Metraipolis › archive › dc_18170006cfba

AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization — arXiv:2609.12471

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12471
License (as archived)
CC0-1.0
Archived
2026-10-16T03:08:21.817Z
SHA-256 of the archived text
ad76e9963d1198d36bc6469b21ca10bb9b84d6fe08fb9a0515f999d315761c8e
Stable URL of this page
https://metraipolis.com/documento/dc_18170006cfba

How to cite

AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization — arXiv:2609.12471 — arXiv (en), https://arxiv.org/abs/2609.12471 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_18170006cfba (Metraipolis archive dc_18170006cfba, sha256 ad76e9963d1198d36bc6469b21ca10bb9b84d6fe08fb9a0515f999d315761c8e)
BibTeX
@misc{dc18170006cfba,
  title = {AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization — arXiv:2609.12471},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12471},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_18170006cfba; sha256 ad76e9963d1198d36bc6469b21ca10bb9b84d6fe08fb9a0515f999d315761c8e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12471. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce AMDKernelVault, an open HIP and Triton kernel corpus and training framework for recent AMD CDNA GPUs. Existing LLM-based kernel agents are largely CUDA/NVIDIA-centric and often depend on repeated frontier-LLM calls for generation, reflection, and optimization. To address this gap, we develop HIPKernelGen and TritonKernelGen, agent-driven pipelines that transform PyTorch references into HIP or Triton kernels, compile and validate candidates under ROCm, and latency-profile them on AMD hardware. The corpus contains 62,153 execution-verified HIP kernel samples, 2,377 production-grounded ROCm Libraries QA entries, and 39,893 Triton kernels. We further train Qwen3-8B with supervised fine-tuning and execution-aware reinforcement learning as a demonstration of the corpus's utility. Under fixed evaluation budgets, it achieves the highest correctness among the compared models on PyTorch-to-HIP (34.0% Pass@1), TritonBench-G (33.2% Corr@3), and ROCmBench (41.94% Corr@3), but does not uniformly lead compilation or speed metrics. The corpus and documentation are available at this https URL , and the associated training and kernel-generation code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.12471 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T03:02:47.541Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).