Tuan Truong Vu, Cheng Tan · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28429 · open-access PDF
Kernel GPU sangat penting untuk kinerja layanan AI saat ini, namun operator yang sama ditulis ulang berulang kali: untuk setiap generasi GPU, format numerik, rezim layanan, dan bahasa kernel. Setiap rewrite harus mempertahankan fungsi yang dihitung oleh implementasi yang diganti. Hari ini, kewajiban ini hampir sepenuhnya tergantung pada pengujian diferensial: menjalankan kernel baru dan referensi tepercaya pada tensor yang disesuaikan secara acak, kemudian membandingkan output mereka dalam toleransi. pendekatan ini memiliki titik buta yang kasus pengujian tambahan tidak dapat dihilangkan.
Machine translation (Meta M2M100); the English original follows.
GPU kernels are critical to the performance of today's AI services, yet the same operators are rewritten repeatedly: for each GPU generation, numeric format, serving regime, and kernel language. Every rewrite must preserve the function computed by the implementation it replaces. Today, this obligation depends almost entirely on differential testing: run the new kernel and a trusted reference on randomly sampled tensors, then compare their outputs within a tolerance. This approach has blind spots that additional test cases cannot eliminate. For example, a logical bug may produce an error smalle
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28429, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange