{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:40:02Z","timestamp":1759066802240,"version":"3.44.0"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032063427","type":"print"},{"value":"9783032063434","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"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\/978-3-032-06343-4_7","type":"book-chapter","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:24:01Z","timestamp":1759065841000},"page":"99-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Profile Generation for GPU Targets"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7151-3433","authenticated-orcid":false,"given":"Ethan Luis","family":"McDonough","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9699-5599","authenticated-orcid":false,"given":"Joel E.","family":"Denny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7870-8963","authenticated-orcid":false,"given":"Johannes","family":"Doerfert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"7_CR1","unstructured":"Extend kernel-info to emit PGO-based FLOP count. https:\/\/github.com\/llvm\/llvm-project\/pull\/110586. Accessed 1 June 2025"},{"key":"7_CR2","unstructured":"KernelInfo https:\/\/llvm.org\/docs\/KernelInfo.html. Accessed 1 June 2025"},{"key":"7_CR3","unstructured":"LLVM Instrumentation Profile Format. https:\/\/llvm.org\/docs\/InstrProfileFormat.html. Accessed 23 May 2025"},{"key":"7_CR4","unstructured":"MI300 and MI200 series performance counters and metrics. https:\/\/rocm.docs.amd.com\/en\/latest\/conceptual\/gpu-arch\/mi300-mi200-performance-counters.html Accessed 22 July 2025"},{"key":"7_CR5","unstructured":"[RFC] Fix Loop Transformations to Preserve Block Frequencies. https:\/\/discourse.llvm.org\/t\/rfc-fix-loop-transformations-to-preserve-block-frequencies\/85785. Accessed 1 June 2025"},{"key":"7_CR6","unstructured":"ROCm Compute Profiler. https:\/\/github.com\/ROCm\/rocprofiler-compute.git. Accessed 1 June 2025"},{"key":"7_CR7","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-030-20656-7_13","volume-title":"High Performance Computing","author":"J Doerfert","year":"2019","unstructured":"Doerfert, J., Homerding, B., Finkel, H.: Performance exploration through optimistic static program annotations. In: Weiland, M., Juckeland, G., Trinitis, C., Sadayappan, P. (eds.) High Performance Computing, pp. 247\u2013268. Springer International Publishing, Cham (2019)"},{"key":"7_CR8","unstructured":"Jaiyen, B., Liu, J.: Implementing profile-guided speculative code motion in LLVM. Technical report (2012)"},{"key":"7_CR9","unstructured":"Kumar, A.: Hot cold splitting optimization pass in LLVM. In: 2019 LLVM Developers\u2019 Meeting (2019)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Mehta, N.A., Gayatri, R., Ghadar, Y., Knight, C., Deslippe, J.: Evaluating performance portability of OpenMP for snap on NVIDIA, Intel, and AMD GPUs using the roofline methodology. In: Bhalachandra, S., Wienke, S., Chandrasekaran, S., Juckeland, G. (eds.) Accelerator Programming Using Directives, pp. 3\u201324. Springer International Publishing, Cham (2021)","DOI":"10.1007\/978-3-030-74224-9_1"},{"key":"7_CR11","doi-asserted-by":"publisher","unstructured":"Novillo, D.: Samplepgo - the power of profile guided optimizations without the usability burden. In: 2014 LLVM Compiler Infrastructure in HPC, pp. 22\u201328 (2014). https:\/\/doi.org\/10.1109\/LLVM-HPC.2014.8","DOI":"10.1109\/LLVM-HPC.2014.8"},{"key":"7_CR12","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.anucene.2014.07.048","volume":"82","author":"PK Romano","year":"2015","unstructured":"Romano, P.K., et al.: OpenMC: A state-of-the-art Monte Carlo code for research and development. Ann. Nucl. Energy 82, 90\u201397 (2015). https:\/\/doi.org\/10.1016\/j.anucene.2014.07.048","journal-title":"Ann. Nucl. Energy"},{"key":"7_CR13","unstructured":"Rotem, N., Cummins, C.: Profile guided optimization without profiles: a machine learning approach. CoRR abs\/2112.14679 (2021). https:\/\/arxiv.org\/abs\/2112.14679"},{"key":"7_CR14","doi-asserted-by":"publisher","unstructured":"Shen, D., Song, S.L., Li, A., Liu, X.: Cudaadvisor: LLVM-based runtime profiling for modern GPUs. In: Proceedings of the 2018 International Symposium on Code Generation and Optimization, pp. 214\u2013227. CGO \u201918, Association for Computing Machinery, New York, USA (2018). https:\/\/doi.org\/10.1145\/3168831, https:\/\/doi.org\/10.1145\/3168831","DOI":"10.1145\/3168831"},{"key":"7_CR15","unstructured":"Tramm, J.R.: OpenMC Offloading Benchmarks. https:\/\/github.com\/jtramm\/openmc_offloading_benchmarks. Accessed 1 June 2025"},{"key":"7_CR16","unstructured":"Tramm, J.R.: OpenMC Offloading Builder. https:\/\/github.com\/jtramm\/openmc_offloading_builder. Accessed 1 June 2025"},{"key":"7_CR17","doi-asserted-by":"publisher","unstructured":"Tramm, J.R., Siegel, A.R., Forget, B., Josey, C.: Performance analysis of a reduced data movement algorithm for neutron cross section data in Monte Carlo simulations. In: EASC 2014 - Solving Software Challenges for Exascale. Stockholm (2014). https:\/\/doi.org\/10.1007\/978-3-319-15976-8_3","DOI":"10.1007\/978-3-319-15976-8_3"},{"key":"7_CR18","doi-asserted-by":"publisher","unstructured":"Tramm, J.R., Siegel, A.R., Islam, T., Schulz, M.: XSBench - the development and verification of a performance abstraction for Monte Carlo reactor analysis. The Role of Reactor Physics toward a Sustainable Future (PHYSOR) (2014). https:\/\/doi.org\/10.11484\/jaea-conf-2014-003","DOI":"10.11484\/jaea-conf-2014-003"},{"key":"7_CR19","doi-asserted-by":"publisher","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009). https:\/\/doi.org\/10.1145\/1498765.1498785","DOI":"10.1145\/1498765.1498785"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Balancing Productivity and Performance Portability"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06343-4_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:24:03Z","timestamp":1759065843000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06343-4_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"ISBN":["9783032063427","9783032063434"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06343-4_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"29 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Charlotte, NC","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 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":"iwomp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iwomp.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}