deepseek-ai / deepseek-ai/DeepEP
Questions About AR Support for Low-latency
Open
- Dominant language
- Cuda
- Stars
- 10.1k
- Forks
- 1.4k
- Avg merge
- 4d 1h
- Merged PRs (30d)
- 2
Description
Commit: [2d0cf41dd1900b105d74cb071f4cac35e3fb6f47](https://github.com/nvshmem/nvshmem/commit/2d0cf41dd1900b105d74cb071f4cac35e3fb6f47)
Low latency kernels use rdma atomic to support AR.
This commit replaces two functions:
- `nvshmemi_ibgda_rma_p`
- `nvshmemi_ibgda_poll_recv`
with a new function: `nvshmemi_ibgda_amo_nonfetch_add`
From code inspection, `nvshmemi_ibgda_rma_p` appears to use **RDMA Write with Immediate Data**.
Does RDMA Write with IMM not support AR? Why we have to use `nvshmemi_ibgda_amo_nonfetch_add` to add AR support for low-latency ?
Thank you!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.