{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:46:38Z","timestamp":1743075998869,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031695827"},{"type":"electronic","value":"9783031695834"}],"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\/978-3-031-69583-4_16","type":"book-chapter","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:02:05Z","timestamp":1724612525000},"page":"225-239","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GPU Cache System for\u00a0COMPSs: A Task-Based Distributed Computing Framework"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8848-9436","authenticated-orcid":false,"given":"Cristian C\u0103t\u0103lin","family":"Tatu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6401-6229","authenticated-orcid":false,"given":"Javier","family":"Conejero","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5634-509X","authenticated-orcid":false,"given":"Fernando","family":"V\u00e1zquez-Novoa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2941-5499","authenticated-orcid":false,"given":"Rosa M.","family":"Badia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Cid-Fuentes, J.\u00c1., Sol\u00e0, S., \u00c1lvarez, P., Castro-Ginard, A., Badia, R.M.: dislib: large scale high performance machine learning in python. In: 2019 15th International Conference on eScience (eScience), pp. 96\u2013105. IEEE (2019)","DOI":"10.1109\/eScience.2019.00018"},{"key":"16_CR2","unstructured":"Extrae\u2014BSC-Tools: Web page. https:\/\/tools.bsc.es\/extrae. Access 22 Mar 2024"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"Hong, S., Choi, W., Jeong, W.K.: GPU in-memory processing using spark for iterative computation. In: 2017 17th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), pp. 31\u201341 (2017). https:\/\/doi.org\/10.1109\/CCGRID.2017.41","DOI":"10.1109\/CCGRID.2017.41"},{"key":"16_CR4","unstructured":"NVIDIA, Vingelmann, P., Fitzek, F.H.: Cuda, release: 10.2.89 (2020). https:\/\/developer.nvidia.com\/cuda-toolkit"},{"key":"16_CR5","unstructured":"Okuta, R., Unno, Y., Nishino, D., Hido, S., Loomis, C.: CuPy: a NumPy-compatible library for NVIDIA GPU calculations. In: Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS) (2017). http:\/\/learningsys.org\/nips17\/assets\/papers\/paper_16.pdf"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Pandey, S., Kamath, A.K., Basu, A.: GPM: leveraging persistent memory from a GPU. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2022, pp. 142\u2013156. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3503222.3507758","DOI":"10.1145\/3503222.3507758"},{"key":"16_CR7","unstructured":"Paraver: a flexible performance analysis tool\u2014BSC-Tools: Web page. https:\/\/tools.bsc.es\/paraver. Accessed 22 Mar 2024"},{"key":"16_CR8","unstructured":"Pillet, V., Labarta, J., Cortes, T., Girona, S.: Paraver: a tool to visualize and analyze parallel code. In: Proceedings of WoTUG-18: Transputer and Occam Developments, vol.\u00a044, pp. 17\u201331. Citeseer (1995)"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Qureshi, Z., et al.: GPU-initiated on-demand high-throughput storage access in the bam system architecture. In: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2023, vol. 2, pp. 325\u2013339. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3575693.3575748","DOI":"10.1145\/3575693.3575748"},{"key":"16_CR10","doi-asserted-by":"publisher","unstructured":"Tatu, C.: Compss GPU cache DNN distributed training (2024). https:\/\/doi.org\/10.48546\/WORKFLOWHUB.WORKFLOW.802.1","DOI":"10.48546\/WORKFLOWHUB.WORKFLOW.802.1"},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Tatu, C.: Compss GPU cache k-means (2024). https:\/\/doi.org\/10.48546\/WORKFLOWHUB.WORKFLOW.800.1","DOI":"10.48546\/WORKFLOWHUB.WORKFLOW.800.1"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Tatu, C.: Compss GPU cache matrix multiplication (2024). https:\/\/doi.org\/10.48546\/WORKFLOWHUB.WORKFLOW.798.1","DOI":"10.48546\/WORKFLOWHUB.WORKFLOW.798.1"},{"key":"16_CR13","doi-asserted-by":"publisher","unstructured":"Tatu, C.: Compss GPU DNN distributed training (2024). https:\/\/doi.org\/10.48546\/WORKFLOWHUB.WORKFLOW.801.1","DOI":"10.48546\/WORKFLOWHUB.WORKFLOW.801.1"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Tatu, C.: Compss GPU k-means (2024). https:\/\/doi.org\/10.48546\/WORKFLOWHUB.WORKFLOW.799.1","DOI":"10.48546\/WORKFLOWHUB.WORKFLOW.799.1"},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Tatu, C.: Compss GPU matrix multiplication (2024). https:\/\/doi.org\/10.48546\/WORKFLOWHUB.WORKFLOW.797.1","DOI":"10.48546\/WORKFLOWHUB.WORKFLOW.797.1"},{"issue":"1","key":"16_CR16","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1177\/1094342015594678","volume":"31","author":"E Tejedor","year":"2017","unstructured":"Tejedor, E., et al.: PyCOMPSs: parallel computational workflows in Python. Int, J. High Perform. Comput. Appl. 31(1), 66\u201382 (2017)","journal-title":"Int, J. High Perform. Comput. Appl."},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Yuan, Y., Salmi, M.F., Huai, Y., Wang, K., Lee, R., Zhang, X.: Spark-GPU: an accelerated in-memory data processing engine on clusters. In: 2016 IEEE International Conference on Big Data (Big Data), pp. 273\u2013283 (2016). https:\/\/doi.org\/10.1109\/BigData.2016.7840613","DOI":"10.1109\/BigData.2016.7840613"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2024: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-69583-4_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T06:05:36Z","timestamp":1732687536000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-69583-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031695827","9783031695834"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-69583-4_16","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":"26 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}