{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:01:38Z","timestamp":1750309298597,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3659914.3659921","type":"proceedings-article","created":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T14:13:51Z","timestamp":1715782431000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Using Read-After-Read Dependencies to Control Task-Granularity"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1746-2256","authenticated-orcid":false,"given":"Andres","family":"Gartmann","sequence":"first","affiliation":[{"name":"mynatix ag, Basel, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1750-0817","authenticated-orcid":false,"given":"Mathias","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"meteoblue ag, Basel, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2024,6,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Control flow analysis. SIGPLAN Not., 5, 7, (July","author":"Allen Frances E.","year":"1970","unstructured":"Frances E. Allen. 1970. Control flow analysis. SIGPLAN Not., 5, 7, (July 1970), 1--19."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/29873.29875"},{"volume-title":"Performance factors for superscalar processors. Computer Systems Laboratory","author":"Bennett James E","key":"e_1_3_2_1_3_1","unstructured":"James E Bennett and Michael J Flynn. 1995. Performance factors for superscalar processors. Computer Systems Laboratory, Stanford University."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259028"},{"key":"e_1_3_2_1_5_1","unstructured":"Rohit Chandra Leo Dagum David Kohr Ramesh Menon Dror Maydan and Jeff McDonald. 2001. Parallel programming in OpenMP. Morgan Kaufmann."},{"volume-title":"12th Media Services","author":"Community Gcc Developer","key":"e_1_3_2_1_6_1","unstructured":"Gcc Developer Community. 2018. GCC 8.0 GNU Compiler Collection Internals. Richard M. Stallman, (Ed.) 12th Media Services."},{"key":"e_1_3_2_1_7_1","volume-title":"Retrieved","author":"Intel Corporation","year":"2023","unstructured":"Intel Corporation. 2023. Oneapi threading building blocks (onetbb). Retrieved Nov. 25, 2023 from https:\/\/oneapi-src.github.io\/oneTBB\/."},{"volume-title":"Retrieved","year":"2023","key":"e_1_3_2_1_8_1","unstructured":"cppreference.com. 2023. Date and time utilities. Retrieved Nov. 25, 2023 from https:\/\/en.cppreference.com\/w\/cpp\/chrono."},{"key":"e_1_3_2_1_9_1","volume-title":"Linear Programming and Extensions","author":"Dantzig George B.","year":"1963","unstructured":"George B. Dantzig. 1963. Linear Programming and Extensions. United States Air Force Project RAND. The RAND Corporation, (Aug. 1963). http:\/\/www.rand.org\/pubs\/reports\/R366.html."},{"key":"e_1_3_2_1_10_1","volume-title":"Instructional level parallelism. (July","author":"Roy Taposh Dutta","year":"2015","unstructured":"Taposh Dutta Roy. 2015. Instructional level parallelism. (July 2015)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1972.5009071"},{"key":"e_1_3_2_1_12_1","volume-title":"Practical dependence testing. SIGPLAN Not., 26, 6, (May","author":"Goff Gina","year":"1991","unstructured":"Gina Goff, Ken Kennedy, and Chau-Wen Tseng. 1991. Practical dependence testing. SIGPLAN Not., 26, 6, (May 1991), 15--29."},{"key":"e_1_3_2_1_13_1","volume-title":"Jan Karel Lenstra, and AHG Rinnooy Kan.","author":"Graham Ronald Lewis","year":"1979","unstructured":"Ronald Lewis Graham, Eugene Leighton Lawler, Jan Karel Lenstra, and AHG Rinnooy Kan. 1979. Optimization and approximation in deterministic sequencing and scheduling: a survey. In Annals of discrete mathematics. Vol. 5. Elsevier, 287--326."},{"volume-title":"Proceedings of the International Symposium on Code Generation and Optimization (CGO '05)","author":"Guo Bolei","key":"e_1_3_2_1_14_1","unstructured":"Bolei Guo, Matthew J. Bridges, Spyridon Triantafyllis, Guilherme Ottoni, Easwaran Raman, and David I. August. 2005. Practical and accurate low-level pointer analysis. In Proceedings of the International Symposium on Code Generation and Optimization (CGO '05). IEEE Computer Society, USA, 291--302. isbn: 076952298X."},{"key":"e_1_3_2_1_15_1","volume-title":"Patterson","author":"Hennessy John L.","year":"2017","unstructured":"John L. Hennessy and David A. Patterson. 2017. Computer Architecture, Sixth Edition: A Quantitative Approach. (6th ed.). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA. isbn: 0128119055.","edition":"6"},{"key":"e_1_3_2_1_16_1","volume-title":"Retrieved","author":"IBM.","year":"2023","unstructured":"IBM. 2023. Time.h. Retrieved Nov. 25, 2023 from https:\/\/www.ibm.com\/docs\/en\/i\/7.5?topic=extensions-standard-c-library-functions-table-by-name."