{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T19:47:24Z","timestamp":1765828044596,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T00:00:00Z","timestamp":1619481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"German Federal Ministry of Education and Research (BMBF)","award":["05M20ZBM"],"award-info":[{"award-number":["05M20ZBM"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,4,27]]},"DOI":"10.1145\/3456669.3456698","type":"proceedings-article","created":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T15:22:31Z","timestamp":1619536951000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Performance Evaluation and Improvements of the PoCL Open-Source OpenCL Implementation on Intel CPUs"],"prefix":"10.1145","author":[{"given":"Tobias","family":"Baumann","sequence":"first","affiliation":[{"name":"Zuse Institute Berlin (ZIB), DE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Noack","sequence":"additional","affiliation":[{"name":"Zuse Institute Berlin (ZIB), DE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Steinke","sequence":"additional","affiliation":[{"name":"Zuse Institute Berlin (ZIB), DE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. libclc website. https:\/\/libclc.llvm.org\/ Accessed: 2021-03-18.  [n.d.]. libclc website. https:\/\/libclc.llvm.org\/ Accessed: 2021-03-18."},{"key":"e_1_3_2_1_2_1","unstructured":"[n.d.]. TBB Partitioner Summary. https:\/\/www.threadingbuildingblocks.org\/docs\/help\/tbb_userguide\/Partitioner_Summary.html Accessed: 2021-03-18.  [n.d.]. TBB Partitioner Summary. https:\/\/www.threadingbuildingblocks.org\/docs\/help\/tbb_userguide\/Partitioner_Summary.html Accessed: 2021-03-18."},{"key":"e_1_3_2_1_3_1","unstructured":"[n.d.]. Vectorization Plan. https:\/\/llvm.org\/docs\/Proposals\/VectorizationPlan.html Accessed: 2021-01-13.  [n.d.]. Vectorization Plan. https:\/\/llvm.org\/docs\/Proposals\/VectorizationPlan.html Accessed: 2021-01-13."},{"key":"e_1_3_2_1_4_1","unstructured":"2020. TOP500 November 2020. https:\/\/top500.org\/lists\/top500\/2020\/11\/Accessed: 2021-03-18.  2020. TOP500 November 2020. https:\/\/top500.org\/lists\/top500\/2020\/11\/Accessed: 2021-03-18."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3199610.3199614"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3148173.3148185"},{"key":"e_1_3_2_1_7_1","unstructured":"Graham Holland. 2019. Abstracting OpenCL for Multi-Application Workloads on CPU-FPGA Clusters.  Graham Holland. 2019. Abstracting OpenCL for Multi-Application Workloads on CPU-FPGA Clusters."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-014-0320-y"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-018-1416-1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Ralf Karrenberg and Sebastian Hack. 2012. Improving Performance of OpenCL on CPUs. In Compiler Construction. http:\/\/www.cdl.uni-saarland.de\/papers\/karrenberg_opencl.pdf  Ralf Karrenberg and Sebastian Hack. 2012. Improving Performance of OpenCL on CPUs. In Compiler Construction. http:\/\/www.cdl.uni-saarland.de\/papers\/karrenberg_opencl.pdf","DOI":"10.1007\/978-3-642-28652-0_1"},{"key":"e_1_3_2_1_11_1","unstructured":"Khronos OpenCL Working Group. 2020. The OpenCL Specification. https:\/\/www.khronos.org\/registry\/OpenCL\/specs\/3.0-unified\/pdf\/OpenCL_API.pdf  Khronos OpenCL Working Group. 2020. The OpenCL Specification. https:\/\/www.khronos.org\/registry\/OpenCL\/specs\/3.0-unified\/pdf\/OpenCL_API.pdf"},{"key":"e_1_3_2_1_12_1","volume-title":"OpenCL performance evaluation on modern multicore CPUs. Scientific Programming 2015","author":"Lee Joo\u00a0Hwan","year":"2015","unstructured":"Joo\u00a0Hwan Lee , Nimit Nigania , Hyesoon Kim , Kaushik Patel , and Hyojong Kim . 2015. OpenCL performance evaluation on modern multicore CPUs. Scientific Programming 2015 ( 2015 ). Joo\u00a0Hwan Lee, Nimit Nigania, Hyesoon Kim, Kaushik Patel, and Hyojong Kim. 2015. OpenCL performance evaluation on modern multicore CPUs. Scientific Programming 2015 (2015)."},{"key":"e_1_3_2_1_13_1","volume-title":"Performance Obstacles for Threading: How do they affect OpenMP code? (January","author":"Lindberg Paul","year":"2009","unstructured":"Paul Lindberg . 2009. Performance Obstacles for Threading: How do they affect OpenMP code? (January 2009 ). https:\/\/web.archive.org\/web\/20131126073803\/https:\/\/software.intel.com\/en-us\/articles\/performance-obstacles-for-threading-how-do-they-affect-openmp-code Accessed : 2021-03-18. Paul Lindberg. 2009. Performance Obstacles for Threading: How do they affect OpenMP code? (January 2009). https:\/\/web.archive.org\/web\/20131126073803\/https:\/\/software.intel.com\/en-us\/articles\/performance-obstacles-for-threading-how-do-they-affect-openmp-code Accessed: 2021-03-18."},{"key":"e_1_3_2_1_14_1","unstructured":"Matthias Noack. 2015-2021. hexciton_benchmark source code on Github. https:\/\/github.com\/noma\/hexciton_benchmark  Matthias Noack. 2015-2021. hexciton_benchmark source code on Github. https:\/\/github.com\/noma\/hexciton_benchmark"},{"key":"e_1_3_2_1_15_1","unstructured":"Matthias Noack. 