{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:54:20Z","timestamp":1776930860478,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"The US Department of Energy, Office of Science�s Advanced Scientific Computing Research program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3731599.3767398","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T16:18:44Z","timestamp":1762532324000},"page":"524-533","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing ChatPORT with CUDA-to-SYCL Kernel Translation Capability"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7197-780X","authenticated-orcid":false,"given":"Zheming","family":"Jin","sequence":"first","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8544-6367","authenticated-orcid":false,"given":"Swaroop","family":"Pophale","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6647-2690","authenticated-orcid":false,"given":"Keita","family":"Teranishi","sequence":"additional","affiliation":[{"name":"Oak Ridge National Laboratory (ORNL), Oak Ridge, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_1_1_2","unstructured":"Roziere B. Lachaux M.A. Chanussot L. and Lample G. 2020. Unsupervised translation of programming languages. Advances in neural information processing systems 33 pp.20601-20611."},{"key":"e_1_3_3_1_2_2","volume-title":"Proceedings of the 52nd International Conference on Parallel Processing Workshops (pp. 136-144)","author":"Godoy W.","unstructured":"Godoy, W., Valero-Lara, P., Teranishi, K., Balaprakash, P. and Vetter, J., 2023, August. Evaluation of OpenAI Codex for HPC parallel programming models kernel generation. In Proceedings of the 52nd International Conference on Parallel Processing Workshops (pp. 136-144)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2008.57"},{"key":"e_1_3_3_1_4_2","volume-title":"SYCL: Single-source C++ accelerator programming. In Parallel Computing: On the Road to Exascale (pp. 673-682)","author":"Reyes R.","year":"2016","unstructured":"Reyes, R. and Lom\u00fcller, V., 2016. SYCL: Single-source C++ accelerator programming. In Parallel Computing: On the Road to Exascale (pp. 673-682). IOS Press."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3585341.3585349"},{"key":"e_1_3_3_1_6_2","unstructured":"Intel DPC++ Compatibility Tool Developer Guide and Reference 2025."},{"key":"e_1_3_3_1_7_2","unstructured":"Clang: A C language family frontend for LLVM https:\/\/clang.llvm.org\/index.html"},{"key":"e_1_3_3_1_8_2","unstructured":"Valero P. Young A. Vetter J. Jin Z. Pophale S. Monil M. Teranishi K. Godoy W. ChatHPC: Building the Foundations for a Productive and Trustworthy AI-Assisted HPC Ecosystem. To appear in SC25: International Conference for High Performance Computing Networking Storage and Analysis."},{"key":"e_1_3_3_1_9_2","volume-title":"Oct, 2025.","author":"Pophale S","unstructured":"Pophale, S, Jin, Z., and Teranishi, K. ChatPORT: Fine-tuned LLM for Easy Code {PORT}ing. To appear at International Workshop on OpenMP 2025. Oct, 2025."},{"key":"e_1_3_3_1_10_2","volume-title":"2023 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) (pp. 325-327)","author":"Jin Z.","unstructured":"Jin, Z. and Vetter, J.S., 2023, April. A benchmark suite for improving performance portability of the SYCL programming model. In 2023 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) (pp. 325-327). IEEE."},{"key":"e_1_3_3_1_11_2","unstructured":"CUDA C++ Programming Guide https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide"},{"key":"e_1_3_3_1_12_2","unstructured":"SYCL 2020 Specification (Revision 10) https:\/\/registry.khronos.org\/SYCL\/specs\/sycl-2020\/html\/sycl-2020.html"},{"key":"e_1_3_3_1_13_2","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin J.","unstructured":"Devlin, J., Chang, M.W., Lee, K. and Toutanova, K., 2019, June. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (pp. 4171-4186)."},{"key":"e_1_3_3_1_14_2","unstructured":"Bao H. Dong L. Piao S. and Wei F. 2021. BEiT: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254."},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Feng Z. Guo D. Tang D. Duan N. Feng X. Gong M. Shou L. Qin B. Liu T. Jiang D. and Zhou M. 2020. CodeBERT: A pre-trained model for programming and natural languages. arXiv preprint arXiv:2002.08155.","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_1_16_2","volume-title":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (pp. 39-51)","author":"Shi E.","unstructured":"Shi, E., Wang, Y., Zhang, H., Du, L., Han, S., Zhang, D. and Sun, H., 2023, July. Towards efficient fine-tuning of pre-trained code models: An experimental study and beyond. In Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (pp. 39-51)."},{"key":"e_1_3_3_1_17_2","unstructured":"Chu T. Zhai Y. Yang J. Tong S. Xie S. Schuurmans D. Le Q.V. Levine S. and Ma Y. 2025. SFT memorizes RL generalizes: A comparative study of foundation model post-training. arXiv preprint arXiv:2501.17161."},{"key":"e_1_3_3_1_18_2","first-page":"100965","article-title":". CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming","volume":"37","author":"Tehrani A.","year":"2024","unstructured":"Tehrani, A., Bhattacharjee, A., Chen, L., Ahmed, N.K., Yazdanbakhsh, A. and Jannesari, A., 2024. CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming. Advances in Neural Information Processing Systems, 37, pp.100965-100999.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_1_19_2","volume-title":"LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes. In 2024 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops) (pp. 136-143)","author":"Dearing M.T.","year":"2024","unstructured":"Dearing, M.T., Tao, Y., Wu, X., Lan, Z. and Taylor, V., 2024, September. LASSI: An LLM-based Automated Self-Correcting Pipeline for Translating Parallel Scientific Codes. In 2024 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops) (pp. 136-143). IEEE."},{"key":"e_1_3_3_1_20_2","volume-title":"Code Llama: Open foundation models for code. arXiv preprint arXiv:2308.12950.","author":"Roziere B.","year":"2023","unstructured":"Roziere, B., Gehring, J., Gloeckle, F., Sootla, S., Gat, I., Tan, X.E., Adi, Y., Liu, J., Sauvestre, R., Remez, T. and Rapin, J., 2023. Code Llama: Open foundation models for code. arXiv preprint arXiv:2308.12950."},{"key":"e_1_3_3_1_21_2","unstructured":"Li R. Allal L.B. Zi Y. Muennighoff N. Kocetkov D. Mou C. Marone M. Akiki C. Li J. Chim J. and Liu Q. 2023. StarCoder: may the source be with you!. arXiv preprint arXiv:2305.06161."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Chaturvedi A. Nichols D. Singh S. and Bhatele A. 2024. HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages. arXiv preprint arXiv:2412.15178.","DOI":"10.23919\/ISC.2025.11017585"},{"key":"e_1_3_3_1_23_2","unstructured":"Hui B. Yang J. Cui Z. Yang J. Liu D. Zhang L. Liu T. Zhang J. Yu B. Lu K. and Dang K. 2024. Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186."},{"key":"e_1_3_3_1_24_2","unstructured":"Mishra M. Stallone M. Zhang G. Shen Y. Prasad A. Soria A.M. Merler M. Selvam P. Surendran S. Singh S. and Sethi M. 2024. Granite code models: A family of open foundation models for code intelligence. arXiv preprint arXiv:2405.04324."},{"key":"e_1_3_3_1_25_2","unstructured":"Team C. Zhao H. Hui J. Howland J. Nguyen N. Zuo S. Hu A. Choquette-Choo C.A. Shen J. Kelley J. and Bansal K. 2024. CodeGemma: Open code models based on gemma. arXiv preprint arXiv:2406.11409."},{"key":"e_1_3_3_1_26_2","unstructured":"Paszke A. Gross S. Massa F. Lerer A. Bradbury J. Chanan G. Killeen T. Lin Z. Gimelshein N. Antiga L. and Desmaison A. 2019. PyTorch: An imperative style high-performance deep learning library. Advances in Neural Information Processing Systems 32."},{"key":"e_1_3_3_1_27_2","unstructured":"State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods https:\/\/github.com\/huggingface\/peft"},{"key":"e_1_3_3_1_28_2","unstructured":"Transformer Reinforcement Learning (TRL) https:\/\/huggingface.co\/docs\/trl\/index"},{"issue":"2","key":"e_1_3_3_1_29_2","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1","author":"Hu E.J.","year":"2022","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L. and Chen, W., 2022. LoRA: Low-rank adaptation of large language models. ICLR, 1(2), p.3.","journal-title":"ICLR"},{"key":"e_1_3_3_1_30_2","unstructured":"Dettmers T. Pagnoni A. Holtzman A. and Zettlemoyer L. 2023. QLoRA: Efficient finetuning of quantized LLMs. Advances in neural information processing systems 36 pp.10088-10115."},{"key":"e_1_3_3_1_31_2","unstructured":"Dettmers T. Lewis M. Shleifer S. and Zettlemoyer L. 2021. 8-bit optimizers via block-wise quantization. arXiv preprint arXiv:2110.02861."},{"key":"e_1_3_3_1_32_2","unstructured":"Loshchilov I. and Hutter F. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101."},{"key":"e_1_3_3_1_33_2","volume-title":"Codet: Code generation with generated tests. arXiv preprint arXiv:2207.10397.","author":"Chen B.","year":"2022","unstructured":"Chen, B., Zhang, F., Nguyen, A., Zan, D., Lin, Z., Lou, J.G. and Chen, W., 2022. Codet: Code generation with generated tests. arXiv preprint arXiv:2207.10397."},{"key":"e_1_3_3_1_34_2","first-page":"21558","article-title":"Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation","volume":"36","author":"Liu J.","year":"2023","unstructured":"Liu, J., Xia, C.S., Wang, Y. and Zhang, L., 2023. Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation. Advances in Neural Information Processing Systems, 36, pp.21558-21572.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_1_35_2","volume-title":"Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing (pp. 281-294)","author":"Nichols D.","unstructured":"Nichols, D., Davis, J.H., Xie, Z., Rajaram, A. and Bhatele, A., 2024, June. Can large language models write parallel code?. In Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing (pp. 281-294)."},{"key":"e_1_3_3_1_36_2","unstructured":"Holtzman A. Buys J. Du L. Forbes M. and Choi Y. 2019. The curious case of neural text degeneration. arXiv preprint arXiv:1904.09751."},{"key":"e_1_3_3_1_37_2","volume-title":"Proceedings of the International Workshop on OpenCL (pp. 1-5).","author":"Brown G.","unstructured":"Brown, G., Reyes, R. and Wong, M., 2019, May. Towards heterogeneous and distributed computing in C++. In Proceedings of the International Workshop on OpenCL (pp. 1-5)."}],"event":{"name":"SC Workshops '25: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St Louis MO USA","acronym":"SC Workshops '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731599.3767398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:34:44Z","timestamp":1767987284000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731599.3767398"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":37,"alternative-id":["10.1145\/3731599.3767398","10.1145\/3731599"],"URL":"https:\/\/doi.org\/10.1145\/3731599.3767398","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}