{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:31:17Z","timestamp":1792787477303,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NSFC","award":["62293510\/62293513"],"award-info":[{"award-number":["62293510\/62293513"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"DOI":"10.1145\/3832810.3832867","type":"proceedings-article","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T00:19:06Z","timestamp":1789258746000},"page":"250-259","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PIM-Forge: Toward Autonomous PIM Kernel Synthesis through Constraint-Guided Hardware Exploration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1369-6633","authenticated-orcid":false,"given":"Yixing","family":"Du","sequence":"first","affiliation":[{"name":"Nankai University, Tianjin, China and School of Computer Science, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3100-0578","authenticated-orcid":false,"given":"Qingyun","family":"Tang","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China and School of Computer Science, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4017-0974","authenticated-orcid":false,"given":"Lixiao","family":"Cui","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China and School of Computer Science, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6623-350X","authenticated-orcid":false,"given":"Yusen","family":"Li","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China and School of Computer Science, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0387-2501","authenticated-orcid":false,"given":"Gang","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China and School of Computer Science, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9010-3278","authenticated-orcid":false,"given":"Xiaoguang","family":"Liu","sequence":"additional","affiliation":[{"name":"Nankai University, Tianjin, China and School of Computer Science, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,9,27]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_3_1_3_2","unstructured":"Anthropic. 2026. System Card: Claude Sonnet 4.6. Accessed: 2026-04-16. https:\/\/www.anthropic.com\/claude-sonnet-4-6-system-card"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Kazi Asifuzzaman Narasinga\u00a0Rao Miniskar Aaron\u00a0R. Young Frank Liu and Jeffrey\u00a0S. Vetter. 2023. A Survey on Processing-in-Memory Techniques: Advances and Challenges. Memories \u2013 Materials Devices Circuits and Systems 4 (2023) 100022. Available online December 2022. 10.1016\/j.memori.2022.100022","DOI":"10.1016\/j.memori.2022.100022"},{"key":"e_1_3_3_1_5_2","unstructured":"Carlo Baronio Pietro Marsella Ben Pan Simon Guo and Silas Alberti. 2025. Kevin: Multi-Turn RL for Generating CUDA Kernels. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.11948 (2025). https:\/\/arxiv.org\/abs\/2507.11948"},{"key":"e_1_3_3_1_6_2","unstructured":"Xinzi Cao et\u00a0al. 2026. AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.07160 (2026). https:\/\/arxiv.org\/abs\/2601.07160"},{"key":"e_1_3_3_1_7_2","first-page":"578","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI). USENIX Association, 578\u2013594. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_3_1_8_2","unstructured":"DeepSeek-AI. 2025. DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2512.02556\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2512.02556"},{"key":"e_1_3_3_1_9_2","unstructured":"Jinye Du et\u00a0al. 2025. AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.23424 (2025). https:\/\/arxiv.org\/abs\/2512.23424"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Christina Giannoula Ivan Fernandez Juan G\u00f3mez-Luna Nectarios Koziris Georgios Goumas and Onur Mutlu. 2022. SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Architectures. Proc. ACM Meas. Anal. Comput. Syst. 6 1 Article 21 (2022) 21:1\u201321:49\u00a0pages. 10.1145\/3508041","DOI":"10.1145\/3508041"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Christina Giannoula Peiming Yang Ivan Fernandez Jiacheng Yang Sankeerth Durvasula Yu\u00a0Xin Li Mohammad Sadrosadati Juan Gomez Luna Onur Mutlu and Gennady Pekhimenko. 2024. PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architectures. Proceedings of the ACM on Measurement and Analysis of Computing Systems 8 3 Article 43 (2024) 36\u00a0pages. 10.1145\/3700434","DOI":"10.1145\/3700434"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Juan G\u00f3mez-Luna Izzat El Hajj Ivan Fernandez Christina Giannoula Geraldo\u00a0F. Oliveira and Onur Mutlu. 2022. Benchmarking a New Paradigm: Experimental Analysis and Characterization of a Real Processing-in-Memory System. IEEE Access 10 (2022) 52565\u201352608. 10.1109\/ACCESS.2022.3174101","DOI":"10.1109\/ACCESS.2022.3174101"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS57527.2023.00013"},{"key":"e_1_3_3_1_14_2","volume-title":"Gemini 3.1 Pro Model Card","author":"DeepMind Google","year":"2026","unstructured":"Google DeepMind. 2026. Gemini 3.1 Pro Model Card. Technical Report. Google DeepMind. https:\/\/storage.googleapis.com\/deepmind-media\/Model-Cards\/Gemini-3-1-Pro-Model-Card.pdf"},{"key":"e_1_3_3_1_15_2","volume-title":"MindSpore: An All-Scenario Deep Learning Computing Framework","author":"Ltd. Huawei Technologies Co.,","year":"2021","unstructured":"Huawei Technologies Co., Ltd.2021. MindSpore: An All-Scenario Deep Learning Computing Framework. White Paper. Huawei Technologies Co., Ltd."},{"key":"e_1_3_3_1_16_2","unstructured":"Kimi Team. 2026. Kimi K2.5: Visual Agentic Intelligence. arxiv:https:\/\/arXiv.org\/abs\/2602.02276https:\/\/arxiv.org\/abs\/2602.02276"},{"key":"e_1_3_3_1_17_2","unstructured":"Lingcheng Kong Jiateng Wei Hanzhang Shen and Huan Wang. 2025. ConCuR: Conciseness Makes State-of-the-Art Kernel Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.07356 (2025). https:\/\/arxiv.org\/abs\/2510.07356"},{"key":"e_1_3_3_1_18_2","unstructured":"Robert\u00a0Tjarko Lange Qi Sun Aaditya Prasad Maxence Faldor Yujin Tang and David Ha. 2025. Towards Robust Agentic CUDA Kernel Benchmarking Verification and Optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.14279 (2025). https:\/\/arxiv.org\/abs\/2509.14279"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640376"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1183"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-7487-7_7"},{"key":"e_1_3_3_1_23_2","unstructured":"OpenAI. 2026. GPT-5.4 Thinking System Card. Accessed: 2026-04-16. https:\/\/deploymentsafety.openai.com\/gpt-5-4-thinking\/gpt-5-4-thinking.pdf"},{"key":"e_1_3_3_1_24_2","series-title":"Proceedings of Machine Learning Research","first-page":"47356","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","volume":"267","author":"Ouyang Anne","year":"2025","unstructured":"Anne Ouyang, Simon Guo, Simran Arora, Alex\u00a0L. Zhang, William Hu, Christopher R\u00e9, and Azalia Mirhoseini. 2025. KernelBench: Can LLMs Write Efficient GPU Kernels?. In Proceedings of the 42nd International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0267). PMLR, 47356\u201347415. https:\/\/proceedings.mlr.press\/v267\/ouyang25a.html"},{"key":"e_1_3_3_1_25_2","unstructured":"Songqiao Su Xiaofei Sun Xiaoya Li Albert Wang Jiwei Li and Chris Shum. 2025. CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.02551 (2025). https:\/\/arxiv.org\/abs\/2512.02551"},{"key":"e_1_3_3_1_26_2","volume-title":"NeurIPS 2025 Fourth Workshop on Deep Learning for Code","author":"Wei Anjiang","year":"2025","unstructured":"Anjiang Wei, Tianran Sun, Yogesh Seenichamy, Hang Song, Anne Ouyang, Azalia Mirhoseini, Ke Wang, and Alex Aiken. 2025. Astra: A Multi-Agent System for GPU Kernel Performance Optimization. In NeurIPS 2025 Fourth Workshop on Deep Learning for Code. arxiv:https:\/\/arXiv.org\/abs\/2509.07506https:\/\/arxiv.org\/abs\/2509.07506"},{"key":"e_1_3_3_1_27_2","unstructured":"Shanli Xing Yiyan Zhai Alexander Jiang Yixin Dong Yong Wu Zihao Ye Charlie Ruan Yingyi Huang Yineng Zhang Liangsheng Yin Aksara Bayyapu Luis Ceze and Tianqi Chen. 2026. FlashInfer-Bench: Building the Virtuous Cycle for AI-driven LLM Systems. arxiv:https:\/\/arXiv.org\/abs\/2601.00227\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2601.00227"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i34.40155"}],"event":{"name":"ICPP '26: Proceedings of the 55th International Conference on Parallel Processing","location":"Singapore , Singapore","acronym":"ICPP '26"},"container-title":["Proceedings of the 55th International Conference on Parallel Processing"],"original-title":[],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T18:06:42Z","timestamp":1789582002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3832810.3832867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,27]]},"references-count":27,"alternative-id":["10.1145\/3832810.3832867","10.1145\/3832810"],"URL":"https:\/\/doi.org\/10.1145\/3832810.3832867","relation":{},"subject":[],"published":{"date-parts":[[2026,9,27]]},"assertion":[{"value":"2026-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}