{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:00:42Z","timestamp":1784203242080,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T00:00:00Z","timestamp":1699660800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["21J22305"],"award-info":[{"award-number":["21J22305"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003382","name":"Core Research for Evolutional Science and Technology","doi-asserted-by":"publisher","award":["JPMJCR21M2"],"award-info":[{"award-number":["JPMJCR21M2"]}],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,12]]},"DOI":"10.1145\/3581784.3607049","type":"proceedings-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T20:34:48Z","timestamp":1698698088000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Itoyori: Reconciling Global Address Space and Global Fork-Join Task Parallelism"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9129-3448","authenticated-orcid":false,"given":"Shumpei","family":"Shiina","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5224-382X","authenticated-orcid":false,"given":"Kenjiro","family":"Taura","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,11,11]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/341800.341801"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 17th Annual International Symposium on Computer Architecture","author":"Sarita","unstructured":"Sarita V. Adve and Mark D. Hill. 1990. Weak Ordering - A New Definition. In Proceedings of the 17th Annual International Symposium on Computer Architecture (Seattle, Washington, USA) (ISCA '90). 2--14."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749246.2749272"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.2197\/ipsjjip.24.583"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03869-3_80"},{"key":"e_1_3_2_2_6_1","first-page":"3","article-title":"The Design of OpenMP Tasks","volume":"20","author":"Ayguad\u00e9 Eduard","year":"2008","unstructured":"Eduard Ayguad\u00e9, Nawal Copty, Alejandro Duran, Jay Hoeflinger, Yuan Lin, Federico Massaioli, Xavier Teruel, Priya Unnikrishnan, and Guansong Zhang. 2008. The Design of OpenMP Tasks. IEEE Transactions on Parallel and Distributed Systems 20, 3 (June 2008), 404--418.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1122971.1122990"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2388996.2389086"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the Second ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","author":"Bennett J. K.","unstructured":"J. K. Bennett, J. B. Carter, and W. Zwaenepoel. 1990. Munin: Distributed Shared Memory Based on Type-Specific Memory Coherence. In Proceedings of the Second ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (Seattle, Washington, USA) (PPOPP '90). 168--176."},{"key":"e_1_3_2_2_11_1","volume-title":"The Midway Distributed Shared Memory System. In Digest of Papers. The 38th IEEE Computer Society International Conference","author":"Bershad B.N.","unstructured":"B.N. Bershad, M.J. Zekauskas, and W.A. Sawdon. 1993. The Midway Distributed Shared Memory System. In Digest of Papers. The 38th IEEE Computer Society International Conference (San Francisco, California, USA) (COMPCON Spring '93). 528--537."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989493.1989553"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the Eighth Annual ACM Symposium on Parallel Algorithms and Architectures","author":"Blumofe Robert D.","unstructured":"Robert D. Blumofe, Matteo Frigo, Christopher F. Joerg, Charles E. Leiserson, and Keith H. Randall. 1996. An Analysis of Dag-Consistent Distributed Shared-Memory Algorithms. In Proceedings of the Eighth Annual ACM Symposium on Parallel Algorithms and Architectures (Padua, Italy) (SPAA '96). 297--308."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the 10th International Parallel Processing Symposium","author":"Blumofe Robert D.","unstructured":"Robert D. Blumofe, Matteo Frigo, Christopher F. Joerg, Charles E. Leiserson, and Keith H. Randall. 1996. Dag-Consistent Distributed Shared Memory. In Proceedings of the 10th International Parallel Processing Symposium (Honolulu, Hawaii, USA) (IPPS '96). 132--141."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/209936.209958"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/324133.324234"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2013.98"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23400-2_52"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236209"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the 50th International Conference on Parallel Processing","author":"Cartier Hannah","unstructured":"Hannah Cartier, James Dinan, and D. Brian Larkins. 2021. Optimizing Work Stealing Communication with Structured Atomic Operations. In Proceedings of the 50th International Conference on Parallel Processing (Lemont, Illinois, USA) (ICPP '21). 36:1--36:10."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342007078442"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020373.2020375"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1094811.1094852"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383669.3398278"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.92"},{"key":"e_1_3_2_2_26_1","volume-title":"Proceedings of the 37th International Conference on Parallel Processing","author":"Dinan James","unstructured":"James Dinan, Sriram Krishnamoorthy, D. Brian Larkins, Jarek Nieplocha, and P. Sadayappan. 2008. Scioto: A Framework for Global-View Task Parallelism. In Proceedings of the 37th International Conference on Parallel Processing (Portland, Oregon, USA) (ICPP '08). 