Sean Keely 2328e07883 Handle high levels of concurrency in rocm_agent_enumerator. ...

rocm_agent_enumerator may invoke rocminfo.  Rocminfo opens the
GPU device which allocates limited resource.  Beyond 254
concurrent processes this resource will be exhausted and rocminfo
will return an error.

This patch loops rocm_agent_enumerator when recieving a failure
message from rocminfo indicating KFD is out of memory.

Change-Id: I8637e214f5fa012642975c28578ae6bf9200eda8


[ROCm/rocminfo commit: b57c02d131]

2021-10-29 20:22:19 -05:00

projects/rocminfo

Handle high levels of concurrency in rocm_agent_enumerator.

2021-10-29 20:22:19 -05:00

S

Opis

No description provided

282 MiB

Languages

C++ 67.5%

C 20.6%

Python 6.6%

CMake 3.4%

Shell 0.6%

Pozostałe 1.1%