Publications

@inproceedings{stawinoga2026mlir,
  title         = {An {MLIR} Lowering Pipeline for Stencils at Wafer-Scale},
  author        = {Stawinoga, Nicolai and Katz, David and Lydike, Anton and Zarins, Justs and Brown, Nick and Bisbas, George and Grosser, Tobias},
  booktitle     = {Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2},
  series        = {ASPLOS '26},
  pages         = {94--109},
  year          = {2026},
  publisher     = {ACM},
  doi           = {10.1145/3779212.3790124},
  archivePrefix = {arXiv},
  eprint        = {2601.17754},
  primaryClass  = {cs.DC},
}

@inproceedings{song2026designing,
  title     = {Designing Domain-Specific Compilers for Lossy Compression: A Case Study on Wafer-Scale Engine},
  author    = {Song, Shihui and Underwood, Robert and Di, Sheng and Jiang, Peng and Cappello, Franck},
  booktitle = {2026 IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
  pages     = {1091--1104},
  year      = {2026},
  publisher = {IEEE},
  doi       = {10.1109/IPDPS65963.2026.00092},
}

@inproceedings{joshi2026glow,
  title     = {{GLOW}: Accelerating Geometric Multigrid Layers on {Cerebras} Wafer-Scale Engine},
  author    = {Joshi, Sameeran and Antepara, Oscar and Williams, Samuel and Johansen, Hans and Hall, Mary},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=pap694&sess=sess200},
}

@inproceedings{li2026llm,
  title     = {{LLM} Agents Meet Lossy Compression: Benchmark, Demystify, and Optimize Across {HPC} Architectures},
  author    = {Li, Changqing and Di, Sheng and Zhao, Kai and Dong, Wenqian},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=pap282&sess=sess224},
}

@inproceedings{he2026meshrt,
  title         = {{MeshRT}: Compile-Time Governed Wafer-Scale Runtime for Low-Latency High-Throughput Inference},
  author        = {He, Congjie and Xu, Le and Lu, Zhan and Huang, Yeqi and Xiao, Haocheng and Deng, Cheng and Ma, Lingxiao and Miao, Ziming and Yang, Fan and Mai, Luo},
  booktitle     = {Proceedings of the ACM SIGOPS 32nd Symposium on Operating Systems Principles},
  series        = {SOSP '26},
  pages         = {1122--1138},
  year          = {2026},
  publisher     = {ACM},
  doi           = {10.1145/3830418.3843856},
  archivePrefix = {arXiv},
  eprint        = {2611.08508},
}

@inproceedings{gianinazzi2026spada,
  title         = {{SpaDA}: A Spatial Dataflow Architecture Programming Language},
  author        = {Gianinazzi, Lukas and Ben-Nun, Tal and Hoefler, Torsten},
  booktitle     = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis},
  year          = {2026},
  url           = {https://sc26.conference-program.com/presentation/?id=pap782&sess=sess200},
  archivePrefix = {arXiv},
  eprint        = {2511.09447},
  primaryClass  = {cs.DC},
}

@inproceedings{huang2026wavel,
  title     = {Wavel: A Fast and Efficient Compilation System for Wafer-Scale Accelerators},
  author    = {Huang, Yeqi and He, Congjie and Xiao, Haocheng and Ye, Yanwei and Wang, Yi-Chieh and Song, Boyao and Deng, Yangshen and Miao, Ziming and Ma, Lingxiao and Yang, Fan and Mai, Luo},
  booktitle = {Proceedings of the ACM SIGOPS 32nd Symposium on Operating Systems Principles},
  series    = {SOSP '26},
  pages     = {1107--1121},
  year      = {2026},
  publisher = {ACM},
  doi       = {10.1145/3830418.3843884},
}

