Besar Wicaksono (xN/A) TX [TEXT] ea67bb8374 Sdma wraparound optimization. ...

Remove mutex and just make the thread spin again if the queue is wrapping.
Remove the wait for the queue to finish wrapping, and just check if there is enough space to recycle when reserving queue space.

[git-p4: depot-paths = "//depot/stg/hsa/drivers/hsa/runtime/": change = 1256713]

2016-04-11 18:31:45 -05:00

runtime/hsa-runtime

Sdma wraparound optimization.

2016-04-11 18:31:45 -05:00

samples

Update Private Segment Size parameter of the dispatch packet

2016-04-05 14:03:33 -05:00

S

描述

无详细信息

282 MiB

语言

C++ 67.5%

C 20.6%

Python 6.6%

CMake 3.4%

Shell 0.6%

其它 1.1%