys (2017)","DOI":"10.1145\/3064176.3064194"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Chen, J., Banerjee, S.S., Kalbarczyk, Z.T., Iyer, R.K.: Machine learning for load balancing in the Linux kernel. In: APSys (2020)","DOI":"10.1145\/3409963.3410492"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Chiang, M.L., Tu, S.W., Su, W.L., Lin, C.W.: Enhancing inter-node process migration for load balancing on Linux-based NUMA multicore systems. In: COMPSAC (2018)","DOI":"10.1109\/COMPSAC.2018.10264"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Kirmani, S., Park, J., Raghavan, P.: An embedded sectioning scheme for multiprocessor topology-aware mapping of irregular applications. IJHPCA (2017)","DOI":"10.1177\/1094342015597082"},{"key":"37_CR16","doi-asserted-by":"crossref","unstructured":"Kirmani, S., Raghavan, P.: Scalable parallel graph partitioning. In: SC (2013)","DOI":"10.1145\/2503210.2503280"},{"key":"37_CR17","unstructured":"Lepers, B., Qu\u00e9ma, V., Fedorova, A.: Thread and memory placement on NUMA systems: asymmetry matters. In: ATC (2015)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Lozi, J.P., Lepers, B., Funston, J., Gaud, F., Qu\u00e9ma, V., Fedorova, A.: The Linux scheduler: a decade of wasted cores. In: EuroSys (2016)","DOI":"10.1145\/2901318.2901326"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Ma, T., et al.: Efficient scheduler live update for Linux kernel with modularization. In: ASPLOS (2023)","DOI":"10.1145\/3582016.3582054"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Pang, P., et al.: PAC: preference-aware co-location scheduling on heterogeneous NUMA architectures to improve resource utilization. In: ICS (2023)","DOI":"10.1145\/3577193.3593709"},{"key":"37_CR21","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez\u00a0Barrera, I., Black-Schaffer, D., Casas, M., Moret\u00f3, M., Stupnikova, A., Popov, M.: Modeling and optimizing NUMA effects and prefetching with machine learning. In: SC (2020)","DOI":"10.1145\/3392717.3392765"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Saroliya, U., Arima, E., Liu, D., Schulz, M.: Reinforcement learning-driven co-scheduling and diverse resource assignments on NUMA systems. In: ICCD (2024)","DOI":"10.1109\/ICCD63220.2024.00034"},{"key":"37_CR23","unstructured":"Srikanthan, S., Dwarkadas, S., Shen, K.: Data sharing or resource contention: toward performance transparency on multicore systems. In: ATC (2015)"},{"key":"37_CR24","unstructured":"Srikanthan, S., Dwarkadas, S., Shen, K.: Coherence stalls or latency tolerance: informed CPU scheduling for socket and core sharing. In: ATC (2016)"},{"key":"37_CR25","unstructured":"Xu, D., Ryu, J., Shin, K., Su, P., Li, D.: FlexMem: adaptive page profiling and migration for tiered memory. In: ATC (2024)"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, C., Tao, Y., Yang, R., Tang, H., Xu, J.: Fuxi: a fault-tolerant resource management and job scheduling system at internet scale. In: VLDB (2014)","DOI":"10.14778\/2733004.2733012"}],"container-title":["Lecture Notes in Computer Science","Network and Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10466-3_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T06:59:44Z","timestamp":1763189984000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10466-3_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9783032104656","9783032104663"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10466-3_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Network and Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nha Trang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"npc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.npc-conference.com\/#\/npc2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}