viable/strict/1791693334: Let fastAtomicAdd derive its bound from a packed accessor (#196155)
- PyTorch 近 90 天出现 2165 次
- PyTorch 近 90 天第 2136 次发版
- 上一次:同一天稍早 · ciflow/trunk/200538: [UPDATE] Update
发生了什么
fastAtomicAdd needs a bound on how far it may look for a pairing partner when packing a 16-bit atomic. Callers holding a raw pointer supply that themselves, and getting it wrong is silent (too large lets the pairing write past the allocation) -- which is why ~20 scatter sites that subscript a packed accessor still use the plain atomic rather than hand-deriving a bound. Adds an accessor overload that derives offset a…
摘要按规则整理自下方来源原文