@article{miyajima2026characterizing,
  title     = {Characterizing Effective Compute, Memory, and Communication Performance on {Cerebras} {WSE-2}},
  author    = {Miyajima, Takaaki and Fukuoka, Leon},
  journal   = {Journal of Information Processing},
  volume    = {34},
  pages     = {1072--1083},
  year      = {2026},
  publisher = {Information Processing Society of Japan},
  doi       = {10.2197/ipsjjip.34.1072},
}

@article{miyajima2026single,
  title     = {Single-precision Matrix Multiplication Performance on {Cerebras} {CS-2}: Evaluation and Modelling of Performance, Scalability and Energy Efficiency},
  author    = {Miyajima, Takaaki and Matsuzaki, Ryunosuke and Mukunoki, Daichi},
  journal   = {Journal of Information Processing},
  volume    = {34},
  pages     = {132--139},
  year      = {2026},
  publisher = {Information Processing Society of Japan},
  doi       = {10.2197/ipsjjip.34.132},
}

@inproceedings{li2026evaluating,
  title         = {Evaluating {LLM} Coding Agents on {SZ}-Family Lossy Compression Across Architectures},
  author        = {Li, Changqing and Gao, Shouwei and Zhao, Kai and Di, Sheng and Dong, Wenqian},
  booktitle     = {2026 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)},
  note          = {HPAI4S Workshop},
  pages         = {672--676},
  year          = {2026},
  publisher     = {IEEE},
  doi           = {10.1109/IPDPSW71298.2026.00111},
  archivePrefix = {arXiv},
  eprint        = {2606.17058},
  primaryClass  = {cs.DC},
}

@inproceedings{shah2026exploring,
  title         = {Exploring Sparse Matrix Multiplication Operations on {Cerebras} {CS-3} Platforms},
  author        = {Shah, Milan and Di, Sheng and Becchi, Michela},
  booktitle     = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Workshops)},
  note          = {IA$^3$ 2026: 16th Workshop on Irregular Applications: Architectures and Algorithms. arXiv version titled "Exploring Sparse Matrix Multiplication Kernels on the Cerebras CS-3"},
  year          = {2026},
  url           = {https://sc26.conference-program.com/presentation/?id=ws_ia140&sess=sess115},
  archivePrefix = {arXiv},
  eprint        = {2604.27985},
  primaryClass  = {cs.DC},
}

@inproceedings{luo2026fabrica,
  title         = {Fabrica: Agentic {CUDA}-to-{CSL} Translation and Optimization for Wafer-Scale Systems},
  author        = {Luo, Yuebo and Huerta, Eliu and Vishwanath, Venkatram and Ding, Caiwen and Thakur, Rajeev and Chen, Le},
  booktitle     = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Workshops)},
  note          = {AgenticAI4HPC'26: The First International Workshop on Agentic AI for HPC},
  year          = {2026},
  url           = {https://sc26.conference-program.com/presentation/?id=ws_aaihpc109&sess=sess120},
  archivePrefix = {arXiv},
  eprint        = {2608.25124},
  primaryClass  = {cs.CE},
}

@inproceedings{nagashima2026performance,
  title     = {Performance comparison and analysis of macroscopic cross section lookup kernel on {Cerebras} {CS-3} and {NVIDIA} {GPUs}},
  author    = {Nagashima, Reo and Nakamura, Akeru and Tramm, John R. and Miyajima, Takaaki},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Workshops)},
  note      = {PMBS26: The 17th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computer Systems},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=ws_pmbsf133&sess=sess109},
}

@inproceedings{urquhart2026wafer,
  title     = {Wafer Scale Acceleration of Unstructured Finite Element Methods},
  author    = {Urquhart, Emma},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Workshops)},
  note      = {Twelfth International Workshop on Heterogeneous High-Performance Reconfigurable Computing (H2RC 2026)},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=ws_h2rc108&sess=sess139},
}

@inproceedings{polak2026linear,
  title     = {A Linear-Scaling, Sparse Matrix Electronic Structure Solver on the {Cerebras} Wafer-Scale Engine},
  author    = {Polak, Md Sabbir Hossain and Gatti, Anthony and Niklasson, Anders M. N. and Southworth, Benjamin S. and Finkelstein, Joshua},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Research Posters)},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=rpost127&sess=sess313},
}

