{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T03:49:12Z","timestamp":1782964152971,"version":"3.54.5"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030206550","type":"print"},{"value":"9783030206567","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","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":[[2019]]},"DOI":"10.1007\/978-3-030-20656-7_12","type":"book-chapter","created":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T23:02:40Z","timestamp":1559689360000},"page":"227-246","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["GPUMixer: Performance-Driven Floating-Point Tuning for GPU Scientific Applications"],"prefix":"10.1007","author":[{"given":"Ignacio","family":"Laguna","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul C.","family":"Wood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ranvijay","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saurabh","family":"Bagchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,5,17]]},"reference":[{"key":"12_CR1","unstructured":"CoMD-CUDA (2017). \n                      https:\/\/github.com\/NVIDIA\/CoMD-CUDA"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: IEEE International Symposium on Workload Characterization (IISWC 2009), pp. 44\u201354. IEEE (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Chiang, W.F., Baranowski, M., Briggs, I., Solovyev, A., Gopalakrishnan, G., Rakamari\u0107, Z.: Rigorous floating-point mixed-precision tuning. In: 44th ACM SIGPLAN Symposium on Principles of Programming Languages, POPL 2017. Association for Computing Machinery (2017)","DOI":"10.1145\/3009837.3009846"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Chiang, W.-F., Gopalakrishnan, G., Rakamaric, Z., Solovyev, A.: Efficient search for inputs causing high floating-point errors. In: Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2014, pp. 43\u201352. ACM, New York (2014)","DOI":"10.1145\/2692916.2555265"},{"key":"12_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-319-19458-5_3","volume-title":"Formal Methods for Industrial Critical Systems","author":"N Damouche","year":"2015","unstructured":"Damouche, N., Martel, M., Chapoutot, A.: Intra-procedural optimization of the numerical accuracy of programs. In: N\u00fa\u00f1ez, M., G\u00fcdemann, M. (eds.) FMICS 2015. LNCS, vol. 9128, pp. 31\u201346. Springer, Cham (2015). \n                      https:\/\/doi.org\/10.1007\/978-3-319-19458-5_3"},{"issue":"2","key":"12_CR6","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1145\/3014426","volume":"39","author":"E Darulova","year":"2017","unstructured":"Darulova, E., Kuncak, V.: Towards a compiler for reals. ACM Trans. Program. Lang. Syst. (TOPLAS) 39(2), 8 (2017)","journal-title":"ACM Trans. Program. Lang. Syst. (TOPLAS)"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Guo, H., Rubio-Gonz\u00e1lez, C.: Exploiting community structure for floating-point precision tuning. In: Proceedings of the 27th ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 333\u2013343. ACM (2018)","DOI":"10.1145\/3213846.3213862"},{"key":"12_CR8","unstructured":"Harris, M.: Mini-nbody: a simple N-body code (2014). \n                      https:\/\/github.com\/harrism\/mini-nbody"},{"key":"12_CR9","unstructured":"Iskhodzhanov, T., Potapenko, A., Samsonov, A., Serebryany, K., Stepanov, E., Vyukov, D.: ThreadSanitizer, MemorySanitizer, 8 November 2012. \n                      https:\/\/urldefense.proofpoint.com\/v2\/url?u=http-3A__www.llvm.org_devmtg_2012-2D11_Serebryany-5FTSan-2DMSan.pdf&d=DwIF-g&c=vh6FgFnduejNhPPD0fl_yRaSfZy8CWbWnIf4XJhSqx8&r=UyK1_569d50MjVlUSODJYRW2epEY0RveVNq0YCmePcDz4DQHW-CkWcttrwneZ0md&m=QbB1B0a55LgDuuwoFrE3U3GhMpMGOKghlpBLKQdmd1A&s=XadD1efiG2KOXnZcaadrIMuS10vDECEVJu__wnFtYQU&e="},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Karlin, I., Keasler, J., Neely, R.: Lulesh 2.0 updates and changes. Technical report LLNL-TR-641973, August 2013","DOI":"10.2172\/1090032"},{"key":"12_CR11","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1177\/1094342016652462","volume":"32","author":"MO Lam","year":"2016","unstructured":"Lam, M.O., Hollingsworth, J.K.: Fine-grained floating-point precision analysis. Int. J. High Perform. Comput. Appl. 32, 231 (2016). 1094342016652462","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Lam, M.O., Hollingsworth, J.K., de Supinski, B.R., LeGendre, M.P.: Automatically adapting programs for mixed-precision floating-point computation. In: Proceedings of the 27th International ACM Conference on Supercomputing, pp. 369\u2013378. ACM (2013)","DOI":"10.1145\/2464996.2465018"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Lam, M.O., Rountree, B.L.: Floating-point shadow value analysis. In: Proceedings of the 5th Workshop on Extreme-Scale Programming Tools, pp. 18\u201325. IEEE Press (2016)","DOI":"10.1109\/ESPT.2016.007"},{"key":"12_CR14","unstructured":"Lattner, C., Adve, V.: LLVM: a compilation framework for lifelong program analysis & transformation. In: Proceedings of the International Symposium on Code Generation and Optimization: Feedback-Directed and Runtime Optimization, p. 75. IEEE Computer Society (2004)"},{"key":"12_CR15","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1145\/1064978.1065034","volume":"40","author":"C-K Luk","year":"2005","unstructured":"Luk, C.-K., et al.: Pin: building customized program analysis tools with dynamic instrumentation. ACM SIGPLAN Not. 40, 190\u2013200 (2005)","journal-title":"ACM SIGPLAN Not."},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Menon, H., et al.: ADAPT: algorithmic differentiation applied to floating-point precision tuning. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, p. 48. IEEE Press (2018)","DOI":"10.1109\/SC.2018.00051"},{"key":"12_CR17","unstructured":"NDIDIA. CUDA ToolKit Documentation - NVVM IR Specification 1.5 (2018). \n                      https:\/\/docs.nvidia.com\/cuda\/nvvm-ir-spec\/index.html"},{"key":"12_CR18","first-page":"677","volume-title":"GPU Gems 3","author":"H Nguyen","year":"2007","unstructured":"Nguyen, H.: GPU Gems 3, pp. 677\u2013694. Addison-Wesley Professional, Reading (2007). chapter 31"},{"key":"12_CR19","unstructured":"Nvidia. Nvidia Tesla P100 GPU. Pascal Architecture White Paper (2016)"},{"key":"12_CR20","unstructured":"Nvidia. CUDA C Programming Guide, v9.0 (2018). \n                      http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Paganelli, G., Ahrendt, W.: Verifying (in-) stability in floating-point programs by increasing precision, using SMT solving. In: 2013 15th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC), pp. 209\u2013216. IEEE (2013)","DOI":"10.1109\/SYNASC.2013.35"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Rubio-Gonz\u00e1lez, C., et al.: Floating-point precision tuning using blame analysis. In: Proceedings of the 38th International Conference on Software Engineering, ICSE 2016, pp. 1074\u20131085. ACM, New York (2016)","DOI":"10.1145\/2884781.2884850"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Rubio-Gonz\u00e1lez, C., et al.: Precimonious: tuning assistant for floating-point precision. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, p. 27. ACM (2013)","DOI":"10.1145\/2503210.2503296"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-20656-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T23:18:13Z","timestamp":1559690293000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-20656-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030206550","9783030206567"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-20656-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"17 May 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Frankfurt","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"16 June 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 June 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"70","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"17","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"24% - 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"}},{"value":"4-5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"n\/a","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}