Sean Keely 5af558f739 Place GPU local resources in nearest NUMA node. ...

For minimal latency we should place command queues and blit code
in the nearest numa node to each GPU.  Add an allocator matching
the current runtime default allocator interface to each GpuAgent
that allocates on the closest numa node as represented by kfd
topology.  Use this allocator for queue ring buffers and blit
objects.

Change-Id: I181127f9c27bafe68976312963146616e3f58369

2021-09-14 17:49:24 -04:00

rocrtst

Add emulator build notification to rocrtst.

2021-08-13 16:46:26 -05:00

runtime

Place GPU local resources in nearest NUMA node.

2021-09-14 17:49:24 -04:00

samples

Add Iommu Perf Cntrs

2017-08-28 12:57:11 -05:00

S

Περιγραφή

No description provided

282 MiB

Languages

C++ 67.5%

C 20.6%

Python 6.6%

CMake 3.4%

Shell 0.6%

Άλλο 1.1%