Yanfei Guo

## Pull Request Description ## Author Checklist * [ ] **Provide Description** Particularly focus on _why_, not _what_. Reference background, issues, test failures, xfail entries, etc. * [ ] **Commits...

stubnm: add missing data structure

1

Fix building failure due to missing partitioned communication data structure. ## Pull Request Description ## Author Checklist * [ ] **Provide Description** Particularly focus on _why_, not _what_. Reference background,...

PMI: allow user to override PMI key value length

1

## Pull Request Description This PR fixes the #6924. The SDSC Expanse seems to have a long key value length that is not compatible with the MPICH default. This PR...

ch4/am: Caching buffer attribute in request and use typerep fast path for H2H

3

## Pull Request Description This PR add three things 1. A fast path in typerep copy/pack/unpack for H2H case. It bypasses pointer attribute query and related branches. This is enabled...

am-only build with UCX occasionally fails osu_bw benchmark in inter-NUMA setup

1

Just taking some notes. I run into this problem on skylake when testing. gcc 14.1.0 with UCX main branch. UCX v1.16.0 also have this problem UCX v1.15.0 (MPICH embedded) is...

ch4/shm: fix performance degradation on Sapphire Rapids with Intel Compiler

5

## Pull Request Description @zhenggb72 reported performance degradation in inter-NUMA SHM communication when compare to v4.2.2. The issue was introduced in #7046. MPICH v4.2.2 was getting ~14us latency for 64KB...

Adding NUMA control for memory location of MPICH

2

We need to provide a runtime option to control where MPICH allocates its memory (e.g. DDR or HBM).

mpichversion: Adding feature string for GPU support for easy detection

2

## Pull Request Description This PR add new feature strings to `mpichversion` for the GPU support. MPICH built with CUDA, HIP or ZE support will show cuda, hip or ze...

ch4/posix: using polling loop for recv and send queue

3

Trying do multiple polling for the recv and send queue to improve the message latency. This helps the for multiple incoming messages or deferred sends use cases. Two CVARs are...

## Pull Request Description Description WIP. PR need some clean up as well. But the functionality is ready and performance analysis is done. ## Author Checklist * [ ] **Provide...