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263595"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37658-0_12"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48086-2_16"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_21_1","first-page":"226","article-title":"Exceeding the dataflow limit via value prediction. In Proceedings of the 29th Annual IEEE\/ACM International Symposium on Microarchitecture","volume":"29","author":"Lipasti M.H.","year":"1996","unstructured":"M.H. Lipasti and J.P. Shen. 1996. Exceeding the dataflow limit via value prediction. In Proceedings of the 29th Annual IEEE\/ACM International Symposium on Microarchitecture. MICRO 29, 226--237.","journal-title":"MICRO"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305212"},{"volume-title":"2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), 179--192","author":"Angelo","key":"e_1_3_2_1_23_1","unstructured":"Angelo Matni et al. 2022. Noelle offers empowering llvm extensions. In 2022 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), 179--192."},{"key":"e_1_3_2_1_24_1","unstructured":"Daniel Molka. 2016. Performance analysis of complex shared memory systems. In https:\/\/api.semanticscholar.org\/CorpusID:5080429."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"K. W. Morton and D. F. Mayers. 2005. Numerical Solution of Partial Differential Equations: An Introduction. (2nd ed.). Cambridge University Press.","DOI":"10.1017\/CBO9780511812248"},{"volume-title":"Proceedings of the 32nd Annual ACM\/IEEE International Symposium on Microarchitecture, 177--185","author":"Moshovos A.","key":"e_1_3_2_1_26_1","unstructured":"A. Moshovos and G.S. Sohi. 1999. Read-after-read memory dependence prediction. In MICRO-32. Proceedings of the 32nd Annual ACM\/IEEE International Symposium on Microarchitecture, 177--185."},{"key":"e_1_3_2_1_27_1","volume-title":"Retrieved","author":"Nervadof G.","year":"2020","unstructured":"G. Nervadof. 2020. Solving 2d heat equation numerically using python. (Oct. 13, 2020). Retrieved Nov. 25, 2023 from https:\/\/levelup.gitconnected.com\/solving-2d-heat-equation-numerically-using-python-3334004aa01a."},{"key":"e_1_3_2_1_28_1","volume-title":"Fitzek","author":"P\u00e9ter Vingelmann NVIDIA","year":"2020","unstructured":"NVIDIA, P\u00e9ter Vingelmann, and Frank H.P. Fitzek. 2020. Cuda, release: 10.2.89. (2020). https:\/\/developer.nvidia.com\/cuda-toolkit."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/9780470050118.ecse357"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917757"},{"key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Instruction-level parallel processing: history, overview, and perspective","volume":"7","author":"Ramakrishna Rau B.","year":"1993","unstructured":"B. Ramakrishna Rau and Joseph A. Fisher. 1993. Instruction-level parallel processing: history, overview, and perspective. J. Supercomput., 7, 1--2, (May 1993), 9--50.","journal-title":"J. Supercomput."},{"key":"e_1_3_2_1_32_1","volume-title":"Compile-time partitioning and scheduling of parallel programs. SIGPLAN Not., 21, 7, (July","author":"Sarkar Vivek","year":"1986","unstructured":"Vivek Sarkar and John Hennessy. 1986. Compile-time partitioning and scheduling of parallel programs. SIGPLAN Not., 21, 7, (July 1986), 17--26."},{"key":"e_1_3_2_1_34_1","volume-title":"Retrieved","author":"Sigoure Benoit","year":"2010","unstructured":"Benoit Sigoure. 2010. Little micro-benchmarks to assess the performance overhead of context switching. Retrieved Nov. 25, 2023 from https:\/\/github.com\/tsuna\/contextswitch\/blob\/master\/timetctxsw.c."},{"volume-title":"Proceedings 22nd Annual International Symposium on Computer Architecture, 414--425","author":"Sohi G.S.","key":"e_1_3_2_1_35_1","unstructured":"G.S. Sohi, S.E. Breach, and T.N. Vijaykumar. 1995. Multiscalar processors. In Proceedings 22nd Annual International Symposium on Computer Architecture, 414--425."},{"key":"e_1_3_2_1_37_1","unstructured":"J.J. van Hoorn. 2016. Dynamic Programming for Routing and Scheduling: Optimizing Sequences of Decisions. English. PhD-Thesis - Research and graduation internal. Vrije Universiteit Amsterdam. Naam instelling promotie: VU Vrije Universiteit Naam instelling onderzoek: VU Vrije Universiteit."},{"key":"e_1_3_2_1_38_1","volume-title":"CMOS VLSI Design: A Circuits and Systems Perspective","author":"Weste Neil","unstructured":"Neil Weste and David Harris. 2010. CMOS VLSI Design: A Circuits and Systems Perspective. (4th ed.). Addison-Wesley Publishing Company, USA. isbn: 0321547748.","edition":"4"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2821505"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS51385.2021.00030"}],"event":{"name":"PASC '24: Platform for Advanced Scientific Computing Conference","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","ETH Zurich \/ CSCS"],"location":"Zurich Switzerland","acronym":"PASC '24"},"container-title":["Proceedings of the Platform for Advanced Scientific Computing Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659914.3659921","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:38Z","timestamp":1750291418000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659914.3659921"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":38,"alternative-id":["10.1145\/3659914.3659921","10.1145\/3659914"],"URL":"https:\/\/doi.org\/10.1145\/3659914.3659921","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-06-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}