@inproceedings{sakai2026naive,
  title     = {A Naive {D3Q27} Lattice {Boltzmann} Implementation on the {Cerebras} {CS-3}: Comparison with {GPUs}},
  author    = {Sakai, Kouki and Orihara, Saho and Shimokawabe, Takashi and Miyajima, Takaaki},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Research Posters)},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=rpost201&sess=sess313},
}

@inproceedings{belli2026algebraic,
  title     = {Algebraic Breadth-First Search on the {Cerebras} Wafer-Scale Engine},
  author    = {Belli, Elia and De Sensi, Daniele},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (ACM SRC Posters)},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=src_post105&sess=sess313},
}

@inproceedings{pasqualoni2026exploring,
  title     = {Exploring Tree-Based Approaches for Collective Communications on {Cerebras} {WSE-3}},
  author    = {Pasqualoni, Saverio and Canini, Marco and De Sensi, Daniele},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (ACM SRC Posters)},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=src_post121&sess=sess313},
}

@inproceedings{orihara2026load,
  title     = {Load Balancing and Communication Bottlenecks in {SpMV} on the {Cerebras} {WSE-3}},
  author    = {Orihara, Saho and Sakai, Kouki and Nagashima, Reo and Miyajima, Takaaki},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Research Posters)},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=rpost204&sess=sess313},
}

@inproceedings{sun2026sparse,
  title     = {Sparse Matrix-Vector Multiplication on {Cerebras} {WSE-3}},
  author    = {Sun, Zenchang and Margarian, Arman and Zhou, Jefferson and Guidi, Giulia},
  booktitle = {SC26: International Conference for High Performance Computing, Networking, Storage and Analysis (Research Posters)},
  year      = {2026},
  url       = {https://sc26.conference-program.com/presentation/?id=rpost307&sess=sess313},
}

@misc{belli2026stencil,
  title         = {Stencil Computations on {Cerebras} Wafer-Scale Engine},
  author        = {Belli, Elia and De Sensi, Daniele},
  year          = {2026},
  howpublished  = {arXiv preprint arXiv:2605.07954},
  archivePrefix = {arXiv},
  eprint        = {2605.07954},
  primaryClass  = {cs.DC},
}

@misc{luczynski2026unstructured,
  title         = {Unstructured Hydrodynamics on Spatial Dataflow Architectures: A Joint Code and Data Decomposition Approach},
  author        = {Luczynski, Piotr and Ben-Nun, Tal and Wilson, Leighton and Van Essen, Brian},
  year          = {2026},
  howpublished  = {arXiv preprint arXiv:2607.18650},
  archivePrefix = {arXiv},
  eprint        = {2607.18650},
  primaryClass  = {cs.DC},
}

@inproceedings{song2025memory,
  title     = {A Memory-Efficient and Computation-Balanced Lossy Compressor on Wafer-Scale Engine},
  author    = {Song, Shihui and Underwood, Robert and Di, Sheng and Huang, Yafan and Jiang, Peng and Cappello, Franck},
  booktitle = {2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS)},
  pages     = {1--13},
  year      = {2025},
  publisher = {IEEE},
  doi       = {10.1109/IPDPS64566.2025.00084},
}

@inproceedings{singhvi2025scalable,
  title         = {A Scalable Trie Building Algorithm for High-Throughput Phyloanalysis of Wafer-Scale Digital Evolution Experiments},
  author        = {Singhvi, Vivaan and Wagner, Joey and Dolson, Emily and Zaman, Luis and Moreno, Matthew Andres},
  booktitle     = {ALIFE 2025: Ciphers of Life: Proceedings of the Artificial Life Conference 2025},
  volume        = {37},
  articleno     = {62},
  year          = {2025},
  publisher     = {MIT Press},
  doi           = {10.1162/isal.a.890},
  archivePrefix = {arXiv},
  eprint        = {2508.15074},
  primaryClass  = {cs.NE},
}

@inproceedings{he2025waferllm,
  title         = {{WaferLLM}: Large Language Model Inference at Wafer Scale},
  author        = {He, Congjie and Huang, Yeqi and Mu, Pei and Miao, Ziming and Xue, Jilong and Ma, Lingxiao and Yang, Fan and Mai, Luo},
  booktitle     = {19th USENIX Symposium on Operating Systems Design and Implementation (OSDI 25)},
  pages         = {257--273},
  year          = {2025},
  publisher     = {USENIX Association},
  isbn          = {978-1-939133-47-2},
  url           = {https://www.usenix.org/conference/osdi25/presentation/he},
  archivePrefix = {arXiv},
  eprint        = {2502.04563},
  primaryClass  = {cs.LG},
}

@article{vanputten2025slide,
  title         = {Slide {FFT} on a homogeneous mesh in wafer-scale computing},
  author        = {van Putten, Maurice H. P. M. and Wilson, Leighton and Lavely, Adam and Hair, Mark},
  journal       = {Discover Computing},
  volume        = {28},
  number        = {1},
  articleno     = {16},
  year          = {2025},
  publisher     = {Springer},
  doi           = {10.1007/s10791-025-09508-2},
  archivePrefix = {arXiv},
  eprint        = {2401.05427},
  primaryClass  = {eess.SP},
}

@inproceedings{miyajima2025benchmarking,
  title     = {Benchmarking the {Cerebras} Wafer Scale Engine-2 Architecture},
  author    = {Miyajima, Takaaki and Fukuoka, Leon},
  booktitle = {Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis},
  note      = {IA$^3$ 2025: 15th Workshop on Irregular Applications: Architectures and Algorithms},
  pages     = {818--822},
  year      = {2025},
  publisher = {ACM},
  doi       = {10.1145/3731599.3767438},
}

@inproceedings{nagashima2025csdf,
  title     = {{csDF}: A Double-Float Arithmetic Library for the {Cerebras} {CS-2}},
  author    = {Nagashima, Reo and Nakamura, Akeru and Murakami, Kai and Matsuzaki, Ryunosuke and Mukunoki, Daichi and Miyajima, Takaaki},
  booktitle = {SC25: International Conference for High Performance Computing, Networking, Storage and Analysis (Research and ACM SRC Posters)},
  year      = {2025},
  url       = {https://sc25.conference-program.com/presentation/?id=post112&sess=sess527},
}

@inproceedings{moreno2025wafer,
  title     = {Wafer-Scale Simulation of Mutator Allele Dynamics in Large Asexual Populations},
  author    = {Moreno, Matthew Andres and Dolson, Emily and Zaman, Luis},
  booktitle = {SC25: International Conference for High Performance Computing, Networking, Storage and Analysis (Research and ACM SRC Posters)},
  year      = {2025},
  url       = {https://sc25.conference-program.com/presentation/?id=post164&sess=sess527},
}

@misc{yang2025downstream,
  title         = {{Downstream}: efficient cross-platform algorithms for fixed-capacity stream downsampling},
  author        = {Yang, Connor and Wagner, Joey and Dolson, Emily and Zaman, Luis and Moreno, Matthew Andres},
  year          = {2025},
  howpublished  = {arXiv preprint arXiv:2506.12975},
  archivePrefix = {arXiv},
  eprint        = {2506.12975},
  primaryClass  = {cs.DS},
}

@inproceedings{sai2024automated,
  title     = {Automated Code Generation of High-Order Stencils for a Dataflow Architecture},
  author    = {Sai, Ryuichi and Mellor-Crummey, John and Xu, Jinfan and Araya-Polo, Mauricio},
  booktitle = {SC24: International Conference for High Performance Computing, Networking, Storage and Analysis},
  pages     = {1--13},
  year      = {2024},
  publisher = {IEEE},
  doi       = {10.1109/SC41406.2024.00025},
}

@inproceedings{song2024ceresz,
  title     = {{CereSZ}: Enabling and Scaling Error-bounded Lossy Compression on {Cerebras} {CS-2}},
  author    = {Song, Shihui and Huang, Yafan and Jiang, Peng and Yu, Xiaodong and Zheng, Weijian and Di, Sheng and Cao, Qinglei and Feng, Yunhe and Xie, Zhen and Cappello, Franck},
  booktitle = {Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing},
  series    = {HPDC '24},
  pages     = {309--321},
  year      = {2024},
  publisher = {ACM},
  doi       = {10.1145/3625549.3658691},
}

@inproceedings{sai2024matrix,
  title         = {Matrix-Free Finite Volume Kernels on a Dataflow Architecture},
  author        = {Sai, Ryuichi and Hamon, François P. and Mellor-Crummey, John and Araya-Polo, Mauricio},
  booktitle     = {SC24: International Conference for High Performance Computing, Networking, Storage and Analysis},
  pages         = {1--11},
  year          = {2024},
  publisher     = {IEEE},
  doi           = {10.1109/SC41406.2024.00034},
  archivePrefix = {arXiv},
  eprint        = {2408.03452},
  primaryClass  = {cs.MS},
}

@inproceedings{tramm2024monte,
  title     = {{Monte Carlo} with Single-Cycle Latency: Optimization of a Continuous Energy Cross Section Lookup Kernel for {AI} Accelerator Hardware},
  author    = {Tramm, John and Allen, Bryce and Yoshii, Kazutomo and Siegel, Andrew},
  booktitle = {International Conference on Physics of Reactors (PHYSOR 2024)},
  pages     = {1694--1702},
  year      = {2024},
  publisher = {American Nuclear Society},
  doi       = {10.13182/PHYSOR24-43696},
}

@inproceedings{luczynski2024near,
  title         = {Near-Optimal Wafer-Scale Reduce},
  author        = {Luczynski, Piotr and Gianinazzi, Lukas and Iff, Patrick and Wilson, Leighton and De Sensi, Daniele and Hoefler, Torsten},
  booktitle     = {Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing},
  series        = {HPDC '24},
  pages         = {334--347},
  year          = {2024},
  publisher     = {ACM},
  doi           = {10.1145/3625549.3658693},
  archivePrefix = {arXiv},
  eprint        = {2404.15888},
  primaryClass  = {cs.DC},
}

@inproceedings{moreno2024trackablea,
  title         = {Trackable Agent-based Evolution Models at Wafer Scale},
  author        = {Moreno, Matthew Andres and Yang, Connor and Dolson, Emily and Zaman, Luis},
  booktitle     = {The 2024 Conference on Artificial Life},
  series        = {ALIFE 2024},
  year          = {2024},
  publisher     = {MIT Press},
  doi           = {10.1162/isal_a_00830},
  archivePrefix = {arXiv},
  eprint        = {2404.10861},
  primaryClass  = {cs.NE},
}

@inproceedings{moreno2024trackableb,
  title         = {Trackable Island-model Genetic Algorithms at Wafer Scale},
  author        = {Moreno, Matthew Andres and Yang, Connor and Dolson, Emily and Zaman, Luis},
  booktitle     = {Proceedings of the Genetic and Evolutionary Computation Conference Companion},
  series        = {GECCO '24 Companion},
  pages         = {101--102},
  year          = {2024},
  publisher     = {ACM},
  doi           = {10.1145/3638530.3664090},
  archivePrefix = {arXiv},
  eprint        = {2405.03605},
  primaryClass  = {cs.NE},
}

