{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:14:39Z","timestamp":1787314479118,"version":"3.56.0"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032071934","type":"print"},{"value":"9783032071941","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"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\/978-3-032-07194-1_9","type":"book-chapter","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:07:02Z","timestamp":1760465222000},"page":"143-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Extending the\u00a0SPMD IR for\u00a0RMA Models and\u00a0Static Data Race Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6048-9643","authenticated-orcid":false,"given":"Semih","family":"Burak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7121-7205","authenticated-orcid":false,"given":"Simon","family":"Schwitanski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3137-5596","authenticated-orcid":false,"given":"Felix","family":"Tomski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5343-414X","authenticated-orcid":false,"given":"Jens","family":"Domke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2545-5258","authenticated-orcid":false,"given":"Matthias","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Aiken, A., Gay, D.: Barrier inference. In: Proceedings of the 25th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, POPL 1998, pp. 342\u2013354. Association for Computing Machinery, New York (1998). https:\/\/doi.org\/10.1145\/268946.268974","DOI":"10.1145\/268946.268974"},{"key":"9_CR2","unstructured":"Aitkaci, T.C., Sergent, M., Saillard, E., Barthou, D., Papaur\u00e9, G.: Dynamic data race detection for MPI-RMA programs. In: EuroMPI 2021 - European MPI Users\u2019s Group Meeting, Munich, Germany (2021). https:\/\/hal.science\/hal-03374614"},{"key":"9_CR3","unstructured":"AMD: ROCm Communication Collectives Library (RCCL) Documentation, Version 2.22.3 (2025). https:\/\/rocm.docs.amd.com\/projects\/rccl\/en\/docs-6.4.1\/. Accessed 11 June 2025"},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Belwal, M., TSB, S.: Intermediate representation for heterogeneous multi-core: a survey. In: 2015 International Conference on VLSI Systems, Architecture, Technology and Applications (VLSI-SATA), pp.\u00a01\u20136 (2015). https:\/\/doi.org\/10.1109\/VLSI-SATA.2015.7050496","DOI":"10.1109\/VLSI-SATA.2015.7050496"},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Brown, N., Bareford, M., Weiland, M.: Leveraging MPI RMA to optimize halo-swapping communications in MONC on Cray machines. Concurr. Comput. Pract. Exp. 31(16) (2019). https:\/\/doi.org\/10.1002\/cpe.5008","DOI":"10.1002\/cpe.5008"},{"key":"9_CR6","doi-asserted-by":"publisher","unstructured":"Brown, N., Jamieson, M., Lydike, A., Bauer, E., Grosser, T.: Fortran performance optimisation and auto-parallelisation by leveraging MLIR-based domain specific abstractions in Flang. In: Proceedings of the SC 2023 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W 2023, pp. 904\u2013913. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3624062.3624167","DOI":"10.1145\/3624062.3624167"},{"key":"9_CR7","doi-asserted-by":"publisher","unstructured":"Burak, S., Ivanov, I.R., Domke, J., M\u00fcller, M.: SPMD IR: unifying SPMD and multi-value IR showcased for static verification of collectives. In: Recent Advances in the Message Passing Interface: 31st European MPI Users\u2019 Group Meeting, EuroMPI 2024, Perth, WA, Australia, 25\u201327 September 2024, Proceedings, pp. 3\u201320. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73370-3_1","DOI":"10.1007\/978-3-031-73370-3_1"},{"key":"9_CR8","unstructured":"DeepEP Developers: DeepEP - Git Repository. https:\/\/github.com\/deepseek-ai\/DeepEP. Accessed 02 June 2025"},{"key":"9_CR9","unstructured":"DeepSeek-AI, Liu, A., Feng, B., Xue, B., et\u00a0al.: DeepSeek-V3 Technical Report (2025). https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Dinan, J., Balaji, P., Buntinas, D., Goodell, D., Gropp, W., Thakur, R.: An implementation and evaluation of the MPI 3.0 one-sided communication interface. Concurr. Comput. Pract. Exp. 28(17), 4385\u20134404 (2016). https:\/\/doi.org\/10.1002\/cpe.3758","DOI":"10.1002\/cpe.3758"},{"key":"9_CR11","unstructured":"GASPI Forum: GASPI: Global Address Space Programming Interface, Version 17.1 (2017). https:\/\/raw.githubusercontent.com\/GASPI-Forum\/GASPI-Forum.github.io\/master\/standards\/GASPI-17.1.pdf. Accessed 02 June 2025"},{"key":"9_CR12","unstructured":"Hammond, J.: Parallel Research Kerneles (PRK) - Git Repository. https:\/\/github.com\/jeffhammond\/PRK. Accessed 02 June 2025"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Hammond, J., Dalcin, L., Schnetter, E., P\u00e9Rache, M., et\u00a0al.: MPI application binary interface standardization. In: Proceedings of the 30th European MPI Users\u2019 Group Meeting, EuroMPI 2023. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3615318.3615319","DOI":"10.1145\/3615318.3615319"},{"key":"9_CR14","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-642-11261-4_5","volume-title":"Tools for High Performance Computing 2009","author":"T Hilbrich","year":"2010","unstructured":"Hilbrich, T., Schulz, M., Supinski, B.R., M\u00fcller, M.S.: MUST: a scalable approach to runtime error detection in MPI programs. In: M\u00fcller, M.S., Resch, M.M., Schulz, A., Nagel, W.E. (eds.) Tools for High Performance Computing 2009, pp. 53\u201366. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-11261-4_5"},{"key":"9_CR15","unstructured":"INRIA Researchers: PARCOACH - Git Repository. https:\/\/gitlab.inria.fr\/parcoach\/parcoach. Accessed 02 June 2025"},{"key":"9_CR16","unstructured":"Jammer, T., et al.: MPI-BugBench - Git Repository. https:\/\/git-ce.rwth-aachen.de\/hpc-public\/mpi-bugbench. Accessed 28 May 2025"},{"key":"9_CR17","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-031-73370-3_8","volume-title":"Recent Advances in the Message Passing Interface","author":"T Jammer","year":"2025","unstructured":"Jammer, T., et al.: MPI-BugBench: a framework for assessing MPI correctness tools. In: Blaas-Schenner, C., Niethammer, C., Haas, T. (eds.) Recent Advances in the Message Passing Interface, pp. 121\u2013137. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73370-3_8"},{"key":"9_CR18","doi-asserted-by":"publisher","unstructured":"Jammer, T., Schmidt, A., Bischof, C.: Annotation of compiler attributes for MPI functions. In: Recent Advances in the Message Passing Interface: 31st European MPI Users\u2019 Group Meeting, EuroMPI 2024, Perth, WA, Australia, 25\u201327 September 2024, Proceedings, pp. 21\u201335. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73370-3_2","DOI":"10.1007\/978-3-031-73370-3_2"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Lattner, C., Adve, V.: LLVM: a compilation framework for lifelong program analysis & transformation. In: International Symposium on Code Generation and Optimization, CGO 2004, pp. 75\u201386 (2004). https:\/\/doi.org\/10.1109\/CGO.2004.1281665","DOI":"10.1109\/CGO.2004.1281665"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Lattner, C., et al.: MLIR: scaling compiler infrastructure for domain specific computation. In: 2021 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), pp. 2\u201314 (2021). https:\/\/doi.org\/10.1109\/CGO51591.2021.9370308","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Lazzaro, A., VandeVondele, J., Hutter, J., Sch\u00fctt, O.: Increasing the efficiency of sparse matrix-matrix multiplication with a 2.5D algorithm and one-sided MPI. In: Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2017. Association for Computing Machinery, New York (2017). https:\/\/doi.org\/10.1145\/3093172.3093228","DOI":"10.1145\/3093172.3093228"},{"key":"9_CR22","unstructured":"Lin, T., et\u00a0al.: TeaLeaf Proxy App - Git Repository. https:\/\/github.com\/UoB-HPC\/TeaLeaf. Accessed 02 June 2025"},{"key":"9_CR23","unstructured":"LLVM Community: Project Website of CLANG IR (2024). https:\/\/llvm.github.io\/clangir\/. Accessed 02 June 2025"},{"key":"9_CR24","unstructured":"LLVM Community: Project Website of FLANG (2025). https:\/\/flang.llvm.org\/. Accessed 02 June 2025"},{"key":"9_CR25","unstructured":"Message Passing Interface Forum: MPI: A Message-Passing Interface Standard, Version 5.0 (2025). https:\/\/www.mpi-forum.org\/docs\/mpi-5.0\/mpi50-report.pdf. Accessed 06 June 2025"},{"key":"9_CR26","unstructured":"MLIR Community: Project Website of Upstream MLIR on the MPI Dialect (2024). https:\/\/mlir.llvm.org\/docs\/Dialects\/MPI\/. Accessed 02 June 2025"},{"key":"9_CR27","doi-asserted-by":"publisher","unstructured":"Moses, W.S., Chelini, L., Zhao, R., Zinenko, O.: Polygeist: raising C to polyhedral MLIR. In: 2021 30th International Conference on Parallel Architectures and Compilation Techniques (PACT), pp. 45\u201359 (2021). https:\/\/doi.org\/10.1109\/PACT52795.2021.00011","DOI":"10.1109\/PACT52795.2021.00011"},{"key":"9_CR28","doi-asserted-by":"publisher","unstructured":"Moses, W.S., Ivanov, I.R., Domke, J., Endo, T., Doerfert, J., Zinenko, O.: High-performance GPU-to-CPU transpilation and optimization via high-level parallel constructs. In: Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, PPoPP 2023, pp. 119\u2013134. