{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T05:53:20Z","timestamp":1750830800884,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,20]]},"DOI":"10.1145\/3652586.3663314","type":"proceedings-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T16:39:11Z","timestamp":1718901551000},"page":"25-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Shray: An Owner-Compute Distributed Shared-Memory System"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1874-0233","authenticated-orcid":false,"given":"Stefan","family":"Schrijvers","sequence":"first","affiliation":[{"name":"Radboud University, Nijmegen, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1031-7226","authenticated-orcid":false,"given":"Thomas","family":"Koopman","sequence":"additional","affiliation":[{"name":"Radboud University, Nijmegen, Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8663-1043","authenticated-orcid":false,"given":"Sven-Bodo","family":"Scholz","sequence":"additional","affiliation":[{"name":"Radboud University, Nijmegen, Netherlands"}]}],"member":"320","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n. d.]. MVAPICH Benchmark. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/ Accessed: 2023-08-02"},{"volume-title":"d.]. Oak Ridge\u2019s exascale \u2019Frontier","year":"2023","key":"e_1_3_2_1_2_1","unstructured":"[n. d.]. Oak Ridge\u2019s exascale \u2019Frontier\u2019 system named world\u2019s most powerful supercomputer on Top500. https:\/\/www.datacenterdynamics.com\/en\/news\/oak-ridges-exascale-frontier-system-named-worlds-most-powerful-supercomputer-on-top500\/ Accessed: 2023-08-02"},{"key":"e_1_3_2_1_3_1","unstructured":"[n. d.]. Shray. https:\/\/gitlab.sac-home.org\/sac-group\/shray2 Accessed: 2023-08-02"},{"volume-title":"Proceedings of the 1984 SIGPLAN Symposium on Compiler Construction (SIGPLAN \u201984)","author":"John","key":"e_1_3_2_1_4_1","unstructured":"John R. Allen and Ken Kennedy. 1984. Automatic Loop Interchange. In Proceedings of the 1984 SIGPLAN Symposium on Compiler Construction (SIGPLAN \u201984). Association for Computing Machinery, New York, NY, USA. 233\u2013246. isbn:0897911393 https:\/\/doi.org\/10.1145\/502874.502897 10.1145\/502874.502897"},{"key":"e_1_3_2_1_5_1","volume-title":"Alex Woo, and Maurice Yarrow.","author":"Bailey David","year":"1995","unstructured":"David Bailey, Tim Harris, William Saphir, Rob Van Der Wijngaart, Alex Woo, and Maurice Yarrow. 1995. The NAS parallel benchmarks 2.0. Technical Report NAS-95-020, NASA Ames Research Center."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/567806.567807"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/192007.192024"},{"volume-title":"Proceedings of the Twenty-First Annual Symposium on Parallelism in Algorithms and Architectures (SPAA \u201909)","author":"Bulu\u00e7 Aydin","key":"e_1_3_2_1_8_1","unstructured":"Aydin Bulu\u00e7, Jeremy T. Fineman, Matteo Frigo, John R. Gilbert, and Charles E. Leiserson. 2009. Parallel Sparse Matrix-Vector and Matrix-Transpose-Vector Multiplication Using Compressed Sparse Blocks. In Proceedings of the Twenty-First Annual Symposium on Parallelism in Algorithms and Architectures (SPAA \u201909). Association for Computing Machinery, New York, NY, USA. 233\u2013244. isbn:9781605586069 https:\/\/doi.org\/10.1145\/1583991.1584053 10.1145\/1583991.1584053"},{"key":"e_1_3_2_1_9_1","volume-title":"Ninth International Workshop on High-Level Parallel Programming Models and Supportive Environments, 2004. Proceedings.. 52\u201360","author":"Callahan D.","year":"2004","unstructured":"D. Callahan, B.L. Chamberlain, and H.P. Zima. 2004. The cascade high productivity language. In Ninth International Workshop on High-Level Parallel Programming Models and Supportive Environments, 2004. Proceedings.. 52\u201360. https:\/\/doi.org\/10.1109\/HIPS.2004.1299190 10.1109\/HIPS.2004.1299190"},{"key":"e_1_3_2_1_10_1","volume-title":"14th International Conference on Parallel Architectures and Compilation Techniques (PACT\u201905)","author":"Chen Wei-Yu","year":"2005","unstructured":"Wei-Yu Chen, C. Iancu, and K. Yelick. 