{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:45:30Z","timestamp":1782999930153,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100019065","name":"Tianjin Science and Technology Program","doi-asserted-by":"publisher","award":["24HHXCSS00001"],"award-info":[{"award-number":["24HHXCSS00001"]}],"id":[{"id":"10.13039\/501100019065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800551","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"132-144","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CKTI: A Domain-Specific Compiler for Lowering CUDA Kernels to Triton-IR"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5732-2207","authenticated-orcid":false,"given":"Changqing","family":"Shi","sequence":"first","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1786-2519","authenticated-orcid":false,"given":"Rui","family":"Chen","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9778-9575","authenticated-orcid":false,"given":"Yufei","family":"Sun","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-7435","authenticated-orcid":false,"given":"Yicheng","family":"Sui","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9906-940X","authenticated-orcid":false,"given":"Junyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3451-0206","authenticated-orcid":false,"given":"Yudong","family":"Xie","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6650-8029","authenticated-orcid":false,"given":"Mingda","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0995-7039","authenticated-orcid":false,"given":"Shuangpeng","family":"Ming","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3454-1806","authenticated-orcid":false,"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6729-925X","authenticated-orcid":false,"given":"Yuzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nankai University, TianJin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"An open-source stack, composed primarily of open-source software, designed for graphics processing unit (GPU) computation","author":"Micro\u00a0Devices Inc. Advanced","year":"2015","unstructured":"Inc. Advanced Micro\u00a0Devices. 2015. An open-source stack, composed primarily of open-source software, designed for graphics processing unit (GPU) computation. Retrieved December 1, 2025 from https:\/\/github.com\/ROCm\/ROCm"},{"key":"e_1_3_3_1_3_2","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","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, et\u00a0al. 2018. { TVM} : An automated { End-to-End} optimizing compiler for deep learning. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). 578\u2013594."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Yunji Chen Tianshi Chen Zhiwei Xu Ninghui Sun and Olivier Temam. 2016. DianNao family: energy-efficient hardware accelerators for machine learning. Commun. ACM 59 11 (2016) 105\u2013112.","DOI":"10.1145\/2996864"},{"key":"e_1_3_3_1_5_2","volume-title":"Intel DPC++ Compatibility Tool","author":"Corporation Intel","year":"2021","unstructured":"Intel Corporation. 2021. Intel DPC++ Compatibility Tool. Retrieved December 1, 2025 from https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/dpc-compatibility-tool.html"},{"key":"e_1_3_3_1_6_2","unstructured":"Scott Cyphers Arjun\u00a0K Bansal Anahita Bhiwandiwalla Jayaram Bobba Matthew Brookhart Avijit Chakraborty Will Constable Christian Convey Leona Cook Omar Kanawi et\u00a0al. 2018. Intel ngraph: An intermediate representation compiler and executor for deep learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1801.08058 (2018)."},{"key":"e_1_3_3_1_7_2","volume-title":"IREE Compiler Homepage","author":"al. Ben\u00a0Vanik et","year":"2022","unstructured":"Ben\u00a0Vanik et al.2022. IREE Compiler Homepage. Retrieved December 1, 2025 from https:\/\/github.com\/iree-org\/iree"},{"key":"e_1_3_3_1_8_2","volume-title":"ONNX-MLIR Project Homepage","author":"al. Tung D.\u00a0Le et","year":"2017","unstructured":"Tung D.