@article{tramm2024efficient,
  title         = {Efficient algorithms for {Monte Carlo} particle transport on {AI} accelerator hardware},
  author        = {Tramm, John and Allen, Bryce and Yoshii, Kazutomo and Siegel, Andrew and Wilson, Leighton},
  journal       = {Computer Physics Communications},
  volume        = {298},
  pages         = {109072},
  year          = {2024},
  publisher     = {Elsevier},
  doi           = {10.1016/j.cpc.2023.109072},
  archivePrefix = {arXiv},
  eprint        = {2311.01739},
  primaryClass  = {cs.DC},
}

@inproceedings{matsuzaki2024performance,
  title     = {Performance evaluation and modelling of single-precision matrix multiplication on {Cerebras} {CS-2}},
  author    = {Matsuzaki, Ryunosuke and Mukunoki, Daichi and Miyajima, Takaaki},
  booktitle = {SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis},
  note      = {IA$^3$ 2024: 14th Workshop on Irregular Applications: Architectures \& Algorithms},
  pages     = {727--731},
  year      = {2024},
  publisher = {IEEE},
  doi       = {10.1109/SCW63240.2024.00101},
}

@inproceedings{ltaief2023scaling,
  title     = {Scaling the ``Memory Wall'' for Multi-Dimensional Seismic Processing with Algebraic Compression on {Cerebras} {CS-2} Systems},
  author    = {Ltaief, Hatem and Hong, Yuxi and Wilson, Leighton and Jacquelin, Mathias and Ravasi, Matteo and Keyes, David Elliot},
  booktitle = {Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis},
  series    = {SC '23},
  pages     = {1--12},
  year      = {2023},
  publisher = {ACM},
  doi       = {10.1145/3581784.3627042},
  note      = {ACM Gordon Bell Prize finalist},
}

@inproceedings{orenesvera2023wafer,
  title         = {Wafer-Scale Fast {Fourier} Transforms},
  author        = {Orenes-Vera, Marcelo and Sharapov, Ilya and Schreiber, Robert and Jacquelin, Mathias and Vandermersch, Philippe and Chetlur, Sharan},
  booktitle     = {Proceedings of the 37th International Conference on Supercomputing},
  series        = {ICS '23},
  pages         = {180--191},
  year          = {2023},
  publisher     = {ACM},
  doi           = {10.1145/3577193.3593708},
  archivePrefix = {arXiv},
  eprint        = {2209.15040},
  primaryClass  = {cs.DC},
}

@inproceedings{sai2023massively,
  title         = {Massively Distributed Finite-Volume Flux Computation},
  author        = {Sai, Ryuichi and Jacquelin, Mathias and Hamon, Francois and Araya-Polo, Mauricio and Settgast, Randolph R.},
  booktitle     = {Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis},
  note          = {ScalAH'23: 14th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Heterogeneous Systems},
  pages         = {1713--1720},
  year          = {2023},
  publisher     = {ACM},
  doi           = {10.1145/3624062.3624252},
  archivePrefix = {arXiv},
  eprint        = {2304.11274},
  primaryClass  = {cs.MS},
}

@misc{sai2023portable,
  title         = {A Portable Framework for Accelerating Stencil Computations on Modern Node Architectures},
  author        = {Sai, Ryuichi and Mellor-Crummey, John and Xu, Jinfan and Araya-Polo, Mauricio},
  year          = {2023},
  howpublished  = {arXiv preprint arXiv:2309.04671},
  archivePrefix = {arXiv},
  eprint        = {2309.04671},
  primaryClass  = {cs.DC},
}

@inproceedings{jacquelin2022scalable,
  title         = {Scalable Distributed High-Order Stencil Computations},
  author        = {Jacquelin, Mathias and Araya-Polo, Mauricio and Meng, Jie},
  booktitle     = {SC22: International Conference for High Performance Computing, Networking, Storage and Analysis},
  pages         = {1--13},
  year          = {2022},
  publisher     = {IEEE},
  doi           = {10.1109/SC41404.2022.00035},
  note          = {arXiv version titled "Massively scalable stencil algorithm"},
  archivePrefix = {arXiv},
  eprint        = {2204.03775},
  primaryClass  = {cs.MS},
}