2005. Communication optimizations for fine-grained UPC applications. In 14th International Conference on Parallel Architectures and Compilation Techniques (PACT\u201905). 267\u2013278. https:\/\/doi.org\/10.1109\/PACT.2005.13 10.1109\/PACT.2005.13"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2716320"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/65.93183"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing. IPPS\/SPDP 1999","author":"Dwarkadas S.","year":"1999","unstructured":"S. Dwarkadas, N. Hardavellas, L. Kontothanassis, R. Nikhil, and R. Stets. 1999. Cashmere-VLM: Remote memory paging for software distributed shared memory. In Proceedings 13th International Parallel Processing Symposium and 10th Symposium on Parallel and Distributed Processing. IPPS\/SPDP 1999. 153\u2013159. https:\/\/doi.org\/10.1109\/IPPS.1999.760451 10.1109\/IPPS.1999.760451"},{"volume-title":"Proceedings of the 2006 ACM\/IEEE conference on Supercomputing.","author":"Tarek","key":"e_1_3_2_1_14_1","unstructured":"Tarek A. El-Ghazawi and Lauren Smith. 2006. UPC: unified parallel C. Proceedings of the 2006 ACM\/IEEE conference on Supercomputing."},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 8th ACM SIGPLAN International Workshop on Libraries, Languages and Compilers for Array Programming (ARRAY 2022","author":"Kharroubi Micha\u00ebl El","year":"2022","unstructured":"Micha\u00ebl El Kharroubi, Baptiste Coudray, and Orestis Malaspinas. 2022. Distributed Parallel Computing with Futhark: A Functional Language to Generate Distributed Parallel Code. In Proceedings of the 8th ACM SIGPLAN International Workshop on Libraries, Languages and Compilers for Array Programming (ARRAY 2022). Association for Computing Machinery, New York, NY, USA. 12\u201324. isbn:9781450392693 https:\/\/doi.org\/10.1145\/3520306.3534501 10.1145\/3520306.3534501"},{"volume-title":"Proceedings of the Twelfth ACM Symposium on Operating Systems Principles (SOSP \u201989)","author":"Fleisch B.","key":"e_1_3_2_1_16_1","unstructured":"B. Fleisch and G. Popek. 1989. Mirage: A Coherent Distributed Shared Memory Design. In Proceedings of the Twelfth ACM Symposium on Operating Systems Principles (SOSP \u201989). Association for Computing Machinery, New York, NY, USA. 211\u2013223. isbn:0897913388 https:\/\/doi.org\/10.1145\/74850.74871 10.1145\/74850.74871"},{"key":"e_1_3_2_1_17_1","volume-title":"MPI: A Message-Passing Interface Standard. USA.","author":"Forum Message P","year":"1994","unstructured":"Message P Forum. 1994. MPI: A Message-Passing Interface Standard. USA. Available at https:\/\/www.mpi-forum.org\/docs\/"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI","author":"Henriksen Troels","year":"2017","unstructured":"Troels Henriksen, Niels G. W. Serup, Martin Elsman, Fritz Henglein, and Cosmin E. Oancea. 2017. Futhark: Purely Functional GPU-programming with Nested Parallelism and In-place Array Updates. In Proceedings of the 38th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI 2017). ACM, New York, NY, USA. 556\u2013571. isbn:978-1-4503-4988-8 https:\/\/doi.org\/10.1145\/3062341.3062354 10.1145\/3062341.3062354"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","first-page":"409","DOI":"10.6028\/jres.049.044","article-title":"Methods of conjugate gradients for solving linear systems","volume":"49","author":"Hestenes Magnus R","year":"1952","unstructured":"Magnus R Hestenes and Eduard Stiefel. 1952. Methods of conjugate gradients for solving linear systems. Journal of research of the National Bureau of Standards, 49, 6 (1952), 409\u2013436.","journal-title":"Journal of research of the National Bureau of Standards"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 2007 International Conference on High Performance Computing, Networking, Storage and Analysis, SC07","author":"Hoefler Torsten","year":"2007","unstructured":"Torsten Hoefler, Andrew Lumsdaine, and Wolfgang Rehm. 2007. Implementation and Performance Analysis of Non-Blocking Collective Operations for MPI. In Proceedings of the 2007 International Conference on High Performance Computing, Networking, Storage and Analysis, SC07. IEEE Computer Society\/ACM."