2016-2021. op_benchmark source code on Github. https:\/\/github.com\/noma\/op_benchmark  Matthias Noack. 2016-2021. op_benchmark source code on Github. https:\/\/github.com\/noma\/op_benchmark"},{"key":"e_1_3_2_1_16_1","unstructured":"Matthias Noack. 2017-2019. OpenCL Helper library on Github. https:\/\/github.com\/noma\/ocl  Matthias Noack. 2017-2019. OpenCL Helper library on Github. https:\/\/github.com\/noma\/ocl"},{"key":"e_1_3_2_1_17_1","volume-title":"DM-HEOM: A Portable and Scalable Solver-Framework for the Hierarchical Equations of Motion. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). 947\u2013956","author":"Noack Matthias","year":"2018","unstructured":"Matthias Noack , Alexander Reinefeld , Tobias Kramer , and Thomas Steinke . 2018 . DM-HEOM: A Portable and Scalable Solver-Framework for the Hierarchical Equations of Motion. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). 947\u2013956 . https:\/\/doi.org\/10.1109\/IPDPSW.2018.00149 Matthias Noack, Alexander Reinefeld, Tobias Kramer, and Thomas Steinke. 2018. DM-HEOM: A Portable and Scalable Solver-Framework for the Hierarchical Equations of Motion. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). 947\u2013956. https:\/\/doi.org\/10.1109\/IPDPSW.2018.00149"},{"volume-title":"OpenCL: There and Back Again","author":"Noack Matthias","key":"e_1_3_2_1_18_1","unstructured":"Matthias Noack , Florian Wende , and Klaus-Dieter Oertel . 2015. OpenCL: There and Back Again . In High Performance Parallelism Pearls, James Reinders and Jim Jeffers (Eds.). Vol.\u00a02. Morgan Kaufmann , Boston, 355\u2013378. https:\/\/doi.org\/10.1016\/B978-0-12-803819-2.00001-X Matthias Noack, Florian Wende, and Klaus-Dieter Oertel. 2015. OpenCL: There and Back Again. In High Performance Parallelism Pearls, James Reinders and Jim Jeffers (Eds.). Vol.\u00a02. Morgan Kaufmann, Boston, 355\u2013378. https:\/\/doi.org\/10.1016\/B978-0-12-803819-2.00001-X"},{"volume-title":"KART \u2013 A Runtime Compilation Library for Improving HPC Application Performance","author":"Noack Matthias","key":"e_1_3_2_1_19_1","unstructured":"Matthias Noack , Florian Wende , Georg Zitzlsberger , Michael Klemm , and Thomas Steinke . 2017. KART \u2013 A Runtime Compilation Library for Improving HPC Application Performance . In High Performance Computing, Julian\u00a0M. Kunkel, Rio Yokota, Michela Taufer, and John Shalf (Eds.). Springer International Publishing , Cham , 389\u2013403. Matthias Noack, Florian Wende, Georg Zitzlsberger, Michael Klemm, and Thomas Steinke. 2017. KART \u2013 A Runtime Compilation Library for Improving HPC Application Performance. In High Performance Computing, Julian\u00a0M. Kunkel, Rio Yokota, Michela Taufer, and John Shalf (Eds.). Springer International Publishing, Cham, 389\u2013403."},{"key":"e_1_3_2_1_20_1","unstructured":"OpenMP Architecture Review Board. 2018. OpenMP API Specification. https:\/\/www.openmp.org\/spec-html\/5.0\/openmp.html  OpenMP Architecture Review Board. 2018. OpenMP API Specification. https:\/\/www.openmp.org\/spec-html\/5.0\/openmp.html"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MECO49872.2020.9134270"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2960333"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3140582.3081040"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337801.3337819"},{"key":"e_1_3_2_1_25_1","unstructured":"Alexander Veselov. 2016-2021. raytracing_benchmark source code on Github. https:\/\/github.com\/new2f7\/RayTracing  Alexander Veselov. 2016-2021. raytracing_benchmark source code on Github. https:\/\/github.com\/new2f7\/RayTracing"},{"volume-title":"C++ Parallel Programming with Threading Building Blocks","author":"Voss Michael","key":"e_1_3_2_1_26_1","unstructured":"Michael Voss , Rafael Asenjo , and James Reinders . 2019. Pro TBB : C++ Parallel Programming with Threading Building Blocks . Springer Nature . https:\/\/doi.org\/10.1007\/978-1-4842-4398-5 Michael Voss, Rafael Asenjo, and James Reinders. 2019. Pro TBB : C++ Parallel Programming with Threading Building Blocks. Springer Nature. https:\/\/doi.org\/10.1007\/978-1-4842-4398-5"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3203217.3203244"}],"event":{"name":"IWOCL'21: International Workshop on OpenCL","acronym":"IWOCL'21","location":"Munich Germany"},"container-title":["International Workshop on OpenCL"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3456669.3456698","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3456669.3456698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:46:55Z","timestamp":1750193215000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3456669.3456698"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,27]]},"references-count":27,"alternative-id":["10.1145\/3456669.3456698","10.1145\/3456669"],"URL":"https:\/\/doi.org\/10.1145\/3456669.3456698","relation":{},"subject":[],"published":{"date-parts":[[2021,4,27]]},"assertion":[{"value":"2021-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}