变更摘要

本次变更修复了 ForeachAddList 算子在 tiling 阶段的一个 bug：在 perCoreElements 按 ALIGN_SIZE 向上对齐后，原先的 needCoreNum 不再与对齐后的每核元素数匹配，导致可能出现多余的核参与计算。修复方式是在 perCoreElements 对齐后重新计算 needCoreNum，使核数与对齐后的分块大小保持一致。

主要改动

• ForeachAddListTilingFunc 中重新计算 needCoreNum：在对 perCoreElements 进行 ALIGN_SIZE 对齐后，新增一行 needCoreNum = Ops::Base::CeilDiv(totalElements, perCoreElements)，确保所需的核数基于对齐后的每核元素数重新计算，避免因对齐放大导致核数冗余。

代码审查

✅ 未发现问题

Thanks for your pull-request.
The full list of commands accepted by me can be found at here。
You can get sig-info at here

PR Approval Progress

✅ Congratulations! All modules have met the lgtm and approve requirements.

Module Approval Details

💡 Tip:

• Committer can comment /approve or /lgtm
• Commenting /approve implies both code review (lgtm) and intent to merge (approve)

CLA Signature Pass

zhaozhongyao, thanks for your pull request. All authors of the commits have signed the CLA. 👍

/lgtm