Sean Keely 35a270ef7e Do not initialize runtime internal queues based on mapping memory to a GPU.
Conserves VMIDs when multiple processes are in use and memory operations
are not GPU specific.  For instance HIP API hipHostMalloc does not accept
a target GPU so when used with one process per GPU (ie GPU == MPI rank) we can
quickly exceed the available VMID slots if every process consumes a VMID on
every GPU.

Change-Id: Ib6fa051290089f71581029c09f9a44b9992237d1
2018-07-13 19:58:45 -04:00
2017-08-28 12:57:11 -05:00
S
Açıklama
Hiçbir açıklama sağlanmadı
282 MiB
Dil
C++ 67.5%
C 20.6%
Python 6.6%
CMake 3.4%
Shell 0.6%
Diğer 1.1%