@inproceedings{heakl-etal-2026-cass,
    title = "{CASS}: Nvidia to {AMD} Transpilation with Data, Models, and Benchmark",
    author = "Heakl, Ahmed  and
      Stahl, Gustavo Bertolo  and
      Hashmi, Sarim  and
      Han, Seung Hun Eddie  and
      Ranjan, Mukul  and
      Kharlamova, Arina  and
      Khan, Salman  and
      Mahmoud, Abdulrahman",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1592/",
    pages = "34489--34508",
    ISBN = "979-8-89176-390-6",
    abstract = "Cross-architecture GPU code transpilation is essential for unlocking low-level hardware portability, yet no scalable solution exists. We introduce CASS, the first dataset and model suite for source- and assembly-level GPU translation (CUDA {\ensuremath{\leftrightarrow}} HIP, SASS {\ensuremath{\leftrightarrow}} RDNA3). CASS contains 60k verified host-device code pairs, enabling learning-based translation across both ISA and runtime boundaries. We generate each sample using our automated pipeline that scrapes, translates, compiles, and aligns GPU programs across vendor stacks. Leveraging CASS, we train a suite of domain-specific translation models that achieve 88.2{\%} accuracy on CUDA {\textrightarrow} HIP and 69.1{\%} on SASS {\textrightarrow} RDNA3, outperforming commercial baselines including GPT-5.1, Claude-4.5, and Hipify by wide margins. Generated code matches native performance in 85{\%} of cases, preserving both runtime and memory behavior. To support rigorous evaluation, we introduce CASS-Bench, a curated benchmark spanning 18 GPU domains with ground-truth execution. All data, models, and evaluation tools will be released as open source to support progress in GPU compiler tooling, binary compatibility, and LLM-guided code translation."
}