{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:12:51Z","timestamp":1761808371253,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030507428"},{"type":"electronic","value":"9783030507435"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-50743-5_22","type":"book-chapter","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T19:03:45Z","timestamp":1592247825000},"page":"434-452","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Timemory: Modular Performance Analysis for HPC"],"prefix":"10.1007","author":[{"given":"Jonathan R.","family":"Madsen","sequence":"first","affiliation":[]},{"given":"Muaaz G.","family":"Awan","sequence":"additional","affiliation":[]},{"given":"Hugo","family":"Brunie","sequence":"additional","affiliation":[]},{"given":"Jack","family":"Deslippe","sequence":"additional","affiliation":[]},{"given":"Rahul","family":"Gayatri","sequence":"additional","affiliation":[]},{"given":"Leonid","family":"Oliker","sequence":"additional","affiliation":[]},{"given":"Yunsong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Charlene","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Samuel","family":"Williams","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,6,15]]},"reference":[{"issue":"6","key":"22_CR1","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1002\/cpe.v22:6","volume":"22","author":"L Adhianto","year":"2010","unstructured":"Adhianto, L., et al.: HPCToolkit: tools for performance analysis of optimized parallel programs. Concurr. Comput.: Pract. Exp. 22(6), 685\u2013701 (2010). https:\/\/doi.org\/10.1002\/cpe.v22:6. http:\/\/hpctoolkit.org","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"22_CR2","doi-asserted-by":"publisher","unstructured":"Agostinelli, S., et al.: Geant4 simulation toolkit, 506(3), 250\u2013303 (2003). https:\/\/doi.org\/10.1016\/S0168-9002(03)01368-8. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0168900203013688","DOI":"10.1016\/S0168-9002(03)01368-8"},{"key":"22_CR3","unstructured":"Awan, M.G.: GPU accelerated smith-waterman for performing batch alignments (GPU-BSW) (2019). https:\/\/github.com\/m-gul\/GPU-BSW"},{"key":"22_CR4","doi-asserted-by":"publisher","unstructured":"Bernat, A.R., et al.: Anywhere, any-time binary instrumentation. In: PASTE 2011, pp. 9\u201316. ACM, New York (2011). https:\/\/doi.org\/10.1145\/2024569.2024572","DOI":"10.1145\/2024569.2024572"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Boehme, D., et al.: The case for a common instrumentation interface for HPC codes. In: Workshop on Programming and Performance Visualization Tools (ProTools 19) (October 2019)","DOI":"10.1109\/ProTools49597.2019.00010"},{"key":"22_CR6","unstructured":"Boehme, D., et al.: Caliper: performance introspection for HPC software stacks. In: SC 2016, pp. 47:1\u201347:11. IEEE Computer Society (November 2016). http:\/\/dl.acm.org\/citation.cfm?id=3014904.3014967. lLNL-CONF-699263"},{"issue":"12","key":"22_CR7","doi-asserted-by":"publisher","first-page":"3202","DOI":"10.1016\/j.jpdc.2014.07.003","volume":"74","author":"H Carter Edwards","year":"2014","unstructured":"Carter Edwards, H., et al.: Kokkos. J. Parallel Distrib. Comput. 74(12), 3202\u20133216 (2014). https:\/\/doi.org\/10.1016\/j.jpdc.2014.07.003","journal-title":"J. Parallel Distrib. Comput."},{"key":"22_CR8","unstructured":"Corp., I.: Intel VTune profiler user guide - instrumenting your application (2019)"},{"key":"22_CR9","unstructured":"Corp., N.: CUPTI documentation (2019). https:\/\/docs.nvidia.com\/cupti\/Cupti\/index.html"},{"key":"22_CR10","doi-asserted-by":"publisher","unstructured":"Di Franco, A., et al.: A comprehensive study of real-world numerical bug characteristics, pp. 509\u2013519 (October 2017). https:\/\/doi.org\/10.1109\/ASE.2017.8115662","DOI":"10.1109\/ASE.2017.8115662"},{"key":"22_CR11","unstructured":"Dimakopoulou, M., et al.: Reliable and efficient performance monitoring in Linux. In: SC 2016, pp. 34:1\u201334:13. IEEE Press, Piscataway (2016). http:\/\/dl.acm.org\/citation.cfm?id=3014904.3014950"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Ding, N., et al.: An instruction roofline model for GPUs. In: Performance Modeling, Benchmarking and Simulation (PMBS19) (2019)","DOI":"10.1109\/PMBS49563.2019.00007"},{"key":"22_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/978-3-642-40698-0_13","volume-title":"OpenMP in the Era of Low Power Devices and Accelerators","author":"AE Eichenberger","year":"2013","unstructured":"Eichenberger, A.E., et al.: OMPT: an OpenMP tools application programming interface for performance analysis. In: Rendell, A.P., Chapman, B.M., M\u00fcller, M.S. (eds.) IWOMP 2013. LNCS, vol. 8122, pp. 171\u2013185. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40698-0_13"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Finkel, H., et al.: ClangJIT: enhancing C++ with just-in-time compilation. CoRR (2019). http:\/\/arxiv.org\/abs\/1904.08555","DOI":"10.1109\/P3HPC49587.2019.00013"},{"issue":"1","key":"22_CR15","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1145\/103162.103163","volume":"23","author":"D Goldberg","year":"1991","unstructured":"Goldberg, D.: What every computer scientist should know about floating-point arithmetic. ACM Comput. Surv. 23(1), 5\u201348 (1991). https:\/\/doi.org\/10.1145\/103162.103163. http:\/\/portal.acm.org\/citation.cfm?doid=103162.103163","journal-title":"ACM Comput. Surv."