avinashkethineedi 5869709dac Update all_reduce algorithm to use internal put/get functions for updating pWrk and pSync arrays ...

* Change log_stride calcualtions to stride calculations
* Update all_reduce example code to use team based interface


[ROCm/rocshmem commit: abec29bd6a]

2024-10-28 22:10:18 +00:00

..

backend_ipc.cpp

Add fine grained memory buffers for work/sync arrays

2024-10-21 15:28:39 +00:00

backend_ipc.hpp

Add fine grained memory buffers for work/sync arrays

2024-10-21 15:28:39 +00:00

CMakeLists.txt

first cut on collectives and sync

2024-08-27 15:03:38 -07:00

context_ipc_device_coll.cpp

fix barrier synchronization on gfx90a

2024-10-24 15:08:28 +00:00

context_ipc_device.cpp

fix barrier synchronization on gfx90a

2024-10-24 15:08:28 +00:00

context_ipc_device.hpp

Update all_reduce algorithm to use internal put/get functions for updating pWrk and pSync arrays

2024-10-28 22:10:18 +00:00

context_ipc_host.cpp

Add IPC backend

2024-08-14 22:59:02 -07:00

context_ipc_host.hpp

updated *_wait* APIs to use int rather than roc_shmem_cmps

2024-10-11 13:34:28 -07:00

context_ipc_tmpl_device.hpp

Update all_reduce algorithm to use internal put/get functions for updating pWrk and pSync arrays

2024-10-28 22:10:18 +00:00

context_ipc_tmpl_host.hpp

updated *_wait* APIs to use int rather than roc_shmem_cmps

2024-10-11 13:34:28 -07:00

ipc_backend_proxy.hpp

Add IPC backend

2024-08-14 22:59:02 -07:00

ipc_context_proxy.hpp

Fix quiet and fence of default context

2024-10-22 16:18:05 +00:00

ipc_team.cpp

Add IPC teams

2024-08-22 09:15:44 -07:00

ipc_team.hpp

Add IPC teams

2024-08-22 09:15:44 -07:00