- Add option to skip stream allocation on access.
- Avoid null stream allocation in ihipFree, so an inactive device
won't be initialized
Change-Id: Id24426640df59a5e7a08b2dd9dcd4d67758b84bf
hipEventRecord is much slower in hipclang/vdi
- Make sure default streams don't sync each other.
- Add null stream into the list of default streams.
- Code clean-up to simplify queue look-up.
Change-Id: I36e1fc8d86a600e3dce806694d95d146ed8afd03
- HIPPerfDispatchSpeed disparity between HIP/HCC vs HIP/VDI
Insert a wait marker command in the default stream only when
HIP has pending operations on other async streams
Change-Id: I68660a54867fab7571ba57eb1df5feb1bca1c61a
Support hipLaunchCooperativeKernelMultiDevice()
- Add validation logic for MGPU launches to pass a cuda test
Change-Id: Iccca7fde43493fc3bc6685512d39202271ae3e92
German Andryeyev
Alex Xie
Vlad Sytchenko
Christophe Paquot
Laurent Morichetti