},{"key":"e_1_3_2_1_22_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 (WTEC\u201994). USENIX Association, USA. 10."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 21st Annual International Symposium on Computer Architecture (ISCA \u201994)","author":"Kuskin J.","year":"1865","unstructured":"J. Kuskin, D. Ofelt, M. Heinrich, J. Heinlein, R. Simoni, K. Gharachorloo, J. Chapin, D. Nakahira, J. Baxter, M. Horowitz, A. Gupta, M. Rosenblum, and J. Hennessy. 1994. The Stanford FLASH Multiprocessor. In Proceedings of the 21st Annual International Symposium on Computer Architecture (ISCA \u201994). IEEE Computer Society Press, Washington, DC, USA. 302\u2013313. isbn:0818655100 https:\/\/doi.org\/10.1109\/ISCA.1994.288140 10.1109\/ISCA.1994.288140"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2508834.2513149"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.599898"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.121510"},{"key":"e_1_3_2_1_27_1","first-page":"2","volume-title":"Proceedings of the International Conference on Parallel Processing","author":"Li Kai","year":"1988","unstructured":"Kai Li. 1988. IVY: a shared virtual memory system for parallel computing. Proceedings of the International Conference on Parallel Processing, 2 (1988), 1 Dec., 94\u2013101. issn:0190-3918"},{"key":"e_1_3_2_1_28_1","unstructured":"Piotr Luszczek Jack Dongarra David Koester Rolf Rabenseifner Bob Lucas Jeremy Kepner John McCalpin David Bailey and Daisuke Takahashi. 2004. Introduction to the HPC Challenge Benchmark Suite. 12."},{"key":"e_1_3_2_1_29_1","volume-title":"SAC Goes Cluster: Fully Implicit Distributed Computing. In 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 996\u20131006","author":"Macht Thomas","year":"2019","unstructured":"Thomas Macht and Clemens Grelck. 2019. SAC Goes Cluster: Fully Implicit Distributed Computing. In 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). 996\u20131006. https:\/\/doi.org\/10.1109\/IPDPS.2019.00107 10.1109\/IPDPS.2019.00107"},{"key":"e_1_3_2_1_30_1","volume-title":"ViSMI: Software Distributed Shared Memory for InfiniBand Clusters. In 2013 IEEE 12th International Symposium on Network Computing and Applications. IEEE Computer Society","author":"Mairandres M.","year":"2004","unstructured":"M. Mairandres, C. Trinitis, J. Tao, and C. Osendorfer. 2004. ViSMI: Software Distributed Shared Memory for InfiniBand Clusters. In 2013 IEEE 12th International Symposium on Network Computing and Applications. IEEE Computer Society, Los Alamitos, CA, USA. 185\u2013191. https:\/\/doi.org\/10.1109\/NCA.2004.1347776 10.1109\/NCA.2004.1347776"},{"key":"e_1_3_2_1_31_1","volume-title":"Thirty-Fifth IEEE Computer Society International Conference on Intellectual Leverage. 73\u201381","author":"Maples C.","year":"1990","unstructured":"C. Maples and L. Wittie. 1990. MERLIN. A superglue for multicomputer systems. In Digest of Papers Compcon Spring \u201990. Thirty-Fifth IEEE Computer Society International Conference on Intellectual Leverage. 73\u201381. https:\/\/doi.org\/10.1109\/CMPCON.1990.63656 10.1109\/CMPCON.1990.63656"},{"key":"e_1_3_2_1_32_1","volume-title":"1994 ACM\/IEEE Conference on Supercomputing. 340\u2013349","author":"Nieplocha J.","year":"1994","unstructured":"J. Nieplocha, R.J. Harrison, and R.J. Littlefield. 1994. Global Arrays: a portable \u00dfhared-memory\" programming model for distributed memory computers. In Supercomputing \u201994:Proceedings of the 1994 ACM\/IEEE Conference on Supercomputing. 340\u2013349. https:\/\/doi.org\/10.1109\/SUPERC.1994.344297 10.1109\/SUPERC.1994.344297"},{"key":"e_1_3_2_1_33_1","unstructured":"Omni OpenMP Compiler Project. 