\u00a0Le et al.2017. ONNX-MLIR Project Homepage. Retrieved December 1, 2025 from https:\/\/github.com\/onnx\/onnx-mlir"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.45"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339595"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2909437.2909443"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Kai Han Yunhe Wang Hanting Chen Xinghao Chen Jianyuan Guo Zhenhua Liu Yehui Tang An Xiao Chunjing Xu Yixing Xu et\u00a0al. 2022. A survey on vision transformer. IEEE transactions on pattern analysis and machine intelligence 45 1 (2022) 87\u2013110.","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Matt\u00a0J Harvey and Gianni De\u00a0Fabritiis. 2011. Swan: A tool for porting CUDA programs to OpenCL. Computer Physics Communications 182 4 (2011) 1093\u20131099.","DOI":"10.1016\/j.cpc.2010.12.052"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1201\/9781003408291-8"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"John\u00a0L Hennessy and David\u00a0A Patterson. 2019. A new golden age for computer architecture. Commun. ACM 62 2 (2019) 48\u201360.","DOI":"10.1145\/3282307"},{"key":"e_1_3_3_1_17_2","volume-title":"Development Guide for the Ascend Platform","author":"Technologies\u00a0Co. Ltd Huawei","year":"2018","unstructured":"Ltd Huawei Technologies\u00a0Co.2018. Development Guide for the Ascend Platform. Retrieved December 1, 2025 from https:\/\/www.hiascend.com\/document\/detail\/zh\/CANNCommunityEdition\/80RC2alpha002\/devguide\/devguide\/devguide_0001.html"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO57630.2024.10444828"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807621"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661172"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Yongbon Koo Sunghoon Kim and Young-guk Ha. 2021. OpenCL-Darknet: implementation and optimization of OpenCL-based deep learning object detection framework. World Wide Web 24 (2021) 1299\u20131319.","DOI":"10.1007\/s11280-020-00778-y"},{"key":"e_1_3_3_1_22_2","first-page":"1","volume-title":"The BSD conference","author":"Lattner Chris","year":"2008","unstructured":"Chris Lattner. 2008. LLVM and Clang: Next generation compiler technology. In The BSD conference , Vol.\u00a05. 1\u201320."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"e_1_3_3_1_25_2","volume-title":"Graphcore Poplar SDK Overview","author":"Ltd Graphcore","year":"2016","unstructured":"Graphcore Ltd. 2016. Graphcore Poplar SDK Overview. Retrieved December 1, 2025 from https:\/\/docs.graphcore.ai\/projects\/sdk-overview\/en\/latest\/overview.html"},{"key":"e_1_3_3_1_26_2","unstructured":"Yanjun Ma Dianhai Yu Tian Wu and Haifeng Wang. 2019. PaddlePaddle: An open-source deep learning platform from industrial practice. Frontiers of Data and Domputing 1 1 (2019) 105\u2013115."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2011.48"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Marjan Mernik Jan Heering and Anthony\u00a0M Sloane. 2005. When and how to develop domain-specific languages. ACM computing surveys (CSUR) 37 4 (2005) 316\u2013344.","DOI":"10.1145\/1118890.1118892"},{"key":"e_1_3_3_1_29_2","series-title":"(PACT \u201921)","volume-title":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","author":"Moses William\u00a0S.","year":"2021","unstructured":"William\u00a0S. Moses, Lorenzo Chelini, Ruizhe Zhao, and Oleksandr Zinenko. 2021. Polygeist: Raising C to Polyhedral MLIR. In Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques (Virtual Event) (PACT \u201921). Association for Computing Machinery, New York, NY, USA, 12\u00a0pages."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577475"},{"key":"e_1_3_3_1_31_2","volume-title":"The Documentation for NVCC","year":"2009","unstructured":"NVIDIA. 2009. The Documentation for NVCC. Retrieved December 1, 2025 from https:\/\/docs.nvidia.com\/cuda\/cuda-compiler-driver-nvcc"},{"key":"e_1_3_3_1_32_2","unstructured":"Alex Osterneck UMGC Itec625 Gerard Steube and Bo Yang. 2024. Deep Learning Accelerators\u2026 The Future is Now (Accelerate the Accelerators). (2024)."},{"key":"e_1_3_3_1_33_2","unstructured":"Hugh Perkins. 2016. Cltorch: a hardware-agnostic backend for the torch deep neural network library based on opencl. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1606.04884 (2016)."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3078155.3078156"},{"key":"e_1_3_3_1_35_2","unstructured":"How Much Longer Can\u00a0Computing Power and Drive Artificial\u00a0Intelligence Progress. [n. d.]. AI and Compute. ([n. d.])."},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"Jonathan Ragan-Kelley Connelly Barnes Andrew Adams Sylvain Paris Fr\u00e9do Durand and Saman Amarasinghe. 2013. Halide: a language and compiler for optimizing parallelism locality and recomputation in image processing pipelines. Acm Sigplan Notices 48 6 (2013) 519\u2013530.","DOI":"10.1145\/2499370.2462176"},{"key":"e_1_3_3_1_37_2","unstructured":"Amit Sabne. 2020. Xla: Compiling machine learning for peak performance. Google Res (2020)."},{"key":"e_1_3_3_1_38_2","volume-title":"CUDA by example: an introduction to general-purpose GPU programming","author":"Sanders Jason","year":"2010","unstructured":"Jason Sanders and Edward Kandrot. 2010. CUDA by example: an introduction to general-purpose GPU programming. Addison-Wesley Professional."},{"key":"e_1_3_3_1_39_2","unstructured":"Changqing Shi Yufei Sun Rui Chen Jiahao Wang Qiang Guo Chunye Gong Yicheng Sui Yutong Jin and Yuzhi Zhang. 2025. TransCL: An Automatic CUDA-to-OpenCL Programs Transformation Framework. ACM Transactions on Architecture and Code Optimization (2025)."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"John\u00a0E Stone David Gohara and Guochun Shi. 2010. OpenCL: A parallel programming standard for heterogeneous computing systems. Computing in science & engineering 12 3 (2010) 66.","DOI":"10.1109\/MCSE.2010.69"},{"key":"e_1_3_3_1_41_2","volume-title":"A project dedicated to converting the Triton Dialect to the Linalg Dialect for the Triton compiler","author":"Team Cambricon","year":"2024","unstructured":"Cambricon Team. 2024. A project dedicated to converting the Triton Dialect to the Linalg Dialect for the Triton compiler. Retrieved December 1, 2025 from https:\/\/github.com\/Cambricon\/triton-linalg"},{"key":"e_1_3_3_1_42_2","volume-title":"Triton compiler framework targeting the Ascend platform","author":"Team HUAWEI\u00a0Ascend","year":"2024","unstructured":"HUAWEI\u00a0Ascend Team. 2024. Triton compiler framework targeting the Ascend platform. Retrieved December 1, 2025 from https:\/\/github.com\/Ascend\/triton-ascend"},{"key":"e_1_3_3_1_43_2","volume-title":"The Documentation for MetaX GPU and MXMACA","author":"Team MetaX","year":"2020","unstructured":"MetaX Team. 2020. The Documentation for MetaX GPU and MXMACA. Retrieved December 1, 2025 from https:\/\/developer.metax-tech.com\/doc\/index"},{"key":"e_1_3_3_1_44_2","volume-title":"CINN Compiler Homepage","author":"Team PaddlePaddle","year":"2022","unstructured":"PaddlePaddle Team. 2022. CINN Compiler Homepage. Retrieved December 1, 2025 from https:\/\/github.com\/PaddlePaddle\/CINN"},{"key":"e_1_3_3_1_45_2","volume-title":"Dynamo Overview","author":"Team PyTorch","year":"2022","unstructured":"PyTorch Team. 2022. Dynamo Overview. Retrieved December 1, 2025 from https:\/\/pytorch.org\/docs\/stable\/torch.compiler_dynamo_overview.html"},{"key":"e_1_3_3_1_46_2","unstructured":"R Tiernan. 2021. OpenAI proposes open-source Triton language as an alternative to NVIDIA\u2019s CUDA. ZDNET (July 28 2021) (2021)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_3_1_48_2","unstructured":"Kernel Tuner. 2024. Master Computer Science. (2024)."},{"key":"e_1_3_3_1_49_2","unstructured":"Lei Wang Yu Cheng Yining Shi Zhengju Tang Zhiwen Mo Wenhao Xie Lingxiao Ma Yuqing Xia Jilong Xue Fan Yang et\u00a0al. 2025. TileLang: A Composable Tiled Programming Model for AI Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.17577 (2025)."}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:08:37Z","timestamp":1782997717000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":48,"alternative-id":["10.1145\/3797905.3800551","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800551","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}