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3572848.3577475","DOI":"10.1145\/3572848.3577475"},{"key":"9_CR29","unstructured":"MUST Developers: MUST - Project Website. https:\/\/itc.rwth-aachen.de\/must. Accessed 05 June 2025"},{"key":"9_CR30","doi-asserted-by":"publisher","unstructured":"Mutlu, E., et al.: COMET: a domain-specific compilation of high-performance computational chemistry. In: Chapman, B., Moreira, J. (eds.) Languages and Compilers for Parallel Computing, pp. 87\u2013103. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-95953-1_7","DOI":"10.1007\/978-3-030-95953-1_7"},{"key":"9_CR31","unstructured":"Norman, M., Larkin, J., Lyngaas, I.: MiniWeather Proxy App - Git Repository. https:\/\/github.com\/mrnorman\/miniWeather. Accessed 02 June 2025"},{"key":"9_CR32","unstructured":"NVIDIA: NVIDIA OpenSHMEM Library (NVSHMEM) Documentation, Version 2.8.0 (2023). https:\/\/docs.nvidia.com\/nvshmem\/archives\/nvshmem-280\/api\/index.html. Accessed 02 June 2025"},{"key":"9_CR33","unstructured":"NVIDIA: CUDA Toolkit Documentation, Version 12.9 (2024). https:\/\/docs.nvidia.com\/cuda\/archive\/12.9.0\/. Accessed 02 June 2025"},{"key":"9_CR34","unstructured":"NVIDIA: NVIDIA Collective Communications Library (NCCL) Documentation, Version 2.26.5 (2025). https:\/\/docs.nvidia.com\/deeplearning\/nccl\/archives\/nccl_2265\/user-guide\/docs\/index.html. Accessed 02 June 2025"},{"key":"9_CR35","unstructured":"OpenSHMEM Team: OpenSHMEM Application Programming Interface Specification, Version 1.6 (2024). http:\/\/openshmem.org\/site\/sites\/default\/site_files\/OpenSHMEM-1.6.pdf. Accessed 02 June 2025"},{"key":"9_CR36","unstructured":"Perplexity Developers: Perplexity MoE Kernels - Git Repository. https:\/\/github.com\/ppl-ai\/pplx-kernels. Accessed 02 June 2025"},{"key":"9_CR37","doi-asserted-by":"publisher","unstructured":"Potluri, S., Lai, P., Tomko, K., Sur, S., et\u00a0al.: Quantifying performance benefits of overlap using MPI-2 in a seismic modeling application. In: Proceedings of the 24th ACM International Conference on Supercomputing, ICS 2010, pp. 17\u201325. Association for Computing Machinery, New York (2010). https:\/\/doi.org\/10.1145\/1810085.1810092","DOI":"10.1145\/1810085.1810092"},{"key":"9_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-319-26428-8_2","volume-title":"OpenSHMEM and Related Technologies. Experiences, Implementations, and Technologies","author":"S Potluri","year":"2015","unstructured":"Potluri, S., et al.: Exploring OpenSHMEM model to program GPU-based extreme-scale systems. In: Gorentla Venkata, M., Shamis, P., Imam, N., Lopez, M.G. (eds.) OpenSHMEM 2014. LNCS, vol. 9397, pp. 18\u201335. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-26428-8_2"},{"key":"9_CR39","doi-asserted-by":"publisher","unstructured":"Saillard, E., Sergent, M., Ait\u00a0Kaci, C.T., Barthou, D.: Static local concurrency errors detection in MPI-RMA programs. In: 2022 IEEE\/ACM Sixth International Workshop on Software Correctness for HPC Applications (Correctness), pp. 18\u201326 (2022). https:\/\/doi.org\/10.1109\/Correctness56720.2022.00008","DOI":"10.1109\/Correctness56720.2022.00008"},{"key":"9_CR40","doi-asserted-by":"publisher","unstructured":"Schardl, T.B., Moses, W.S., Leiserson, C.E.: Tapir: embedding recursive fork-join parallelism into LLVM\u2019s intermediate representation. ACM Trans. Parallel Comput. 6(4) (2019). https:\/\/doi.org\/10.1145\/3365655","DOI":"10.1145\/3365655"},{"key":"9_CR41","unstructured":"Schwitanski, S., Jenke, J., Klotz, S., M\u00fcller, M.S.: RMARaceBench - Git Repository. https:\/\/github.com\/RWTH-HPC\/RMARaceBench. Accessed 05 June 2025"},{"key":"9_CR42","doi-asserted-by":"publisher","unstructured":"Schwitanski, S., Jenke, J., Klotz, S., M\u00fcller, M.S.: RMARaceBench: a microbenchmark suite to evaluate race detection tools for RMA programs. In: Proceedings of the SC 2023 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC-W 2023, pp. 205\u2013214. