d6d5fac1521d58149badd40169959fbaedf8233c
* update AG direct and single node LL threshold
* update thresholds based on MI350 expeirmental results
* disable using LL for direct AG
* enable direct AG for lower GPU counts
* direct AG single node tuning
* fix in-place buffer allocation for AG unit test
* whitespace fix
* gate direct AG for gfx950 and gfx942
---------
Co-authored-by: Nusrat Islam <nusislam@nova-login-gtu2.prov.gtu.zts.cpe.ice.amd.com>
[ROCm/rccl commit: d22a39e954]
Popis
Nebyl uveden žádný popis
Jazyky
C++
67.5%
C
20.6%
Python
6.6%
CMake
3.4%
Shell
0.6%
Jiný
1.1%