Hacktoberfest 2026：维护者为十月标记出来的 issue，仍然开放、适合新手。 浏览 Hacktoberfest issue

[FEA]: NVSHMEM Support

未关闭
#10 1 条评论 1 个 reaction 已指派 1 人 在 GitHub 查看

@aterrel 已经在做这个了。

开始于 2025年12月10日。

评估

这个 Issue 还没有评估数据。

描述

dep: cuda-tileir feature request status: triaged
Is this a new feature, an improvement, or a change to existing functionality?

New Feature

How would you describe the priority of this feature request?

Critical (currently preventing usage)

Please provide a clear description of problem this feature solves

Is NVSHMEM integration planned for cuTile? Lack of NVSHMEM support prevents kernels from performing fine-grained, in-kernel communication, limiting compute–communication overlap.

Feature Description

Support to NVSHMEM device APIs (e.g. nvshmemx_putmem_block)

Describe your ideal solution

@ct.kernel
def vector_add(a, b, remote_c, tile_size: ct.Constant[int], pe: ct.Constant[int]):
# Get the 1D pid
pid = ct.bid(0)

# Load input tiles
a_tile = ct.load(a, index=(pid,), shape=(tile_size,))
b_tile = ct.load(b, index=(pid,), shape=(tile_size,))

# Perform elementwise addition
result = a_tile + b_tile

# Store result using NVSHMEM
ct. nvshmemx_putmem_block(remote_c, result, index=(pid,), pe=pe)
Describe any alternatives you have considered

No response

Additional context

No response

Contributing Guidelines
  • I agree to follow cuTile Python's contributing guidelines
  • I have searched the open feature requests and have found no duplicates for this feature request
主要语言
Python
星标
2.2k
派生
155
30 天内没有已合并 PR

贡献指南

打开贡献指南

从这里开始

  1. 先读完整个 Issue，再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库，在一个分支上完成修改。
  4. 提交 Pull Request，并在描述里引用这个 Issue 编号。

NVIDIA/cutile-python 的其他 Issue

查看 NVIDIA/cutile-python 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。