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3624062.3624087","DOI":"10.1145\/3624062.3624087"},{"key":"9_CR43","doi-asserted-by":"publisher","unstructured":"Schwitanski, S., Jenke, J., Tomski, F., Terboven, C., M\u00fcller, M.S.: On-the-fly data race detection for mpi rma programs with MUST. In: 2022 IEEE\/ACM Sixth International Workshop on Software Correctness for HPC Applications (Correctness), pp. 27\u201336. IEEE, Dallas, TX, USA (2022). https:\/\/doi.org\/10.1109\/Correctness56720.2022.00009","DOI":"10.1109\/Correctness56720.2022.00009"},{"key":"9_CR44","doi-asserted-by":"publisher","unstructured":"Schwitanski, S., Oraji, Y.M., P\u00e4tzold, C., Jenke, J., Tomski, F., M\u00fcller, M.S.: RMASanitizer: generalized runtime detection of data races in remote memory access applications. In: Proceedings of the 53rd International Conference on Parallel Processing, ICPP 2024, pp. 833\u2013844. Association for Computing Machinery, New York (2024). https:\/\/doi.org\/10.1145\/3673038.3673109","DOI":"10.1145\/3673038.3673109"},{"key":"9_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/978-3-642-29860-8_9","volume-title":"Runtime Verification","author":"K Serebryany","year":"2012","unstructured":"Serebryany, K., Potapenko, A., Iskhodzhanov, T., Vyukov, D.: Dynamic race detection with LLVM compiler. In: Khurshid, S., Sen, K. (eds.) RV 2011. LNCS, vol. 7186, pp. 110\u2013114. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-29860-8_9"},{"key":"9_CR46","unstructured":"Simon Schwitanski: RMASanitizer - Git Repository. https:\/\/github.com\/RWTH-HPC\/rmasanitizer-artifact. Accessed 02 June 2025"},{"key":"9_CR47","doi-asserted-by":"publisher","unstructured":"Spanier, A., Mahoney, W.: Static vulnerability analysis using intermediate representations: a literature review. European Conference on Cyber Warfare and Security 22, 458\u2013465 (2023). https:\/\/doi.org\/10.34190\/eccws.22.1.1154","DOI":"10.34190\/eccws.22.1.1154"},{"key":"9_CR48","doi-asserted-by":"publisher","unstructured":"Susungi, A., Tadonki, C.: Intermediate representations for explicitly parallel programs. ACM Comput. Surv. 54(5) (2021). https:\/\/doi.org\/10.1145\/3452299","DOI":"10.1145\/3452299"},{"key":"9_CR49","doi-asserted-by":"publisher","unstructured":"Tian, R., Guo, L., Li, J., Ren, B., Kestor, G.: A high performance sparse tensor algebra compiler in MLIR. In: 2021 IEEE\/ACM 7th Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC), pp. 27\u201338 (2021). https:\/\/doi.org\/10.1109\/LLVMHPC54804.2021.00009","DOI":"10.1109\/LLVMHPC54804.2021.00009"},{"key":"9_CR50","doi-asserted-by":"publisher","unstructured":"Tiotto, E., et al.: Experiences building an MLIR-based SYCL compiler. In: 2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO), pp. 399\u2013410 (2024). https:\/\/doi.org\/10.1109\/CGO57630.2024.10444866","DOI":"10.1109\/CGO57630.2024.10444866"},{"key":"9_CR51","unstructured":"UPC++ Specification Working Group: UPC++ Specification, Version 1.0 (2023). https:\/\/bitbucket.org\/berkeleylab\/upcxx\/downloads\/upcxx-spec-2023.9.0.pdf. Accessed 02 June 2025"},{"key":"9_CR52","doi-asserted-by":"publisher","unstructured":"Wang, A., Yi, X., Yan, Y.: UPIR: toward the design of unified parallel intermediate representation for parallel programming models. In: Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, PACT 2022, pp. 530\u2013531. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3559009.3569646","DOI":"10.1145\/3559009.3569646"},{"key":"9_CR53","unstructured":"Zhang, B., Chen, W., Chiu, H.C., Zhang, C.: Unveiling the Power of Intermediate Representations for Static Analysis: A Survey (2024). https:\/\/arxiv.org\/abs\/2405.12841"}],"container-title":["Lecture Notes in Computer Science","Recent Advances in the Message Passing Interface"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07194-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T10:53:00Z","timestamp":1774954380000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07194-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"ISBN":["9783032071934","9783032071941"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07194-1_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]},"assertion":[{"value":"15 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}