2014. NPB3.0-omp-C. https:\/\/github.com\/benchmark-subsetting\/NPB3.0-omp-C"},{"key":"e_1_3_2_1_34_1","volume-title":"2011 IEEE 17th International Conference on Parallel and Distributed Systems. 212\u2013219","author":"Ramesh Bharath","year":"2011","unstructured":"Bharath Ramesh, Calvin J. Ribbens, and Srinidhi Varadarajan. 2011. Is It Time to Rethink Distributed Shared Memory Systems? In 2011 IEEE 17th International Conference on Parallel and Distributed Systems. 212\u2013219. https:\/\/doi.org\/10.1109\/ICPADS.2011.75 10.1109\/ICPADS.2011.75"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1017\/S0956796802004458","article-title":"Single Assignment C \u2014 Efficient Support for High-level Array Operations in a Functional Setting","volume":"13","author":"Scholz Sven-Bodo","year":"2003","unstructured":"Sven-Bodo Scholz. 2003. Single Assignment C \u2014 Efficient Support for High-level Array Operations in a Functional Setting. Journal of Functional Programming, 13, 6 (2003), 1005\u20131059. https:\/\/doi.org\/10.1.1.138.6995","journal-title":"Journal of Functional Programming"},{"key":"e_1_3_2_1_36_1","article-title":"Comparative Study of Various Consistency Models in Distributed Shared Memory System","volume":"6","author":"Singh Sindhu","year":"2010","unstructured":"Sindhu Singh. 2010. Comparative Study of Various Consistency Models in Distributed Shared Memory System. The IUP Journal of Information Technology, 6 (2010), 03, 64\u201375.","journal-title":"The IUP Journal of Information Technology"},{"key":"e_1_3_2_1_37_1","volume-title":"1989 ACM\/IEEE Conference on Supercomputing. 655\u2013664","author":"Wolfe M.","year":"1989","unstructured":"M. Wolfe. 1989. More iteration space tiling. In Supercomputing \u201989:Proceedings of the 1989 ACM\/IEEE Conference on Supercomputing. 655\u2013664. https:\/\/doi.org\/10.1145\/76263.76337 10.1145\/76263.76337"},{"key":"e_1_3_2_1_38_1","volume-title":"2012 IEEE 18th International Conference on Parallel and Distributed Systems. 684\u2013691","author":"Xianyi Zhang","year":"2012","unstructured":"Zhang Xianyi, Wang Qian, and Zhang Yunquan. 2012. Model-driven Level 3 BLAS Performance Optimization on Loongson 3A Processor. In 2012 IEEE 18th International Conference on Parallel and Distributed Systems. 684\u2013691. https:\/\/doi.org\/10.1109\/ICPADS.2012.97 10.1109\/ICPADS.2012.97"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models (PGAS \u201914)","author":"Zhou Huan","year":"2014","unstructured":"Huan Zhou, Yousri Mhedheb, Kamran Idrees, Colin W. Glass, Jos\u00e9 Gracia, and Karl F\u00fcrlinger. 2014. DART-MPI: An MPI-Based Implementation of a PGAS Runtime System. In Proceedings of the 8th International Conference on Partitioned Global Address Space Programming Models (PGAS \u201914). Association for Computing Machinery, New York, NY, USA. Article 3, 11 pages. isbn:9781450332477 https:\/\/doi.org\/10.1145\/2676870.2676875 10.1145\/2676870.2676875"}],"event":{"name":"ARRAY '24: 10th ACM SIGPLAN International Workshop on Libraries, Languages and Compilers for Array Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"],"location":"Copenhagen Denmark","acronym":"ARRAY '24"},"container-title":["Proceedings of the 10th ACM SIGPLAN International Workshop on Libraries, Languages and Compilers for Array Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652586.3663314","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652586.3663314","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:30Z","timestamp":1750291410000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652586.3663314"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,20]]},"references-count":39,"alternative-id":["10.1145\/3652586.3663314","10.1145\/3652586"],"URL":"https:\/\/doi.org\/10.1145\/3652586.3663314","relation":{},"subject":[],"published":{"date-parts":[[2024,6,20]]},"assertion":[{"value":"2024-06-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}