586--593."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654113"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1214527"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDRM51949.2020.00006"},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the 2015 9th International Conference on Partitioned Global Address Space Programming Models (Washington, District of Columbia, USA) (PGAS '15)","author":"Michael","unstructured":"Michael P. Ferguson and Daniel Buettner. 2015. Caching Puts and Gets in a PGAS Language Runtime. In Proceedings of the 2015 9th International Conference on Partitioned Global Address Space Programming Models (Washington, District of Columbia, USA) (PGAS '15). 13--24."},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (Montreal","author":"Frigo Matteo","unstructured":"Matteo Frigo, Charles E. Leiserson, and Keith H. Randall. 1998. The Implementation of the Cilk-5 Multithreaded Language. In Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (Montreal, Quebec, Canada) (PLDI '98). 212--223."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0140"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1278177.1278182"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/325164.325102"},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the 2021 IEEE\/ACM 21st International Symposium on Cluster, Cloud and Internet Computing","author":"Ghosh Sayan","unstructured":"Sayan Ghosh, Yanfei Guo, Pavan Balaji, and Assefaw H. Gebremedhin. 2021. RMACXX: An Efficient High-Level C++ Interface over MPI-3 RMA. In Proceedings of the 2021 IEEE\/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (Melbourne, Australia) (CCGrid '21). 143--155."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50995-2_1"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1504176.1504187"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/135226.135230"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2780584"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2676870.2676883"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749246.2749250"},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the USENIX","author":"Keleher Pete","year":"1994","unstructured":"Pete Keleher, Alan L. Cox, Sandhya Dwarkadas, and Willy Zwaenepoel. 1994. TreadMarks: Distributed Shared Memory on Standard Workstations and Operating Systems. In Proceedings of the USENIX Winter 1994 Technical Conference on USENIX Winter 1994 Technical Conference (San Francisco, California, USA) (WTEC '94)."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/139669.139676"},{"key":"e_1_3_2_2_44_1","volume-title":"High Performance Fortran Handbook","author":"Koelbel Charles H.","unstructured":"Charles H. Koelbel, David Loveman, Robert S. Schreiber, Guy L. Steele Jr., and Mary Zosel. 1993. High Performance Fortran Handbook. The MIT Press."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2676870.2676879"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/2145816.2145827"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2010.62"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/75104.75105"},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the 28th International European Conference on Parallel and Distributed Computing (Glasgow","author":"Mena Jimmy Aguilar","year":"2022","unstructured":"Jimmy Aguilar Mena, Omar Shaaban, Vicen\u00e7 Beltran, Paul Carpenter, Eduard Ayguade, and Jesus Labarta. 2022. OmpSs-2@Cluster: Distributed Memory Execution of Nested OpenMP-style Tasks. In Proceedings of the 28th International European Conference on Parallel and Distributed Computing (Glasgow, Scotland, UK) (Euro-Par '22). 319--334."},{"key":"e_1_3_2_2_50_1","volume-title":"Proceedings of the Fifth Conference on Partitioned Global Address Space Programming Models","author":"Min Seung-Jai","year":"2011","unstructured":"Seung-Jai Min, Costin Iancu, and Katherine Yelick. 2011. Hierarchical Work Stealing on Manycore Clusters. In Proceedings of the Fifth Conference on Partitioned Global Address Space Programming Models (Galveston Island, Texas, USA) (PGAS '11). 1--10."},{"key":"e_1_3_2_2_51_1","volume-title":"Proceedings of the 1990 ACM Conference on LISP and Functional Programming","author":"Mohr Eric","unstructured":"Eric Mohr, David A. Kranz, and Robert H. Halstead. 1990. Lazy Task Creation: A Technique for Increasing the Granularity of Parallel Programs. In Proceedings of the 1990 ACM Conference on LISP and Functional Programming (Nice, France) (LFP '90). 185--197."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.117"},{"key":"e_1_3_2_2_53_1","volume-title":"MassiveThreads: A Thread Library for High Productivity Languages. Concurrent Objects and Beyond 8665 (Jan","author":"Nakashima Jun","year":"2014","unstructured":"Jun Nakashima and Kenjiro Taura. 2014. MassiveThreads: A Thread Library for High Productivity Languages. Concurrent Objects and Beyond 8665 (Jan. 2014), 222--238."},{"key":"e_1_3_2_2_54_1","volume-title":"Proceedings of the First International Workshop on Rack-Scale Computing","author":"Nelson Jacob","year":"2014","unstructured":"Jacob Nelson, Brandon Holt, Brandon Myers, Preston Briggs, Luis Ceze, Simon Kahan, and Mark Oskin. 2014. Grappa: A Latency-Tolerant Runtime for Large-Scale Irregular Applications. In Proceedings of the First International Workshop on Rack-Scale Computing (Amsterdam, The Netherlands) (WRSC '14). 1--7."},{"key":"e_1_3_2_2_55_1","volume-title":"Proceedings of the 2015 USENIX Annual Technical Conference (Denver, Colorado, USA) (USENIX ATC '15). 