},{"key":"22_CR16","unstructured":"Kahan, W.: Personal website (2008). http:\/\/people.eecs.berkeley.edu\/~wkahan\/. Accessed 16 Dec 2019"},{"key":"22_CR17","doi-asserted-by":"publisher","unstructured":"Kn\u00fcpfer, A., et al.: Score-p: a joint performance measurement run-time infrastructure for periscope, scalasca, tau, and vampir. In: Tools for High Performance Computing 2011, pp. 79\u201391. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31476-6_7","DOI":"10.1007\/978-3-642-31476-6_7"},{"key":"22_CR18","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, CGO 2004, pp. 75\u201386. IEEE Computer Society, Washington (2004). http:\/\/dl.acm.org\/citation.cfm?id=977395.977673"},{"key":"22_CR19","unstructured":"LLVM: LLVM (2019). https:\/\/llvm.org\/"},{"key":"22_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-3-319-17248-4_7","volume-title":"High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation","author":"YJ Lo","year":"2015","unstructured":"Lo, Y.J., et al.: Roofline model toolkit: a practical tool for architectural and program analysis. In: Jarvis, S.A., Wright, S.A., Hammond, S.D. (eds.) PMBS 2014. LNCS, vol. 8966, pp. 129\u2013148. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-17248-4_7"},{"key":"22_CR21","doi-asserted-by":"publisher","unstructured":"Markidis, S., et al.: NVIDIA tensor core programmability, performance & precision, pp. 522\u2013531 (May 2018). https:\/\/doi.org\/10.1109\/IPDPSW.2018.00091. arXiv: 1803.04014","DOI":"10.1109\/IPDPSW.2018.00091"},{"key":"22_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/BFb0031632","volume-title":"High-Performance Computing and Networking","author":"S Mintchev","year":"1997","unstructured":"Mintchev, S., Getov, V.: PMPI: high-level message passing in Fortran77 and C. In: Hertzberger, B., Sloot, P. (eds.) HPCN-Europe 1997. LNCS, vol. 1225, pp. 601\u2013614. Springer, Heidelberg (1997). https:\/\/doi.org\/10.1007\/BFb0031632"},{"key":"22_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-030-17872-7_11","volume-title":"Programming and Performance Visualization Tools","author":"D Poliakoff","year":"2019","unstructured":"Poliakoff, D., LeGendre, M.: Gotcha: an function-wrapping interface for HPC tools. In: Bhatele, A., Boehme, D., Levine, J.A., Malony, A.D., Schulz, M. (eds.) ESPT\/VPA 2017-2018. LNCS, vol. 11027, pp. 185\u2013197. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-17872-7_11"},{"key":"22_CR24","doi-asserted-by":"publisher","unstructured":"Ramesh, S., et al.: MPI performance engineering with the MPI tool interface: The integration of mvapich and tau, EuroMPI 2017, pp. 16:1\u201316:11. ACM, New York (2017). https:\/\/doi.org\/10.1145\/3127024.3127036","DOI":"10.1145\/3127024.3127036"},{"key":"22_CR25","doi-asserted-by":"publisher","unstructured":"Rubio-Gonz\u00e1lez, C., et al.: Precimonious: tuning assistant for floating-point precision, pp. 1\u201312 (November 2013). https:\/\/doi.org\/10.1145\/2503210.2503296","DOI":"10.1145\/2503210.2503296"},{"issue":"2","key":"22_CR26","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1177\/1094342006064482","volume":"20","author":"SS Shende","year":"2006","unstructured":"Shende, S.S., Malony, A.D.: The tau parallel performance system. Int. J. High Perform. Comput. Appl. 20(2), 287\u2013311 (2006). https:\/\/doi.org\/10.1177\/1094342006064482","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"22_CR27","doi-asserted-by":"publisher","unstructured":"Terpstra, D., et al.: Collecting performance data with PAPI-C. In: M\u00fcller, M., Resch, M., Schulz, A., Nagel, W. (eds.)Tools for High Performance Computing 2009, pp. 157\u2013173. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-11261-4_11","DOI":"10.1007\/978-3-642-11261-4_11"},{"key":"22_CR28","doi-asserted-by":"publisher","unstructured":"Treibig, J., et al.: LIKWID: a lightweight performance-oriented tool suite for x86 multicore environments. In: ICPPW 2010, pp. 207\u2013216. IEEE Computer Society, Washington (2010). https:\/\/doi.org\/10.1109\/ICPPW.2010.38","DOI":"10.1109\/ICPPW.2010.38"},{"issue":"4","key":"22_CR29","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., et al.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009). https:\/\/doi.org\/10.1145\/1498765.1498785","journal-title":"Commun. ACM"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-50743-5_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:04:19Z","timestamp":1702929859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-50743-5_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030507428","9783030507435"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-50743-5_22","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":"15 June 2020","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 am Main","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 June 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2020","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 (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"87","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":"27","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":"0","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":"31% - 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":"3.73","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":"4.33","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}