291--305","author":"Nelson Jacob","year":"2015","unstructured":"Jacob Nelson, Brandon Holt, Brandon Myers, Preston Briggs, Luis Ceze, Simon Kahan, and Mark Oskin. 2015. Latency-Tolerant Software Distributed Shared Memory. In Proceedings of the 2015 USENIX Annual Technical Conference (Denver, Colorado, USA) (USENIX ATC '15). 291--305."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/243179.243182"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/289918.289920"},{"key":"e_1_3_2_2_58_1","volume-title":"Proceedings of the 19th International Conference on Languages and Compilers for Parallel Computing (New Orleans","author":"Olivier Stephen","year":"2006","unstructured":"Stephen Olivier, Jun Huan, Jinze Liu, Jan Prins, James Dinan, P. Sadayappan, and Chau-Wen Tseng. 2006. UTS: An Unbalanced Tree Search Benchmark. In Proceedings of the 19th International Conference on Languages and Compilers for Parallel Computing (New Orleans, Los Angeles, USA) (LCPC '06). 235--250."},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.19"},{"key":"e_1_3_2_2_60_1","volume-title":"Cilk: Efficient Multithreaded Computing. Ph. D. Dissertation. Department of Electrical Engineering and Computer Science","author":"Randall Keith H.","year":"1998","unstructured":"Keith H. Randall. 1998. Cilk: Efficient Multithreaded Computing. Ph. D. Dissertation. Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology."},{"key":"e_1_3_2_2_61_1","volume-title":"Intel Threading Building Blocks: Outfitting C++ for Multi-Core Processor Parallelism","author":"Reinders James","unstructured":"James Reinders. 2007. Intel Threading Building Blocks: Outfitting C++ for Multi-Core Processor Parallelism. O'Reilly Media."},{"key":"e_1_3_2_2_62_1","volume-title":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (Montreal, QC, Canada) (PPoPP '23)","author":"Tao","unstructured":"Tao B. Schardl and I-Ting Angelina Lee. 2023. OpenCilk: A Modular and Extensible Software Infrastructure for Fast Task-Parallel Code. In Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming (Montreal, QC, Canada) (PPoPP '23). 189--203."},{"key":"e_1_3_2_2_63_1","volume-title":"Global Task Data-Dependencies in PGAS Applications. In High Performance Computing: the 34th International Conference, ISC High Performance 2019 (Frankfurt\/Main, Germany) (ISC '19)","author":"Schuchart Joseph","year":"2019","unstructured":"Joseph Schuchart and Jos\u00e9 Gracia. 2019. Global Task Data-Dependencies in PGAS Applications. In High Performance Computing: the 34th International Conference, ISC High Performance 2019 (Frankfurt\/Main, Germany) (ISC '19). 312--329."},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356161"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER51413.2022.00027"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3196192"},{"key":"e_1_3_2_2_67_1","volume-title":"Proceedings of the 8th Workshop on OpenSHMEM and Related Technologies (Virtual Event) (OpenSHMEM '21)","author":"Si Min","year":"2021","unstructured":"Min Si, Huansong Fu, Jeff R. Hammond, and Pavan Balaji. 2021. OpenSHMEM over MPI as a Performance Contender: Thorough Analysis and Optimizations. In Proceedings of the 8th Workshop on OpenSHMEM and Related Technologies (Virtual Event) (OpenSHMEM '21). 39--60."},{"key":"e_1_3_2_2_68_1","volume-title":"Proceedings of the 48th International Symposium on Microarchitecture","author":"Sinclair Matthew D.","unstructured":"Matthew D. Sinclair, Johnathan Alsop, and Sarita V. Adve. 2015. Efficient GPU Synchronization without Scopes: Saying No to Complex Consistency Models. In Proceedings of the 48th International Symposium on Microarchitecture (Waikiki, Hawaii, USA) (MICRO-48). 647--659."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"crossref","unstructured":"Kenjiro Taura Jun Nakashima Rio Yokota and Naoya Maruyama. 2012. A Task Parallel Implementation of Fast Multipole Methods. In 2012 SC Companion: High Performance Computing Networking Storage and Analysis-Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (Salt Lake City Utah USA) (ScalA' 12). 617--625.","DOI":"10.1109\/SC.Companion.2012.86"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3149457.3154482"},{"key":"e_1_3_2_2_71_1","unstructured":"Rio Yokota and Lorena Barba. 2020. GitHub repository: exafmm\/exafmm-beta. Retrieved 2022-11-30 from https:\/\/github.com\/exafmm\/exafmm-beta"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2012.09.011"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS53621.2022.00099"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/2567634.2567639"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDP.2006.16"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.115"}],"event":{"name":"SC '23: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver CO USA","acronym":"SC '23","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607049","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3581784.3607049","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3607049","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581784.3607049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:36:22Z","timestamp":1750178182000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581784.3607049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,11]]},"references-count":75,"alternative-id":["10.1145\/3581784.3607049","10.1145\/3581784"],"URL":"https:\/\/doi.org\/10.1145\/3581784.3607049","relation":{},"subject":[],"published":{"date-parts":[[2023,11,11]]},"assertion":[{"value":"2023-11-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}